Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion cmake/llvm-hash.txt
Original file line number Diff line number Diff line change
@@ -1 +1 @@
979132a02d146ec79e2f046e31877516d7f32d20
ac5dc54d509169d387fcfd495d71853d81c46484
1 change: 1 addition & 0 deletions python/src/llvm.cc
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,7 @@ createTargetMachine(llvm::Module *module, std::string proc,
bool disableLLVMOpt = mlir::triton::tools::getBoolEnv("DISABLE_LLVM_OPT");
if (enable_fp_fusion)
opt.AllowFPOpFusion = llvm::FPOpFusion::Fast;
opt.NoInfsFPMath = false;
opt.NoNaNsFPMath = true;
opt.TrapUnreachable = true;
opt.MCOptions.AsmVerbose = true;
Expand Down
4 changes: 1 addition & 3 deletions python/test/unit/language/test_core.py
Original file line number Diff line number Diff line change
Expand Up @@ -1382,9 +1382,7 @@ def kernel(X, Z):
# atom.add.bf16 is unsupported prior to Hopper so instead we generate an
# atom.cas add loop on Ampere and prior
if dst_type == 'bfloat16' and torch.cuda.get_device_capability()[0] < 9:
assert "atom.relaxed.gpu.global.cas" in h.asm["ptx"]
if sem_str != "relaxed":
assert "fence.acq_rel.gpu" in h.asm["ptx"]
assert f"atom.{sem_str}.gpu.global.cas" in h.asm["ptx"]
return

assert f"atom.global.gpu.{sem_str}" in h.asm["ptx"]
Expand Down
Loading