mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-16 11:30:51 +00:00
1f996fa36b
This is equivalent to the AMDGPUTargetMachine now, but it is the starting point for separating R600 and GCN functionality into separate targets. It is recommened that users start using the gcn triple for GCN-based GPUs, because using the r600 triple for these GPUs will be deprecated in the future. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225277 91177308-0d34-0410-b5e6-96231b3b80d8
27 lines
851 B
LLVM
27 lines
851 B
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: ds_read_b64
|
|
; SI: buffer_store_dword
|
|
; SI: buffer_load_dword
|
|
; SI: buffer_store_dword
|
|
; SI: s_endpgm
|
|
define void @missing_store_reduced(i32 addrspace(1)* %out, i32 addrspace(1)* %gptr) #0 {
|
|
%ptr0 = load i32 addrspace(2)* addrspace(3)* @ptr_load, align 8
|
|
%ptr2 = getelementptr inbounds i32 addrspace(2)* %ptr0, i64 2
|
|
|
|
store i32 99, i32 addrspace(1)* %gptr, align 4
|
|
%tmp2 = load i32 addrspace(2)* %ptr2, align 4
|
|
|
|
store i32 %tmp2, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|
|
|