llvm-project/llvm/test/CodeGen/AMDGPU/waitcnt-loop-irreducible.mir

48 lines
1009 B
YAML

# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefixes=GCN %s
# GCN-LABEL: name: irreducible_loop{{$}}
# GCN: S_LOAD_DWORDX4_IMM
# GCN: S_WAITCNT 127{{$}}
# GCN: S_BUFFER_LOAD_DWORD_IMM
# GCN: S_WAITCNT 127{{$}}
# GCN: S_CMP_GE_I32
--- |
define amdgpu_ps void @irreducible_loop() {
main:
ret void
}
...
---
name: irreducible_loop
body: |
bb.0:
successors: %bb.3, %bb.2
S_CBRANCH_VCCZ %bb.2, implicit $vcc
S_BRANCH %bb.3
bb.1:
successors: %bb.3, %bb.2
S_CBRANCH_VCCNZ %bb.3, implicit $vcc
bb.2:
successors: %bb.3
renamable $sgpr4_sgpr5_sgpr6_sgpr7 = S_LOAD_DWORDX4_IMM renamable $sgpr0_sgpr1, 0, 0
renamable $sgpr3 = S_BUFFER_LOAD_DWORD_IMM killed renamable $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0
bb.3:
successors: %bb.1, %bb.4
S_CMP_GE_I32 renamable $sgpr2, renamable $sgpr3, implicit-def $scc
S_CBRANCH_SCC0 %bb.1, implicit killed $scc
bb.4:
S_ENDPGM
...