Skip to content

[MLIR][NVVM] Align the PTX string for StMatrixOp with the docs #148250

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Pecco-314 wants to merge 3 commits into from
Closed

[MLIR][NVVM] Align the PTX string for StMatrixOp with the docs #148250

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dacee08
[MLIR] Fix the PTX generation bug for StMatrixOp
Pecco-314 Jul 11, 2025
8ed67ea
Fix the testcase
Pecco-314 Jul 11, 2025
dcb7360
Merge branch 'main' of https://github.com/Pecco-314/llvm-project into…
Pecco-314 Jul 11, 2025
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
8 changes: 4 additions & 4 deletions mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2006,13 +2006,13 @@ def NVVM_StMatrixOp: NVVM_PTXBuilder_Op<"stmatrix">,
let extraClassDefinition = [{
std::string $cppClass::getPtx() {
int d = getSources().size();
std::string ptx = "stmatrix.sync.aligned";
std::string ptx = "stmatrix.sync.aligned.m8n8";
ptx += ".x" + std::to_string(d);
if (getLayout() == NVVM::MMALayout::col)
ptx += ".trans";
if(d == 1) ptx += ".m8n8.shared.b16 [%0], {%1};";
if(d == 2) ptx += ".m8n8.shared.b16 [%0], {%1, %2};";
if(d == 4) ptx += ".m8n8.shared.b16 [%0], {%1, %2, %3, %4};";
if(d == 1) ptx += ".shared.b16 [%0], {%1};";
if(d == 2) ptx += ".shared.b16 [%0], {%1, %2};";
if(d == 4) ptx += ".shared.b16 [%0], {%1, %2, %3, %4};";
return ptx;
}
}];
Expand Down
12 changes: 6 additions & 6 deletions mlir/test/Conversion/NVVMToLLVM/nvvm-to-llvm.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -587,12 +587,12 @@ func.func @elect_one_leader_sync() {
// CHECK-SAME: %[[arg3:[a-zA-Z0-9_]+]]: i32,
// CHECK-SAME: %[[arg4:[a-zA-Z0-9_]+]]: i32)
llvm.func @stmatrix(%arg0 : !llvm.ptr<3>, %m1 : i32, %m2 : i32, %m3 : i32, %m4 : i32) {
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.x1.m8n8.shared.b16 [$0], {$1};", "r,r" %[[arg0]], %[[arg1]] : (!llvm.ptr<3>, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.x2.m8n8.shared.b16 [$0], {$1, $2};", "r,r,r" %[[arg0]], %[[arg1]], %[[arg2]] : (!llvm.ptr<3>, i32, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.x4.m8n8.shared.b16 [$0], {$1, $2, $3, $4};", "r,r,r,r,r" %[[arg0]], %[[arg1]], %[[arg2]], %[[arg3]], %[[arg4]] : (!llvm.ptr<3>, i32, i32, i32, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.x1.trans.m8n8.shared.b16 [$0], {$1};", "r,r" %[[arg0]], %[[arg1]] : (!llvm.ptr<3>, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.x2.trans.m8n8.shared.b16 [$0], {$1, $2};", "r,r,r" %[[arg0]], %[[arg1]], %[[arg2]] : (!llvm.ptr<3>, i32, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.x4.trans.m8n8.shared.b16 [$0], {$1, $2, $3, $4};", "r,r,r,r,r" %[[arg0]], %[[arg1]], %[[arg2]], %[[arg3]], %[[arg4]] : (!llvm.ptr<3>, i32, i32, i32, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.m8n8.x1.shared.b16 [$0], {$1};", "r,r" %[[arg0]], %[[arg1]] : (!llvm.ptr<3>, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.m8n8.x2.shared.b16 [$0], {$1, $2};", "r,r,r" %[[arg0]], %[[arg1]], %[[arg2]] : (!llvm.ptr<3>, i32, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.m8n8.x4.shared.b16 [$0], {$1, $2, $3, $4};", "r,r,r,r,r" %[[arg0]], %[[arg1]], %[[arg2]], %[[arg3]], %[[arg4]] : (!llvm.ptr<3>, i32, i32, i32, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.m8n8.x1.trans.shared.b16 [$0], {$1};", "r,r" %[[arg0]], %[[arg1]] : (!llvm.ptr<3>, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.m8n8.x2.trans.shared.b16 [$0], {$1, $2};", "r,r,r" %[[arg0]], %[[arg1]], %[[arg2]] : (!llvm.ptr<3>, i32, i32) -> ()
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att "stmatrix.sync.aligned.m8n8.x4.trans.shared.b16 [$0], {$1, $2, $3, $4};", "r,r,r,r,r" %[[arg0]], %[[arg1]], %[[arg2]], %[[arg3]], %[[arg4]] : (!llvm.ptr<3>, i32, i32, i32, i32) -> ()
nvvm.stmatrix %arg0, %m1 {layout = #nvvm.mma_layout<row>} : !llvm.ptr<3>, i32
nvvm.stmatrix %arg0, %m1, %m2 {layout = #nvvm.mma_layout<row>} : !llvm.ptr<3>, i32, i32
nvvm.stmatrix %arg0, %m1, %m2, %m3, %m4 {layout = #nvvm.mma_layout<row>} : !llvm.ptr<3>, i32, i32, i32, i32
Expand Down