mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-24 13:33:37 +02:00
71c5d5fa5f
In the case where op = add, y = base_ptr, and x = offset, this transform: (op y, (op x, c1)) -> (op (op x, y), c1) breaks the canonical form of add by putting the base pointer in the second operand and the offset in the first. This fix is important for the R600 target, because for some address spaces the base pointer and the offset are stored in separate register classes. The old pattern caused the ISel code for matching addressing modes to put the base pointer and offset in the wrong register classes, which required no-trivial code transformations to fix. llvm-svn: 262148
34 lines
1.3 KiB
LLVM
34 lines
1.3 KiB
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
; Test for a bug where DAGCombiner::ReassociateOps() was creating adds
|
|
; with offset in the first operand and base pointers in the second.
|
|
|
|
; CHECK-LABEL: {{^}}store_same_base_ptr:
|
|
; CHECK: buffer_store_dword v{{[0-9]+}}, [[VADDR:v\[[0-9]+:[0-9]+\]]], [[SADDR:s\[[0-9]+:[0-9]+\]]]
|
|
; CHECK: buffer_store_dword v{{[0-9]+}}, [[VADDR]], [[SADDR]]
|
|
; CHECK: buffer_store_dword v{{[0-9]+}}, [[VADDR]], [[SADDR]]
|
|
; CHECK: buffer_store_dword v{{[0-9]+}}, [[VADDR]], [[SADDR]]
|
|
|
|
define void @store_same_base_ptr(i32 addrspace(1)* %out) {
|
|
entry:
|
|
%id = call i32 @llvm.amdgcn.workitem.id.x() #0
|
|
%offset = sext i32 %id to i64
|
|
%offset0 = add i64 %offset, 1027
|
|
%ptr0 = getelementptr i32, i32 addrspace(1)* %out, i64 %offset0
|
|
store i32 3, i32 addrspace(1)* %ptr0
|
|
%offset1 = add i64 %offset, 1026
|
|
%ptr1 = getelementptr i32, i32 addrspace(1)* %out, i64 %offset1
|
|
store i32 2, i32 addrspace(1)* %ptr1
|
|
%offset2 = add i64 %offset, 1025
|
|
%ptr2 = getelementptr i32, i32 addrspace(1)* %out, i64 %offset2
|
|
store i32 1, i32 addrspace(1)* %ptr2
|
|
%offset3 = add i64 %offset, 1024
|
|
%ptr3 = getelementptr i32, i32 addrspace(1)* %out, i64 %offset3
|
|
store i32 0, i32 addrspace(1)* %ptr3
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #0
|
|
|
|
attributes #0 = { nounwind readnone }
|