intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-28 19:43:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

[mlir][nvvm] Fix mov.u32 to mov.pred (#70027)

Browse Source 
This PR fixes the incorrect `mov` instruction in PTX. We actually move a
predicate here, not u32, so the correct instruction should be
`mov.pred`.
This commit is contained in:
Guray Ozen
2023-10-25 21:00:09 +02:00
committed by GitHub
parent 006cd37960
commit 01ac180c11
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td
View File

@@ -469,9 +469,9 @@ def NVVM_ElectSyncOp : NVVM_Op<"elect.sync",
"{ \n"
".reg .u32 rx; \n"
".reg .pred px; \n"
" mov.u32 %0, 0; \n"
" mov.pred %0, 0; \n"
" elect.sync rx | px, 0xFFFFFFFF;\n"
"@px mov.u32 %0, 1; \n"
"@px mov.pred %0, 1; \n"
"}\n"
);
}

4
mlir/test/Conversion/NVVMToLLVM/nvvm-to-llvm.mlir
View File

@@ -497,9 +497,9 @@ func.func @elect_one_leader_sync() {
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "{
// CHECK-SAME: .reg .u32 rx;
// CHECK-SAME: .reg .pred px;
// CHECK-SAME: mov.u32 $0, 0;
// CHECK-SAME: mov.pred $0, 0;
// CHECK-SAME: elect.sync rx | px, 0xFFFFFFFF;
// CHECK-SAME: @px mov.u32 $0, 1;
// CHECK-SAME: @px mov.pred $0, 1;
// CHECK-SAME: "=b" : () -> i1
%cnd = nvvm.elect.sync -> i1
return