1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
llvm-mirror/test/CodeGen/AMDGPU/fold-multiple.mir
Matt Arsenault a8a00a4e2a AMDGPU: Use SGPR_128 instead of SReg_128 for vregs
SGPR_128 only includes the real allocatable SGPRs, and SReg_128 adds
the additional non-allocatable TTMP registers. There's no point in
allocating SReg_128 vregs. This shrinks the size of the classes
regalloc needs to consider, which is usually good.

llvm-svn: 374284
2019-10-10 07:11:33 +00:00

41 lines
1.2 KiB
YAML

# RUN: llc --mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs -run-pass si-fold-operands,si-shrink-instructions %s -o - | FileCheck %s
--- |
define amdgpu_kernel void @test() #0 {
ret void
}
attributes #0 = { nounwind }
...
---
# This used to crash / trigger an assertion, because re-scanning the use list
# after constant-folding the definition of %3 lead to the definition of %2
# being processed twice.
# CHECK-LABEL: name: test
# CHECK: %2:vgpr_32 = V_LSHLREV_B32_e32 2, killed %0, implicit $exec
# CHECK: %4:vgpr_32 = V_AND_B32_e32 8, killed %2, implicit $exec
name: test
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32 }
- { id: 1, class: sreg_32 }
- { id: 2, class: vgpr_32 }
- { id: 3, class: sreg_32 }
- { id: 4, class: vgpr_32 }
- { id: 5, class: sgpr_128 }
body: |
bb.0 (%ir-block.0):
%0 = IMPLICIT_DEF
%1 = S_MOV_B32 2
%2 = V_LSHLREV_B32_e64 %1, killed %0, implicit $exec
%3 = S_LSHL_B32 %1, killed %1, implicit-def dead $scc
%4 = V_AND_B32_e64 killed %2, killed %3, implicit $exec
%5 = IMPLICIT_DEF
BUFFER_STORE_DWORD_OFFSET killed %4, killed %5, 0, 0, 0, 0, 0, 0, 0, implicit $exec
S_ENDPGM 0
...