Skip to content

[MLIR][XeGPU] Enable blocking for scatter ops with offsets #162896

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
nbpatel merged 2 commits into from
Oct 13, 2025
Merged

[MLIR][XeGPU] Enable blocking for scatter ops with offsets #162896

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8941125
Enable blocking for scatter ops with offsets
nbpatel Oct 10, 2025
a5b81d2
Remove CHECK
nbpatel Oct 10, 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
17 changes: 15 additions & 2 deletions mlir/lib/Dialect/XeGPU/Transforms/XeGPUBlocking.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,11 +161,24 @@ XeGPUBlockingPass::getTileShape(Operation *op) const {
xegpu::UpdateOffsetOp, xegpu::LoadMatrixOp>(op))
return getTileShape(op->getOpResult(0));
if (isa<xegpu::PrefetchNdOp, xegpu::LoadNdOp, xegpu::PrefetchOp,
xegpu::LoadGatherOp, xegpu::StoreMatrixOp>(op))
xegpu::StoreMatrixOp>(op))
return getTileShape(op->getOpOperand(0));
if (isa<xegpu::StoreNdOp, xegpu::StoreScatterOp>(op))
if (isa<xegpu::StoreNdOp>(op))
return getTileShape(op->getOpOperand(1));

// Handle LoadGatherOp and StoreScatterOp (with and without offset)
if (auto loadGatherOp = dyn_cast<xegpu::LoadGatherOp>(op)) {
if (loadGatherOp.getOffsets())
return getTileShape(loadGatherOp->getOpResult(0));
else
return getTileShape(loadGatherOp->getOpOperand(0));
}

if (auto storeScatterOp = dyn_cast<xegpu::StoreScatterOp>(op))
return getTileShape(storeScatterOp.getOffsets()
? storeScatterOp->getOpOperand(0)
: storeScatterOp->getOpOperand(1));

if (isa<xegpu::DpasOp>(op)) {
std::optional<SmallVector<int64_t>> aTile =
getTileShape(op->getOpOperand(0));
Expand Down
98 changes: 98 additions & 0 deletions mlir/test/Dialect/XeGPU/xegpu-blocking.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -584,3 +584,101 @@ gpu.module @test_kernel {
gpu.return
}
}

// -----
gpu.module @test_kernel {
// CHECK-LABEL: load_with_offsets
// CHECK-COUNT-2: xegpu.load {{.*}}[{{.*}}], {{.*}} <{chunk_size = 1 : i64, l1_hint = #xegpu.cache_hint<cached>}> : ui64, vector<16xindex>, vector<16xi1> -> vector<16xf32>
gpu.func @load_with_offsets(%src: ui64) -> vector<32xf32> {
%cst = arith.constant dense<[
0, 8, 16, 24, 32, 40, 48, 56,
64, 72, 80, 88, 96, 104, 112, 120,
128, 136, 144, 152, 160, 168, 176, 184,
192, 200, 208, 216, 224, 232, 240, 248
]> : vector<32xindex>

%c17 = arith.constant 17: index
%mask = vector.create_mask %c17: vector<32xi1>
%ld = xegpu.load %src[%cst], %mask {chunk_size = 1, layout_result_0 = #xegpu.layout<inst_data = [16]>, l1_hint = #xegpu.cache_hint<cached>} : ui64, vector<32xindex>, vector<32xi1> -> vector<32xf32>

gpu.return %ld : vector<32xf32>
}
}

// -----
gpu.module @test_kernel {
// CHECK-LABEL: store_with_offsets
// CHECK-COUNT-2: xegpu.store {{.*}}[{{.*}}], {{.*}} <{chunk_size = 1 : i64, l1_hint = #xegpu.cache_hint<cached>}> : vector<16xf32>, ui64, vector<16xindex>, vector<16xi1>
gpu.func @store_with_offsets(%src: ui64) {
%cst = arith.constant dense<[
0, 8, 16, 24, 32, 40, 48, 56,
64, 72, 80, 88, 96, 104, 112, 120,
128, 136, 144, 152, 160, 168, 176, 184,
192, 200, 208, 216, 224, 232, 240, 248
]> : vector<32xindex>

%c17 = arith.constant 17: index
%mask = vector.create_mask %c17: vector<32xi1>

%st_vec = arith.constant dense<1023.0>: vector<32xf32>
xegpu.store %st_vec, %src[%cst], %mask {chunk_size = 1, layout_operand_0 = #xegpu.layout<inst_data = [16]>,
layout_operand_2 = #xegpu.layout<inst_data = [16]>,
layout_operand_3 = #xegpu.layout<inst_data = [16]>,
l1_hint = #xegpu.cache_hint<cached>} : vector<32xf32>, ui64, vector<32xindex>, vector<32xi1>

gpu.return
}
}

// -----
gpu.module @test_kernel {
// CHECK-LABEL: load_with_offsets_chunk
// CHECK: [[cst:%.+]] = arith.constant dense<0.000000e+00> : vector<32x4xf32>
// CHECK: [[cst0:%.+]] = arith.constant dense<[130, 138, 146, 154, 162, 170, 178, 186, 194, 202, 210, 218, 226, 234, 242, 250]> : vector<16xindex>
// CHECK: [[cst1:%.+]] = arith.constant dense<[2, 10, 18, 26, 34, 42, 50, 58, 66, 74, 82, 90, 98, 106, 114, 122]> : vector<16xindex>
// CHECK: [[cst2:%.+]] = arith.constant dense<[128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248]> : vector<16xindex>
// CHECK: [[cst3:%.+]] = arith.constant dense<[0, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120]> : vector<16xindex>
// CHECK-COUNT-4: xegpu.load {{.*}}[{{.*}}], {{.*}} <{chunk_size = 2 : i64, l1_hint = #xegpu.cache_hint<cached>}> : ui64, vector<16xindex>, vector<16xi1> -> vector<16x2xf32>
gpu.func @load_with_offsets_chunk(%src: ui64) -> vector<32x4xf32> {
%cst = arith.constant dense<[
0, 8, 16, 24, 32, 40, 48, 56,
64, 72, 80, 88, 96, 104, 112, 120,
128, 136, 144, 152, 160, 168, 176, 184,
192, 200, 208, 216, 224, 232, 240, 248
]> : vector<32xindex>

%c17 = arith.constant 17: index
%mask = vector.create_mask %c17: vector<32xi1>
%ld = xegpu.load %src[%cst], %mask {chunk_size = 4, layout_result_0 = #xegpu.layout<inst_data = [16, 2]>, l1_hint = #xegpu.cache_hint<cached>} : ui64, vector<32xindex>, vector<32xi1> -> vector<32x4xf32>
gpu.return %ld : vector<32x4xf32>
}
}

// -----
gpu.module @test_kernel {
// CHECK-LABEL: store_with_offsets_chunk
// CHECK: [[cst:%.+]] = arith.constant dense<1.023000e+03> : vector<16x2xf32
// CHECK: [[cst0:%.+]] = arith.constant dense<[130, 138, 146, 154, 162, 170, 178, 186, 194, 202, 210, 218, 226, 234, 242, 250]> : vector<16xindex>
// CHECK: [[cst1:%.+]] = arith.constant dense<[2, 10, 18, 26, 34, 42, 50, 58, 66, 74, 82, 90, 98, 106, 114, 122]> : vector<16xindex>
// CHECK: [[cst2:%.+]] = arith.constant dense<[128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248]> : vector<16xindex>
// CHECK: [[cst3:%.+]] = arith.constant dense<[0, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120]> : vector<16xindex>
// CHECK-COUNT-4: xegpu.store {{.*}}[{{.*}}], {{.*}} <{chunk_size = 2 : i64, l1_hint = #xegpu.cache_hint<cached>}> : vector<16x2xf32>, ui64, vector<16xindex>, vector<16xi1>
gpu.func @store_with_offsets_chunk(%src: ui64) {
%cst = arith.constant dense<[
0, 8, 16, 24, 32, 40, 48, 56,
64, 72, 80, 88, 96, 104, 112, 120,
128, 136, 144, 152, 160, 168, 176, 184,
192, 200, 208, 216, 224, 232, 240, 248
]> : vector<32xindex>

%c17 = arith.constant 17: index
%mask = vector.create_mask %c17: vector<32xi1>

%st_vec = arith.constant dense<1023.>: vector<32x4xf32>
xegpu.store %st_vec, %src[%cst], %mask {chunk_size = 4, layout_operand_0 = #xegpu.layout<inst_data = [16, 2]>,
layout_operand_2 = #xegpu.layout<inst_data = [16, 2]>,
layout_operand_3 = #xegpu.layout<inst_data = [16, 2]>,
l1_hint = #xegpu.cache_hint<cached>} : vector<32x4xf32>, ui64, vector<32xindex>, vector<32xi1>
gpu.return
}
}