Skip to content

[mlir][ROCDL] Add tensor load and store instructions to ROCDL #165016

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 7 commits into from
Oct 28, 2025
Merged

[mlir][ROCDL] Add tensor load and store instructions to ROCDL #165016

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
1bea035
[mlir][ROCDL] Add tensor load and store instructions to ROCDL
justinrosner Oct 24, 2025
983aff0
Merge branch 'main' into justinr-rocdl-tensor-load-store
justinrosner Oct 27, 2025
2fcb81e
Update Arg types
justinrosner Oct 27, 2025
c966631
Remove mem properties
justinrosner Oct 27, 2025
04c5172
Update LIT tests and add description to ops
justinrosner Oct 28, 2025
0bcaa1f
Attend to more review comments
justinrosner Oct 28, 2025
2c70cf5
Add back unique types to assembly string
justinrosner Oct 28, 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
64 changes: 64 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 @@ -663,6 +663,70 @@ def ROCDL_GlobalLoadLDSOp :
}];
}

//===---------------------------------------------------------------------===//
// Tensor load/store intrinsics (available in GFX1250)
//===---------------------------------------------------------------------===//

// Base class for tensor load/store operations with 4 descriptor groups.
class ROCDL_TensorLDSIntrOp<string mnemonic> :
ROCDL_IntrOp<mnemonic, [], [], [], 0, 0, 1, 0, [4], ["cachePolicy"]> {
dag args = (ins LLVM_VectorOf<I32>:$dgroup0, LLVM_VectorOf<I32>:$dgroup1,
LLVM_VectorOf<I32>:$dgroup2, LLVM_VectorOf<I32>:$dgroup3,
I32Attr:$cachePolicy);
let arguments = !con(args, baseArgs);
let summary = "Base class for ROCDL tensor load/store to/from LDS.";
let description = [{
Moves tiles of tensor data between global memory and LDS. The tile is
described by the $dgroup descriptors. 4 $dgroup descriptors allows for
movement of up to 5D tensors. $cachePolicy describes the memory scope and an
indicator of expected data re-use.

This op is for gfx1250+ architectures.
}];
let assemblyFormat = [{
$dgroup0 `,` $dgroup1 `,` $dgroup2 `,` $dgroup3 `,` $cachePolicy
attr-dict `:` type($dgroup0) `,` type($dgroup1) `,` type($dgroup2) `,` type($dgroup3)
}];
let extraClassDefinition = [{
SmallVector<Value> $cppClass::getAccessedOperands() {
return {getDgroup0(), getDgroup1(), getDgroup2(), getDgroup3()};
}
}];
}

// Base class for tensor load/store operations with 2 descriptor groups
// (D2 variant).
class ROCDL_TensorLDSIntrD2Op<string mnemonic> :
ROCDL_IntrOp<mnemonic, [], [], [], 0, 0, 1, 0, [2], ["cachePolicy"]> {
dag args = (ins LLVM_VectorOf<I32>:$dgroup0, LLVM_VectorOf<I32>:$dgroup1,
I32Attr:$cachePolicy);
let arguments = !con(args, baseArgs);
let summary = "Base class for ROCDL tensor load/store to/from LDS (D2 variant).";
let description = [{
Moves tiles of tensor data between global memory and LDS. The tile is
described by the $dgroup descriptors. 2 $dgroup descriptors allows for
movement of up to 2D tensors. $cachePolicy describes the memory scope and an
indicator of expected data re-use.

This op is for gfx1250+ architectures.
}];
let assemblyFormat = [{
$dgroup0 `,` $dgroup1 `,` $cachePolicy
attr-dict `:` type($dgroup0) `,` type($dgroup1)
}];
let extraClassDefinition = [{
SmallVector<Value> $cppClass::getAccessedOperands() {
return {getDgroup0(), getDgroup1()};
}
}];
}

// Tensor load and store operations
def ROCDL_TensorLoadToLDSOp : ROCDL_TensorLDSIntrOp<"tensor.load.to.lds">;
def ROCDL_TensorStoreFromLDSOp : ROCDL_TensorLDSIntrOp<"tensor.store.from.lds">;
def ROCDL_TensorLoadToLDSD2Op : ROCDL_TensorLDSIntrD2Op<"tensor.load.to.lds.d2">;
def ROCDL_TensorStoreFromLDSD2Op : ROCDL_TensorLDSIntrD2Op<"tensor.store.from.lds.d2">;

//===---------------------------------------------------------------------===//
// Operations on raw buffer resources (stride of 0, bounds checks either off or in
// raw buffer mode).
Expand Down
30 changes: 30 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 +664,36 @@ llvm.func @rocdl.global.load.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
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>) {
// CHECK: rocdl.tensor.load.to.lds %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}, 0 : vector<4xi32>, vector<8xi32>, vector<4xi32>, vector<4xi32>
rocdl.tensor.load.to.lds %dgroup0, %dgroup1, %dgroup2, %dgroup3, 0 : vector<4xi32>, vector<8xi32>, vector<4xi32>, vector<4xi32>
llvm.return
}

// CHECK-LABEL @rocdl.tensor.store.from.lds
llvm.func @rocdl.tensor.store.from.lds(%dgroup0 : vector<4xi32>, %dgroup1 : vector<8xi32>,
%dgroup2 : vector<4xi32>, %dgroup3 : vector<4xi32>) {
// CHECK: rocdl.tensor.store.from.lds %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}, 0 : vector<4xi32>, vector<8xi32>, vector<4xi32>, vector<4xi32>
rocdl.tensor.store.from.lds %dgroup0, %dgroup1, %dgroup2, %dgroup3, 0 : vector<4xi32>, vector<8xi32>, vector<4xi32>, vector<4xi32>
llvm.return
}

llvm.func @rocdl.tensor.load.to.lds.d2(%dgroup0 : vector<4xi32>, %dgroup1 : vector<8xi32>) {
// CHECK-LABEL @rocdl.tensor.load.to.lds.d2
// CHECK: rocdl.tensor.load.to.lds.d2 %{{.*}}, %{{.*}}, 0 : vector<4xi32>, vector<8xi32>
rocdl.tensor.load.to.lds.d2 %dgroup0, %dgroup1, 0 : vector<4xi32>, vector<8xi32>
llvm.return
}

llvm.func @rocdl.tensor.store.from.lds.d2(%dgroup0 : vector<4xi32>, %dgroup1 : vector<8xi32>) {
// CHECK-LABEL @rocdl.tensor.store.from.lds.d2
// CHECK: rocdl.tensor.store.from.lds.d2 %{{.*}}, %{{.*}}, 0 : vector<4xi32>, vector<8xi32>
rocdl.tensor.store.from.lds.d2 %dgroup0, %dgroup1, 0 : vector<4xi32>, vector<8xi32>
llvm.return
}

llvm.func @rocdl.make.buffer.rsrc(%ptr : !llvm.ptr,
%stride : i16,
%numRecords : i64,
Expand Down
30 changes: 30 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 +1040,36 @@ llvm.func @rocdl.global.load.lds(%src : !llvm.ptr<1>, %dst: !llvm.ptr<3>) {
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>) {
// CHECK: call void @llvm.amdgcn.tensor.load.to.lds(<4 x i32> %{{.*}}, <8 x i32> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> %{{.*}}, i32 0)
rocdl.tensor.load.to.lds %dgroup0, %dgroup1, %dgroup2, %dgroup3, 0 : vector<4xi32>, vector<8xi32>, vector<4xi32>, vector<4xi32>
llvm.return
}

// CHECK-LABEL: rocdl.tensor.store.from.lds
llvm.func @rocdl.tensor.store.from.lds(%dgroup0 : vector<4xi32>, %dgroup1 : vector<8xi32>,
%dgroup2 : vector<4xi32>, %dgroup3 : vector<4xi32>) {
// CHECK: call void @llvm.amdgcn.tensor.store.from.lds(<4 x i32> %{{.*}}, <8 x i32> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> %{{.*}}, i32 0)
rocdl.tensor.store.from.lds %dgroup0, %dgroup1, %dgroup2, %dgroup3, 0 : vector<4xi32>, vector<8xi32>, vector<4xi32>, vector<4xi32>
llvm.return
}

llvm.func @rocdl.tensor.load.to.lds.d2(%dgroup0 : vector<4xi32>, %dgroup1 : vector<8xi32>) {
// CHECK-LABEL: rocdl.tensor.load.to.lds.d2
// CHECK: call void @llvm.amdgcn.tensor.load.to.lds.d2(<4 x i32> %{{.*}}, <8 x i32> %{{.*}}, i32 0)
rocdl.tensor.load.to.lds.d2 %dgroup0, %dgroup1, 0 : vector<4xi32>, vector<8xi32>
llvm.return
}

llvm.func @rocdl.tensor.store.from.lds.d2(%dgroup0 : vector<4xi32>, %dgroup1 : vector<8xi32>) {
// CHECK-LABEL: rocdl.tensor.store.from.lds.d2
// CHECK: call void @llvm.amdgcn.tensor.store.from.lds.d2(<4 x i32> %{{.*}}, <8 x i32> %{{.*}}, i32 0)
rocdl.tensor.store.from.lds.d2 %dgroup0, %dgroup1, 0 : vector<4xi32>, vector<8xi32>
llvm.return
}

llvm.func @rocdl.make.buffer.rsrc(%ptr : !llvm.ptr,
%stride : i16,
%numRecords : i64,
Expand Down