Commit Graph

20 Commits

Author SHA1 Message Date
Artem Belevich 8c635ba4a8 [CUDA] Fix missed CUDA version mappings. 2020-04-13 15:54:12 -07:00
Artem Belevich a9627b7ea7 [CUDA] Add partial support for recent CUDA versions.
Generate PTX using newer versions of PTX and allow using sm_80 with CUDA-11.
None of the new features of CUDA-10.2+ have been implemented yet, so using these
versions will still produce a warning.

Differential Revision: https://reviews.llvm.org/D77670
2020-04-08 11:19:44 -07:00
Artem Belevich 33386b20aa [CUDA] Simplify GPU variant handling. NFC.
Instead of hardcoding individual GPU mappings in multiple functions, keep them
all in one table and use it to look up the mappings.

We also don't care about 'virtual' architecture much, so the API is trimmed down
down to a simpler GPU->Virtual arch name lookup.

Differential Revision: https://reviews.llvm.org/D77665
2020-04-08 11:19:43 -07:00
Michael Liao b952d799ca [cuda][hip] Fix `RegisterVar` function prototype.
Summary:
- `RegisterVar` has `void` return type and `size_t` in its variable size
  parameter in HIP or CUDA 9.0+.

Reviewers: tra, yaxunl

Subscribers: cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D77398
2020-04-03 12:57:09 -04:00
Artem Belevich 12fefeef20 [CUDA] Assume the latest known CUDA version if we've found an unknown one.
This makes clang somewhat forward-compatible with new CUDA releases
without having to patch it for every minor release without adding
any new function.

If an unknown version is found, clang issues a warning (can be disabled
with -Wno-cuda-unknown-version) and assumes that it has detected
the latest known version. CUDA releases are usually supersets
of older ones feature-wise, so it should be sufficient to keep
released clang versions working with minor CUDA updates without
having to upgrade clang, too.

Differential Revision: https://reviews.llvm.org/D73231
2020-01-28 10:11:42 -08:00
Yaxun Liu 6add24adaf [HIP] Add GPU arch gfx1010, gfx1011, and gfx1012
Differential Revision: https://reviews.llvm.org/D64364

llvm-svn: 365799
2019-07-11 17:50:09 +00:00
Stanislav Mekhanoshin 0cfd75a07d [AMDGPU] gfx908 clang target
Differential Revision: https://reviews.llvm.org/D64430

llvm-svn: 365528
2019-07-09 18:19:00 +00:00
Artem Belevich 4071763bb8 Basic CUDA-10 support.
Differential Revision: https://reviews.llvm.org/D57771

llvm-svn: 353232
2019-02-05 22:38:58 +00:00
Artem Belevich 8fa28a0db0 [CUDA] Propagate detected version of CUDA to cc1
..and use it to control that parts of CUDA compilation
that depend on the specific version of CUDA SDK.

This patch has a placeholder for a 'new launch API' support
which is in a separate patch. The list will be further
extended in the upcoming patch to support CUDA-10.1.

Differential Revision: https://reviews.llvm.org/D57487

llvm-svn: 352798
2019-01-31 21:32:24 +00:00
Tim Renouf 632f35d495 Add gfx909 to GPU Arch
Subscribers: jholewinski, cfe-commits

Differential Revision: https://reviews.llvm.org/D53558

llvm-svn: 345198
2018-10-24 21:19:02 +00:00
Yaxun Liu 83b5f35d85 Add gfx904 and gfx906 to GPU Arch
Differential Revision: https://reviews.llvm.org/D53472

llvm-svn: 344996
2018-10-23 02:05:31 +00:00
Artem Belevich 44ecb0e3c2 [CUDA] Added basic support for compiling with CUDA-10.0
llvm-svn: 342924
2018-09-24 23:10:44 +00:00
Artem Belevich 3cce307799 [CUDA] Enable CUDA compilation with CUDA-9.2
Differential Revision: https://reviews.llvm.org/D45827

llvm-svn: 330753
2018-04-24 18:23:19 +00:00
Yaxun Liu 8a5fc15aa4 [CUDA] Add amdgpu sub archs
Patch by Greg Rodgers.
Revised and lit tests added by Yaxun Liu.

Differential Revision: https://reviews.llvm.org/D45277

llvm-svn: 329232
2018-04-04 21:19:27 +00:00
Erich Keane d45879d8ad Add NVPTX Support to ValidCPUList (enabling march notes)
A followup to: https://reviews.llvm.org/D42978
This patch adds NVPTX support for
enabling the march notes.

Differential Revision: https://reviews.llvm.org/D43045

llvm-svn: 324675
2018-02-08 23:16:00 +00:00
Artem Belevich fbc56a904f [CUDA] Added partial support for CUDA-9.1
Clang can use CUDA-9.1 now, though new APIs (are not implemented yet.

The major change is that headers in CUDA-9.1 went through substantial
changes that started in CUDA-9.0 which required substantial changes
in the cuda compatibility headers provided by clang.

There are two major issues:
* CUDA SDK no longer provides declarations for libdevice functions.
* A lot of device-side functions have become nvcc's builtins and
  CUDA headers no longer contain their implementations.

This patch changes the way CUDA headers are handled if we compile
with CUDA 9.x. Both 9.0 and 9.1 are affected.

* Clang provides its own declarations of libdevice functions.
* For CUDA-9.x clang now provides implementation of device-side
  'standard library' functions using libdevice.

This patch should not affect compilation with CUDA-8. There may be
some observable differences for CUDA-9.0, though they are not expected
to affect functionality.

Tested: CUDA test-suite tests for all supported combinations of:
        CUDA: 7.0,7.5,8.0,9.0,9.1
        GPU: sm_20, sm_35, sm_60, sm_70

Differential Revision: https://reviews.llvm.org/D42513

llvm-svn: 323713
2018-01-30 00:00:12 +00:00
Justin Lebar 066494d8c1 [CUDA] Print an error if you try to compile with < sm_30 on CUDA 9.
Summary:
CUDA 9's minimum sm is sm_30.

Ideally we should also make sm_30 the default when compiling with CUDA
9, but that seems harder than it should be.

Subscribers: sanjoy

Differential Revision: https://reviews.llvm.org/D39109

llvm-svn: 316611
2017-10-25 21:32:06 +00:00
Artem Belevich 8af4e23d1e [CUDA] Added rudimentary support for CUDA-9 and sm_70.
For now CUDA-9 is not included in the list of CUDA versions clang
searches for, so the path to CUDA-9 must be explicitly passed
via --cuda-path=.

On LLVM side NVPTX added sm_70 GPU type which bumps required
PTX version to 6.0, but otherwise is equivalent to sm_62 at the moment.

Differential Revision: https://reviews.llvm.org/D37576

llvm-svn: 312734
2017-09-07 18:14:32 +00:00
Justin Lebar d9bc485cfe [CUDA] Fix "control reaches end of non-void function" warnings in Cuda.cpp.
Some compilers are too dumb to realize that the switch statement covers
all cases.

(Don't use a "default" label, because we explicitly want to get a warning
if our switch doesn't cover all the cases.)

llvm-svn: 274713
2016-07-07 01:06:59 +00:00
Justin Lebar 629076178a [CUDA] Add utility functions for dealing with CUDA versions / architectures.
Summary:
Currently our handling of CUDA architectures is scattered all around
clang.  This patch centralizes it.

A key advantage of this centralization is that you can now write a C++
switch on e.g. CudaArch and get a compile error if you don't handle one
of the enum values.

Reviewers: tra

Subscribers: cfe-commits

Differential Revision: http://reviews.llvm.org/D21867

llvm-svn: 274681
2016-07-06 21:21:39 +00:00