This is an automated email from the git hooks/post-receive script.
unknown user pushed a change to branch master in repository llvm.
from 0b9f636469b [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source m [...] new a90929573cc [AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic new d15747e2fa0 Fix flat-error-unsupported-gpu-hsa test
The 2 revisions listed above as "new" are entirely new to this repository and will be described in separate emails. The revisions listed as "adds" were already present in the repository and have only been added to this reference.
Summary of changes: lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp | 32 ++++++---- lib/Target/AMDGPU/SIInstrInfo.cpp | 13 +++-- lib/Target/AMDGPU/SIInstrInfo.td | 7 ++- lib/Target/AMDGPU/SILoadStoreOptimizer.cpp | 12 ++-- lib/Target/AMDGPU/SIRegisterInfo.cpp | 9 ++- lib/Target/AMDGPU/VOP2Instructions.td | 29 +++++---- test/CodeGen/AMDGPU/endpgm-dce.mir | 2 +- .../AMDGPU/flat-error-unsupported-gpu-hsa.ll | 2 +- .../fold-immediate-operand-shrink-with-carry.mir | 18 +++--- .../AMDGPU/fold-immediate-operand-shrink.mir | 50 ++++++++-------- test/CodeGen/AMDGPU/global-load-store-atomics.mir | 4 +- test/CodeGen/AMDGPU/inserted-wait-states.mir | 4 +- .../AMDGPU/macro-fusion-cluster-vcc-uses.mir | 44 +++++++------- test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir | 68 +++++++++++----------- test/CodeGen/AMDGPU/sched-crash-dbg-value.mir | 20 +++---- test/CodeGen/AMDGPU/sdwa-ops.mir | 60 +++++++++---------- test/CodeGen/AMDGPU/shrink-carry.mir | 8 +-- test/CodeGen/AMDGPU/shrink-vop3-carry-out.mir | 20 +++---- test/CodeGen/AMDGPU/vop-shrink-frame-index.mir | 12 ++-- test/CodeGen/AMDGPU/vop-shrink-non-ssa.mir | 4 +- test/MC/AMDGPU/vop3-gfx9.s | 37 ++++++++++++ test/MC/AMDGPU/vop3.s | 24 ++++++++ test/MC/Disassembler/AMDGPU/vop3_gfx9.txt | 28 +++++++++ test/MC/Disassembler/AMDGPU/vop3_vi.txt | 19 ++++++ 24 files changed, 335 insertions(+), 191 deletions(-)