maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/verify-duplicate-literal.mir

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

29 lines
1.0 KiB
Plaintext
Raw Normal View History

[AMDGPU] Allow multiple uses of the same literal In GFX10 VOP3 can have a literal, which opens up the possibility of two operands using the same literal value, which is allowed and only counts as one use of the constant bus. AMDGPUAsmParser::validateConstantBusLimitations already knew about this but SIInstrInfo::verifyInstruction did not. Differential Revision: https://reviews.llvm.org/D100770
2021-04-08 19:58:49 +08:00
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass machineverifier -o - %s | FileCheck %s
# Two uses of the same literal only count as one use of the constant bus.
---
name: use_duplicate_literal_cndmask
tracksRegLiveness: true
body: |
bb.0:
liveins: $vcc_lo
; CHECK-LABEL: name: use_duplicate_literal_cndmask
; CHECK: liveins: $vcc_lo
; CHECK: $vgpr0 = V_CNDMASK_B32_e64 0, 1234567, 0, 1234567, killed $vcc_lo, implicit $exec
$vgpr0 = V_CNDMASK_B32_e64 0, 1234567, 0, 1234567, killed $vcc_lo, implicit $exec
...
---
name: use_duplicate_literal_fma
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: use_duplicate_literal_fma
; CHECK: liveins: $vgpr0
; CHECK: $vgpr0 = V_FMA_F32_e64 0, $vgpr0, 0, 1077936128, 0, 1077936128, 0, 0, implicit $mode, implicit $exec
$vgpr0 = V_FMA_F32_e64 0, $vgpr0, 0, 1077936128, 0, 1077936128, 0, 0, implicit $mode, implicit $exec
...