diff options
3 files changed, 5 insertions, 9 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp index ce17f027b52..00c88a4fb50 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp @@ -267,12 +267,10 @@ unsigned AMDGPUTTIImpl::getLoadStoreVecRegBitWidth(unsigned AddrSpace) const { return 512; } - if (AddrSpace == AS.FLAT_ADDRESS) - return 128; - - if (AddrSpace == AS.LOCAL_ADDRESS || + if (AddrSpace == AS.FLAT_ADDRESS || + AddrSpace == AS.LOCAL_ADDRESS || AddrSpace == AS.REGION_ADDRESS) - return ST->useDS128() ? 128 : 64; + return 128; if (AddrSpace == AS.PRIVATE_ADDRESS) return 8 * ST->getMaxPrivateElementSize(); diff --git a/llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/merge-stores.ll b/llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/merge-stores.ll index 19fc44bb6c8..5eb3b25c1dc 100644 --- a/llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/merge-stores.ll +++ b/llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/merge-stores.ll @@ -504,8 +504,7 @@ define amdgpu_kernel void @merge_local_store_2_constants_i32_align_2(i32 addrspa } ; CHECK-LABEL: @merge_local_store_4_constants_i32 -; CHECK: store <2 x i32> <i32 456, i32 333>, <2 x i32> addrspace(3)* -; CHECK: store <2 x i32> <i32 1234, i32 123>, <2 x i32> addrspace(3)* +; CHECK: store <4 x i32> <i32 1234, i32 123, i32 456, i32 333>, <4 x i32> addrspace(3)* define amdgpu_kernel void @merge_local_store_4_constants_i32(i32 addrspace(3)* %out) #0 { %out.gep.1 = getelementptr i32, i32 addrspace(3)* %out, i32 1 %out.gep.2 = getelementptr i32, i32 addrspace(3)* %out, i32 2 diff --git a/llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/multiple_tails.ll b/llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/multiple_tails.ll index 8a78f3d7e9b..b684ca8c12c 100644 --- a/llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/multiple_tails.ll +++ b/llvm/test/Transforms/LoadStoreVectorizer/AMDGPU/multiple_tails.ll @@ -29,11 +29,10 @@ define amdgpu_kernel void @no_crash(i32 %arg) { ; longest chain vectorized ; CHECK-LABEL: @interleave_get_longest -; CHECK: load <2 x i32> +; CHECK: load <4 x i32> ; CHECK: load i32 ; CHECK: store <2 x i32> zeroinitializer ; CHECK: load i32 -; CHECK: load <2 x i32> ; CHECK: load i32 ; CHECK: load i32 |
