llvm-project/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies.mir

129 lines
3.0 KiB
YAML

# RUN: llc -march=amdgcn -run-pass=si-fix-sgpr-copies -verify-machineinstrs -o - %s | FileCheck --check-prefix=GCN %s
# GCN-LABEL: name: fix-sgpr-copies
# GCN: V_ADD_CO_U32_e32
# GCN: V_ADDC_U32_e32
---
name: fix-sgpr-copies
body: |
bb.0:
%0:vgpr_32 = IMPLICIT_DEF
%1:sreg_32 = IMPLICIT_DEF
%2:sreg_32 = IMPLICIT_DEF
%3:sreg_32 = IMPLICIT_DEF
%4:vgpr_32 = V_CVT_U32_F32_e64 0, %0:vgpr_32, 0, 0, implicit $mode, implicit $exec
%5:sreg_32 = COPY %4:vgpr_32
%6:sreg_32 = S_ADD_I32 %2:sreg_32, %5:sreg_32, implicit-def $scc
%7:sreg_32 = S_ADDC_U32 %3:sreg_32, %1:sreg_32, implicit-def $scc, implicit $scc
...
# Test to ensure i1 phi copies from scalar registers through another phi won't
# be promoted into vector ones.
# GCN-LABEL: name: fix-sgpr-i1-phi-copies
# GCN: .8:
# GCN-NOT: vreg_64 = PHI
---
name: fix-sgpr-i1-phi-copies
tracksRegLiveness: true
body: |
bb.9:
S_BRANCH %bb.0
bb.4:
S_CBRANCH_SCC1 %bb.6, implicit undef $scc
bb.5:
%3:vreg_1 = IMPLICIT_DEF
bb.6:
%4:vreg_1 = PHI %2:sreg_64, %bb.4, %3:vreg_1, %bb.5
bb.7:
%5:vreg_1 = PHI %2:sreg_64, %bb.3, %4:vreg_1, %bb.6
S_BRANCH %bb.8
bb.0:
S_CBRANCH_SCC1 %bb.2, implicit undef $scc
bb.1:
%0:sreg_64 = S_MOV_B64 0
S_BRANCH %bb.3
bb.2:
%1:sreg_64 = S_MOV_B64 -1
S_BRANCH %bb.3
bb.3:
%2:sreg_64 = PHI %0:sreg_64, %bb.1, %1:sreg_64, %bb.2
S_CBRANCH_SCC1 %bb.7, implicit undef $scc
S_BRANCH %bb.4
bb.8:
...
# Avoid infinite loop in SIInstrInfo::legalizeGenericOperand when checking for ImpDef.
# GCN-LABEL: name: legalize-operand-search-each-def-once
# GCN-NOT: sreg_64 PHI
---
name: legalize-operand-search-each-def-once
tracksRegLiveness: true
body: |
bb.0:
successors: %bb.1, %bb.2
liveins: $sgpr0_sgpr1
%0:sgpr_64 = COPY $sgpr0_sgpr1
S_CBRANCH_VCCZ %bb.2, implicit undef $vcc
S_BRANCH %bb.1
bb.1:
%1:vreg_64 = IMPLICIT_DEF
S_BRANCH %bb.2
bb.2:
%2:sgpr_64 = PHI %0, %bb.0, %1, %bb.1
$sgpr0_sgpr1 = COPY %0
...
# A REG_SEQUENCE that uses registers defined by both a PHI and a COPY could
# result in an endless search.
# GCN-LABEL: name: process-phi-search-each-use-once
# GCN-NOT: sreg_32 PHI
---
name: process-phi-search-each-use-once
tracksRegLiveness: true
body: |
bb.0:
successors: %bb.1, %bb.2
liveins: $vgpr3
%0:vgpr_32 = COPY $vgpr3
S_CBRANCH_VCCZ %bb.2, implicit undef $vcc
S_BRANCH %bb.1
bb.1:
%1:sgpr_32 = IMPLICIT_DEF
S_BRANCH %bb.2
bb.2:
%2:sgpr_32 = PHI %0, %bb.0, %1, %bb.1
%3:vreg_64 = REG_SEQUENCE %2, %subreg.sub0, %0, %subreg.sub1
$vgpr3 = COPY %3.sub0
...
# Test to ensure that undef SCC gets properly propagated.
# GCN-LABEL: name: scc_undef
# GCN: S_CSELECT_B64 -1, 0, implicit undef $scc
# GCN: V_CNDMASK
---
name: scc_undef
tracksRegLiveness: true
body: |
bb.0:
%1:vgpr_32 = IMPLICIT_DEF
%2:sreg_32 = S_MOV_B32 1
%3:sreg_32 = COPY %1:vgpr_32
%4:sreg_32 = S_CSELECT_B32 killed %2:sreg_32, killed %3:sreg_32, implicit undef $scc
---