1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-23 04:52:54 +02:00
llvm-mirror/test/CodeGen/AMDGPU/promote-alloca-shaders.ll
Nicolai Haehnle bd0d64e160 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
2016-07-18 09:02:47 +00:00

30 lines
1.5 KiB
LLVM

; 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" }