For the co-execution of the TRANS ops, the requirement is: 1 independent op or V_NOP (since TRANS takes 2 cycles) after the trans op before its sources can be overwritten or the output of the trans op can be used.
133 lines
6.0 KiB
YAML
133 lines
6.0 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -mtriple=amdgcn -mcpu=gfx1250 -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN,GFX1250 %s
|
|
# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN,GFX1200 %s
|
|
|
|
---
|
|
name: trans_writes_valu_reads_hazard
|
|
body: |
|
|
bb.0:
|
|
; GFX1250-LABEL: name: trans_writes_valu_reads_hazard
|
|
; GFX1250: $vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GFX1250-NEXT: V_NOP_e32 implicit $exec
|
|
; GFX1250-NEXT: $vgpr3 = V_ADD_F32_e32 $vgpr1, $vgpr2, implicit $mode, implicit $exec
|
|
;
|
|
; GFX1200-LABEL: name: trans_writes_valu_reads_hazard
|
|
; GFX1200: $vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GFX1200-NEXT: $vgpr3 = V_ADD_F32_e32 $vgpr1, $vgpr2, implicit $mode, implicit $exec
|
|
$vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$vgpr3 = V_ADD_F32_e32 $vgpr1, $vgpr2, implicit $mode, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans_writes_valu_valu_reads_hazard_covered
|
|
body: |
|
|
bb.0:
|
|
; GCN-LABEL: name: trans_writes_valu_valu_reads_hazard_covered
|
|
; GCN: $vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GCN-NEXT: $vgpr2 = V_ADD_F32_e32 $vgpr2, $vgpr3, implicit $mode, implicit $exec
|
|
; GCN-NEXT: $vgpr4 = V_ADD_F32_e32 $vgpr1, $vgpr2, implicit $mode, implicit $exec
|
|
$vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$vgpr2 = V_ADD_F32_e32 $vgpr2, $vgpr3, implicit $mode, implicit $exec
|
|
$vgpr4 = V_ADD_F32_e32 $vgpr1, $vgpr2, implicit $mode, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans_writes_salu_valu_reads_hazard
|
|
body: |
|
|
bb.0:
|
|
; GFX1250-LABEL: name: trans_writes_salu_valu_reads_hazard
|
|
; GFX1250: $vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GFX1250-NEXT: $sgpr2 = S_ADD_U32 $sgpr0, $sgpr1, implicit-def $scc
|
|
; GFX1250-NEXT: V_NOP_e32 implicit $exec
|
|
; GFX1250-NEXT: $vgpr4 = V_ADD_F32_e32 $vgpr1, $vgpr2, implicit $mode, implicit $exec
|
|
;
|
|
; GFX1200-LABEL: name: trans_writes_salu_valu_reads_hazard
|
|
; GFX1200: $vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GFX1200-NEXT: $sgpr2 = S_ADD_U32 $sgpr0, $sgpr1, implicit-def $scc
|
|
; GFX1200-NEXT: $vgpr4 = V_ADD_F32_e32 $vgpr1, $vgpr2, implicit $mode, implicit $exec
|
|
$vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$sgpr2 = S_ADD_U32 $sgpr0, $sgpr1, implicit-def $scc
|
|
$vgpr4 = V_ADD_F32_e32 $vgpr1, $vgpr2, implicit $mode, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans_no_hazard
|
|
body: |
|
|
bb.0:
|
|
; GCN-LABEL: name: trans_no_hazard
|
|
; GCN: $vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GCN-NEXT: $vgpr3 = V_ADD_F32_e32 $vgpr0, $vgpr2, implicit $mode, implicit $exec
|
|
$vgpr1 = V_SQRT_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$vgpr3 = V_ADD_F32_e32 $vgpr0, $vgpr2, implicit $mode, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans_reads_valu_writes_hazard
|
|
body: |
|
|
bb.0:
|
|
; GFX1250-LABEL: name: trans_reads_valu_writes_hazard
|
|
; GFX1250: $vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GFX1250-NEXT: V_NOP_e32 implicit $exec
|
|
; GFX1250-NEXT: $vgpr0 = V_ADD_F32_e32 $vgpr2, $vgpr3, implicit $mode, implicit $exec
|
|
;
|
|
; GFX1200-LABEL: name: trans_reads_valu_writes_hazard
|
|
; GFX1200: $vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GFX1200-NEXT: $vgpr0 = V_ADD_F32_e32 $vgpr2, $vgpr3, implicit $mode, implicit $exec
|
|
$vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$vgpr0 = V_ADD_F32_e32 $vgpr2, $vgpr3, implicit $mode, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans_reads_valu_valu_writes_hazard_covered
|
|
body: |
|
|
bb.0:
|
|
; GCN-LABEL: name: trans_reads_valu_valu_writes_hazard_covered
|
|
; GCN: $vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GCN-NEXT: $vgpr2 = V_ADD_F32_e32 $vgpr2, $vgpr3, implicit $mode, implicit $exec
|
|
; GCN-NEXT: $vgpr0 = V_ADD_F32_e32 $vgpr4, $vgpr2, implicit $mode, implicit $exec
|
|
$vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$vgpr2 = V_ADD_F32_e32 $vgpr2, $vgpr3, implicit $mode, implicit $exec
|
|
$vgpr0 = V_ADD_F32_e32 $vgpr4, $vgpr2, implicit $mode, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans_reads__salu_valu_writes_hazard
|
|
body: |
|
|
bb.0:
|
|
; GFX1250-LABEL: name: trans_reads__salu_valu_writes_hazard
|
|
; GFX1250: $vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GFX1250-NEXT: $sgpr2 = S_ADD_U32 $sgpr0, $sgpr1, implicit-def $scc
|
|
; GFX1250-NEXT: V_NOP_e32 implicit $exec
|
|
; GFX1250-NEXT: $vgpr0 = V_ADD_F32_e32 $vgpr4, $vgpr2, implicit $mode, implicit $exec
|
|
;
|
|
; GFX1200-LABEL: name: trans_reads__salu_valu_writes_hazard
|
|
; GFX1200: $vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GFX1200-NEXT: $sgpr2 = S_ADD_U32 $sgpr0, $sgpr1, implicit-def $scc
|
|
; GFX1200-NEXT: $vgpr0 = V_ADD_F32_e32 $vgpr4, $vgpr2, implicit $mode, implicit $exec
|
|
$vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$sgpr2 = S_ADD_U32 $sgpr0, $sgpr1, implicit-def $scc
|
|
$vgpr0 = V_ADD_F32_e32 $vgpr4, $vgpr2, implicit $mode, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans_writes_trans_reads_no_hazard
|
|
body: |
|
|
bb.0:
|
|
; GCN-LABEL: name: trans_writes_trans_reads_no_hazard
|
|
; GCN: $vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GCN-NEXT: $vgpr2 = V_SQRT_F32_e32 $vgpr1, implicit $mode, implicit $exec
|
|
$vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$vgpr2 = V_SQRT_F32_e32 $vgpr1, implicit $mode, implicit $exec
|
|
...
|
|
|
|
---
|
|
name: trans_reads_trans_writes_no_hazard
|
|
body: |
|
|
bb.0:
|
|
; GCN-LABEL: name: trans_reads_trans_writes_no_hazard
|
|
; GCN: $vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
; GCN-NEXT: $vgpr0 = V_SQRT_F32_e32 $vgpr2, implicit $mode, implicit $exec
|
|
$vgpr1 = V_COS_F32_e32 $vgpr0, implicit $mode, implicit $exec
|
|
$vgpr0 = V_SQRT_F32_e32 $vgpr2, implicit $mode, implicit $exec
|
|
...
|