Skip to content

[mlir][rocdl] Add GlobalLoadAsyncToLDS operation #165374

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

Merged
merged 3 commits into from
Nov 4, 2025
Merged

[mlir][rocdl] Add GlobalLoadAsyncToLDS operation #165374

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fe4f87b
[mlir][rocdl] Add GlobalLoadAsyncToLDS operation
pabloantoniom Oct 28, 2025
4a11e80
Address ravil comments, note that I changed the foreach slightly
pabloantoniom Oct 31, 2025
36dd422
Address Krzysztofs nit
pabloantoniom Nov 4, 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
32 changes: 32 additions & 0 deletions mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -692,6 +692,38 @@ def ROCDL_GlobalLoadLDSOp :
}];
}

//===---------------------------------------------------------------------===//
// Async load to LDS intrinsic (available in GFX1250)
//===---------------------------------------------------------------------===//

foreach bitsVal = [8, 32, 64, 128] in {
defvar bitsStr = "b" # !cast<string>(bitsVal);
def ROCDL_GlobalLoadAsyncToLDS # !toupper(bitsStr) # Op :
ROCDL_IntrOp<"global.load.async.to.lds." # bitsStr, [], [], [], 0, 0, 1, 0, [2, 3], ["offset", "aux"]> {
dag args = (ins Arg<ROCDLGlobalBuffer, "", [MemRead]>:$globalPtr,
Arg<ROCDLBufferLDS, "", [MemWrite]>:$ldsPtr,
I32Attr:$offset,
I32Attr:$aux);
let arguments = !con(args, baseArgs);
let assemblyFormat = [{
$globalPtr `,` $ldsPtr `,` $offset `,` $aux
attr-dict `:` type($globalPtr)
Copy link
Contributor

@krzysz00 krzysz00 Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd go for type($globalPtr), type($ldsPtr) if we're doing this sort of thing

}];
let description = [{
Asynchronously loads }] # !cast<string>(bitsVal) # [{ bits of data from a global memory pointer
to a Local Data Share (LDS) pointer.

Available on gfx1250+.
}];

let extraClassDefinition = [{
::llvm::SmallVector<::mlir::Value> $cppClass::getAccessedOperands() {
return {getGlobalPtr(), getLdsPtr()};
}
}];
}
}

//===---------------------------------------------------------------------===//
// Tensor load/store intrinsics (available in GFX1250)
//===---------------------------------------------------------------------===//
Expand Down
13 changes: 13 additions & 0 deletions mlir/test/Dialect/LLVMIR/rocdl.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -664,6 +664,19 @@ llvm.func @rocdl.global.load.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
llvm.return
}

llvm.func @rocdl.global.load.async.to.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
// CHECK-LABEL @rocdl.global.load.async.to.lds
// CHECK: rocdl.global.load.async.to.lds.b8 %{{.*}}, %{{.*}}, 0, 0
// CHECK: rocdl.global.load.async.to.lds.b32 %{{.*}}, %{{.*}}, 0, 0
// CHECK: rocdl.global.load.async.to.lds.b64 %{{.*}}, %{{.*}}, 0, 0
// CHECK: rocdl.global.load.async.to.lds.b128 %{{.*}}, %{{.*}}, 0, 0
rocdl.global.load.async.to.lds.b8 %src, %dst, 0, 0 : <1>
rocdl.global.load.async.to.lds.b32 %src, %dst, 0, 0 : <1>
rocdl.global.load.async.to.lds.b64 %src, %dst, 0, 0 : <1>
rocdl.global.load.async.to.lds.b128 %src, %dst, 0, 0 : <1>
llvm.return
}

// CHECK-LABEL @rocdl.tensor.load.to.lds
llvm.func @rocdl.tensor.load.to.lds(%dgroup0 : vector<4xi32>, %dgroup1 : vector<8xi32>,
%dgroup2 : vector<4xi32>, %dgroup3 : vector<4xi32>) {
Expand Down
13 changes: 13 additions & 0 deletions mlir/test/Target/LLVMIR/rocdl.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1040,6 +1040,19 @@ llvm.func @rocdl.global.load.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
llvm.return
}

// CHECK-LABEL: rocdl.global.load.async.to.lds
llvm.func @rocdl.global.load.async.to.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
// CHECK: call void @llvm.amdgcn.global.load.async.to.lds.b8
rocdl.global.load.async.to.lds.b8 %src, %dst, 0, 0 : !llvm.ptr<1>
// CHECK: call void @llvm.amdgcn.global.load.async.to.lds.b32
rocdl.global.load.async.to.lds.b32 %src, %dst, 0, 0 : !llvm.ptr<1>
// CHECK: call void @llvm.amdgcn.global.load.async.to.lds.b64
rocdl.global.load.async.to.lds.b64 %src, %dst, 0, 0 : !llvm.ptr<1>
// CHECK: call void @llvm.amdgcn.global.load.async.to.lds.b128
rocdl.global.load.async.to.lds.b128 %src, %dst, 0, 0 : !llvm.ptr<1>
llvm.return
}

// CHECK-LABEL: rocdl.tensor.load.to.lds
llvm.func @rocdl.tensor.load.to.lds(%dgroup0 : vector<4xi32>, %dgroup1 : vector<8xi32>,
%dgroup2 : vector<4xi32>, %dgroup3 : vector<4xi32>) {
Expand Down