linaro-toolchain

linaro-toolchain@lists.linaro.org

9 participants
5482 discussions

[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O3 - Build # 8 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3. So far, this commit has regressed CI configurations: - tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3 Culprit: <cut> commit e771614bae0a05585f720812d5936a0b81dcddf0 Author: David Green <david.green(a)arm.com> Date: Thu Feb 11 11:58:55 2021 +0000 [ARM] Change getScalarizationOverhead overload used in gather costs. NFC This changes which of the getScalarizationOverhead overloads is used in the gather/scatter cost to use the base variant directly, not relying on the version using heuristics on the number of args with no args provided. It should still produce the same costs for scalarized gathers/scatters. </cut> Results regressed to (for first_bad == e771614bae0a05585f720812d5936a0b81dcddf0) # 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-e771614bae0a05585f720812d5936a0b81dcddf0/results_id: 1 # 445.gobmk,[.] fastlib regressed by 115 from (for last_good == a31eae840525e9292a3a42c1fdac3fc594f42949) # 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-a31eae840525e9292a3a42c1fdac3fc594f42949/results_id: 1 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/3644 Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/3642 Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Configuration details: Reproduce builds: <cut> mkdir investigate-llvm-e771614bae0a05585f720812d5936a0b81dcddf0 cd investigate-llvm-e771614bae0a05585f720812d5936a0b81dcddf0 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_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --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 e771614bae0a05585f720812d5936a0b81dcddf0 ../artifacts/test.sh # Reproduce last_good build git checkout --detach a31eae840525e9292a3a42c1fdac3fc594f42949 ../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_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Full commit (up to 1000 lines): <cut> commit e771614bae0a05585f720812d5936a0b81dcddf0 Author: David Green <david.green(a)arm.com> Date: Thu Feb 11 11:58:55 2021 +0000 [ARM] Change getScalarizationOverhead overload used in gather costs. NFC This changes which of the getScalarizationOverhead overloads is used in the gather/scatter cost to use the base variant directly, not relying on the version using heuristics on the number of args with no args provided. It should still produce the same costs for scalarized gathers/scatters. --- llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp index af67839c2d75..de2c0607d2ed 100644 --- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp +++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp @@ -1416,8 +1416,9 @@ unsigned ARMTTIImpl::getGatherScatterOpCost(unsigned Opcode, Type *DataTy, unsigned VectorCost = NumElems * LT.first * ST->getMVEVectorCostFactor(); // The scalarization cost should be a lot higher. We use the number of vector // elements plus the scalarization overhead. - unsigned ScalarCost = - NumElems * LT.first + BaseT::getScalarizationOverhead(VTy, {}); + unsigned ScalarCost = NumElems * LT.first + + BaseT::getScalarizationOverhead(VTy, true, false) + + BaseT::getScalarizationOverhead(VTy, false, true); if (EltSize < 8 || Alignment < EltSize / 8) return ScalarCost; </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3 - Build # 19 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations: - tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3 Culprit: <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. </cut> 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 -- -O3 artifacts/build-4389a413e2129d7d55ee779638b649aa852b6f8a/results_id: 1 # 470.lbm,lbm_base.default regressed by 108 # 447.dealII,dealII_base.default regressed by 104 # 447.dealII,[.] _ZNK12SparseMatrixIdE5vmultI6VectorIdES3_EEvRT regressed by 120 # 444.namd,namd_base.default regressed by 104 # 400.perlbench,perlbench_base.default regressed by 103 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 -- -O3 artifacts/build-dfce2909ee1ea1523ec27b834a0e56429e9c2beb/results_id: 1 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3640 Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3621 Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Configuration details: Reproduce builds: <cut> mkdir investigate-llvm-4389a413e2129d7d55ee779638b649aa852b6f8a cd investigate-llvm-4389a413e2129d7d55ee779638b649aa852b6f8a 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_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 4389a413e2129d7d55ee779638b649aa852b6f8a ../artifacts/test.sh # Reproduce last_good build git checkout --detach dfce2909ee1ea1523ec27b834a0e56429e9c2beb ../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_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… 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, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O3_LTO - Build # 5 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO. So far, this commit has regressed CI configurations: - tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO Culprit: <cut> commit 669ddd1e9b1226432b003dbba05b99f8e992285b Author: Arthur Eubanks <aeubanks(a)google.com> Date: Mon Jan 25 11:00:56 2021 -0800 Turn on the new pass manager by default This turns on the new pass manager by default for the optimization pipeline in Clang and ThinLTO in various LLD backends. This also makes uses of `opt -instcombine` use the new pass manager (unless specifically opted out). This does not affect the backend target-dependent codegen pipeline. If this causes regressions, you can opt out of the new pass manager either via the -DENABLE_EXPERIMENTAL_NEW_PASS_MANAGER=OFF CMake flag while building LLVM, or via various compiler flags, e.g. -flegacy-pass-manager for Clang or -Wl,--lto-legacy-pass-manager for ELF LLD. Please file bugs for any regressions. Major differences: * The inliner works slightly differently * -O1 does some amount of inlining * LCSSA and LoopSimplify are run before all loop passes * Loop unswitching is implemented slightly differently * A new SpeculateAroundPHIs pass is added to the pipeline https://lists.llvm.org/pipermail/llvm-dev/2021-January/148098.html Reviewed By: asbirlea, ychen, MaskRay, echristo Differential Revision: https://reviews.llvm.org/D95380 </cut> Results regressed to (for first_bad == 669ddd1e9b1226432b003dbba05b99f8e992285b) # 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 -- -O3_LTO artifacts/build-669ddd1e9b1226432b003dbba05b99f8e992285b/results_id: 1 # 473.astar,astar_base.default regressed by 106 from (for last_good == b15cbaf5a03d0b32dbc32c37766e32ccf66e6c87) # 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 -- -O3_LTO artifacts/build-b15cbaf5a03d0b32dbc32c37766e32ccf66e6c87/results_id: 1 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/3543 Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/3539 Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… Configuration details: Reproduce builds: <cut> mkdir investigate-llvm-669ddd1e9b1226432b003dbba05b99f8e992285b cd investigate-llvm-669ddd1e9b1226432b003dbba05b99f8e992285b 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_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --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 669ddd1e9b1226432b003dbba05b99f8e992285b ../artifacts/test.sh # Reproduce last_good build git checkout --detach b15cbaf5a03d0b32dbc32c37766e32ccf66e6c87 ../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_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… Full commit (up to 1000 lines): <cut> commit 669ddd1e9b1226432b003dbba05b99f8e992285b Author: Arthur Eubanks <aeubanks(a)google.com> Date: Mon Jan 25 11:00:56 2021 -0800 Turn on the new pass manager by default This turns on the new pass manager by default for the optimization pipeline in Clang and ThinLTO in various LLD backends. This also makes uses of `opt -instcombine` use the new pass manager (unless specifically opted out). This does not affect the backend target-dependent codegen pipeline. If this causes regressions, you can opt out of the new pass manager either via the -DENABLE_EXPERIMENTAL_NEW_PASS_MANAGER=OFF CMake flag while building LLVM, or via various compiler flags, e.g. -flegacy-pass-manager for Clang or -Wl,--lto-legacy-pass-manager for ELF LLD. Please file bugs for any regressions. Major differences: * The inliner works slightly differently * -O1 does some amount of inlining * LCSSA and LoopSimplify are run before all loop passes * Loop unswitching is implemented slightly differently * A new SpeculateAroundPHIs pass is added to the pipeline https://lists.llvm.org/pipermail/llvm-dev/2021-January/148098.html Reviewed By: asbirlea, ychen, MaskRay, echristo Differential Revision: https://reviews.llvm.org/D95380 --- llvm/CMakeLists.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/llvm/CMakeLists.txt b/llvm/CMakeLists.txt index 1affc289e64b..f5298de9f7ca 100644 --- a/llvm/CMakeLists.txt +++ b/llvm/CMakeLists.txt @@ -688,8 +688,8 @@ else() endif() option(LLVM_ENABLE_PLUGINS "Enable plugin support" ${LLVM_ENABLE_PLUGINS_default}) -set(ENABLE_EXPERIMENTAL_NEW_PASS_MANAGER FALSE CACHE BOOL - "Enable the experimental new pass manager by default.") +set(ENABLE_EXPERIMENTAL_NEW_PASS_MANAGER TRUE CACHE BOOL + "Enable the new pass manager by default.") include(HandleLLVMOptions) </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-aarch64-spec2k6-Os_LTO - Build # 5 - Fixed!

by ci_notify＠linaro.org

Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Os_LTO. So far, this commit has regressed CI configurations: - tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Os_LTO Culprit: <cut> commit 0a241e90d4931a764109da70c2322a0a9386b1a7 Author: Roman Lebedev <lebedev.ri(a)gmail.com> Date: Sat Aug 7 15:59:21 2021 +0300 [NFC][InstCombine] `vector_reduce_xor(?ext(<n x i1>))` --> `?ext(vector_reduce_add(<n x i1>))` Instead of expanding it ourselves, we can just forward to `?ext(vector_reduce_add(<n x i1>))`, as per alive2: https://alive2.llvm.org/ce/z/ymz7zE (self) https://alive2.llvm.org/ce/z/eKu2v2 (skipped zext) https://alive2.llvm.org/ce/z/c3BXgc (skipped sext) </cut> Results regressed to (for first_bad == 0a241e90d4931a764109da70c2322a0a9386b1a7) # 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 -- -Os_LTO artifacts/build-0a241e90d4931a764109da70c2322a0a9386b1a7/results_id: 1 # 433.milc,milc_base.default regressed by 102 # 453.povray,povray_base.default regressed by 102 # 470.lbm,lbm_base.default regressed by 103 from (for last_good == c6ff867f92f67c6451ed1709f2af66211cb7b901) # 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 -- -Os_LTO artifacts/build-c6ff867f92f67c6451ed1709f2af66211cb7b901/results_id: 1 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… Results ID of last_good: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Os_LTO/3523 Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… Results ID of first_bad: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Os_LTO/3530 Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… Configuration details: Reproduce builds: <cut> mkdir investigate-llvm-0a241e90d4931a764109da70c2322a0a9386b1a7 cd investigate-llvm-0a241e90d4931a764109da70c2322a0a9386b1a7 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_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 0a241e90d4931a764109da70c2322a0a9386b1a7 ../artifacts/test.sh # Reproduce last_good build git checkout --detach c6ff867f92f67c6451ed1709f2af66211cb7b901 ../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_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… Full commit (up to 1000 lines): <cut> commit 0a241e90d4931a764109da70c2322a0a9386b1a7 Author: Roman Lebedev <lebedev.ri(a)gmail.com> Date: Sat Aug 7 15:59:21 2021 +0300 [NFC][InstCombine] `vector_reduce_xor(?ext(<n x i1>))` --> `?ext(vector_reduce_add(<n x i1>))` Instead of expanding it ourselves, we can just forward to `?ext(vector_reduce_add(<n x i1>))`, as per alive2: https://alive2.llvm.org/ce/z/ymz7zE (self) https://alive2.llvm.org/ce/z/eKu2v2 (skipped zext) https://alive2.llvm.org/ce/z/c3BXgc (skipped sext) --- llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp index 2ba326d791c2..210652e23377 100644 --- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp @@ -2038,20 +2038,17 @@ Instruction *InstCombinerImpl::visitCallInst(CallInst &CI) { if (IID == Intrinsic::vector_reduce_xor) { // Exclusive disjunction reduction over the vector with // (potentially-extended) i1 element type is actually a - // (potentially-extended) parity check: + // (potentially-extended) arithmetic `add` reduction over the original + // non-extended value: // vector_reduce_xor(?ext(<n x i1>)) // --> - // ?ext(trunc(vector_reduce_and(<n x i1>) to i1)) + // ?ext(vector_reduce_add(<n x i1>)) Value *Arg = II->getArgOperand(0); Value *Vect; if (match(Arg, m_ZExtOrSExtOrSelf(m_Value(Vect)))) { if (auto *FTy = dyn_cast<FixedVectorType>(Vect->getType())) if (FTy->getElementType() == Builder.getInt1Ty()) { - Value *V = Builder.CreateBitCast( - Vect, Builder.getIntNTy(FTy->getNumElements())); - Value *Res = Builder.CreateUnaryIntrinsic(Intrinsic::ctpop, V); - Res = Builder.CreateTrunc(Res, - IntegerType::get(Res->getContext(), 1)); + Value *Res = Builder.CreateAddReduce(Vect); if (Arg != Vect) Res = Builder.CreateCast(cast<CastInst>(Arg)->getOpcode(), Res, II->getType()); </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O2 - Build # 16 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2. So far, this commit has regressed CI configurations: - tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2 Culprit: <cut> commit 7d15c4941499b1454432d63604dc6bbe56e32ce7 Author: Sanjay Patel <spatel(a)rotateright.com> Date: Tue May 18 14:02:11 2021 -0400 [x86] trim zeros from constants for readability; NFC </cut> Results regressed to (for first_bad == 7d15c4941499b1454432d63604dc6bbe56e32ce7) # 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 -- -O2_marm artifacts/build-7d15c4941499b1454432d63604dc6bbe56e32ce7/results_id: 1 # 482.sphinx3,sphinx_livepretend_base.default regressed by 104 from (for last_good == 2257e4a70e4aabe7255161f3a54922d7dcf1c059) # 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 -- -O2_marm artifacts/build-2257e4a70e4aabe7255161f3a54922d7dcf1c059/results_id: 1 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/3446 Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/3510 Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Configuration details: Reproduce builds: <cut> mkdir investigate-llvm-7d15c4941499b1454432d63604dc6bbe56e32ce7 cd investigate-llvm-7d15c4941499b1454432d63604dc6bbe56e32ce7 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_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --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 7d15c4941499b1454432d63604dc6bbe56e32ce7 ../artifacts/test.sh # Reproduce last_good build git checkout --detach 2257e4a70e4aabe7255161f3a54922d7dcf1c059 ../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_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… Full commit (up to 1000 lines): <cut> commit 7d15c4941499b1454432d63604dc6bbe56e32ce7 Author: Sanjay Patel <spatel(a)rotateright.com> Date: Tue May 18 14:02:11 2021 -0400 [x86] trim zeros from constants for readability; NFC --- llvm/test/CodeGen/X86/fma-fneg-combine.ll | 58 +++++++++++++++---------------- 1 file changed, 29 insertions(+), 29 deletions(-) diff --git a/llvm/test/CodeGen/X86/fma-fneg-combine.ll b/llvm/test/CodeGen/X86/fma-fneg-combine.ll index a67595c1e95a..9e47548f27f1 100644 --- a/llvm/test/CodeGen/X86/fma-fneg-combine.ll +++ b/llvm/test/CodeGen/X86/fma-fneg-combine.ll @@ -11,7 +11,7 @@ define <16 x float> @test1(<16 x float> %a, <16 x float> %b, <16 x float> %c) { ; CHECK-NEXT: vfmsub213ps {{.*#+}} zmm0 = (zmm1 * zmm0) - zmm2 ; CHECK-NEXT: retq entry: - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 4) #2 ret <16 x float> %0 } @@ -28,7 +28,7 @@ define <16 x float> @test2(<16 x float> %a, <16 x float> %b, <16 x float> %c) { ; CHECK-NEXT: retq entry: %0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i32 4) #2 - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0 + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0 ret <16 x float> %sub.i } @@ -39,7 +39,7 @@ define <16 x float> @test3(<16 x float> %a, <16 x float> %b, <16 x float> %c) { ; CHECK-NEXT: retq entry: %0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 -1, i32 4) #2 - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0 + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0 ret <16 x float> %sub.i } @@ -50,7 +50,7 @@ define <16 x float> @test4(<16 x float> %a, <16 x float> %b, <16 x float> %c) { ; CHECK-NEXT: retq entry: %0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 -1, i32 4) #2 - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0 + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0 ret <16 x float> %sub.i } @@ -60,7 +60,7 @@ define <16 x float> @test5(<16 x float> %a, <16 x float> %b, <16 x float> %c) { ; CHECK-NEXT: vfmsub213ps {ru-sae}, %zmm2, %zmm1, %zmm0 ; CHECK-NEXT: retq entry: - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 10) #2 ret <16 x float> %0 } @@ -72,7 +72,7 @@ define <16 x float> @test6(<16 x float> %a, <16 x float> %b, <16 x float> %c) { ; CHECK-NEXT: retq entry: %0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 -1, i32 10) #2 - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0 + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0 ret <16 x float> %sub.i } @@ -84,7 +84,7 @@ define <8 x float> @test7(<8 x float> %a, <8 x float> %b, <8 x float> %c) { ; CHECK-NEXT: retq entry: %0 = tail call <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %c) #2 - %sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0 + %sub.i = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0 ret <8 x float> %sub.i } @@ -94,7 +94,7 @@ define <8 x float> @test8(<8 x float> %a, <8 x float> %b, <8 x float> %c) { ; CHECK-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2 ; CHECK-NEXT: retq entry: - %sub.c = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.c = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %sub.c) #2 ret <8 x float> %0 } @@ -109,7 +109,7 @@ define <8 x double> @test9(<8 x double> %a, <8 x double> %b, <8 x double> %c) { ; CHECK-NEXT: retq entry: %0 = tail call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a, <8 x double> %b, <8 x double> %c, i32 4) #2 - %sub.i = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %0 + %sub.i = fsub <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>, %0 ret <8 x double> %sub.i } @@ -123,7 +123,7 @@ define <2 x double> @test10(<2 x double> %a, <2 x double> %b, <2 x double> %c) { ; CHECK-NEXT: retq entry: %0 = tail call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 -1, i32 4) #2 - %sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %0 + %sub.i = fsub <2 x double> <double -0.0, double -0.0>, %0 ret <2 x double> %sub.i } @@ -149,7 +149,7 @@ define <4 x float> @test11(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze ; KNL-NEXT: vmovaps %xmm3, %xmm0 ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %sub.i, i8 %mask, i32 4) #10 ret <4 x float> %0 } @@ -169,7 +169,7 @@ define <4 x float> @test11b(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 z ; KNL-NEXT: vfmsub213ss {{.*#+}} xmm0 {%k1} = (xmm1 * xmm0) - xmm2 ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %sub.i, i8 %mask, i32 4) #10 ret <4 x float> %0 } @@ -194,7 +194,7 @@ entry: %0 = tail call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a, <8 x double> %b, <8 x double> %c, i32 4) #2 %bc = bitcast i8 %mask to <8 x i1> %sel = select <8 x i1> %bc, <8 x double> %0, <8 x double> %a - %sub.i = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %sel + %sub.i = fsub <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>, %sel ret <8 x double> %sub.i } @@ -218,7 +218,7 @@ define <2 x double> @test13(<2 x double> %a, <2 x double> %b, <2 x double> %c, i ; KNL-NEXT: retq entry: - %sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %a + %sub.i = fsub <2 x double> <double -0.0, double -0.0>, %a %0 = tail call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %sub.i, <2 x double> %b, <2 x double> %c, i8 %mask, i32 4) ret <2 x double> %0 } @@ -239,7 +239,7 @@ define <16 x float> @test14(<16 x float> %a, <16 x float> %b, <16 x float> %c, i ; KNL-NEXT: retq entry: %0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask, i32 10) #2 - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0 + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0 ret <16 x float> %sub.i } @@ -265,7 +265,7 @@ define <16 x float> @test15(<16 x float> %a, <16 x float> %b, <16 x float> %c, i ; KNL-NEXT: retq entry: %bc = bitcast i16 %mask to <16 x i1> - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %a %0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %sub.i, <16 x float> %b, <16 x float> %c, i32 10) %sel = select <16 x i1> %bc, <16 x float> %0, <16 x float> %sub.i %1 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %sel, <16 x float> %sub.i, <16 x float> %c, i32 9) @@ -285,7 +285,7 @@ define <16 x float> @test16(<16 x float> %a, <16 x float> %b, <16 x float> %c, i ; KNL-NEXT: kmovw %edi, %k1 ; KNL-NEXT: vfmsubadd132ps {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1} ; KNL-NEXT: retq - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c %res = call <16 x float> @llvm.x86.avx512.vfmaddsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 9) %bc = bitcast i16 %mask to <16 x i1> %sel = select <16 x i1> %bc, <16 x float> %res, <16 x float> %a @@ -305,7 +305,7 @@ define <8 x double> @test17(<8 x double> %a, <8 x double> %b, <8 x double> %c, i ; KNL-NEXT: kmovw %edi, %k1 ; KNL-NEXT: vfmsubadd132pd {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) -/+ zmm2 ; KNL-NEXT: retq - %sub.i = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %c + %sub.i = fsub <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>, %c %res = call <8 x double> @llvm.x86.avx512.vfmaddsub.pd.512(<8 x double> %a, <8 x double> %b, <8 x double> %sub.i, i32 4) %bc = bitcast i8 %mask to <8 x i1> %sel = select <8 x i1> %bc, <8 x double> %res, <8 x double> %a @@ -326,7 +326,7 @@ define <4 x float> @test18(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze ; KNL-NEXT: vfnmadd213ss {{.*#+}} xmm0 {%k1} = -(xmm1 * xmm0) + xmm2 ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b %0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %c, i8 %mask, i32 4) #10 ret <4 x float> %0 } @@ -344,8 +344,8 @@ define <4 x float> @test19(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze ; KNL-NEXT: vfnmsub213ss {{.*#+}} xmm0 {%k1} = -(xmm1 * xmm0) - xmm2 ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b - %sub.i.2 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b + %sub.i.2 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %sub.i.2, i8 %mask, i32 4) #10 ret <4 x float> %0 } @@ -365,7 +365,7 @@ define <4 x float> @test20(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze ; KNL-NEXT: vmovaps %xmm2, %xmm0 ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b %0 = tail call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %c, i8 %mask, i32 4) #10 ret <4 x float> %0 } @@ -383,7 +383,7 @@ define <4 x float> @test21(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze ; KNL-NEXT: vfnmadd213ss {rn-sae}, %xmm2, %xmm1, %xmm0 {%k1} ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b %0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %c, i8 %mask, i32 8) #10 ret <4 x float> %0 } @@ -401,8 +401,8 @@ define <4 x float> @test22(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze ; KNL-NEXT: vfnmsub213ss {rn-sae}, %xmm2, %xmm1, %xmm0 {%k1} ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b - %sub.i.2 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b + %sub.i.2 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %sub.i.2, i8 %mask, i32 8) #10 ret <4 x float> %0 } @@ -422,7 +422,7 @@ define <4 x float> @test23(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze ; KNL-NEXT: vmovaps %xmm2, %xmm0 ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b %0 = tail call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %c, i8 %mask, i32 8) #10 ret <4 x float> %0 } @@ -440,7 +440,7 @@ define <4 x float> @test24(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze ; KNL-NEXT: vfmsub213ss {rn-sae}, %xmm2, %xmm1, %xmm0 {%k1} ; KNL-NEXT: retq entry: - %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %sub.i, i8 %mask, i32 8) #10 ret <4 x float> %0 } @@ -451,8 +451,8 @@ define <16 x float> @test25(<16 x float> %a, <16 x float> %b, <16 x float> %c) ; CHECK-NEXT: vfnmsub213ps {rn-sae}, %zmm2, %zmm1, %zmm0 ; CHECK-NEXT: retq entry: - %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b - %sub.i.2 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c + %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %b + %sub.i.2 = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c %0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %sub.i, <16 x float> %sub.i.2, i32 8) #2 ret <16 x float> %0 } </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-release-aarch64-spec2k6-O2 - Build # 25 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations: - tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2 Culprit: <cut> commit df7c22831f1e48dba49479c5960c1c180d8eab2c Author: Richard Sandiford <richard.sandiford(a)arm.com> Date: Thu Nov 14 15:12:58 2019 +0000 Support vectorisation with mixed vector sizes After previous patches, it's now possible to make the vectoriser support multiple vector sizes in the same vector region, using related_vector_mode to pick the right vector mode for a given element mode. No port yet takes advantage of this, but I have a follow-on patch for AArch64. This patch also seemed like a good opportunity to add some more dump messages: one to make it clear which vector size/mode was being used when analysis passed or failed, and another to say when we've decided to skip a redundant vector size/mode. 2019-11-14 Richard Sandiford <richard.sandiford(a)arm.com> gcc/ * machmode.h (opt_machine_mode::operator==): New function. (opt_machine_mode::operator!=): Likewise. * tree-vectorizer.h (vec_info::vector_mode): Update comment. (get_related_vectype_for_scalar_type): Delete. (get_vectype_for_scalar_type_and_size): Declare. * tree-vect-slp.c (vect_slp_bb_region): Print dump messages to say whether analysis passed or failed, and with what vector modes. Use related_vector_mode to check whether trying a particular vector mode would be redundant with the autodetected mode, and print a dump message if we decide to skip it. * tree-vect-loop.c (vect_analyze_loop): Likewise. (vect_create_epilog_for_reduction): Use get_related_vectype_for_scalar_type instead of get_vectype_for_scalar_type_and_size. * tree-vect-stmts.c (get_vectype_for_scalar_type_and_size): Replace with... (get_related_vectype_for_scalar_type): ...this new function. Take a starting/"prevailing" vector mode rather than a vector size. Take an optional nunits argument, with the same meaning as for related_vector_mode. Use related_vector_mode when not auto-detecting a mode, falling back to mode_for_vector if no target mode exists. (get_vectype_for_scalar_type): Update accordingly. (get_same_sized_vectype): Likewise. * tree-vectorizer.c (get_vec_alignment_for_array_type): Likewise. From-SVN: r278240 </cut> Results regressed to (for first_bad == df7c22831f1e48dba49479c5960c1c180d8eab2c) # 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 -- -O2 artifacts/build-df7c22831f1e48dba49479c5960c1c180d8eab2c/results_id: 1 # 453.povray,[.] _ZN3povL24All_Sphere_IntersectionsEPNS_13Objec regressed by 114 # 482.sphinx3,[.] subvq_mgau_shortlist regressed by 112 from (for last_good == 7f52eb891b738337d5cf82c7c440a5eea8c7b0c9) # 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 -- -O2 artifacts/build-7f52eb891b738337d5cf82c7c440a5eea8c7b0c9/results_id: 1 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3483 Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3492 Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… Configuration details: Reproduce builds: <cut> mkdir investigate-gcc-df7c22831f1e48dba49479c5960c1c180d8eab2c cd investigate-gcc-df7c22831f1e48dba49479c5960c1c180d8eab2c 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_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --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 df7c22831f1e48dba49479c5960c1c180d8eab2c ../artifacts/test.sh # Reproduce last_good build git checkout --detach 7f52eb891b738337d5cf82c7c440a5eea8c7b0c9 ../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_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… Full commit (up to 1000 lines): <cut> commit df7c22831f1e48dba49479c5960c1c180d8eab2c Author: Richard Sandiford <richard.sandiford(a)arm.com> Date: Thu Nov 14 15:12:58 2019 +0000 Support vectorisation with mixed vector sizes After previous patches, it's now possible to make the vectoriser support multiple vector sizes in the same vector region, using related_vector_mode to pick the right vector mode for a given element mode. No port yet takes advantage of this, but I have a follow-on patch for AArch64. This patch also seemed like a good opportunity to add some more dump messages: one to make it clear which vector size/mode was being used when analysis passed or failed, and another to say when we've decided to skip a redundant vector size/mode. 2019-11-14 Richard Sandiford <richard.sandiford(a)arm.com> gcc/ * machmode.h (opt_machine_mode::operator==): New function. (opt_machine_mode::operator!=): Likewise. * tree-vectorizer.h (vec_info::vector_mode): Update comment. (get_related_vectype_for_scalar_type): Delete. (get_vectype_for_scalar_type_and_size): Declare. * tree-vect-slp.c (vect_slp_bb_region): Print dump messages to say whether analysis passed or failed, and with what vector modes. Use related_vector_mode to check whether trying a particular vector mode would be redundant with the autodetected mode, and print a dump message if we decide to skip it. * tree-vect-loop.c (vect_analyze_loop): Likewise. (vect_create_epilog_for_reduction): Use get_related_vectype_for_scalar_type instead of get_vectype_for_scalar_type_and_size. * tree-vect-stmts.c (get_vectype_for_scalar_type_and_size): Replace with... (get_related_vectype_for_scalar_type): ...this new function. Take a starting/"prevailing" vector mode rather than a vector size. Take an optional nunits argument, with the same meaning as for related_vector_mode. Use related_vector_mode when not auto-detecting a mode, falling back to mode_for_vector if no target mode exists. (get_vectype_for_scalar_type): Update accordingly. (get_same_sized_vectype): Likewise. * tree-vectorizer.c (get_vec_alignment_for_array_type): Likewise. From-SVN: r278240 --- gcc/ChangeLog | 28 +++++++++++++++++++++++++ gcc/machmode.h | 3 +++ gcc/tree-vect-loop.c | 54 +++++++++++++++++++++++++++++++++++------------- gcc/tree-vect-slp.c | 33 +++++++++++++++++++++++++---- gcc/tree-vect-stmts.c | 57 ++++++++++++++++++++++++++++++++++++--------------- gcc/tree-vectorizer.c | 2 +- gcc/tree-vectorizer.h | 8 +++++--- 7 files changed, 147 insertions(+), 38 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 41c94140b1a..680aa85121a 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,31 @@ +2019-11-14 Richard Sandiford <richard.sandiford(a)arm.com> + + * machmode.h (opt_machine_mode::operator==): New function. + (opt_machine_mode::operator!=): Likewise. + * tree-vectorizer.h (vec_info::vector_mode): Update comment. + (get_related_vectype_for_scalar_type): Delete. + (get_vectype_for_scalar_type_and_size): Declare. + * tree-vect-slp.c (vect_slp_bb_region): Print dump messages to say + whether analysis passed or failed, and with what vector modes. + Use related_vector_mode to check whether trying a particular + vector mode would be redundant with the autodetected mode, + and print a dump message if we decide to skip it. + * tree-vect-loop.c (vect_analyze_loop): Likewise. + (vect_create_epilog_for_reduction): Use + get_related_vectype_for_scalar_type instead of + get_vectype_for_scalar_type_and_size. + * tree-vect-stmts.c (get_vectype_for_scalar_type_and_size): Replace + with... + (get_related_vectype_for_scalar_type): ...this new function. + Take a starting/"prevailing" vector mode rather than a vector size. + Take an optional nunits argument, with the same meaning as for + related_vector_mode. Use related_vector_mode when not + auto-detecting a mode, falling back to mode_for_vector if no + target mode exists. + (get_vectype_for_scalar_type): Update accordingly. + (get_same_sized_vectype): Likewise. + * tree-vectorizer.c (get_vec_alignment_for_array_type): Likewise. + 2019-11-14 Richard Sandiford <richard.sandiford(a)arm.com> * tree-vect-stmts.c (vectorizable_call): Require the types diff --git a/gcc/machmode.h b/gcc/machmode.h index 6750833c2fe..a507ed66c3f 100644 --- a/gcc/machmode.h +++ b/gcc/machmode.h @@ -258,6 +258,9 @@ public: bool exists () const; template<typename U> bool exists (U *) const; + bool operator== (const T &m) const { return m_mode == m; } + bool operator!= (const T &m) const { return m_mode != m; } + private: machine_mode m_mode; }; diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index 213d620ed2c..e60c159d11a 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -2435,6 +2435,17 @@ vect_analyze_loop (class loop *loop, vec_info_shared *shared) res = vect_analyze_loop_2 (loop_vinfo, fatal, &n_stmts); if (mode_i == 0) autodetected_vector_mode = loop_vinfo->vector_mode; + if (dump_enabled_p ()) + { + if (res) + dump_printf_loc (MSG_NOTE, vect_location, + "***** Analysis succeeded with vector mode %s\n", + GET_MODE_NAME (loop_vinfo->vector_mode)); + else + dump_printf_loc (MSG_NOTE, vect_location, + "***** Analysis failed with vector mode %s\n", + GET_MODE_NAME (loop_vinfo->vector_mode)); + } loop->aux = NULL; if (res) @@ -2501,9 +2512,22 @@ vect_analyze_loop (class loop *loop, vec_info_shared *shared) } if (mode_i < vector_modes.length () - && known_eq (GET_MODE_SIZE (vector_modes[mode_i]), - GET_MODE_SIZE (autodetected_vector_mode))) - mode_i += 1; + && VECTOR_MODE_P (autodetected_vector_mode) + && (related_vector_mode (vector_modes[mode_i], + GET_MODE_INNER (autodetected_vector_mode)) + == autodetected_vector_mode) + && (related_vector_mode (autodetected_vector_mode, + GET_MODE_INNER (vector_modes[mode_i])) + == vector_modes[mode_i])) + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_NOTE, vect_location, + "***** Skipping vector mode %s, which would" + " repeat the analysis for %s\n", + GET_MODE_NAME (vector_modes[mode_i]), + GET_MODE_NAME (autodetected_vector_mode)); + mode_i += 1; + } if (mode_i == vector_modes.length () || autodetected_vector_mode == VOIDmode) @@ -4898,13 +4922,14 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info, halves against each other. */ enum machine_mode mode1 = mode; tree stype = TREE_TYPE (vectype); - unsigned sz = tree_to_uhwi (TYPE_SIZE_UNIT (vectype)); - unsigned sz1 = sz; + unsigned nunits = TYPE_VECTOR_SUBPARTS (vectype).to_constant (); + unsigned nunits1 = nunits; if (!slp_reduc && (mode1 = targetm.vectorize.split_reduction (mode)) != mode) - sz1 = GET_MODE_SIZE (mode1).to_constant (); + nunits1 = GET_MODE_NUNITS (mode1).to_constant (); - tree vectype1 = get_vectype_for_scalar_type_and_size (stype, sz1); + tree vectype1 = get_related_vectype_for_scalar_type (TYPE_MODE (vectype), + stype, nunits1); reduce_with_shift = have_whole_vector_shift (mode1); if (!VECTOR_MODE_P (mode1)) reduce_with_shift = false; @@ -4918,11 +4943,13 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info, /* First reduce the vector to the desired vector size we should do shift reduction on by combining upper and lower halves. */ new_temp = new_phi_result; - while (sz > sz1) + while (nunits > nunits1) { gcc_assert (!slp_reduc); - sz /= 2; - vectype1 = get_vectype_for_scalar_type_and_size (stype, sz); + nunits /= 2; + vectype1 = get_related_vectype_for_scalar_type (TYPE_MODE (vectype), + stype, nunits); + unsigned int bitsize = tree_to_uhwi (TYPE_SIZE (vectype1)); /* The target has to make sure we support lowpart/highpart extraction, either via direct vector extract or through @@ -4947,15 +4974,14 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info, = gimple_build_assign (dst2, BIT_FIELD_REF, build3 (BIT_FIELD_REF, vectype1, new_temp, TYPE_SIZE (vectype1), - bitsize_int (sz * BITS_PER_UNIT))); + bitsize_int (bitsize))); gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT); } else { /* Extract via punning to appropriately sized integer mode vector. */ - tree eltype = build_nonstandard_integer_type (sz * BITS_PER_UNIT, - 1); + tree eltype = build_nonstandard_integer_type (bitsize, 1); tree etype = build_vector_type (eltype, 2); gcc_assert (convert_optab_handler (vec_extract_optab, TYPE_MODE (etype), @@ -4984,7 +5010,7 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info, = gimple_build_assign (tem, BIT_FIELD_REF, build3 (BIT_FIELD_REF, eltype, new_temp, TYPE_SIZE (eltype), - bitsize_int (sz * BITS_PER_UNIT))); + bitsize_int (bitsize))); gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT); dst2 = make_ssa_name (vectype1); epilog_stmt = gimple_build_assign (dst2, VIEW_CONVERT_EXPR, diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c index 3885d9cbe4a..1e00db5a326 100644 --- a/gcc/tree-vect-slp.c +++ b/gcc/tree-vect-slp.c @@ -3203,7 +3203,12 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin, && dbg_cnt (vect_slp)) { if (dump_enabled_p ()) - dump_printf_loc (MSG_NOTE, vect_location, "SLPing BB part\n"); + { + dump_printf_loc (MSG_NOTE, vect_location, + "***** Analysis succeeded with vector mode" + " %s\n", GET_MODE_NAME (bb_vinfo->vector_mode)); + dump_printf_loc (MSG_NOTE, vect_location, "SLPing BB part\n"); + } bb_vinfo->shared->check_datarefs (); vect_schedule_slp (bb_vinfo); @@ -3223,6 +3228,13 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin, vectorized = true; } + else + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_NOTE, vect_location, + "***** Analysis failed with vector mode %s\n", + GET_MODE_NAME (bb_vinfo->vector_mode)); + } if (mode_i == 0) autodetected_vector_mode = bb_vinfo->vector_mode; @@ -3230,9 +3242,22 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin, delete bb_vinfo; if (mode_i < vector_modes.length () - && known_eq (GET_MODE_SIZE (vector_modes[mode_i]), - GET_MODE_SIZE (autodetected_vector_mode))) - mode_i += 1; + && VECTOR_MODE_P (autodetected_vector_mode) + && (related_vector_mode (vector_modes[mode_i], + GET_MODE_INNER (autodetected_vector_mode)) + == autodetected_vector_mode) + && (related_vector_mode (autodetected_vector_mode, + GET_MODE_INNER (vector_modes[mode_i])) + == vector_modes[mode_i])) + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_NOTE, vect_location, + "***** Skipping vector mode %s, which would" + " repeat the analysis for %s\n", + GET_MODE_NAME (vector_modes[mode_i]), + GET_MODE_NAME (autodetected_vector_mode)); + mode_i += 1; + } if (vectorized || mode_i == vector_modes.length () diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c index 80f59accad7..36f832bb522 100644 --- a/gcc/tree-vect-stmts.c +++ b/gcc/tree-vect-stmts.c @@ -11138,18 +11138,28 @@ vect_remove_stores (stmt_vec_info first_stmt_info) } } -/* Function get_vectype_for_scalar_type_and_size. +/* If NUNITS is nonzero, return a vector type that contains NUNITS + elements of type SCALAR_TYPE, or null if the target doesn't support + such a type. - Returns the vector type corresponding to SCALAR_TYPE and SIZE as supported - by the target. */ + If NUNITS is zero, return a vector type that contains elements of + type SCALAR_TYPE, choosing whichever vector size the target prefers. + + If PREVAILING_MODE is VOIDmode, we have not yet chosen a vector mode + for this vectorization region and want to "autodetect" the best choice. + Otherwise, PREVAILING_MODE is a previously-chosen vector TYPE_MODE + and we want the new type to be interoperable with it. PREVAILING_MODE + in this case can be a scalar integer mode or a vector mode; when it + is a vector mode, the function acts like a tree-level version of + related_vector_mode. */ tree -get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size) +get_related_vectype_for_scalar_type (machine_mode prevailing_mode, + tree scalar_type, poly_uint64 nunits) { tree orig_scalar_type = scalar_type; scalar_mode inner_mode; machine_mode simd_mode; - poly_uint64 nunits; tree vectype; if (!is_int_mode (TYPE_MODE (scalar_type), &inner_mode) @@ -11189,10 +11199,11 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size) if (scalar_type == NULL_TREE) return NULL_TREE; - /* If no size was supplied use the mode the target prefers. Otherwise - lookup a vector mode of the specified size. */ - if (known_eq (size, 0U)) + /* If no prevailing mode was supplied, use the mode the target prefers. + Otherwise lookup a vector mode based on the prevailing mode. */ + if (prevailing_mode == VOIDmode) { + gcc_assert (known_eq (nunits, 0U)); simd_mode = targetm.vectorize.preferred_simd_mode (inner_mode); if (SCALAR_INT_MODE_P (simd_mode)) { @@ -11208,9 +11219,19 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size) return NULL_TREE; } } - else if (!multiple_p (size, nbytes, &nunits) - || !mode_for_vector (inner_mode, nunits).exists (&simd_mode)) - return NULL_TREE; + else if (SCALAR_INT_MODE_P (prevailing_mode) + || !related_vector_mode (prevailing_mode, + inner_mode, nunits).exists (&simd_mode)) + { + /* Fall back to using mode_for_vector, mostly in the hope of being + able to use an integer mode. */ + if (known_eq (nunits, 0U) + && !multiple_p (GET_MODE_SIZE (prevailing_mode), nbytes, &nunits)) + return NULL_TREE; + + if (!mode_for_vector (inner_mode, nunits).exists (&simd_mode)) + return NULL_TREE; + } vectype = build_vector_type_for_mode (scalar_type, simd_mode); @@ -11238,9 +11259,8 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size) tree get_vectype_for_scalar_type (vec_info *vinfo, tree scalar_type) { - tree vectype; - poly_uint64 vector_size = GET_MODE_SIZE (vinfo->vector_mode); - vectype = get_vectype_for_scalar_type_and_size (scalar_type, vector_size); + tree vectype = get_related_vectype_for_scalar_type (vinfo->vector_mode, + scalar_type); if (vectype && vinfo->vector_mode == VOIDmode) vinfo->vector_mode = TYPE_MODE (vectype); return vectype; @@ -11273,8 +11293,13 @@ get_same_sized_vectype (tree scalar_type, tree vector_type) if (VECT_SCALAR_BOOLEAN_TYPE_P (scalar_type)) return truth_type_for (vector_type); - return get_vectype_for_scalar_type_and_size - (scalar_type, GET_MODE_SIZE (TYPE_MODE (vector_type))); + poly_uint64 nunits; + if (!multiple_p (GET_MODE_SIZE (TYPE_MODE (vector_type)), + GET_MODE_SIZE (TYPE_MODE (scalar_type)), &nunits)) + return NULL_TREE; + + return get_related_vectype_for_scalar_type (TYPE_MODE (vector_type), + scalar_type, nunits); } /* Function vect_is_simple_use. diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c index d6de78350e6..7be81a0b27f 100644 --- a/gcc/tree-vectorizer.c +++ b/gcc/tree-vectorizer.c @@ -1359,7 +1359,7 @@ get_vec_alignment_for_array_type (tree type) poly_uint64 array_size, vector_size; tree scalar_type = strip_array_types (type); - tree vectype = get_vectype_for_scalar_type_and_size (scalar_type, 0); + tree vectype = get_related_vectype_for_scalar_type (VOIDmode, scalar_type); if (!vectype || !poly_int_tree_p (TYPE_SIZE (type), &array_size) || !poly_int_tree_p (TYPE_SIZE (vectype), &vector_size) diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h index f6efed1f863..fadc4d89d16 100644 --- a/gcc/tree-vectorizer.h +++ b/gcc/tree-vectorizer.h @@ -335,8 +335,9 @@ public: /* Cost data used by the target cost model. */ void *target_cost_data; - /* If we've chosen a vector size for this vectorization region, - this is one mode that has such a size, otherwise it is VOIDmode. */ + /* The argument we should pass to related_vector_mode when looking up + the vector mode for a scalar mode, or VOIDmode if we haven't yet + made any decisions about which vector modes to use. */ machine_mode vector_mode; private: @@ -1624,8 +1625,9 @@ extern bool vect_can_advance_ivs_p (loop_vec_info); extern void vect_update_inits_of_drs (loop_vec_info, tree, tree_code); /* In tree-vect-stmts.c. */ +extern tree get_related_vectype_for_scalar_type (machine_mode, tree, + poly_uint64 = 0); extern tree get_vectype_for_scalar_type (vec_info *, tree); -extern tree get_vectype_for_scalar_type_and_size (tree, poly_uint64); extern tree get_mask_type_for_scalar_type (vec_info *, tree); extern tree get_same_sized_vectype (tree, tree); extern bool vect_get_loop_mask_type (loop_vec_info); </cut>

3 years, 3 months

[ACTIVITY] week ending Aug. 15 2021

by Alex Bennée

VirtIO Initiative ([STR-9]) =========================== - posted Enabling hypervisor agnosticism for VirtIO backends Message-Id: <87v94ldrqq.fsf(a)linaro.org> VirtIO RPMB ([STR-5]) - made more progress and now have PROGRAM_KEY/WRITE_COUNTER done - feels like it's getting faster [hacking branch] <https://github.com/stsquad/virtio-rpmb/tree/hacking> Fix VirtIO spec as per Rucha's email ------------------------------------ QEMU Upstream Work ([UM-2]) =========================== - posted [PATCH for 6.1-rc3 v1 0/4] gitlab and plugins pre-PR Message-Id: <20210806141015.2487502-1-alex.bennee(a)linaro.org> - prepared a potential [pull request for testing issues] but looks like it will wait for 6.2 [pull request for testing issues] <https://github.com/stsquad/qemu/tree/pr/120821-for-6.1-rc4-1> Write a generic overview of vhost user usage for the manual Enable plugins by default on TCG builds - [X] clean-up testing matrix Completed Reviews [10/10] ========================= [PATCH 00/13] new plugin argument passing scheme Message-Id: <20210717100920.240793-1-ma.mandourr(a)gmail.com> [PATCH 0/9] new plugin argument passing scheme Message-Id: <20210716080345.136784-1-ma.mandourr(a)gmail.com> [RFC PATCH] Subject: [RFC PATCH] plugins: Passed the parsed arguments directly to plugins Message-Id: <20210623155553.481099-1-ma.mandourr(a)gmail.com> [PATCH 3/6] plugins/cache: Fixed a use-after-free bug with multithreaded usermode Message-Id: <20210714172151.8494-4-ma.mandourr(a)gmail.com> [PATCH v8] tests/tcg/s390x: Test SIGILL and SIGSEGV handling Message-Id: <20210804225146.154513-1-iii(a)linux.ibm.com> [RFC PATCH v2] Add a post for the new TCG cache modelling plugin Message-Id: <20210617121707.764126-1-ma.mandourr(a)gmail.com> [PATCH for 6.1] plugins: do not limit exported symbols if modules are active Message-Id: <20210811100550.54714-1-pbonzini(a)redhat.com> [PATCH v4 00/13] new plugin argument passing scheme Message-Id: <20210730135817.17816-1-ma.mandourr(a)gmail.com> [PATCH 0/6] docs/devel: Organize devel manual into further subsections Message-Id: <20210804005621.1577302-1-jsnow(a)redhat.com> [PATCH] Makefile: Fix cscope issues on MacOS and soft links Message-Id: <20210801171144.60412-1-peterx(a)redhat.com> Absences ======== - Another partial week - On holiday for rest of August Current Review Queue ==================== TODO [PATCH v3] accel/tcg: Clear PAGE_WRITE before translation Message-Id: <20210805204835.158918-1-iii(a)linux.ibm.com> ===================================================================================================================== TODO [PATCH 0/7] tcg: some small towards more modular tcg Message-Id: <20210804143826.3402872-1-kraxel(a)redhat.com> ================================================================================================================= TODO [PATCH 0/2] Acceptance Tests: clean up of temporary dirs and MAINTAINERS entry Message-Id: <20210803193447.3946219-1-crosa(a)redhat.com> ========================================================================================================================================== TODO [PATCH v2 00/11] Atomic cleanup + clang-12 build fix Message-Id: <20210717014121.1784956-1-richard.henderson(a)linaro.org> ============================================================================================================================ -- Alex Bennée

3 years, 3 months

[ACTIVITY] report week ending 13 Aug

by Peter Maydell

Progress: * UM-2 [QEMU upstream maintainership] + Getting rc3 out of the door + Finished the systick timer refactoring series and sent it out for review (it ended up weighing in at 25 patches...) + Worked through some Coverity issue reports to analyze them and either close as false-positive or send out patches fixing them -- PMM

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O2 - Build # 14 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations: - tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2 Culprit: <cut> commit 2db8461a9492cb64046a085f35048b9c4e45bfc2 Author: Raphael Isemann <teemperor(a)gmail.com> Date: Tue Aug 10 16:15:57 2021 +0200 [lldb][NFC] Fix inversed documentation of Process::GetID/SetID </cut> Results regressed to (for first_bad == 2db8461a9492cb64046a085f35048b9c4e45bfc2) # 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-2db8461a9492cb64046a085f35048b9c4e45bfc2/results_id: 1 # 453.povray,[.] _ZN3povL24All_Sphere_IntersectionsEPNS_13Objec regressed by 116 from (for last_good == 9900af52f6b186a260d83321791177728fb369c5) # 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-9900af52f6b186a260d83321791177728fb369c5/results_id: 1 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2/3417 Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2/3391 Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Configuration details: Reproduce builds: <cut> mkdir investigate-llvm-2db8461a9492cb64046a085f35048b9c4e45bfc2 cd investigate-llvm-2db8461a9492cb64046a085f35048b9c4e45bfc2 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_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 2db8461a9492cb64046a085f35048b9c4e45bfc2 ../artifacts/test.sh # Reproduce last_good build git checkout --detach 9900af52f6b186a260d83321791177728fb369c5 ../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_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… Full commit (up to 1000 lines): <cut> commit 2db8461a9492cb64046a085f35048b9c4e45bfc2 Author: Raphael Isemann <teemperor(a)gmail.com> Date: Tue Aug 10 16:15:57 2021 +0200 [lldb][NFC] Fix inversed documentation of Process::GetID/SetID --- lldb/include/lldb/Target/Process.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/lldb/include/lldb/Target/Process.h b/lldb/include/lldb/Target/Process.h index aaa2470d2931..8dcc15b1667b 100644 --- a/lldb/include/lldb/Target/Process.h +++ b/lldb/include/lldb/Target/Process.h @@ -536,13 +536,13 @@ public: uint32_t GetAddressByteSize() const; + /// Returns the pid of the process or LLDB_INVALID_PROCESS_ID if there is + /// no known pid. + lldb::pid_t GetID() const { return m_pid; } + /// Sets the stored pid. /// /// This does not change the pid of underlying process. - lldb::pid_t GetID() const { return m_pid; } - - /// Returns the pid of the process or LLDB_INVALID_PROCESS_ID if there is - /// no known pid. void SetID(lldb::pid_t new_pid) { m_pid = new_pid; } uint32_t GetUniqueID() const { return m_process_unique_id; } </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-master-arm-next-allmodconfig - Build # 20 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-master-arm-next-allmodconfig. So far, this commit has regressed CI configurations: - tcwg_kernel/llvm-master-arm-next-allmodconfig Culprit: <cut> commit 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15 Author: Eric Dumazet <edumazet(a)google.com> Date: Tue Aug 10 02:45:47 2021 -0700 net: igmp: fix data-race in igmp_ifc_timer_expire() Fix the data-race reported by syzbot [1] Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count while another change just occured from another context. in_dev->mr_ifc_count is only 8bit wide, so the race had little consequences. [1] BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0: igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821 igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356 ____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461 __ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199 ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218 do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline] ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423 tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657 sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362 __sys_setsockopt+0x18f/0x200 net/socket.c:2159 __do_sys_setsockopt net/socket.c:2170 [inline] __se_sys_setsockopt net/socket.c:2167 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2167 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1: igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808 call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419 expire_timers+0x135/0x250 kernel/time/timer.c:1464 __run_timers+0x358/0x420 kernel/time/timer.c:1732 run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745 __do_softirq+0x12c/0x26e kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636 sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100 asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638 console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646 vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174 vprintk_default+0x22/0x30 kernel/printk/printk.c:2185 vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392 printk+0x62/0x87 kernel/printk/printk.c:2216 selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041 security_netlink_send+0x42/0x90 security/security.c:2070 netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:703 [inline] sock_sendmsg net/socket.c:723 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2392 ___sys_sendmsg net/socket.c:2446 [inline] __sys_sendmsg+0x1ed/0x270 net/socket.c:2475 __do_sys_sendmsg net/socket.c:2484 [inline] __se_sys_sendmsg net/socket.c:2482 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2482 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x01 -> 0x02 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> </cut> Results regressed to (for first_bad == 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15) # reset_artifacts: -10 # build_abe binutils: -9 # build_llvm: -5 # build_abe qemu: -2 # linux_n_obj: 21692 # First few build errors in logs: # 00:03:56 ld.lld: error: undefined symbol: __bad_cmpxchg # 00:03:56 make: *** [Makefile:1176: vmlinux] Error 1 from (for last_good == 37c86c4a0bfc2faaf0ed959db9de814c85797f09) # reset_artifacts: -10 # build_abe binutils: -9 # build_llvm: -5 # build_abe qemu: -2 # linux_n_obj: 29753 # linux build successful: all Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… Configuration details: rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#761c6d7…" Reproduce builds: <cut> mkdir investigate-linux-4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15 cd investigate-linux-4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15 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-arm-next-allm… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… --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 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15 ../artifacts/test.sh # Reproduce last_good build git checkout --detach 37c86c4a0bfc2faaf0ed959db9de814c85797f09 ../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-arm-next-allm… Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… Full commit (up to 1000 lines): <cut> commit 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15 Author: Eric Dumazet <edumazet(a)google.com> Date: Tue Aug 10 02:45:47 2021 -0700 net: igmp: fix data-race in igmp_ifc_timer_expire() Fix the data-race reported by syzbot [1] Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count while another change just occured from another context. in_dev->mr_ifc_count is only 8bit wide, so the race had little consequences. [1] BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0: igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821 igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356 ____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461 __ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199 ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218 do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline] ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423 tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657 sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362 __sys_setsockopt+0x18f/0x200 net/socket.c:2159 __do_sys_setsockopt net/socket.c:2170 [inline] __se_sys_setsockopt net/socket.c:2167 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2167 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1: igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808 call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419 expire_timers+0x135/0x250 kernel/time/timer.c:1464 __run_timers+0x358/0x420 kernel/time/timer.c:1732 run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745 __do_softirq+0x12c/0x26e kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636 sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100 asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638 console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646 vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174 vprintk_default+0x22/0x30 kernel/printk/printk.c:2185 vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392 printk+0x62/0x87 kernel/printk/printk.c:2216 selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041 security_netlink_send+0x42/0x90 security/security.c:2070 netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:703 [inline] sock_sendmsg net/socket.c:723 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2392 ___sys_sendmsg net/socket.c:2446 [inline] __sys_sendmsg+0x1ed/0x270 net/socket.c:2475 __do_sys_sendmsg net/socket.c:2484 [inline] __se_sys_sendmsg net/socket.c:2482 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2482 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x01 -> 0x02 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> --- net/ipv4/igmp.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6b3c558a4f23..a51360087b19 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); + u8 mr_ifc_count; igmpv3_send_cr(in_dev); - if (in_dev->mr_ifc_count) { - in_dev->mr_ifc_count--; +restart: + mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); + + if (mr_ifc_count) { + if (cmpxchg(&in_dev->mr_ifc_count, + mr_ifc_count, + mr_ifc_count - 1) != mr_ifc_count) + goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } @@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev) struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv); igmp_ifc_start_timer(in_dev, 1); } @@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, in_dev->mr_qri; } /* cancel the interface change timer */ - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ @@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; @@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); @@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); </cut>

3 years, 3 months

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

linaro-toolchain