forked from OSchip/llvm-project
118 lines
5.7 KiB
LLVM
118 lines
5.7 KiB
LLVM
; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-promote-alloca < %s | FileCheck %s
|
|
|
|
; CHECK: @promote_alloca_size_63.stack = internal unnamed_addr addrspace(3) global [63 x [5 x i32]] undef, align 4
|
|
|
|
define void @promote_alloca_size_63(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 {
|
|
entry:
|
|
%stack = alloca [5 x i32], align 4
|
|
%0 = load i32, i32 addrspace(1)* %in, align 4
|
|
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
|
|
store i32 4, i32* %arrayidx1, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
|
|
%1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
|
|
%arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
|
|
store i32 5, i32* %arrayidx3, align 4
|
|
%arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
|
|
%2 = load i32, i32* %arrayidx10, align 4
|
|
store i32 %2, i32 addrspace(1)* %out, align 4
|
|
%arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
|
|
%3 = load i32, i32* %arrayidx12
|
|
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
|
|
store i32 %3, i32 addrspace(1)* %arrayidx13
|
|
ret void
|
|
}
|
|
|
|
; CHECK: @promote_alloca_size_256.stack = internal unnamed_addr addrspace(3) global [256 x [5 x i32]] undef, align 4
|
|
|
|
define void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #1 {
|
|
entry:
|
|
%stack = alloca [5 x i32], align 4
|
|
%0 = load i32, i32 addrspace(1)* %in, align 4
|
|
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
|
|
store i32 4, i32* %arrayidx1, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
|
|
%1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
|
|
%arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
|
|
store i32 5, i32* %arrayidx3, align 4
|
|
%arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
|
|
%2 = load i32, i32* %arrayidx10, align 4
|
|
store i32 %2, i32 addrspace(1)* %out, align 4
|
|
%arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
|
|
%3 = load i32, i32* %arrayidx12
|
|
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
|
|
store i32 %3, i32 addrspace(1)* %arrayidx13
|
|
ret void
|
|
}
|
|
|
|
; CHECK: @promote_alloca_size_1600.stack = internal unnamed_addr addrspace(3) global [1600 x [5 x i32]] undef, align 4
|
|
|
|
define void @promote_alloca_size_1600(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #2 {
|
|
entry:
|
|
%stack = alloca [5 x i32], align 4
|
|
%0 = load i32, i32 addrspace(1)* %in, align 4
|
|
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
|
|
store i32 4, i32* %arrayidx1, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
|
|
%1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
|
|
%arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
|
|
store i32 5, i32* %arrayidx3, align 4
|
|
%arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
|
|
%2 = load i32, i32* %arrayidx10, align 4
|
|
store i32 %2, i32 addrspace(1)* %out, align 4
|
|
%arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
|
|
%3 = load i32, i32* %arrayidx12
|
|
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
|
|
store i32 %3, i32 addrspace(1)* %arrayidx13
|
|
ret void
|
|
}
|
|
|
|
; CHECK: @occupancy_0(
|
|
; CHECK: alloca [5 x i32]
|
|
define void @occupancy_0(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #3 {
|
|
entry:
|
|
%stack = alloca [5 x i32], align 4
|
|
%0 = load i32, i32 addrspace(1)* %in, align 4
|
|
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
|
|
store i32 4, i32* %arrayidx1, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
|
|
%1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
|
|
%arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
|
|
store i32 5, i32* %arrayidx3, align 4
|
|
%arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
|
|
%2 = load i32, i32* %arrayidx10, align 4
|
|
store i32 %2, i32 addrspace(1)* %out, align 4
|
|
%arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
|
|
%3 = load i32, i32* %arrayidx12
|
|
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
|
|
store i32 %3, i32 addrspace(1)* %arrayidx13
|
|
ret void
|
|
}
|
|
|
|
; CHECK: @occupancy_max(
|
|
; CHECK: alloca [5 x i32]
|
|
define void @occupancy_max(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #4 {
|
|
entry:
|
|
%stack = alloca [5 x i32], align 4
|
|
%0 = load i32, i32 addrspace(1)* %in, align 4
|
|
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
|
|
store i32 4, i32* %arrayidx1, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
|
|
%1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
|
|
%arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
|
|
store i32 5, i32* %arrayidx3, align 4
|
|
%arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
|
|
%2 = load i32, i32* %arrayidx10, align 4
|
|
store i32 %2, i32 addrspace(1)* %out, align 4
|
|
%arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
|
|
%3 = load i32, i32* %arrayidx12
|
|
%arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
|
|
store i32 %3, i32 addrspace(1)* %arrayidx13
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind "amdgpu-max-work-group-size"="63" }
|
|
attributes #1 = { nounwind "amdgpu-max-waves-per-eu"="3" "amdgpu-max-work-group-size"="256" }
|
|
attributes #2 = { nounwind "amdgpu-max-waves-per-eu"="1" "amdgpu-max-work-group-size"="1600" }
|
|
attributes #3 = { nounwind "amdgpu-max-waves-per-eu"="0" }
|
|
attributes #4 = { nounwind "amdgpu-max-waves-per-eu"="-1" }
|