1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
llvm-mirror/test/CodeGen/AMDGPU/cluster-flat-loads-postra.mir
Konstantin Zhuravlyov a76ecb87cf AMDGPU: Add target id and code object v4 support
- Add target id support (https://clang.llvm.org/docs/ClangOffloadBundler.html#target-id)
  - Add code object v4 support (https://llvm.org/docs/AMDGPUUsage.html#elf-code-object)
    - Add kernarg_size to kernel descriptor
    - Change trap handler ABI to no longer move queue pointer into s[0:1]
  - Cleanup ELF definitions
    - Add V2, V3, V4 suffixes to make a clear distinction for code object version
    - Consolidate note names

Differential Revision: https://reviews.llvm.org/D95638
2021-03-24 11:54:05 -04:00

32 lines
1.1 KiB
YAML

# RUN: llc -march=amdgcn -mcpu=tonga -mattr=-xnack -run-pass post-RA-sched -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
# GCN: FLAT_LOAD_DWORD
# GCN-NEXT: FLAT_LOAD_DWORD
# GCN: FLAT_STORE_DWORD
# GCN-NEXT: FLAT_STORE_DWORD
---
name: cluster_loads_post_ra
tracksRegLiveness: true
registers:
liveins:
- { reg: '$vgpr0' }
body: |
bb.0:
liveins: $vgpr0
$vgpr0_vgpr1 = IMPLICIT_DEF
$vgpr4_vgpr5 = IMPLICIT_DEF
$vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: (load 4)
$vgpr4 = FLAT_LOAD_DWORD $vgpr4_vgpr5, 0, 0, implicit $exec, implicit $flat_scr :: (load 4)
$vgpr2 = IMPLICIT_DEF
$vgpr3 = IMPLICIT_DEF
$vgpr6 = IMPLICIT_DEF
$vgpr0 = V_ADD_CO_U32_e32 16, $vgpr2, implicit-def $vcc, implicit $exec
$vgpr1 = V_ADDC_U32_e32 $vgpr3, killed $vgpr6, implicit-def dead $vcc, implicit $vcc, implicit $exec
FLAT_STORE_DWORD $vgpr2_vgpr3, killed $vgpr0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4)
FLAT_STORE_DWORD $vgpr0_vgpr1, killed $vgpr4, 0, 0, implicit $exec, implicit $flat_scr :: (store 4)
S_ENDPGM 0
...