maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/promote-alloca-array-alloca...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

51 lines
2.2 KiB
LLVM
Raw Normal View History

AMDGPU: Fix mishandling array allocations when promoting alloca The canonical form for allocas is a single allocation of the array type. In case we see a non-canonical array alloca, make sure we aren't replacing this with an array N times smaller. llvm-svn: 267916
2016-04-29 02:38:48 +08:00
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-promote-alloca < %s | FileCheck %s
; Make sure this allocates the correct size if the alloca has a non-0
; number of elements.
; CHECK-LABEL: @array_alloca(
; CHECK: %stack = alloca i32, i32 5, align 4
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @array_alloca(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 {
AMDGPU: Fix mishandling array allocations when promoting alloca The canonical form for allocas is a single allocation of the array type. In case we see a non-canonical array alloca, make sure we aren't replacing this with an array N times smaller. llvm-svn: 267916
2016-04-29 02:38:48 +08:00
entry:
%stack = alloca i32, i32 5, align 4
%ld0 = load i32, i32 addrspace(1)* %in, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %stack, i32 %ld0
store i32 4, i32* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
%ld1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %stack, i32 %ld1
store i32 5, i32* %arrayidx3, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %stack, i32 0
%ld2 = load i32, i32* %arrayidx10, align 4
store i32 %ld2, i32 addrspace(1)* %out, align 4
%arrayidx12 = getelementptr inbounds i32, i32* %stack, i32 1
%ld3 = load i32, i32* %arrayidx12
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
store i32 %ld3, i32 addrspace(1)* %arrayidx13
ret void
}
; CHECK-LABEL: @array_alloca_dynamic(
; CHECK: %stack = alloca i32, i32 %size, align 4
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 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). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @array_alloca_dynamic(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in, i32 %size) #0 {
AMDGPU: Fix mishandling array allocations when promoting alloca The canonical form for allocas is a single allocation of the array type. In case we see a non-canonical array alloca, make sure we aren't replacing this with an array N times smaller. llvm-svn: 267916
2016-04-29 02:38:48 +08:00
entry:
%stack = alloca i32, i32 %size, align 4
%ld0 = load i32, i32 addrspace(1)* %in, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %stack, i32 %ld0
store i32 4, i32* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
%ld1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %stack, i32 %ld1
store i32 5, i32* %arrayidx3, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %stack, i32 0
%ld2 = load i32, i32* %arrayidx10, align 4
store i32 %ld2, i32 addrspace(1)* %out, align 4
%arrayidx12 = getelementptr inbounds i32, i32* %stack, i32 1
%ld3 = load i32, i32* %arrayidx12
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
store i32 %ld3, i32 addrspace(1)* %arrayidx13
ret void
}
attributes #0 = { nounwind }