AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4,432 Commits 3 Branches 0 Tags
7ab3583c60a7ca5aee8dbfadaaf42885787c01fb
Commit Graph

1189 Commits

Author SHA1 Message Date
Sameer Sahasrabuddhe 7ab3583c60 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.

[ROCm/hip commit: 899c878703]
 2020-03-17 14:03:27 +05:30
Joseph Greathouse 504ba0a4c9 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).

[ROCm/hip commit: f7e85649f4]
 2020-03-17 14:02:59 +05:30
Joseph Greathouse 122c2f9034 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.

[ROCm/hip commit: 4128d68ed7]
 2020-03-17 14:02:48 +05:30
Sarbojit2019 0310e4d7f8 Fix __sad signature match with Cuda (#1936) 
Fix for issue #1930

[ROCm/hip commit: 320742e8a0]
 2020-03-17 14:02:00 +05:30
Aryan Salmanpour 03654845a4 [HIP] add cooperative kernel launch APIs on NVCC (#1929) 
[ROCm/hip commit: 015895a265]
 2020-03-17 14:01:11 +05:30
Maneesh Gupta 8feab1161e Annotate __constant__ (#1901) 
[ROCm/hip commit: eee5cc8621]
 2020-03-17 13:59:44 +05:30
mhbliao e0da34b5b1 [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.

[ROCm/hip commit: 774035d869]
 2020-03-17 13:59:24 +05:30
Evgeny Mankov 6039400c04 Merge pull request #1908 from asalmanp/prop_mulit_coop 
[HIP] add hip specific properties for cooperative kernel multi device

[ROCm/hip commit: 70f5646f8a]
 2020-03-12 19:12:11 +03:00
Alex Voicu 8cecdaa704 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_robust_constant 
[ROCm/hip commit: 1c5f526e6b]
 2020-03-12 14:20:26 +00:00
Maneesh Gupta d44d5f8cdd Expose support for non-returning atomic FADD (#1909) 
Change-Id: If5359488324477315a9bd4f308a75f606c065b39

[ROCm/hip commit: 0726abf424]
 2020-03-11 14:33:15 +05:30
Nick Curtis 98b7cb62aa Fix incorrect shfl_xor for Windows 
copy/paste error, need __shfl_xor w/ lane_mask

[ROCm/hip commit: 09edc7e49c]
 2020-03-10 12:04:05 -05:00
Sameer Sahasrabuddhe 07abb2d633 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.


[ROCm/hip commit: 09130b3b92]
 2020-03-09 09:40:05 +05:30
Aryan Salmanpour feb28352cb move new enums to the end to maintain compatibility 
[ROCm/hip commit: 7e45c54ea6]
 2020-03-06 11:38:44 -05:00
Maneesh Gupta 08ed6ab780 Expose support for non-returning atomic FADD 
Change-Id: If5359488324477315a9bd4f308a75f606c065b39


[ROCm/hip commit: 4a40010ac6]
 2020-03-05 10:30:52 +05:30
Aryan Salmanpour df81136734 [HIP] add hip specific properties for cooperative kernel multi device 
[ROCm/hip commit: 03797ae986]
 2020-03-03 13:25:36 -05:00
Alex Voicu abbb594f7c Annotate __constant__ 
[ROCm/hip commit: 27480ff5a2]
 2020-02-28 22:54:00 +02:00
saleelk 3c66b171e1 Fix HIPRTC headers to export C style symbols (#1879) 
[ROCm/hip commit: 3e1f41c165]
 2020-02-28 16:47:29 +05:30
Rahul Garg c34c9a4b4d Remove deprecated HIP markers (#1876) 
[ROCm/hip commit: 6c5fa32815]
 2020-02-28 16:47:15 +05:30
Rahul Garg 5229ffff99 Add hipDrvOccupancyMaxActiveBlocksPerMultiprocessor[WithFlags] (#1854) 
Equivalent to cuOccupancyMaxActiveBlocksPerMultiprocessor[WithFlags].

[ROCm/hip commit: edc97f3073]
 2020-02-28 16:46:55 +05:30
Nick Curtis 2715d1b036 fix long shuffle implementations for windows (#1895) 
Fixes for SWDEV-223694

[ROCm/hip commit: b7dd073d93]
 2020-02-26 15:53:56 +05:30
Rahul Garg f1746197c7 Fix hipMemcpy3D (#1798) 
Fixes #1790 and #1791. hipMemcpy3D still requires further refactoring for different input and output combinations.

[ROCm/hip commit: 8c5e5e435b]
 2020-02-17 19:35:35 +05:30
Nick Curtis 6d661ba6ca Implement long / long long shuffles (#1829) 
Implement additional data-types for shuffles (long and long long).
Based upon the double implementation.


[ROCm/hip commit: 797a929a65]
 2020-02-15 09:51:09 +05:30
ansurya fb53186682 Reduce GPU copying based on arch it runs on (#1751) 
Implements SWDEV-213230.

[ROCm/hip commit: 8c6934223b]
 2020-02-13 14:21:51 +05:30
Aryan Salmanpour 07c3e4f898 fix build error in nvcc path 
[ROCm/hip commit: 959f1b0f0e]
 2020-02-11 12:16:51 -05:00
Aryan Salmanpour 5db60dab96 Fix a typo causing a build error 
[ROCm/hip commit: 5a29f27455]
 2020-02-10 11:44:40 -05:00
Aryan Salmanpour 964a272004 resolve merge conflict 
[ROCm/hip commit: 874b201ee2]
 2020-02-10 10:30:55 -05:00
Maneesh Gupta 7753b3e827 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 e38db9fb6f.

[ROCm/hip commit: f8e1c01900]
 2020-02-10 10:45:28 +05:30
Alex Voicu 5d5344eea1 (Maybe) Match alignment between Clang and GCC. (#1789) 
Should fix #1740 and the related internal bug.

[ROCm/hip commit: dd34ea95d6]
 2020-02-10 10:44:49 +05:30
vsytch e5243c1834 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>


[ROCm/hip commit: ef514eef71]
 2020-02-05 20:56:17 +05:30
Aryan Salmanpour adc9134318 code clean up 
[ROCm/hip commit: c8137263d6]
 2020-01-31 13:08:25 -05:00
Aryan Salmanpour 78a36b4fb8 [HIP][HIPIFY] Add some missing flags for cooperative launch and occupancy APIs 
[ROCm/hip commit: 6e867eacb6]
 2020-01-30 15:05:53 -05:00
satyanveshd e38db9fb6f Match Occupancy APIs syntax with CUDA (#1625) 
* Match Occupancy APIs syntax with CUDA and fix tests using these APIs


[ROCm/hip commit: fa98798b63]
 2020-01-29 13:05:53 -08:00
vsytch 1af35a6044 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.


[ROCm/hip commit: f72a669487]
 2020-01-27 16:37:00 -08:00
vsytch 95ee059bbb Update the HIP_TRSF_* flags to match their Cuda equivalents. (#1801) 
[ROCm/hip commit: 9cfada0f9d]
 2020-01-24 11:41:15 -08:00
mshivama c630cb57b2 SWDEV-220503: this_grid().thread_rank() gives incorrect result (#1808) 
* fix a minor bug while computing this.grid()::thread_rank()

[ROCm/hip commit: bed8f1c1b8]
 2020-01-24 16:23:28 +05:30
kpyzhov dabbde21c6 Don't use accelerated vector element access for hip-clang. (#1796) 
[ROCm/hip commit: 566adc4594]
 2020-01-15 18:17:08 -08:00
kpyzhov 4c457c2bb5 Add missing constructors for Scalar_accessor class. (#1792) 
[ROCm/hip commit: fae85cf6d2]
 2020-01-14 11:30:21 -08:00
Evgeny Mankov 3d22f829f5 [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


[ROCm/hip commit: a005a8550d]
 2020-01-10 13:47:18 +05:30
Maneesh Gupta 6ebf5ca991 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 b7803eb0c6.
- Revert "Fix rocFFT build failure (#1777)"
   This reverts commit 9c8c3df294.

[ROCm/hip commit: 00bd5d1cec]
 2020-01-08 15:11:58 +05:30
ansurya 9c8c3df294 Fix rocFFT build failure (#1777) 
Fixes SWDEV-217761

[ROCm/hip commit: 753277422a]
 2020-01-07 08:12:37 +05:30
Rahul Garg 327a45b18b Add hipBindTexture2D on NVCC path (#1773) 
[ROCm/hip commit: a5d7e7d8d3]
 2020-01-06 12:33:50 +05:30
Rahul Garg 86dbb13897 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.

[ROCm/hip commit: f3cafd5855]
 2020-01-06 12:33:23 +05:30
Evgeny Mankov 6ac4d18753 Merge pull request #1759 from emankov/master 
[HIP] Unify hipError_t (Step 2)

[ROCm/hip commit: 0dadb23327]
 2019-12-30 19:21:09 +03:00
Sarbojit2019 6d2ec032fe 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.

[ROCm/hip commit: aa4aea0754]
 2019-12-30 12:44:24 +05:30
Aryan Salmanpour ffea90f865 [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.

[ROCm/hip commit: 6968aeb841]
 2019-12-30 12:42:17 +05:30
Evgeny Mankov abef353b5b [HIP] Clean-up deprecated HIP error codes 
hipErrorMemoryAllocation -> hipErrorOutOfMemory
hipErrorInitializationError -> hipErrorNotInitialized
hipErrorMapBufferObjectFailed -> hipErrorMapFailed
hipErrorInvalidResourceHandle -> hipErrorInvalidHandle


[ROCm/hip commit: 4921678b6c]
 2019-12-23 17:01:35 +03:00
Yaxun (Sam) Liu d10837db9d Add macro __HIP_ENABLE_CUDA_WRAPPER_FOR_OPENMP__ (#1761) 
This is to allow force enable cuda wrapper for OpenMP for flexibility

[ROCm/hip commit: 3c90d57072]
 2019-12-23 19:24:54 +05:30
saleelk bb7fa73dcc Fix the return type of demangle function so that its compatible across ABIs (#1744) 
[ROCm/hip commit: 080b0b9a68]
 2019-12-23 19:11:40 +05:30
Alex Voicu 1f5ecc0f6a Fix late-coming issues. (#1724) 
Implementation for hipMemcpyWithStream.


[ROCm/hip commit: 75a11330aa]
 2019-12-23 19:11:24 +05:30
Maneesh Gupta 91f82210fb replace array designator C99 (#1694) 
* replace array designator C99

* Update texture_functions.h

Highlight valid and invalid values in texFormatToSize

Co-authored-by: Maneesh Gupta <maneesh.gupta@amd.com>


[ROCm/hip commit: 7d6634ce9d]
 2019-12-23 19:10:24 +05:30