]> granicus.if.org Git - llvm/commit
Merging r258901:
authorTom Stellard <thomas.stellard@amd.com>
Thu, 2 Jun 2016 21:01:38 +0000 (21:01 +0000)
committerTom Stellard <thomas.stellard@amd.com>
Thu, 2 Jun 2016 21:01:38 +0000 (21:01 +0000)
commitd9a2679200db693d8521b1a7312aa3b45442f1a2
treea92102167cdd1ec00c4ba389d8db9606769d0dde
parent0cb3cc3d79894ccfe7dcade9b09c410c90ddbbdf
Merging r258901:

------------------------------------------------------------------------
r258901 | Matthew.Arsenault | 2016-01-26 18:17:49 -0800 (Tue, 26 Jan 2016) | 17 lines

AMDGPU: Fix default device handling

When no device name is specified, default to kaveri
for HSA since SI is not supported and it woud fail.

Default to "tahiti" instead of "SI" since these are
effectively the same, and tahiti is an actual device.

Move default device handling to the TargetMachine
rather than the AMDGPUSubtarget. The module ISA version
is computed from the device name provided with the target
machine, so the attributes printed by the AsmPrinter were
inconsistent with those computed in the subtarget.

Also remove DevName field from subtarget since it's redundant
with getCPU() in the superclass.

------------------------------------------------------------------------

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_38@271588 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/AMDGPUSubtarget.cpp
lib/Target/AMDGPU/AMDGPUSubtarget.h
lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
test/CodeGen/AMDGPU/hsa-default-device.ll [new file with mode: 0644]