Граф коммитов

13197 Коммитов

Автор SHA1 Сообщение Дата
Brian Sumner 8d80abb30f Drop use of NVCC_COMPAT since it is always set 2018-07-27 09:29:29 -07:00
foreman 46a6b4b4d7 P4 to Git Change 1586299 by chui@ocl-promo-incrementor on 2018/07/27 02:56:34
SWDEV-2 - Change OpenCL version number from 2703 to 2704.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2451 edit
2018-07-27 03:21:21 -04:00
foreman 2544968e15 P4 to Git Change 1586165 by gandryey@gera-w8 on 2018/07/26 18:11:39
SWDEV-79445 - OCL generic changes and code clean-up
	- Make sure RAVEN2 uses PAL path for offline devices

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#597 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#167 edit
2018-07-26 18:27:12 -04:00
foreman 9ddfeef105 P4 to Git Change 1585929 by asalmanp@asalmanp-ocl-stg on 2018/07/26 12:26:11
SWDEV-132899 - [OCL][GFX10] removing gfx1001 (target for Navi10 Lite if xnack is enabled)
	 starting from gfx10, we will use the same target (e.g., gfx1000) no matter if xnack is enabled/disbaled and we pass "-xnack" option to Finalizer if xnack is enabled on the target
	ReviewURLBoard = http://ocltc.amd.com/reviews/r/15492/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#99 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#64 edit
2018-07-26 13:08:44 -04:00
foreman f7701ab726 P4 to Git Change 1585682 by chui@ocl-promo-incrementor on 2018/07/26 02:56:37
SWDEV-2 - Change OpenCL version number from 2702 to 2703.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2450 edit
2018-07-26 03:28:32 -04:00
Maneesh Gupta 17f612def1 Merge pull request #596 from mangupta/patch5-fixhiplaunchparm
[tests] Fixed hipLaunchParm test on nvcc path
2018-07-26 06:17:50 +05:30
Maneesh Gupta 86188f04c8 Merge pull request #595 from mangupta/patch4-fixhipStdComplex
[tests] Fixed build & disabled run of hipStdComplex on nvcc path
2018-07-26 06:17:04 +05:30
Maneesh Gupta ec6995485c Merge pull request #592 from mangupta/patch1-initialize-cudapath
[hipcc] Initialize CUDA_PATH before printing
2018-07-26 06:16:31 +05:30
Maneesh Gupta ddcb85a77b Merge pull request #590 from ROCm-Developer-Tools/fix-ballot-anyall-return
Fix return EXIT_FAILURE if ballot or anyall fails
2018-07-26 06:16:23 +05:30
foreman adf6570955 P4 to Git Change 1585460 by jatang@jatang-opencl-hsa-stg5 on 2018/07/25 17:25:24
SWDEV-1 - Also catch clGetPlatformIDs error, so clinfo won't get a page fault when no platform is found.

	Instead clinfo now shows:

	ERROR: clGetPlatformIDs(-1001)

Affected files ...

... //depot/stg/opencl/drivers/opencl/tools/clinfo/clinfo.cpp#5 edit
2018-07-25 17:38:16 -04:00
Aaron Enye Shi bf6fdca1e8 Enable HIP texture functions with HIP vector types
Include texture_functions.h on HIP-Clang path. Use HIP vector types instead of hc::short_vectors for texture_functions, and remove HCC headers.
2018-07-25 19:52:19 +00:00
foreman 16c55e6a36 P4 to Git Change 1585268 by wchau@wchau_OCL_boltzmann on 2018/07/25 12:33:45
SWDEV-160377 - [OCL][ROCM] Add OpenCL Runtime Support for GFX10 in ROCm

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdefs.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#92 edit
2018-07-25 12:43:09 -04:00
Maneesh Gupta 51307ac705 [tests] Fixed hipLaunchParm test on nvcc path
- Uses c++11 features. Added it to nvcc options
- Arguments for some kernels exceeded 4096 bytes which is the limit
  imposed by nvcc. Reduced BLOCK_DIM_SIZE to 512 to handle this
- Fixed compilation issues on nvcc path

Change-Id: I14f6b28afcb7c6b24a085fd707b2104e2ed64627
2018-07-25 15:41:04 +05:30
Maneesh Gupta 843020bfe6 [tests] Fixed build & disabled run of hipStdComplex on nvcc path
Change-Id: I885e96902faa065f6559183f33b6a7aa1f37e393
2018-07-25 15:39:45 +05:30
Maneesh Gupta 7a5987e289 [FindHIP] Remove rdynamic from CMAKE_SHARED_LIBRARY_LINK_HIP_FLAGS
CMAKE_SHARED_LIBRARY_LINK_CXX_FLAGS contains -rdynamic which does not go
well with nvcc

Change-Id: I10e6d21553de0e43c6a7ae5fb3ec2418087959ff
2018-07-25 15:32:14 +05:30
Maneesh Gupta 2027675b3f [hipcc] Initialize CUDA_PATH before printing
Change-Id: Ifd448b628fa4a7055f4a439ed2c817c5f11f9bef
2018-07-25 15:29:57 +05:30
foreman cfccbd91ab P4 to Git Change 1585041 by chui@ocl-promo-incrementor on 2018/07/25 02:57:40
SWDEV-2 - Change OpenCL version number from 2701 to 2702.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2449 edit
2018-07-25 03:10:25 -04:00
Maneesh Gupta 8c195a3588 Merge pull request #589 from gargrahul/set_offset_gettexalignoffset
Set offset in hipGetTextureAlignmentOffset
2018-07-25 12:13:31 +05:30
foreman ebe91eeace P4 to Git Change 1584936 by vsytchen@vsytchen-win10 on 2018/07/24 18:57:28
SWDEV-79445 - OCL generic changes and code clean-up

	1. In SvmCopyMemoryCommand handle the case when both src and dst pointer don't belong to the SVM space.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15481/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#424 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#117 edit
2018-07-24 19:14:26 -04:00
foreman 5ac4970a68 P4 to Git Change 1584863 by yaxunl@yaxunl-lc10 on 2018/07/24 17:00:42
SWDEV-145570 - [HIP] - Update prototype of __hipRegisterVar

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#13 edit
2018-07-24 17:14:35 -04:00
foreman b207b2ae94 P4 to Git Change 1584842 by asalmanp@asalmanp-ocl-stg on 2018/07/24 16:31:05
SWDEV-132899 - Removing gfx1001 and adding gfx1010 target for Navi10 (gfx10.1)

	ReviewURLBoard = http://ocltc.amd.com/reviews/r/15473/

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/libUtils.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings.h#23 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_hsail.h#26 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_hsail64.h#26 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/linker.cpp#158 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/libUtils.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings.h#55 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_hsail.h#51 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_hsail64.h#46 edit
... //depot/stg/opencl/drivers/opencl/compiler/tools/driver/driver.cpp#68 edit
2018-07-24 17:00:55 -04:00
foreman 439ddcff00 P4 to Git Change 1584825 by asalmanp@asalmanp-ocl-stg on 2018/07/24 16:08:09
SWDEV-132899 - Propagate -xnack option to Finalizer

	ReviewURLBoard = http://ocltc.amd.com/reviews/r/15478/

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/hsail_be.cpp#70 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/OPTIONS.def#139 edit
2018-07-24 16:41:18 -04:00
Aaron Enye Shi 8ab8a37812 Fix return EXIT_FAILURE if ballot or anyall fails 2018-07-24 20:39:48 +00:00
Jenkins f9d7d2bf7c Merge 'master' into 'amd-master'
Change-Id: I7e307defaf54b3e95d97e8910bb61faba1021d3e
2018-07-24 04:09:46 -05:00
foreman f1157f1cfb P4 to Git Change 1584378 by chui@ocl-promo-incrementor on 2018/07/24 02:56:41
SWDEV-2 - Change OpenCL version number from 2700 to 2701.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2448 edit
2018-07-24 03:14:10 -04:00
Rahul Garg f17c897751 Null check before setting offset 2018-07-24 12:25:40 +05:30
Rahul Garg 0ec64e8b24 Set offset in hipGetTextureAlignmentOffset 2018-07-24 10:11:26 +05:30
Maneesh Gupta cab5e80b22 Merge pull request #582 from ROCm-Developer-Tools/set-vdi-path
Let hipcc use proper include and lib path for HIP/VDI
2018-07-24 07:32:54 +05:30
Maneesh Gupta bb02937dd5 Merge pull request #580 from ROCm-Developer-Tools/document-fatbin
Document hip-clang fatbinary format and initialization function
2018-07-24 07:31:19 +05:30
Maneesh Gupta 25ba9f6f94 Fix typo 2018-07-24 07:30:05 +05:30
foreman c84525aa73 P4 to Git Change 1584196 by gandryey@gera-w8 on 2018/07/23 18:05:14
SWDEV-79445 - OCL generic changes and code clean-up
	- Reset memory dependency if runtime invalidated L1 for the profiling logic workaround. Profiling can be enabled for wave limiter, which could cause L1 invalidation twice.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#116 edit
2018-07-23 18:19:58 -04:00
Jorghi12 25c780c89e Fixing a HIP bug that causes DEBUG symbols to be dropped.
I've noticed that in the generated makefiles, we'd have 

if(NOT build_configuration)
    set(build_configuration Debug)
endif()

However, only definitions with all capitals are provided. 

e.g.

set(HIP_HCC_FLAGS_DEBUG -g)

This is because of lines 442 to 448. We capitalize the configuration ${config_upper}.

This PR fixes this bug.
2018-07-23 18:16:00 -04:00
foreman 12a063779d P4 to Git Change 1584092 by zukhan@zukhan-lc-win10 on 2018/07/23 15:24:19
SWDEV-155860 - [OCL][LC] 62 Failures running on OCL/LC Windows drivers
	 - Conformance test  basic->vload_private was failing due to alignment assert check on akc->workitem_private_segment_byte_size.
	 - Determined needed to add alignment, so added alignment into the header file, and removed assert check (as alignment was done afterwards).

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15451/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#57 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#18 edit
2018-07-23 15:41:16 -04:00
Yaxun Sam Liu 555c2f9c08 Fix warnings about unused command line option --hip-link
and set search path for libhip_hcc.so
2018-07-23 14:55:07 -04:00
Yaxun Sam Liu 674b45902d Document hip-clang fatbinary format and initialization function
This is for documenting the change in hip-clang: https://reviews.llvm.org/D49083
2018-07-23 09:28:40 -04:00
Yaxun Sam Liu 6053c71323 Fix hipcc for -M for hip-clang 2018-07-23 09:26:42 -04:00
Yaxun Sam Liu 4627aa0085 Let hipcc use proper include and lib path for HIP/VDI
Add support of environment variable HIP_VDI_HOME.

By setting environment variable HIP_VDI_HOME to the distribution directory of HIP/VDI, hipcc
will choose proper include and lib path for hip-clang.
2018-07-23 09:26:42 -04:00
Evgeny Mankov a5afadec7e Merge pull request #583 from emankov/cuDNN
[HIPIFY][DNN] cuDNN support revise
2018-07-23 14:13:54 +03:00
Maneesh Gupta e2615335c0 Merge pull request #568 from Srinivasuluch/sprint2_9tests
Adding a few more struct scenarions and a ResultValidation()
2018-07-23 14:44:06 +05:30
Maneesh Gupta 00c1542487 Merge pull request #558 from Jorghi12/patch-8
Fix the FindHIP.cmake script.
2018-07-23 11:48:42 +05:30
saleelk e8a5ad629f Fix hipHostRegister mem leak and copy kind in hipMemcpyAsync (#587) 2018-07-23 11:04:14 +05:30
Maneesh Gupta 4637e11a24 Fix typo in FindHIP.cmake 2018-07-23 10:39:45 +05:30
Maneesh Gupta 137d7f559f Merge pull request #559 from rpathani/master
Adding functor unit tests
2018-07-23 10:15:16 +05:30
Maneesh Gupta 123af1a9c6 Merge pull request #584 from ROCm-Developer-Tools/fix-vector-explicit-cast
Fix explicit cast required
2018-07-23 10:13:05 +05:30
Maneesh Gupta 4d6a3f3eba Merge pull request #581 from ROCm-Developer-Tools/fix-warning-math-decl
[HIPClang] Switch ordering on math functions
2018-07-23 10:12:01 +05:30
Maneesh Gupta c53d0f967e Merge pull request #554 from gargrahul/cleanup_hipmemset3d_test
Cleaned up hipMemset3D test
2018-07-23 10:11:49 +05:30
foreman 8fb21f8181 P4 to Git Change 1583683 by chui@ocl-promo-incrementor on 2018/07/21 02:56:33
SWDEV-2 - Change OpenCL version number from 2699 to 2700.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2447 edit
2018-07-21 03:09:20 -04:00
foreman 9aca622a92 P4 to Git Change 1583633 by vsytchen@vsytchen-win10 on 2018/07/20 18:09:50
SWDEV-79445 - OCL generic changes and code clean-up

	1. Purge reduntant SVM alignment. The size will always get correctly aligned inside of PAL/GSL.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15454/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#596 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#245 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#98 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#70 edit
2018-07-20 19:34:45 -04:00
Aaron Enye Shi 032ebd41ea Fix explicit cast required
This is required for PyTorch which runs into an issue with narrowing types. Requires an explicit cast.
2018-07-20 16:34:15 -04:00
Evgeny Mankov 618b1f5171 [HIPIFY][DNN] cuDNN support revise
+ add doc for CUDDN API supported by HIP
+ cuDNN softMax test
2018-07-20 21:00:24 +03:00