1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
llvm-mirror/test/CodeGen/AMDGPU/hazard.mir
Nicolai Haehnle 12b9057d7f AMDGPU: Make worst-case assumption about the wait states in inline assembly
Summary:
Mesa still uses a hack where empty inline assembly is used as a kind of
optimization barrier. This exposed a problem where not enough wait states
were inserted, because the hazard recognizer implicitly assumed that each
inline assembly "instruction" has at least one wait state.

Reviewers: arsenm

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

Differential Revision: https://reviews.llvm.org/D37205

llvm-svn: 312635
2017-09-06 13:50:13 +00:00

61 lines
1.7 KiB
YAML

# RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefix=GCN -check-prefix=VI %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
# GCN-LABEL: name: hazard_implicit_def
# GCN: bb.0.entry:
# GCN: %m0 = S_MOV_B32
# GFX9: S_NOP 0
# VI-NOT: S_NOP_0
# GCN: V_INTERP_P1_F32
---
name: hazard_implicit_def
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
liveins:
- { reg: '%sgpr7', virtual-reg: '' }
- { reg: '%vgpr4', virtual-reg: '' }
body: |
bb.0.entry:
liveins: %sgpr7, %vgpr4
%m0 = S_MOV_B32 killed %sgpr7
%vgpr5 = IMPLICIT_DEF
%vgpr0 = V_INTERP_P1_F32 killed %vgpr4, 0, 0, implicit %m0, implicit %exec
SI_RETURN_TO_EPILOG killed %vgpr5, killed %vgpr0
...
# GCN-LABEL: name: hazard_inlineasm
# GCN: bb.0.entry:
# GCN: %m0 = S_MOV_B32
# GFX9: S_NOP 0
# VI-NOT: S_NOP_0
# GCN: V_INTERP_P1_F32
---
name: hazard_inlineasm
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
liveins:
- { reg: '%sgpr7', virtual-reg: '' }
- { reg: '%vgpr4', virtual-reg: '' }
body: |
bb.0.entry:
liveins: %sgpr7, %vgpr4
%m0 = S_MOV_B32 killed %sgpr7
INLINEASM $"; no-op", 1, 327690, def %vgpr5
%vgpr0 = V_INTERP_P1_F32 killed %vgpr4, 0, 0, implicit %m0, implicit %exec
SI_RETURN_TO_EPILOG killed %vgpr5, killed %vgpr0
...