1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 12:43:36 +01:00
llvm-mirror/test/CodeGen/AMDGPU/cmp_shrink.mir
Jay Foad 936643e784 [AMDGPU] Avoid using s_cmpk when src0 is not register
The hardware spec require src0 of s_cmpk should be a register. So, we
should not optimize s_cmp to s_cmpk if src0 is not register.

Patch by Ruiling Song!
2020-07-14 09:05:53 +01:00

12 lines
413 B
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass si-shrink-instructions -verify-machineinstrs %s -o - | FileCheck -check-prefix=GCN %s
---
name: not_shrink_icmp
body: |
bb.0:
; GCN-LABEL: name: not_shrink_icmp
; GCN: S_CMP_GT_I32 1, 65, implicit-def $scc
S_CMP_GT_I32 1, 65, implicit-def $scc
...