llvm/test/CodeGen/AMDGPU/splitkit.mir

# RUN: llc -o - %s -mtriple=amdgcn-- -mcpu=fiji -verify-machineinstrs -run-pass=greedy,virtregrewriter | FileCheck %s
--- |
  define amdgpu_kernel void @func0() #0 { ret void }
  define amdgpu_kernel void @func1() #0 { ret void }
  define amdgpu_kernel void @splitHoist() #0 { ret void }

  attributes #0 = { "amdgpu-num-sgpr"="12" }
...
---
# Make sure we only get a single spill+reload even if liverange splitting
# created a sequence of multiple copy instructions.
# CHECK-LABEL: name: func0
# CHECK: SI_SPILL_S128_SAVE
# CHECK-NOT: SI_SPILL_S128_SAVE
# CHECK: S_NOP 0
# CHECK: SI_SPILL_S128_RESTORE
# CHECK-NOT: SI_SPILL_S128_RESTORE
name: func0
body: |
  bb.0:
    S_NOP 0, implicit-def undef %0.sub0 : sreg_128
    S_NOP 0, implicit-def %0.sub3 : sreg_128

    ; Clobber registers
    S_NOP 0, implicit-def dead %sgpr0, implicit-def dead %sgpr1, implicit-def dead %sgpr2, implicit-def dead %sgpr3, implicit-def dead %sgpr4, implicit-def dead %sgpr5, implicit-def dead %sgpr6, implicit-def dead %sgpr7, implicit-def dead %sgpr8, implicit-def dead %sgpr9, implicit-def dead %sgpr10, implicit-def dead %sgpr11

    S_NOP 0, implicit %0.sub0
    S_NOP 0, implicit %0.sub3
    S_NOP 0, implicit %0.sub0
    S_NOP 0, implicit %0.sub3
...
---
# LiveRange splitting should split this into 2 intervals with the second getting
# allocated to sgpr0_sgpr1 and the first to something else so we see two copies
# in between for the two subregisters that are alive.
# CHECK-LABEL: name: func1
# CHECK: [[REG0:%sgpr[0-9]+]] = COPY %sgpr0
# CHECK: [[REG1:%sgpr[0-9]+]] = COPY %sgpr2
# CHECK: S_NOP 0
# CHECK: S_NOP 0, implicit [[REG0]]
# CHECK: S_NOP 0, implicit [[REG1]]
# CHECK: %sgpr0 = COPY [[REG0]]
# CHECK: %sgpr2 = COPY [[REG1]]
# CHECK: S_NOP
# CHECK: S_NOP 0, implicit %sgpr0
# CHECK: S_NOP 0, implicit %sgpr2
name: func1
tracksRegLiveness: true
body: |
  bb.0:
    liveins: %sgpr0, %sgpr1, %sgpr2
    undef %0.sub0 : sreg_128 = COPY %sgpr0
    %0.sub2 = COPY %sgpr2

    S_NOP 0, implicit-def dead %sgpr0, implicit-def dead %sgpr1

    S_NOP 0, implicit %0.sub0
    S_NOP 0, implicit %0.sub2

    ; Clobber everything but sgpr0-sgpr3
    S_NOP 0, implicit-def dead %sgpr4, implicit-def dead %sgpr5, implicit-def dead %sgpr6, implicit-def dead %sgpr7, implicit-def dead %sgpr8, implicit-def dead %sgpr9, implicit-def dead %sgpr10, implicit-def dead %sgpr11, implicit-def dead %sgpr12, implicit-def dead %sgpr13, implicit-def dead %sgpr14, implicit-def dead %sgpr15, implicit-def dead %vcc_lo, implicit-def dead %vcc_hi

    S_NOP 0, implicit %0.sub0
    S_NOP 0, implicit %0.sub2
...
---
# Check that copy hoisting out of loops works. This mainly should not crash the
# compiler when it hoists a subreg copy sequence.
# CHECK-LABEL: name: splitHoist
# CHECK: S_NOP 0, implicit-def %sgpr0
# CHECK: S_NOP 0, implicit-def %sgpr3
# CHECK-NEXT: SI_SPILL_S128_SAVE
name: splitHoist
tracksRegLiveness: true
body: |
  bb.0:
    successors: %bb.1, %bb.2
    S_NOP 0, implicit-def undef %0.sub0 : sreg_128
    S_NOP 0, implicit-def %0.sub3 : sreg_128

    S_CBRANCH_VCCNZ %bb.1, implicit undef %vcc
    S_BRANCH %bb.2

  bb.1:
    successors: %bb.1, %bb.3
    S_NOP 0, implicit %0.sub0

    ; Clobber registers
    S_NOP 0, implicit-def dead %sgpr0, implicit-def dead %sgpr1, implicit-def dead %sgpr2, implicit-def dead %sgpr3, implicit-def dead %sgpr4, implicit-def dead %sgpr5, implicit-def dead %sgpr6, implicit-def dead %sgpr7, implicit-def dead %sgpr8, implicit-def dead %sgpr9, implicit-def dead %sgpr10, implicit-def dead %sgpr11

    S_CBRANCH_VCCNZ %bb.1, implicit undef %vcc
    S_BRANCH %bb.3

  bb.2:
    successors: %bb.3
    ; Clobber registers
    S_NOP 0, implicit-def dead %sgpr0, implicit-def dead %sgpr1, implicit-def dead %sgpr2, implicit-def dead %sgpr3, implicit-def dead %sgpr4, implicit-def dead %sgpr5, implicit-def dead %sgpr6, implicit-def dead %sgpr7, implicit-def dead %sgpr8, implicit-def dead %sgpr9, implicit-def dead %sgpr10, implicit-def dead %sgpr11
    S_BRANCH %bb.3

  bb.3:
    S_NOP 0, implicit %0.sub0
    S_NOP 0, implicit %0.sub3
    S_NOP 0, implicit %0.sub0
    S_NOP 0, implicit %0.sub3
...