1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 12:43:36 +01:00
llvm-mirror/test/CodeGen/AMDGPU/merge-store-crash.ll
Matt Arsenault 53cf167c73 AMDGPU: Convert some tests to use new buffer intrinsics
The legacy not struct or raw buffer intrinsics should now all be
consolidated into the tests specifically for those intrinsics.
2020-07-30 10:30:43 -04:00

37 lines
1.6 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck %s
; This is used to crash in LiveIntervalAnalysis via SILoadStoreOptimizer
; while fixing up the merge of two ds_write instructions.
@tess_lds = external addrspace(3) global [8192 x i32]
; CHECK-LABEL: {{^}}main:
; CHECK-DAG: ds_write_b32
; CHECK-DAG: ds_write_b32
; CHECK-DAG: v_mov_b32_e32 v1, v0
; CHECK: tbuffer_store_format_xyzw v[0:3],
define amdgpu_vs void @main(i32 inreg %arg) {
main_body:
%tmp = load float, float addrspace(3)* undef, align 4
%tmp1 = load float, float addrspace(3)* undef, align 4
store float %tmp, float addrspace(3)* null, align 4
%tmp2 = bitcast float %tmp to i32
%tmp3 = add nuw nsw i32 0, 1
%tmp4 = zext i32 %tmp3 to i64
%tmp5 = getelementptr [8192 x i32], [8192 x i32] addrspace(3)* @tess_lds, i64 0, i64 %tmp4
%tmp6 = bitcast i32 addrspace(3)* %tmp5 to float addrspace(3)*
store float %tmp1, float addrspace(3)* %tmp6, align 4
%tmp7 = bitcast float %tmp1 to i32
%tmp8 = insertelement <4 x i32> undef, i32 %tmp2, i32 0
%tmp9 = insertelement <4 x i32> %tmp8, i32 %tmp7, i32 1
%tmp10 = insertelement <4 x i32> %tmp9, i32 undef, i32 2
%tmp11 = insertelement <4 x i32> %tmp10, i32 undef, i32 3
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %tmp11, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 78, i32 3) #2
ret void
}
declare void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32, i32 immarg, i32 immarg) #0
attributes #0 = { nounwind willreturn writeonly }