AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
13 197 Commits 3 Branches 0 Tags
f6c8bbf4dcc2ec0022ea4faa5a9d75afb2a58a11
Commit Graph

13197 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Aditya Avinash Atluri 9c4819bc29 Merge pull request #4 from AMDComputeLibraries/memtracker 
hipGetPointerAttrib behavioral changes
 2016-02-27 10:51:23 -06:00
pensun bcbc76470d Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 2016-02-27 04:25:28 -06:00
Ben Sander 3eb281aeff disable rocrv2, properly 2016-02-27 03:31:30 -06:00
foreman 208f92951f P4 to Git Change 1241505 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/27 03:01:23 
SWDEV-2 - Change OpenCL version number from 2046 to 2047.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1793 edit
 2016-02-27 03:10:47 -05:00
Aditya Avinash Atluri e9a9c760fc Updated hipPointerAttrib.cpp to pass HC backend 
The changes are according to the new API function change in HC backend for HIP. Especially hipPointerGetAttribute(...)
 2016-02-26 19:42:07 -06:00
Aditya Avinash Atluri db8bedc4d3 Update README.md 2016-02-26 19:39:14 -06:00
Aditya Avinash Atluri 08a82b405a Update README.md 2016-02-26 19:38:22 -06:00
Aditya Avinash Atluri 2ca6162593 Corrected hipPointerGetAttribute 
Made hipPointerGetAttribute work same as cudaPointerGetAttribute for HCC
 2016-02-26 18:50:40 -06:00
atimofee 351e7c74ea 1.CUDA structure types (and pointers to the types) in function parameter declaration conversion – DONE. 
2.Wrong source locations in qualified types declaration:  – FIXED
3.cudaRuntimeGetVersion added to the names map
4.sizeof expression matcher added, expression handler is not yet ready - upcoming soon
 2016-02-26 23:35:27 +03:00
Aditya Avinash Atluri aeb86755c3 Null argument handling HIPCC 
This change makes hipcc handle no-arguments passed to it. It solves https://github.com/AMDComputeLibraries/HIP-privatestaging/issues/1
 2016-02-26 13:47:58 -06:00
Aditya Avinash Atluri a31f878218 Added CUDA support for hipPointerGetAttributes 2016-02-26 12:33:55 -06:00
pensun e21841c152 relsove conflicts 2016-02-26 09:57:40 -06:00
pensun 980ec93f46 fix compiling error 2016-02-26 09:50:00 -06:00
Ben Sander 8105bd636f fixes for titan platform 2016-02-26 05:25:30 -06:00
Ben Sander 822c7292c9 Disable ROCR_V2 2016-02-26 23:34:45 -06:00
Ben Sander 7a1b4c3878 Merge branch 'memtracker' into privatestaging 
Conflicts:
	include/nvcc_detail/hip_runtime_api.h
 2016-02-26 06:17:05 -06:00
Ben Sander 4a6173fe58 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 2016-02-26 06:15:09 -06:00
foreman dcf942f977 P4 to Git Change 1241072 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/26 03:00:11 
SWDEV-2 - Change OpenCL version number from 2045 to 2046.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1792 edit
 2016-02-26 03:14:36 -05:00
Ben Sander 69bb511b10 Merge branch 'memtracker' of https://github.com/AMDComputeLibraries/HIP-privatestaging into memtracker 
Conflicts:
	tests/src/hipMemcpy.cpp
 2016-02-25 23:24:22 -06:00
Ben Sander 8d985188dd Merge branch 'memtracker' of https://github.com/AMDComputeLibraries/HIP-privatestaging into memtracker 
Conflicts:
	tests/src/hipMemcpy.cpp
 2016-02-25 23:22:51 -06:00
Ben Sander 67e96e983f Add PATH and LD_LIBRARY_FLAGS 2016-02-25 23:07:18 -06:00
Ben Sander af97f5e317 Merge branch 'memtracker' into privatestaging 
Conflicts:
	src/hip_hcc.cpp
 2016-02-25 19:38:46 -06:00
Ben Sander d3e1773704 Tweak version numbers 2016-02-25 19:30:42 -06:00
Ben Sander 91ed5c7d78 Improve memory copy and commands switching 
- Add chicken bits to use host-side dependency management.
- Add optional PinInPlace path for unpinned copies
- Synchronize before pinned memcpy path.
- Add mutex to protect two threads launching to same stream.
 2016-02-25 19:19:49 -06:00
Aditya Avinash Atluri 6ec52348ea Update hip.vim 
Added d2d and h2h highlights
 2016-02-25 14:49:58 -06:00
Evgeny Mankov 7bb0f17656 Attribute hipDeviceAttributeIsMultiGpuBoard for obtaining Device property isMultiGpuBoard is added. 
On HIP path property obtaining done through hsa_iterate_agents and counting the devices of HSA_DEVICE_TYPE_GPU type.

P.S.
On multi-boards systems it might be problems with detection what board a GPU plugged into (not tested).
 2016-02-25 23:44:39 +03:00
atimofee 27921652a6 Merge branch 'master' of https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP-hipify 2016-02-25 22:55:49 +03:00
atimofee 63df6f915f Fixed tool crash on kernels with empty parameter list 2016-02-25 22:54:58 +03:00
foreman abb2291941 P4 to Git Change 1240661 by smekhano@stas-nova-hsa on 2016/02/25 13:30:49 
SWDEV-85940 - Complib: fix memory leak in aclCompileInternal() CodeGenInit
	Testing: smoke, precheckin, test_compiler
	Reviewed by Evgeny Mankov

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/v0_8/if_acl.cpp#91 edit
 2016-02-25 13:45:17 -05:00
dfukalov 3d5de5305d fixed lit script discovery in standalone build case 2016-02-25 15:18:14 +03:00
Ben Sander 2228bbd119 Add test for thread-safety on streams 2016-02-25 04:22:34 -06:00
Ben Sander 382638df1e Add abstraction for pinned/unpinned, and sync/async mem copies selection in tests 2016-02-25 04:21:24 -06:00
foreman 7a5a8b264c P4 to Git Change 1240452 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/25 03:00:15 
SWDEV-2 - Change OpenCL version number from 2044 to 2045.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1791 edit
 2016-02-25 03:12:42 -05:00
atimofee 36833c78f3 String literal bug fixed + string literal processing refactoring 2016-02-24 21:22:32 +03:00
atimofee 2056dadaa1 Merge branch 'master' of https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP-hipify 2016-02-24 19:27:52 +03:00
atimofee a5695b1d52 TAB deleted 2016-02-24 19:27:02 +03:00
atimofee 665d3dc443 CUDA names in string literals replacment added 2016-02-24 19:23:23 +03:00
dfukalov ac30cbfe65 -o=<output_filename> option added 2016-02-24 19:10:00 +03:00
atimofee 8bf31a49c8 CUDA names in string literals replacment added 2016-02-24 17:42:02 +03:00
foreman e0b92ebb45 P4 to Git Change 1240006 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/24 03:00:11 
SWDEV-2 - Change OpenCL version number from 2043 to 2044.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1790 edit
 2016-02-24 03:12:54 -05:00
Aditya Avinash Atluri b86a905958 Update hip.vim 2016-02-23 13:40:20 -06:00
Ben Sander 836c485d0b Add tests for multi-threaded streams 2016-02-23 12:08:22 -06:00
foreman 25c8e12f86 P4 to Git Change 1239589 by mtomarov@stg-ocl-mtomarov on 2016/02/23 07:47:15 
SWDEV-76870 - Add write feature to AMD extension (Merging //depot/rel/r6/15.30.1023/stream/opencl/... to //depot/stg/opencl/drivers/opencl/...)

	Add clEnqueueReadBufferToFileAMD function to AMD extension (added declaration in cl_context.cpp)
	1. Added clEnqueueReadBufferToFileAMD_fn function declaration to cl_ext.h
	2. Added LiquidFlashFile::writeBlock method who implements transfer from GPU to SSD. In order to avoid code duplication LiquidFlashFile::readBlock and LiquidFlashFile::writeBlock is called from new method LiquidFlashFile::transferBlock (changes in cl_lqdflash_amd.cpp)
	3. clEnqueueWriteBufferFromFileAMD and clEnqueueWriteBufferFromFileAMD call internal function EnqueueTransferBufferFromFileAMD who makes the same preparations as clEnqueueWriteBufferFromFileAMD in the prvious release
	4. WriteBufferFromFileCommand class is renamed to TransferBufferFromFileCommand and new class makes the same preparation except assigning transfer direction (read or write)

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#48 integrate
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_lqdflash_amd.cpp#13 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_lqdflash_amd.h#4 integrate
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.0/CL/cl_ext.h#24 integrate
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#267 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#396 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.hpp#138 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#74 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#81 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.hpp#96 edit
 2016-02-23 07:57:16 -05:00
foreman 1cb5415538 P4 to Git Change 1239589 by mtomarov@stg-ocl-mtomarov on 2016/02/23 07:47:15 
SWDEV-76870 - Add write feature to AMD extension (Merging //depot/rel/r6/15.30.1023/stream/opencl/... to //depot/stg/opencl/drivers/opencl/...)

	Add clEnqueueReadBufferToFileAMD function to AMD extension (added declaration in cl_context.cpp)
	1. Added clEnqueueReadBufferToFileAMD_fn function declaration to cl_ext.h
	2. Added LiquidFlashFile::writeBlock method who implements transfer from GPU to SSD. In order to avoid code duplication LiquidFlashFile::readBlock and LiquidFlashFile::writeBlock is called from new method LiquidFlashFile::transferBlock (changes in cl_lqdflash_amd.cpp)
	3. clEnqueueWriteBufferFromFileAMD and clEnqueueWriteBufferFromFileAMD call internal function EnqueueTransferBufferFromFileAMD who makes the same preparations as clEnqueueWriteBufferFromFileAMD in the prvious release
	4. WriteBufferFromFileCommand class is renamed to TransferBufferFromFileCommand and new class makes the same preparation except assigning transfer direction (read or write)

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#48 integrate
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_lqdflash_amd.cpp#13 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_lqdflash_amd.h#4 integrate
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.0/CL/cl_ext.h#24 integrate
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#267 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#396 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.hpp#138 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#74 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#81 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.hpp#96 edit
 2016-02-23 07:57:16 -05:00
Ben Sander 8f98aca124 Sync review. 
- add calls to ihipInit missing from some routines.
- sync before draining a stream.
 2016-02-23 04:07:11 -06:00
Ben Sander 7d553a1113 add hipLaunchParm 2016-02-23 04:05:41 -06:00
foreman 131b479d5a P4 to Git Change 1239533 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/23 03:00:11 
SWDEV-2 - Change OpenCL version number from 2042 to 2043.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1789 edit
 2016-02-23 03:12:02 -05:00
Ben Sander 28990567fb Improve async copy implementation. 
- Add device-side signal waits when transitioning between command classes
(Kernel, H2D copy, D2H copy).
- Support waiting in staged memory copies as well.
- Add several chicken bits to control implementation:
    - HIP_DISABLE_ENQ_BARRIER
    - HIP_DISABLE_BIDIR_MEMCPY
    - HIP_ONESHOT_COPY_DEP
- Refactor signal pool to support efficient deallocation based on
signsequnm.
- Deallocate copy signals on eventSynchronize.
- Improve copy tests, add pingpong.
 2016-02-22 23:15:24 -06:00
foreman 01f19b6043 P4 to Git Change 1239340 by rili@rili-opencl-stg on 2016/02/22 16:50:49 
SWDEV-84552 - Flush HSAIL kernel execution if workload is too big.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#395 edit
 2016-02-22 17:03:42 -05:00
Ben Sander 784ebcbc86 Fix memcpy for Titan. Add <threads> to common includes 2016-02-22 15:09:23 -06:00