# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=si-peephole-sdwa -o - %s | FileCheck -check-prefix=GFX9 %s
# RUN: llc -mtriple=amdgcn -mcpu=fiji -verify-machineinstrs -run-pass=si-peephole-sdwa -o - %s | FileCheck -check-prefix=GFX9 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -passes=si-peephole-sdwa -o - %s | FileCheck -check-prefix=GFX9 %s
# RUN: llc -mtriple=amdgcn -mcpu=fiji -passes=si-peephole-sdwa -o - %s | FileCheck -check-prefix=GFX9 %s
# test for 3 consecutive _sdwa's
# GFX9-LABEL: name: test1_add_co_sdwa
# GFX9: = nsw V_ADD_CO_U32_sdwa
# GFX9-NEXT: = nuw V_ADDC_U32_e64
# GFX9: V_ADD_CO_U32_sdwa
# GFX9-NEXT: V_ADDC_U32_e64
# GFX9: V_ADD_CO_U32_sdwa
# GFX9-NEXT: V_ADDC_U32_e64
---
name: test1_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%30:vreg_64 = COPY $sgpr0_sgpr1
%63:vgpr_32, %65:sreg_64_xexec = nsw V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%64:vgpr_32, dead %66:sreg_64_xexec = nuw V_ADDC_U32_e64 %30.sub1, %0, killed %65, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
%161:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%163:vgpr_32, %165:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %161, 0, implicit $exec
%164:vgpr_32, dead %166:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, killed %165, 0, implicit $exec
%162:vreg_64 = REG_SEQUENCE %163, %subreg.sub0, %164, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %162, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
%171:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%173:vgpr_32, %175:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %171, 0, implicit $exec
%174:vgpr_32, dead %176:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, killed %175, 0, implicit $exec
%172:vreg_64 = REG_SEQUENCE %173, %subreg.sub0, %174, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %172, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for VCC interference on sdwa, should generate 1 xform only
# GFX9-LABEL: name: test2_add_co_sdwa
# GFX9: V_ADD_CO_U32_sdwa
# GFX9: V_ADDC_U32_e64
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9-NOT: V_ADDC_U32_e32
---
name: test2_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%30:vreg_64 = COPY $sgpr0_sgpr1
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%161:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%163:vgpr_32, %165:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %161, 0, implicit $exec
%164:vgpr_32, dead %166:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, killed %165, 0, implicit $exec
%162:vreg_64 = REG_SEQUENCE %163, %subreg.sub0, %164, %subreg.sub1
%64:vgpr_32, dead %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, killed %65, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
%161:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%163:vgpr_32, %165:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %161, 0, implicit $exec
%164:vgpr_32, dead %166:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, killed %165, 0, implicit $exec
%162:vreg_64 = REG_SEQUENCE %163, %subreg.sub0, %164, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %162, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for CarryOut used, should reject
# GFX9-LABEL: name: test3_add_co_sdwa
# GFX9: V_ADD_CO_U32_e64
# GFX9: V_ADDC_U32_e64
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9-NOT: V_ADDC_U32_e32
---
name: test3_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%30:vreg_64 = COPY $sgpr0_sgpr1
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, killed %65, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %66, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for CarryIn used more than once, should reject
# GFX9-LABEL: name: test4_add_co_sdwa
# GFX9: V_ADD_CO_U32_e64
# GFX9: V_ADDC_U32_e64
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9-NOT: V_ADDC_U32_e32
---
name: test4_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%30:vreg_64 = COPY $sgpr0_sgpr1
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %65, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %65, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for simple example, should generate sdwa
# GFX9-LABEL: name: test5_add_co_sdwa
# GFX9: V_ADD_CO_U32_sdwa
# GFX9: V_ADDC_U32_e64
---
name: test5_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%30:vreg_64 = COPY $sgpr0_sgpr1
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %65, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for V_ADD_CO_U32_e64 only, should reject
# GFX9-LABEL: name: test6_add_co_sdwa
# GFX9: V_ADD_CO_U32_e64
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9-NOT: V_ADDC_U32_e32
---
name: test6_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%30:vreg_64 = COPY $sgpr0_sgpr1
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %23, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for V_ADDC_U32_e64 only, should reject
# GFX9-LABEL: name: test7_add_co_sdwa
# GFX9: V_ADDC_U32_e64
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9-NOT: V_ADDC_U32_e32
---
name: test7_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%24:sreg_64_xexec = COPY $sgpr0_sgpr1
%30:vreg_64 = COPY $sgpr0_sgpr1
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %24, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %23, %subreg.sub0, %23, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %30.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for $vcc defined between two adds, should not generate
# GFX9-LABEL: name: test8_add_co_sdwa
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9: V_ADDC_U32_e64
---
name: test8_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%30:vreg_64 = COPY $sgpr0_sgpr1
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
$vcc = COPY %30
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %65, 0, implicit $exec
%31:vreg_64 = COPY $vcc
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %31.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for non dead $vcc, should not generate
# GFX9-LABEL: name: test9_add_co_sdwa
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9: V_ADDC_U32_e64
---
name: test9_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%30:vreg_64 = COPY $sgpr0_sgpr1
$vcc = COPY %30
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %65, 0, implicit $exec
%31:vreg_64 = COPY $vcc
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %31.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for def $vcc_lo, should not generate
# GFX9-LABEL: name: test10_add_co_sdwa
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9: V_ADDC_U32_e64
---
name: test10_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%30:vreg_64 = COPY $sgpr0_sgpr1
$vcc_lo = COPY %30.sub0
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%31:vgpr_32 = COPY $vcc_lo
%32:vreg_64 = REG_SEQUENCE %31, %subreg.sub0, %23, %subreg.sub1
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %65, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %32.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for read $vcc_hi, should not generate
# GFX9-LABEL: name: test11_add_co_sdwa
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9: V_ADDC_U32_e64
---
name: test11_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%30:vreg_64 = COPY $sgpr0_sgpr1
$vcc_hi = COPY %30.sub0
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
%31:vgpr_32 = COPY $vcc_hi
%32:vreg_64 = REG_SEQUENCE %31, %subreg.sub0, %23, %subreg.sub1
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %65, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %32.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
...
# test for $vcc defined and used between adds, should not generate
# GFX9-LABEL: name: test12_add_co_sdwa
# GFX9-NOT: V_ADD_CO_U32_sdwa
# GFX9: V_ADDC_U32_e64
---
name: test12_add_co_sdwa
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
liveins:
- { reg: '$vgpr0', virtual-reg: '%0' }
- { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
body: |
bb.0:
liveins: $vgpr0, $sgpr0_sgpr1
%1:sgpr_64 = COPY $sgpr0_sgpr1
%0:vgpr_32 = COPY $vgpr0
%22:sreg_32_xm0 = S_MOV_B32 255
%30:vreg_64 = COPY $sgpr0_sgpr1
%23:vgpr_32 = V_AND_B32_e32 %22, %0, implicit $exec
%63:vgpr_32, %65:sreg_64_xexec = V_ADD_CO_U32_e64 %30.sub0, %23, 0, implicit $exec
$vcc = COPY %30
%31:vreg_64 = COPY killed $vcc
%64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %65, 0, implicit $exec
%62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
GLOBAL_STORE_DWORDX2_SADDR %31.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
Codebase Browser
llvm