llvm-project/llvm/test/CodeGen/AMDGPU/spill-special-sgpr.mir

109 lines
5.8 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=CHECK,GFX9 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=CHECK,GFX10 %s
--- |
define amdgpu_kernel void @check_vcc() #0 {
ret void
}
attributes #0 = { "frame-pointer"="all" }
...
---
name: check_vcc
tracksRegLiveness: true
liveins:
- { reg: '$sgpr4_sgpr5' }
- { reg: '$sgpr6_sgpr7' }
- { reg: '$sgpr8' }
frameInfo:
maxAlignment: 4
stack:
- { id: 0, type: spill-slot, size: 8, alignment: 4 }
machineFunctionInfo:
isEntryFunction: true
waveLimiter: true
scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
stackPtrOffsetReg: '$sgpr32'
frameOffsetReg: '$sgpr33'
argumentInfo:
privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
dispatchPtr: { reg: '$sgpr4_sgpr5' }
kernargSegmentPtr: { reg: '$sgpr6_sgpr7' }
workGroupIDX: { reg: '$sgpr8' }
privateSegmentWaveByteOffset: { reg: '$sgpr9' }
body: |
bb.0:
liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7
; CHECK-LABEL: name: check_vcc
; CHECK: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr9
; GFX9: $sgpr33 = S_MOV_B32 0
; GFX9: $sgpr12 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $sgpr13 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $sgpr14 = S_MOV_B32 4294967295, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $sgpr15 = S_MOV_B32 14680064, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $sgpr12 = S_ADD_U32 $sgpr12, $sgpr9, implicit-def $scc, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $sgpr13 = S_ADDC_U32 $sgpr13, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $vcc = IMPLICIT_DEF
; GFX9: $vgpr0 = V_WRITELANE_B32_vi $vcc_lo, 0, undef $vgpr0, implicit $vcc
; GFX9: $vgpr0 = V_WRITELANE_B32_vi $vcc_hi, 1, $vgpr0, implicit $vcc
; GFX9: $vcc = S_MOV_B64 $exec
; GFX9: $exec = S_MOV_B64 3
; GFX9: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
; GFX9: $exec = S_MOV_B64 $vcc
; GFX9: $vcc_hi = V_READLANE_B32_vi $vgpr0, 1
; GFX9: $vcc_lo = V_READLANE_B32_vi killed $vgpr0, 0
; GFX9: $vcc = IMPLICIT_DEF
; GFX9: $vgpr0 = V_WRITELANE_B32_vi $vcc_lo, 0, undef $vgpr0, implicit $vcc
; GFX9: $vgpr0 = V_WRITELANE_B32_vi $vcc_hi, 1, $vgpr0, implicit killed $vcc
; GFX9: $vcc = S_MOV_B64 $exec
; GFX9: $exec = S_MOV_B64 3
; GFX9: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
; GFX9: $exec = S_MOV_B64 killed $vcc
; GFX9: $vcc = S_MOV_B64 $exec
; GFX9: $exec = S_MOV_B64 3
; GFX9: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
; GFX9: $exec = S_MOV_B64 killed $vcc
; GFX9: $vcc_lo = V_READLANE_B32_vi $vgpr0, 0, implicit-def $vcc
; GFX9: $vcc_hi = V_READLANE_B32_vi killed $vgpr0, 1
; GFX10: $sgpr33 = S_MOV_B32 0
; GFX10: $sgpr96 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $sgpr97 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $sgpr98 = S_MOV_B32 4294967295, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $sgpr99 = S_MOV_B32 836853760, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $sgpr96 = S_ADD_U32 $sgpr96, $sgpr9, implicit-def $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $sgpr97 = S_ADDC_U32 $sgpr97, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $vcc = IMPLICIT_DEF
; GFX10: $vgpr0 = V_WRITELANE_B32_gfx10 $vcc_lo, 0, undef $vgpr0, implicit $vcc
; GFX10: $vgpr0 = V_WRITELANE_B32_gfx10 $vcc_hi, 1, $vgpr0, implicit $vcc
; GFX10: $vcc = S_MOV_B64 $exec
; GFX10: $exec = S_MOV_B64 3
; GFX10: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
; GFX10: $exec = S_MOV_B64 $vcc
; GFX10: $vcc_hi = V_READLANE_B32_gfx10 $vgpr0, 1
; GFX10: $vcc_lo = V_READLANE_B32_gfx10 killed $vgpr0, 0
; GFX10: $vcc = IMPLICIT_DEF
; GFX10: $vgpr0 = V_WRITELANE_B32_gfx10 $vcc_lo, 0, undef $vgpr0, implicit $vcc
; GFX10: $vgpr0 = V_WRITELANE_B32_gfx10 $vcc_hi, 1, $vgpr0, implicit killed $vcc
; GFX10: $vcc = S_MOV_B64 $exec
; GFX10: $exec = S_MOV_B64 3
; GFX10: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
; GFX10: $exec = S_MOV_B64 killed $vcc
; GFX10: $vcc = S_MOV_B64 $exec
; GFX10: $exec = S_MOV_B64 3
; GFX10: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
; GFX10: $exec = S_MOV_B64 killed $vcc
; GFX10: $vcc_lo = V_READLANE_B32_gfx10 $vgpr0, 0, implicit-def $vcc
; GFX10: $vcc_hi = V_READLANE_B32_gfx10 killed $vgpr0, 1
$vcc = IMPLICIT_DEF
SI_SPILL_S64_SAVE $vcc, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
$vcc = IMPLICIT_DEF
SI_SPILL_S64_SAVE killed $vcc, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
$vcc = SI_SPILL_S64_RESTORE %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
...