Commit Graph

5048 Commits

Author SHA1 Message Date
Evgeny Mankov 6f501f6094 [HIPIFY] Sync with HIP (Execution Control, Surfaces, Memory)
Execution Control [deprecated since 7.0]:
cudaConfigureCall -> hipConfigureCall
cudaLaunch -> hipLaunchByPtr
cudaSetupArgument -> hipSetupArgument

Surfaces (partially):
cudaSurfaceObject_t -> hipSurfaceObject_t
cudaSurfaceBoundaryMode -> hipSurfaceBoundaryMode
cudaCreateSurfaceObject -> hipCreateSurfaceObject
cudaDestroySurfaceObject -> hipDestroySurfaceObject

Memory Management:
cudaMemset2DAsync -> hipMemset2DAsync
2018-04-24 22:04:04 +03:00
Deven Desai af586bbbf2 Checkin to fix bugs in math functions.
This change fixes the following bugs that were discovered while debuggnig TF unit test failures (cwise_ops_test)

1. __hisinf and __hisnan routines
   Both had incorrect implementations.

2. abs
   A "long long" (64bit int) version was missing, resulting in the 32bit version being used for 64bit ints (which resulted in incorrect results, when the value passed in was outside the 32bit int range)

3. lgamma
  We seemed to have a custom version for the 'double' datatype (which was giving incorrect results). Replaced it with a call to the 'double' version of the underlying 'hc::precision_math::lgamma'
2018-04-24 18:10:07 +00:00
foreman 13355e5de5 P4 to Git Change 1545750 by skudchad@skudchad_test2_win_opencl on 2018/04/24 13:55:57
SWDEV-145570 - [HIP] - Add some hip_mem* APIs. Part 2.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14681/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#11 edit
2018-04-24 14:05:20 -04:00
Aaron Enye Shi 433866eb60 Remove unsupported targets gfx801 and gfx802
These architectures are no longer supported. Should not compile for them.
2018-04-23 15:25:35 -04:00
Evgeny Mankov b36001bbbf Merge pull request #413 from emankov/master
[HIPIFY] undo apply .clangformat to HIPIFY source files
2018-04-23 20:29:43 +03:00
Evgeny Mankov 8499e79e2b [HIPIFY] undo apply .clangformat to HIPIFY source files 2018-04-23 20:22:15 +03:00
foreman 66640b546f P4 to Git Change 1544858 by skudchad@skudchad_rocm on 2018/04/22 21:07:25
SWDEV-144570 - [HIP] - Fix a few APIs and typos.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_device_runtime.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#6 edit
2018-04-22 21:17:27 -04:00
Rahul Garg 39b5b07dc3 Added deprecation note in cuCtx section 2018-04-20 22:43:58 +05:30
Rahul Garg 19cb6c61ab Moved deprecated macro to the end 2018-04-20 21:57:23 +05:30
Lakhan Singh 1c2509dc04 SWDEV-141024 2018-04-20 17:40:00 +05:30
Rahul Garg a039dbf2dd Mark hipCtx APIs as deprecated 2018-04-20 17:34:48 +05:30
foreman 3ce752065a P4 to Git Change 1544061 by skudchad@skudchad_test2_win_opencl on 2018/04/19 18:24:45
SWDEV-145570 - [HIP] - Add some hip_mem* APIs

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14647/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#10 edit
2018-04-19 18:35:00 -04:00
foreman 63babe9e66 P4 to Git Change 1543751 by cpaquot@cpaquot-ocl-lc-lnx on 2018/04/19 11:17:02
SWDEV-145570 - [HIP] Implemented a bunch of texture APIs

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_texture.cpp#5 edit
2018-04-19 12:27:09 -04:00
Maneesh Gupta 35a8deec00 Merge pull request #404 from gargrahul/hipMemset2DAsync_support
Added hipMemset2DAsync support
2018-04-18 14:19:41 +05:30
Rahul Garg ffe18d1505 Resolve tex1D float to int conversion issue 2018-04-18 14:15:18 +05:30
Rahul Garg 3cfb9c0d40 Added hipMemset2DAsync support 2018-04-17 18:27:27 +05:30
Jenkins 1964bb1115 Merge 'master' into 'amd-master'
Change-Id: I599b0d1176a11c635c8b16c395d15677bd431fb5
2018-04-17 04:09:48 -05:00
Maneesh Gupta 33ada06de9 Merge pull request #400 from gargrahul/hipModule_cleanup
hip_module code cleanup
2018-04-17 09:00:15 +05:30
Aaron Enye Shi 5a80c16cd2 Clean up triple_to_hsa_isa naming (#403) 2018-04-17 06:47:55 +05:30
foreman 250e08f31f P4 to Git Change 1541938 by cpaquot@cpaquot-ocl-lc-lnx on 2018/04/16 18:27:17
SWDEV-145570 - [HIP] Set/GetDevice and Create/DestroyTextureObject
	Implemented Set/GetDevice relying on g_context (current context)
	Implemented create linear/2D texture object function
	Implemented hipDestroyTextureObject

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_device_runtime.cpp#5 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_texture.cpp#4 edit
2018-04-16 18:37:17 -04:00
Rahul Garg 1446f78799 hip_module code cleanup
-Fixed missing ihipLogStatus in hipModuleLoad()
-Fixed some ihipXXX functions
2018-04-16 15:35:04 +05:30
Aaron Enye Shi 1a281240d6 Fix bug when using older rocr naming (#399) 2018-04-14 15:47:46 +05:30
foreman e6718d9747 P4 to Git Change 1541197 by skudchad@skudchad_test2_win_opencl on 2018/04/13 17:49:07
SWDEV-145570 - [HIP] -  Add missing HIP APIs and  fill sym table references. The HIP tests can now build if we do a symlink to libhip_hcc.so that we build with VDI in the install folder in github HIP.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14619/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_device.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#3 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#3 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_internal.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#5 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_profile.cpp#1 add
... //depot/stg/opencl/drivers/opencl/api/hip/hip_texture.cpp#3 edit
2018-04-13 18:19:28 -04:00
Aaron Enye Shi ab7e727fa2 Fix new gfx target naming convention (#397)
This was introduced in recent xnack changes naming changes which affected our offload bundler. This patch will fix issues in HIP samples, ROCR tests, and others.
2018-04-13 16:24:39 +05:30
Jenkins fceabfe4d8 Merge 'master' into 'amd-master'
Change-Id: I68d26834a9e5e651e1be4e4219a7521f6da97415
2018-04-13 04:10:05 -05:00
Maneesh Gupta bda18af06d Merge pull request #395 from lmoriche/master
Add missing __device__ function attributes.
2018-04-12 14:51:32 +05:30
Maneesh Gupta 97f67ced66 Merge pull request #393 from mangupta/cmake_update_deps
[cmake] Update target build dependencies
2018-04-12 14:36:49 +05:30
Maneesh Gupta b1057f0be6 Merge pull request #394 from gargrahul/hipMemset_refactoring
hipMemset refactoring
2018-04-12 14:01:49 +05:30
Rahul Garg 16c89d101a Correct missed ihipMemsetCopyDataType change 2018-04-12 10:27:19 +05:30
Rahul Garg 3d6eb75828 Changed ihipMemsetCopyDataType to ihipMemsetDataType 2018-04-12 09:29:22 +05:30
Laurent Morichetti 211c18e674 Add missing __device__ function attributes. 2018-04-11 09:29:37 -07:00
Rahul Garg 294bf50f68 Fix hipMemset stream resolution 2018-04-11 19:01:53 +05:30
Rahul Garg 412a35be20 hipMemset refactoring 2018-04-11 15:58:48 +05:30
Maneesh Gupta b1be325745 [cmake] Update target build dependencies
Change-Id: Ib1c34135c0d04f88daa695e7a90272225d7e64b0
2018-04-11 15:30:13 +05:30
Jenkins aa366257c2 Merge 'master' into 'amd-master'
Change-Id: Icea2117281aa6f24d85bc5ceea1db8c5d737caf3
2018-04-11 04:10:08 -05:00
Maneesh Gupta 7c43396596 Merge pull request #391 from lmoriche/master
Create one hipModule_t per device
2018-04-11 13:06:58 +05:30
foreman 04decb72fc P4 to Git Change 1539198 by skudchad@skudchad_test2_win_opencl on 2018/04/10 17:32:14
SWDEV-145570 - [HIP] -  Add HIP API skeletons for Peer and memory

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14596/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_context.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_peer.cpp#1 add
2018-04-10 17:41:24 -04:00
Laurent Morichetti 91f996035c Create one hipModule_t per device 2018-04-10 08:57:34 -07:00
Jenkins 61c2b91ebe Merge 'master' into 'amd-master'
Change-Id: I2bb8d2d98bb90185d663d0dc3bad1803acd857cc
2018-04-09 04:10:14 -05:00
Maneesh Gupta 399a17d755 Merge pull request #390 from mangupta/hipmemcpy_fix
hipMemcpyAsync returns success when trying to copy 0 bytes
2018-04-09 14:02:36 +05:30
Maneesh Gupta ac7c5dfd0b Merge pull request #388 from lmoriche/master
Add support for clang offload bundles and <<<>>> kernel launch.
2018-04-09 12:40:28 +05:30
Maneesh Gupta 03eca1c57e hipMemcpyAsync returns success when trying to copy 0 bytes
Change-Id: I4c0ee7ccc7563e2df657b50356cdd7fec9a1ef15
2018-04-09 12:39:44 +05:30
Maneesh Gupta 4ac59148a9 [ci] Disable nvcc CI builds 2018-04-09 12:23:56 +05:30
Maneesh Gupta d98eaf5923 Merge pull request #389 from scchan/adjust_texture_hcc_workweek
adjust the hcc work week for the texture fix
2018-04-09 10:54:16 +05:30
foreman e7f206d249 P4 to Git Change 1537729 by cpaquot@cpaquot-ocl-lc-lnx on 2018/04/06 17:59:29
SWDEV-145570 - [HIP] Use Svm path for both hipMalloc and hipHostMalloc
	Make sure hipMemCpy uses SvmBuffer to fetch the cl_mem

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#8 edit
2018-04-06 18:08:18 -04:00
Siu Chi Chan f48e471dd4 adjust the hcc work week for the texture fix 2018-04-06 15:46:55 -04:00
Laurent Morichetti bc6fa2bc62 Don't include __clang_cuda_builtin_vars.h 2018-04-05 16:27:05 -07:00
foreman ce88da9c1b P4 to Git Change 1537232 by skudchad@skudchad_rocm on 2018/04/05 15:00:24
SWDEV-145570 - [HIP] - Fix typo and fix build.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_texture.cpp#2 edit
2018-04-05 15:12:53 -04:00
foreman 204ecba4b6 P4 to Git Change 1537228 by skudchad@skudchad_test2_win_opencl on 2018/04/05 14:53:31
SWDEV-145570 - [HIP] -  Add HIP Memory, texture, surface, context api skeletons

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14565/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_context.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_device.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_event.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_stream.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_surface.cpp#1 add
... //depot/stg/opencl/drivers/opencl/api/hip/hip_texture.cpp#1 add
2018-04-05 15:02:43 -04:00
foreman 15f11c983f P4 to Git Change 1536925 by vsytchen@vsytchen-ocl-win10 on 2018/04/04 17:20:38
SWDEV-79445 - OCL generic changes and code clean-up

	1. This change replaces the use of std::map with std::unordered_map to improve lookup/insert time.
	2. Replace the use of std::make_pair and std::pair constructor with uniform initialization for cleaner code.
	3. Replace the use of std::Container::iterator type with the auto keyword for cleaner code.
	4. Use range based for loops where needed.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14517/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#58 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d10.cpp#16 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d10_amd.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d11.cpp#24 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d11_amd.hpp#13 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d9.cpp#34 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d9_amd.hpp#17 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl.cpp#57 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_pipe.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#46 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpuprogram.cpp#72 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpuvirtual.cpp#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#216 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#297 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuappprofile.cpp#13 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpubinary.cpp#59 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpucompiler.cpp#158 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#587 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#322 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprintf.cpp#46 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.cpp#237 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.hpp#70 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#242 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#415 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.hpp#143 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palappprofile.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#79 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprintf.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#59 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#60 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#84 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#46 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/CMakeLists.txt#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/pro/prodevice.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/pro/prodevice.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocbinary.hpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#42 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccounters.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprintf.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#81 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#81 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#89 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.cpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#29 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.cpp#129 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.hpp#102 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/perfctr.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#91 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.hpp#43 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/sampler.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.cpp#17 edit
2018-04-04 18:00:17 -04:00