Граф коммитов

891 Коммитов

Автор SHA1 Сообщение Дата
Rahul Garg 25a5ca94de Merge pull request #1582 from amd-lthakur/hipExtMLK
Adding a directed test case for hipExtModuleLaunchKernel() api.

[ROCm/hip commit: 4739e68bbe]
2019-10-31 17:13:26 -07:00
Rahul Garg b68c8d2f60 Formatting changes
[ROCm/hip commit: 55f2a38120]
2019-10-30 18:12:51 -07:00
Rahul Garg 8429e15052 Formatting changes ,variable name and check update
[ROCm/hip commit: 4ab71216b4]
2019-10-30 18:09:21 -07:00
Rahul Garg 7e742b1216 Merge pull request #1515 from ansurya/tex_unbind_issue_fix
Fix undefined ref to hipUnbindTexture for texture types

[ROCm/hip commit: ba8105e0cd]
2019-10-30 17:54:15 -07:00
Rahul Garg 70449cfa92 Revert "Fix occupany APIs (#1560)"
This reverts commit 4f23f9cb18.


[ROCm/hip commit: e4a1e44162]
2019-10-29 11:41:08 -07:00
Evgeny Mankov 17fd872099 [HIPIFY][tests] Rename the ambiguous call as well
[ROCm/hip commit: 70c5072302]
2019-10-25 16:07:31 +03:00
Evgeny Mankov 536376b341 [HIPIFY][tests] Fix ambiguous call to cusparseGetErrorString declared in cusparse.h
[ROCm/hip commit: 0410d5dcd2]
2019-10-25 16:04:20 +03:00
Anusha Godavarthy Surya 5c77b7d19a Merge branch 'master' into tex_unbind_issue_fix
[ROCm/hip commit: 03623cc3f1]
2019-10-25 15:54:25 +05:30
amd-lthakur 5e11495936 Excluded the test case for nvcc platform
[ROCm/hip commit: 4239c94fe5]
2019-10-25 15:52:11 +05:30
Anusha Godavarthy Surya 196bdea9c0 merge from master
[ROCm/hip commit: 5f47e99ffe]
2019-10-25 15:52:09 +05:30
Rahul Garg 849ae2bff0 [dtest] Fix hipMemset2D test (#1579)
Reverts changes made in #1399. This is a RT api test. For testing hipMemAllocPitch , a new test should be written and that should use correct memset API.

[ROCm/hip commit: 12e1a86ec1]
2019-10-25 15:44:05 +05:30
Anusha Godavarthy Surya 3007505d30 Merge branch 'master' into tex_unbind_issue_fix
[ROCm/hip commit: 259d8b4cdf]
2019-10-25 15:36:55 +05:30
amd-lthakur 158cab3bb7 Refactored the file as suggested
[ROCm/hip commit: 564418c308]
2019-10-25 10:44:38 +05:30
amd-lthakur 629a933b63 Update matmul.cpp
[ROCm/hip commit: 318df5c36b]
2019-10-25 09:22:07 +05:30
amd-lthakur 4b771db194 Update hipExtModuleLaunchKernel.cpp
[ROCm/hip commit: cd25149225]
2019-10-25 09:19:49 +05:30
satyanveshd 4f23f9cb18 Fix occupany APIs (#1560)
Addresses SWDEV-205006 

[ROCm/hip commit: af351d7e1b]
2019-10-24 17:44:47 +05:30
amd-lthakur 297a20eac7 Adding a directed test case for hipExtModuleLaunchKernel() api.
[ROCm/hip commit: 8b496e4715]
2019-10-24 15:06:28 +05:30
Rahul Garg 66f0280f0b Merge pull request #1559 from vsytch/win10_aligned_alloc
Fixes for hipMemcpy_simple on Windows

[ROCm/hip commit: fe5f7d4245]
2019-10-23 13:10:59 -07:00
Evgeny Mankov d39793f0f7 [HIPIFY] Disable delayed template parsing
By implicit unconditional passing -fno-delayed-template-parsing option (which appeared in LLVM 3.8.0, thus doesn't need compatibility wrapping) to hipify-clang.

[Reason] To parse uncalled template functions otherwise they are not parsed without calling, thus not hipified.

Affects cub_03.cu test, which has uncalled global template function.


[ROCm/hip commit: b6e6f12b54]
2019-10-22 19:07:37 +03:00
Evgeny Mankov 9822351686 [HIPIFY][#1569] Fix
[ROCm/hip commit: 6f88c81a78]
2019-10-22 11:08:37 +03:00
Evgeny Mankov a9b05f246b [HIPIFY][tests] Set max clang's CudaArch for corresponding CUDA major.minor version
[Reason] To support maximum CUDA features in offline tests

+ Add defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 600 restriction for atomicAdd on doubles in atomics.cu.
  So if LLVM < 7 and --cuda-gpu-arch doesn't work, __CUDA_ARCH__ is unset too (350 by default in clang);
  if LLVM >= 7 --cuda-gpu-arch is used and __CUDA_ARCH__ is set based on it.


[ROCm/hip commit: 39e7d213cf]
2019-10-21 17:50:00 +03:00
Evgeny Mankov f345ec8c58 [HIPIFY][tests] Set max clang's CudaArch for corresponding CUDA version
[Reason] To support maximum CUDA features in offline tests

+ Add CUDA_VERSION >= 800 restriction for atomics.cu

[TODO] Find a way to use or exclude atomicAdd for doubles if LLVM < 7, because
LLVM 6.0.1 and older do not use --cuda-gpu-arch in clang's Driver code at all (option is only declared)


[ROCm/hip commit: 14b4df126c]
2019-10-21 15:51:25 +03:00
Evgeny Mankov 57b2e130e0 [HIPIFY][tests] Set -I for CUDA path instead of --cuda-path for LLVM < 4
[ROCm/hip commit: 6cfea9b600]
2019-10-20 20:08:56 +03:00
Evgeny Mankov 9ec744aaae [HIPIFY][tests] Exclude all CUB tests if CUDA_CUB_ROOT_DIR is not set
[ROCm/hip commit: ccb075b1db]
2019-10-20 20:03:18 +03:00
Vladislav Sytchenko 05cf0313ce Remove extra #endif.
[ROCm/hip commit: 664b115c44]
2019-10-18 16:40:29 -04:00
Evgeny Mankov 376037abfc [HIPIFY][tests] Test clean-up
[ROCm/hip commit: 82adc93e69]
2019-10-18 18:55:52 +03:00
Evgeny Mankov 55e2ef4c7a [HIPIFY][CUB][#1460] Add "using namespace cub" translation support
+ Add cub_03.cu


[ROCm/hip commit: 98874c0e7f]
2019-10-18 18:51:40 +03:00
Vladislav Sytchenko fd17d3b737 _aligned_malloc() on Windows first takes size, then alignment, which is the opposite of how the similar function behaves on Linux. Memory allocated by it also has to be freed using _aligned_free(), unlike Linux where we can use regular free().
Edit aligned_alloc() macro and add a aligned_free() one to align with the above behaviour.


[ROCm/hip commit: 8f0a226660]
2019-10-17 18:58:32 -04:00
Rahul Garg f82e9cd090 Merge pull request #1544 from vsytch/master
QoL changes to the hipMemset family

[ROCm/hip commit: e1aac060da]
2019-10-16 18:54:20 -07:00
Evgeny Mankov 60c5f0a6c7 [HIPIFY][CUB][#1460] Add cub:: namespace support in TemplateInstantiation of cudaLaunchKernel
+ Update cub_02.cu test accordingly


[ROCm/hip commit: edfd05a86d]
2019-10-16 19:02:13 +03:00
Vladislav Sytchenko 779d723ac2 hipMemset2D and hipMemset3D tests should be passing by default.
[ROCm/hip commit: c747b77ac1]
2019-10-16 11:02:38 -04:00
Evgeny Mankov dcbe9432bd [HIPIFY][CUB][#1460] Implement cubFunctionTemplateDecl matcher
+ Add cub_02.cu test
+ Partial fixes #1460


[ROCm/hip commit: 6960574850]
2019-10-16 13:08:11 +03:00
vsytch eaa616bf6d Update hipMathFunctions, hipTestHalf and hipTestNativeHalf tests to support Navi10 and Navi14. (#1545)
[ROCm/hip commit: 2fb734ef5f]
2019-10-16 10:51:48 +05:30
Vladislav Sytchenko 948dd510eb In the hipMemset2D and hipMemset3D tests synchronize with the default stream after performing an async memset.
[ROCm/hip commit: f5af263aba]
2019-10-15 17:15:49 -04:00
Vladislav Sytchenko 6180a9edb3 Update indentation in the hipMemset3D test. Replace all tabs with four spaces.
[ROCm/hip commit: 346bfa90d6]
2019-10-15 15:29:14 -04:00
Vladislav Sytchenko 5a29d10dbb Add async subtest to hipMemSet3D
[ROCm/hip commit: 00425bdf3d]
2019-10-15 14:24:04 -04:00
Vladislav Sytchenko 28089f61b6 hipMemset2D test should pass only if both async and sync subtests pass.
[ROCm/hip commit: 3db2ecc52b]
2019-10-15 14:20:14 -04:00
Evgeny Mankov 44ca50dfd0 [HIPIFY][tests] Exclude tests for the libs, which are not defined in cmake command line
+ affects cuDNN and CUB tests, paths to libraries of which are defined by CUDA_DNN_ROOT_DIR and CUDA_CUB_ROOT_DIR
+ Warn about excluding and why, for instance:
  "WARN: cuDNN tests are excluded due to unset CUDA_DNN_ROOT_DIR"


[ROCm/hip commit: 3444834e3a]
2019-10-15 14:20:23 +03:00
Anusha Godavarthy Surya e74d2cff3f Added unbind texture to samples and tests
[ROCm/hip commit: d5b1e887e9]
2019-10-15 11:34:15 +05:30
Evgeny Mankov d174cad0aa [HIPIFY][CUB] Add missing unit test
[ROCm/hip commit: 92fb5a3a94]
2019-10-14 12:03:20 +03:00
Evgeny Mankov 3deccebb07 [HIPIFY][CUB] Initial support (hipify-clang only)
+ Add one matcher (will be more)
+ Update Maps and Statistics
+ Add cub_01.cu unit test
+ Update lit harness to support standalone CUB
+ Update README.md
+ Update hipify-perl (only CUB header is supported for now)

[IMPORTANT]
clang (and hipify-clang) works correctly only with official NVLabs version on GitHub.
Compilation of CUB from official CUDA release has conflicts with THRUST.
Thus, to compile CUB sources, option "-I" should be specified to the cloned CUB from NVLAB on GitHub.


[ROCm/hip commit: 277d3b8369]
2019-10-14 11:55:55 +03:00
Jatin Chaudhary adf925d497 Re enable test RTC (#1516)
Adding target resolution in hiprtc tests and reenable them.

[ROCm/hip commit: 32eb6d3bec]
2019-10-10 19:59:55 +05:30
ansurya b37210badc Fix for directed tests failure (#1511)
directed_tests/runtimeApi/module/hipLaunchCooperativeKernel.tst - Disabling test temporarily until driver support is available.
directed_tests/runtimeApi/memory/hipArray.tst - Disabling test temporarily to reimplement it correctly.

[ROCm/hip commit: 87834500b9]
2019-10-10 19:58:41 +05:30
Evgeny Mankov b4d99584dc [HIPIFY][test] Update allocators.cu test
[ROCm/hip commit: 88cb3504ff]
2019-10-10 17:20:41 +03:00
Anusha Godavarthy Surya 04080d4bb1 Fix undefine ref to hipUbindTexture for texture types
[ROCm/hip commit: af5f195e46]
2019-10-09 16:26:06 +05:30
Evgeny Mankov 69ea727e92 [HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace
+ Modify CUDA2HIP_perl for the fix
+ Add ns_kernel_launch.cu test
+ Update hipify-perl by hipify-clang -perl


[ROCm/hip commit: 3286ffdfc0]
2019-10-08 15:58:48 +03:00
ansurya 66e94b1b1f Added new Memory API's (#1399)
Added new memory API's hipMemAllocPitch, hipMemAllocHost, hipMemsetD16, hipMemsetD16Async, hipMemsetD8Async
Modified to support all scenarios hipMemcpyParam2DAsync, hipMemcpyParam2D.


[ROCm/hip commit: ba9c6e13e4]
2019-10-04 13:36:31 +05:30
Evgeny Mankov eab4a41336 [HIPIFY] Return to wrapping with HIP_KERNEL_NAME(...) macro of a template instantiation kernel launch
[REASON]

1. hip-clang is fine with the templated kernel launch, brackets are unneeded: HIP_KERNEL_NAME(...) __VA_ARGS__
2. HCC is not, thus: HIP_KERNEL_NAME(...) (__VA_ARGS__)

[TODO] Clean-up entirely kernel name wrapping when HCC is finally obsolete.

+ Update perl generation, hipify-perl, and affected tests accordingly.


[ROCm/hip commit: 6bb9913e8a]
2019-10-02 16:01:07 +03:00
Evgeny Mankov 8e6ab7a6c0 Merge pull request #1492 from emankov/master
[HIPIFY][#1490][fix] Populate the list of supported device atomic functions

[ROCm/hip commit: 108992428d]
2019-10-01 14:00:07 +03:00
Evgeny Mankov 3652d77965 [HIPIFY][#1490][fix] Populate the list of supported device atomic functions
+ Update hipify-perl accordingly
+ Add atomics.cu test on all atomics


[ROCm/hip commit: b5f17e8ff0]
2019-10-01 13:57:46 +03:00