mirror of
https://github.com/RPCSX/llvm.git
synced 2024-12-18 01:18:33 +00:00
d706d030af
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). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
31 lines
1.1 KiB
LLVM
31 lines
1.1 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=SI %s
|
|
|
|
@ptr_load = addrspace(3) global i32 addrspace(2)* undef, align 8
|
|
|
|
; Make sure when the load from %ptr2 is folded the chain isn't lost,
|
|
; resulting in losing the store to gptr
|
|
|
|
; FUNC-LABEL: {{^}}missing_store_reduced:
|
|
; SI: s_load_dwordx2
|
|
; SI: ds_read_b64
|
|
; SI-DAG: buffer_store_dword
|
|
; SI-DAG: v_readfirstlane_b32 s[[PTR_LO:[0-9]+]], v{{[0-9]+}}
|
|
; SI: v_readfirstlane_b32 s[[PTR_HI:[0-9]+]], v{{[0-9]+}}
|
|
; SI: s_nop 3
|
|
; SI: s_load_dword s{{[0-9]+}}, s{{\[}}[[PTR_LO]]:[[PTR_HI]]{{\]}}
|
|
; SI: buffer_store_dword
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @missing_store_reduced(i32 addrspace(1)* %out, i32 addrspace(1)* %gptr) #0 {
|
|
%ptr0 = load i32 addrspace(2)*, i32 addrspace(2)* addrspace(3)* @ptr_load, align 8
|
|
%ptr2 = getelementptr inbounds i32, i32 addrspace(2)* %ptr0, i64 2
|
|
|
|
store i32 99, i32 addrspace(1)* %gptr, align 4
|
|
%tmp2 = load i32, i32 addrspace(2)* %ptr2, align 4
|
|
|
|
store i32 %tmp2, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|
|
|