llvm-project/llvm/test/CodeGen/AMDGPU/true16-saveexec.mir
Brox Chen db973cea7c
[AMDGPU][True16][CodeGen] True16 Add OpSel when optimizing exec mask (#128928)
True16 Add OpSel when optimizing exec mask

True16 VOPCX have the opsel argument. Add it when we create these
instructions in SIOptimizeExecMasking.

---------

Co-authored-by: Matt Arsenault <arsenm2@gmail.com>
2025-02-28 09:41:05 -05:00

65 lines
2.6 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
# RUN: llc -march=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -run-pass=si-optimize-exec-masking -o - %s | FileCheck %s
---
name: int
tracksRegLiveness: true
body: |
; CHECK-LABEL: name: int
; CHECK: bb.0:
; CHECK-NEXT: successors: %bb.1(0x80000000)
; CHECK-NEXT: liveins: $vgpr20
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $sgpr0_sgpr1 = S_MOV_B64 $exec
; CHECK-NEXT: V_CMPX_LT_I16_t16_nosdst_e64 0, 15, 0, $vgpr20_lo16, 0, implicit-def $exec, implicit $exec
; CHECK-NEXT: renamable $sgpr0_sgpr1 = S_XOR_B64 $exec, killed renamable $sgpr0_sgpr1, implicit-def dead $scc
; CHECK-NEXT: S_CBRANCH_EXECZ %bb.1, implicit $exec
; CHECK-NEXT: S_BRANCH %bb.1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1:
; CHECK-NEXT: S_ENDPGM 0
bb.1:
liveins: $vgpr20
$vcc = V_CMP_LT_I16_t16_e64 0, 15, 0, $vgpr20_lo16, 0, implicit $exec
renamable $sgpr0_sgpr1 = COPY $exec, implicit-def $exec
renamable $sgpr2_sgpr3 = S_AND_B64 renamable $sgpr0_sgpr1, killed $vcc, implicit-def dead $scc
renamable $sgpr0_sgpr1 = S_XOR_B64 renamable $sgpr2_sgpr3, killed renamable $sgpr0_sgpr1, implicit-def dead $scc
$exec = S_MOV_B64_term killed renamable $sgpr2_sgpr3
S_CBRANCH_EXECZ %bb.2, implicit $exec
S_BRANCH %bb.2
bb.2:
S_ENDPGM 0
...
---
name: float
tracksRegLiveness: true
body: |
; CHECK-LABEL: name: float
; CHECK: bb.0:
; CHECK-NEXT: successors: %bb.1(0x80000000)
; CHECK-NEXT: liveins: $vgpr20
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $sgpr0_sgpr1 = S_MOV_B64 $exec
; CHECK-NEXT: V_CMPX_LT_F16_t16_nosdst_e64 0, 15, 0, $vgpr20_lo16, 1, 0, implicit-def $exec, implicit $mode, implicit $exec
; CHECK-NEXT: renamable $sgpr0_sgpr1 = S_XOR_B64 $exec, killed renamable $sgpr0_sgpr1, implicit-def dead $scc
; CHECK-NEXT: S_CBRANCH_EXECZ %bb.1, implicit $exec
; CHECK-NEXT: S_BRANCH %bb.1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1:
; CHECK-NEXT: S_ENDPGM 0
bb.1:
liveins: $vgpr20
$vcc = V_CMP_LT_F16_t16_e64 0, 15, 0, $vgpr20_lo16, 1, 0, implicit $exec, implicit $mode
renamable $sgpr0_sgpr1 = COPY $exec, implicit-def $exec
renamable $sgpr2_sgpr3 = S_AND_B64 renamable $sgpr0_sgpr1, killed $vcc, implicit-def dead $scc
renamable $sgpr0_sgpr1 = S_XOR_B64 renamable $sgpr2_sgpr3, killed renamable $sgpr0_sgpr1, implicit-def dead $scc
$exec = S_MOV_B64_term killed renamable $sgpr2_sgpr3
S_CBRANCH_EXECZ %bb.2, implicit $exec
S_BRANCH %bb.2
bb.2:
S_ENDPGM 0
...