llvm.org GIT mirror llvm / release_90 test / CodeGen / AMDGPU / fold-readlane.mir
release_90

Tree @release_90 (Download .tar.gz)

fold-readlane.mir @release_90raw · history · blame

# RUN: llc -march=amdgcn -run-pass si-fold-operands -verify-machineinstrs %s -o - | FileCheck -check-prefix=GCN %s

# GCN-LABEL: name: fold-imm-readfirstlane{{$}}
# GCN: %1:sreg_32_xm0 = S_MOV_B32 123
---
name: fold-imm-readfirstlane
tracksRegLiveness: true
body:             |
  bb.0:
    %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
    %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
...

# GCN-LABEL: name: fold-imm-readfirstlane-readfirstlane{{$}}
# GCN: %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
# GCN: %1:sreg_32_xm0 = S_MOV_B32 123
# GCN: %2:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
# GCN: %3:sreg_32_xm0 = S_MOV_B32 123

---
name: fold-imm-readfirstlane-readfirstlane
tracksRegLiveness: true
body:             |
  bb.0:
    %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
    %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
    %2:vgpr_32 = COPY %1
    %3:sreg_32_xm0 = V_READFIRSTLANE_B32 %2, implicit $exec

...


# GCN-LABEL: name: fold-copy-readfirstlane{{$}}
# GCN: %0:sreg_32_xm0 = COPY $sgpr10
# GCN: %1:vgpr_32 = COPY %0
# GCN: %2:sreg_32_xm0 = COPY %1
---
name: fold-copy-readfirstlane
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10
    %0:sreg_32_xm0 = COPY $sgpr10
    %1:vgpr_32 = COPY %0
    %2:sreg_32_xm0 = V_READFIRSTLANE_B32 %1, implicit $exec

...

# GCN-LABEL: name: no-fold-copy-readfirstlane-physreg0{{$}}
# GCN: %0:vgpr_32 = COPY $sgpr10
# GCN-NEXT: %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
---
name: no-fold-copy-readfirstlane-physreg0
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10
    %0:vgpr_32 = COPY $sgpr10
    %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec

...

# GCN-LABEL: name: no-fold-copy-readfirstlane-physreg1{{$}}
# GCN: $vgpr0 = COPY $sgpr10
# GCN-NEXT: %0:sreg_32_xm0 = V_READFIRSTLANE_B32 $vgpr0, implicit $exec
---
name: no-fold-copy-readfirstlane-physreg1
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10
    $vgpr0 = COPY $sgpr10
    %0:sreg_32_xm0 = V_READFIRSTLANE_B32 $vgpr0, implicit $exec

...

# GCN-LABEL: name: no-fold-imm-readfirstlane-physreg{{$}}
# GCN: $vgpr0 = V_MOV_B32_e32 123, implicit $exec
# GCN-NEXT: V_READFIRSTLANE_B32 $vgpr0, implicit $exec

---
name: no-fold-imm-readfirstlane-physreg
tracksRegLiveness: true
body:             |
  bb.0:
    $vgpr0 = V_MOV_B32_e32 123, implicit $exec
    %0:sreg_32_xm0 = V_READFIRSTLANE_B32 $vgpr0, implicit $exec
...

# TODO: This could be folded, if the search for exec modifications was
# smarter.

# GCN-LABEL: name: fold-imm-readfirstlane-cross-block{{$}}
# GCN: V_MOV_B32
# GCN: V_READFIRSTLANE_B32
---
name: fold-imm-readfirstlane-cross-block
tracksRegLiveness: true
body:             |
  bb.0:
    %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec

  bb.1:
    %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
...

# TODO: This could be folded, if the search for exec modifications was
# smarter.

# GCN-LABEL: name: fold-copy-readfirstlane-cross-block{{$}}
# GCN: V_MOV_B32
# GCN: V_READFIRSTLANE_B32
---
name: fold-copy-readfirstlane-cross-block
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr12
    %0:sreg_32_xm0 = COPY $sgpr12
    %1:vgpr_32 = V_MOV_B32_e32 %0, implicit $exec

  bb.1:
    %2:sreg_32_xm0 = V_READFIRSTLANE_B32 %1, implicit $exec
...

# GCN-LABEL: name: fold-copy-readfirstlane-cross-block-exec-def{{$}}
# GCN: V_MOV_B32
# GCN: $exec = S_MOV_B64_term
# GCN: V_READFIRSTLANE_B32
---
name: fold-copy-readfirstlane-cross-block-exec-def
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10_sgpr11, $sgpr12
    %0:sreg_32_xm0 = COPY $sgpr12
    %1:vgpr_32 = V_MOV_B32_e32 %0, implicit $exec
    $exec = S_MOV_B64_term $sgpr10_sgpr11

  bb.1:
    %2:sreg_32_xm0 = V_READFIRSTLANE_B32 %1, implicit $exec
...

# GCN-LABEL: name: fold-copy-readfirstlane-same-block-exec-def{{$}}
# GCN: COPY
# GCN-NEXT: %1:vgpr_32 = COPY %0
# GCN-NEXT: $exec = S_MOV_B64
# GCN-NEXT: V_READFIRSTLANE_B32
---
name: fold-copy-readfirstlane-same-block-exec-def
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10_sgpr11, $sgpr12
    %0:sreg_32_xm0 = COPY $sgpr12
    %1:vgpr_32 = COPY %0, implicit $exec
    $exec = S_MOV_B64 $sgpr10_sgpr11
    %2:sreg_32_xm0 = V_READFIRSTLANE_B32 %1, implicit $exec

...

# GCN-LABEL: name: fold-imm-readfirstlane-cross-block-exec-def{{$}}
# GCN: V_MOV_B32
# GCN: $exec = S_MOV_B64
# GCN: V_READFIRSTLANE_B32

---
name: fold-imm-readfirstlane-cross-block-exec-def
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10_sgpr11, $sgpr12_sgpr13
    %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
    $exec = S_MOV_B64_term $sgpr10_sgpr11

  bb.1:
    %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
...

# GCN-LABEL: name: fold-imm-readfirstlane-same-block-exec-def{{$}}
# GCN: V_MOV_B32
# GCN-NEXT: $exec = S_MOV_B64
# GCN-NEXT: V_READFIRSTLANE_B32
---
name: fold-imm-readfirstlane-same-block-exec-def
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10_sgpr11
    %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
    $exec = S_MOV_B64 $sgpr10_sgpr11
    %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec

...

# GCN-LABEL: name: fold-sgpr-copy-readfirstlane-same-block-exec-def{{$}}
# GCN: COPY
# GCN-NEXT: $exec = S_MOV_B64
# GCN-NEXT: V_READFIRSTLANE_B32
---
name: fold-sgpr-copy-readfirstlane-same-block-exec-def
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10_sgpr11, $sgpr12
    %0:vgpr_32 = COPY $sgpr12
    $exec = S_MOV_B64 $sgpr10_sgpr11
    %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
...

# GCN-LABEL: name: fold-imm-readfirstlane-user{{$}}
# GCN: %3:sreg_32_xm0 = S_MOV_B32 123
---
name: fold-imm-readfirstlane-user
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $sgpr0_sgpr1
    %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
    %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
    %2:sreg_32_xm0 = COPY %1
    %3:sreg_32_xm0 = COPY %2
    S_ENDPGM 0, implicit %3
...

# GCN-LABEL: name: fold-imm-readlane{{$}}
# GCN: %1:sreg_32_xm0 = S_MOV_B32 123
---
name: fold-imm-readlane
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $sgpr0_sgpr1
    %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
    %1:sreg_32_xm0 = V_READLANE_B32 %0, 0, implicit $exec
...

# GCN-LABEL: name: fold-imm-readlane-src1{{$}}
# GCN: %0:vgpr_32 = COPY $vgpr0
# GCN: V_READLANE_B32 %0, 12, implicit $exec
---
name: fold-imm-readlane-src1
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0
    %0:vgpr_32 = COPY $vgpr0
    %1:sreg_32_xm0 = S_MOV_B32 12
    %2:sreg_32_xm0 = V_READLANE_B32 %0, %1, implicit $exec
...

# Constant for subreg0
# GCN-LABEL: name: fold-imm-readfirstlane-regsequence0{{$}}

# GCN: %0:vgpr_32 = COPY $vgpr0
# GCN-NEXT: %1:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
# GCN-NEXT: %2:vreg_64 = REG_SEQUENCE %0, %subreg.sub0, killed %1, %subreg.sub1
# GCN-NEXT: %3:sgpr_32 = V_READFIRSTLANE_B32 %2.sub0, implicit $exec
# GCN-NEXT: %4:sgpr_32 = S_MOV_B32 0
---
name: fold-imm-readfirstlane-regsequence0
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0
    %0:vgpr_32 = COPY $vgpr0
    %1:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    %2:vreg_64 = REG_SEQUENCE %0:vgpr_32, %subreg.sub0, killed %1:vgpr_32, %subreg.sub1
    %3:sgpr_32 = V_READFIRSTLANE_B32 %2.sub0:vreg_64, implicit $exec
    %4:sgpr_32 = V_READFIRSTLANE_B32 %2.sub1:vreg_64, implicit $exec
...

# Constant for subreg1
# GCN-LABEL: name: fold-imm-readfirstlane-regsequence1{{$}}
# GCN: %0:vgpr_32 = COPY $vgpr0
# GCN-NEXT: %1:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
# GCN-NEXT: %2:vreg_64 = REG_SEQUENCE %1, %subreg.sub0, killed %0, %subreg.sub1
# GCN-NEXT: %3:sgpr_32 = S_MOV_B32 0
# GCN-NEXT: %4:sgpr_32 = V_READFIRSTLANE_B32 %2.sub1, implicit $exec

---
name: fold-imm-readfirstlane-regsequence1
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0
    %0:vgpr_32 = COPY $vgpr0
    %1:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    %2:vreg_64 = REG_SEQUENCE %1:vgpr_32, %subreg.sub0, killed %0:vgpr_32, %subreg.sub1
    %3:sgpr_32 = V_READFIRSTLANE_B32 %2.sub0:vreg_64, implicit $exec
    %4:sgpr_32 = V_READFIRSTLANE_B32 %2.sub1:vreg_64, implicit $exec
...

# Different constant regs for each subreg
# GCN-LABEL: name: fold-imm-readfirstlane-regsequence2{{$}}
# GCN: %0:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
# GCN-NEXT: %1:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
# GCN-NEXT: %2:vreg_64 = REG_SEQUENCE %0, %subreg.sub0, killed %1, %subreg.sub1
# GCN-NEXT: %3:sgpr_32 = S_MOV_B32 0
# GCN-NEXT: %4:sgpr_32 = S_MOV_B32 1
---
name: fold-imm-readfirstlane-regsequence2
tracksRegLiveness: true
body:             |
  bb.0:
    %0:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    %1:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
    %2:vreg_64 = REG_SEQUENCE %0:vgpr_32, %subreg.sub0, killed %1:vgpr_32, %subreg.sub1
    %3:sgpr_32 = V_READFIRSTLANE_B32 %2.sub0:vreg_64, implicit $exec
    %4:sgpr_32 = V_READFIRSTLANE_B32 %2.sub1:vreg_64, implicit $exec
...

# Same constant reg for each subreg, so there are multiple constant uses
# GCN-LABEL: name: fold-imm-readfirstlane-regsequence3{{$}}
# GCN: %0:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
# GCN-NEXT: %1:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
# GCN-NEXT: %2:vreg_64 = REG_SEQUENCE %0, %subreg.sub0, killed %1, %subreg.sub1
# GCN-NEXT: %3:sgpr_32 = S_MOV_B32 0
# GCN-NEXT: %4:sgpr_32 = S_MOV_B32 0
---
name: fold-imm-readfirstlane-regsequence3
tracksRegLiveness: true
body:             |
  bb.0:
    %0:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    %1:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    %2:vreg_64 = REG_SEQUENCE %0:vgpr_32, %subreg.sub0, killed %1:vgpr_32, %subreg.sub1
    %3:sgpr_32 = V_READFIRSTLANE_B32 %2.sub0:vreg_64, implicit $exec
    %4:sgpr_32 = V_READFIRSTLANE_B32 %2.sub1:vreg_64, implicit $exec
...

# FIXME: This should fold
# GCN-LABEL: name: fold-copy-readfirstlane-regsequence0{{$}}
# GCN: %0:vgpr_32 = COPY $sgpr10
# GCN-NEXT: %1:vgpr_32 = COPY $sgpr11
# GCN-NEXT: %2:vreg_64 = REG_SEQUENCE %0, %subreg.sub0, killed %1, %subreg.sub1
# GCN-NEXT: %3:sgpr_32 = V_READFIRSTLANE_B32 %2.sub0, implicit $exec
# GCN-NEXT: %4:sgpr_32 = V_READFIRSTLANE_B32 %2.sub1, implicit $exec
---
name: fold-copy-readfirstlane-regsequence0
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10, $sgpr11
    %0:vgpr_32 = COPY $sgpr10
    %1:vgpr_32 = COPY $sgpr11
    %2:vreg_64 = REG_SEQUENCE %0:vgpr_32, %subreg.sub0, killed %1:vgpr_32, %subreg.sub1
    %3:sgpr_32 = V_READFIRSTLANE_B32 %2.sub0:vreg_64, implicit $exec
    %4:sgpr_32 = V_READFIRSTLANE_B32 %2.sub1:vreg_64, implicit $exec
...

# GCN-LABEL: name: fold-copy-readfirstlane-regsequence1{{$}}
# GCN: %0:sreg_32_xm0 = COPY $sgpr10
# GCN-NEXT: %1:sreg_32_xm0 = COPY $sgpr11
# GCN-NEXT: %2:vgpr_32 = COPY %0
# GCN-NEXT: %3:vgpr_32 = COPY %1
# GCN-NEXT: %4:vreg_64 = REG_SEQUENCE %2, %subreg.sub0, killed %3, %subreg.sub1
# GCN-NEXT: %5:sgpr_32 = V_READFIRSTLANE_B32 %4.sub0, implicit $exec
# GCN-NEXT: %6:sgpr_32 = V_READFIRSTLANE_B32 %4.sub1, implicit $exec
---
name: fold-copy-readfirstlane-regsequence1
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $sgpr10, $sgpr11
    %0:sreg_32_xm0 = COPY $sgpr10
    %1:sreg_32_xm0 = COPY $sgpr11
    %2:vgpr_32 = COPY %0
    %3:vgpr_32 = COPY %1
    %4:vreg_64 = REG_SEQUENCE %2:vgpr_32, %subreg.sub0, killed %3:vgpr_32, %subreg.sub1
    %5:sgpr_32 = V_READFIRSTLANE_B32 %4.sub0:vreg_64, implicit $exec
    %6:sgpr_32 = V_READFIRSTLANE_B32 %4.sub1:vreg_64, implicit $exec
...