AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
735 коммитов 3 Ветки 0 Теги
2e754d27dc5932edaee8cb0a0f0ae2102d76a430
Граф коммитов

727 Коммитов

Автор SHA1 Сообщение Дата
Aditya Atluri 2e754d27dc Signal Fix: Changed global signal count to per stream signal count 
1. The number of kernels that can use signals are increased to 128
2. The kernel count is now specific to the stream

Change-Id: Ie6d1aa3f437aad8f08c3333fe48bd3f46e551e60
 2016-07-26 14:03:51 -05:00
Aditya Atluri 524127b4a4 removed redundant signal destroy 
Change-Id: Icf0cd76b2620d34c87cfb6c7a83049087c0a0bc4
 2016-07-26 13:35:35 -05:00
Ben Sander 77be00e8d3 Doc update for FAQ and future RELEASE notes 
Change-Id: I7e7c32d9a19fdaea0a0e41f1d4fa4652e53640f2
 2016-07-26 12:14:15 -05:00
Ben Sander 75d1f8c297 Doc update for README.md - add more intro text, example 
Change-Id: I99b8eaacd6460dfdbdbc8ddba3fe589647d877e7
 2016-07-26 12:14:02 -05:00
Ben Sander b9e48d6066 Make HCC ignore register keyword 
- (previously would emit a warning)
- Also tweak documentation.

Change-Id: I0f4f00f82f8cc53d420112570f2d7675535e6aea
 2016-07-26 12:13:48 -05:00
Aditya Atluri 0232e6bbb4 Added re-fix for memcpy kernel sync 
1. The patch uses HIP signal pools to sync between copy and kernel commands
2. The hsa_signal_create is removed
3. Left the redundant enqueueBarrier method just in case

Change-Id: I3dff3e8ee57fff3cd49bec802ff735ed128e5ca1
 2016-07-26 09:22:59 -05:00
Rahul Garg d11d65d401 D2H and H2D unpinned memory transfer support 
Change-Id: If6d6c970f435e5d917d5cc6cddc2ee2918cd1c37

Conflicts:
	src/hip_hcc.cpp
 2016-07-25 14:36:07 +05:30
Aditya Atluri 1704006bed Partial fix async after kernel launch signal issue 
Change-Id: Ib48d6564379160035bded9493b93663fba361710
 2016-07-23 14:54:20 -05:00
pensun 6db08e5135 Add empty stubs for threadfence family routines, changes include: 
- stubs and documentation in include/hcc_details/hip_runtime.h
    - stubs with "no-op" in src/hip_memory.cpp
    - document update in hip_kernel_language.md, add suggestions to
    disable L1 and L2 caches when using the threadfence routines.

Change-Id: Ic0753170f802003055bca9d7476d7f48817b98b7
 2016-07-22 10:40:58 -05:00
Maneesh Gupta b485470819 Replace calls to ihipInit with use of HIP_INIT_API macro 
Change-Id: Iabf7df79f0238a8ddffea4607fe945df36642850
 2016-07-22 15:46:55 +05:30
Maneesh Gupta 5c18187741 hip_hcc package now depends on rocm-profiler 
Change-Id: I80d1c6048cc18c47c2024efb90368b17139a09ad
 2016-07-22 15:45:32 +05:30
Maneesh Gupta dffed956fb Fix using ATP markers 
Change-Id: If2d04f80b580237426c569737551e2001a8cd35a
 2016-07-21 16:02:51 +05:30
Maneesh Gupta 7d5cffdc17 Merge branch 'hiparray' into amd-develop 
Change-Id: I63ca7b1db7b593ac5cfb3fd7cd5d08d6e4075a4c
 2016-07-21 12:29:56 +05:30
Maneesh Gupta 8c4cd59903 Bump HIP version to 0.92.00 
Change-Id: I4d653213dcf3ddf7d09d36433afe31e21d17a7ee
 2016-07-21 09:52:08 +05:30
Aditya Atluri 300ec2af1e added kernel launch stress test 
Change-Id: Ib50d47e55079839ba31aabb524b70b704d7a46fe
 2016-07-19 13:57:56 -05:00
Aditya Atluri 77d7134619 added fix for signal overflow in kernels 
Change-Id: Ie0b1f97f69b7d7b34e445f6f120472819be03a0e
 2016-07-19 13:51:44 -05:00
Maneesh Gupta 538eeb7cc0 Add markdown documentation to hip_docs package 
Change-Id: I4075e6baaf287356ac8b485cccc231bfb729f078
 2016-07-19 14:30:03 +05:30
Maneesh Gupta 89cbfadf86 Set cmake policy CMP0037 to old behavior for newer cmake versions 
Change-Id: Ib2a7da53a238a489e73d6c006c50f12f07f866a1
 2016-07-19 06:52:38 +05:30
Ben Sander 4b3102b578 Update documentation. 
- Add more detailed feature comparison HIP vs specific CUDA SDK revs.
- Remove reference to old codenames.
- Fix TOC in some md files.

Change-Id: If0f6a05dc61237c4710c4d4bf2d933d556dcaeae
 2016-07-18 13:56:22 -05:00
Maneesh Gupta a181262ae5 README.md: Fix link to clang-hipify documentation 
Change-Id: I4c668c0e3c5ee2b16dfc213b48ccd1dbaac7b2a2
 2016-07-15 14:18:59 +05:30
Maneesh Gupta 0eb4f5e108 Handle linker warning correctly 
Change-Id: Ifca5886e31b4551603944c2b90a8e532442e889f
 2016-07-15 10:40:56 +05:30
Maneesh Gupta 1be2dbb150 Add specifying ROCm target support to HIP 
Change-Id: I42930d8ccf0dafe408ce5bebe2d95f99e544ee8d
 2016-07-15 10:08:27 +05:30
Maneesh Gupta 2410d285a2 Merge branch 'release_0.90.00' into amd-develop 
Conflicts:
	bin/hipcc

Change-Id: Iced6290fe205551f5d30f656088530b0ea813193
 2016-07-15 10:04:03 +05:30
Maneesh Gupta b0dc9d208a Whitespace cleanup in hipcc 
Change-Id: I36d32808e9e393df44ffd80b49d09ccf68b5751e
 2016-07-13 11:26:03 +05:30
Maneesh Gupta b4b9ab1d28 Cleanup hip_hcc packaging script 
Change-Id: I41168b3135b36263369b97974a2d2646516e8401
 2016-07-12 13:08:21 +05:30
Maneesh Gupta 7d3217a3e3 Fix whitespace in cmakefile 
Change-Id: Ide671e19ea15d57cc8619ec57ad10bca615b3858
 2016-07-12 13:00:42 +05:30
Maneesh Gupta 22941235e1 cmake queries hip version from hipconfig 
Change-Id: I8c65ca508ddc288111eaa1d818213c72ef27ac1b
 2016-07-12 12:40:35 +05:30
Maneesh Gupta 1b184c8527 Move hip version information to hipconfig 
Change-Id: I2892a9eb9356ac5310b89a433d858c1c3eb986ee
 2016-07-11 16:38:41 +05:30
Evgeny Mankov 9f77666802 clang-hipify: Populate replacement rules and fix typos. 
+ fix typo in hipStreamWaitEvent.
+ hipHostAlloc -> hipHostMalloc.
+ Memory Types, Pointer Attributes are added.
+ Event, Host Malloc and Register, Device and Stream Flags are added.
+ exclude cudacommon.h.prehip from includes' replacement rules.
 2016-07-07 18:01:41 +03:00
Maneesh Gupta 5947731054 Merge branch 'amd-master' into amd-develop 2016-07-05 21:40:22 +05:30
Maneesh Gupta e936f584f7 Merge remote-tracking branch 'hipblas' into hipblas 2016-07-05 10:04:10 +05:30
Maneesh Gupta 5bb51a3150 don't bundle source in rocm packages 
Change-Id: I36bd93e2bff9db1310724dd79c6c736ee17aa806
 2016-07-05 08:18:30 +05:30
Evgeny Mankov 5d04a17a44 clang-hipify: add Replacement Excludes 
Excludes are not replaced, for instance, CHECK_CUDA_ERROR and CUDA_SAFE_CALL.
Add check for excludes in MacroExpands and CallExpr routines.
 2016-07-01 19:58:14 +03:00
Aditya Atluri adad6ef71f added more nvcc event functions 
Change-Id: I79ee20ef444d4c1ab6ada3c0d56730ce754ab6b6
 2016-06-30 21:03:19 -05:00
Maneesh Gupta 2577b6158f Merge branch 'amd-develop' into amd-master 
Change-Id: I04f85b207e15e66c1a546675dc0937726ee08362
 2016-06-30 18:36:07 +05:30
Fan Cao dc0a787984 Replace GPU agent with CPU agent properly for memory async copy API 
ihipStream_t::copySync use GPU agent in memory async copy API, even
if the src/dst memory does not belong to GPU, which cause the hsa
runtime to choose a slower copy engine.

SWDEV-95191

Change-Id: If3cab3d493c0c96ed63721cdcf28247a1193887c
 2016-06-30 18:23:29 +05:30
Aditya Atluri 38720f8a4e moved half support to a source file 
Change-Id: I7c09b41877e22c1b743dea25a585e5307427dafd
 2016-06-30 18:23:29 +05:30
Aditya Atluri 4a6ebce880 added fp16 software support 
Change-Id: Ic0fdd9f8248a66911169fc00d3af71f50b36e233
 2016-06-30 18:23:29 +05:30
Evgeny Mankov 53401727a8 clang-hipify: fix typos and populate replacement rules 
+ typos in cudaDeviceAttr and cudaDeviceAttr
+ Device Attribules are added
+ More error codes are added
 2016-06-29 20:32:05 +03:00
Maneesh Gupta 88ca6f7312 Update release notes 
Change-Id: I6ae7e5c44b1f7d084abb7cedd353276b81531f82
 2016-06-29 20:50:14 +05:30
Maneesh Gupta 4138461080 Update markdown documentation 
Change-Id: I92cf4411d601e5bbd62ce6c3346cdac0ea2945a8
 2016-06-29 20:49:40 +05:30
Evgeny Mankov f19992760e clang-hipify: Array of elements of typedef type translation support. 
Example: cudaStream_t streams[2]
 2016-06-28 19:57:08 +03:00
Evgeny Mankov ab2a7f436d cublas to hipblas translation support in clang-hipify 
+ CUBLAS V2 functions support
+ annotating, formatting
 2016-06-28 15:33:38 +03:00
7SK 54034e5048 NVCC_COMPAT 
add support for both cuda compatible implementation and hcc(faster)
implementation with test

Change-Id: I79a22344f458391d7dffac5f147619a542e97e4e
 2016-06-28 09:36:06 +05:30
Maneesh Gupta 058cdf2a8c hip_samples package now contains uncompressed samples 
Change-Id: I69e773ebeff59733e016abd5a90bd1637798b1f5
 2016-06-24 21:17:52 +05:30
Rahul Garg dc5ca03143 Included code to calculate value of maxThreadsPerMultiprocessor property 
Change-Id: Ie7cad7442f36a7163e715048de5a309febc28664
 2016-06-24 21:17:30 +05:30
Maneesh Gupta dca8fca8eb Merge branch 'amd-master' into amd-develop 2016-06-24 21:13:11 +05:30
Maneesh Gupta 75f14acb79 hip_samples package now contains uncompressed samples 
Change-Id: I69e773ebeff59733e016abd5a90bd1637798b1f5
 2016-06-24 21:10:37 +05:30
Rahul Garg 226aa917e7 Included code to calculate value of maxThreadsPerMultiprocessor property 
Change-Id: Ie7cad7442f36a7163e715048de5a309febc28664
 2016-06-24 15:10:11 +05:30
Evgeny Mankov aa75bff6ee Initial cublas to hipblas translation support in clang-hipify. 
To run clang-hipify with hipblas support please specify corresponding hipblas include directory, for example:

./hipify-clang --print-stats matrixMult.cpp.cuda -- -I/srv/git/HIP/HIP-Examples/hipblas/include

Additionally:
+ typedef translation support is added (cudaEvent_t and cudaStream_t are converted now).
+ anonymous typedef enum translation support.
+ function name macro expansion support.
+ clang options propagation is restored.
P.S. In order to avoid the following error message:
“Could not auto-detect compilation database for file "… .cu"
No compilation database found in /srv/git/HIP/build/clang-hipify or any parent directory
json-compilation-database: Error while opening JSON database: No such file or directory
Running without flags.”
please append “--“ to the end of clang-hipify’s command line.
 2016-06-22 19:15:03 +03:00