maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] stop buffer_store being moved illegally 

Summary:
The machine instruction scheduler was illegally moving a buffer store
past a buffer load with the same descriptor and offset. Fixed by marking
buffer ops as mayAlias and isAliased. This may be overly conservative,
and we may need to revisit.

Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D43332

Change-Id: Iff3173d9e0653e830474546276ab9d30318b8ef7
llvm-svn: 325567
This commit is contained in:
Tim Renouf 2018-02-20 10:03:38 +00:00
parent b8bf5a6c85
commit 8234b4893a
2 changed files with 55 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
View File

@ -70,15 +70,11 @@ public:
}
bool isAliased(const MachineFrameInfo *) const override {
// FIXME: If we ever change image intrinsics to accept fat pointers, then
// this could be true for some cases.
return false;
return true;
}
bool mayAlias(const MachineFrameInfo *) const override {
// FIXME: If we ever change image intrinsics to accept fat pointers, then
// this could be true for some cases.
return false;
return true;
}
};

53
llvm/test/CodeGen/AMDGPU/buffer-schedule.ll Normal file
View File

@ -0,0 +1,53 @@
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx803 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN %s
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN %s
; The buffer_loads and buffer_stores all access the same location. Check they do
; not get reordered by the scheduler.
; GCN-LABEL: {{^}}_amdgpu_cs_main:
; GCN: buffer_load_dword
; GCN: buffer_store_dword
; GCN: buffer_load_dword
; GCN: buffer_store_dword
; GCN: buffer_load_dword
; GCN: buffer_store_dword
; GCN: buffer_load_dword
; GCN: buffer_store_dword
; Function Attrs: nounwind
define amdgpu_cs void @_amdgpu_cs_main(<3 x i32> inreg %arg3, <3 x i32> %arg5) {
.entry:
%tmp9 = add <3 x i32> %arg3, %arg5
%tmp10 = extractelement <3 x i32> %tmp9, i32 0
%tmp11 = shl i32 %tmp10, 2
%tmp12 = inttoptr i64 undef to <4 x i32> addrspace(4)*
%tmp13 = load <4 x i32>, <4 x i32> addrspace(4)* %tmp12, align 16
%tmp14 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %tmp13, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp17 = load <4 x i32>, <4 x i32> addrspace(4)* %tmp12, align 16
call void @llvm.amdgcn.buffer.store.f32(float %tmp14, <4 x i32> %tmp17, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp20 = load <4 x i32>, <4 x i32> addrspace(4)* %tmp12, align 16
%tmp21 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %tmp20, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp22 = fadd reassoc nnan arcp contract float %tmp21, 1.000000e+00
call void @llvm.amdgcn.buffer.store.f32(float %tmp22, <4 x i32> %tmp20, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp25 = load <4 x i32>, <4 x i32> addrspace(4)* %tmp12, align 16
%tmp26 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %tmp25, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp27 = fadd reassoc nnan arcp contract float %tmp26, 1.000000e+00
call void @llvm.amdgcn.buffer.store.f32(float %tmp27, <4 x i32> %tmp25, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp30 = load <4 x i32>, <4 x i32> addrspace(4)* %tmp12, align 16
%tmp31 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %tmp30, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp32 = fadd reassoc nnan arcp contract float %tmp31, 1.000000e+00
call void @llvm.amdgcn.buffer.store.f32(float %tmp32, <4 x i32> %tmp30, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp35 = load <4 x i32>, <4 x i32> addrspace(4)* %tmp12, align 16
%tmp36 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %tmp35, i32 0, i32 %tmp11, i1 false, i1 false) #0
%tmp37 = fadd reassoc nnan arcp contract float %tmp36, 1.000000e+00
call void @llvm.amdgcn.buffer.store.f32(float %tmp37, <4 x i32> %tmp35, i32 0, i32 %tmp11, i1 false, i1 false) #0
ret void
}
declare float @llvm.amdgcn.buffer.load.f32(<4 x i32>, i32, i32, i1, i1) #2
declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1) #3
attributes #2 = { nounwind readonly }
attributes #3 = { nounwind writeonly }