llvm-for-llvmta/test/CodeGen/AMDGPU/pei-scavenge-sgpr-gfx9.mir

58 lines
6.1 KiB
YAML

# 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 --check-prefix=MUBUF %s
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs -run-pass=prologepilog -amdgpu-enable-flat-scratch %s -o - | FileCheck --check-prefix=FLATSCR %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
frameOffsetReg: $sgpr33
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; MUBUF-LABEL: name: scavenge_sgpr_pei_no_sgprs
; MUBUF: liveins: $sgpr27, $vgpr1
; MUBUF: $sgpr27 = frame-setup COPY $sgpr33
; MUBUF: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 524224, implicit-def $scc
; MUBUF: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294443008, implicit-def $scc
; MUBUF: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 1572864, implicit-def $scc
; MUBUF: 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
; MUBUF: $vgpr0 = V_LSHRREV_B32_e64 6, $sgpr33, implicit $exec
; MUBUF: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr33, implicit $exec
; MUBUF: $vgpr2 = V_ADD_U32_e32 8192, killed $vgpr2, implicit $exec
; MUBUF: $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
; MUBUF: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 1572864, implicit-def $scc
; MUBUF: $sgpr33 = frame-setup COPY $sgpr27
; MUBUF: S_ENDPGM 0, implicit $vcc
; FLATSCR-LABEL: name: scavenge_sgpr_pei_no_sgprs
; FLATSCR: liveins: $sgpr27, $vgpr1
; FLATSCR: $sgpr27 = frame-setup COPY $sgpr33
; FLATSCR: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 8191, implicit-def $scc
; FLATSCR: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294959104, implicit-def $scc
; FLATSCR: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 24576, implicit-def $scc
; FLATSCR: 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
; FLATSCR: $vgpr0 = V_MOV_B32_e32 $sgpr33, implicit $exec
; FLATSCR: $sgpr33 = S_ADD_U32 $sgpr33, 8192, implicit-def $scc
; FLATSCR: $vgpr0 = V_OR_B32_e32 $sgpr33, $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
; FLATSCR: $sgpr33 = S_SUB_U32 $sgpr33, 8192, implicit-def $scc
; FLATSCR: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 24576, implicit-def $scc
; FLATSCR: $sgpr33 = frame-setup COPY $sgpr27
; FLATSCR: 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_MOV_B32_e32 %stack.0, implicit $exec
$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
...