mirror of
https://github.com/RPCS3/llvm.git
synced 2025-05-15 09:56:02 +00:00
d706d030af
Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
31 lines
1.3 KiB
LLVM
31 lines
1.3 KiB
LLVM
; RUN: opt -mtriple=amdgcn-- -load-store-vectorizer -S -o - %s | FileCheck %s
|
|
|
|
@lds = internal addrspace(3) global [512 x float] undef, align 4
|
|
|
|
; The original load has an implicit alignment of 4, and should not
|
|
; increase to an align 8 load.
|
|
|
|
; CHECK-LABEL: @load_keep_base_alignment_missing_align(
|
|
; CHECK: load <2 x float>, <2 x float> addrspace(3)* %{{[0-9]+}}, align 4
|
|
define amdgpu_kernel void @load_keep_base_alignment_missing_align(float addrspace(1)* %out) {
|
|
%ptr0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 11
|
|
%val0 = load float, float addrspace(3)* %ptr0
|
|
|
|
%ptr1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 12
|
|
%val1 = load float, float addrspace(3)* %ptr1
|
|
%add = fadd float %val0, %val1
|
|
store float %add, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
; CHECK-LABEL: @store_keep_base_alignment_missing_align(
|
|
; CHECK: store <2 x float> zeroinitializer, <2 x float> addrspace(3)* %{{[0-9]+}}, align 4
|
|
define amdgpu_kernel void @store_keep_base_alignment_missing_align() {
|
|
%arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 1
|
|
%arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 2
|
|
store float 0.0, float addrspace(3)* %arrayidx0
|
|
store float 0.0, float addrspace(3)* %arrayidx1
|
|
ret void
|
|
}
|