a1fb307b4b
Conversatively allow hoisting/sinking of VALU comparisons. If the result of a comparison is masked with exec, narrowing the set of active lanes, then it is safe to hoist it as the masking instruction will never by hoisted. Heuristically this is also true for sinking, as we do not expect the result of a sunk comparison that is masked with exec to be used outside of the loop. Reviewed By: rampitec Differential Revision: https://reviews.llvm.org/D118975
134 lines
3.8 KiB
YAML
134 lines
3.8 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -run-pass=machinelicm -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
|
|
|
|
---
|
|
name: hoist_move
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; GCN-LABEL: name: hoist_move
|
|
; GCN: bb.0:
|
|
; GCN-NEXT: successors: %bb.1(0x80000000)
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
|
|
; GCN-NEXT: S_BRANCH %bb.1
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: bb.1:
|
|
; GCN-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: $exec = S_OR_B64 $exec, 1, implicit-def $scc
|
|
; GCN-NEXT: S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
|
; GCN-NEXT: S_BRANCH %bb.2
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: bb.2:
|
|
; GCN-NEXT: S_ENDPGM 0
|
|
bb.0:
|
|
S_BRANCH %bb.1
|
|
|
|
bb.1:
|
|
%0:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
|
|
$exec = S_OR_B64 $exec, 1, implicit-def $scc
|
|
S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.2:
|
|
S_ENDPGM 0
|
|
...
|
|
---
|
|
name: no_hoist_cmp
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; GCN-LABEL: name: no_hoist_cmp
|
|
; GCN: bb.0:
|
|
; GCN-NEXT: successors: %bb.1(0x80000000)
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: S_BRANCH %bb.1
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: bb.1:
|
|
; GCN-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 1, 2, implicit $exec
|
|
; GCN-NEXT: $exec = S_OR_B64 $exec, [[V_CMP_EQ_U32_e64_]], implicit-def $scc
|
|
; GCN-NEXT: S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
|
; GCN-NEXT: S_BRANCH %bb.2
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: bb.2:
|
|
; GCN-NEXT: S_ENDPGM 0
|
|
bb.0:
|
|
S_BRANCH %bb.1
|
|
|
|
bb.1:
|
|
%0:sreg_64 = V_CMP_EQ_U32_e64 1, 2, implicit $exec
|
|
$exec = S_OR_B64 $exec, %0:sreg_64, implicit-def $scc
|
|
S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.2:
|
|
S_ENDPGM 0
|
|
...
|
|
---
|
|
name: allowable_hoist_cmp
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; GCN-LABEL: name: allowable_hoist_cmp
|
|
; GCN: bb.0:
|
|
; GCN-NEXT: successors: %bb.1(0x80000000)
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 1, 2, implicit $exec
|
|
; GCN-NEXT: S_BRANCH %bb.1
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: bb.1:
|
|
; GCN-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: $exec = S_AND_B64 $exec, [[V_CMP_EQ_U32_e64_]], implicit-def $scc
|
|
; GCN-NEXT: S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
|
; GCN-NEXT: S_BRANCH %bb.2
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: bb.2:
|
|
; GCN-NEXT: S_ENDPGM 0
|
|
bb.0:
|
|
S_BRANCH %bb.1
|
|
|
|
bb.1:
|
|
%0:sreg_64 = V_CMP_EQ_U32_e64 1, 2, implicit $exec
|
|
$exec = S_AND_B64 $exec, %0:sreg_64, implicit-def $scc
|
|
S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.2:
|
|
S_ENDPGM 0
|
|
...
|
|
---
|
|
name: no_hoist_readfirstlane
|
|
tracksRegLiveness: true
|
|
body: |
|
|
; GCN-LABEL: name: no_hoist_readfirstlane
|
|
; GCN: bb.0:
|
|
; GCN-NEXT: successors: %bb.1(0x80000000)
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
|
|
; GCN-NEXT: S_BRANCH %bb.1
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: bb.1:
|
|
; GCN-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sgpr_32 = V_READFIRSTLANE_B32 [[DEF]], implicit $exec
|
|
; GCN-NEXT: $exec = S_OR_B64 $exec, 1, implicit-def $scc
|
|
; GCN-NEXT: S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
|
; GCN-NEXT: S_BRANCH %bb.2
|
|
; GCN-NEXT: {{ $}}
|
|
; GCN-NEXT: bb.2:
|
|
; GCN-NEXT: S_ENDPGM 0
|
|
bb.0:
|
|
%0:vgpr_32 = IMPLICIT_DEF
|
|
S_BRANCH %bb.1
|
|
|
|
bb.1:
|
|
%1:sgpr_32 = V_READFIRSTLANE_B32 %0:vgpr_32, implicit $exec
|
|
$exec = S_OR_B64 $exec, 1, implicit-def $scc
|
|
S_CBRANCH_EXECNZ %bb.1, implicit $exec
|
|
S_BRANCH %bb.2
|
|
|
|
bb.2:
|
|
S_ENDPGM 0
|
|
...
|