pei-scavenge-sgpr-gfx9.mir 3.99 KB
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck %s

# Test what happens when an SGPR is unavailable for the unused add. The non-inline constant needs to be folded into the add instruction and not materialized in a register.

---
name: scavenge_sgpr_pei_no_sgprs
tracksRegLiveness: true

stack:
  - { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
  - { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }

machineFunctionInfo:
  isEntryFunction: false
  scratchRSrcReg:  $sgpr0_sgpr1_sgpr2_sgpr3
  scratchWaveOffsetReg: $sgpr34
  frameOffsetReg:  $sgpr33
  stackPtrOffsetReg:  $sgpr32

body:             |
  bb.0:
    liveins: $vgpr1

    ; CHECK-LABEL: name: scavenge_sgpr_pei_no_sgprs
    ; CHECK: liveins: $vgpr1
    ; CHECK: $sgpr27 = frame-setup COPY $sgpr33
    ; CHECK: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 524224, implicit-def $scc
    ; CHECK: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294443008, implicit-def $scc
    ; CHECK: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 1572864, implicit-def $scc
    ; CHECK: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr28, implicit-def $sgpr29, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
    ; CHECK: $sgpr33 = S_SUB_U32 $sgpr33, $sgpr34, implicit-def $scc
    ; CHECK: $vgpr3 = V_LSHRREV_B32_e64 6, killed $sgpr33, implicit $exec
    ; CHECK: $vgpr2 = V_ADD_U32_e32 8192, killed $vgpr3, implicit $exec
    ; CHECK: $sgpr33 = S_ADD_U32 $sgpr33, $sgpr34, implicit-def $scc
    ; CHECK: $vgpr0 = V_OR_B32_e32 killed $vgpr2, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31
    ; CHECK: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 1572864, implicit-def $scc
    ; CHECK: $sgpr33 = frame-setup COPY $sgpr27
    ; CHECK: S_ENDPGM 0, implicit $vcc
    S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr28, implicit-def $sgpr29, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
    $vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31
    S_ENDPGM 0, implicit $vcc
...