AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,752 Commits 3 Branches 0 Tags
dec701df030d21f6da6eedd2f012169cd8572415
Commit Graph

3752 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Maneesh Gupta dec701df03 Merge pull request #1265 from gargrahul/fix_hip_porting_guide_texture_ref_use 
[docs]Fix texture reference APIs usage part
 2019-07-31 15:42:54 +00:00
Rahul Garg b9e6d72ee6 Add hip init in hipExtLaunchMultiKernelMultiDevice (#1263) 
* Add hip init in hipExtLaunchMultiKernelMultiDevice

* Add more logstatus for multiple return paths

* Fix missing i in function name
 2019-07-31 15:42:29 +00:00
Rahul Garg 0517c30507 Add HIP init in hipFuncGetAttributes (#1262) 
* Add HIP init in hipFuncGetAttributes

* [dtest]Remove explicit hip init call in hipFuncGetAttributes dtest
 2019-07-31 15:42:08 +00:00
Maneesh Gupta e1376699c3 Merge pull request #1270 from mangupta/ci_stablity 
[ci] Disable flaky hipMemoryAllocateCoherentDriver on CI for now
 2019-07-31 05:03:25 +00:00
ansurya 0f0b60f57d 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
 2019-07-31 05:02:35 +00:00
ansurya 50597e2085 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
 2019-07-31 05:02:20 +00:00
Maneesh Gupta 756d4ba1a0 [ci] Disable flaky hipMemoryAllocateCoherentDriver on CI for now 
Change-Id: Ib90dd390ed71d0b3867e5dc36a41988cc4d42a99
 2019-07-31 09:35:43 +05:30
Evgeny Mankov 707fc26ee7 Merge pull request #1268 from emankov/cuDNN 
[HIPIFY][DNN][doc] Populate cuDNN API doc with CUDA version field
 2019-07-30 20:55:08 +03:00
Evgeny Mankov c48fca494a [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.
 2019-07-30 20:53:57 +03:00
Rahul Garg ccaea193b2 [docs]Fix texture reference APIs usage part 2019-07-30 02:56:47 +05:30
Evgeny Mankov 0471e10208 Merge pull request #1261 from emankov/cuDNN 
[HIPIFY][SPARSE] Sync cuSPARSE 10.1 - HIP - HIPIFY (Step 2 of 2)
 2019-07-29 21:14:17 +03:00
Evgeny Mankov 18117a4ad1 [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
 2019-07-29 21:12:35 +03:00
Evgeny Mankov f37edda013 Merge pull request #1259 from emankov/cuDNN 
[HIPIFY][SPARSE] Sync cuSPARSE 10.1 - HIP - HIPIFY (Step 1 of 2)
 2019-07-26 21:35:52 +03:00
Evgeny Mankov 2adad9c68d [HIPIFY][SPARSE] Sync cuSPARSE 10.1 - HIP - HIPIFY (Step 1 of 2) 2019-07-26 21:34:36 +03:00
Evgeny Mankov fa5ea9e3c6 Merge pull request #1258 from emankov/cuDNN 
[HIPIFY][SPARSE][doc] Populate cuSPARSE API doc with CUDA version field
 2019-07-26 19:08:11 +03:00
Evgeny Mankov 6f6aa13448 [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
 2019-07-26 19:05:42 +03:00
Evgeny Mankov 1285425e91 Merge pull request #1256 from emankov/cuDNN 
[HIPIFY][FFT][doc] Populate cuFFT API doc with CUDA version field
 2019-07-25 19:34:50 +03:00
Evgeny Mankov 697c7d87d3 [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.
 2019-07-25 19:32:50 +03:00
Evgeny Mankov a1ab9aa9c4 Merge pull request #1255 from emankov/cuDNN 
[HIPIFY][BLAS][doc] Populate cuBlas API doc with CUDA version field
 2019-07-25 18:50:25 +03:00
Evgeny Mankov 667defc65d [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.
 2019-07-25 18:49:23 +03:00
Evgeny Mankov e01e405df8 Merge pull request #1253 from emankov/cuDNN 
[HIPIFY][doc] Fix typo
 2019-07-24 21:11:02 +03:00
Evgeny Mankov 7dfed2ad0d [HIPIFY][doc] Fix typo 2019-07-24 21:10:14 +03:00
Evgeny Mankov 1c9add54f3 Merge pull request #1252 from emankov/cuDNN 
[HIPIFY][doc] Fix typos
 2019-07-24 21:05:59 +03:00
Evgeny Mankov 4573177fe7 [HIPIFY][doc] Fix typos 2019-07-24 21:04:41 +03:00
Evgeny Mankov 071f03b521 Merge pull request #1251 from emankov/cuDNN 
[HIPIFY][doc] Populate Driver API doc with CUDA version field
 2019-07-24 20:53:57 +03:00
Evgeny Mankov 75c0dc9d8f [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.
 2019-07-24 20:52:42 +03:00
Aryan Salmanpour f3c4952f80 [hip][tests] add a unit test for using hipExtLaunchMultiKernelMultiDevice API (#1250) 2019-07-24 07:57:39 +00:00
Aaron Enye Shi b754de37c1 Add GFX908 specific changes to HIP (#1229) 
* Add GFX908 specific for HIP

* Fix missing __halfTest in hipTestNativeHalf
 2019-07-24 07:51:17 +00:00
Maneesh Gupta 75abc65e12 [dtests] Fix complex_loading_behavior.cpp build issues on nvcc path (#1242) 2019-07-24 07:49:39 +00:00
Aaron Enye Shi 0de4caa085 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
 2019-07-24 07:49:20 +00:00
Evgeny Mankov cde3d75fa4 Merge pull request #1249 from emankov/cuDNN 
[HIPIFY][doc] Update Readme.md
 2019-07-23 19:35:19 +03:00
Evgeny Mankov b8e4f93b5c [HIPIFY][doc] Update Readme.md 
+ 8.0.1 - is the latest supported clang version on Linux
+ Testing update
 2019-07-23 19:30:57 +03:00
Evgeny Mankov 4204c99cc5 Merge pull request #1248 from emankov/cuDNN 
HIPIFY] Clang 8.0.1 support
 2019-07-23 19:20:12 +03:00
Evgeny Mankov 91e461fcf2 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.
 2019-07-23 19:18:17 +03:00
Evgeny Mankov 543da8e8ae Merge pull request #1244 from emankov/cuDNN 
[HIPIFY][#1239] Fix an assert
 2019-07-22 22:18:58 +03:00
Evgeny Mankov d19fcbcde4 [HIPIFY][#1239] Fix an assert 2019-07-22 22:13:54 +03:00
Evgeny Mankov 866cc4e646 Merge pull request #1241 from emankov/cuDNN 
[HIPIFY][#941][fix] Workaround for an assert on forbidden option "--"
 2019-07-19 20:25:19 +03:00
Evgeny Mankov f5d6bb8267 [HIPIFY][#941][fix] Workaround for an assert on forbidden option "--" 
+ Fixes the following assert in debug version:
Assertion failed: (S.empty() || S[0] != '-') && "Option can't start with '-", file C:\GIT\LLVM\trunk-for-submits\llvm-project\llvm\lib\Support\CommandLine.cpp, line 440
+ DashDash option left declared in order to be listed in help.
 2019-07-19 20:23:17 +03:00
Yaxun (Sam) Liu d7aea38d74 Temporarily disable maxTexture1D in hipDeviceProp_t for VDI (#1237) 2019-07-19 15:38:32 +00:00
gilbertlee-amd 8ff7a99a4c Fix Typo HipHostMemory to HipHostMalloc (#1236) 2019-07-19 04:46:07 +00:00
Maneesh Gupta 888ccbc205 [hit] Workaround for %cc and %cxx mappings. (#1233) 
* [hit] Workaround for %cc and %cxx mappings.

HIP CMakeLists.txt modifies CMAKE_C_COMPILER and CMAKE_CXX_COMPILER.
This messes up any dtests that want to test against cc/c++.

So hardcode %cc to /usr/bin/cc and %cxx to /usr/bin/c++ for now till
we come up with a better solution.

Change-Id: I7dce93ce8360191e612a94e3a735e5612ac27ab5

* [hit] Add auto-variable %hip-path to syntax for BUILD_CMD

Change-Id: Id097a183fbce2b2c9691d0180d3304dd17a4e016
 2019-07-19 04:45:56 +00:00
cdevadas d5dba47804 Increased the number of implicit-kernarg bytes to 56 (#1217) 2019-07-19 04:45:34 +00:00
ansurya fa4d6b353a [HIP][Tests] Added new testcases for Module API (#1150) 
* [HIP][tests] New testcases for module api

* [HIP][Tests]Support for CUDA devices

* Updated tests as per latest master & test GetGlobal to work on all platforms
 2019-07-19 04:45:20 +00:00
wkwchau 38254caf7a Fixed bug of determine max block size in hipOccupancyMaxPotentialBlockSize (#1235) 2019-07-18 03:19:29 +00:00
ansurya 8e496c09d9 Add Max Texture 1D,2D,3D device properties (#1226) 
* Add Max Texture 1D,2D,3D device properties

* Corrected testcase to use enums defined in hipDeviceAttribute_t

* Added texture 1D,2D and 3D support for NVIDIA path
 2019-07-18 03:18:50 +00:00
ansurya 6b6258b84f UChar and UShort textures as Normalized Float (#1213) 
* UChar and UShort textures as Normalized Float

* UChar and UShort textures as Normalized Float for all float variants

* Handled uninitilaized texture format value
 2019-07-18 03:18:28 +00:00
ansurya 84f8441146 HIPCommander code cleanup (#1207) 
* HIPCommander code cleanup

* Removed non-used headerfiles

* Removed empty ifdef
 2019-07-18 03:18:15 +00:00
Rahul Garg 1dcf618d20 Fix HIP_VISIBLE_DEVICES order (#1184) 
* Fix HIP_VISIBLE_DEVICES order

* Fix device IDs mismatch

* Fix review comments- loop order and device range check

* Handle incomplete VISIBLE device env variable

* Revert "Handle incomplete VISIBLE device env variable"
 2019-07-18 03:18:04 +00:00
Aryan Salmanpour 034201f658 [hip] fix a bug where we parse kernel's arguments layout for a given kernel multiple times (#1232) 2019-07-17 07:29:07 +00:00
Evgeny Mankov b1fad7915b [HIPIFY][bash] Make 'find' sorted by extension (#1231) 
+ Source files are the first to go. It is needed for in-place hipification in order to avoid errors with included but already hipified header files.
+ More extensions support for batch processing.
 2019-07-17 07:28:54 +00:00