RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
Code Issues Projects Releases Wiki Activity

AMDGPU: Fix assert on inline asm on gfx90a

Browse Source 
This was assuming all mayLoad instructions have one def.
This commit is contained in:
Matt Arsenault 2021-04-22 22:34:17 -04:00
parent 438fece2aa
commit 182934f750
3 changed files with 29 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/Target/AMDGPU/SIFoldOperands.cpp
View File

@ -1655,7 +1655,7 @@ bool SIFoldOperands::tryFoldLCSSAPhi(MachineInstr &PHI) {
// Attempt to convert VGPR load to an AGPR load.
bool SIFoldOperands::tryFoldLoad(MachineInstr &MI) {
assert(MI.mayLoad());
if (!ST->hasGFX90AInsts() || !MI.getNumOperands())
if (!ST->hasGFX90AInsts() || MI.getNumExplicitDefs() != 1)
return false;
MachineOperand &Def = MI.getOperand(0);

13
test/CodeGen/AMDGPU/swdev282079.ll Normal file
View File

@ -0,0 +1,13 @@
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a < %s
define protected amdgpu_kernel void @foo(i64 addrspace(1)* %arg, i64 addrspace(1)* %arg1) {
bb:
%tmp = addrspacecast i64* addrspace(5)* null to i64**
%tmp2 = call i64 @eggs(i64* undef) #1
%tmp3 = load i64*, i64** %tmp, align 8
%tmp4 = getelementptr inbounds i64, i64* %tmp3, i64 undef
store i64 %tmp2, i64* %tmp4, align 8
ret void
}
declare hidden i64 @eggs(i64*)

15
test/CodeGen/AMDGPU/swdev282079.mir
View File

@ -100,3 +100,18 @@ body: |
S_ENDPGM 0
...
# This would crash looking for a def in any mayLoad instruction
---
name: fold_inlineasm_def
tracksRegLiveness: true
body: |
bb.0:
; CHECK-LABEL: name: fold_inlineasm_def
; CHECK: INLINEASM &"s_waitcnt vmcnt($0)", 41 /* sideeffect mayload isconvergent attdialect */, 13 /* imm */, 0
; CHECK: S_ENDPGM 0
INLINEASM &"s_waitcnt vmcnt($0)", 41 /* sideeffect mayload isconvergent attdialect */, 13 /* imm */, 0
S_ENDPGM 0
...