AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4,182 Commits 3 Branches 0 Tags
ca9eb34000a6c80a41e4ba166ebab2b38cdb5ea3
Commit Graph

3720 Commits

Author SHA1 Message Date
Maneesh Gupta ca9eb34000 Bump version to 3.0 (#1648) 
Change-Id: Id1e6eb222080a339af938212e74a52c39c305eab

[ROCm/clr commit: 0a2682625f]
 2019-11-10 20:23:58 -08:00
Michael LIAO a10e227b56 Remove redundant declarations. 
- The revised `hip/hip_ext.h` have that declarations.


[ROCm/clr commit: d28ad401c9]
 2019-11-07 10:11:22 -05:00
Evgeny Mankov 62b86d1c76 [HIPIFY] Clang style formatting 
[ROCm/clr commit: 7f143585f6]
 2019-11-07 12:48:05 +03:00
Evgeny Mankov db5f0b0237 [HIPIFY][fix] Delete canCompileHostAndDeviceInOneJob declaration as well 
[ROCm/clr commit: 4d2424ad36]
 2019-11-07 11:32:53 +03:00
Evgeny Mankov be483c4b3e [HIPIFY][fix] Abandon canCompileHostAndDeviceInOneJob check for --cuda-compile-host-device option 
[Reason] It turned out that it is not so: 2 jobs are always


[ROCm/clr commit: 21c3d25403]
 2019-11-07 11:30:40 +03:00
Evgeny Mankov ba52f11231 [HIPIFY] Reorder options propagation to clang 
[Reason] Leave overriding opportunity for -D, -std=c++XX, etc.


[ROCm/clr commit: f18e63b8a9]
 2019-11-07 11:21:06 +03:00
Jeff Daily bc5596cc74 General hipMemset improvements (#1495) 
* hipMemset et al can use HSA API directly for synchronous cases

* lock and flush stream in hipMemset, hold lock until complete

* move hipMemset async check to front of conditional

* use hsa_amd_memory_fill for additional sync memset cases

code cleanup/review for all memset calls

* Fix inversion of execution mutating value.

* ihipMemsetSync fall back to kernel if HSA memset fails

* Never fallback, never surrender.

* Allow NULL stream.

* Optimise memset kernel. Remove deadwood.

* Update hip_memory.cpp

* Clean up stream logic in sync memset

* Revert "Clean up stream logic in sync memset"

This reverts commit 6117dedf673367f44cc704192573a117a3d92477.


[ROCm/clr commit: 854147e911]
 2019-11-07 13:19:54 +05:30
Alex Voicu 44d2a3bb73 Remove native vector support from the GCC case, since it never worked (#1637) 
[ROCm/clr commit: d38cc8efba]
 2019-11-07 13:19:14 +05:30
Sarbojit2019 4d0b7e65bb [HIP] Fixed hipStreamAddCallback [SWDEV#165185] (#1425) 
Fixed hipStreamAddCallback() as requested in SWDEV#165185
Added unit test to test the behavior


[ROCm/clr commit: 97fca3439d]
 2019-11-07 13:18:12 +05:30
ansurya f5a92e5cb6 Fixed texture 2D mapping for pitched arrays & 3D Texture read (#1415) 
Texture 2D image mapping for pitched arrays:
github issue: Texture Object's Buffer seems to be Misaligned #886
JIRA ticket: SWDEV-199313

SWDEV-151670 : Fixed issue with 3D texture with 4 components
SWDEV-151671 : Issue with 2D layered texture with 4 components

[ROCm/clr commit: dc8f556460]
 2019-11-07 13:17:46 +05:30
Rahul Garg cf648f7dbe Rename hip/hip_hcc.h to hip/hip_ext.h (#1341) 
* Rename hip/hip_hcc.h to hip/hip_ext.h

* Deprecate hip_hcc.h


[ROCm/clr commit: dfee3ae279]
 2019-11-07 13:17:10 +05:30
Rahul Garg 7cde192635 Merge pull request #1630 from ROCm-Developer-Tools/hotfix_volatile_accessors 
__half2 should walk like CUDA and talk like CUDA

[ROCm/clr commit: d8e9a09064]
 2019-11-06 10:25:03 -08:00
Rahul Garg 15c457396d Merge pull request #1620 from jeffdaily/hipEventRecord_patch 
fix race condition in hipEventRecord

[ROCm/clr commit: 5af7ca4445]
 2019-11-06 10:23:24 -08:00
Evgeny Mankov c3a76d58da [HIPIFY][Win][fix] canCompileHostAndDeviceInOneJob is true only for LLVM >= 10 
[ROCm/clr commit: 97a0670d29]
 2019-11-06 19:25:42 +03:00
Evgeny Mankov d5b2d0fd63 [HIPIFY][doc] Update README.md 
+ Supported versions, testing


[ROCm/clr commit: 3f737625ee]
 2019-11-06 19:18:13 +03:00
Jeff Daily 39a98df790 hipEventRecord only needs one lock; remove locked_eventIsReady 
[ROCm/clr commit: b2af1820f5]
 2019-11-06 15:56:32 +00:00
Jeff Daily 539d0c2ae3 remove ihipEvent_t::refreshEventStatus(), new hipEventElapsedTime 
This fixes possible races in hipEventElapsedTime.


[ROCm/clr commit: 444122dfb9]
 2019-11-06 15:46:46 +00:00
Evgeny Mankov 4ef69e128b [HIPIFY][format] Apply clang style formatting in LLVMCompat 
[ROCm/clr commit: 4cad5fab78]
 2019-11-06 14:43:22 +03:00
Evgeny Mankov bb93c0b039 [HIPIFY] Add a compatibility for CharSourceRange if LLVM < 7 
[ROCm/clr commit: 3dcae8760d]
 2019-11-06 14:30:39 +03:00
Alex Voicu 7efa901dfa Remove leftover noise. 
[ROCm/clr commit: 1df423165b]
 2019-11-06 02:46:21 +02:00
Alex Voicu 3ce73d1ef6 __half2 should walk like CUDA and talk like CUDA 
[ROCm/clr commit: 55fd1363e2]
 2019-11-06 02:43:04 +02:00
Rahul Garg b854e0a392 Merge pull request #1626 from mhbliao/hliao/master/fix.windows.build 
Use portable macro for deprecation message.

[ROCm/clr commit: 6833886449]
 2019-11-05 10:08:43 -08:00
Evgeny Mankov 388181ada7 Merge pull request #1595 from emankov/cmake 
[HIP][cmake] Simplify `UNIX` related code (the beginning)

[ROCm/clr commit: 7b1ca3dd91]
 2019-11-05 20:30:55 +03:00
Michael LIAO a1b2dcf87d Use portable macro for deprecation message. 
[ROCm/clr commit: 7ca43b98d1]
 2019-11-05 11:51:00 -05:00
Evgeny Mankov ecad81b794 Merge pull request #1624 from emankov/hipify 
[HIPIFY][#1409] Fix for kernel launch macro expansion

[ROCm/clr commit: cf5d1caab3]
 2019-11-05 14:04:51 +03:00
Evgeny Mankov 3889be3031 [HIPIFY][#1409] Fix for kernel launch macro expansion 
+ Add a corresponding test kernel_launch_01.cu
+ Add isBefore() check to avoid crash on Replacement with negative length

TODO:
+ Compatibility with former LLVM versions
+ More complicated kernel launch tests


[ROCm/clr commit: a1c380f38d]
 2019-11-05 14:00:13 +03:00
Rahul Garg 92393d6ecf Deprecate HIP Markers (#1622) 
* Deprecate HIP markers

* Deprecate profiler start/stop


[ROCm/clr commit: 8b3fce8069]
 2019-11-05 12:32:59 +05:30
Aryan Salmanpour 92a06b531d [hip][tests] Add two more workgroup sizes for testing hipLaunchCooperativeKernel (#1613) 
[ROCm/clr commit: 7a3d592ed0]
 2019-11-05 12:32:46 +05:30
Jeff Daily f7e255c3c4 fix race condition in hipEventRecord 
[ROCm/clr commit: 6c3479a155]
 2019-11-04 17:45:11 +00:00
Alex Voicu 1a3d02fb08 Separate volatile for clarity. Handle assignment. 
[ROCm/clr commit: ed0d6ec51e]
 2019-11-02 22:02:08 +02:00
Evgeny Mankov bc9690328f [HIPIFY] Introduce --cuda-gpu-arch as hipify-clang's option 
+ Pass it to clang if specified


[ROCm/clr commit: 7142b884ab]
 2019-11-02 14:19:31 +03:00
Alex Voicu 5c2503f0bd Accessors should work even when oddly volatile. 
[ROCm/clr commit: 2d76dde05b]
 2019-11-01 22:18:01 +02:00
Evgeny Mankov 3b84d8e638 Merge pull request #1615 from emankov/hipify 
[HIPIFY][CUB][#1460][perl] Add "cub::" namespace prefix support in hipify-perl as well

[ROCm/clr commit: 48bb6df7e2]
 2019-11-01 14:35:55 +03:00
Evgeny Mankov 43d286e9ce [HIPIFY][CUB][#1460][perl] Add "cub::" namespace prefix support in hipify-perl as well 
[ROCm/clr commit: c5a2a2daf2]
 2019-11-01 14:34:18 +03:00
Rahul Garg 2cf205bc7b Merge pull request #1582 from amd-lthakur/hipExtMLK 
Adding a directed test case for hipExtModuleLaunchKernel() api.

[ROCm/clr commit: 1bec1445bb]
 2019-10-31 17:13:26 -07:00
Rahul Garg e61ff0408c Merge pull request #1598 from lmoriche/master 
Fix a code object memory corruption

[ROCm/clr commit: 2199f8a6c6]
 2019-10-31 17:12:24 -07:00
Rahul Garg 138b0327da Add stream 
[ROCm/clr commit: f556e15361]
 2019-10-31 12:15:56 -04:00
Rahul Garg 440a172f0e Fix HIP init calls in hipMemcpy2DFromArray 
[ROCm/clr commit: 0718ba0f00]
 2019-10-31 12:15:56 -04:00
Evgeny Mankov 0cfdeda490 [HIPIFY][cmake][#1572] Fix: Do not override CMAKE_INSTALL_PREFIX 
Affects building with HIP, standalone building is not changed


[ROCm/clr commit: e79fd55d01]
 2019-10-31 16:55:06 +03:00
Rahul Garg 31fc374120 Formatting changes 
[ROCm/clr commit: 07f4431de8]
 2019-10-30 18:12:51 -07:00
Rahul Garg 5bcc1f66c5 Formatting changes ,variable name and check update 
[ROCm/clr commit: cd1435cbc7]
 2019-10-30 18:09:21 -07:00
Rahul Garg 04785f2d54 Merge pull request #1515 from ansurya/tex_unbind_issue_fix 
Fix undefined ref to hipUnbindTexture for texture types

[ROCm/clr commit: aeb7cebbad]
 2019-10-30 17:54:15 -07:00
Laurent Morichetti f1f649e57c Addressed review comments 
Change comment "must exceed" to "must be no shorter than"
move the std::string instead of creating a copy


[ROCm/clr commit: 3243f06eef]
 2019-10-30 13:14:41 -07:00
Evgeny Mankov 5403e7edcc Merge pull request #1593 from emankov/doc 
[HIP][cmake] Move all *_INSTALL_DIR variables up before first add_subdirectory()

[ROCm/clr commit: 961bc5737e]
 2019-10-30 22:10:05 +03:00
Michael LIAO 64f2d5e861 [HIP] Correct headers and add missing function templates for hip-clang. 
- Fix 2 runtime API prototypes
  `hipOccupancyMaxActiveBlocksPerMultiprocessor` and
  `hipOccupancyMaxActiveBlocksPerMultiprocessorWithFlags`
- Add missing function templates of them in hip-clang.


[ROCm/clr commit: 61bc68a5f4]
 2019-10-29 22:00:11 -04:00
Rahul Garg 42ab7b830e Merge pull request #1602 from ROCm-Developer-Tools/revert-1560-satyanveshd/hipoccupy 
Revert "Cooperative groups match with cuda SWDEV-205006"

[ROCm/clr commit: 9840cdac99]
 2019-10-29 16:54:36 -07:00
Evgeny Mankov dc0186720c [HIPIFY][#1603] Fix 
[ROCm/clr commit: 050fdad7b7]
 2019-10-29 22:10:36 +03:00
Rahul Garg 72c686ed67 Revert "Fix occupany APIs (#1560)" 
This reverts commit ad1e409a24.


[ROCm/clr commit: 27221bc823]
 2019-10-29 11:41:08 -07:00
Evgeny Mankov d8e846fc91 [HIPIFY][Linux] Rollback --cuda-compile-host-device on Linux 
[Reason] It doesn't work with LLVM 9 and higher; Windows is fine


[ROCm/clr commit: dd2243f2fa]
 2019-10-29 20:53:54 +03:00
Evgeny Mankov 21d798394a [HIPIFY] Introduce --cuda-compile-host-device for LLVM >= 9 
* LLVM < 9 continues using --cuda-host-only


[ROCm/clr commit: 411b18a124]
 2019-10-29 19:42:53 +03:00