maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Avoid doing tile + fuse if tile sizes are zero. 

Reviewed By: gysit

Differential Revision: https://reviews.llvm.org/D118576
This commit is contained in:
Mahesh Ravishankar 2022-02-01 16:54:05 +00:00
parent 3615182025
commit a2361eb281
2 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
mlir/lib/Dialect/Linalg/Transforms/Transforms.cpp
View File

@ -592,6 +592,10 @@ LogicalResult mlir::linalg::LinalgTileAndFuseTensorOpsPattern::matchAndRewrite(
SmallVector<int64_t> rootTileSizes(options.tileSizes.begin(),
options.tileSizes.begin() +
rootOp.getNumLoops());
if (llvm::all_of(rootTileSizes, [](int64_t ts) { return ts == 0; })) {
return rewriter.notifyMatchFailure(
op, "all tile sizes are zero, nothing to do");
}
SmallVector<int64_t> rootInterchange =
options.tileInterchange.empty()
? llvm::to_vector<6>(llvm::seq<int64_t>(0, rootOp.getNumLoops()))

19
mlir/test/Dialect/Linalg/tile-and-fuse-no-fuse.mlir Normal file
View File

@ -0,0 +1,19 @@
// RUN: mlir-opt %s -test-linalg-codegen-strategy="anchor-op=linalg.generic fuse tile-sizes=0,0 run-enable-pass=false" -cse -split-input-file | FileCheck %s
builtin.func @no_fuse_gemm(%arg0 : tensor<?x?xf32>, %arg1 : tensor<?x?xf32>) -> tensor<?x?xf32> {
%c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index
%cst = arith.constant 0.0 : f32
%d0 = tensor.dim %arg0, %c0 : tensor<?x?xf32>
%d1 = tensor.dim %arg1, %c1 : tensor<?x?xf32>
%init = linalg.init_tensor [%d0, %d1] : tensor<?x?xf32>
%fill = linalg.fill(%cst, %init) : f32, tensor<?x?xf32> -> tensor<?x?xf32>
%result = linalg.matmul ins(%arg0, %arg1 : tensor<?x?xf32>, tensor<?x?xf32>)
outs(%fill : tensor<?x?xf32>) -> tensor<?x?xf32>
return %result : tensor<?x?xf32>
}
// CHECK-LABEL: @no_fuse_gemm(
// CHECK-NOT: scf.for
// CHECK: linalg.fill
// CHECK-NOT: scf.for
// CHECK: linalg.matmul