llvm/test/CodeGen/AMDGPU/promote-alloca-globals.ll
Matt Arsenault 7985e4be56 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.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@269708 91177308-0d34-0410-b5e6-96231b3b80d8
2016-05-16 21:19:59 +00:00

36 lines
1.9 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
@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
; IR-LABEL: define void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) {
; IR: alloca [10 x i32]
; ASM-LABEL: {{^}}promote_alloca_size_256:
; ASM: ; LDSByteSize: 60000 bytes/workgroup (compile time only)
define void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) {
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
%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
ret void
}