Skip to content
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

[LLVMGPU] Support masked contraction in operand upcasting #19972

Merged
merged 1 commit into from
Feb 13, 2025
Merged

[LLVMGPU] Support masked contraction in operand upcasting #19972

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
21 changes: 14 additions & 7 deletions compiler/src/iree/compiler/Codegen/LLVMGPU/LLVMGPUVectorLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,11 +26,13 @@ namespace mlir::iree_compiler {
namespace {

struct PromoteContractOperands final
: public OpRewritePattern<vector::ContractionOp> {
using OpRewritePattern::OpRewritePattern;
: public vector::MaskableOpRewritePattern<vector::ContractionOp> {
using MaskableOpRewritePattern::MaskableOpRewritePattern;

LogicalResult matchAndRewrite(vector::ContractionOp contractOp,
PatternRewriter &rewriter) const override {
FailureOr<Value>
matchAndRewriteMaskableOp(vector::ContractionOp contractOp,
vector::MaskingOpInterface maskOp,
PatternRewriter &rewriter) const override {
Type operandElType = getElementTypeOrSelf(contractOp.getLhsType());
Type resultElType = getElementTypeOrSelf(contractOp.getResultType());

Expand All @@ -44,11 +46,16 @@ struct PromoteContractOperands final
Value rhs =
promoteToElementType(loc, rewriter, contractOp.getRhs(), resultElType);

rewriter.replaceOpWithNewOp<vector::ContractionOp>(
contractOp, lhs, rhs, contractOp.getAcc(), contractOp.getIndexingMaps(),
auto replacement = rewriter.create<vector::ContractionOp>(
loc, lhs, rhs, contractOp.getAcc(), contractOp.getIndexingMaps(),
contractOp.getIteratorTypes());

return success();
if (!maskOp) {
return replacement.getResult();
}
auto maskedOp = vector::maskOperation(
rewriter, replacement, maskOp.getMask(), maskOp.getPassthru());
return maskedOp->getResult(0);
}

Value promoteToElementType(Location loc, RewriterBase &rewriter, Value v,
Expand Down
21 changes: 21 additions & 0 deletions compiler/src/iree/compiler/Codegen/LLVMGPU/test/vector_lowering.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,3 +17,24 @@ module {
// CHECK: %[[SPLAT:.+]] = vector.splat %[[ELEM]] : vector<8xf16>
// CHECK: %[[INSERT:.+]] = vector.insert %[[SPLAT]], %[[INIT]] [0] : vector<8xf16> into vector<1x8xf16>
// CHECK: return %[[INSERT]]

// -----

module {
func.func @contraction_masked(%lhs: vector<3xf16>, %rhs: vector<2x3xf16>, %acc: vector<2xf32>, %mask: vector<3x2xi1>) -> vector<2xf32> {
%ret = vector.mask %mask { vector.contract {indexing_maps = [affine_map<(d0, d1) -> (d0)>, affine_map<(d0, d1) -> (d1, d0)>, affine_map<(d0, d1) -> (d1)>], iterator_types = ["reduction", "parallel"], kind = #vector.kind<add>} %lhs, %rhs, %acc : vector<3xf16>, vector<2x3xf16> into vector<2xf32> } : vector<3x2xi1> -> vector<2xf32>
return %ret: vector<2xf32>
}
}

// CHECK-LABEL: func.func @contraction_masked
// CHECK-SAME: %[[LHS:.+]]: vector<3xf16>, %[[RHS:.+]]: vector<2x3xf16>, %[[ACC:.+]]: vector<2xf32>, %[[MASK:.+]]: vector<3x2xi1>
// CHECK: %[[TPRHS:.+]] = vector.transpose %[[RHS]], [1, 0] : vector<2x3xf16> to vector<3x2xf16>
// CHECK: %[[RHS_EXTRACT:.+]] = vector.extract %[[TPRHS]][0] : vector<2xf16> from vector<3x2xf16>
// CHECK: %[[LHS_EXTRACT:.+]] = vector.extract %[[LHS]][0] : f16 from vector<3xf16>
// CHECK: %[[RHS_CAST:.+]] = arith.extf %[[RHS_EXTRACT]] : vector<2xf16> to vector<2xf32>
// CHECK: %[[LHS_CAST:.+]] = arith.extf %[[LHS_EXTRACT]] : f16 to f32
// CHECK: %[[MASK_EXTRACT:.+]] = vector.extract %[[MASK]][0] : vector<2xi1> from vector<3x2xi1>
// CHECK: %[[LHS_SPLAT:.+]] = vector.splat %[[LHS_CAST]] : vector<2xf32>
// CHECK: %[[FMA:.+]] = vector.fma %[[RHS_CAST]], %[[LHS_SPLAT]], %[[ACC]] : vector<2xf32>
// CHECK: arith.select %[[MASK_EXTRACT]], %[[FMA]], %[[ACC]] : vector<2xi1>, vector<2xf32>
Loading