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

AMDGPU: Disable AMDGPUPromoteAlloca pass for shader calling conventions. 

Summary:
The work item intrinsics are not available for the shader
calling conventions. And even if we did hook them up most
shader stages haves some extra restrictions on the amount
of available LDS.

Reviewers: tstellarAMD, arsenm

Subscribers: nhaehnle, arsenm, llvm-commits, kzhuravl

Differential Revision: https://reviews.llvm.org/D20728

llvm-svn: 275779
This commit is contained in:
Nicolai Haehnle 2016-07-18 09:02:47 +00:00
parent 97be487728
commit bef1ceb815
2 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
View File

@ -649,6 +649,12 @@ void AMDGPUPromoteAlloca::handleAlloca(AllocaInst &I) {
const Function &ContainingFunction = *I.getParent()->getParent();
// Don't promote the alloca to LDS for shader calling conventions as the work
// item ID intrinsics are not supported for these calling conventions.
// Furthermore not all LDS is available for some of the stages.
if (AMDGPU::isShader(ContainingFunction.getCallingConv()))
return;
// FIXME: We should also try to get this value from the reqd_work_group_size
// function attribute if it is available.
unsigned WorkGroupSize = AMDGPU::getMaximumWorkGroupSize(ContainingFunction);

29
llvm/test/CodeGen/AMDGPU/promote-alloca-shaders.ll Normal file
View File

@ -0,0 +1,29 @@
; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-promote-alloca < %s | FileCheck -check-prefix=IR %s
; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=ASM %s
; IR-LABEL: define amdgpu_vs void @promote_alloca_shaders(i32 addrspace(1)* inreg %out, i32 addrspace(1)* inreg %in) #0 {
; IR: alloca [5 x i32]
; ASM-LABEL: {{^}}promote_alloca_shaders:
; ASM: ; LDSByteSize: 0 bytes/workgroup (compile time only)
define amdgpu_vs void @promote_alloca_shaders(i32 addrspace(1)* inreg %out, i32 addrspace(1)* inreg %in) #0 {
entry:
%stack = alloca [5 x i32], align 4
%tmp0 = load i32, i32 addrspace(1)* %in, align 4
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %tmp0
store i32 4, i32* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
%tmp1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %tmp1
store i32 5, i32* %arrayidx3, align 4
%arrayidx4 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
%tmp2 = load i32, i32* %arrayidx4, align 4
store i32 %tmp2, i32 addrspace(1)* %out, align 4
%arrayidx5 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
%tmp3 = load i32, i32* %arrayidx5
%arrayidx6 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
store i32 %tmp3, i32 addrspace(1)* %arrayidx6
ret void
}
attributes #0 = { nounwind "amdgpu-max-work-group-size"="64" }