Граф коммитов

1702 Коммитов

Автор SHA1 Сообщение Дата
Sun, Peng 7e9cfda45e Additional GGL make_kernel_functor_* macros, contributed by Alex
Change-Id: I01aabb7d2b5418fcefb1bbf78eb5d1888dbc5c96


[ROCm/hip commit: fd36303c24]
2017-06-14 11:10:52 -05:00
Rahul Garg a8a8b2c888 Validity check of input arguments in Ipc Mem APIs
Change-Id: Ia48e949d19f354f10c7e44cc2457fd4154bf6d76


[ROCm/hip commit: ba51d7f676]
2017-06-14 15:18:57 +05:30
Maneesh Gupta 77804112c6 Bump HIP base version to 1.2
Change-Id: I8ecc164afed4383f78579ed86a5c8c11a73b0780


[ROCm/hip commit: 901538da77]
2017-06-14 09:45:46 +05:30
Sandeep Kumar 7b3f0eb15f Add peer2peer bandwidth and latency test
Change-Id: I6d88e4aa9f6e64096af16579eebef4740734203e


[ROCm/hip commit: c17ab84882]
2017-06-14 09:44:56 +05:30
Evgeny Mankov df7cbf0a1a [HIPIFY] Initial sync HIPIFY with HIP by CUDA Driver API functions.
+ CUDA_Driver_API_functions_supported_by_HIP.md update.
+ Initial update of HIPIFY with CUDA driver API functions:
  1.Error Handling, 2.Initialization, 3.Version Management, 5-6.Device Management, 7.Primary Context, 8-9.Context, 10.Module Management, 11.Memory Management.
+ Sync HIP functions against CUDA Driver and Runtime API functions.
+ Typo fixes.

ToDo: 12-30 modules of CUDA Driver API.


[ROCm/hip commit: f805bd0c1d]
2017-06-13 20:25:11 +03:00
Rahul Garg 0e4dbe0b2f Input args NULL check in hipChooseDevice
Change-Id: I1a7b8cded2f81d739645bbf3dab2f04bb9c3c796


[ROCm/hip commit: a833b9a704]
2017-06-13 13:35:50 +05:30
Rahul Garg aaa09cbf1c Update P2P test for using memcpy and kernel tests
Change-Id: Ib0f8fc9425e6e85fd11d7d02395c52bc713dcb37


[ROCm/hip commit: a9449533a1]
2017-06-12 11:53:25 +05:30
Maneesh Gupta e69bd819d5 Updated RELEASE.md
Change-Id: Ic451612555c66f3ed7131514fc97fcc41091370a


[ROCm/hip commit: ad33c9406a]
2017-06-12 11:20:28 +05:30
Maneesh Gupta 5a2d48117d Update directed tests README.md
Change-Id: I395245454d376508f04e5a4a62c8933895cb3867


[ROCm/hip commit: b850a08d99]
2017-06-12 11:19:55 +05:30
Patrick Flick 3b5222dc42 fix typo
[ROCm/hip commit: 5dfe207eb9]
2017-06-12 10:15:27 +05:30
Maneesh Gupta fba97f5d36 Merge branch hipify-updates into amd-develop
Change-Id: I13d8750027a2a8787e4eb2e1ed525cf69d14b805


[ROCm/hip commit: 5977a2e8b9]
2017-06-12 10:10:19 +05:30
Maneesh Gupta ce0ecfd067 Initial implementation of hipify-cmakefile
Change-Id: Id365da9f887b5c3409639f000b430d093fd4f6b3


[ROCm/hip commit: 5339320485]
2017-06-12 09:57:17 +05:30
Sun, Peng 47921e39d2 Fix error related to undefined reference of __get_dynamicgroupbaseptr().
Change-Id: I14951e1725e35dd5f5e53805f81cdb58661f59f2


[ROCm/hip commit: 43df5ba660]
2017-06-08 19:24:32 -05:00
Sun, Peng 8b14507650 Add clang version guard so the hip_fp16.h header won't be picked up by gcc
Change-Id: Ia21335a455bc93210901b44bc8c76a7f4a385b55


[ROCm/hip commit: 06816fb68b]
2017-06-08 19:24:32 -05:00
Ben Sander ef7c9be9c6 Use amHostCoherentFlag. Requires new HCC version.
[ROCm/hip commit: 99e9c7cca5]
2017-06-07 09:06:40 -05:00
Maneesh Gupta cd3beb8c66 hip_hcc package: add libstdc++-static as a rpm dependency
Change-Id: I83a79353492a6be3d788b7c0ce4a8f3aa740d9d9


[ROCm/hip commit: 6b768c2f0a]
2017-06-07 15:50:28 +05:30
Maneesh Gupta 59a792d892 hipMemcpy-size test: reduce max size to make it work correctly on nvcc path
Change-Id: I9ce9f5a9e141ffd8ddf961269010b33358e02771


[ROCm/hip commit: 1c93d8592e]
2017-06-07 15:25:54 +05:30
Maneesh Gupta ee92e19e7a hipDeviceMemcpy test: make it functional on nvcc path
Change-Id: Id10c79b48747ed701adbd0a233c53cd60cfa743b


[ROCm/hip commit: e6cafbf342]
2017-06-07 15:24:44 +05:30
Maneesh Gupta 7213c7a1ad p2p_copy_coherency test: gracefully handle single gpu case
Change-Id: I216663f67ef58c673136332635dab8b57079b909


[ROCm/hip commit: 1efb6ce994]
2017-06-07 15:23:37 +05:30
Ben Sander 1d1e50fa77 Enable HCC_OPT_FLUSH=1.
Requires appropriate HCC with this support   :
commit 38e392b517a46a09a3b1c8f388e6a0db3741c510


[ROCm/hip commit: ac634bf334]
2017-06-07 00:15:05 -05:00
Sun, Peng 3f9b16c397 Improve HIP kernel names, attributes and codegen, contributed by Alex Voicu
Change-Id: I2cafbdc5a98e26c7f4fad84739c915e7dc09993c


[ROCm/hip commit: a9808961bd]
2017-06-05 11:39:00 -05:00
Ben Sander 65f91dbb0d Enable HIP_SYNC_NULL_STREAM=0 optimization.
[ROCm/hip commit: decf3eee18]
2017-06-05 08:50:41 -05:00
Ben Sander 445042f916 Fix HIP_SYNC_NULL_STREAM=0 mode.
- Fix null-stream sync
- hipStreamDestroy of null stream returns hipErrorInvalidResourceHandle
- Update documentation.
- Add tests for null stream sync, hipEventElapsedTime.
- Rename internal enum hipEventStatusRecorded to hipEventStatusComplete
- refactor hipStreamWaitEvent to streamline control-flow


[ROCm/hip commit: 39c18e5e5f]
2017-06-05 08:50:22 -05:00
Ben Sander f3950e0748 Update tests.
Fix some NVCC issues.
Add hipStreamSync2, record_event tests.


[ROCm/hip commit: 8ce6d17983]
2017-06-04 20:18:37 -05:00
Ben Sander a1bdd5f585 Update tests, add p2p coherency test.
[ROCm/hip commit: d5c1616324]
2017-06-03 17:11:34 -05:00
Aditya Atluri 47ec040140 added half data type and vector destructors
1. Added half data types to hip_fp16.h
2. Added destructor to vector data types

Change-Id: Id5ae76a663bb90a4bde2839ec79c58fbaee5072f


[ROCm/hip commit: cb7c4c423c]
2017-06-02 11:19:33 -05:00
emankov 737e0cc93e [HIPIFY] annotation
[ROCm/hip commit: ccc4cd1a3e]
2017-06-02 16:33:48 +03:00
emankov ca707fe693 [HIPIFY] rename legacy hipify perl script and its usage to hipify-perl
[ROCm/hip commit: 4d035caedf]
2017-06-02 16:30:43 +03:00
Evgeny Mankov 0c12f09ba5 [HIPIFY] All CUDA 8.0.44 API functions update
(for both Driver and Runtime APIs)

1) P2P
cuDeviceGetP2PAttribute   cudaDeviceGetP2PAttribute

2) Memory Mngmnt
cuMemPrefetchAsync        cudaMemPrefetchAsync
cuMemAdvise               cudaMemAdvise
cuMemRangeGetAttribute    cudaMemRangeGetAttribute
cuMemRangeGetAttributes   cudaMemRangeGetAttributes

3) Streams (Driver API only, no analogues in Runtime API)
cuStreamWaitValue32
cuStreamWaitValue32
cuStreamWriteValue32

4) Texture Reference Mngmnt (Driver API only, no analogues in Runtime API)
cuTexRefSetBorderColor
cuTexRefGetBorderColor


[ROCm/hip commit: 4a5484c616]
2017-06-01 21:08:33 +03:00
Siu Chi Chan cc54bc4d85 fix atomicCAS:remove load for the return value after CAS
[ROCm/hip commit: 741eb844fe]
2017-05-31 15:20:19 -04:00
Evgeny Mankov 7a3befc555 [HIP] [HIPIFY] CUDA Driver API 8.0.44 JIT options support.
[ROCm/hip commit: 6e99e388ea]
2017-05-31 18:55:29 +03:00
Maneesh Gupta 404c3f6751 Fix hipMemoryAllocate test for single GPU
Change-Id: If121c18ab490ba125dc689ffc08a8839fd280c38


[ROCm/hip commit: 502a74fcd6]
2017-05-31 10:16:57 +05:30
Maneesh Gupta be2c61b72a Disable rcbrtf, scalblnf, scalbnf in single precision device test
Change-Id: I8a250a64a0cb05132d022a11d9766ced9cdf11a7


[ROCm/hip commit: 5cdd1b2bf5]
2017-05-31 10:16:19 +05:30
Maneesh Gupta ed41fcd51a Disable rcbrt, scalbln and scalbn double precision device test
Change-Id: I46bd895701c46d3592b553090cafba99e41a2e2d


[ROCm/hip commit: 4919863d3e]
2017-05-31 10:15:41 +05:30
Sandeep Kumar ee62cf4869 Add readme for inline asm and unroll cookbook samples
Change-Id: I71b7a5652c3dad181c5df60ab0dd1b81d79f1bfb


[ROCm/hip commit: 0154c97ddd]
2017-05-31 09:25:50 +05:30
Sandeep Kumar 96a7f1853e Add inline asm hip directed tests for v_add and v_mac
Change-Id: Ie5ace2e42d5da89b16e040537df2bb13d3883c6d


[ROCm/hip commit: 830f2b100d]
2017-05-31 09:25:40 +05:30
Sandeep Kumar 1859451523 Add unroll and inline asm cookbook samples
Change-Id: Ie5a0fbb01b7fca82959090d89299533d49e092f1


[ROCm/hip commit: e4f0b28bb9]
2017-05-31 09:25:35 +05:30
Sandeep Kumar a28399f456 Print msg for single gpu
Change-Id: I2d23c73542add8973990ba96592016726994422e


[ROCm/hip commit: dfcba01db6]
2017-05-31 09:25:17 +05:30
Ben Sander 59833bea80 Set event->_stream on hipHccModuleLaunchKernel path if start/stop used
Ensure _stream is always non-null in recorded events.
Fixes isDefaultStream fault.


[ROCm/hip commit: cb60763737]
2017-05-30 21:55:46 -05:00
Evgeny Mankov f99ab93b61 [HIPIFY] Add the rest CUDA Runtime API 8.0.44 Data structures.
+ sync with corresponding CUDA Driver API Data structures.

P.S.
There is no any new changes in CUDA Runtime API 8.0.61 Data structures since 8.0.44.


[ROCm/hip commit: 063539308e]
2017-05-30 19:45:59 +03:00
Evgeny Mankov 8a05cf882f [HIPIFY] Add the rest CUDA Driver API 8.0.44 Data structures.
+ Memory advise values
+ Memory Range Attributes
+ P2P Attributes

P.S.
There is no any new changes in CUDA Driver API 8.0.61 Data structures since 8.0.44.


[ROCm/hip commit: 1cc5f42e34]
2017-05-30 18:29:14 +03:00
Evgeny Mankov 8574437d36 [HIPIFY] Add more CUDA Driver API 8.0.44 Data structures.
[ROCm/hip commit: 3e99bc23e7]
2017-05-30 17:58:13 +03:00
Maneesh Gupta 56bf96c6df Disable normcdfinvf on __host__
Change-Id: If7bfc9826a09eb9b7675ea2a417b9418759b7912


[ROCm/hip commit: 4ff01c971f]
2017-05-30 15:45:22 +05:30
Ben Sander b3e01ed74f Add event controls for release fences.
Env var : HIP_EVENT_SYS_RELEASE
Event allocation flags : hipEventReleaseToDevice, hipEventReleaseToSystem
   (remove hipEventDisableSystemRelease)

Update test for new functionality.


[ROCm/hip commit: ec7102f461]
2017-05-27 16:02:34 -05:00
Ben Sander e24627aa80 Cleanup hipEvent. (Intermediate checkpoint)
Support hipEventDisableSystemRelease flag.
Update test.
Remove stray printf


[ROCm/hip commit: 620eb30691]
2017-05-27 16:02:34 -05:00
Ben Sander c88190d698 Updates so hip compiles on CUDA.
[ROCm/hip commit: be8d0ba644]
2017-05-27 15:55:07 -05:00
Ben Sander 715aeef97c Add isDefaultStream() accessor.
Fix code that checked for stream==nullptr after stream had been
resolved to a "true stream".


[ROCm/hip commit: b251d72917]
2017-05-26 13:46:48 -05:00
Siu Chi Chan ef1a8c2788 fix hip_fast_dsqrt* to call a double fp sqrt function
[ROCm/hip commit: 1dce01f9bb]
2017-05-25 23:15:30 -04:00
Evgeny Mankov bc9b970f82 [FIX] [HIPIFY] Add matchers for function return types.
https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/issues/73

Examples (https://github.com/thrust/thrust/blob/master/thrust/system/cuda/detail/trivial_copy.inl):

template<typename System1,
         typename System2>
cudaStream_t cuda_memcpy_stream(const thrust::cpp::execution_policy<System1> &,
                                const thrust::cuda::execution_policy<System2> &exec)

template<typename System1,
         typename System2>
cudaMemcpyKind cuda_memcpy_kind(const thrust::cuda::execution_policy<System1> &,
                                const thrust::cpp::execution_policy<System2> &)


[ROCm/hip commit: c863215611]
2017-05-24 18:25:40 +03:00
Ben Sander b7b7c7b7ac Remove HIP_NUM_KERNELS_INFLIGHT. (redundant with HCC controls)
[ROCm/hip commit: 578d430bb3]
2017-05-24 01:03:28 -05:00