Граф коммитов

1191 Коммитов

Автор SHA1 Сообщение Дата
Yaxun (Sam) Liu 0307ae4c9a Workaround for libc++ include path for HIP-Clang (#1917)
HIP-Clang cuda_wrapper headers require clang include path before standard C++ include path.
However libc++ include path requires to be before clang include path.
To workaround this, we pass -isystem with the parent directory of clang include
path instead of the clang include path itself.
2020-03-18 11:20:21 +05:30
Jatin Chaudhary 8a3ce17ba6 Adding Half Abs APIs (#1902) 2020-03-17 14:13:19 +05:30
Sameer Sahasrabuddhe 446a9e82e2 enable HCC printf when using hip-clang (#1947)
This allows printf to work with hip-clang and HCC runtime. See comments under #1919 for a reported bug and feature request.
2020-03-17 14:03:27 +05:30
Joseph Greathouse dc9ecf03f8 Fix compiler warning on NVCC path (#1942)
GCC emits a warning about using static functions like
hipCUDAErrorTohipError inside this function, because it has an
inline directive, but it's not static. Adding static to this function
to silence warnings (and prevent potential problems in the future).
2020-03-17 14:02:59 +05:30
Joseph Greathouse 7f49e47217 Fix occupancy calculations API on NVCC (#1941)
NVCC warned if you tried to use hipOccupancyMaxActiveBlocksPerMultiprocessor
because when passing in a device function pointer, "const void* func" was
insufficient to describe it accurately. Adding a C++ templated class type
definition for this function.
2020-03-17 14:02:48 +05:30
Sarbojit2019 5ddb9e1eb7 Fix __sad signature match with Cuda (#1936)
Fix for issue #1930
2020-03-17 14:02:00 +05:30
Aryan Salmanpour e509a6d0b4 [HIP] add cooperative kernel launch APIs on NVCC (#1929) 2020-03-17 14:01:11 +05:30
Maneesh Gupta e8bd9768d1 Annotate __constant__ (#1901) 2020-03-17 13:59:44 +05:30
mhbliao fc223dc584 [hip] Improve the portability of the header for vector type support. (#1873)
- Need to check the availability of `__has_attribute` builtin macro
  instead of compiler versions. That's more reliable and portable among
  various compilers.
- Provides a very basic support of vectors for unknown compilers.
2020-03-17 13:59:24 +05:30
Evgeny Mankov 21ccb0be01 Merge pull request #1908 from asalmanp/prop_mulit_coop
[HIP] add hip specific properties for cooperative kernel multi device
2020-03-12 19:12:11 +03:00
Alex Voicu b9544eabe8 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_robust_constant 2020-03-12 14:20:26 +00:00
Maneesh Gupta af933d0900 Expose support for non-returning atomic FADD (#1909)
Change-Id: If5359488324477315a9bd4f308a75f606c065b39
2020-03-11 14:33:15 +05:30
Nick Curtis a9af4755cb Fix incorrect shfl_xor for Windows
copy/paste error, need __shfl_xor w/ lane_mask
2020-03-10 12:04:05 -05:00
Sameer Sahasrabuddhe 2c3dfdda41 separate printf declaration for vdi/clang
There are now two implementations of printf in HIP:

1. The implemenation for HCC is controlled by the HC_FEATURE_PRINTF
   macro, and it works only with the HCC compiler used in combination
   with the HCC runtime.

2. The implementation for hip-clang requires the VDI runtime, and is
   always enabled with that combination.
2020-03-09 09:40:05 +05:30
Aryan Salmanpour ddd0b31d16 move new enums to the end to maintain compatibility 2020-03-06 11:38:44 -05:00
Maneesh Gupta 48f5524fdc Expose support for non-returning atomic FADD
Change-Id: If5359488324477315a9bd4f308a75f606c065b39
2020-03-05 10:30:52 +05:30
Aryan Salmanpour 7bfb990ef7 [HIP] add hip specific properties for cooperative kernel multi device 2020-03-03 13:25:36 -05:00
Alex Voicu 3441cd7f16 Annotate __constant__ 2020-02-28 22:54:00 +02:00
saleelk 40a28e767e Fix HIPRTC headers to export C style symbols (#1879) 2020-02-28 16:47:29 +05:30
Rahul Garg 6be7537cf9 Remove deprecated HIP markers (#1876) 2020-02-28 16:47:15 +05:30
Rahul Garg 1c794045e0 Add hipDrvOccupancyMaxActiveBlocksPerMultiprocessor[WithFlags] (#1854)
Equivalent to cuOccupancyMaxActiveBlocksPerMultiprocessor[WithFlags].
2020-02-28 16:46:55 +05:30
Nick Curtis a094c87038 fix long shuffle implementations for windows (#1895)
Fixes for SWDEV-223694
2020-02-26 15:53:56 +05:30
Rahul Garg ec84c16d75 Fix hipMemcpy3D (#1798)
Fixes #1790 and #1791. hipMemcpy3D still requires further refactoring for different input and output combinations.
2020-02-17 19:35:35 +05:30
Nick Curtis 5b0f34c59b Implement long / long long shuffles (#1829)
Implement additional data-types for shuffles (long and long long).
Based upon the double implementation.
2020-02-15 09:51:09 +05:30
ansurya 888a7f2a90 Reduce GPU copying based on arch it runs on (#1751)
Implements SWDEV-213230.
2020-02-13 14:21:51 +05:30
Aryan Salmanpour 1c013bab3e fix build error in nvcc path 2020-02-11 12:16:51 -05:00
Aryan Salmanpour 504412c1e4 Fix a typo causing a build error 2020-02-10 11:44:40 -05:00
Aryan Salmanpour dfa565d76f resolve merge conflict 2020-02-10 10:30:55 -05:00
Maneesh Gupta d032637934 Revert "Match Occupancy APIs syntax with CUDA (#1625)" (#1857)
Reverting this for now till we figure out how to avoid the build
breakage.

This reverts commit 262ad13dd5.
2020-02-10 10:45:28 +05:30
Alex Voicu 8f96152d3a (Maybe) Match alignment between Clang and GCC. (#1789)
Should fix #1740 and the related internal bug.
2020-02-10 10:44:49 +05:30
vsytch fa363ae721 Device texture functions should not normalize the sampled pixel (#1826)
* Device texture functions should not normalize the sampled pixel. This is already done by HW.
* Add support to use h/w capability for normalized float data convertion for driver API's

Co-authored-by: ansurya <50609411+ansurya@users.noreply.github.com>
2020-02-05 20:56:17 +05:30
Aryan Salmanpour 75572a4175 code clean up 2020-01-31 13:08:25 -05:00
Aryan Salmanpour 6db9b782be [HIP][HIPIFY] Add some missing flags for cooperative launch and occupancy APIs 2020-01-30 15:05:53 -05:00
satyanveshd 262ad13dd5 Match Occupancy APIs syntax with CUDA (#1625)
* Match Occupancy APIs syntax with CUDA and fix tests using these APIs
2020-01-29 13:05:53 -08:00
vsytch 6da0c82b78 Add missing texturePitchAlignment member to the hipDeviceProp_t struct. (#1802)
* Add missing texturePitchAlignment member to the hipDeviceProp_t struct.

* Add missing hipDeviceAttributeTexturePitchAlignment enumerator to the hipDeviceAttribute_t enum.

* Initialize texturePitchAlignment to 256. This works for gfx9+, but is technically overaligned in most cases for pre-gfx9.

* Add the texturePitchAlignment property to the NVCC path.
2020-01-27 16:37:00 -08:00
vsytch e419a1609f Update the HIP_TRSF_* flags to match their Cuda equivalents. (#1801) 2020-01-24 11:41:15 -08:00
mshivama 0605426049 SWDEV-220503: this_grid().thread_rank() gives incorrect result (#1808)
* fix a minor bug while computing this.grid()::thread_rank()
2020-01-24 16:23:28 +05:30
kpyzhov 1d6a2fb064 Don't use accelerated vector element access for hip-clang. (#1796) 2020-01-15 18:17:08 -08:00
kpyzhov 0918614615 Add missing constructors for Scalar_accessor class. (#1792) 2020-01-14 11:30:21 -08:00
Evgeny Mankov 9c2fcff9ce [HIP] Unify hipError_t (Step 3): Sync nvcc path (#1778)
* [HIP] Unify hipError_t (Step 3): Sync nvcc path

* [HIP][fix] Add CUDA 10.x support to nvcc path
2020-01-10 13:47:18 +05:30
Maneesh Gupta c091635f5a Revert PRs that break ROCm builds (#1781)
Fixes SWDEV-218626 and SWDEV-218629

Changes:
- Revert "`static inline` in a header, just like excess sugar in a diet, causes bloat (#1692)"
   This reverts commit cf526f5484.
- Revert "Fix rocFFT build failure (#1777)"
   This reverts commit cbd8f604ec.
2020-01-08 15:11:58 +05:30
ansurya cbd8f604ec Fix rocFFT build failure (#1777)
Fixes SWDEV-217761
2020-01-07 08:12:37 +05:30
Rahul Garg 534376cb41 Add hipBindTexture2D on NVCC path (#1773) 2020-01-06 12:33:50 +05:30
Rahul Garg 3fe1695c3a Fix hipcc warning related to hipVersion (#1767)
* Fix hipcc warning related to hipVersion
* Rename hipVersion.h to hip_version.h
* Remove HIP_VERSION splitting
* Update .gitignore
- Ignore generated include/hip/hip_version.h
- Removed some stale entries
- Added executables from samples/1_Utils/*/ for consistency with bin/ entries.
2020-01-06 12:33:23 +05:30
Evgeny Mankov ed43699a3a Merge pull request #1759 from emankov/master
[HIP] Unify hipError_t (Step 2)
2019-12-30 19:21:09 +03:00
Sarbojit2019 4fd77f8336 Change to generate hipVersion.h (#1726)
HIP_VERSION_MAJOR, HIP_VERSION_MINOR, HIP_VERSION_PATCH and HIP_VERSION pre-processor macros are now defined in hipVersion.h instead of being set by hipcc.
2019-12-30 12:44:24 +05:30
Aryan Salmanpour 857052be1e [hip] refactoring cooperative kernel launch APIs (#1737)
This PR is a follow-up on PR# #1698 and it makes two more APIs (hipLaunchCooperativeKernel/hipLaunchCooperativeKernelMultiDevice) inline so that they can work correctly with lazy binding.
2019-12-30 12:42:17 +05:30
Evgeny Mankov 4aaa2336a8 [HIP] Clean-up deprecated HIP error codes
hipErrorMemoryAllocation -> hipErrorOutOfMemory
hipErrorInitializationError -> hipErrorNotInitialized
hipErrorMapBufferObjectFailed -> hipErrorMapFailed
hipErrorInvalidResourceHandle -> hipErrorInvalidHandle
2019-12-23 17:01:35 +03:00
Yaxun (Sam) Liu 35988729f3 Add macro __HIP_ENABLE_CUDA_WRAPPER_FOR_OPENMP__ (#1761)
This is to allow force enable cuda wrapper for OpenMP for flexibility
2019-12-23 19:24:54 +05:30
saleelk 1ca75e5f6d Fix the return type of demangle function so that its compatible across ABIs (#1744) 2019-12-23 19:11:40 +05:30