# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN,GFX11 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN,GFX12 %s
--- |
@mem = internal unnamed_addr addrspace(4) constant [4 x <4 x i32>] [<4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>]
define amdgpu_gs void @mask_hazard_getpc1() { ret void }
define amdgpu_gs void @mask_hazard_getpc2() { ret void }
define amdgpu_gs void @mask_hazard_vcc1() { ret void }
define amdgpu_gs void @mask_hazard_vcc2() { ret void }
define amdgpu_gs void @mask_hazard_cndmask_dpp1() { ret void }
define amdgpu_gs void @mask_hazard_cndmask_dpp2() { ret void }
define amdgpu_gs void @mask_hazard_cndmask_dpp3() { ret void }
define amdgpu_gs void @mask_hazard_cndmask_dpp4() { ret void }
define amdgpu_gs void @mask_hazard_addc1() { ret void }
define amdgpu_gs void @mask_hazard_addc2() { ret void }
define amdgpu_gs void @mask_hazard_addc3() { ret void }
define amdgpu_gs void @mask_hazard_addc4() { ret void }
define amdgpu_gs void @mask_hazard_subb1() { ret void }
define amdgpu_gs void @mask_hazard_subb2() { ret void }
define amdgpu_gs void @mask_hazard_subb3() { ret void }
define amdgpu_gs void @mask_hazard_subb4() { ret void }
define amdgpu_gs void @mask_hazard_subbrev1() { ret void }
define amdgpu_gs void @mask_hazard_subbrev2() { ret void }
define amdgpu_gs void @mask_hazard_subbrev3() { ret void }
define amdgpu_gs void @mask_hazard_subbrev4() { ret void }
define amdgpu_gs void @mask_hazard_div_fmas_f32() { ret void }
define amdgpu_gs void @mask_hazard_div_fmas_f64() { ret void }
define amdgpu_gs void @mask_hazard_subreg1() { ret void }
define amdgpu_gs void @mask_hazard_subreg2() { ret void }
define amdgpu_gs void @mask_hazard_subreg3() { ret void }
define amdgpu_gs void @mask_hazard_subreg4() { ret void }
define amdgpu_gs void @mask_hazard_subreg5() { ret void }
define amdgpu_gs void @mask_hazard_waitcnt() { ret void }
define amdgpu_gs void @mask_hazard_gap1() { ret void }
define amdgpu_gs void @mask_hazard_gap2() { ret void }
define amdgpu_gs void @mask_hazard_gap3() { ret void }
define amdgpu_gs void @mask_hazard_no_hazard1() { ret void }
define amdgpu_gs void @mask_hazard_no_hazard2() { ret void }
define amdgpu_gs void @mask_hazard_no_hazard3() { ret void }
...
---
name: mask_hazard_getpc1
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_getpc1
; GCN: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
; GCN-NEXT: $sgpr0_sgpr1 = S_GETPC_B64
; GCN-NEXT: S_WAITCNT_DEPCTR 65534
; GCN-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
$sgpr0_sgpr1 = S_GETPC_B64
$sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
S_ENDPGM 0
...
---
name: mask_hazard_getpc2
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_getpc2
; GCN: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
; GCN-NEXT: BUNDLE implicit-def $sgpr0_sgpr1 {
; GCN-NEXT: $sgpr0_sgpr1 = S_GETPC_B64
; GCN-NEXT: S_WAITCNT_DEPCTR 65534
; GCN-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, target-flags(amdgpu-rel32-lo) @mem + 8, implicit-def $scc
; GCN-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, target-flags(amdgpu-rel32-lo) @mem + 16, implicit-def $scc, implicit $scc
; GCN-NEXT: }
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
BUNDLE implicit-def $sgpr0_sgpr1 {
$sgpr0_sgpr1 = S_GETPC_B64
$sgpr0 = S_ADD_U32 $sgpr0, target-flags(amdgpu-rel32-lo) @mem + 4, implicit-def $scc
$sgpr1 = S_ADDC_U32 $sgpr1, target-flags(amdgpu-rel32-lo) @mem + 12, implicit-def $scc, implicit $scc
}
S_ENDPGM 0
...
---
name: mask_hazard_vcc1
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_vcc1
; GFX11: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_vcc1
; GFX12: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_vcc2
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_vcc2
; GFX11: $vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_vcc2
; GFX12: $vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_cndmask_dpp1
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_cndmask_dpp1
; GFX11: $vgpr0 = V_CNDMASK_B32_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, 1, 15, 15, 1, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_cndmask_dpp1
; GFX12: $vgpr0 = V_CNDMASK_B32_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, 1, 15, 15, 1, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0 = V_CNDMASK_B32_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, 1, 15, 15, 1, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_cndmask_dpp2
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_cndmask_dpp2
; GFX11: $vgpr0 = V_CNDMASK_B32_e64_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, 1, 15, 15, 1, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_cndmask_dpp2
; GFX12: $vgpr0 = V_CNDMASK_B32_e64_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, 1, 15, 15, 1, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0 = V_CNDMASK_B32_e64_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, 1, 15, 15, 1, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_cndmask_dpp4
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_cndmask_dpp4
; GFX11: $vgpr0 = V_CNDMASK_B16_e64_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, 1, 15, 15, 1, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_cndmask_dpp4
; GFX12: $vgpr0 = V_CNDMASK_B16_e64_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, 1, 15, 15, 1, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0 = V_CNDMASK_B16_e64_dpp $vgpr0, 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, 1, 15, 15, 1, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_addc1
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_addc1
; GFX11: $vgpr1, $vcc = V_ADDC_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_addc1
; GFX12: $vgpr1, $vcc = V_ADDC_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr1, $vcc = V_ADDC_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_addc2
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_addc2
; GFX11: $vgpr1 = V_ADDC_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_addc2
; GFX12: $vgpr1 = V_ADDC_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr1 = V_ADDC_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_addc3
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_addc3
; GFX11: $vgpr0 = V_ADDC_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_addc3
; GFX12: $vgpr0 = V_ADDC_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0 = V_ADDC_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_addc4
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_addc4
; GFX11: $vgpr0, $sgpr2_sgpr3 = V_ADDC_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_addc4
; GFX12: $vgpr0, $sgpr2_sgpr3 = V_ADDC_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0, $sgpr2_sgpr3 = V_ADDC_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_subb1
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subb1
; GFX11: $vgpr1, $vcc = V_SUBB_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subb1
; GFX12: $vgpr1, $vcc = V_SUBB_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr1, $vcc = V_SUBB_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_subb2
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subb2
; GFX11: $vgpr1 = V_SUBB_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subb2
; GFX12: $vgpr1 = V_SUBB_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr1 = V_SUBB_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_subb3
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subb3
; GFX11: $vgpr0 = V_SUBB_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subb3
; GFX12: $vgpr0 = V_SUBB_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0 = V_SUBB_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_subb4
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subb4
; GFX11: $vgpr0, $sgpr2_sgpr3 = V_SUBB_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subb4
; GFX12: $vgpr0, $sgpr2_sgpr3 = V_SUBB_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0, $sgpr2_sgpr3 = V_SUBB_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_subbrev1
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subbrev1
; GFX11: $vgpr1, $vcc = V_SUBBREV_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subbrev1
; GFX12: $vgpr1, $vcc = V_SUBBREV_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr1, $vcc = V_SUBBREV_U32_e64 0, $vgpr1, $sgpr2_sgpr3, 0, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_subbrev2
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subbrev2
; GFX11: $vgpr1 = V_SUBBREV_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subbrev2
; GFX12: $vgpr1 = V_SUBBREV_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr1 = V_SUBBREV_U32_e32 0, $vgpr1, implicit-def $vcc, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_subbrev3
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subbrev3
; GFX11: $vgpr0 = V_SUBBREV_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subbrev3
; GFX12: $vgpr0 = V_SUBBREV_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0 = V_SUBBREV_U32_dpp $vgpr0, $vgpr1, $vgpr2, 1, 15, 15, 1, implicit-def $vcc, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_subbrev4
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subbrev4
; GFX11: $vgpr0, $sgpr2_sgpr3 = V_SUBBREV_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
; GFX11-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subbrev4
; GFX12: $vgpr0, $sgpr2_sgpr3 = V_SUBBREV_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
; GFX12-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0, $sgpr2_sgpr3 = V_SUBBREV_U32_e64_dpp $vgpr0, $vgpr1, $vgpr2, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
$sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_div_fmas_f32
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_div_fmas_f32
; GFX11: $vgpr0 = V_DIV_FMAS_F32_e64 0, $vgpr1, 0, $vgpr2, 0, $vgpr3, 0, 0, implicit $mode, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_div_fmas_f32
; GFX12: $vgpr0 = V_DIV_FMAS_F32_e64 0, $vgpr1, 0, $vgpr2, 0, $vgpr3, 0, 0, implicit $mode, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0 = V_DIV_FMAS_F32_e64 0, $vgpr1, 0, $vgpr2, 0, $vgpr3, 0, 0, implicit $mode, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
---
name: mask_hazard_div_fmas_f64
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_div_fmas_f64
; GFX11: $vgpr0_vgpr1 = V_DIV_FMAS_F64_e64 0, $vgpr0_vgpr1, 0, $vgpr2_vgpr3, 0, $vgpr4_vgpr5, 0, 0, implicit $mode, implicit $vcc, implicit $exec
; GFX11-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_div_fmas_f64
; GFX12: $vgpr0_vgpr1 = V_DIV_FMAS_F64_e64 0, $vgpr0_vgpr1, 0, $vgpr2_vgpr3, 0, $vgpr4_vgpr5, 0, 0, implicit $mode, implicit $vcc, implicit $exec
; GFX12-NEXT: $vcc = S_CSELECT_B64 -1, 0, implicit $scc
; GFX12-NEXT: S_ENDPGM 0
$vgpr0_vgpr1 = V_DIV_FMAS_F64_e64 0, $vgpr0_vgpr1, 0, $vgpr2_vgpr3, 0, $vgpr4_vgpr5, 0, 0, implicit $mode, implicit $vcc, implicit $exec
$vcc = S_CSELECT_B64 -1, 0, implicit $scc
S_ENDPGM 0
...
# Check low word overlap
---
name: mask_hazard_subreg1
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subreg1
; GFX11: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GFX11-NEXT: $sgpr2 = S_MOV_B32 0
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subreg1
; GFX12: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GFX12-NEXT: $sgpr2 = S_MOV_B32 0
; GFX12-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
$sgpr2 = S_MOV_B32 0
S_ENDPGM 0
...
# Check high word overlap
---
name: mask_hazard_subreg2
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subreg2
; GFX11: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GFX11-NEXT: $sgpr3 = S_MOV_B32 0
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subreg2
; GFX12: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GFX12-NEXT: $sgpr3 = S_MOV_B32 0
; GFX12-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
$sgpr3 = S_MOV_B32 0
S_ENDPGM 0
...
# Check multiple subreg overlap
---
name: mask_hazard_subreg3
body: |
bb.0:
; GFX11-LABEL: name: mask_hazard_subreg3
; GFX11: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GFX11-NEXT: $sgpr2 = S_MOV_B32 0
; GFX11-NEXT: S_WAITCNT_DEPCTR 65534
; GFX11-NEXT: $sgpr3 = S_MOV_B32 0
; GFX11-NEXT: S_ENDPGM 0
;
; GFX12-LABEL: name: mask_hazard_subreg3
; GFX12: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GFX12-NEXT: $sgpr2 = S_MOV_B32 0
; GFX12-NEXT: $sgpr3 = S_MOV_B32 0
; GFX12-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
$sgpr2 = S_MOV_B32 0
$sgpr3 = S_MOV_B32 0
S_ENDPGM 0
...
# Check vcc_lo overlap
---
name: mask_hazard_subreg4
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_subreg4
; GCN: $vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
; GCN-NEXT: $vcc_lo = S_MOV_B32 0
; GCN-NEXT: S_WAITCNT_DEPCTR 65534
; GCN-NEXT: $sgpr2 = S_MOV_B32 $vcc_lo
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
$vcc_lo = S_MOV_B32 0
$sgpr2 = S_MOV_B32 $vcc_lo
S_ENDPGM 0
...
# Check vcc_hi overlap
---
name: mask_hazard_subreg5
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_subreg5
; GCN: $vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
; GCN-NEXT: $vcc_hi = S_MOV_B32 0
; GCN-NEXT: S_WAITCNT_DEPCTR 65534
; GCN-NEXT: $sgpr2 = S_MOV_B32 $vcc_hi
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
$vcc_hi = S_MOV_B32 0
$sgpr2 = S_MOV_B32 $vcc_hi
S_ENDPGM 0
...
# S_WAITCNT does not mitigate hazard
---
name: mask_hazard_waitcnt
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_waitcnt
; GCN: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
; GCN-NEXT: S_WAITCNT 0
; GCN-NEXT: $sgpr0_sgpr1 = S_GETPC_B64
; GCN-NEXT: S_WAITCNT_DEPCTR 65534
; GCN-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
S_WAITCNT 0
$sgpr0_sgpr1 = S_GETPC_B64
$sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
S_ENDPGM 0
...
# Check implicit $exec
---
name: mask_hazard_gap1
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_gap1
; GCN: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
; GCN-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
; GCN-NEXT: $vgpr3 = V_MOV_B32_e32 0, implicit $exec
; GCN-NEXT: $sgpr0_sgpr1 = S_GETPC_B64
; GCN-NEXT: S_WAITCNT_DEPCTR 65534
; GCN-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
$vgpr2 = V_MOV_B32_e32 0, implicit $exec
$vgpr3 = V_MOV_B32_e32 0, implicit $exec
$sgpr0_sgpr1 = S_GETPC_B64
$sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
S_ENDPGM 0
...
# Check implicit $mode
---
name: mask_hazard_gap2
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_gap2
; GCN: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
; GCN-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec, implicit $mode
; GCN-NEXT: $sgpr0_sgpr1 = S_GETPC_B64
; GCN-NEXT: S_WAITCNT_DEPCTR 65534
; GCN-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
$vgpr2 = V_MOV_B32_e32 0, implicit $exec, implicit $mode
$sgpr0_sgpr1 = S_GETPC_B64
$sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
S_ENDPGM 0
...
# Check explicit $exec
---
name: mask_hazard_gap3
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_gap3
; GCN: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
; GCN-NEXT: $vgpr2 = V_WRITELANE_B32 $exec_lo, 0, $vgpr2
; GCN-NEXT: $sgpr0_sgpr1 = S_GETPC_B64
; GCN-NEXT: S_WAITCNT_DEPCTR 65534
; GCN-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr0_sgpr1, implicit $exec
$vgpr2 = V_WRITELANE_B32 $exec_lo, 0, $vgpr2
$sgpr0_sgpr1 = S_GETPC_B64
$sgpr0 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
S_ENDPGM 0
...
# Different SGPR write
---
name: mask_hazard_no_hazard1
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_no_hazard1
; GCN: $vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
; GCN-NEXT: $sgpr0 = S_MOV_B32 0
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e64 0, $vgpr1, 0, $vgpr2, $sgpr2_sgpr3, implicit $exec
$sgpr0 = S_MOV_B32 0
S_ENDPGM 0
...
# Different SGPR write with mask read overlap
---
name: mask_hazard_no_hazard2
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_no_hazard2
; GCN: $vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
; GCN-NEXT: $sgpr0_sgpr1 = S_MOV_B64 $vcc
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
$sgpr0_sgpr1 = S_MOV_B64 $vcc
S_ENDPGM 0
...
# Overlapping VGPR write
---
name: mask_hazard_no_hazard3
body: |
bb.0:
; GCN-LABEL: name: mask_hazard_no_hazard3
; GCN: $vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
; GCN-NEXT: $vgpr2 = V_MOV_B32_e32 0, implicit $exec
; GCN-NEXT: S_ENDPGM 0
$vgpr1 = V_CNDMASK_B32_e32 $vgpr1, $vgpr2, implicit $vcc, implicit $exec
$vgpr2 = V_MOV_B32_e32 0, implicit $exec
S_ENDPGM 0
...
Codebase Browser
llvm