Alex Voicu
b859635575
This difference makes absolutely no sense.
...
[ROCm/hip commit: a85b0fe68e ]
2019-08-02 12:30:03 +03:00
wkwchau
c666fdaa08
Added query of hipDeviceAttributeHdpMemFlushCntl and hipDeviceAttribu… ( #1238 )
...
* Added query of hipDeviceAttributeHdpMemFlushCntl and hipDeviceAttributeHdpRegFlushCntl
* Added NVCC blocker for the hip*FlushCntl test cases
[ROCm/hip commit: e7447d5809 ]
2019-08-01 16:03:35 +00:00
Maneesh Gupta
87bc7183bf
Merge pull request #1277 from mangupta/nvcc_devprop
...
[nvcc] Populate missing fields in hipGetDeviceProperties
[ROCm/hip commit: adc95002c6 ]
2019-08-01 08:59:58 +00:00
Maneesh Gupta
bcd4ffb953
Merge pull request #1276 from vsytch/SWDEV-197675
...
[hip][tests] Don't use a hardcoded warp size, since it can be dynamically changed.…
[ROCm/hip commit: 79358e086a ]
2019-08-01 08:59:43 +00:00
Maneesh Gupta
77f847711c
Merge pull request #1275 from yxsamliu/fix-std
...
Fix -std=c++14 for windows
[ROCm/hip commit: be168102c2 ]
2019-08-01 08:59:27 +00:00
Maneesh Gupta
6ae756ccfd
Merge pull request #1243 from jeffdaily/master-stream-lock-fix
...
remove stream locks where it is safe to do so
[ROCm/hip commit: 859fb94f3d ]
2019-08-01 08:59:13 +00:00
wkwchau
7676b86f12
Added support of hipOccupancyMaxActiveBlocksPerMultiprocessor & hipOc… ( #1240 )
...
* Added support of hipOccupancyMaxActiveBlocksPerMultiprocessor & hipOccupancyMaxActiveBlocksPerMultiprocessorWithFlags APIs
* Taking into account of SGPR usage to determine the max active blocks in hipOccupancyMaxActiveBlocksPerMultiprocessor()
[ROCm/hip commit: 4b18b321f7 ]
2019-08-01 08:58:48 +00:00
Maneesh Gupta
1e92f785bc
[nvcc] Populate missing fields in hipGetDeviceProperties
...
Change-Id: Ie90e02674d503e385f144f1ead3d53ff7b49cecc
[ROCm/hip commit: 3ec381d729 ]
2019-08-01 13:16:39 +05:30
Vladislav Sytchenko
6837312da4
Don't use a hardcoded warp size, since it can be dynamically changed. Query it from the runtime instead.
...
[ROCm/hip commit: fd3b626386 ]
2019-07-31 17:04:31 -04:00
Yaxun (Sam) Liu
76ea65c212
Fix -std=c++14 for windows
...
[ROCm/hip commit: f467cb850e ]
2019-07-31 16:36:47 -04:00
Evgeny Mankov
357038ab51
Merge pull request #1274 from emankov/cuDNN
...
[HIP][doc] Populate CUDA Runtime API doc with CUDA version field
[ROCm/hip commit: 7809783a91 ]
2019-07-31 23:01:32 +03:00
Evgeny Mankov
2810475577
[HIP][doc] Populate CUDA Runtime API doc with CUDA version field
...
+ CUDA version - version in which API has appeared and (optional) last version before abandoning it; no value in case of earlier versions < 7.5.
+ Fix typos, add missing references.
[ROCm/hip commit: 77e9ade9bc ]
2019-07-31 22:59:05 +03:00
Maneesh Gupta
ba53d3f04c
Merge pull request #1269 from gargrahul/fix_ptr_attr_unkonwn_to_invalid
...
hipPointerGetAttributes- Change hipErrorUnknown to hipErrorInvalidValue
[ROCm/hip commit: a4407f13db ]
2019-07-31 15:43:06 +00:00
Maneesh Gupta
b0976644d2
Merge pull request #1265 from gargrahul/fix_hip_porting_guide_texture_ref_use
...
[docs]Fix texture reference APIs usage part
[ROCm/hip commit: dec701df03 ]
2019-07-31 15:42:54 +00:00
Rahul Garg
617a6d43dc
Add hip init in hipExtLaunchMultiKernelMultiDevice ( #1263 )
...
* Add hip init in hipExtLaunchMultiKernelMultiDevice
* Add more logstatus for multiple return paths
* Fix missing i in function name
[ROCm/hip commit: b9e6d72ee6 ]
2019-07-31 15:42:29 +00:00
Rahul Garg
d7973153ca
Add HIP init in hipFuncGetAttributes ( #1262 )
...
* Add HIP init in hipFuncGetAttributes
* [dtest]Remove explicit hip init call in hipFuncGetAttributes dtest
[ROCm/hip commit: 0517c30507 ]
2019-07-31 15:42:08 +00:00
Maneesh Gupta
0cb7c0c369
Merge pull request #1270 from mangupta/ci_stablity
...
[ci] Disable flaky hipMemoryAllocateCoherentDriver on CI for now
[ROCm/hip commit: e1376699c3 ]
2019-07-31 05:03:25 +00:00
ansurya
1aee311e6a
Testcase to validate signed/unsigned char,short as normalized float ( #1267 )
...
* Testcase to validate signed/unsigned char,short as normalized float
* corrected test_common.cpp file path
[ROCm/hip commit: 0f0b60f57d ]
2019-07-31 05:02:35 +00:00
ansurya
357c361949
Add HSA_PATH to hip_Includes in cmake and hipconfig ( #1260 )
...
* Add HSA_PATH to hip_Includes in cmake and hipconfig
* HSA_PATH to CACHE path,checks for HSA include path
* Removed new lines at EOF
[ROCm/hip commit: 50597e2085 ]
2019-07-31 05:02:20 +00:00
Maneesh Gupta
877a201ce8
[ci] Disable flaky hipMemoryAllocateCoherentDriver on CI for now
...
Change-Id: Ib90dd390ed71d0b3867e5dc36a41988cc4d42a99
[ROCm/hip commit: 756d4ba1a0 ]
2019-07-31 09:35:43 +05:30
Rahul Garg
0009dc1067
Change hipErrorUnknown to hipErrorInvalidValue
...
[ROCm/hip commit: 483aab031f ]
2019-07-31 00:28:30 +05:30
Evgeny Mankov
9fbb45ba91
Merge pull request #1268 from emankov/cuDNN
...
[HIPIFY][DNN][doc] Populate cuDNN API doc with CUDA version field
[ROCm/hip commit: 707fc26ee7 ]
2019-07-30 20:55:08 +03:00
Evgeny Mankov
632bb1b190
[HIPIFY][DNN][doc] Populate cuDNN API doc with CUDA version field
...
+ CUDA version - version in which API has appeared and (optional) last version before abandoning it; no value in case of earlier versions < 7.5.
+ Fix typos.
[ROCm/hip commit: c48fca494a ]
2019-07-30 20:53:57 +03:00
Rahul Garg
a53639b073
[docs]Fix texture reference APIs usage part
...
[ROCm/hip commit: ccaea193b2 ]
2019-07-30 02:56:47 +05:30
Evgeny Mankov
2b60a5fa2a
Merge pull request #1261 from emankov/cuDNN
...
[HIPIFY][SPARSE] Sync cuSPARSE 10.1 - HIP - HIPIFY (Step 2 of 2)
[ROCm/hip commit: 0471e10208 ]
2019-07-29 21:14:17 +03:00
Evgeny Mankov
f7ef437302
[HIPIFY][SPARSE] Sync cuSPARSE 10.1 - HIP - HIPIFY (Step 2 of 2)
...
+ Add undocumented but presented in cusparse.h functions since CUDA 10.1 Update 1
[ROCm/hip commit: 18117a4ad1 ]
2019-07-29 21:12:35 +03:00
Evgeny Mankov
a8ec74ba80
Merge pull request #1259 from emankov/cuDNN
...
[HIPIFY][SPARSE] Sync cuSPARSE 10.1 - HIP - HIPIFY (Step 1 of 2)
[ROCm/hip commit: f37edda013 ]
2019-07-26 21:35:52 +03:00
Evgeny Mankov
ae32b99c20
[HIPIFY][SPARSE] Sync cuSPARSE 10.1 - HIP - HIPIFY (Step 1 of 2)
...
[ROCm/hip commit: 2adad9c68d ]
2019-07-26 21:34:36 +03:00
Evgeny Mankov
ff1f884184
Merge pull request #1258 from emankov/cuDNN
...
[HIPIFY][SPARSE][doc] Populate cuSPARSE API doc with CUDA version field
[ROCm/hip commit: fa5ea9e3c6 ]
2019-07-26 19:08:11 +03:00
Evgeny Mankov
26923a8644
[HIPIFY][SPARSE][doc] Populate cuSPARSE API doc with CUDA version field
...
+ CUDA version - version in which API has appeared and (optional) last version before abandoning it; no value in case of earlier versions < 7.5.
+ Fix typos
[ROCm/hip commit: 6f6aa13448 ]
2019-07-26 19:05:42 +03:00
Evgeny Mankov
a2c99270a4
Merge pull request #1256 from emankov/cuDNN
...
[HIPIFY][FFT][doc] Populate cuFFT API doc with CUDA version field
[ROCm/hip commit: 1285425e91 ]
2019-07-25 19:34:50 +03:00
Evgeny Mankov
5787c06d10
[HIPIFY][FFT][doc] Populate cuFFT API doc with CUDA version field
...
CUDA version - version in which API has appeared and (optional) last version before abandoning it; no value in case of earlier versions < 7.5.
[ROCm/hip commit: 697c7d87d3 ]
2019-07-25 19:32:50 +03:00
Evgeny Mankov
0ce3cf3a0e
Merge pull request #1255 from emankov/cuDNN
...
[HIPIFY][BLAS][doc] Populate cuBlas API doc with CUDA version field
[ROCm/hip commit: a1ab9aa9c4 ]
2019-07-25 18:50:25 +03:00
Evgeny Mankov
251810f38b
[HIPIFY][BLAS][doc] Populate cuBlas API doc with CUDA version field
...
CUDA version - version in which API has appeared and (optional) last version before abandoning it; no value in case of earlier versions < 7.5.
[ROCm/hip commit: 667defc65d ]
2019-07-25 18:49:23 +03:00
Evgeny Mankov
cc470ab72d
Merge pull request #1253 from emankov/cuDNN
...
[HIPIFY][doc] Fix typo
[ROCm/hip commit: e01e405df8 ]
2019-07-24 21:11:02 +03:00
Evgeny Mankov
598fba997e
[HIPIFY][doc] Fix typo
...
[ROCm/hip commit: 7dfed2ad0d ]
2019-07-24 21:10:14 +03:00
Evgeny Mankov
d547ed81a8
Merge pull request #1252 from emankov/cuDNN
...
[HIPIFY][doc] Fix typos
[ROCm/hip commit: 1c9add54f3 ]
2019-07-24 21:05:59 +03:00
Evgeny Mankov
0026feb920
[HIPIFY][doc] Fix typos
...
[ROCm/hip commit: 4573177fe7 ]
2019-07-24 21:04:41 +03:00
Evgeny Mankov
2b06f28c88
Merge pull request #1251 from emankov/cuDNN
...
[HIPIFY][doc] Populate Driver API doc with CUDA version field
[ROCm/hip commit: 071f03b521 ]
2019-07-24 20:53:57 +03:00
Evgeny Mankov
deaa48acca
[HIPIFY][doc] Populate Driver API doc with CUDA version field
...
CUDA version - version in which API has appeared and (optional) last version before abandoning it; no value in case of earlier versions < 7.5.
[ROCm/hip commit: 75c0dc9d8f ]
2019-07-24 20:52:42 +03:00
Aryan Salmanpour
563b385ad6
[hip][tests] add a unit test for using hipExtLaunchMultiKernelMultiDevice API ( #1250 )
...
[ROCm/hip commit: f3c4952f80 ]
2019-07-24 07:57:39 +00:00
Aaron Enye Shi
2e45e37c51
Add GFX908 specific changes to HIP ( #1229 )
...
* Add GFX908 specific for HIP
* Fix missing __halfTest in hipTestNativeHalf
[ROCm/hip commit: b754de37c1 ]
2019-07-24 07:51:17 +00:00
Maneesh Gupta
57289b2d4c
[dtests] Fix complex_loading_behavior.cpp build issues on nvcc path ( #1242 )
...
[ROCm/hip commit: 75abc65e12 ]
2019-07-24 07:49:39 +00:00
Aaron Enye Shi
85fa58c117
Fix hipMemcpy-size test running out of Host Mem ( #1224 )
...
* Fix hipMemcpy-size test running out of Host Mem
The hipMemcpy-size uses a maxElem calculated from the total GPU mem /8. Then it will allocate 4 times that amount of host memory. This tests begins failing when there is not enough host memory, such as on systems with 32GB GPU mem, and 16GB RAM. This fixes the test if not enough host memory is available on the system.
* Add windows support to hipMemcpy-size fix
* avoid linking extra libs for windows
* HIPMemcpy-size Remove freeCPU including swap
[ROCm/hip commit: 0de4caa085 ]
2019-07-24 07:49:20 +00:00
Evgeny Mankov
b108a66459
Merge pull request #1249 from emankov/cuDNN
...
[HIPIFY][doc] Update Readme.md
[ROCm/hip commit: cde3d75fa4 ]
2019-07-23 19:35:19 +03:00
Evgeny Mankov
4c704f9b44
[HIPIFY][doc] Update Readme.md
...
+ 8.0.1 - is the latest supported clang version on Linux
+ Testing update
[ROCm/hip commit: b8e4f93b5c ]
2019-07-23 19:30:57 +03:00
Evgeny Mankov
f513a9c320
Merge pull request #1248 from emankov/cuDNN
...
HIPIFY] Clang 8.0.1 support
[ROCm/hip commit: 4204c99cc5 ]
2019-07-23 19:20:12 +03:00
Evgeny Mankov
14ee787b43
HIPIFY] Clang 8.0.1 support
...
+ Tested on Windows and Linux;
+ Provide patch for clang's bug 38811;
+ Update Readme.md accordingly.
P.S.
With the next 9.0.0 release patches for Windows won't be needed, cause all fixes will be there.
[ROCm/hip commit: 91e461fcf2 ]
2019-07-23 19:18:17 +03:00
Evgeny Mankov
ecc0b6009a
Merge pull request #1244 from emankov/cuDNN
...
[HIPIFY][#1239 ] Fix an assert
[ROCm/hip commit: 543da8e8ae ]
2019-07-22 22:18:58 +03:00
Evgeny Mankov
3ad30304a4
[HIPIFY][ #1239 ] Fix an assert
...
[ROCm/hip commit: d19fcbcde4 ]
2019-07-22 22:13:54 +03:00