[TCWG CI] Regression caused by llvm:2eb554a9feafff5188d8b924908205c87d7f2fee
by ci_notify＠linaro.org
Identified regression caused by *llvm:2eb554a9feafff5188d8b924908205c87d7f2fee*:
commit 2eb554a9feafff5188d8b924908205c87d7f2fee
Author: Roman Lebedev <lebedev.ri(a)gmail.com>
Revert "Reland [SimplifyCFG] performBranchToCommonDestFolding(): form block-closed SSA form before cloning instructions (PR51125)"
Results regressed to (for first_bad == 2eb554a9feafff5188d8b924908205c87d7f2fee)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-2eb554a9feafff5188d8b924908205c87d7f2fee/results_id:
1
# 483.xalancbmk,libc.so.6 regressed by 81400
from (for last_good == 7142eb17fb3419a76c9ac4afce0df986ff08d61c)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-7142eb17fb3419a76c9ac4afce0df986ff08d61c/results_id:
1
This commit has regressed these CI configurations:
- tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-O3
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Even more details: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Reproduce builds:
<cut>
mkdir investigate-llvm-2eb554a9feafff5188d8b924908205c87d7f2fee
cd investigate-llvm-2eb554a9feafff5188d8b924908205c87d7f2fee
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 2eb554a9feafff5188d8b924908205c87d7f2fee
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 7142eb17fb3419a76c9ac4afce0df986ff08d61c
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 2eb554a9feafff5188d8b924908205c87d7f2fee
Author: Roman Lebedev <lebedev.ri(a)gmail.com>
Date: Mon Aug 16 10:53:15 2021 +0300
Revert "Reland [SimplifyCFG] performBranchToCommonDestFolding(): form block-closed SSA form before cloning instructions (PR51125)"
This is still wrong, as failing bots suggest.
This reverts commit 3d9beefc7d713ad8462d92427ccd17b9532ce904.
---
llvm/lib/Transforms/Utils/SimplifyCFG.cpp | 75 +++-------------------
.../SimplifyCFG/fold-branch-to-common-dest.ll | 18 +++---
2 files changed, 18 insertions(+), 75 deletions(-)
diff --git a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
index 68a0388398fc..847fdd760d2f 100644
--- a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -1095,24 +1095,17 @@ static void CloneInstructionsIntoPredecessorBlockAndUpdateSSAUses(
// Update (liveout) uses of bonus instructions,
// now that the bonus instruction has been cloned into predecessor.
- // Note that we expect to be in a block-closed SSA form for this to work!
+ SSAUpdater SSAUpdate;
+ SSAUpdate.Initialize(BonusInst.getType(),
+ (NewBonusInst->getName() + ".merge").str());
+ SSAUpdate.AddAvailableValue(BB, &BonusInst);
+ SSAUpdate.AddAvailableValue(PredBlock, NewBonusInst);
for (Use &U : make_early_inc_range(BonusInst.uses())) {
auto *UI = cast<Instruction>(U.getUser());
- auto *PN = dyn_cast<PHINode>(UI);
- if (!PN) {
- assert(UI->getParent() == BB && BonusInst.comesBefore(UI) &&
- "If the user is not a PHI node, then it should be in the same "
- "block as, and come after, the original bonus instruction.");
- continue; // Keep using the original bonus instruction.
- }
- // Is this the block-closed SSA form PHI node?
- if (PN->getIncomingBlock(U) == BB)
- continue; // Great, keep using the original bonus instruction.
- // The only other alternative is an "use" when coming from
- // the predecessor block - here we should refer to the cloned bonus instr.
- assert(PN->getIncomingBlock(U) == PredBlock &&
- "Not in block-closed SSA form?");
- U.set(NewBonusInst);
+ if (UI->getParent() != PredBlock)
+ SSAUpdate.RewriteUseAfterInsertions(U);
+ else // Use is in the same block as, and comes before, NewBonusInst.
+ SSAUpdate.RewriteUse(U);
}
}
}
@@ -3039,56 +3032,6 @@ static bool performBranchToCommonDestFolding(BranchInst *BI, BranchInst *PBI,
LLVM_DEBUG(dbgs() << "FOLDING BRANCH TO COMMON DEST:\n" << *PBI << *BB);
- // We want to duplicate all the bonus instructions in this block,
- // and rewrite their uses, but in some cases with self-loops,
- // the naive use rewrite approach won't work (will result in miscompilations).
- // To avoid this problem, let's form block-closed SSA form.
- for (Instruction &BonusInst :
- reverse(iterator_range<BasicBlock::iterator>(*BB))) {
- auto IsBCSSAUse = [BB, &BonusInst](Use &U) {
- auto *UI = cast<Instruction>(U.getUser());
- if (auto *PN = dyn_cast<PHINode>(UI))
- return PN->getIncomingBlock(U) == BB;
- return UI->getParent() == BB && BonusInst.comesBefore(UI);
- };
-
- // Does this instruction require rewriting of uses?
- if (all_of(BonusInst.uses(), IsBCSSAUse))
- continue;
-
- SSAUpdater SSAUpdate;
- Type *Ty = BonusInst.getType();
- SmallVector<PHINode *, 8> BCSSAPHIs;
- SSAUpdate.Initialize(Ty, BonusInst.getName());
-
- // Into each successor block of BB, insert a PHI node, that receives
- // the BonusInst when coming from it's basic block, or poison otherwise.
- for (BasicBlock *Succ : successors(BB)) {
- // The block may have the same successor multiple times. Do it only once.
- if (SSAUpdate.HasValueForBlock(Succ))
- continue;
- BCSSAPHIs.emplace_back(PHINode::Create(
- Ty, 0, BonusInst.getName() + ".bcssa", &Succ->front()));
- PHINode *PN = BCSSAPHIs.back();
- for (BasicBlock *PredOfSucc : predecessors(Succ))
- PN->addIncoming(PredOfSucc == BB ? (Value *)&BonusInst
- : PoisonValue::get(Ty),
- PredOfSucc);
- SSAUpdate.AddAvailableValue(Succ, PN);
- }
-
- // And rewrite all uses that break block-closed SSA form.
- for (Use &U : make_early_inc_range(BonusInst.uses()))
- if (!IsBCSSAUse(U))
- SSAUpdate.RewriteUseAfterInsertions(U);
-
- // We might not have ended up needing PHI's in all of the succ blocks,
- // drop the ones that are certainly unused, but don't bother otherwise.
- for (PHINode *PN : BCSSAPHIs)
- if (PN->use_empty())
- PN->eraseFromParent();
- }
-
IRBuilder<> Builder(PBI);
// The builder is used to create instructions to eliminate the branch in BB.
// If BB's terminator has !annotation metadata, add it to the new
diff --git a/llvm/test/Transforms/SimplifyCFG/fold-branch-to-common-dest.ll b/llvm/test/Transforms/SimplifyCFG/fold-branch-to-common-dest.ll
index d948b61d65a0..2ff041826077 100644
--- a/llvm/test/Transforms/SimplifyCFG/fold-branch-to-common-dest.ll
+++ b/llvm/test/Transforms/SimplifyCFG/fold-branch-to-common-dest.ll
@@ -834,7 +834,7 @@ define void @pr48450() {
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
-; CHECK-NEXT: [[COUNTDOWN:%.*]] = phi i8 [ 8, [[ENTRY:%.*]] ], [ [[DEC_BCSSA1:%.*]], [[FOR_BODYTHREAD_PRE_SPLIT:%.*]] ]
+; CHECK-NEXT: [[COUNTDOWN:%.*]] = phi i8 [ 8, [[ENTRY:%.*]] ], [ [[DEC_MERGE:%.*]], [[FOR_BODYTHREAD_PRE_SPLIT:%.*]] ]
; CHECK-NEXT: [[C:%.*]] = call i1 @gen1()
; CHECK-NEXT: br i1 [[C]], label [[FOR_INC:%.*]], label [[IF_THEN:%.*]]
; CHECK: for.inc:
@@ -849,7 +849,7 @@ define void @pr48450() {
; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[C2_NOT]], i1 true, i1 [[CMP_NOT]]
; CHECK-NEXT: br i1 [[OR_COND]], label [[IF_END_LOOPEXIT]], label [[FOR_BODYTHREAD_PRE_SPLIT]]
; CHECK: for.bodythread-pre-split:
-; CHECK-NEXT: [[DEC_BCSSA1]] = phi i8 [ [[DEC_OLD]], [[FOR_INC]] ], [ [[DEC]], [[IF_THEN]] ]
+; CHECK-NEXT: [[DEC_MERGE]] = phi i8 [ [[DEC]], [[IF_THEN]] ], [ [[DEC_OLD]], [[FOR_INC]] ]
; CHECK-NEXT: call void @sideeffect0()
; CHECK-NEXT: br label [[FOR_BODY]]
; CHECK: if.end.loopexit:
@@ -885,7 +885,7 @@ define void @pr48450_2(i1 %enable_loopback) {
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
-; CHECK-NEXT: [[COUNTDOWN:%.*]] = phi i8 [ 8, [[ENTRY:%.*]] ], [ [[DEC_BCSSA1:%.*]], [[FOR_BODYTHREAD_PRE_SPLIT:%.*]] ]
+; CHECK-NEXT: [[COUNTDOWN:%.*]] = phi i8 [ 8, [[ENTRY:%.*]] ], [ [[DEC_MERGE:%.*]], [[FOR_BODYTHREAD_PRE_SPLIT:%.*]] ]
; CHECK-NEXT: [[C:%.*]] = call i1 @gen1()
; CHECK-NEXT: br i1 [[C]], label [[FOR_INC:%.*]], label [[IF_THEN:%.*]]
; CHECK: for.inc:
@@ -900,7 +900,7 @@ define void @pr48450_2(i1 %enable_loopback) {
; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[C2_NOT]], i1 true, i1 [[CMP_NOT]]
; CHECK-NEXT: br i1 [[OR_COND]], label [[IF_END_LOOPEXIT]], label [[FOR_BODYTHREAD_PRE_SPLIT]]
; CHECK: for.bodythread-pre-split:
-; CHECK-NEXT: [[DEC_BCSSA1]] = phi i8 [ poison, [[FOR_BODYTHREAD_PRE_SPLIT_LOOPBACK:%.*]] ], [ [[DEC_OLD]], [[FOR_INC]] ], [ [[DEC]], [[IF_THEN]] ]
+; CHECK-NEXT: [[DEC_MERGE]] = phi i8 [ [[DEC_OLD]], [[FOR_INC]] ], [ [[DEC_MERGE]], [[FOR_BODYTHREAD_PRE_SPLIT_LOOPBACK:%.*]] ], [ [[DEC]], [[IF_THEN]] ]
; CHECK-NEXT: [[SHOULD_LOOPBACK:%.*]] = phi i1 [ true, [[FOR_INC]] ], [ false, [[FOR_BODYTHREAD_PRE_SPLIT_LOOPBACK]] ], [ true, [[IF_THEN]] ]
; CHECK-NEXT: [[DO_LOOPBACK:%.*]] = and i1 [[SHOULD_LOOPBACK]], [[ENABLE_LOOPBACK:%.*]]
; CHECK-NEXT: call void @sideeffect0()
@@ -1005,8 +1005,8 @@ define void @pr49510() {
; CHECK-NEXT: [[TOBOOL_OLD:%.*]] = icmp ne i16 [[DOTOLD]], 0
; CHECK-NEXT: br i1 [[TOBOOL_OLD]], label [[LAND_RHS:%.*]], label [[FOR_END:%.*]]
; CHECK: land.rhs:
-; CHECK-NEXT: [[DOTBCSSA:%.*]] = phi i16 [ [[DOTOLD]], [[ENTRY:%.*]] ], [ [[TMP0:%.*]], [[LAND_RHS]] ]
-; CHECK-NEXT: [[CMP:%.*]] = icmp slt i16 [[DOTBCSSA]], 0
+; CHECK-NEXT: [[DOTMERGE:%.*]] = phi i16 [ [[TMP0:%.*]], [[LAND_RHS]] ], [ [[DOTOLD]], [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[CMP:%.*]] = icmp slt i16 [[DOTMERGE]], 0
; CHECK-NEXT: [[TMP0]] = load i16, i16* @global_pr49510, align 1
; CHECK-NEXT: [[TOBOOL:%.*]] = icmp ne i16 [[TMP0]], 0
; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[CMP]], i1 [[TOBOOL]], i1 false
@@ -1043,15 +1043,15 @@ define i32 @pr51125() {
; CHECK-NEXT: [[ISZERO_OLD:%.*]] = icmp eq i32 [[LD_OLD]], 0
; CHECK-NEXT: br i1 [[ISZERO_OLD]], label [[EXIT:%.*]], label [[L2:%.*]]
; CHECK: L2:
-; CHECK-NEXT: [[LD_BCSSA1:%.*]] = phi i32 [ [[LD_OLD]], [[ENTRY:%.*]] ], [ [[LD:%.*]], [[L2]] ]
+; CHECK-NEXT: [[LD_MERGE:%.*]] = phi i32 [ [[LD:%.*]], [[L2]] ], [ [[LD_OLD]], [[ENTRY:%.*]] ]
; CHECK-NEXT: store i32 -1, i32* @global_pr51125, align 4
-; CHECK-NEXT: [[CMP:%.*]] = icmp ne i32 [[LD_BCSSA1]], -1
+; CHECK-NEXT: [[CMP:%.*]] = icmp ne i32 [[LD_MERGE]], -1
; CHECK-NEXT: [[LD]] = load i32, i32* @global_pr51125, align 4
; CHECK-NEXT: [[ISZERO:%.*]] = icmp eq i32 [[LD]], 0
; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[CMP]], i1 true, i1 [[ISZERO]]
; CHECK-NEXT: br i1 [[OR_COND]], label [[EXIT]], label [[L2]]
; CHECK: exit:
-; CHECK-NEXT: [[R:%.*]] = phi i32 [ [[LD_BCSSA1]], [[L2]] ], [ [[LD_OLD]], [[ENTRY]] ]
+; CHECK-NEXT: [[R:%.*]] = phi i32 [ [[LD]], [[L2]] ], [ [[LD_OLD]], [[ENTRY]] ]
; CHECK-NEXT: ret i32 [[R]]
;
entry:
</cut>
3 years, 9 months
- 1
- 0
[TCWG CI] Regression caused by gcc:76b75018b3d053a890ebe155e47814de14b3c9fb
by ci_notify＠linaro.org
Identified regression caused by *gcc:76b75018b3d053a890ebe155e47814de14b3c9fb*:
commit 76b75018b3d053a890ebe155e47814de14b3c9fb
Author: Jason Merrill <jason(a)redhat.com>
c++: implement C++17 hardware interference size
Results regressed to (for first_bad == 76b75018b3d053a890ebe155e47814de14b3c9fb)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# build_abe stage1:
2
# build_abe linux:
3
# build_abe glibc:
4
# First few build errors in logs:
from (for last_good == 8ea292591e42aa4d52b4b7a00b86335bfd2e2e85)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# build_abe stage1:
2
# build_abe linux:
3
# build_abe glibc:
4
# build_abe stage2:
5
# build_abe gdb:
6
# build_abe qemu:
7
This commit has regressed these CI configurations:
- tcwg_gnu_cross_build/master-aarch64
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/2/arti…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/2/arti…
Even more details: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/2/arti…
Reproduce builds:
<cut>
mkdir investigate-gcc-76b75018b3d053a890ebe155e47814de14b3c9fb
cd investigate-gcc-76b75018b3d053a890ebe155e47814de14b3c9fb
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/2/arti… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/2/arti… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/2/arti… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 76b75018b3d053a890ebe155e47814de14b3c9fb
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 8ea292591e42aa4d52b4b7a00b86335bfd2e2e85
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 76b75018b3d053a890ebe155e47814de14b3c9fb
Author: Jason Merrill <jason(a)redhat.com>
Date: Thu Jul 15 15:30:17 2021 -0400
c++: implement C++17 hardware interference size
The last missing piece of the C++17 standard library is the hardware
intereference size constants. Much of the delay in implementing these has
been due to uncertainty about what the right values are, and even whether
there is a single constant value that is suitable; the destructive
interference size is intended to be used in structure layout, so program
ABIs will depend on it.
In principle, both of these values should be the same as the target's L1
cache line size. When compiling for a generic target that is intended to
support a range of target CPUs with different cache line sizes, the
constructive size should probably be the minimum size, and the destructive
size the maximum, unless you are constrained by ABI compatibility with
previous code.
From discussion on gcc-patches, I've come to the conclusion that the
solution to the difficulty of choosing stable values is to give up on it,
and instead encourage only uses where ABI stability is unimportant: in
particular, uses where the ABI is shared at most between translation units
built at the same time with the same flags.
To that end, I've added a warning for any use of the constant value of
std::hardware_destructive_interference_size in a header or module export.
Appropriate uses within a project can disable the warning.
A previous iteration of this patch included an -finterference-tune flag to
make the value vary with -mtune; this iteration makes that the default
behavior, which should be appropriate for all reasonable uses of the
variable. The previous default of "stable-ish" seems to me likely to have
been more of an attractive nuisance; since we can't promise actual
stability, we should instead make proper uses more convenient.
JF Bastien's implementation proposal is summarized at
https://github.com/itanium-cxx-abi/cxx-abi/issues/74
I implement this by adding new --params for the two sizes. Targets can
override these values in targetm.target_option.override() to support a range
of values for the generic target; otherwise, both will default to the L1
cache line size.
64 bytes still seems correct for all x86.
I'm not sure why he proposed 64/64 for generic 32-bit ARM, since the Cortex
A9 has a 32-byte cache line, so I'd think 32/64 would make more sense.
He proposed 64/128 for generic AArch64, but since the A64FX now has a 256B
cache line, I've changed that to 64/256.
Other arch maintainers are invited to set ranges for their generic targets
if that seems better than using the default cache line size for both values.
With the above choice to reject stability as a goal, getting these values
"right" is now just a matter of what we want the default optimization to be,
and we can feel free to adjust them as CPUs with different cache lines
become more and less common.
gcc/ChangeLog:
* params.opt: Add destructive-interference-size and
constructive-interference-size.
* doc/invoke.texi: Document them.
* config/aarch64/aarch64.c (aarch64_override_options_internal):
Set them.
* config/arm/arm.c (arm_option_override): Set them.
* config/i386/i386-options.c (ix86_option_override_internal):
Set them.
gcc/c-family/ChangeLog:
* c.opt: Add -Winterference-size.
* c-cppbuiltin.c (cpp_atomic_builtins): Add __GCC_DESTRUCTIVE_SIZE
and __GCC_CONSTRUCTIVE_SIZE.
gcc/cp/ChangeLog:
* constexpr.c (maybe_warn_about_constant_value):
Complain about std::hardware_destructive_interference_size.
(cxx_eval_constant_expression): Call it.
* decl.c (cxx_init_decl_processing): Check
--param *-interference-size values.
libstdc++-v3/ChangeLog:
* include/std/version: Define __cpp_lib_hardware_interference_size.
* libsupc++/new: Define hardware interference size variables.
gcc/testsuite/ChangeLog:
* g++.dg/warn/Winterference.H: New file.
* g++.dg/warn/Winterference.C: New test.
* g++.target/aarch64/interference.C: New test.
* g++.target/arm/interference.C: New test.
* g++.target/i386/interference.C: New test.
---
gcc/c-family/c-cppbuiltin.c | 14 ++++++
gcc/c-family/c.opt | 5 ++
gcc/config/aarch64/aarch64.c | 22 +++++++++
gcc/config/arm/arm.c | 22 +++++++++
gcc/config/i386/i386-options.c | 6 +++
gcc/cp/constexpr.c | 33 +++++++++++++
gcc/cp/decl.c | 32 ++++++++++++
gcc/doc/invoke.texi | 65 +++++++++++++++++++++++++
gcc/params.opt | 16 ++++++
gcc/testsuite/g++.dg/warn/Winterference-2.C | 14 ++++++
gcc/testsuite/g++.dg/warn/Winterference.C | 6 +++
gcc/testsuite/g++.dg/warn/Winterference.H | 7 +++
gcc/testsuite/g++.target/aarch64/interference.C | 9 ++++
gcc/testsuite/g++.target/arm/interference.C | 9 ++++
gcc/testsuite/g++.target/i386/interference.C | 8 +++
libstdc++-v3/include/std/version | 3 ++
libstdc++-v3/libsupc++/new | 10 +++-
17 files changed, 279 insertions(+), 2 deletions(-)
diff --git a/gcc/c-family/c-cppbuiltin.c b/gcc/c-family/c-cppbuiltin.c
index 48cbefd8bf8..ce88e707127 100644
--- a/gcc/c-family/c-cppbuiltin.c
+++ b/gcc/c-family/c-cppbuiltin.c
@@ -741,6 +741,20 @@ cpp_atomic_builtins (cpp_reader *pfile)
builtin_define_with_int_value ("__GCC_ATOMIC_TEST_AND_SET_TRUEVAL",
targetm.atomic_test_and_set_trueval);
+ /* Macros for C++17 hardware interference size constants. Either both or
+ neither should be set. */
+ gcc_assert (!param_destruct_interfere_size
+ == !param_construct_interfere_size);
+ if (param_destruct_interfere_size)
+ {
+ /* FIXME The way of communicating these values to the library should be
+ part of the C++ ABI, whether macro or builtin. */
+ builtin_define_with_int_value ("__GCC_DESTRUCTIVE_SIZE",
+ param_destruct_interfere_size);
+ builtin_define_with_int_value ("__GCC_CONSTRUCTIVE_SIZE",
+ param_construct_interfere_size);
+ }
+
/* ptr_type_node can't be used here since ptr_mode is only set when
toplev calls backend_init which is not done with -E or pch. */
psize = POINTER_SIZE_UNITS;
diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
index c5fe90003f2..9c151d19870 100644
--- a/gcc/c-family/c.opt
+++ b/gcc/c-family/c.opt
@@ -722,6 +722,11 @@ Winit-list-lifetime
C++ ObjC++ Var(warn_init_list) Warning Init(1)
Warn about uses of std::initializer_list that can result in dangling pointers.
+Winterference-size
+C++ ObjC++ Var(warn_interference_size) Warning Init(1)
+Warn about nonsensical values of --param destructive-interference-size or
+constructive-interference-size.
+
Wimplicit
C ObjC Var(warn_implicit) Warning LangEnabledBy(C ObjC,Wall)
Warn about implicit declarations.
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 30d9a0b7a3d..36519ccc5a5 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -16540,6 +16540,28 @@ aarch64_override_options_internal (struct gcc_options *opts)
SET_OPTION_IF_UNSET (opts, &global_options_set,
param_l1_cache_line_size,
aarch64_tune_params.prefetch->l1_cache_line_size);
+
+ if (aarch64_tune_params.prefetch->l1_cache_line_size >= 0)
+ {
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_destruct_interfere_size,
+ aarch64_tune_params.prefetch->l1_cache_line_size);
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_construct_interfere_size,
+ aarch64_tune_params.prefetch->l1_cache_line_size);
+ }
+ else
+ {
+ /* For a generic AArch64 target, cover the current range of cache line
+ sizes. */
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_destruct_interfere_size,
+ 256);
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_construct_interfere_size,
+ 64);
+ }
+
if (aarch64_tune_params.prefetch->l2_cache_size >= 0)
SET_OPTION_IF_UNSET (opts, &global_options_set,
param_l2_cache_size,
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index f1e628253d0..6c6e77fab66 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -3669,6 +3669,28 @@ arm_option_override (void)
SET_OPTION_IF_UNSET (&global_options, &global_options_set,
param_l1_cache_line_size,
current_tune->prefetch.l1_cache_line_size);
+ if (current_tune->prefetch.l1_cache_line_size >= 0)
+ {
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size,
+ current_tune->prefetch.l1_cache_line_size);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size,
+ current_tune->prefetch.l1_cache_line_size);
+ }
+ else
+ {
+ /* For a generic ARM target, JF Bastien proposed using 64 for both. */
+ /* ??? Cortex A9 has a 32-byte cache line, so why not 32 for
+ constructive? */
+ /* More recent Cortex chips have a 64-byte cache line, but are marked
+ ARM_PREFETCH_NOT_BENEFICIAL, so they get these defaults. */
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size, 64);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size, 64);
+ }
+
if (current_tune->prefetch.l1_cache_size >= 0)
SET_OPTION_IF_UNSET (&global_options, &global_options_set,
param_l1_cache_size,
diff --git a/gcc/config/i386/i386-options.c b/gcc/config/i386/i386-options.c
index 2cb87cedec0..c0006b3674b 100644
--- a/gcc/config/i386/i386-options.c
+++ b/gcc/config/i386/i386-options.c
@@ -2579,6 +2579,12 @@ ix86_option_override_internal (bool main_args_p,
SET_OPTION_IF_UNSET (opts, opts_set, param_l2_cache_size,
ix86_tune_cost->l2_cache_size);
+ /* 64B is the accepted value for these for all x86. */
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size, 64);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size, 64);
+
/* Enable sw prefetching at -O3 for CPUS that prefetching is helpful. */
if (opts->x_flag_prefetch_loop_arrays < 0
&& HAVE_prefetch
diff --git a/gcc/cp/constexpr.c b/gcc/cp/constexpr.c
index 7772fe62d95..0c2498aee22 100644
--- a/gcc/cp/constexpr.c
+++ b/gcc/cp/constexpr.c
@@ -6075,6 +6075,37 @@ inline_asm_in_constexpr_error (location_t loc)
"%<constexpr%> function in C++20");
}
+/* We're getting the constant value of DECL in a manifestly constant-evaluated
+ context; maybe complain about that. */
+
+static void
+maybe_warn_about_constant_value (location_t loc, tree decl)
+{
+ static bool explained = false;
+ if (cxx_dialect >= cxx17
+ && warn_interference_size
+ && !global_options_set.x_param_destruct_interfere_size
+ && DECL_CONTEXT (decl) == std_node
+ && id_equal (DECL_NAME (decl), "hardware_destructive_interference_size")
+ && (LOCATION_FILE (input_location) != main_input_filename
+ || module_exporting_p ())
+ && warning_at (loc, OPT_Winterference_size, "use of %qD", decl)
+ && !explained)
+ {
+ explained = true;
+ inform (loc, "its value can vary between compiler versions or "
+ "with different %<-mtune%> or %<-mcpu%> flags");
+ inform (loc, "if this use is part of a public ABI, change it to "
+ "instead use a constant variable you define");
+ inform (loc, "the default value for the current CPU tuning "
+ "is %d bytes", param_destruct_interfere_size);
+ inform (loc, "you can stabilize this value with %<--param "
+ "hardware_destructive_interference_size=%d%>, or disable "
+ "this warning with %<-Wno-interference-size%>",
+ param_destruct_interfere_size);
+ }
+}
+
/* Attempt to reduce the expression T to a constant value.
On failure, issue diagnostic and return error_mark_node. */
/* FIXME unify with c_fully_fold */
@@ -6219,6 +6250,8 @@ cxx_eval_constant_expression (const constexpr_ctx *ctx, tree t,
r = *p;
break;
}
+ if (ctx->manifestly_const_eval)
+ maybe_warn_about_constant_value (loc, t);
if (COMPLETE_TYPE_P (TREE_TYPE (t))
&& is_really_empty_class (TREE_TYPE (t), /*ignore_vptr*/false))
{
diff --git a/gcc/cp/decl.c b/gcc/cp/decl.c
index bce62ad202a..c2065027369 100644
--- a/gcc/cp/decl.c
+++ b/gcc/cp/decl.c
@@ -4752,6 +4752,38 @@ cxx_init_decl_processing (void)
/* Show we use EH for cleanups. */
if (flag_exceptions)
using_eh_for_cleanups ();
+
+ /* Check that the hardware interference sizes are at least
+ alignof(max_align_t), as required by the standard. */
+ const int max_align = max_align_t_align () / BITS_PER_UNIT;
+ if (param_destruct_interfere_size)
+ {
+ if (param_destruct_interfere_size < max_align)
+ error ("%<--param destructive-interference-size=%d%> is less than "
+ "%d", param_destruct_interfere_size, max_align);
+ else if (param_destruct_interfere_size < param_l1_cache_line_size)
+ warning (OPT_Winterference_size,
+ "%<--param destructive-interference-size=%d%> "
+ "is less than %<--param l1-cache-line-size=%d%>",
+ param_destruct_interfere_size, param_l1_cache_line_size);
+ }
+ else if (param_l1_cache_line_size >= max_align)
+ param_destruct_interfere_size = param_l1_cache_line_size;
+ /* else leave it unset. */
+
+ if (param_construct_interfere_size)
+ {
+ if (param_construct_interfere_size < max_align)
+ error ("%<--param constructive-interference-size=%d%> is less than "
+ "%d", param_construct_interfere_size, max_align);
+ else if (param_construct_interfere_size > param_l1_cache_line_size)
+ warning (OPT_Winterference_size,
+ "%<--param constructive-interference-size=%d%> "
+ "is greater than %<--param l1-cache-line-size=%d%>",
+ param_construct_interfere_size, param_l1_cache_line_size);
+ }
+ else if (param_l1_cache_line_size >= max_align)
+ param_construct_interfere_size = param_l1_cache_line_size;
}
/* Enter an abi node in global-module context. returns a cookie to
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 23cc68f92b5..78cfc100ac2 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -9018,6 +9018,43 @@ that has already been done in the current function. Therefore,
seemingly insignificant changes in the source program can cause the
warnings produced by @option{-Winline} to appear or disappear.
+@item -Winterference-size
+@opindex Winterference-size
+Warn about use of C++17 @code{std::hardware_destructive_interference_size}
+without specifying its value with @option{--param destructive-interference-size}.
+Also warn about questionable values for that option.
+
+This variable is intended to be used for controlling class layout, to
+avoid false sharing in concurrent code:
+
+@smallexample
+struct independent_fields @{
+ alignas(std::hardware_destructive_interference_size) std::atomic<int> one;
+ alignas(std::hardware_destructive_interference_size) std::atomic<int> two;
+@};
+@end smallexample
+
+Here @samp{one} and @samp{two} are intended to be far enough apart
+that stores to one won't require accesses to the other to reload the
+cache line.
+
+By default, @option{--param destructive-interference-size} and
+@option{--param constructive-interference-size} are set based on the
+current @option{-mtune} option, typically to the L1 cache line size
+for the particular target CPU, sometimes to a range if tuning for a
+generic target. So all translation units that depend on ABI
+compatibility for the use of these variables must be compiled with
+the same @option{-mtune} (or @option{-mcpu}).
+
+If ABI stability is important, such as if the use is in a header for a
+library, you should probably not use the hardware interference size
+variables at all. Alternatively, you can force a particular value
+with @option{--param}.
+
+If you are confident that your use of the variable does not affect ABI
+outside a single build of your project, you can turn off the warning
+with @option{-Wno-interference-size}.
+
@item -Wint-in-bool-context
@opindex Wint-in-bool-context
@opindex Wno-int-in-bool-context
@@ -13938,6 +13975,34 @@ prefetch hints can be issued for any constant stride.
This setting is only useful for strides that are known and constant.
+@item destructive-interference-size
+@item constructive-interference-size
+The values for the C++17 variables
+@code{std::hardware_destructive_interference_size} and
+@code{std::hardware_constructive_interference_size}. The destructive
+interference size is the minimum recommended offset between two
+independent concurrently-accessed objects; the constructive
+interference size is the maximum recommended size of contiguous memory
+accessed together. Typically both will be the size of an L1 cache
+line for the target, in bytes. For a generic target covering a range of L1
+cache line sizes, typically the constructive interference size will be
+the small end of the range and the destructive size will be the large
+end.
+
+The destructive interference size is intended to be used for layout,
+and thus has ABI impact. The default value is not expected to be
+stable, and on some targets varies with @option{-mtune}, so use of
+this variable in a context where ABI stability is important, such as
+the public interface of a library, is strongly discouraged; if it is
+used in that context, users can stabilize the value using this
+option.
+
+The constructive interference size is less sensitive, as it is
+typically only used in a @samp{static_assert} to make sure that a type
+fits within a cache line.
+
+See also @option{-Winterference-size}.
+
@item loop-interchange-max-num-stmts
The maximum number of stmts in a loop to be interchanged.
diff --git a/gcc/params.opt b/gcc/params.opt
index 3a701e22c46..658ca028851 100644
--- a/gcc/params.opt
+++ b/gcc/params.opt
@@ -361,6 +361,22 @@ The maximum code size growth ratio when expanding into a jump table (in percent)
Common Joined UInteger Var(param_l1_cache_line_size) Init(32) Param Optimization
The size of L1 cache line.
+-param=destructive-interference-size=
+Common Joined UInteger Var(param_destruct_interfere_size) Init(0) Param Optimization
+The minimum recommended offset between two concurrently-accessed objects to
+avoid additional performance degradation due to contention introduced by the
+implementation. Typically the L1 cache line size, but can be larger to
+accommodate a variety of target processors with different cache line sizes.
+C++17 code might use this value in structure layout, but is strongly
+discouraged from doing so in public ABIs.
+
+-param=constructive-interference-size=
+Common Joined UInteger Var(param_construct_interfere_size) Init(0) Param Optimization
+The maximum recommended size of contiguous memory occupied by two objects
+accessed with temporal locality by concurrent threads. Typically the L1 cache
+line size, but can be smaller to accommodate a variety of target processors with
+different cache line sizes.
+
-param=l1-cache-size=
Common Joined UInteger Var(param_l1_cache_size) Init(64) Param Optimization
The size of L1 cache.
diff --git a/gcc/testsuite/g++.dg/warn/Winterference-2.C b/gcc/testsuite/g++.dg/warn/Winterference-2.C
new file mode 100644
index 00000000000..2af75c63f83
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference-2.C
@@ -0,0 +1,14 @@
+// { dg-do compile { target c++20 } }
+// { dg-additional-options -fmodules-ts }
+
+module ;
+
+#include <new>
+
+export module foo;
+
+export {
+ struct A {
+ alignas(std::hardware_destructive_interference_size) int x; // { dg-warning Winterference-size }
+ };
+}
diff --git a/gcc/testsuite/g++.dg/warn/Winterference.C b/gcc/testsuite/g++.dg/warn/Winterference.C
new file mode 100644
index 00000000000..57c001bc032
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference.C
@@ -0,0 +1,6 @@
+// Test that we warn about use of std::hardware_destructive_interference_size
+// in a header.
+// { dg-do compile { target c++17 } }
+
+// { dg-warning Winterference-size "" { target *-*-* } 0 }
+#include "Winterference.H"
diff --git a/gcc/testsuite/g++.dg/warn/Winterference.H b/gcc/testsuite/g++.dg/warn/Winterference.H
new file mode 100644
index 00000000000..36f0ad5f6d1
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference.H
@@ -0,0 +1,7 @@
+#include <new>
+
+struct A
+{
+ alignas(std::hardware_destructive_interference_size) int i;
+ alignas(std::hardware_destructive_interference_size) int j;
+};
diff --git a/gcc/testsuite/g++.target/aarch64/interference.C b/gcc/testsuite/g++.target/aarch64/interference.C
new file mode 100644
index 00000000000..0fc01655223
--- /dev/null
+++ b/gcc/testsuite/g++.target/aarch64/interference.C
@@ -0,0 +1,9 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// Most AArch64 CPUs have an L1 cache line size of 64, but some recent ones use
+// 128 or even 256.
+static_assert(std::hardware_destructive_interference_size == 256);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/gcc/testsuite/g++.target/arm/interference.C b/gcc/testsuite/g++.target/arm/interference.C
new file mode 100644
index 00000000000..34fe8a52bff
--- /dev/null
+++ b/gcc/testsuite/g++.target/arm/interference.C
@@ -0,0 +1,9 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// Recent ARM CPUs have a cache line size of 64. Older ones have
+// a size of 32, but I guess they're old enough that we don't care?
+static_assert(std::hardware_destructive_interference_size == 64);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/gcc/testsuite/g++.target/i386/interference.C b/gcc/testsuite/g++.target/i386/interference.C
new file mode 100644
index 00000000000..c7b910e3ada
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/interference.C
@@ -0,0 +1,8 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// It is generally agreed that these are the right values for all x86.
+static_assert(std::hardware_destructive_interference_size == 64);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/libstdc++-v3/include/std/version b/libstdc++-v3/include/std/version
index f950bf0f0db..f41004b5911 100644
--- a/libstdc++-v3/include/std/version
+++ b/libstdc++-v3/include/std/version
@@ -140,6 +140,9 @@
#define __cpp_lib_filesystem 201703
#define __cpp_lib_gcd 201606
#define __cpp_lib_gcd_lcm 201606
+#ifdef __GCC_DESTRUCTIVE_SIZE
+# define __cpp_lib_hardware_interference_size 201703L
+#endif
#define __cpp_lib_hypot 201603
#define __cpp_lib_invoke 201411L
#define __cpp_lib_lcm 201606
diff --git a/libstdc++-v3/libsupc++/new b/libstdc++-v3/libsupc++/new
index 3349b13fd1b..7bc67a6cb02 100644
--- a/libstdc++-v3/libsupc++/new
+++ b/libstdc++-v3/libsupc++/new
@@ -183,9 +183,9 @@ inline void operator delete[](void*, void*) _GLIBCXX_USE_NOEXCEPT { }
} // extern "C++"
#if __cplusplus >= 201703L
-#ifdef _GLIBCXX_HAVE_BUILTIN_LAUNDER
namespace std
{
+#ifdef _GLIBCXX_HAVE_BUILTIN_LAUNDER
#define __cpp_lib_launder 201606
/// Pointer optimization barrier [ptr.launder]
template<typename _Tp>
@@ -205,8 +205,14 @@ namespace std
void launder(const void*) = delete;
void launder(volatile void*) = delete;
void launder(const volatile void*) = delete;
-}
#endif // _GLIBCXX_HAVE_BUILTIN_LAUNDER
+
+#ifdef __GCC_DESTRUCTIVE_SIZE
+# define __cpp_lib_hardware_interference_size 201703L
+ inline constexpr size_t hardware_destructive_interference_size = __GCC_DESTRUCTIVE_SIZE;
+ inline constexpr size_t hardware_constructive_interference_size = __GCC_CONSTRUCTIVE_SIZE;
+#endif // __GCC_DESTRUCTIVE_SIZE
+}
#endif // C++17
#if __cplusplus > 201703L
</cut>
3 years, 9 months
- 1
- 0
[TCWG CI] Regression caused by gcc:76b75018b3d053a890ebe155e47814de14b3c9fb
by ci_notify＠linaro.org
Identified regression caused by *gcc:76b75018b3d053a890ebe155e47814de14b3c9fb*:
commit 76b75018b3d053a890ebe155e47814de14b3c9fb
Author: Jason Merrill <jason(a)redhat.com>
c++: implement C++17 hardware interference size
Results regressed to (for first_bad == 76b75018b3d053a890ebe155e47814de14b3c9fb)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# First few build errors in logs:
from (for last_good == 8ea292591e42aa4d52b4b7a00b86335bfd2e2e85)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# build_abe bootstrap:
2
This commit has regressed these CI configurations:
- tcwg_gcc_bootstrap/master-aarch64-bootstrap
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra…
Even more details: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra…
Reproduce builds:
<cut>
mkdir investigate-gcc-76b75018b3d053a890ebe155e47814de14b3c9fb
cd investigate-gcc-76b75018b3d053a890ebe155e47814de14b3c9fb
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 76b75018b3d053a890ebe155e47814de14b3c9fb
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 8ea292591e42aa4d52b4b7a00b86335bfd2e2e85
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 76b75018b3d053a890ebe155e47814de14b3c9fb
Author: Jason Merrill <jason(a)redhat.com>
Date: Thu Jul 15 15:30:17 2021 -0400
c++: implement C++17 hardware interference size
The last missing piece of the C++17 standard library is the hardware
intereference size constants. Much of the delay in implementing these has
been due to uncertainty about what the right values are, and even whether
there is a single constant value that is suitable; the destructive
interference size is intended to be used in structure layout, so program
ABIs will depend on it.
In principle, both of these values should be the same as the target's L1
cache line size. When compiling for a generic target that is intended to
support a range of target CPUs with different cache line sizes, the
constructive size should probably be the minimum size, and the destructive
size the maximum, unless you are constrained by ABI compatibility with
previous code.
From discussion on gcc-patches, I've come to the conclusion that the
solution to the difficulty of choosing stable values is to give up on it,
and instead encourage only uses where ABI stability is unimportant: in
particular, uses where the ABI is shared at most between translation units
built at the same time with the same flags.
To that end, I've added a warning for any use of the constant value of
std::hardware_destructive_interference_size in a header or module export.
Appropriate uses within a project can disable the warning.
A previous iteration of this patch included an -finterference-tune flag to
make the value vary with -mtune; this iteration makes that the default
behavior, which should be appropriate for all reasonable uses of the
variable. The previous default of "stable-ish" seems to me likely to have
been more of an attractive nuisance; since we can't promise actual
stability, we should instead make proper uses more convenient.
JF Bastien's implementation proposal is summarized at
https://github.com/itanium-cxx-abi/cxx-abi/issues/74
I implement this by adding new --params for the two sizes. Targets can
override these values in targetm.target_option.override() to support a range
of values for the generic target; otherwise, both will default to the L1
cache line size.
64 bytes still seems correct for all x86.
I'm not sure why he proposed 64/64 for generic 32-bit ARM, since the Cortex
A9 has a 32-byte cache line, so I'd think 32/64 would make more sense.
He proposed 64/128 for generic AArch64, but since the A64FX now has a 256B
cache line, I've changed that to 64/256.
Other arch maintainers are invited to set ranges for their generic targets
if that seems better than using the default cache line size for both values.
With the above choice to reject stability as a goal, getting these values
"right" is now just a matter of what we want the default optimization to be,
and we can feel free to adjust them as CPUs with different cache lines
become more and less common.
gcc/ChangeLog:
* params.opt: Add destructive-interference-size and
constructive-interference-size.
* doc/invoke.texi: Document them.
* config/aarch64/aarch64.c (aarch64_override_options_internal):
Set them.
* config/arm/arm.c (arm_option_override): Set them.
* config/i386/i386-options.c (ix86_option_override_internal):
Set them.
gcc/c-family/ChangeLog:
* c.opt: Add -Winterference-size.
* c-cppbuiltin.c (cpp_atomic_builtins): Add __GCC_DESTRUCTIVE_SIZE
and __GCC_CONSTRUCTIVE_SIZE.
gcc/cp/ChangeLog:
* constexpr.c (maybe_warn_about_constant_value):
Complain about std::hardware_destructive_interference_size.
(cxx_eval_constant_expression): Call it.
* decl.c (cxx_init_decl_processing): Check
--param *-interference-size values.
libstdc++-v3/ChangeLog:
* include/std/version: Define __cpp_lib_hardware_interference_size.
* libsupc++/new: Define hardware interference size variables.
gcc/testsuite/ChangeLog:
* g++.dg/warn/Winterference.H: New file.
* g++.dg/warn/Winterference.C: New test.
* g++.target/aarch64/interference.C: New test.
* g++.target/arm/interference.C: New test.
* g++.target/i386/interference.C: New test.
---
gcc/c-family/c-cppbuiltin.c | 14 ++++++
gcc/c-family/c.opt | 5 ++
gcc/config/aarch64/aarch64.c | 22 +++++++++
gcc/config/arm/arm.c | 22 +++++++++
gcc/config/i386/i386-options.c | 6 +++
gcc/cp/constexpr.c | 33 +++++++++++++
gcc/cp/decl.c | 32 ++++++++++++
gcc/doc/invoke.texi | 65 +++++++++++++++++++++++++
gcc/params.opt | 16 ++++++
gcc/testsuite/g++.dg/warn/Winterference-2.C | 14 ++++++
gcc/testsuite/g++.dg/warn/Winterference.C | 6 +++
gcc/testsuite/g++.dg/warn/Winterference.H | 7 +++
gcc/testsuite/g++.target/aarch64/interference.C | 9 ++++
gcc/testsuite/g++.target/arm/interference.C | 9 ++++
gcc/testsuite/g++.target/i386/interference.C | 8 +++
libstdc++-v3/include/std/version | 3 ++
libstdc++-v3/libsupc++/new | 10 +++-
17 files changed, 279 insertions(+), 2 deletions(-)
diff --git a/gcc/c-family/c-cppbuiltin.c b/gcc/c-family/c-cppbuiltin.c
index 48cbefd8bf8..ce88e707127 100644
--- a/gcc/c-family/c-cppbuiltin.c
+++ b/gcc/c-family/c-cppbuiltin.c
@@ -741,6 +741,20 @@ cpp_atomic_builtins (cpp_reader *pfile)
builtin_define_with_int_value ("__GCC_ATOMIC_TEST_AND_SET_TRUEVAL",
targetm.atomic_test_and_set_trueval);
+ /* Macros for C++17 hardware interference size constants. Either both or
+ neither should be set. */
+ gcc_assert (!param_destruct_interfere_size
+ == !param_construct_interfere_size);
+ if (param_destruct_interfere_size)
+ {
+ /* FIXME The way of communicating these values to the library should be
+ part of the C++ ABI, whether macro or builtin. */
+ builtin_define_with_int_value ("__GCC_DESTRUCTIVE_SIZE",
+ param_destruct_interfere_size);
+ builtin_define_with_int_value ("__GCC_CONSTRUCTIVE_SIZE",
+ param_construct_interfere_size);
+ }
+
/* ptr_type_node can't be used here since ptr_mode is only set when
toplev calls backend_init which is not done with -E or pch. */
psize = POINTER_SIZE_UNITS;
diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
index c5fe90003f2..9c151d19870 100644
--- a/gcc/c-family/c.opt
+++ b/gcc/c-family/c.opt
@@ -722,6 +722,11 @@ Winit-list-lifetime
C++ ObjC++ Var(warn_init_list) Warning Init(1)
Warn about uses of std::initializer_list that can result in dangling pointers.
+Winterference-size
+C++ ObjC++ Var(warn_interference_size) Warning Init(1)
+Warn about nonsensical values of --param destructive-interference-size or
+constructive-interference-size.
+
Wimplicit
C ObjC Var(warn_implicit) Warning LangEnabledBy(C ObjC,Wall)
Warn about implicit declarations.
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 30d9a0b7a3d..36519ccc5a5 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -16540,6 +16540,28 @@ aarch64_override_options_internal (struct gcc_options *opts)
SET_OPTION_IF_UNSET (opts, &global_options_set,
param_l1_cache_line_size,
aarch64_tune_params.prefetch->l1_cache_line_size);
+
+ if (aarch64_tune_params.prefetch->l1_cache_line_size >= 0)
+ {
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_destruct_interfere_size,
+ aarch64_tune_params.prefetch->l1_cache_line_size);
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_construct_interfere_size,
+ aarch64_tune_params.prefetch->l1_cache_line_size);
+ }
+ else
+ {
+ /* For a generic AArch64 target, cover the current range of cache line
+ sizes. */
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_destruct_interfere_size,
+ 256);
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_construct_interfere_size,
+ 64);
+ }
+
if (aarch64_tune_params.prefetch->l2_cache_size >= 0)
SET_OPTION_IF_UNSET (opts, &global_options_set,
param_l2_cache_size,
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index f1e628253d0..6c6e77fab66 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -3669,6 +3669,28 @@ arm_option_override (void)
SET_OPTION_IF_UNSET (&global_options, &global_options_set,
param_l1_cache_line_size,
current_tune->prefetch.l1_cache_line_size);
+ if (current_tune->prefetch.l1_cache_line_size >= 0)
+ {
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size,
+ current_tune->prefetch.l1_cache_line_size);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size,
+ current_tune->prefetch.l1_cache_line_size);
+ }
+ else
+ {
+ /* For a generic ARM target, JF Bastien proposed using 64 for both. */
+ /* ??? Cortex A9 has a 32-byte cache line, so why not 32 for
+ constructive? */
+ /* More recent Cortex chips have a 64-byte cache line, but are marked
+ ARM_PREFETCH_NOT_BENEFICIAL, so they get these defaults. */
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size, 64);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size, 64);
+ }
+
if (current_tune->prefetch.l1_cache_size >= 0)
SET_OPTION_IF_UNSET (&global_options, &global_options_set,
param_l1_cache_size,
diff --git a/gcc/config/i386/i386-options.c b/gcc/config/i386/i386-options.c
index 2cb87cedec0..c0006b3674b 100644
--- a/gcc/config/i386/i386-options.c
+++ b/gcc/config/i386/i386-options.c
@@ -2579,6 +2579,12 @@ ix86_option_override_internal (bool main_args_p,
SET_OPTION_IF_UNSET (opts, opts_set, param_l2_cache_size,
ix86_tune_cost->l2_cache_size);
+ /* 64B is the accepted value for these for all x86. */
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size, 64);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size, 64);
+
/* Enable sw prefetching at -O3 for CPUS that prefetching is helpful. */
if (opts->x_flag_prefetch_loop_arrays < 0
&& HAVE_prefetch
diff --git a/gcc/cp/constexpr.c b/gcc/cp/constexpr.c
index 7772fe62d95..0c2498aee22 100644
--- a/gcc/cp/constexpr.c
+++ b/gcc/cp/constexpr.c
@@ -6075,6 +6075,37 @@ inline_asm_in_constexpr_error (location_t loc)
"%<constexpr%> function in C++20");
}
+/* We're getting the constant value of DECL in a manifestly constant-evaluated
+ context; maybe complain about that. */
+
+static void
+maybe_warn_about_constant_value (location_t loc, tree decl)
+{
+ static bool explained = false;
+ if (cxx_dialect >= cxx17
+ && warn_interference_size
+ && !global_options_set.x_param_destruct_interfere_size
+ && DECL_CONTEXT (decl) == std_node
+ && id_equal (DECL_NAME (decl), "hardware_destructive_interference_size")
+ && (LOCATION_FILE (input_location) != main_input_filename
+ || module_exporting_p ())
+ && warning_at (loc, OPT_Winterference_size, "use of %qD", decl)
+ && !explained)
+ {
+ explained = true;
+ inform (loc, "its value can vary between compiler versions or "
+ "with different %<-mtune%> or %<-mcpu%> flags");
+ inform (loc, "if this use is part of a public ABI, change it to "
+ "instead use a constant variable you define");
+ inform (loc, "the default value for the current CPU tuning "
+ "is %d bytes", param_destruct_interfere_size);
+ inform (loc, "you can stabilize this value with %<--param "
+ "hardware_destructive_interference_size=%d%>, or disable "
+ "this warning with %<-Wno-interference-size%>",
+ param_destruct_interfere_size);
+ }
+}
+
/* Attempt to reduce the expression T to a constant value.
On failure, issue diagnostic and return error_mark_node. */
/* FIXME unify with c_fully_fold */
@@ -6219,6 +6250,8 @@ cxx_eval_constant_expression (const constexpr_ctx *ctx, tree t,
r = *p;
break;
}
+ if (ctx->manifestly_const_eval)
+ maybe_warn_about_constant_value (loc, t);
if (COMPLETE_TYPE_P (TREE_TYPE (t))
&& is_really_empty_class (TREE_TYPE (t), /*ignore_vptr*/false))
{
diff --git a/gcc/cp/decl.c b/gcc/cp/decl.c
index bce62ad202a..c2065027369 100644
--- a/gcc/cp/decl.c
+++ b/gcc/cp/decl.c
@@ -4752,6 +4752,38 @@ cxx_init_decl_processing (void)
/* Show we use EH for cleanups. */
if (flag_exceptions)
using_eh_for_cleanups ();
+
+ /* Check that the hardware interference sizes are at least
+ alignof(max_align_t), as required by the standard. */
+ const int max_align = max_align_t_align () / BITS_PER_UNIT;
+ if (param_destruct_interfere_size)
+ {
+ if (param_destruct_interfere_size < max_align)
+ error ("%<--param destructive-interference-size=%d%> is less than "
+ "%d", param_destruct_interfere_size, max_align);
+ else if (param_destruct_interfere_size < param_l1_cache_line_size)
+ warning (OPT_Winterference_size,
+ "%<--param destructive-interference-size=%d%> "
+ "is less than %<--param l1-cache-line-size=%d%>",
+ param_destruct_interfere_size, param_l1_cache_line_size);
+ }
+ else if (param_l1_cache_line_size >= max_align)
+ param_destruct_interfere_size = param_l1_cache_line_size;
+ /* else leave it unset. */
+
+ if (param_construct_interfere_size)
+ {
+ if (param_construct_interfere_size < max_align)
+ error ("%<--param constructive-interference-size=%d%> is less than "
+ "%d", param_construct_interfere_size, max_align);
+ else if (param_construct_interfere_size > param_l1_cache_line_size)
+ warning (OPT_Winterference_size,
+ "%<--param constructive-interference-size=%d%> "
+ "is greater than %<--param l1-cache-line-size=%d%>",
+ param_construct_interfere_size, param_l1_cache_line_size);
+ }
+ else if (param_l1_cache_line_size >= max_align)
+ param_construct_interfere_size = param_l1_cache_line_size;
}
/* Enter an abi node in global-module context. returns a cookie to
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 23cc68f92b5..78cfc100ac2 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -9018,6 +9018,43 @@ that has already been done in the current function. Therefore,
seemingly insignificant changes in the source program can cause the
warnings produced by @option{-Winline} to appear or disappear.
+@item -Winterference-size
+@opindex Winterference-size
+Warn about use of C++17 @code{std::hardware_destructive_interference_size}
+without specifying its value with @option{--param destructive-interference-size}.
+Also warn about questionable values for that option.
+
+This variable is intended to be used for controlling class layout, to
+avoid false sharing in concurrent code:
+
+@smallexample
+struct independent_fields @{
+ alignas(std::hardware_destructive_interference_size) std::atomic<int> one;
+ alignas(std::hardware_destructive_interference_size) std::atomic<int> two;
+@};
+@end smallexample
+
+Here @samp{one} and @samp{two} are intended to be far enough apart
+that stores to one won't require accesses to the other to reload the
+cache line.
+
+By default, @option{--param destructive-interference-size} and
+@option{--param constructive-interference-size} are set based on the
+current @option{-mtune} option, typically to the L1 cache line size
+for the particular target CPU, sometimes to a range if tuning for a
+generic target. So all translation units that depend on ABI
+compatibility for the use of these variables must be compiled with
+the same @option{-mtune} (or @option{-mcpu}).
+
+If ABI stability is important, such as if the use is in a header for a
+library, you should probably not use the hardware interference size
+variables at all. Alternatively, you can force a particular value
+with @option{--param}.
+
+If you are confident that your use of the variable does not affect ABI
+outside a single build of your project, you can turn off the warning
+with @option{-Wno-interference-size}.
+
@item -Wint-in-bool-context
@opindex Wint-in-bool-context
@opindex Wno-int-in-bool-context
@@ -13938,6 +13975,34 @@ prefetch hints can be issued for any constant stride.
This setting is only useful for strides that are known and constant.
+@item destructive-interference-size
+@item constructive-interference-size
+The values for the C++17 variables
+@code{std::hardware_destructive_interference_size} and
+@code{std::hardware_constructive_interference_size}. The destructive
+interference size is the minimum recommended offset between two
+independent concurrently-accessed objects; the constructive
+interference size is the maximum recommended size of contiguous memory
+accessed together. Typically both will be the size of an L1 cache
+line for the target, in bytes. For a generic target covering a range of L1
+cache line sizes, typically the constructive interference size will be
+the small end of the range and the destructive size will be the large
+end.
+
+The destructive interference size is intended to be used for layout,
+and thus has ABI impact. The default value is not expected to be
+stable, and on some targets varies with @option{-mtune}, so use of
+this variable in a context where ABI stability is important, such as
+the public interface of a library, is strongly discouraged; if it is
+used in that context, users can stabilize the value using this
+option.
+
+The constructive interference size is less sensitive, as it is
+typically only used in a @samp{static_assert} to make sure that a type
+fits within a cache line.
+
+See also @option{-Winterference-size}.
+
@item loop-interchange-max-num-stmts
The maximum number of stmts in a loop to be interchanged.
diff --git a/gcc/params.opt b/gcc/params.opt
index 3a701e22c46..658ca028851 100644
--- a/gcc/params.opt
+++ b/gcc/params.opt
@@ -361,6 +361,22 @@ The maximum code size growth ratio when expanding into a jump table (in percent)
Common Joined UInteger Var(param_l1_cache_line_size) Init(32) Param Optimization
The size of L1 cache line.
+-param=destructive-interference-size=
+Common Joined UInteger Var(param_destruct_interfere_size) Init(0) Param Optimization
+The minimum recommended offset between two concurrently-accessed objects to
+avoid additional performance degradation due to contention introduced by the
+implementation. Typically the L1 cache line size, but can be larger to
+accommodate a variety of target processors with different cache line sizes.
+C++17 code might use this value in structure layout, but is strongly
+discouraged from doing so in public ABIs.
+
+-param=constructive-interference-size=
+Common Joined UInteger Var(param_construct_interfere_size) Init(0) Param Optimization
+The maximum recommended size of contiguous memory occupied by two objects
+accessed with temporal locality by concurrent threads. Typically the L1 cache
+line size, but can be smaller to accommodate a variety of target processors with
+different cache line sizes.
+
-param=l1-cache-size=
Common Joined UInteger Var(param_l1_cache_size) Init(64) Param Optimization
The size of L1 cache.
diff --git a/gcc/testsuite/g++.dg/warn/Winterference-2.C b/gcc/testsuite/g++.dg/warn/Winterference-2.C
new file mode 100644
index 00000000000..2af75c63f83
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference-2.C
@@ -0,0 +1,14 @@
+// { dg-do compile { target c++20 } }
+// { dg-additional-options -fmodules-ts }
+
+module ;
+
+#include <new>
+
+export module foo;
+
+export {
+ struct A {
+ alignas(std::hardware_destructive_interference_size) int x; // { dg-warning Winterference-size }
+ };
+}
diff --git a/gcc/testsuite/g++.dg/warn/Winterference.C b/gcc/testsuite/g++.dg/warn/Winterference.C
new file mode 100644
index 00000000000..57c001bc032
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference.C
@@ -0,0 +1,6 @@
+// Test that we warn about use of std::hardware_destructive_interference_size
+// in a header.
+// { dg-do compile { target c++17 } }
+
+// { dg-warning Winterference-size "" { target *-*-* } 0 }
+#include "Winterference.H"
diff --git a/gcc/testsuite/g++.dg/warn/Winterference.H b/gcc/testsuite/g++.dg/warn/Winterference.H
new file mode 100644
index 00000000000..36f0ad5f6d1
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference.H
@@ -0,0 +1,7 @@
+#include <new>
+
+struct A
+{
+ alignas(std::hardware_destructive_interference_size) int i;
+ alignas(std::hardware_destructive_interference_size) int j;
+};
diff --git a/gcc/testsuite/g++.target/aarch64/interference.C b/gcc/testsuite/g++.target/aarch64/interference.C
new file mode 100644
index 00000000000..0fc01655223
--- /dev/null
+++ b/gcc/testsuite/g++.target/aarch64/interference.C
@@ -0,0 +1,9 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// Most AArch64 CPUs have an L1 cache line size of 64, but some recent ones use
+// 128 or even 256.
+static_assert(std::hardware_destructive_interference_size == 256);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/gcc/testsuite/g++.target/arm/interference.C b/gcc/testsuite/g++.target/arm/interference.C
new file mode 100644
index 00000000000..34fe8a52bff
--- /dev/null
+++ b/gcc/testsuite/g++.target/arm/interference.C
@@ -0,0 +1,9 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// Recent ARM CPUs have a cache line size of 64. Older ones have
+// a size of 32, but I guess they're old enough that we don't care?
+static_assert(std::hardware_destructive_interference_size == 64);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/gcc/testsuite/g++.target/i386/interference.C b/gcc/testsuite/g++.target/i386/interference.C
new file mode 100644
index 00000000000..c7b910e3ada
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/interference.C
@@ -0,0 +1,8 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// It is generally agreed that these are the right values for all x86.
+static_assert(std::hardware_destructive_interference_size == 64);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/libstdc++-v3/include/std/version b/libstdc++-v3/include/std/version
index f950bf0f0db..f41004b5911 100644
--- a/libstdc++-v3/include/std/version
+++ b/libstdc++-v3/include/std/version
@@ -140,6 +140,9 @@
#define __cpp_lib_filesystem 201703
#define __cpp_lib_gcd 201606
#define __cpp_lib_gcd_lcm 201606
+#ifdef __GCC_DESTRUCTIVE_SIZE
+# define __cpp_lib_hardware_interference_size 201703L
+#endif
#define __cpp_lib_hypot 201603
#define __cpp_lib_invoke 201411L
#define __cpp_lib_lcm 201606
diff --git a/libstdc++-v3/libsupc++/new b/libstdc++-v3/libsupc++/new
index 3349b13fd1b..7bc67a6cb02 100644
--- a/libstdc++-v3/libsupc++/new
+++ b/libstdc++-v3/libsupc++/new
@@ -183,9 +183,9 @@ inline void operator delete[](void*, void*) _GLIBCXX_USE_NOEXCEPT { }
} // extern "C++"
#if __cplusplus >= 201703L
-#ifdef _GLIBCXX_HAVE_BUILTIN_LAUNDER
namespace std
{
+#ifdef _GLIBCXX_HAVE_BUILTIN_LAUNDER
#define __cpp_lib_launder 201606
/// Pointer optimization barrier [ptr.launder]
template<typename _Tp>
@@ -205,8 +205,14 @@ namespace std
void launder(const void*) = delete;
void launder(volatile void*) = delete;
void launder(const volatile void*) = delete;
-}
#endif // _GLIBCXX_HAVE_BUILTIN_LAUNDER
+
+#ifdef __GCC_DESTRUCTIVE_SIZE
+# define __cpp_lib_hardware_interference_size 201703L
+ inline constexpr size_t hardware_destructive_interference_size = __GCC_DESTRUCTIVE_SIZE;
+ inline constexpr size_t hardware_constructive_interference_size = __GCC_CONSTRUCTIVE_SIZE;
+#endif // __GCC_DESTRUCTIVE_SIZE
+}
#endif // C++17
#if __cplusplus > 201703L
</cut>
3 years, 9 months
- 1
- 0
[TCWG CI] Regression caused by gcc:76b75018b3d053a890ebe155e47814de14b3c9fb
by ci_notify＠linaro.org
Identified regression caused by *gcc:76b75018b3d053a890ebe155e47814de14b3c9fb*:
commit 76b75018b3d053a890ebe155e47814de14b3c9fb
Author: Jason Merrill <jason(a)redhat.com>
c++: implement C++17 hardware interference size
Results regressed to (for first_bad == 76b75018b3d053a890ebe155e47814de14b3c9fb)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# First few build errors in logs:
from (for last_good == 8ea292591e42aa4d52b4b7a00b86335bfd2e2e85)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# build_abe gcc:
2
# build_abe linux:
4
# build_abe glibc:
5
# build_abe gdb:
6
This commit has regressed these CI configurations:
- tcwg_gnu_native_build/master-arm
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/2/artifac…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/2/artifac…
Even more details: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/2/artifac…
Reproduce builds:
<cut>
mkdir investigate-gcc-76b75018b3d053a890ebe155e47814de14b3c9fb
cd investigate-gcc-76b75018b3d053a890ebe155e47814de14b3c9fb
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/2/artifac… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/2/artifac… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/2/artifac… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 76b75018b3d053a890ebe155e47814de14b3c9fb
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 8ea292591e42aa4d52b4b7a00b86335bfd2e2e85
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 76b75018b3d053a890ebe155e47814de14b3c9fb
Author: Jason Merrill <jason(a)redhat.com>
Date: Thu Jul 15 15:30:17 2021 -0400
c++: implement C++17 hardware interference size
The last missing piece of the C++17 standard library is the hardware
intereference size constants. Much of the delay in implementing these has
been due to uncertainty about what the right values are, and even whether
there is a single constant value that is suitable; the destructive
interference size is intended to be used in structure layout, so program
ABIs will depend on it.
In principle, both of these values should be the same as the target's L1
cache line size. When compiling for a generic target that is intended to
support a range of target CPUs with different cache line sizes, the
constructive size should probably be the minimum size, and the destructive
size the maximum, unless you are constrained by ABI compatibility with
previous code.
From discussion on gcc-patches, I've come to the conclusion that the
solution to the difficulty of choosing stable values is to give up on it,
and instead encourage only uses where ABI stability is unimportant: in
particular, uses where the ABI is shared at most between translation units
built at the same time with the same flags.
To that end, I've added a warning for any use of the constant value of
std::hardware_destructive_interference_size in a header or module export.
Appropriate uses within a project can disable the warning.
A previous iteration of this patch included an -finterference-tune flag to
make the value vary with -mtune; this iteration makes that the default
behavior, which should be appropriate for all reasonable uses of the
variable. The previous default of "stable-ish" seems to me likely to have
been more of an attractive nuisance; since we can't promise actual
stability, we should instead make proper uses more convenient.
JF Bastien's implementation proposal is summarized at
https://github.com/itanium-cxx-abi/cxx-abi/issues/74
I implement this by adding new --params for the two sizes. Targets can
override these values in targetm.target_option.override() to support a range
of values for the generic target; otherwise, both will default to the L1
cache line size.
64 bytes still seems correct for all x86.
I'm not sure why he proposed 64/64 for generic 32-bit ARM, since the Cortex
A9 has a 32-byte cache line, so I'd think 32/64 would make more sense.
He proposed 64/128 for generic AArch64, but since the A64FX now has a 256B
cache line, I've changed that to 64/256.
Other arch maintainers are invited to set ranges for their generic targets
if that seems better than using the default cache line size for both values.
With the above choice to reject stability as a goal, getting these values
"right" is now just a matter of what we want the default optimization to be,
and we can feel free to adjust them as CPUs with different cache lines
become more and less common.
gcc/ChangeLog:
* params.opt: Add destructive-interference-size and
constructive-interference-size.
* doc/invoke.texi: Document them.
* config/aarch64/aarch64.c (aarch64_override_options_internal):
Set them.
* config/arm/arm.c (arm_option_override): Set them.
* config/i386/i386-options.c (ix86_option_override_internal):
Set them.
gcc/c-family/ChangeLog:
* c.opt: Add -Winterference-size.
* c-cppbuiltin.c (cpp_atomic_builtins): Add __GCC_DESTRUCTIVE_SIZE
and __GCC_CONSTRUCTIVE_SIZE.
gcc/cp/ChangeLog:
* constexpr.c (maybe_warn_about_constant_value):
Complain about std::hardware_destructive_interference_size.
(cxx_eval_constant_expression): Call it.
* decl.c (cxx_init_decl_processing): Check
--param *-interference-size values.
libstdc++-v3/ChangeLog:
* include/std/version: Define __cpp_lib_hardware_interference_size.
* libsupc++/new: Define hardware interference size variables.
gcc/testsuite/ChangeLog:
* g++.dg/warn/Winterference.H: New file.
* g++.dg/warn/Winterference.C: New test.
* g++.target/aarch64/interference.C: New test.
* g++.target/arm/interference.C: New test.
* g++.target/i386/interference.C: New test.
---
gcc/c-family/c-cppbuiltin.c | 14 ++++++
gcc/c-family/c.opt | 5 ++
gcc/config/aarch64/aarch64.c | 22 +++++++++
gcc/config/arm/arm.c | 22 +++++++++
gcc/config/i386/i386-options.c | 6 +++
gcc/cp/constexpr.c | 33 +++++++++++++
gcc/cp/decl.c | 32 ++++++++++++
gcc/doc/invoke.texi | 65 +++++++++++++++++++++++++
gcc/params.opt | 16 ++++++
gcc/testsuite/g++.dg/warn/Winterference-2.C | 14 ++++++
gcc/testsuite/g++.dg/warn/Winterference.C | 6 +++
gcc/testsuite/g++.dg/warn/Winterference.H | 7 +++
gcc/testsuite/g++.target/aarch64/interference.C | 9 ++++
gcc/testsuite/g++.target/arm/interference.C | 9 ++++
gcc/testsuite/g++.target/i386/interference.C | 8 +++
libstdc++-v3/include/std/version | 3 ++
libstdc++-v3/libsupc++/new | 10 +++-
17 files changed, 279 insertions(+), 2 deletions(-)
diff --git a/gcc/c-family/c-cppbuiltin.c b/gcc/c-family/c-cppbuiltin.c
index 48cbefd8bf8..ce88e707127 100644
--- a/gcc/c-family/c-cppbuiltin.c
+++ b/gcc/c-family/c-cppbuiltin.c
@@ -741,6 +741,20 @@ cpp_atomic_builtins (cpp_reader *pfile)
builtin_define_with_int_value ("__GCC_ATOMIC_TEST_AND_SET_TRUEVAL",
targetm.atomic_test_and_set_trueval);
+ /* Macros for C++17 hardware interference size constants. Either both or
+ neither should be set. */
+ gcc_assert (!param_destruct_interfere_size
+ == !param_construct_interfere_size);
+ if (param_destruct_interfere_size)
+ {
+ /* FIXME The way of communicating these values to the library should be
+ part of the C++ ABI, whether macro or builtin. */
+ builtin_define_with_int_value ("__GCC_DESTRUCTIVE_SIZE",
+ param_destruct_interfere_size);
+ builtin_define_with_int_value ("__GCC_CONSTRUCTIVE_SIZE",
+ param_construct_interfere_size);
+ }
+
/* ptr_type_node can't be used here since ptr_mode is only set when
toplev calls backend_init which is not done with -E or pch. */
psize = POINTER_SIZE_UNITS;
diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
index c5fe90003f2..9c151d19870 100644
--- a/gcc/c-family/c.opt
+++ b/gcc/c-family/c.opt
@@ -722,6 +722,11 @@ Winit-list-lifetime
C++ ObjC++ Var(warn_init_list) Warning Init(1)
Warn about uses of std::initializer_list that can result in dangling pointers.
+Winterference-size
+C++ ObjC++ Var(warn_interference_size) Warning Init(1)
+Warn about nonsensical values of --param destructive-interference-size or
+constructive-interference-size.
+
Wimplicit
C ObjC Var(warn_implicit) Warning LangEnabledBy(C ObjC,Wall)
Warn about implicit declarations.
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 30d9a0b7a3d..36519ccc5a5 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -16540,6 +16540,28 @@ aarch64_override_options_internal (struct gcc_options *opts)
SET_OPTION_IF_UNSET (opts, &global_options_set,
param_l1_cache_line_size,
aarch64_tune_params.prefetch->l1_cache_line_size);
+
+ if (aarch64_tune_params.prefetch->l1_cache_line_size >= 0)
+ {
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_destruct_interfere_size,
+ aarch64_tune_params.prefetch->l1_cache_line_size);
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_construct_interfere_size,
+ aarch64_tune_params.prefetch->l1_cache_line_size);
+ }
+ else
+ {
+ /* For a generic AArch64 target, cover the current range of cache line
+ sizes. */
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_destruct_interfere_size,
+ 256);
+ SET_OPTION_IF_UNSET (opts, &global_options_set,
+ param_construct_interfere_size,
+ 64);
+ }
+
if (aarch64_tune_params.prefetch->l2_cache_size >= 0)
SET_OPTION_IF_UNSET (opts, &global_options_set,
param_l2_cache_size,
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index f1e628253d0..6c6e77fab66 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -3669,6 +3669,28 @@ arm_option_override (void)
SET_OPTION_IF_UNSET (&global_options, &global_options_set,
param_l1_cache_line_size,
current_tune->prefetch.l1_cache_line_size);
+ if (current_tune->prefetch.l1_cache_line_size >= 0)
+ {
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size,
+ current_tune->prefetch.l1_cache_line_size);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size,
+ current_tune->prefetch.l1_cache_line_size);
+ }
+ else
+ {
+ /* For a generic ARM target, JF Bastien proposed using 64 for both. */
+ /* ??? Cortex A9 has a 32-byte cache line, so why not 32 for
+ constructive? */
+ /* More recent Cortex chips have a 64-byte cache line, but are marked
+ ARM_PREFETCH_NOT_BENEFICIAL, so they get these defaults. */
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size, 64);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size, 64);
+ }
+
if (current_tune->prefetch.l1_cache_size >= 0)
SET_OPTION_IF_UNSET (&global_options, &global_options_set,
param_l1_cache_size,
diff --git a/gcc/config/i386/i386-options.c b/gcc/config/i386/i386-options.c
index 2cb87cedec0..c0006b3674b 100644
--- a/gcc/config/i386/i386-options.c
+++ b/gcc/config/i386/i386-options.c
@@ -2579,6 +2579,12 @@ ix86_option_override_internal (bool main_args_p,
SET_OPTION_IF_UNSET (opts, opts_set, param_l2_cache_size,
ix86_tune_cost->l2_cache_size);
+ /* 64B is the accepted value for these for all x86. */
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_destruct_interfere_size, 64);
+ SET_OPTION_IF_UNSET (&global_options, &global_options_set,
+ param_construct_interfere_size, 64);
+
/* Enable sw prefetching at -O3 for CPUS that prefetching is helpful. */
if (opts->x_flag_prefetch_loop_arrays < 0
&& HAVE_prefetch
diff --git a/gcc/cp/constexpr.c b/gcc/cp/constexpr.c
index 7772fe62d95..0c2498aee22 100644
--- a/gcc/cp/constexpr.c
+++ b/gcc/cp/constexpr.c
@@ -6075,6 +6075,37 @@ inline_asm_in_constexpr_error (location_t loc)
"%<constexpr%> function in C++20");
}
+/* We're getting the constant value of DECL in a manifestly constant-evaluated
+ context; maybe complain about that. */
+
+static void
+maybe_warn_about_constant_value (location_t loc, tree decl)
+{
+ static bool explained = false;
+ if (cxx_dialect >= cxx17
+ && warn_interference_size
+ && !global_options_set.x_param_destruct_interfere_size
+ && DECL_CONTEXT (decl) == std_node
+ && id_equal (DECL_NAME (decl), "hardware_destructive_interference_size")
+ && (LOCATION_FILE (input_location) != main_input_filename
+ || module_exporting_p ())
+ && warning_at (loc, OPT_Winterference_size, "use of %qD", decl)
+ && !explained)
+ {
+ explained = true;
+ inform (loc, "its value can vary between compiler versions or "
+ "with different %<-mtune%> or %<-mcpu%> flags");
+ inform (loc, "if this use is part of a public ABI, change it to "
+ "instead use a constant variable you define");
+ inform (loc, "the default value for the current CPU tuning "
+ "is %d bytes", param_destruct_interfere_size);
+ inform (loc, "you can stabilize this value with %<--param "
+ "hardware_destructive_interference_size=%d%>, or disable "
+ "this warning with %<-Wno-interference-size%>",
+ param_destruct_interfere_size);
+ }
+}
+
/* Attempt to reduce the expression T to a constant value.
On failure, issue diagnostic and return error_mark_node. */
/* FIXME unify with c_fully_fold */
@@ -6219,6 +6250,8 @@ cxx_eval_constant_expression (const constexpr_ctx *ctx, tree t,
r = *p;
break;
}
+ if (ctx->manifestly_const_eval)
+ maybe_warn_about_constant_value (loc, t);
if (COMPLETE_TYPE_P (TREE_TYPE (t))
&& is_really_empty_class (TREE_TYPE (t), /*ignore_vptr*/false))
{
diff --git a/gcc/cp/decl.c b/gcc/cp/decl.c
index bce62ad202a..c2065027369 100644
--- a/gcc/cp/decl.c
+++ b/gcc/cp/decl.c
@@ -4752,6 +4752,38 @@ cxx_init_decl_processing (void)
/* Show we use EH for cleanups. */
if (flag_exceptions)
using_eh_for_cleanups ();
+
+ /* Check that the hardware interference sizes are at least
+ alignof(max_align_t), as required by the standard. */
+ const int max_align = max_align_t_align () / BITS_PER_UNIT;
+ if (param_destruct_interfere_size)
+ {
+ if (param_destruct_interfere_size < max_align)
+ error ("%<--param destructive-interference-size=%d%> is less than "
+ "%d", param_destruct_interfere_size, max_align);
+ else if (param_destruct_interfere_size < param_l1_cache_line_size)
+ warning (OPT_Winterference_size,
+ "%<--param destructive-interference-size=%d%> "
+ "is less than %<--param l1-cache-line-size=%d%>",
+ param_destruct_interfere_size, param_l1_cache_line_size);
+ }
+ else if (param_l1_cache_line_size >= max_align)
+ param_destruct_interfere_size = param_l1_cache_line_size;
+ /* else leave it unset. */
+
+ if (param_construct_interfere_size)
+ {
+ if (param_construct_interfere_size < max_align)
+ error ("%<--param constructive-interference-size=%d%> is less than "
+ "%d", param_construct_interfere_size, max_align);
+ else if (param_construct_interfere_size > param_l1_cache_line_size)
+ warning (OPT_Winterference_size,
+ "%<--param constructive-interference-size=%d%> "
+ "is greater than %<--param l1-cache-line-size=%d%>",
+ param_construct_interfere_size, param_l1_cache_line_size);
+ }
+ else if (param_l1_cache_line_size >= max_align)
+ param_construct_interfere_size = param_l1_cache_line_size;
}
/* Enter an abi node in global-module context. returns a cookie to
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 23cc68f92b5..78cfc100ac2 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -9018,6 +9018,43 @@ that has already been done in the current function. Therefore,
seemingly insignificant changes in the source program can cause the
warnings produced by @option{-Winline} to appear or disappear.
+@item -Winterference-size
+@opindex Winterference-size
+Warn about use of C++17 @code{std::hardware_destructive_interference_size}
+without specifying its value with @option{--param destructive-interference-size}.
+Also warn about questionable values for that option.
+
+This variable is intended to be used for controlling class layout, to
+avoid false sharing in concurrent code:
+
+@smallexample
+struct independent_fields @{
+ alignas(std::hardware_destructive_interference_size) std::atomic<int> one;
+ alignas(std::hardware_destructive_interference_size) std::atomic<int> two;
+@};
+@end smallexample
+
+Here @samp{one} and @samp{two} are intended to be far enough apart
+that stores to one won't require accesses to the other to reload the
+cache line.
+
+By default, @option{--param destructive-interference-size} and
+@option{--param constructive-interference-size} are set based on the
+current @option{-mtune} option, typically to the L1 cache line size
+for the particular target CPU, sometimes to a range if tuning for a
+generic target. So all translation units that depend on ABI
+compatibility for the use of these variables must be compiled with
+the same @option{-mtune} (or @option{-mcpu}).
+
+If ABI stability is important, such as if the use is in a header for a
+library, you should probably not use the hardware interference size
+variables at all. Alternatively, you can force a particular value
+with @option{--param}.
+
+If you are confident that your use of the variable does not affect ABI
+outside a single build of your project, you can turn off the warning
+with @option{-Wno-interference-size}.
+
@item -Wint-in-bool-context
@opindex Wint-in-bool-context
@opindex Wno-int-in-bool-context
@@ -13938,6 +13975,34 @@ prefetch hints can be issued for any constant stride.
This setting is only useful for strides that are known and constant.
+@item destructive-interference-size
+@item constructive-interference-size
+The values for the C++17 variables
+@code{std::hardware_destructive_interference_size} and
+@code{std::hardware_constructive_interference_size}. The destructive
+interference size is the minimum recommended offset between two
+independent concurrently-accessed objects; the constructive
+interference size is the maximum recommended size of contiguous memory
+accessed together. Typically both will be the size of an L1 cache
+line for the target, in bytes. For a generic target covering a range of L1
+cache line sizes, typically the constructive interference size will be
+the small end of the range and the destructive size will be the large
+end.
+
+The destructive interference size is intended to be used for layout,
+and thus has ABI impact. The default value is not expected to be
+stable, and on some targets varies with @option{-mtune}, so use of
+this variable in a context where ABI stability is important, such as
+the public interface of a library, is strongly discouraged; if it is
+used in that context, users can stabilize the value using this
+option.
+
+The constructive interference size is less sensitive, as it is
+typically only used in a @samp{static_assert} to make sure that a type
+fits within a cache line.
+
+See also @option{-Winterference-size}.
+
@item loop-interchange-max-num-stmts
The maximum number of stmts in a loop to be interchanged.
diff --git a/gcc/params.opt b/gcc/params.opt
index 3a701e22c46..658ca028851 100644
--- a/gcc/params.opt
+++ b/gcc/params.opt
@@ -361,6 +361,22 @@ The maximum code size growth ratio when expanding into a jump table (in percent)
Common Joined UInteger Var(param_l1_cache_line_size) Init(32) Param Optimization
The size of L1 cache line.
+-param=destructive-interference-size=
+Common Joined UInteger Var(param_destruct_interfere_size) Init(0) Param Optimization
+The minimum recommended offset between two concurrently-accessed objects to
+avoid additional performance degradation due to contention introduced by the
+implementation. Typically the L1 cache line size, but can be larger to
+accommodate a variety of target processors with different cache line sizes.
+C++17 code might use this value in structure layout, but is strongly
+discouraged from doing so in public ABIs.
+
+-param=constructive-interference-size=
+Common Joined UInteger Var(param_construct_interfere_size) Init(0) Param Optimization
+The maximum recommended size of contiguous memory occupied by two objects
+accessed with temporal locality by concurrent threads. Typically the L1 cache
+line size, but can be smaller to accommodate a variety of target processors with
+different cache line sizes.
+
-param=l1-cache-size=
Common Joined UInteger Var(param_l1_cache_size) Init(64) Param Optimization
The size of L1 cache.
diff --git a/gcc/testsuite/g++.dg/warn/Winterference-2.C b/gcc/testsuite/g++.dg/warn/Winterference-2.C
new file mode 100644
index 00000000000..2af75c63f83
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference-2.C
@@ -0,0 +1,14 @@
+// { dg-do compile { target c++20 } }
+// { dg-additional-options -fmodules-ts }
+
+module ;
+
+#include <new>
+
+export module foo;
+
+export {
+ struct A {
+ alignas(std::hardware_destructive_interference_size) int x; // { dg-warning Winterference-size }
+ };
+}
diff --git a/gcc/testsuite/g++.dg/warn/Winterference.C b/gcc/testsuite/g++.dg/warn/Winterference.C
new file mode 100644
index 00000000000..57c001bc032
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference.C
@@ -0,0 +1,6 @@
+// Test that we warn about use of std::hardware_destructive_interference_size
+// in a header.
+// { dg-do compile { target c++17 } }
+
+// { dg-warning Winterference-size "" { target *-*-* } 0 }
+#include "Winterference.H"
diff --git a/gcc/testsuite/g++.dg/warn/Winterference.H b/gcc/testsuite/g++.dg/warn/Winterference.H
new file mode 100644
index 00000000000..36f0ad5f6d1
--- /dev/null
+++ b/gcc/testsuite/g++.dg/warn/Winterference.H
@@ -0,0 +1,7 @@
+#include <new>
+
+struct A
+{
+ alignas(std::hardware_destructive_interference_size) int i;
+ alignas(std::hardware_destructive_interference_size) int j;
+};
diff --git a/gcc/testsuite/g++.target/aarch64/interference.C b/gcc/testsuite/g++.target/aarch64/interference.C
new file mode 100644
index 00000000000..0fc01655223
--- /dev/null
+++ b/gcc/testsuite/g++.target/aarch64/interference.C
@@ -0,0 +1,9 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// Most AArch64 CPUs have an L1 cache line size of 64, but some recent ones use
+// 128 or even 256.
+static_assert(std::hardware_destructive_interference_size == 256);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/gcc/testsuite/g++.target/arm/interference.C b/gcc/testsuite/g++.target/arm/interference.C
new file mode 100644
index 00000000000..34fe8a52bff
--- /dev/null
+++ b/gcc/testsuite/g++.target/arm/interference.C
@@ -0,0 +1,9 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// Recent ARM CPUs have a cache line size of 64. Older ones have
+// a size of 32, but I guess they're old enough that we don't care?
+static_assert(std::hardware_destructive_interference_size == 64);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/gcc/testsuite/g++.target/i386/interference.C b/gcc/testsuite/g++.target/i386/interference.C
new file mode 100644
index 00000000000..c7b910e3ada
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/interference.C
@@ -0,0 +1,8 @@
+// Test C++17 hardware interference size constants
+// { dg-do compile { target c++17 } }
+
+#include <new>
+
+// It is generally agreed that these are the right values for all x86.
+static_assert(std::hardware_destructive_interference_size == 64);
+static_assert(std::hardware_constructive_interference_size == 64);
diff --git a/libstdc++-v3/include/std/version b/libstdc++-v3/include/std/version
index f950bf0f0db..f41004b5911 100644
--- a/libstdc++-v3/include/std/version
+++ b/libstdc++-v3/include/std/version
@@ -140,6 +140,9 @@
#define __cpp_lib_filesystem 201703
#define __cpp_lib_gcd 201606
#define __cpp_lib_gcd_lcm 201606
+#ifdef __GCC_DESTRUCTIVE_SIZE
+# define __cpp_lib_hardware_interference_size 201703L
+#endif
#define __cpp_lib_hypot 201603
#define __cpp_lib_invoke 201411L
#define __cpp_lib_lcm 201606
diff --git a/libstdc++-v3/libsupc++/new b/libstdc++-v3/libsupc++/new
index 3349b13fd1b..7bc67a6cb02 100644
--- a/libstdc++-v3/libsupc++/new
+++ b/libstdc++-v3/libsupc++/new
@@ -183,9 +183,9 @@ inline void operator delete[](void*, void*) _GLIBCXX_USE_NOEXCEPT { }
} // extern "C++"
#if __cplusplus >= 201703L
-#ifdef _GLIBCXX_HAVE_BUILTIN_LAUNDER
namespace std
{
+#ifdef _GLIBCXX_HAVE_BUILTIN_LAUNDER
#define __cpp_lib_launder 201606
/// Pointer optimization barrier [ptr.launder]
template<typename _Tp>
@@ -205,8 +205,14 @@ namespace std
void launder(const void*) = delete;
void launder(volatile void*) = delete;
void launder(const volatile void*) = delete;
-}
#endif // _GLIBCXX_HAVE_BUILTIN_LAUNDER
+
+#ifdef __GCC_DESTRUCTIVE_SIZE
+# define __cpp_lib_hardware_interference_size 201703L
+ inline constexpr size_t hardware_destructive_interference_size = __GCC_DESTRUCTIVE_SIZE;
+ inline constexpr size_t hardware_constructive_interference_size = __GCC_CONSTRUCTIVE_SIZE;
+#endif // __GCC_DESTRUCTIVE_SIZE
+}
#endif // C++17
#if __cplusplus > 201703L
</cut>
3 years, 9 months
- 1
- 0
[TCWG CI] Regression caused by gcc:5485bbebb3679245dd4bc7c149bbc940f8b2e632
by ci_notify＠linaro.org
Identified regression caused by *gcc:5485bbebb3679245dd4bc7c149bbc940f8b2e632*:
commit 5485bbebb3679245dd4bc7c149bbc940f8b2e632
Author: Aldy Hernandez <aldyh(a)redhat.com>
Refactor jump_thread_path_registry.
Results regressed to (for first_bad == 5485bbebb3679245dd4bc7c149bbc940f8b2e632)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -Os artifacts/build-5485bbebb3679245dd4bc7c149bbc940f8b2e632/results_id:
1
# 458.sjeng,sjeng_base.default regressed by 104
from (for last_good == 3fca63b0b6faf6a30ed735b86b8eb59944701fc1)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -Os artifacts/build-3fca63b0b6faf6a30ed735b86b8eb59944701fc1/results_id:
1
This commit has regressed these CI configurations:
- tcwg_bmk_gnu_apm/gnu-master-aarch64-spec2k6-Os
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa…
Even more details: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa…
Reproduce builds:
<cut>
mkdir investigate-gcc-5485bbebb3679245dd4bc7c149bbc940f8b2e632
cd investigate-gcc-5485bbebb3679245dd4bc7c149bbc940f8b2e632
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 5485bbebb3679245dd4bc7c149bbc940f8b2e632
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 3fca63b0b6faf6a30ed735b86b8eb59944701fc1
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 5485bbebb3679245dd4bc7c149bbc940f8b2e632
Author: Aldy Hernandez <aldyh(a)redhat.com>
Date: Sat Sep 11 09:37:39 2021 +0200
Refactor jump_thread_path_registry.
In an attempt to refactor thread_through_all_blocks(), I've realized
that there is a mess of code dealing with coexisting forward and
backward thread types. However, this is an impossible scenario, as
the registry contains either forward/old-style threads, or backward
threads (EDGE_FSM_THREADs), never both.
The fact that both types of threads cannot coexist, simplifies the
code considerably. For that matter, it splits things up nicely
because there are some common bits that can go into a base class, and
some differing code that can go into derived classes.
Diving things in this way makes it very obvious which parts belong in
the old-style copier and which parts belong to the generic copier.
Doing all this provided some nice cleanups, as well as fixing a latent
bug in adjust_paths_after_duplication.
The diff is somewhat hard to read, so perhaps looking at the final
output would be easier.
A general overview of what this patch achieves can be seen by just
looking at this simplified class layout:
// Abstract class for the jump thread registry.
class jt_path_registry
{
public:
jt_path_registry ();
virtual ~jt_path_registry ();
bool register_jump_thread (vec<jump_thread_edge *> *);
bool thread_through_all_blocks (bool peel_loop_headers);
jump_thread_edge *allocate_thread_edge (edge e, jump_thread_edge_type t);
vec<jump_thread_edge *> *allocate_thread_path ();
protected:
vec<vec<jump_thread_edge *> *> m_paths;
unsigned long m_num_threaded_edges;
private:
virtual bool update_cfg (bool peel_loop_headers) = 0;
};
// Forward threader path registry using a custom BB copier.
class fwd_jt_path_registry : public jt_path_registry
{
public:
fwd_jt_path_registry ();
~fwd_jt_path_registry ();
void remove_jump_threads_including (edge);
private:
bool update_cfg (bool peel_loop_headers) override;
void mark_threaded_blocks (bitmap threaded_blocks);
bool thread_block_1 (basic_block, bool noloop_only, bool joiners);
bool thread_block (basic_block, bool noloop_only);
bool thread_through_loop_header (class loop *loop,
bool may_peel_loop_headers);
class redirection_data *lookup_redirection_data (edge e, enum insert_option);
hash_table<struct removed_edges> *m_removed_edges;
hash_table<redirection_data> *m_redirection_data;
};
// Backward threader path registry using a generic BB copier.
class back_jt_path_registry : public jt_path_registry
{
private:
bool update_cfg (bool peel_loop_headers) override;
void adjust_paths_after_duplication (unsigned curr_path_num);
bool duplicate_thread_path (edge entry, edge exit, basic_block *region,
unsigned n_region, unsigned current_path_no);
bool rewire_first_differing_edge (unsigned path_num, unsigned edge_num);
};
That is, the forward and backward bits have been completely split,
while deriving from a base class for the common functionality.
Most everything is mechanical, but there are a few gotchas:
a) back_jt_path_registry::update_cfg(), which contains the backward
threading specific bits, is rather simple, since most of the code in
the original thread_through_all_blocks() only applied to the forward
threader: removed edges, mark_threaded_blocks,
thread_through_loop_header, the copy tables (*).
(*) The back threader has its own copy tables in
duplicate_thread_path.
b) In some cases, adjust_paths_after_duplication() was commoning out
so many blocks that it was removing the initial EDGE_FSM_THREAD
marker. I've fixed this.
c) AFAICT, when run from the forward threader,
thread_through_all_blocks() attempts to remove threads starting with
an edge already seen, but it would never see anything because the loop
doing the checking only has a visited_starting_edges.contains(), and
no corresponding visited_starting_edges.add(). The add() method in
thread_through_all_blocks belongs to the backward threading bits, and
as I've explained, both types cannot coexist. I've removed the checks
in the forward bits since they don't appear to do anything. If this
was an oversight, and we want to avoid threading already seen edges in
the forward threader, I can move this functionality to the base class.
Ultimately I would like to move all the registry code to
tree-ssa-threadregistry.*. I've avoided this in this patch to aid in
review.
My apologies for this longass explanation, but I want to make sure
we're covering all of our bases.
Tested on x86-64 Linux by a very tedious process of moving chunks
around, running "make check-gcc RUNTESTFLAGS=tree-ssa.exp", and
repeating ad-nauseum. And of course, by running a full bootstrap and
tests.
OK?
p.s. In a follow-up patch I will rename the confusing EDGE_FSM_THREAD
type.
gcc/ChangeLog:
* tree-ssa-threadbackward.c (class back_threader_registry): Use
back_jt_path_registry.
* tree-ssa-threadedge.c (jump_threader::jump_threader): Use
fwd_jt_path_registry.
* tree-ssa-threadedge.h (class jump_threader): Same..
* tree-ssa-threadupdate.c
(jump_thread_path_registry::jump_thread_path_registry): Rename...
(jt_path_registry::jt_path_registry): ...to this.
(jump_thread_path_registry::~jump_thread_path_registry): Rename...
(jt_path_registry::~jt_path_registry): ...this.
(fwd_jt_path_registry::fwd_jt_path_registry): New.
(fwd_jt_path_registry::~fwd_jt_path_registry): New.
(jump_thread_path_registry::allocate_thread_edge): Rename...
(jt_path_registry::allocate_thread_edge): ...to this.
(jump_thread_path_registry::allocate_thread_path): Rename...
(jt_path_registry::allocate_thread_path): ...to this.
(jump_thread_path_registry::lookup_redirection_data): Rename...
(fwd_jt_path_registry::lookup_redirection_data): ...to this.
(jump_thread_path_registry::thread_block_1): Rename...
(fwd_jt_path_registry::thread_block_1): ...to this.
(jump_thread_path_registry::thread_block): Rename...
(fwd_jt_path_registry::thread_block): ...to this.
(jt_path_registry::thread_through_loop_header): Rename...
(fwd_jt_path_registry::thread_through_loop_header): ...to this.
(jump_thread_path_registry::mark_threaded_blocks): Rename...
(fwd_jt_path_registry::mark_threaded_blocks): ...to this.
(jump_thread_path_registry::debug_path): Rename...
(jt_path_registry::debug_path): ...to this.
(jump_thread_path_registry::dump): Rename...
(jt_path_registry::debug): ...to this.
(jump_thread_path_registry::rewire_first_differing_edge): Rename...
(back_jt_path_registry::rewire_first_differing_edge): ...to this.
(jump_thread_path_registry::adjust_paths_after_duplication): Rename...
(back_jt_path_registry::adjust_paths_after_duplication): ...to this.
(jump_thread_path_registry::duplicate_thread_path): Rename...
(back_jt_path_registry::duplicate_thread_path): ...to this. Also,
drop ill-formed candidates.
(jump_thread_path_registry::remove_jump_threads_including): Rename...
(fwd_jt_path_registry::remove_jump_threads_including): ...to this.
(jt_path_registry::thread_through_all_blocks): New.
(back_jt_path_registry::update_cfg): New.
(fwd_jt_path_registry::update_cfg): New.
(jump_thread_path_registry::register_jump_thread): Rename...
(jt_path_registry::register_jump_thread): ...to this.
* tree-ssa-threadupdate.h (class jump_thread_path_registry):
Abstract to...
(class jt_path_registry): ...here.
(class fwd_jt_path_registry): New.
(class back_jt_path_registry): New.
---
gcc/tree-ssa-threadbackward.c | 2 +-
gcc/tree-ssa-threadedge.c | 2 +-
gcc/tree-ssa-threadedge.h | 2 +-
gcc/tree-ssa-threadupdate.c | 213 +++++++++++++++++++++---------------------
gcc/tree-ssa-threadupdate.h | 60 +++++++-----
5 files changed, 149 insertions(+), 130 deletions(-)
diff --git a/gcc/tree-ssa-threadbackward.c b/gcc/tree-ssa-threadbackward.c
index e72992328de..7ff5cecbdab 100644
--- a/gcc/tree-ssa-threadbackward.c
+++ b/gcc/tree-ssa-threadbackward.c
@@ -56,7 +56,7 @@ public:
bool register_path (const vec<basic_block> &, edge taken);
bool thread_through_all_blocks (bool may_peel_loop_headers);
private:
- jump_thread_path_registry m_lowlevel_registry;
+ back_jt_path_registry m_lowlevel_registry;
const int m_max_allowable_paths;
int m_threaded_paths;
};
diff --git a/gcc/tree-ssa-threadedge.c b/gcc/tree-ssa-threadedge.c
index 3c7cdc58b93..422cb89401b 100644
--- a/gcc/tree-ssa-threadedge.c
+++ b/gcc/tree-ssa-threadedge.c
@@ -71,7 +71,7 @@ jump_threader::jump_threader (jump_threader_simplifier *simplifier,
dummy_cond = gimple_build_cond (NE_EXPR, integer_zero_node,
integer_zero_node, NULL, NULL);
- m_registry = new jump_thread_path_registry ();
+ m_registry = new fwd_jt_path_registry ();
m_simplifier = simplifier;
m_state = state;
}
diff --git a/gcc/tree-ssa-threadedge.h b/gcc/tree-ssa-threadedge.h
index 0002b200d8b..18e6bd41aaa 100644
--- a/gcc/tree-ssa-threadedge.h
+++ b/gcc/tree-ssa-threadedge.h
@@ -75,7 +75,7 @@ private:
// Dummy condition to avoid creating lots of throw away statements.
gcond *dummy_cond;
- class jump_thread_path_registry *m_registry;
+ class fwd_jt_path_registry *m_registry;
jump_threader_simplifier *m_simplifier;
jt_state *m_state;
};
diff --git a/gcc/tree-ssa-threadupdate.c b/gcc/tree-ssa-threadupdate.c
index 18f16efbb7a..93538104fdf 100644
--- a/gcc/tree-ssa-threadupdate.c
+++ b/gcc/tree-ssa-threadupdate.c
@@ -167,29 +167,36 @@ jump_thread_path_allocator::allocate_thread_path ()
return new (r) vec<jump_thread_edge *> ();
}
-jump_thread_path_registry::jump_thread_path_registry ()
+jt_path_registry::jt_path_registry ()
{
m_paths.create (5);
- m_removed_edges = new hash_table<struct removed_edges> (17);
m_num_threaded_edges = 0;
- m_redirection_data = NULL;
}
-jump_thread_path_registry::~jump_thread_path_registry ()
+jt_path_registry::~jt_path_registry ()
{
m_paths.release ();
+}
+
+fwd_jt_path_registry::fwd_jt_path_registry ()
+{
+ m_removed_edges = new hash_table<struct removed_edges> (17);
+ m_redirection_data = NULL;
+}
+
+fwd_jt_path_registry::~fwd_jt_path_registry ()
+{
delete m_removed_edges;
}
jump_thread_edge *
-jump_thread_path_registry::allocate_thread_edge (edge e,
- jump_thread_edge_type t)
+jt_path_registry::allocate_thread_edge (edge e, jump_thread_edge_type t)
{
return m_allocator.allocate_thread_edge (e, t);
}
vec<jump_thread_edge *> *
-jump_thread_path_registry::allocate_thread_path ()
+jt_path_registry::allocate_thread_path ()
{
return m_allocator.allocate_thread_path ();
}
@@ -426,8 +433,7 @@ create_block_for_threading (basic_block bb,
edges associated with E in the hash table. */
redirection_data *
-jump_thread_path_registry::lookup_redirection_data (edge e,
- enum insert_option insert)
+fwd_jt_path_registry::lookup_redirection_data (edge e, insert_option insert)
{
struct redirection_data **slot;
struct redirection_data *elt;
@@ -1413,9 +1419,9 @@ redirection_block_p (basic_block bb)
If JOINERS is true, then thread through joiner blocks as well. */
bool
-jump_thread_path_registry::thread_block_1 (basic_block bb,
- bool noloop_only,
- bool joiners)
+fwd_jt_path_registry::thread_block_1 (basic_block bb,
+ bool noloop_only,
+ bool joiners)
{
/* E is an incoming edge into BB that we may or may not want to
redirect to a duplicate of BB. */
@@ -1594,7 +1600,7 @@ jump_thread_path_registry::thread_block_1 (basic_block bb,
opportunity. */
bool
-jump_thread_path_registry::thread_block (basic_block bb, bool noloop_only)
+fwd_jt_path_registry::thread_block (basic_block bb, bool noloop_only)
{
bool retval;
retval = thread_block_1 (bb, noloop_only, false);
@@ -1675,9 +1681,8 @@ determine_bb_domination_status (class loop *loop, basic_block bb)
to the inside of the loop. */
bool
-jump_thread_path_registry::thread_through_loop_header
- (class loop *loop,
- bool may_peel_loop_headers)
+fwd_jt_path_registry::thread_through_loop_header (class loop *loop,
+ bool may_peel_loop_headers)
{
basic_block header = loop->header;
edge e, tgt_edge, latch = loop_latch_edge (loop);
@@ -1932,7 +1937,7 @@ count_stmts_and_phis_in_block (basic_block bb)
hash table lookups to map from threaded edge to new target. */
void
-jump_thread_path_registry::mark_threaded_blocks (bitmap threaded_blocks)
+fwd_jt_path_registry::mark_threaded_blocks (bitmap threaded_blocks)
{
unsigned int i;
bitmap_iterator bi;
@@ -2197,7 +2202,7 @@ bb_in_bbs (basic_block bb, basic_block *bbs, int n)
}
void
-jump_thread_path_registry::debug_path (FILE *dump_file, int pathno)
+jt_path_registry::debug_path (FILE *dump_file, int pathno)
{
vec<jump_thread_edge *> *p = m_paths[pathno];
fprintf (dump_file, "path: ");
@@ -2208,7 +2213,7 @@ jump_thread_path_registry::debug_path (FILE *dump_file, int pathno)
}
void
-jump_thread_path_registry::dump ()
+jt_path_registry::debug ()
{
for (unsigned i = 0; i < m_paths.length (); ++i)
debug_path (stderr, i);
@@ -2223,8 +2228,8 @@ jump_thread_path_registry::dump ()
Returns TRUE if we were able to successfully rewire the edge. */
bool
-jump_thread_path_registry::rewire_first_differing_edge (unsigned path_num,
- unsigned edge_num)
+back_jt_path_registry::rewire_first_differing_edge (unsigned path_num,
+ unsigned edge_num)
{
vec<jump_thread_edge *> *path = m_paths[path_num];
edge &e = (*path)[edge_num]->e;
@@ -2269,11 +2274,9 @@ jump_thread_path_registry::rewire_first_differing_edge (unsigned path_num,
specifies the path that was just threaded. */
void
-jump_thread_path_registry::adjust_paths_after_duplication
- (unsigned curr_path_num)
+back_jt_path_registry::adjust_paths_after_duplication (unsigned curr_path_num)
{
vec<jump_thread_edge *> *curr_path = m_paths[curr_path_num];
- gcc_assert ((*curr_path)[0]->type == EDGE_FSM_THREAD);
if (dump_file && (dump_flags & TDF_DETAILS))
{
@@ -2347,8 +2350,16 @@ jump_thread_path_registry::adjust_paths_after_duplication
m_paths.unordered_remove (cand_path_num);
continue;
}
- /* Otherwise, just remove the redundant sub-path. */
- cand_path->block_remove (0, j);
+ if ((*cand_path)[j]->type != EDGE_FSM_THREAD)
+ {
+ /* If all the EDGE_FSM_THREADs are common, all that's
+ left is the final EDGE_NO_COPY_SRC_BLOCK. */
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file, "Dropping illformed candidate.\n");
+ }
+ else
+ /* Otherwise, just remove the redundant sub-path. */
+ cand_path->block_remove (0, j);
}
if (dump_file && (dump_flags & TDF_DETAILS))
{
@@ -2372,11 +2383,11 @@ jump_thread_path_registry::adjust_paths_after_duplication
Returns false if it is unable to copy the region, true otherwise. */
bool
-jump_thread_path_registry::duplicate_thread_path (edge entry,
- edge exit,
- basic_block *region,
- unsigned n_region,
- unsigned current_path_no)
+back_jt_path_registry::duplicate_thread_path (edge entry,
+ edge exit,
+ basic_block *region,
+ unsigned n_region,
+ unsigned current_path_no)
{
unsigned i;
class loop *loop = entry->dest->loop_father;
@@ -2551,7 +2562,7 @@ valid_jump_thread_path (vec<jump_thread_edge *> *path)
DOM/VRP rather than for every case where DOM optimizes away a COND_EXPR. */
void
-jump_thread_path_registry::remove_jump_threads_including (edge_def *e)
+fwd_jt_path_registry::remove_jump_threads_including (edge_def *e)
{
if (!m_paths.exists ())
return;
@@ -2560,69 +2571,52 @@ jump_thread_path_registry::remove_jump_threads_including (edge_def *e)
*slot = e;
}
-/* Walk through all blocks and thread incoming edges to the appropriate
- outgoing edge for each edge pair recorded in THREADED_EDGES.
+/* Thread all paths that have been queued for jump threading, and
+ update the CFG accordingly.
It is the caller's responsibility to fix the dominance information
and rewrite duplicated SSA_NAMEs back into SSA form.
- If MAY_PEEL_LOOP_HEADERS is false, we avoid threading edges through
- loop headers if it does not simplify the loop.
+ If PEEL_LOOP_HEADERS is false, avoid threading edges through loop
+ headers if it does not simplify the loop.
- Returns true if one or more edges were threaded, false otherwise. */
+ Returns true if one or more edges were threaded. */
bool
-jump_thread_path_registry::thread_through_all_blocks
- (bool may_peel_loop_headers)
+jt_path_registry::thread_through_all_blocks (bool peel_loop_headers)
{
- bool retval = false;
- unsigned int i;
- auto_bitmap threaded_blocks;
- hash_set<edge> visited_starting_edges;
-
- if (!m_paths.exists ())
- {
- retval = false;
- goto out;
- }
+ if (m_paths.length () == 0)
+ return false;
m_num_threaded_edges = 0;
- /* Remove any paths that referenced removed edges. */
- if (m_removed_edges)
- for (i = 0; i < m_paths.length (); )
- {
- unsigned int j;
- vec<jump_thread_edge *> *path = m_paths[i];
+ bool retval = update_cfg (peel_loop_headers);
- for (j = 0; j < path->length (); j++)
- {
- edge e = (*path)[j]->e;
- if (m_removed_edges->find_slot (e, NO_INSERT))
- break;
- }
+ statistics_counter_event (cfun, "Jumps threaded", m_num_threaded_edges);
- if (j != path->length ())
- {
- cancel_thread (path, "Thread references removed edge");
- m_paths.unordered_remove (i);
- continue;
- }
- i++;
- }
+ if (retval)
+ {
+ loops_state_set (LOOPS_NEED_FIXUP);
+ return true;
+ }
+ return false;
+}
- /* Jump-thread all FSM threads before other jump-threads. */
- for (i = 0; i < m_paths.length ();)
+/* This is the backward threader version of thread_through_all_blocks
+ using a generic BB copier. */
+
+bool
+back_jt_path_registry::update_cfg (bool /*peel_loop_headers*/)
+{
+ bool retval = false;
+ hash_set<edge> visited_starting_edges;
+
+ while (m_paths.length ())
{
- vec<jump_thread_edge *> *path = m_paths[i];
+ vec<jump_thread_edge *> *path = m_paths[0];
edge entry = (*path)[0]->e;
- /* Only code-generate FSM jump-threads in this loop. */
- if ((*path)[0]->type != EDGE_FSM_THREAD)
- {
- i++;
- continue;
- }
+ gcc_checking_assert ((*path)[0]->type == EDGE_FSM_THREAD);
/* Do not jump-thread twice from the same starting edge.
@@ -2638,8 +2632,8 @@ jump_thread_path_registry::thread_through_all_blocks
|| !valid_jump_thread_path (path))
{
/* Remove invalid FSM jump-thread paths. */
- cancel_thread (path, "Invalid FSM jump-thread path");
- m_paths.unordered_remove (i);
+ cancel_thread (path, "Avoiding threading twice from same edge");
+ m_paths.unordered_remove (0);
continue;
}
@@ -2650,7 +2644,7 @@ jump_thread_path_registry::thread_through_all_blocks
for (unsigned int j = 0; j < len - 1; j++)
region[j] = (*path)[j]->e->dest;
- if (duplicate_thread_path (entry, exit, region, len - 1, i))
+ if (duplicate_thread_path (entry, exit, region, len - 1, 0))
{
/* We do not update dominance info. */
free_dominance_info (CDI_DOMINATORS);
@@ -2660,27 +2654,44 @@ jump_thread_path_registry::thread_through_all_blocks
}
path->release ();
- m_paths.unordered_remove (i);
+ m_paths.unordered_remove (0);
free (region);
}
+ return retval;
+}
- /* Remove from PATHS all the jump-threads starting with an edge already
- jump-threaded. */
- for (i = 0; i < m_paths.length ();)
- {
- vec<jump_thread_edge *> *path = m_paths[i];
- edge entry = (*path)[0]->e;
+/* This is the forward threader version of thread_through_all_blocks,
+ using a custom BB copier. */
- /* Do not jump-thread twice from the same block. */
- if (visited_starting_edges.contains (entry))
- {
- cancel_thread (path, "Avoiding threading twice from same BB");
- m_paths.unordered_remove (i);
- }
- else
+bool
+fwd_jt_path_registry::update_cfg (bool may_peel_loop_headers)
+{
+ bool retval = false;
+
+ /* Remove any paths that referenced removed edges. */
+ if (m_removed_edges)
+ for (unsigned i = 0; i < m_paths.length (); )
+ {
+ unsigned int j;
+ vec<jump_thread_edge *> *path = m_paths[i];
+
+ for (j = 0; j < path->length (); j++)
+ {
+ edge e = (*path)[j]->e;
+ if (m_removed_edges->find_slot (e, NO_INSERT))
+ break;
+ }
+
+ if (j != path->length ())
+ {
+ cancel_thread (path, "Thread references removed edge");
+ m_paths.unordered_remove (i);
+ continue;
+ }
i++;
- }
+ }
+ auto_bitmap threaded_blocks;
mark_threaded_blocks (threaded_blocks);
initialize_original_copy_tables ();
@@ -2737,16 +2748,8 @@ jump_thread_path_registry::thread_through_all_blocks
gcc_assert (e->aux == NULL);
}
- statistics_counter_event (cfun, "Jumps threaded", m_num_threaded_edges);
-
free_original_copy_tables ();
- m_paths.release ();
-
- if (retval)
- loops_state_set (LOOPS_NEED_FIXUP);
-
- out:
return retval;
}
@@ -2761,7 +2764,7 @@ jump_thread_path_registry::thread_through_all_blocks
Return TRUE if PATH was successfully threaded. */
bool
-jump_thread_path_registry::register_jump_thread (vec<jump_thread_edge *> *path)
+jt_path_registry::register_jump_thread (vec<jump_thread_edge *> *path)
{
if (!dbg_cnt (registered_jump_thread))
{
diff --git a/gcc/tree-ssa-threadupdate.h b/gcc/tree-ssa-threadupdate.h
index 2030bda15af..58e3a38e0c5 100644
--- a/gcc/tree-ssa-threadupdate.h
+++ b/gcc/tree-ssa-threadupdate.h
@@ -54,49 +54,65 @@ private:
obstack m_obstack;
};
-// This is the underlying jump thread registry. When all candidates
-// have been registered with register_jump_thread(),
-// thread_through_all_blocks() is called to actually change the CFG.
+// Abstract class for the jump thread registry.
+//
+// When all candidates have been registered with
+// register_jump_thread(), thread_through_all_blocks() is called to
+// update the CFG.
-class jump_thread_path_registry
+class jt_path_registry
{
public:
- jump_thread_path_registry ();
- ~jump_thread_path_registry ();
+ jt_path_registry ();
+ virtual ~jt_path_registry ();
bool register_jump_thread (vec<jump_thread_edge *> *);
- void remove_jump_threads_including (edge);
- bool thread_through_all_blocks (bool);
+ bool thread_through_all_blocks (bool peel_loop_headers);
jump_thread_edge *allocate_thread_edge (edge e, jump_thread_edge_type t);
vec<jump_thread_edge *> *allocate_thread_path ();
- void dump ();
+ void debug ();
+protected:
+ void debug_path (FILE *, int pathno);
+ vec<vec<jump_thread_edge *> *> m_paths;
+ unsigned long m_num_threaded_edges;
+private:
+ virtual bool update_cfg (bool peel_loop_headers) = 0;
+ jump_thread_path_allocator m_allocator;
+ DISABLE_COPY_AND_ASSIGN (jt_path_registry);
+};
+
+// Forward threader path registry using a custom BB copier.
+class fwd_jt_path_registry : public jt_path_registry
+{
+public:
+ fwd_jt_path_registry ();
+ ~fwd_jt_path_registry ();
+ void remove_jump_threads_including (edge);
private:
- void debug_path (FILE *, int pathno);
+ bool update_cfg (bool peel_loop_headers) override;
void mark_threaded_blocks (bitmap threaded_blocks);
- bool rewire_first_differing_edge (unsigned path_num, unsigned edge_num);
- void adjust_paths_after_duplication (unsigned curr_path_num);
- bool duplicate_thread_path (edge entry,
- edge exit,
- basic_block *region,
- unsigned n_region,
- unsigned current_path_no);
bool thread_block_1 (basic_block, bool noloop_only, bool joiners);
bool thread_block (basic_block, bool noloop_only);
bool thread_through_loop_header (class loop *loop,
bool may_peel_loop_headers);
class redirection_data *lookup_redirection_data (edge e, enum insert_option);
- vec<vec<jump_thread_edge *> *> m_paths;
-
hash_table<struct removed_edges> *m_removed_edges;
// Main data structure to hold information for duplicates of BB.
hash_table<redirection_data> *m_redirection_data;
+};
- // Jump threading statistics.
- unsigned long m_num_threaded_edges;
+// Backward threader path registry using a generic BB copier.
- jump_thread_path_allocator m_allocator;
+class back_jt_path_registry : public jt_path_registry
+{
+private:
+ bool update_cfg (bool peel_loop_headers) override;
+ void adjust_paths_after_duplication (unsigned curr_path_num);
+ bool duplicate_thread_path (edge entry, edge exit, basic_block *region,
+ unsigned n_region, unsigned current_path_no);
+ bool rewire_first_differing_edge (unsigned path_num, unsigned edge_num);
};
// Rather than search all the edges in jump thread paths each time DOM
</cut>
3 years, 9 months
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-master-aarch64-mainline-allmodconfig - Build # 10 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-master-aarch64-mainline-allmodconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-master-aarch64-mainline-allmodconfig
Culprit:
<cut>
commit c3496da580b0fc10fdeba8f6a5e6aef4c78b5598
Author: Slark Xiao <slark_xiao(a)163.com>
Date: Tue Aug 31 10:40:25 2021 +0800
net: Add depends on OF_NET for LiteX's LiteETH
Current settings may produce a build error when
CONFIG_OF_NET is disabled. The CONFIG_OF_NET controls
a headfile <linux/of.h> and some functions
in <linux/of_net.h>.
Signed-off-by: Slark Xiao <slark_xiao(a)163.com>
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
</cut>
Results regressed to (for first_bad == c3496da580b0fc10fdeba8f6a5e6aef4c78b5598)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
29873
# linux build successful:
all
# First few build errors in logs:
from (for last_good == a9e7c3cedc2914f63cd135b75832b9bf850af782)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
29873
# linux build successful:
all
# linux boot successful:
boot
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-mainl…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-mainl…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-mainl…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-linux-c3496da580b0fc10fdeba8f6a5e6aef4c78b5598
cd investigate-linux-c3496da580b0fc10fdeba8f6a5e6aef4c78b5598
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-mainl… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-mainl… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-mainl… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach c3496da580b0fc10fdeba8f6a5e6aef4c78b5598
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach a9e7c3cedc2914f63cd135b75832b9bf850af782
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-mainl…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-mainl…
Full commit (up to 1000 lines):
<cut>
commit c3496da580b0fc10fdeba8f6a5e6aef4c78b5598
Author: Slark Xiao <slark_xiao(a)163.com>
Date: Tue Aug 31 10:40:25 2021 +0800
net: Add depends on OF_NET for LiteX's LiteETH
Current settings may produce a build error when
CONFIG_OF_NET is disabled. The CONFIG_OF_NET controls
a headfile <linux/of.h> and some functions
in <linux/of_net.h>.
Signed-off-by: Slark Xiao <slark_xiao(a)163.com>
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
---
drivers/net/ethernet/litex/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/litex/Kconfig b/drivers/net/ethernet/litex/Kconfig
index 265dba414b41..63bf01d28f0c 100644
--- a/drivers/net/ethernet/litex/Kconfig
+++ b/drivers/net/ethernet/litex/Kconfig
@@ -17,6 +17,7 @@ if NET_VENDOR_LITEX
config LITEX_LITEETH
tristate "LiteX Ethernet support"
+ depends on OF_NET
help
If you wish to compile a kernel for hardware with a LiteX LiteEth
device then you should answer Y to this.
</cut>
3 years, 9 months
- 3
- 3
[TCWG CI] Regression caused by llvm:09507b53250dc266632c204558cb1c2b56e8ddea
by ci_notify＠linaro.org
Identified regression caused by *llvm:09507b53250dc266632c204558cb1c2b56e8ddea*:
commit 09507b53250dc266632c204558cb1c2b56e8ddea
Author: Cullen Rhodes <cullen.rhodes(a)arm.com>
[AArch64][SME] Disable NEON in streaming mode
Results regressed to (for first_bad == 09507b53250dc266632c204558cb1c2b56e8ddea)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-09507b53250dc266632c204558cb1c2b56e8ddea/results_id:
1
# 456.hmmer,hmmer_base.default regressed by 103
from (for last_good == 93c55d5ea24b8f455b0621bac373f142e0008739)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-93c55d5ea24b8f455b0621bac373f142e0008739/results_id:
1
This commit has regressed these CI configurations:
- tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-O3
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Even more details: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Reproduce builds:
<cut>
mkdir investigate-llvm-09507b53250dc266632c204558cb1c2b56e8ddea
cd investigate-llvm-09507b53250dc266632c204558cb1c2b56e8ddea
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 09507b53250dc266632c204558cb1c2b56e8ddea
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 93c55d5ea24b8f455b0621bac373f142e0008739
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 09507b53250dc266632c204558cb1c2b56e8ddea
Author: Cullen Rhodes <cullen.rhodes(a)arm.com>
Date: Mon Aug 16 07:31:55 2021 +0000
[AArch64][SME] Disable NEON in streaming mode
In streaming mode most of the NEON instruction set is illegal, disable
NEON when compiling with `+streaming-sve`, unless NEON is explictly
requested.
Subsequent patches will add support for the small subset of NEON
instructions that are legal in streaming mode.
Reviewed By: paulwalker-arm, david-arm
Differential Revision: https://reviews.llvm.org/D107902
---
llvm/lib/Target/AArch64/MCTargetDesc/AArch64MCTargetDesc.cpp | 11 ++++++++++-
llvm/test/MC/AArch64/SME/streaming-sve-feature.s | 8 ++++++++
2 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/llvm/lib/Target/AArch64/MCTargetDesc/AArch64MCTargetDesc.cpp b/llvm/lib/Target/AArch64/MCTargetDesc/AArch64MCTargetDesc.cpp
index 3c2df1621e11..987cabce6cc9 100644
--- a/llvm/lib/Target/AArch64/MCTargetDesc/AArch64MCTargetDesc.cpp
+++ b/llvm/lib/Target/AArch64/MCTargetDesc/AArch64MCTargetDesc.cpp
@@ -57,7 +57,16 @@ createAArch64MCSubtargetInfo(const Triple &TT, StringRef CPU, StringRef FS) {
CPU = "apple-a12";
}
- return createAArch64MCSubtargetInfoImpl(TT, CPU, /*TuneCPU*/ CPU, FS);
+ // Most of the NEON instruction set isn't supported in streaming mode on SME
+ // targets, disable NEON unless explicitly requested.
+ bool RequestedNEON = FS.contains("neon");
+ bool RequestedStreamingSVE = FS.contains("streaming-sve");
+ MCSubtargetInfo *STI =
+ createAArch64MCSubtargetInfoImpl(TT, CPU, /*TuneCPU*/ CPU, FS);
+ if (RequestedStreamingSVE && !RequestedNEON &&
+ STI->hasFeature(AArch64::FeatureNEON))
+ STI->ToggleFeature(AArch64::FeatureNEON);
+ return STI;
}
void AArch64_MC::initLLVMToCVRegMapping(MCRegisterInfo *MRI) {
diff --git a/llvm/test/MC/AArch64/SME/streaming-sve-feature.s b/llvm/test/MC/AArch64/SME/streaming-sve-feature.s
new file mode 100644
index 000000000000..e35505ca39c5
--- /dev/null
+++ b/llvm/test/MC/AArch64/SME/streaming-sve-feature.s
@@ -0,0 +1,8 @@
+// RUN: llvm-mc -triple=aarch64 -mattr=+streaming-sve,+neon < %s 2>&1 | FileCheck %s
+// RUN: not llvm-mc -triple=aarch64 -mattr=+streaming-sve < %s 2>&1 | FileCheck %s --check-prefix=CHECK-ERROR
+
+// Verify NEON is disabled when targeting streaming mode, if it's not
+// explicitly requested.
+add v0.8b, v1.8b, v2.8b
+// CHECK: add v0.8b, v1.8b, v2.8b
+// CHECK-ERROR: error: instruction requires: neon
</cut>
3 years, 9 months
- 1
- 0
[TCWG CI] Regression caused by llvm:4389a413e2129d7d55ee779638b649aa852b6f8a
by ci_notify＠linaro.org
Identified regression caused by *llvm:4389a413e2129d7d55ee779638b649aa852b6f8a*:
commit 4389a413e2129d7d55ee779638b649aa852b6f8a
Author: Zahira Ammarguellat <zahira.ammarguellat(a)intel.com>
Revert "[clang][fpenv][patch] Change clang option -ffp-model=precise to select ffp-contract=on"
Results regressed to (for first_bad == 4389a413e2129d7d55ee779638b649aa852b6f8a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz_LTO artifacts/build-4389a413e2129d7d55ee779638b649aa852b6f8a/results_id:
1
# 470.lbm,lbm_base.default regressed by 104
from (for last_good == dfce2909ee1ea1523ec27b834a0e56429e9c2beb)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz_LTO artifacts/build-dfce2909ee1ea1523ec27b834a0e56429e9c2beb/results_id:
1
This commit has regressed these CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz_LTO
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Even more details: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Reproduce builds:
<cut>
mkdir investigate-llvm-4389a413e2129d7d55ee779638b649aa852b6f8a
cd investigate-llvm-4389a413e2129d7d55ee779638b649aa852b6f8a
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 4389a413e2129d7d55ee779638b649aa852b6f8a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach dfce2909ee1ea1523ec27b834a0e56429e9c2beb
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 4389a413e2129d7d55ee779638b649aa852b6f8a
Author: Zahira Ammarguellat <zahira.ammarguellat(a)intel.com>
Date: Fri Aug 6 12:01:47 2021 -0700
Revert "[clang][fpenv][patch] Change clang option -ffp-model=precise to select ffp-contract=on"
This reverts commit 48ad446a0fb2c9b98cb7047e4daf8a84c29cef8f.
---
clang/docs/UsersManual.rst | 48 ++-----------------------
clang/lib/Driver/ToolChains/Clang.cpp | 33 ++++++++---------
clang/test/CodeGen/ffp-contract-option.c | 47 +++---------------------
clang/test/CodeGen/ppc-emmintrin.c | 4 +--
clang/test/CodeGen/ppc-xmmintrin.c | 4 +--
clang/test/Driver/fp-model.c | 61 +++++++++++++++-----------------
6 files changed, 58 insertions(+), 139 deletions(-)
diff --git a/clang/docs/UsersManual.rst b/clang/docs/UsersManual.rst
index 838669794ea8..980d0ab45975 100644
--- a/clang/docs/UsersManual.rst
+++ b/clang/docs/UsersManual.rst
@@ -1260,50 +1260,8 @@ installed.
Controlling Floating Point Behavior
-----------------------------------
-Clang provides a number of ways to control floating point behavior, including
-with command line options and source pragmas. This section
-describes the various floating point semantic modes and the corresponding options.
-
-.. csv-table:: Floating Point Semantic Modes
- :header: "Mode", "Values"
- :widths: 15, 30, 30
-
- "except_behavior", "{ignore, strict, may_trap}", "ffp-exception-behavior"
- "fenv_access", "{off, on}", "(none)"
- "rounding_mode", "{dynamic, tonearest, downward, upward, towardzero}", "frounding-math"
- "contract", "{on, off, fast}", "ffp-contract"
- "denormal_fp_math", "{IEEE, PreserveSign, PositiveZero}", "fdenormal-fp-math"
- "denormal_fp32_math", "{IEEE, PreserveSign, PositiveZero}", "fdenormal-fp-math-fp32"
- "support_math_errno", "{on, off}", "fmath-errno"
- "no_honor_nans", "{on, off}", "fhonor-nans"
- "no_honor_infinities", "{on, off}", "fhonor-infinities"
- "no_signed_zeros", "{on, off}", "fsigned-zeros"
- "allow_reciprocal", "{on, off}", "freciprocal-math"
- "allow_approximate_fns", "{on, off}", "(none)"
- "allow_reassociation", "{on, off}", "fassociative-math"
-
-
-This table describes the option settings that correspond to the three
-floating point semantic models: precise (the default), strict, and fast.
-
-
-.. csv-table:: Floating Point Models
- :header: "Mode", "Precise", "Strict", "Fast"
- :widths: 25, 15, 15, 15
-
- "except_behavior", "ignore", "strict", "ignore"
- "fenv_access", "off", "on", "off"
- "rounding_mode", "tonearest", "dynamic", "tonearest"
- "contract", "on", "off", "fast"
- "denormal_fp_math", "IEEE", "IEEE", "PreserveSign"
- "denormal_fp32_math", "IEEE","IEEE", "PreserveSign"
- "support_math_errno", "on", "on", "off"
- "no_honor_nans", "off", "off", "on"
- "no_honor_infinities", "off", "off", "on"
- "no_signed_zeros", "off", "off", "on"
- "allow_reciprocal", "off", "off", "on"
- "allow_approximate_fns", "off", "off", "on"
- "allow_reassociation", "off", "off", "on"
+Clang provides a number of ways to control floating point behavior. The options
+are listed below.
.. option:: -ffast-math
@@ -1498,7 +1456,7 @@ Note that floating-point operations performed as part of constant initialization
and ``fast``.
Details:
- * ``precise`` Disables optimizations that are not value-safe on floating-point data, although FP contraction (FMA) is enabled (``-ffp-contract=on``). This is the default behavior.
+ * ``precise`` Disables optimizations that are not value-safe on floating-point data, although FP contraction (FMA) is enabled (``-ffp-contract=fast``). This is the default behavior.
* ``strict`` Enables ``-frounding-math`` and ``-ffp-exception-behavior=strict``, and disables contractions (FMA). All of the ``-ffast-math`` enablements are disabled. Enables ``STDC FENV_ACCESS``: by default ``FENV_ACCESS`` is disabled. This option setting behaves as though ``#pragma STDC FENV_ACESS ON`` appeared at the top of the source file.
* ``fast`` Behaves identically to specifying both ``-ffast-math`` and ``ffp-contract=fast``
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 1c79640be80f..96bbc0250126 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -2641,7 +2641,7 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
llvm::DenormalMode DenormalFPMath = DefaultDenormalFPMath;
llvm::DenormalMode DenormalFP32Math = DefaultDenormalFP32Math;
- StringRef FPContract = "on";
+ StringRef FPContract = "";
bool StrictFPModel = false;
@@ -2666,7 +2666,7 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
ReciprocalMath = false;
SignedZeros = true;
// -fno_fast_math restores default denormal and fpcontract handling
- FPContract = "on";
+ FPContract = "";
DenormalFPMath = llvm::DenormalMode::getIEEE();
// FIXME: The target may have picked a non-IEEE default mode here based on
@@ -2686,18 +2686,20 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
// ffp-model= is a Driver option, it is entirely rewritten into more
// granular options before being passed into cc1.
// Use the gcc option in the switch below.
- if (!FPModel.empty() && !FPModel.equals(Val))
+ if (!FPModel.empty() && !FPModel.equals(Val)) {
D.Diag(clang::diag::warn_drv_overriding_flag_option)
<< Args.MakeArgString("-ffp-model=" + FPModel)
<< Args.MakeArgString("-ffp-model=" + Val);
+ FPContract = "";
+ }
if (Val.equals("fast")) {
optID = options::OPT_ffast_math;
FPModel = Val;
- FPContract = Val;
+ FPContract = "fast";
} else if (Val.equals("precise")) {
optID = options::OPT_ffp_contract;
FPModel = Val;
- FPContract = "on";
+ FPContract = "fast";
PreciseFPModel = true;
} else if (Val.equals("strict")) {
StrictFPModel = true;
@@ -2783,11 +2785,9 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
case options::OPT_ffp_contract: {
StringRef Val = A->getValue();
if (PreciseFPModel) {
- // When -ffp-model=precise is seen on the command line,
- // the boolean PreciseFPModel is set to true which indicates
- // "the current option is actually PreciseFPModel". The optID
- // is changed to OPT_ffp_contract and FPContract is set to "on".
- // the argument Val string is "precise": it shouldn't be checked.
+ // -ffp-model=precise enables ffp-contract=fast as a side effect
+ // the FPContract value has already been set to a string literal
+ // and the Val string isn't a pertinent value.
;
} else if (Val.equals("fast") || Val.equals("on") || Val.equals("off"))
FPContract = Val;
@@ -2897,17 +2897,18 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
// -fno_fast_math restores default denormal and fpcontract handling
DenormalFPMath = DefaultDenormalFPMath;
DenormalFP32Math = llvm::DenormalMode::getIEEE();
- FPContract = "on";
+ FPContract = "";
break;
}
if (StrictFPModel) {
// If -ffp-model=strict has been specified on command line but
// subsequent options conflict then emit warning diagnostic.
- if (HonorINFs && HonorNaNs && !AssociativeMath && !ReciprocalMath &&
- SignedZeros && TrappingMath && RoundingFPMath &&
- DenormalFPMath == llvm::DenormalMode::getIEEE() &&
- DenormalFP32Math == llvm::DenormalMode::getIEEE() &&
- FPContract.equals("off"))
+ if (HonorINFs && HonorNaNs &&
+ !AssociativeMath && !ReciprocalMath &&
+ SignedZeros && TrappingMath && RoundingFPMath &&
+ (FPContract.equals("off") || FPContract.empty()) &&
+ DenormalFPMath == llvm::DenormalMode::getIEEE() &&
+ DenormalFP32Math == llvm::DenormalMode::getIEEE())
// OK: Current Arg doesn't conflict with -ffp-model=strict
;
else {
diff --git a/clang/test/CodeGen/ffp-contract-option.c b/clang/test/CodeGen/ffp-contract-option.c
index efc72c2b5461..52b750795940 100644
--- a/clang/test/CodeGen/ffp-contract-option.c
+++ b/clang/test/CodeGen/ffp-contract-option.c
@@ -1,46 +1,9 @@
-// RUN: %clang_cc1 -O3 -ffp-contract=fast -triple=aarch64-apple-darwin -S -o - %s | FileCheck --check-prefix=CHECK-FMADD %s
+// RUN: %clang_cc1 -O3 -ffp-contract=fast -triple=aarch64-apple-darwin -S -o - %s | FileCheck %s
// REQUIRES: aarch64-registered-target
float fma_test1(float a, float b, float c) {
-// CHECK-FMADD: fmadd
- float x = a * b;
- float y = x + c;
- return y;
-}
-
-// RUN: %clang_cc1 -triple=x86_64 %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULT %s
-//
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=off %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULT %s
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=on %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-ON %s
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=fast %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-CONTRACTFAST %s
-//
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULTFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=off %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULTFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=on %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-ONFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=fast %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-FASTFAST %s
-float mymuladd( float x, float y, float z ) {
- return x * y + z;
- // CHECK-DEFAULT: = fmul float
- // CHECK-DEFAULT: = fadd float
-
- // CHECK-ON: = call float @llvm.fmuladd.f32
-
- // CHECK-CONTRACTFAST: = fmul contract float
- // CHECK-CONTRACTFAST: = fadd contract float
-
- // CHECK-DEFAULTFAST: = fmul reassoc nnan ninf nsz arcp afn float
- // CHECK-DEFAULTFAST: = fadd reassoc nnan ninf nsz arcp afn float
-
- // CHECK-ONFAST: = call reassoc nnan ninf nsz arcp afn float @llvm.fmuladd.f32
-
- // CHECK-FASTFAST: = fmul fast float
- // CHECK-FASTFAST: = fadd fast float
+// CHECK: fmadd
+ float x = a * b;
+ float y = x + c;
+ return y;
}
diff --git a/clang/test/CodeGen/ppc-emmintrin.c b/clang/test/CodeGen/ppc-emmintrin.c
index 4a246ff92d76..fa3801f50a01 100644
--- a/clang/test/CodeGen/ppc-emmintrin.c
+++ b/clang/test/CodeGen/ppc-emmintrin.c
@@ -2,9 +2,9 @@
// REQUIRES: powerpc-registered-target
// RUN: %clang -S -emit-llvm -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
// RUN: %clang -S -emit-llvm -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
// CHECK-BE-DAG: @_mm_movemask_pd.perm_mask = internal constant <4 x i32> <i32 -2139062144, i32 -2139062144, i32 -2139062144, i32 -2139078656>, align 16
// CHECK-BE-DAG: @_mm_shuffle_epi32.permute_selectors = internal constant [4 x i32] [i32 66051, i32 67438087, i32 134810123, i32 202182159], align 4
diff --git a/clang/test/CodeGen/ppc-xmmintrin.c b/clang/test/CodeGen/ppc-xmmintrin.c
index a7f6ed6e0e67..d3f18bfbb1e5 100644
--- a/clang/test/CodeGen/ppc-xmmintrin.c
+++ b/clang/test/CodeGen/ppc-xmmintrin.c
@@ -2,11 +2,11 @@
// REQUIRES: powerpc-registered-target
// RUN: %clang -S -emit-llvm -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
// RUN: %clang -x c++ -fsyntax-only -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns
// RUN: %clang -S -emit-llvm -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
// RUN: %clang -x c++ -fsyntax-only -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns
diff --git a/clang/test/Driver/fp-model.c b/clang/test/Driver/fp-model.c
index c6d683e25c0b..5fa9d110dd83 100644
--- a/clang/test/Driver/fp-model.c
+++ b/clang/test/Driver/fp-model.c
@@ -1,90 +1,88 @@
// Test that incompatible combinations of -ffp-model= options
// and other floating point options get a warning diagnostic.
+//
+// REQUIRES: clang-driver
-// RUN: %clang -target x86_64 -### -ffp-model=fast -ffp-contract=off -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=fast -ffp-contract=off -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN %s
// WARN: warning: overriding '-ffp-model=fast' option with '-ffp-contract=off' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=fast -ffp-contract=on -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=fast -ffp-contract=on -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN1 %s
// WARN1: warning: overriding '-ffp-model=fast' option with '-ffp-contract=on' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fassociative-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fassociative-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN2 %s
// WARN2: warning: overriding '-ffp-model=strict' option with '-fassociative-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffast-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffast-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN3 %s
// WARN3: warning: overriding '-ffp-model=strict' option with '-ffast-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffinite-math-only -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffinite-math-only -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN4 %s
// WARN4: warning: overriding '-ffp-model=strict' option with '-ffinite-math-only' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN5 %s
// WARN5: warning: overriding '-ffp-model=strict' option with '-ffp-contract=fast' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
-// RUN: | FileCheck --check-prefix=WARN6 %s
-// WARN6: warning: overriding '-ffp-model=strict' option with '-ffp-contract=fast' [-Woverriding-t-option]
-
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=on -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffp-contract=on -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN7 %s
// WARN7: warning: overriding '-ffp-model=strict' option with '-ffp-contract=on' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-honor-infinities -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-honor-infinities -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN8 %s
// WARN8: warning: overriding '-ffp-model=strict' option with '-fno-honor-infinities' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-honor-nans -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-honor-nans -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN9 %s
// WARN9: warning: overriding '-ffp-model=strict' option with '-fno-honor-nans' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-rounding-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-rounding-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNa %s
// WARNa: warning: overriding '-ffp-model=strict' option with '-fno-rounding-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-signed-zeros -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-signed-zeros -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNb %s
// WARNb: warning: overriding '-ffp-model=strict' option with '-fno-signed-zeros' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-trapping-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-trapping-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNc %s
// WARNc: warning: overriding '-ffp-model=strict' option with '-fno-trapping-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -freciprocal-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -freciprocal-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNd %s
// WARNd: warning: overriding '-ffp-model=strict' option with '-freciprocal-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -funsafe-math-optimizations -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -funsafe-math-optimizations -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNe %s
// WARNe: warning: overriding '-ffp-model=strict' option with '-funsafe-math-optimizations' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -Ofast -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -Ofast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNf %s
// WARNf: warning: overriding '-ffp-model=strict' option with '-Ofast' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fdenormal-fp-math=preserve-sign,preserve-sign -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fdenormal-fp-math=preserve-sign,preserve-sign -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN10 %s
// WARN10: warning: overriding '-ffp-model=strict' option with '-fdenormal-fp-math=preserve-sign,preserve-sign' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -c %s 2>&1 \
+// RUN: %clang -### -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-NOROUND %s
// CHECK-NOROUND: "-cc1"
// CHECK-NOROUND: "-fno-rounding-math"
-// RUN: %clang -target x86_64 -### -frounding-math -c %s 2>&1 \
+// RUN: %clang -### -frounding-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-ROUND --implicit-check-not ffp-exception-behavior=strict %s
// CHECK-ROUND: "-cc1"
// CHECK-ROUND: "-frounding-math"
-// RUN: %clang -target x86_64 -### -ftrapping-math -c %s 2>&1 \
+// RUN: %clang -### -ftrapping-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-TRAP %s
// CHECK-TRAP: "-cc1"
// CHECK-TRAP: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=fast -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=fast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-FAST %s
// CHECK-FPM-FAST: "-cc1"
// CHECK-FPM-FAST: "-menable-no-infs"
@@ -98,35 +96,34 @@
// CHECK-FPM-FAST: "-ffast-math"
// CHECK-FPM-FAST: "-ffinite-math-only"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=precise -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=precise -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-PRECISE %s
// CHECK-FPM-PRECISE: "-cc1"
-// CHECK-FPM-PRECISE: "-ffp-contract=on"
+// CHECK-FPM-PRECISE: "-ffp-contract=fast"
// CHECK-FPM-PRECISE: "-fno-rounding-math"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=strict -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=strict -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-STRICT %s
// CHECK-FPM-STRICT: "-cc1"
-// CHECK-FPM-STRICT: "-fmath-errno"
-// CHECK-FPM-STRICT: "-ffp-contract=off"
// CHECK-FPM-STRICT: "-frounding-math"
// CHECK-FPM-STRICT: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=strict -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=strict -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-STRICT %s
// CHECK-FEB-STRICT: "-cc1"
// CHECK-FEB-STRICT: "-fno-rounding-math"
// CHECK-FEB-STRICT: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=maytrap -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=maytrap -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-MAYTRAP %s
// CHECK-FEB-MAYTRAP: "-cc1"
// CHECK-FEB-MAYTRAP: "-fno-rounding-math"
// CHECK-FEB-MAYTRAP: "-ffp-exception-behavior=maytrap"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=ignore -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=ignore -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-IGNORE %s
// CHECK-FEB-IGNORE: "-cc1"
// CHECK-FEB-IGNORE: "-fno-rounding-math"
// CHECK-FEB-IGNORE: "-ffp-exception-behavior=ignore"
+
</cut>
3 years, 9 months
- 1
- 0
[TCWG CI] Regression caused by gcc:01b5038718056b024b370b74a874fbd92c5bbab3
by ci_notify＠linaro.org
Identified regression caused by *gcc:01b5038718056b024b370b74a874fbd92c5bbab3*:
commit 01b5038718056b024b370b74a874fbd92c5bbab3
Author: Aldy Hernandez <aldyh(a)redhat.com>
Disable threading through latches until after loop optimizations.
Results regressed to (for first_bad == 01b5038718056b024b370b74a874fbd92c5bbab3)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -Os artifacts/build-01b5038718056b024b370b74a874fbd92c5bbab3/results_id:
1
# 459.GemsFDTD,GemsFDTD_base.default regressed by 102
# 464.h264ref,h264ref_base.default regressed by 102
from (for last_good == fb88bf9931f17d137eb50c001e1c924aa1e34e83)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -Os artifacts/build-fb88bf9931f17d137eb50c001e1c924aa1e34e83/results_id:
1
This commit has regressed these CI configurations:
- tcwg_bmk_gnu_apm/gnu-master-aarch64-spec2k6-Os
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa…
Even more details: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa…
Reproduce builds:
<cut>
mkdir investigate-gcc-01b5038718056b024b370b74a874fbd92c5bbab3
cd investigate-gcc-01b5038718056b024b370b74a874fbd92c5bbab3
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-master-aa… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 01b5038718056b024b370b74a874fbd92c5bbab3
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach fb88bf9931f17d137eb50c001e1c924aa1e34e83
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 01b5038718056b024b370b74a874fbd92c5bbab3
Author: Aldy Hernandez <aldyh(a)redhat.com>
Date: Thu Sep 9 20:30:28 2021 +0200
Disable threading through latches until after loop optimizations.
The motivation for this patch was enabling the use of global ranges in
the path solver, but this caused certain properties of loops being
destroyed which made subsequent loop optimizations to fail.
Consequently, this patch's mail goal is to disable jump threading
involving the latch until after loop optimizations have run.
As can be seen in the test adjustments, we mostly shift the threading
from the early threaders (ethread, thread[12] to the late threaders
thread[34]). I have nuked some of the early notes in the testcases
that came as part of the jump threader rewrite. They're mostly noise
now.
Note that we could probably relax some other restrictions in
profitable_path_p when loop optimizations have completed, but it would
require more testing, and I'm hesitant to touch more things than needed
at this point. I have added a reminder to the function to keep this
in mind.
Finally, perhaps as a follow-up, we should apply the same restrictions to
the forward threader. At some point I'd like to combine the cost models.
Tested on x86-64 Linux.
p.s. There is a thorough discussion involving the limitations of jump
threading involving loops here:
https://gcc.gnu.org/pipermail/gcc/2021-September/237247.html
gcc/ChangeLog:
* tree-pass.h (PROP_loop_opts_done): New.
* gimple-range-path.cc (path_range_query::internal_range_of_expr):
Intersect with global range.
* tree-ssa-loop.c (tree_ssa_loop_done): Set PROP_loop_opts_done.
* tree-ssa-threadbackward.c
(back_threader_profitability::profitable_path_p): Disable
threading through latches until after loop optimizations have run.
gcc/testsuite/ChangeLog:
* gcc.dg/tree-ssa/ssa-dom-thread-2b.c: Adjust for disabling of
threading through latches.
* gcc.dg/tree-ssa/ssa-dom-thread-6.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-7.c: Same.
Co-authored-by: Michael Matz <matz(a)suse.de>
---
gcc/gimple-range-path.cc | 3 ++
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-2b.c | 4 +--
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c | 37 ++---------------------
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c | 17 +----------
gcc/tree-pass.h | 2 ++
gcc/tree-ssa-loop.c | 2 +-
gcc/tree-ssa-threadbackward.c | 28 +++++++++++++++--
7 files changed, 37 insertions(+), 56 deletions(-)
diff --git a/gcc/gimple-range-path.cc b/gcc/gimple-range-path.cc
index a4fa3b296ff..c616b65756f 100644
--- a/gcc/gimple-range-path.cc
+++ b/gcc/gimple-range-path.cc
@@ -127,6 +127,9 @@ path_range_query::internal_range_of_expr (irange &r, tree name, gimple *stmt)
basic_block bb = stmt ? gimple_bb (stmt) : exit_bb ();
if (stmt && range_defined_in_block (r, name, bb))
{
+ if (TREE_CODE (name) == SSA_NAME)
+ r.intersect (gimple_range_global (name));
+
set_cache (r, name);
return true;
}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-2b.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-2b.c
index e1c33e86cd7..823ada982ff 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-2b.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-2b.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-thread1-stats -fdump-tree-dom2-stats -fdisable-tree-ethread" } */
+/* { dg-options "-O2 -fdump-tree-thread3-stats -fdump-tree-dom2-stats -fdisable-tree-ethread" } */
void foo();
void bla();
@@ -26,4 +26,4 @@ void thread_latch_through_header (void)
case. And we want to thread through the header as well. These
are both caught by threading in DOM. */
/* { dg-final { scan-tree-dump-not "Jumps threaded" "dom2"} } */
-/* { dg-final { scan-tree-dump-times "Jumps threaded: 1" 1 "thread1"} } */
+/* { dg-final { scan-tree-dump-times "Jumps threaded: 1" 1 "thread3"} } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c
index c7bf867b084..ee46759bacc 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c
@@ -1,41 +1,8 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-thread1-details -fdump-tree-thread2-details" } */
+/* { dg-options "-O2 -fdump-tree-thread1-details -fdump-tree-thread3-details" } */
-/* All the threads in the thread1 dump start on a X->BB12 edge, as can
- be seen in the dump:
-
- Registering FSM jump thread: (x, 12) incoming edge; ...
- etc
- etc
-
- Before the new evrp, we were threading paths that started at the
- following edges:
-
- Registering FSM jump thread: (10, 12) incoming edge
- Registering FSM jump thread: (6, 12) incoming edge
- Registering FSM jump thread: (9, 12) incoming edge
-
- This was because the PHI at BB12 had constant values coming in from
- BB10, BB6, and BB9:
-
- # state_10 = PHI <state_11(7), 0(10), state_11(5), 1(6), state_11(8), 2(9), state_11(11)>
-
- Now with the new evrp, we get:
-
- # state_10 = PHI <0(7), 0(10), state_11(5), 1(6), 0(8), 2(9), 1(11)>
-
- Thus, we have 3 more paths that are known to be constant and can be
- threaded. Which means that by the second threading pass, we can
- only find one profitable path.
-
- For the record, all these extra constants are better paths coming
- out of switches. For example:
-
- SWITCH_BB -> BBx -> BBy -> BBz -> PHI
-
- We now know the value of the switch index at PHI. */
/* { dg-final { scan-tree-dump-times "Registering FSM jump" 6 "thread1" } } */
-/* { dg-final { scan-tree-dump-times "Registering FSM jump" 1 "thread2" } } */
+/* { dg-final { scan-tree-dump-times "Registering FSM jump" 1 "thread3" } } */
int sum0, sum1, sum2, sum3;
int foo (char *s, char **ret)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
index 5fc2145a432..ba07942f9dd 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
@@ -1,23 +1,8 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fdump-tree-thread1-stats -fdump-tree-thread2-stats -fdump-tree-dom2-stats -fdump-tree-thread3-stats -fdump-tree-dom3-stats -fdump-tree-vrp2-stats -fno-guess-branch-probability" } */
-/* Here we have the same issue as was commented in ssa-dom-thread-6.c.
- The PHI coming into the threader has a lot more constants, so the
- threader can thread more paths.
-
-$ diff clean/a.c.105t.mergephi2 a.c.105t.mergephi2
-252c252
-< # s_50 = PHI <s_49(10), 5(14), s_51(18), s_51(22), 1(26), 1(29), 1(31), s_51(5), 4(12), 1(15), 5(17), 1(19), 3(21), 1(23), 6(25), 7(28), s_51(30)>
----
-> # s_50 = PHI <s_49(10), 5(14), 4(18), 5(22), 1(26), 1(29), 1(31), s_51(5), 4(12), 1(15), 5(17), 1(19), 3(21), 1(23), 6(25), 7(28), 7(30)>
-272a273
-
- I spot checked a few and they all have the same pattern. We are
- basically tracking the switch index better through multiple
- paths. */
-
/* { dg-final { scan-tree-dump "Jumps threaded: 18" "thread1" } } */
-/* { dg-final { scan-tree-dump "Jumps threaded: 8" "thread2" } } */
+/* { dg-final { scan-tree-dump "Jumps threaded: 8" "thread3" } } */
/* { dg-final { scan-tree-dump-not "Jumps threaded" "dom2" } } */
/* aarch64 has the highest CASE_VALUES_THRESHOLD in GCC. It's high enough
diff --git a/gcc/tree-pass.h b/gcc/tree-pass.h
index 83941bc0cee..eb75eb17951 100644
--- a/gcc/tree-pass.h
+++ b/gcc/tree-pass.h
@@ -225,6 +225,8 @@ protected:
been optimized. */
#define PROP_gimple_lomp_dev (1 << 16) /* done omp_device_lower */
#define PROP_rtl_split_insns (1 << 17) /* RTL has insns split. */
+#define PROP_loop_opts_done (1 << 18) /* SSA loop optimizations
+ have completed. */
#define PROP_gimple \
(PROP_gimple_any | PROP_gimple_lcf | PROP_gimple_leh | PROP_gimple_lomp)
diff --git a/gcc/tree-ssa-loop.c b/gcc/tree-ssa-loop.c
index 0cc4b3bbccf..1bbf2f1fb2c 100644
--- a/gcc/tree-ssa-loop.c
+++ b/gcc/tree-ssa-loop.c
@@ -540,7 +540,7 @@ const pass_data pass_data_tree_loop_done =
OPTGROUP_LOOP, /* optinfo_flags */
TV_NONE, /* tv_id */
PROP_cfg, /* properties_required */
- 0, /* properties_provided */
+ PROP_loop_opts_done, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
TODO_cleanup_cfg, /* todo_flags_finish */
diff --git a/gcc/tree-ssa-threadbackward.c b/gcc/tree-ssa-threadbackward.c
index 449232c7715..e72992328de 100644
--- a/gcc/tree-ssa-threadbackward.c
+++ b/gcc/tree-ssa-threadbackward.c
@@ -43,6 +43,7 @@ along with GCC; see the file COPYING3. If not see
#include "ssa.h"
#include "tree-cfgcleanup.h"
#include "tree-pretty-print.h"
+#include "cfghooks.h"
// Path registry for the backwards threader. After all paths have been
// registered with register_path(), thread_through_all_blocks() is called
@@ -564,7 +565,10 @@ back_threader_registry::thread_through_all_blocks (bool may_peel_loop_headers)
TAKEN_EDGE, otherwise it is NULL.
CREATES_IRREDUCIBLE_LOOP, if non-null is set to TRUE if threading this path
- would create an irreducible loop. */
+ would create an irreducible loop.
+
+ ?? It seems we should be able to loosen some of the restrictions in
+ this function after loop optimizations have run. */
bool
back_threader_profitability::profitable_path_p (const vec<basic_block> &m_path,
@@ -725,7 +729,11 @@ back_threader_profitability::profitable_path_p (const vec<basic_block> &m_path,
the last entry in the array when determining if we thread
through the loop latch. */
if (loop->latch == bb)
- threaded_through_latch = true;
+ {
+ threaded_through_latch = true;
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file, " (latch)");
+ }
}
gimple *stmt = get_gimple_control_stmt (m_path[0]);
@@ -845,6 +853,22 @@ back_threader_profitability::profitable_path_p (const vec<basic_block> &m_path,
"a multiway branch.\n");
return false;
}
+
+ /* Threading through an empty latch would cause code to be added to
+ the latch. This could alter the loop form sufficiently to cause
+ loop optimizations to fail. Disable these threads until after
+ loop optimizations have run. */
+ if ((threaded_through_latch
+ || (taken_edge && taken_edge->dest == loop->latch))
+ && !(cfun->curr_properties & PROP_loop_opts_done)
+ && empty_block_p (loop->latch))
+ {
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file,
+ " FAIL: FSM Thread through latch before loop opts would create non-empty latch\n");
+ return false;
+
+ }
return true;
}
</cut>
3 years, 9 months
- 1
- 0
[TCWG CI] Regression caused by llvm:50f4ae58eb136bc9d802cb98f02b6ff237eb61e0
by ci_notify＠linaro.org
Identified regression caused by *llvm:50f4ae58eb136bc9d802cb98f02b6ff237eb61e0*:
commit 50f4ae58eb136bc9d802cb98f02b6ff237eb61e0
Author: David Green <david.green(a)arm.com>
[AArch64] Correct store ReadAdrBase operand
Results regressed to (for first_bad == 50f4ae58eb136bc9d802cb98f02b6ff237eb61e0)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2 artifacts/build-50f4ae58eb136bc9d802cb98f02b6ff237eb61e0/results_id:
1
# 447.dealII,[.] _ZNK9MappingQ1ILi3EE12compute_fillERK12TriaIte regressed by 114
from (for last_good == 955c9437fd605216445fbd608de4ef1d96f825e9)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2 artifacts/build-955c9437fd605216445fbd608de4ef1d96f825e9/results_id:
1
This commit has regressed these CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Even more details: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Reproduce builds:
<cut>
mkdir investigate-llvm-50f4ae58eb136bc9d802cb98f02b6ff237eb61e0
cd investigate-llvm-50f4ae58eb136bc9d802cb98f02b6ff237eb61e0
# Fetch scripts
git clone https://git.linaro.org/toolchain/jenkins-scripts
# Fetch manifests and test.sh script
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 50f4ae58eb136bc9d802cb98f02b6ff237eb61e0
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 955c9437fd605216445fbd608de4ef1d96f825e9
../artifacts/test.sh
cd ..
</cut>
Full commit (up to 1000 lines):
<cut>
commit 50f4ae58eb136bc9d802cb98f02b6ff237eb61e0
Author: David Green <david.green(a)arm.com>
Date: Mon Aug 23 21:07:55 2021 +0100
[AArch64] Correct store ReadAdrBase operand
It appears that the Read operand for stores was being placed on the
first operand (the stored value) not the address base. This adds a
ReadST for the stored value operand, allowing the ReadAdrBase to
correctly act upon the address.
Differential Revision: https://reviews.llvm.org/D108287
---
llvm/lib/Target/AArch64/AArch64InstrFormats.td | 20 +-
llvm/lib/Target/AArch64/AArch64SchedA53.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedA55.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedA57.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedA64FX.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedCyclone.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedExynosM3.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedExynosM4.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedExynosM5.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedFalkor.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedKryo.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedTSV110.td | 1 +
llvm/lib/Target/AArch64/AArch64SchedThunderX.td | 1 +
.../lib/Target/AArch64/AArch64SchedThunderX2T99.td | 1 +
.../Target/AArch64/AArch64SchedThunderX3T110.td | 1 +
llvm/lib/Target/AArch64/AArch64Schedule.td | 1 +
.../llvm-mca/AArch64/Cortex/A55-store-readadv.s | 246 ++++++++++-----------
17 files changed, 148 insertions(+), 133 deletions(-)
diff --git a/llvm/lib/Target/AArch64/AArch64InstrFormats.td b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
index 10c6fcd5cacd..ea0c62d2045f 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrFormats.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
@@ -3482,7 +3482,7 @@ multiclass Store8RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
[(storeop (Ty regtype:$Rt),
(ro_Windexed8 GPR64sp:$Rn, GPR32:$Rm,
ro_Wextend8:$extend))]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b0;
}
@@ -3492,7 +3492,7 @@ multiclass Store8RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
[(storeop (Ty regtype:$Rt),
(ro_Xindexed8 GPR64sp:$Rn, GPR64:$Rm,
ro_Xextend8:$extend))]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b1;
}
@@ -3554,7 +3554,7 @@ multiclass Store16RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
[(storeop (Ty regtype:$Rt),
(ro_Windexed16 GPR64sp:$Rn, GPR32:$Rm,
ro_Wextend16:$extend))]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b0;
}
@@ -3564,7 +3564,7 @@ multiclass Store16RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
[(storeop (Ty regtype:$Rt),
(ro_Xindexed16 GPR64sp:$Rn, GPR64:$Rm,
ro_Xextend16:$extend))]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b1;
}
@@ -3626,7 +3626,7 @@ multiclass Store32RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
[(storeop (Ty regtype:$Rt),
(ro_Windexed32 GPR64sp:$Rn, GPR32:$Rm,
ro_Wextend32:$extend))]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b0;
}
@@ -3636,7 +3636,7 @@ multiclass Store32RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
[(storeop (Ty regtype:$Rt),
(ro_Xindexed32 GPR64sp:$Rn, GPR64:$Rm,
ro_Xextend32:$extend))]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b1;
}
@@ -3698,7 +3698,7 @@ multiclass Store64RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
[(storeop (Ty regtype:$Rt),
(ro_Windexed64 GPR64sp:$Rn, GPR32:$Rm,
ro_Wextend64:$extend))]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b0;
}
@@ -3708,7 +3708,7 @@ multiclass Store64RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
[(storeop (Ty regtype:$Rt),
(ro_Xindexed64 GPR64sp:$Rn, GPR64:$Rm,
ro_Xextend64:$extend))]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b1;
}
@@ -3768,7 +3768,7 @@ multiclass Store128RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
def roW : LoadStore128RO<sz, V, opc, regtype, asm, (outs),
(ins regtype:$Rt, GPR64sp:$Rn, GPR32:$Rm, ro_Wextend128:$extend),
[]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b0;
}
@@ -3776,7 +3776,7 @@ multiclass Store128RO<bits<2> sz, bit V, bits<2> opc, DAGOperand regtype,
def roX : LoadStore128RO<sz, V, opc, regtype, asm, (outs),
(ins regtype:$Rt, GPR64sp:$Rn, GPR64:$Rm, ro_Xextend128:$extend),
[]>,
- Sched<[WriteSTIdx, ReadAdrBase]> {
+ Sched<[WriteSTIdx, ReadST, ReadAdrBase]> {
let Inst{13} = 0b1;
}
diff --git a/llvm/lib/Target/AArch64/AArch64SchedA53.td b/llvm/lib/Target/AArch64/AArch64SchedA53.td
index 65c84b1f39c0..3fef369a4e2b 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedA53.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedA53.td
@@ -149,6 +149,7 @@ def A53WriteFSqrtDP : SchedWriteRes<[A53UnitFPMDS]> { let Latency = 32;
// No forwarding for these reads.
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
+def : ReadAdvance<ReadST, 0>;
def : ReadAdvance<ReadVLD, 0>;
// ALU - Most operands in the ALU pipes are not needed for two cycles. Shiftable
diff --git a/llvm/lib/Target/AArch64/AArch64SchedA55.td b/llvm/lib/Target/AArch64/AArch64SchedA55.td
index 0e680078c348..34d6fb5fb306 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedA55.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedA55.td
@@ -182,6 +182,7 @@ def CortexA55WriteFSqrtDP : SchedWriteRes<[CortexA55UnitFPDIV]> { let Latency =
def : ReadAdvance<ReadVLD, 0>;
def : ReadAdvance<ReadExtrHi, 1>;
def : ReadAdvance<ReadAdrBase, 1>;
+def : ReadAdvance<ReadST, 1>;
// ALU - ALU input operands are generally needed in EX1. An operand produced in
// in say EX2 can be forwarded for consumption to ALU in EX1, thereby
diff --git a/llvm/lib/Target/AArch64/AArch64SchedA57.td b/llvm/lib/Target/AArch64/AArch64SchedA57.td
index c1eacca8cc1f..c9addac18ba7 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedA57.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedA57.td
@@ -116,6 +116,7 @@ def : ReadAdvance<ReadIM, 0>;
def : ReadAdvance<ReadIMA, 2, [WriteIM32, WriteIM64]>;
def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
+def : ReadAdvance<ReadST, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
diff --git a/llvm/lib/Target/AArch64/AArch64SchedA64FX.td b/llvm/lib/Target/AArch64/AArch64SchedA64FX.td
index 6df800487ce2..dc551364ed6f 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedA64FX.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedA64FX.td
@@ -761,6 +761,7 @@ def : ReadAdvance<ReadIMA, 0>;
def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
+def : ReadAdvance<ReadST, 0>;
def : ReadAdvance<ReadVLD, 0>;
//===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AArch64/AArch64SchedCyclone.td b/llvm/lib/Target/AArch64/AArch64SchedCyclone.td
index 11df304a974c..310c240966f9 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedCyclone.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedCyclone.td
@@ -258,6 +258,7 @@ def CyReadAdrBase : SchedReadVariant<[
SchedVar<ScaledIdxPred, [ReadBaseRS]>, // Read base reg after shifting offset.
SchedVar<NoSchedPred, [ReadDefault]>]>; // Read base reg with no shift.
def : SchedAlias<ReadAdrBase, CyReadAdrBase>; // Map AArch64->Cyclone type.
+def : ReadAdvance<ReadST, 0>;
//---
// 7.8.9,7.8.11. Load/Store, paired
diff --git a/llvm/lib/Target/AArch64/AArch64SchedExynosM3.td b/llvm/lib/Target/AArch64/AArch64SchedExynosM3.td
index 6a33258be02c..a96917c9364a 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedExynosM3.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedExynosM3.td
@@ -277,6 +277,7 @@ def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
//===----------------------------------------------------------------------===//
// Finer scheduling model.
diff --git a/llvm/lib/Target/AArch64/AArch64SchedExynosM4.td b/llvm/lib/Target/AArch64/AArch64SchedExynosM4.td
index db066a19b0b6..8c5d6bbf0ceb 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedExynosM4.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedExynosM4.td
@@ -581,6 +581,7 @@ def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
//===----------------------------------------------------------------------===//
// Finer scheduling model.
diff --git a/llvm/lib/Target/AArch64/AArch64SchedExynosM5.td b/llvm/lib/Target/AArch64/AArch64SchedExynosM5.td
index 0429b6ab2ee2..64f88d719aa9 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedExynosM5.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedExynosM5.td
@@ -616,6 +616,7 @@ def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
//===----------------------------------------------------------------------===//
// Finer scheduling model.
diff --git a/llvm/lib/Target/AArch64/AArch64SchedFalkor.td b/llvm/lib/Target/AArch64/AArch64SchedFalkor.td
index 8bb95e442249..8c40efd07e8a 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedFalkor.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedFalkor.td
@@ -111,6 +111,7 @@ def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
// Detailed Refinements
// -----------------------------------------------------------------------------
diff --git a/llvm/lib/Target/AArch64/AArch64SchedKryo.td b/llvm/lib/Target/AArch64/AArch64SchedKryo.td
index 45964e1ed6de..f824ce462fe0 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedKryo.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedKryo.td
@@ -117,6 +117,7 @@ def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
//===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AArch64/AArch64SchedTSV110.td b/llvm/lib/Target/AArch64/AArch64SchedTSV110.td
index 438371c1b6a8..4a1b5167e89d 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedTSV110.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedTSV110.td
@@ -113,6 +113,7 @@ def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
def : InstRW<[WriteI], (instrs COPY)>;
diff --git a/llvm/lib/Target/AArch64/AArch64SchedThunderX.td b/llvm/lib/Target/AArch64/AArch64SchedThunderX.td
index 125eb284cfd1..f41f12733e69 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedThunderX.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedThunderX.td
@@ -192,6 +192,7 @@ def THXT8XWriteFSqrtDP : SchedWriteRes<[THXT8XUnitFPMDS]> {
def : ReadAdvance<ReadExtrHi, 1>;
def : ReadAdvance<ReadAdrBase, 2>;
def : ReadAdvance<ReadVLD, 2>;
+def : ReadAdvance<ReadST, 2>;
// FIXME: This needs more targeted benchmarking.
// ALU - Most operands in the ALU pipes are not needed for two cycles. Shiftable
diff --git a/llvm/lib/Target/AArch64/AArch64SchedThunderX2T99.td b/llvm/lib/Target/AArch64/AArch64SchedThunderX2T99.td
index 8d8675b7ac6f..0da286e942a0 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedThunderX2T99.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedThunderX2T99.td
@@ -362,6 +362,7 @@ def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
//===----------------------------------------------------------------------===//
// 3. Instruction Tables.
diff --git a/llvm/lib/Target/AArch64/AArch64SchedThunderX3T110.td b/llvm/lib/Target/AArch64/AArch64SchedThunderX3T110.td
index 00838cc4b9bd..8f03be9be0dd 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedThunderX3T110.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedThunderX3T110.td
@@ -621,6 +621,7 @@ def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
//===----------------------------------------------------------------------===//
// 3. Instruction Tables.
diff --git a/llvm/lib/Target/AArch64/AArch64Schedule.td b/llvm/lib/Target/AArch64/AArch64Schedule.td
index 49c0c1782236..4e5a67a3a394 100644
--- a/llvm/lib/Target/AArch64/AArch64Schedule.td
+++ b/llvm/lib/Target/AArch64/AArch64Schedule.td
@@ -47,6 +47,7 @@ def WriteAdr : SchedWrite; // Address pre/post increment.
def WriteLDIdx : SchedWrite; // Load from a register index (maybe scaled).
def WriteSTIdx : SchedWrite; // Store to a register index (maybe scaled).
+def ReadST : SchedRead; // Read the stored value.
def ReadAdrBase : SchedRead; // Read the base resister of a reg-offset LD/ST.
// Serialized two-level address load.
diff --git a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-store-readadv.s b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-store-readadv.s
index ff45caf46e21..ad49a96c27c5 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-store-readadv.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Cortex/A55-store-readadv.s
@@ -125,12 +125,12 @@ stp x0, x1, [x2], #16
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 11800
-# CHECK-NEXT: Total Cycles: 20301
+# CHECK-NEXT: Total Cycles: 19801
# CHECK-NEXT: Total uOps: 14400
# CHECK: Dispatch Width: 2
-# CHECK-NEXT: uOps Per Cycle: 0.71
-# CHECK-NEXT: IPC: 0.58
+# CHECK-NEXT: uOps Per Cycle: 0.73
+# CHECK-NEXT: IPC: 0.60
# CHECK-NEXT: Block RThroughput: 72.0
# CHECK: Instruction Info:
@@ -401,127 +401,127 @@ stp x0, x1, [x2], #16
# CHECK-NEXT: - - - - - - - - - - - 1.00 stp x0, x1, [x2], #16
# CHECK: Timeline view:
-# CHECK-NEXT: 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789
-# CHECK-NEXT: Index 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123
+# CHECK-NEXT: 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 012345678
+# CHECK-NEXT: Index 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789 0123456789
-# CHECK: [0,0] DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,1] . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str b0, [x2, #16]
-# CHECK-NEXT: [0,2] . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,3] . .DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str b0, [x2, #16]!
-# CHECK-NEXT: [0,4] . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,5] . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str b0, [x2], #16
-# CHECK-NEXT: [0,6] . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,7] . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str d0, [x2], #16
-# CHECK-NEXT: [0,8] . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,9] . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str d0, [x2, #16]!
-# CHECK-NEXT: [0,10] . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,11] . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str d0, [x2, #16]
-# CHECK-NEXT: [0,12] . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,13] . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str h0, [x2], #16
-# CHECK-NEXT: [0,14] . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,15] . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str h0, [x2, #16]!
-# CHECK-NEXT: [0,16] . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,17] . . . . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str h0, [x2, #16]
-# CHECK-NEXT: [0,18] . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,19] . . . . . . . .DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str q0, [x2], #16
-# CHECK-NEXT: [0,20] . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,21] . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str q0, [x2, #16]!
-# CHECK-NEXT: [0,22] . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,23] . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str q0, [x2, #16]
-# CHECK-NEXT: [0,24] . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,25] . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str s0, [x2], #16
-# CHECK-NEXT: [0,26] . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,27] . . . . . . . . . . .DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str s0, [x2, #16]!
-# CHECK-NEXT: [0,28] . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,29] . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str s0, [x2, #16]
-# CHECK-NEXT: [0,30] . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,31] . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str w0, [x2], #16
-# CHECK-NEXT: [0,32] . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,33] . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str w0, [x2, #16]!
-# CHECK-NEXT: [0,34] . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,35] . . . . . . . . . . . . . .DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . str w0, [x2, #16]
-# CHECK-NEXT: [0,36] . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,37] . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . str x0, [x2], #16
-# CHECK-NEXT: [0,38] . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,39] . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . str x0, [x2, #16]!
-# CHECK-NEXT: [0,40] . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,41] . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . str x0, [x2, #16]
-# CHECK-NEXT: [0,42] . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,43] . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . strb w0, [x2], #16
-# CHECK-NEXT: [0,44] . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,45] . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . strb w0, [x2, #16]!
-# CHECK-NEXT: [0,46] . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,47] . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . strb w0, [x2, #16]
-# CHECK-NEXT: [0,48] . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,49] . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . . . . . . . . . . . . . . strh w0, [x2], #16
-# CHECK-NEXT: [0,50] . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,51] . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . strh w0, [x2, #16]!
-# CHECK-NEXT: [0,52] . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,53] . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . strh w0, [x2, #16]
-# CHECK-NEXT: [0,54] . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,55] . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . str d0, [x2, x2, lsl #3]
-# CHECK-NEXT: [0,56] . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,57] . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . str q0, [x2, w0, sxtw]
-# CHECK-NEXT: [0,58] . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,59] . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . . . . str w0, [x2, w0, sxtw]
-# CHECK-NEXT: [0,60] . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,61] . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . . . . . . . . . . str x0, [x2, w0, sxtw]
-# CHECK-NEXT: [0,62] . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,63] . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . strb w0, [x2, w0, sxtw]
-# CHECK-NEXT: [0,64] . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,65] . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . strh w0, [x2, w0, sxtw]
-# CHECK-NEXT: [0,66] . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,67] . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . stur b0, [x2, #255]
-# CHECK-NEXT: [0,68] . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,69] . . . . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . stur d0, [x2, #255]
-# CHECK-NEXT: [0,70] . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,71] . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . . . . . . . stur h0, [x2, #255]
-# CHECK-NEXT: [0,72] . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,73] . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . stur q0, [x2, #255]
-# CHECK-NEXT: [0,74] . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,75] . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . stur s0, [x2, #255]
-# CHECK-NEXT: [0,76] . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,77] . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . stur w0, [x2, #255]
-# CHECK-NEXT: [0,78] . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,79] . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . sturb w0, [x2, #255]
-# CHECK-NEXT: [0,80] . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,81] . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . . . . sturh w0, [x2, #255]
-# CHECK-NEXT: [0,82] . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,83] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . stnp d0, d1, [x2, #16]
-# CHECK-NEXT: [0,84] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,85] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . stnp q0, q1, [x2, #16]
-# CHECK-NEXT: [0,86] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,87] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . stnp s0, s1, [x2, #16]
-# CHECK-NEXT: [0,88] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,89] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . stnp s0, s1, [x2, #16]
-# CHECK-NEXT: [0,90] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,91] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . stnp w0, w1, [x2, #16]
-# CHECK-NEXT: [0,92] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,93] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . stnp x0, x1, [x2, #16]
-# CHECK-NEXT: [0,94] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,95] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . stp d0, d1, [x2, #16]
-# CHECK-NEXT: [0,96] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,97] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . stp d0, d1, [x2, #16]!
-# CHECK-NEXT: [0,98] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,99] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . stp d0, d1, [x2], #16
-# CHECK-NEXT: [0,100] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,101] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . stp q0, q1, [x2, #16]
-# CHECK-NEXT: [0,102] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,103] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . stp q0, q1, [x2, #16]!
-# CHECK-NEXT: [0,104] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . add x2, x3, #1
-# CHECK-NEXT: [0,105] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . stp q0, q1, [x2], #16
-# CHECK-NEXT: [0,106] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . add x2, x3, #1
-# CHECK-NEXT: [0,107] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . stp s0, s1, [x2, #16]
-# CHECK-NEXT: [0,108] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . add x2, x3, #1
-# CHECK-NEXT: [0,109] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . stp s0, s1, [x2, #16]!
-# CHECK-NEXT: [0,110] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . add x2, x3, #1
-# CHECK-NEXT: [0,111] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . stp s0, s1, [x2], #16
-# CHECK-NEXT: [0,112] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . add x2, x3, #1
-# CHECK-NEXT: [0,113] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . stp x0, x1, [x2, #16]
-# CHECK-NEXT: [0,114] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . add x2, x3, #1
-# CHECK-NEXT: [0,115] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE. . stp x0, x1, [x2, #16]!
-# CHECK-NEXT: [0,116] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE. add x2, x3, #1
-# CHECK-NEXT: [0,117] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE stp x0, x1, [x2], #16
+# CHECK: [0,0] DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,1] . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str b0, [x2, #16]
+# CHECK-NEXT: [0,2] . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,3] . .DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str b0, [x2, #16]!
+# CHECK-NEXT: [0,4] . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,5] . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str b0, [x2], #16
+# CHECK-NEXT: [0,6] . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,7] . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str d0, [x2], #16
+# CHECK-NEXT: [0,8] . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,9] . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str d0, [x2, #16]!
+# CHECK-NEXT: [0,10] . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,11] . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str d0, [x2, #16]
+# CHECK-NEXT: [0,12] . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,13] . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str h0, [x2], #16
+# CHECK-NEXT: [0,14] . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,15] . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str h0, [x2, #16]!
+# CHECK-NEXT: [0,16] . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,17] . . . . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str h0, [x2, #16]
+# CHECK-NEXT: [0,18] . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,19] . . . . . . . .DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str q0, [x2], #16
+# CHECK-NEXT: [0,20] . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,21] . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str q0, [x2, #16]!
+# CHECK-NEXT: [0,22] . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,23] . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str q0, [x2, #16]
+# CHECK-NEXT: [0,24] . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,25] . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str s0, [x2], #16
+# CHECK-NEXT: [0,26] . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,27] . . . . . . . . . . .DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str s0, [x2, #16]!
+# CHECK-NEXT: [0,28] . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,29] . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . str s0, [x2, #16]
+# CHECK-NEXT: [0,30] . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,31] . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . . . . . . str w0, [x2], #16
+# CHECK-NEXT: [0,32] . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,33] . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . . . str w0, [x2, #16]!
+# CHECK-NEXT: [0,34] . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,35] . . . . . . . . . . . . . .DE . . . . . . . . . . . . . . . . . . . . . . . . . . . str w0, [x2, #16]
+# CHECK-NEXT: [0,36] . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,37] . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . . str x0, [x2], #16
+# CHECK-NEXT: [0,38] . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,39] . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . . . . . . . . . . str x0, [x2, #16]!
+# CHECK-NEXT: [0,40] . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,41] . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . . str x0, [x2, #16]
+# CHECK-NEXT: [0,42] . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,43] . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . . strb w0, [x2], #16
+# CHECK-NEXT: [0,44] . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,45] . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . . . strb w0, [x2, #16]!
+# CHECK-NEXT: [0,46] . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,47] . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . . . . . . . strb w0, [x2, #16]
+# CHECK-NEXT: [0,48] . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,49] . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . . . . . . . . . . . . . strh w0, [x2], #16
+# CHECK-NEXT: [0,50] . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,51] . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . . strh w0, [x2, #16]!
+# CHECK-NEXT: [0,52] . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,53] . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . strh w0, [x2, #16]
+# CHECK-NEXT: [0,54] . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,55] . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . . str d0, [x2, x2, lsl #3]
+# CHECK-NEXT: [0,56] . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,57] . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . . str q0, [x2, w0, sxtw]
+# CHECK-NEXT: [0,58] . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,59] . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . . . . . . . . . . str w0, [x2, w0, sxtw]
+# CHECK-NEXT: [0,60] . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,61] . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . . . str x0, [x2, w0, sxtw]
+# CHECK-NEXT: [0,62] . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,63] . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . strb w0, [x2, w0, sxtw]
+# CHECK-NEXT: [0,64] . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,65] . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . . strh w0, [x2, w0, sxtw]
+# CHECK-NEXT: [0,66] . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,67] . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . . . stur b0, [x2, #255]
+# CHECK-NEXT: [0,68] . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,69] . . . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . . . . stur d0, [x2, #255]
+# CHECK-NEXT: [0,70] . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,71] . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . . . . . . . stur h0, [x2, #255]
+# CHECK-NEXT: [0,72] . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,73] . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . stur q0, [x2, #255]
+# CHECK-NEXT: [0,74] . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,75] . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . . stur s0, [x2, #255]
+# CHECK-NEXT: [0,76] . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,77] . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . . . stur w0, [x2, #255]
+# CHECK-NEXT: [0,78] . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,79] . . . . . . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . . . . sturb w0, [x2, #255]
+# CHECK-NEXT: [0,80] . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,81] . . . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . . . . sturh w0, [x2, #255]
+# CHECK-NEXT: [0,82] . . . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,83] . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . stnp d0, d1, [x2, #16]
+# CHECK-NEXT: [0,84] . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,85] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . . stnp q0, q1, [x2, #16]
+# CHECK-NEXT: [0,86] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,87] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . . . stnp s0, s1, [x2, #16]
+# CHECK-NEXT: [0,88] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,89] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . . . . . stnp s0, s1, [x2, #16]
+# CHECK-NEXT: [0,90] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,91] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . . . . . stnp w0, w1, [x2, #16]
+# CHECK-NEXT: [0,92] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,93] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . stnp x0, x1, [x2, #16]
+# CHECK-NEXT: [0,94] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,95] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . . stp d0, d1, [x2, #16]
+# CHECK-NEXT: [0,96] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,97] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . . stp d0, d1, [x2, #16]!
+# CHECK-NEXT: [0,98] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,99] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . . . stp d0, d1, [x2], #16
+# CHECK-NEXT: [0,100] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,101] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE. . . . . . . stp q0, q1, [x2, #16]
+# CHECK-NEXT: [0,102] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,103] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . . . . stp q0, q1, [x2, #16]!
+# CHECK-NEXT: [0,104] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . . add x2, x3, #1
+# CHECK-NEXT: [0,105] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . . stp q0, q1, [x2], #16
+# CHECK-NEXT: [0,106] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DeeE. . . . . add x2, x3, #1
+# CHECK-NEXT: [0,107] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . stp s0, s1, [x2, #16]
+# CHECK-NEXT: [0,108] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . . add x2, x3, #1
+# CHECK-NEXT: [0,109] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . . . stp s0, s1, [x2, #16]!
+# CHECK-NEXT: [0,110] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . . add x2, x3, #1
+# CHECK-NEXT: [0,111] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .DE . . . stp s0, s1, [x2], #16
+# CHECK-NEXT: [0,112] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . add x2, x3, #1
+# CHECK-NEXT: [0,113] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE . . stp x0, x1, [x2, #16]
+# CHECK-NEXT: [0,114] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE . . add x2, x3, #1
+# CHECK-NEXT: [0,115] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE. . stp x0, x1, [x2, #16]!
+# CHECK-NEXT: [0,116] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DeeE. add x2, x3, #1
+# CHECK-NEXT: [0,117] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . DE stp x0, x1, [x2], #16
# CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
</cut>
3 years, 9 months
- 1
- 0