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-globals.ll

36 lines
1.9 KiB
LLVM
Raw Normal View History

AMDGPU: Account for globals in AMDGPUPromoteAlloca pass Patch by Bas Nieuwenhuizen llvm-svn: 267791
2016-04-28 05:05:08 +08:00
; 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
AMDGPU: Fix promote alloca pass creating huge arrays This was assuming it could use all memory before, which is a bad decision because it restricts occupancy. By default, only try to use enough space that could reduce occupancy to 7, an arbitrarily chosen limit. Based on the exist LDS usage, try to round up to the limit in the current tier instead of further hurting occupancy. This isn't ideal, because it doesn't accurately know how much space is going to be used for alignment padding. llvm-svn: 269708
2016-05-17 05:19:59 +08:00
@global_array0 = internal unnamed_addr addrspace(3) global [750 x [10 x i32]] undef, align 4
@global_array1 = internal unnamed_addr addrspace(3) global [750 x [10 x i32]] undef, align 4
AMDGPU: Account for globals in AMDGPUPromoteAlloca pass Patch by Bas Nieuwenhuizen llvm-svn: 267791
2016-04-28 05:05:08 +08:00
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
; IR-LABEL: define amdgpu_kernel void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) {
AMDGPU: Account for globals in AMDGPUPromoteAlloca pass Patch by Bas Nieuwenhuizen llvm-svn: 267791
2016-04-28 05:05:08 +08:00
; IR: alloca [10 x i32]
; ASM-LABEL: {{^}}promote_alloca_size_256:
; ASM: ; LDSByteSize: 60000 bytes/workgroup (compile time only)
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 @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) {
AMDGPU: Account for globals in AMDGPUPromoteAlloca pass Patch by Bas Nieuwenhuizen llvm-svn: 267791
2016-04-28 05:05:08 +08:00
entry:
%stack = alloca [10 x i32], align 4
%tmp = load i32, i32 addrspace(1)* %in, align 4
%arrayidx1 = getelementptr inbounds [10 x i32], [10 x i32]* %stack, i32 0, i32 %tmp
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 [10 x i32], [10 x i32]* %stack, i32 0, i32 %tmp1
store i32 5, i32* %arrayidx3, align 4
%arrayidx10 = getelementptr inbounds [10 x i32], [10 x i32]* %stack, i32 0, i32 0
%tmp2 = load i32, i32* %arrayidx10, align 4
store i32 %tmp2, i32 addrspace(1)* %out, align 4
%arrayidx12 = getelementptr inbounds [10 x i32], [10 x i32]* %stack, i32 0, i32 1
%tmp3 = load i32, i32* %arrayidx12
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
store i32 %tmp3, i32 addrspace(1)* %arrayidx13
AMDGPU: Fix promote alloca pass creating huge arrays This was assuming it could use all memory before, which is a bad decision because it restricts occupancy. By default, only try to use enough space that could reduce occupancy to 7, an arbitrarily chosen limit. Based on the exist LDS usage, try to round up to the limit in the current tier instead of further hurting occupancy. This isn't ideal, because it doesn't accurately know how much space is going to be used for alignment padding. llvm-svn: 269708
2016-05-17 05:19:59 +08:00
%v0 = getelementptr inbounds [750 x [10 x i32]], [750 x [10 x i32]] addrspace(3)* @global_array0, i32 0, i32 0, i32 0
store i32 %tmp3, i32 addrspace(3)* %v0
%v1 = getelementptr inbounds [750 x [10 x i32]], [750 x [10 x i32]] addrspace(3)* @global_array1, i32 0, i32 0, i32 0
store i32 %tmp3, i32 addrspace(3)* %v1
AMDGPU: Account for globals in AMDGPUPromoteAlloca pass Patch by Bas Nieuwenhuizen llvm-svn: 267791
2016-04-28 05:05:08 +08:00
ret void
}