On GFX11.5 shaders having completed exports need to execute/wait at a lower priority than shaders still executing exports. Add code to maintain normal priority of 2 for shaders that export and drop to priority 0 after exports.
295 lines
8.7 KiB
YAML
295 lines
8.7 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
# RUN: llc -mtriple=amdgcn -mcpu=gfx1150 -run-pass=post-RA-hazard-rec %s -o - | FileCheck -check-prefixes=GFX1150 %s
|
|
# RUN: llc -mtriple=amdgcn -mcpu=gfx11-generic -run-pass=post-RA-hazard-rec %s -o - | FileCheck -check-prefixes=GFX1150 %s
|
|
|
|
--- |
|
|
define amdgpu_ps void @end_of_shader() {
|
|
ret void
|
|
}
|
|
define amdgpu_ps void @end_of_shader_return_to_epilogue() {
|
|
ret void
|
|
}
|
|
define amdgpu_ps void @end_of_block() {
|
|
ret void
|
|
}
|
|
define amdgpu_ps void @start_of_block() {
|
|
ret void
|
|
}
|
|
define amdgpu_ps void @block_of_exports() {
|
|
ret void
|
|
}
|
|
define amdgpu_ps void @sparse_exports() {
|
|
ret void
|
|
}
|
|
define amdgpu_ps void @existing_setprio_1() {
|
|
ret void
|
|
}
|
|
define amdgpu_ps void @existing_setprio_2() {
|
|
ret void
|
|
}
|
|
...
|
|
|
|
---
|
|
name: end_of_shader
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
; GFX1150-LABEL: name: end_of_shader
|
|
; GFX1150: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_ENDPGM 0
|
|
EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
---
|
|
name: end_of_shader_return_to_epilogue
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
; GFX1150-LABEL: name: end_of_shader_return_to_epilogue
|
|
; GFX1150: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_WAITCNT_EXPCNT $sgpr_null, 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: SI_RETURN_TO_EPILOG $vgpr0
|
|
EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
SI_RETURN_TO_EPILOG $vgpr0
|
|
...
|
|
|
|
---
|
|
name: end_of_block
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0' }
|
|
body: |
|
|
; GFX1150-LABEL: name: end_of_block
|
|
; GFX1150: bb.0:
|
|
; GFX1150-NEXT: successors: %bb.1(0x80000000)
|
|
; GFX1150-NEXT: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_WAITCNT_EXPCNT $sgpr_null, 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: bb.1:
|
|
; GFX1150-NEXT: S_ENDPGM 0
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
|
|
bb.1:
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
---
|
|
name: start_of_block
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0' }
|
|
body: |
|
|
; GFX1150-LABEL: name: start_of_block
|
|
; GFX1150: bb.0:
|
|
; GFX1150-NEXT: successors: %bb.1(0x80000000)
|
|
; GFX1150-NEXT: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: bb.1:
|
|
; GFX1150-NEXT: successors: %bb.2(0x80000000)
|
|
; GFX1150-NEXT: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_WAITCNT_EXPCNT $sgpr_null, 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: bb.2:
|
|
; GFX1150-NEXT: S_ENDPGM 0
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
|
|
bb.1:
|
|
liveins: $vgpr0
|
|
EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
|
|
bb.2:
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
---
|
|
name: block_of_exports
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
; GFX1150-LABEL: name: block_of_exports
|
|
; GFX1150: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: EXP 2, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: EXP 1, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_ENDPGM 0
|
|
EXP 2, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
EXP 1, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
---
|
|
name: sparse_exports
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
; GFX1150-LABEL: name: sparse_exports
|
|
; GFX1150: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: EXP 2, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_WAITCNT_EXPCNT $sgpr_null, 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: $vgpr0 = V_AND_B32_e32 1, $vgpr0, implicit $exec
|
|
; GFX1150-NEXT: EXP 1, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_WAITCNT_EXPCNT $sgpr_null, 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: $vgpr0 = V_OR_B32_e32 2, $vgpr0, implicit $exec
|
|
; GFX1150-NEXT: EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_ENDPGM 0
|
|
EXP 2, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
$vgpr0 = V_AND_B32_e32 1, $vgpr0, implicit $exec
|
|
EXP 1, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
$vgpr0 = V_OR_B32_e32 2, $vgpr0, implicit $exec
|
|
EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
---
|
|
name: existing_setprio_1
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0' }
|
|
body: |
|
|
; GFX1150-LABEL: name: existing_setprio_1
|
|
; GFX1150: bb.0:
|
|
; GFX1150-NEXT: successors: %bb.1(0x80000000)
|
|
; GFX1150-NEXT: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: $vgpr0 = V_AND_B32_e32 1, $vgpr0, implicit $exec
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: bb.1:
|
|
; GFX1150-NEXT: successors: %bb.2(0x80000000)
|
|
; GFX1150-NEXT: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 3
|
|
; GFX1150-NEXT: $vgpr0 = V_OR_B32_e32 2, $vgpr0, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: bb.2:
|
|
; GFX1150-NEXT: successors: %bb.3(0x80000000)
|
|
; GFX1150-NEXT: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 3
|
|
; GFX1150-NEXT: $vgpr0 = V_OR_B32_e32 3, $vgpr0, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: bb.3:
|
|
; GFX1150-NEXT: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: EXP 1, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_ENDPGM 0
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
$vgpr0 = V_AND_B32_e32 1, $vgpr0, implicit $exec
|
|
|
|
bb.1:
|
|
liveins: $vgpr0
|
|
S_SETPRIO 3
|
|
$vgpr0 = V_OR_B32_e32 2, $vgpr0, implicit $exec
|
|
S_SETPRIO 0
|
|
|
|
bb.2:
|
|
liveins: $vgpr0
|
|
S_SETPRIO 1
|
|
$vgpr0 = V_OR_B32_e32 3, $vgpr0, implicit $exec
|
|
S_SETPRIO 0
|
|
|
|
bb.3:
|
|
liveins: $vgpr0
|
|
EXP 1, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
---
|
|
name: existing_setprio_2
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$vgpr0' }
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
; GFX1150-LABEL: name: existing_setprio_2
|
|
; GFX1150: liveins: $vgpr0
|
|
; GFX1150-NEXT: {{ $}}
|
|
; GFX1150-NEXT: S_SETPRIO 3
|
|
; GFX1150-NEXT: EXP 1, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
; GFX1150-NEXT: S_SETPRIO 0
|
|
; GFX1150-NEXT: S_WAITCNT_EXPCNT $sgpr_null, 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_NOP 0
|
|
; GFX1150-NEXT: S_SETPRIO 2
|
|
; GFX1150-NEXT: S_SETPRIO 3
|
|
; GFX1150-NEXT: S_ENDPGM 0
|
|
S_SETPRIO 3
|
|
EXP 1, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
EXP_DONE 0, $vgpr0, $vgpr0, $vgpr0, $vgpr0, -1, -1, 15, implicit $exec
|
|
S_SETPRIO 3
|
|
S_ENDPGM 0
|
|
...
|