[clang][modules] Don't prevent translation of FW_Private includes when explicitly...
[llvm-project.git] / llvm / test / CodeGen / MIR / AMDGPU / noconvergent-invalid.mir
blobb674629cc5f025113237695d0e7259ed55de8d57
1 # RUN: not --crash llc -mtriple=amdgcn-amd-amdhsa -run-pass=none -verify-machineinstrs %s -o /dev/null 2>&1 | FileCheck %s
3 ---
4 name:            noconvergent_invalid
5 registers:
6 body: |
7   bb.0:
8     ; CHECK: NoConvergent flag expected only on convergent instructions.
9     %2:sreg_32 = IMPLICIT_DEF
10     %3:sreg_32 = noconvergent S_ADD_I32 %2, 1, implicit-def $scc
11 ...