1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 03:33:20 +01:00
llvm-mirror/test/CodeGen/AMDGPU/GlobalISel/inst-select-amdgcn.kernarg.segment.ptr.mir
Matt Arsenault 91c55cb124 AMDGPU/GlobalISel: Add support for llvm.amdgcn.kernarg.segment.ptr
Note a normal select test is not currently possible because this
relies on input registers tracked in SIMachineFunctionInfo which
are not currently serializable in MIR, but this does work end-to-end
from the IR.

llvm-svn: 335490
2018-06-25 16:17:48 +00:00

20 lines
542 B
YAML

# XFAIL: *
# RUN: llc -march=amdgcn -run-pass=instruction-select -verify-machineinstrs -global-isel %s -o - | FileCheck %s -check-prefixes=GCN
# FIXME: This requires additional context for what input registers are special inputs not present in MIR.
---
name: kernarg_segment_Ptr
legalized: true
regBankSelected: true
body: |
bb.0:
%0:vgpr(p4) = G_INTRINSIC intrinsic(@llvm.amdgcn.kernarg.segment.ptr)
%1:sgpr(s32) = G_LOAD %0 :: (load 4)
%2:vgpr(p1) = G_IMPLICIT_DEF
G_STORE %1, %2 :: (store 4)
...
---