RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 20:09:46 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

AMDGPU: Skip all meta instructions in hazard recognizer

Browse Source 
This was not adding a necessary nop due to thinking the kill counted.
This commit is contained in:
Matt Arsenault 2020-09-09 18:08:48 -04:00
parent 532a3cd6c0
commit cc5cc5b57a
2 changed files with 42 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -368,7 +368,7 @@ static int getWaitStatesSince(GCNHazardRecognizer::IsHazardFn IsHazard,
if (IsHazard(&*I))
return WaitStates;
if (I->isInlineAsm() || I->isImplicitDef() || I->isDebugInstr())
if (I->isInlineAsm() || I->isMetaInstruction())
continue;
WaitStates += SIInstrInfo::getNumWaitStates(*I);

41
test/CodeGen/AMDGPU/hazard-recognizer-meta-insts.mir Normal file
View File

@ -0,0 +1,41 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=gfx906 -run-pass=post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GFX9 %s
# Make sure the kill is skipped for hazard purposes, so the nop is
# correctly inserted.
---
name: global_store_dwordx4_data_hazard_kill
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX9-LABEL: name: global_store_dwordx4_data_hazard_kill
; GFX9: GLOBAL_STORE_DWORDX4 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5, 0, 0, 0, 0, implicit $exec
; GFX9: $vgpr2 = KILL
; GFX9: S_NOP 0
; GFX9: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
GLOBAL_STORE_DWORDX4 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5, 0, 0, 0, 0, implicit $exec
$vgpr2 = KILL
$vgpr2 = V_MOV_B32_e32 0, implicit $exec
...
---
name: global_store_dwordx3_data_hazard_kill
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4
; GFX9-LABEL: name: global_store_dwordx3_data_hazard_kill
; GFX9: GLOBAL_STORE_DWORDX3 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4, 0, 0, 0, 0, implicit $exec
; GFX9: $vgpr2 = KILL
; GFX9: S_NOP 0
; GFX9: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
GLOBAL_STORE_DWORDX3 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4, 0, 0, 0, 0, implicit $exec
$vgpr2 = KILL
$vgpr2 = V_MOV_B32_e32 0, implicit $exec
...