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

[mlir] Fix the wrong computation of dynamic strides for lowering AllocOp to LLVM 

Leftover change from before the MLIR merge, reviewed at accepted at
https://github.com/tensorflow/mlir/pull/338.
This commit is contained in:
Tung Le Duc 2019-12-24 16:02:10 +09:00 committed by Alex Zinenko
parent bc5b7217dc
commit e5957ac3d7
2 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
mlir/lib/Conversion/StandardToLLVM/ConvertStandardToLLVM.cpp
View File

@ -1054,14 +1054,15 @@ struct AllocOpLowering : public LLVMLegalizationPattern<AllocOp> {
// Iterate strides in reverse order, compute runningStride and strideValues.
auto nStrides = strides.size();
SmallVector<Value, 4> strideValues(nStrides, nullptr);
for (auto indexedStride : llvm::enumerate(llvm::reverse(strides))) {
int64_t index = nStrides - 1 - indexedStride.index();
for (unsigned i = 0; i < nStrides; ++i) {
int64_t index = nStrides - 1 - i;
if (strides[index] == MemRefType::getDynamicStrideOrOffset())
// Identity layout map is enforced in the match function, so we compute:
// `runningStride *= sizes[index]`
// `runningStride *= sizes[index + 1]`
runningStride =
runningStride
? rewriter.create<LLVM::MulOp>(loc, runningStride, sizes[index])
? rewriter.create<LLVM::MulOp>(loc, runningStride,
sizes[index + 1])
: createIndexConstant(rewriter, loc, 1);
else
runningStride = createIndexConstant(rewriter, loc, strides[index]);

6
mlir/test/Conversion/StandardToLLVM/convert-memref-ops.mlir
View File

@ -101,8 +101,8 @@ func @mixed_alloc(%arg0: index, %arg1: index) -> memref<?x42x?xf32> {
// CHECK-NEXT: %[[off:.*]] = llvm.mlir.constant(0 : index) : !llvm.i64
// CHECK-NEXT: llvm.insertvalue %[[off]], %{{.*}}[2] : !llvm<"{ float*, float*, i64, [3 x i64], [3 x i64] }">
// CHECK-NEXT: %[[st2:.*]] = llvm.mlir.constant(1 : index) : !llvm.i64
// CHECK-NEXT: %[[st1:.*]] = llvm.mul %{{.*}}, %[[c42]] : !llvm.i64
// CHECK-NEXT: %[[st0:.*]] = llvm.mul %{{.*}}, %[[M]] : !llvm.i64
// CHECK-NEXT: %[[st1:.*]] = llvm.mul %{{.*}}, %[[N]] : !llvm.i64
// CHECK-NEXT: %[[st0:.*]] = llvm.mul %{{.*}}, %[[c42]] : !llvm.i64
// CHECK-NEXT: llvm.insertvalue %[[M]], %{{.*}}[3, 0] : !llvm<"{ float*, float*, i64, [3 x i64], [3 x i64] }">
// CHECK-NEXT: llvm.insertvalue %[[st0]], %{{.*}}[4, 0] : !llvm<"{ float*, float*, i64, [3 x i64], [3 x i64] }">
// CHECK-NEXT: llvm.insertvalue %[[c42]], %{{.*}}[3, 1] : !llvm<"{ float*, float*, i64, [3 x i64], [3 x i64] }">
@ -142,7 +142,7 @@ func @dynamic_alloc(%arg0: index, %arg1: index) -> memref<?x?xf32> {
// CHECK-NEXT: %[[off:.*]] = llvm.mlir.constant(0 : index) : !llvm.i64
// CHECK-NEXT: llvm.insertvalue %[[off]], %{{.*}}[2] : !llvm<"{ float*, float*, i64, [2 x i64], [2 x i64] }">
// CHECK-NEXT: %[[st1:.*]] = llvm.mlir.constant(1 : index) : !llvm.i64
// CHECK-NEXT: %[[st0:.*]] = llvm.mul %{{.*}}, %[[M]] : !llvm.i64
// CHECK-NEXT: %[[st0:.*]] = llvm.mul %{{.*}}, %[[N]] : !llvm.i64
// CHECK-NEXT: llvm.insertvalue %[[M]], %{{.*}}[3, 0] : !llvm<"{ float*, float*, i64, [2 x i64], [2 x i64] }">
// CHECK-NEXT: llvm.insertvalue %[[st0]], %{{.*}}[4, 0] : !llvm<"{ float*, float*, i64, [2 x i64], [2 x i64] }">
// CHECK-NEXT: llvm.insertvalue %[[N]], %{{.*}}[3, 1] : !llvm<"{ float*, float*, i64, [2 x i64], [2 x i64] }">