[PATCH] D59435: AMDGPU: Partially fix default device for HSA

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Fri Mar 15 14:55:15 PDT 2019


arsenm created this revision.
arsenm added reviewers: rampitec, nhaehnle, Anastasia.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, wdng, jvesely, kzhuravl.

There are a few different issues, mostly stemming from using
generation based checks for anything instead of subtarget
features. Stop adding flat-address-space as a feature for HSA, as it
should only be a device property. This was incorrectly allowing flat
instructions to select for SI.

      

Increase the default generation for HSA to avoid the encoding error
when emitting objects. This has some other side effects from various
checks which probably should be separate subtarget features (in the
cost model and for dealing with the DS offset folding issue).

      

Partial fix for bug 41070. It should probably be an error to try using
amdhsa without flat support.


https://reviews.llvm.org/D59435

Files:
  lib/Support/TargetParser.cpp
  lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  lib/Target/AMDGPU/GCNProcessors.td
  test/Analysis/CostModel/AMDGPU/fdiv.ll
  test/CodeGen/AMDGPU/flat-error-unsupported-gpu-hsa.ll
  test/CodeGen/AMDGPU/lower-kernargs.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D59435.190907.patch
Type: text/x-patch
Size: 6511 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190315/e4834235/attachment.bin>


More information about the llvm-commits mailing list