Commit Graph

12238 Commits

Author SHA1 Message Date
foreman 0c6cf47532 P4 to Git Change 1727221 by chui@ocl-promo-incrementor on 2019/01/08 03:00:04
SWDEV-2 - Change OpenCL version number from 2810 to 2811.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2558 edit
2019-01-08 03:14:11 -05:00
foreman e631b3978f P4 to Git Change 1727059 by asalmanp@asalmanp-ocl-stg on 2019/01/07 17:48:44
SWDEV-132899 - [OCL][GFX10] report number of WGP by default on gfx10 ASICs
	Both HSAIL/SC and LC compilers use WGP mode by default on gfx10 ASICs (i.e., COMPUTE_PGM_RSRC1.WGP_MODE is set to 1 by both compilers) therefore runtime should report number of WGP (i.e., CU/2) on gfx10 ASICs by default.
	The new environment variable (GPU_ENABLE_WGP_MODE = 0)  can be used to force CU mode on LC (i.e., -mcumode option) if it’s needed (HSAIL/SC doesn't have any compiler option for forcing the CU mode)

	Also, using the new environment variable (GPU_ENABLE_WAVE32_MODE) to control the wave32 mode on gfx10+.

	ReviewRequestURL = http://ocltc.amd.com/reviews/r/16435/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#329 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#121 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#65 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#301 edit
2019-01-07 18:02:10 -05:00
Maneesh Gupta cf7dc26851 Merge pull request #845 from mangupta/cleanup-install-markdown
Update INSTALL.md
2019-01-07 10:04:36 +05:30
Maneesh Gupta 03e1058666 Merge pull request #701 from ssahasra/stream-tests
introduce tests for asynchronous streams
2019-01-07 10:04:29 +05:30
Maneesh Gupta 79251fc4e2 Update hipAsynchronousStreams.cpp
This test needs to be excluded from nvcc platform
2019-01-07 09:26:21 +05:30
Evgeny Mankov 225a29f7bd Merge pull request #852 from emankov/master
[HIPIFY][fix][#851] make_absolute only in case of relative path
2019-01-06 18:25:05 +03:00
emankov 61593291fd [HIPIFY][fix][#851] make_absolute only in case of relative path
Otherwise return the input path.
2019-01-06 17:58:37 +03:00
foreman 612ea757c4 P4 to Git Change 1726612 by chui@ocl-promo-incrementor on 2019/01/06 03:00:07
SWDEV-2 - Change OpenCL version number from 2809 to 2810.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2557 edit
2019-01-06 03:14:42 -05:00
Evgeny Mankov c82dadcd0e Merge pull request #850 from emankov/master
[HIPIFY][fix][#849] Create temporary file based on source file name only
2019-01-05 15:16:14 +03:00
emankov 50ba722a2d [HIPIFY][fix][#849] Create temporary file based on source file name only 2019-01-05 14:52:15 +03:00
foreman e349f1fbb8 P4 to Git Change 1726547 by chui@ocl-promo-incrementor on 2019/01/05 03:00:05
SWDEV-2 - Change OpenCL version number from 2808 to 2809.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2556 edit
2019-01-05 03:11:57 -05:00
Jenkins da5274a0e7 Merge 'master' into 'amd-master'
Change-Id: I4ea252fc1aab6aeeb31c858ca5fcc2e36d989ba0
2019-01-04 20:09:59 -06:00
foreman 915c3da749 P4 to Git Change 1726489 by kjayapra@3_HIPWS_hmc2Dfix on 2019/01/04 19:36:57
SWDEV-145570 - Changing the SRC and DST pointer in hsa_amd_memory_async_copy_rect.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#28 edit
2019-01-04 19:44:36 -05:00
foreman 2b92421194 P4 to Git Change 1726335 by wchau@wchau_OCL_boltzmann on 2019/01/04 14:53:36
SWDEV-174898 - OCL Runtime kernel metadata lookup requires quadratic time

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.hpp#13 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.hpp#15 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#76 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#49 edit
2019-01-04 15:06:29 -05:00
Evgeny Mankov e9f18f2bb4 Merge pull request #848 from emankov/master
[HIPIFY][cmake] Change min supported version of cmake to 3.12.3
2019-01-04 19:12:14 +03:00
emankov 728fb14ab9 [HIPIFY][cmake] Change min supported version of cmake to 3.12.3
[Reason]
CUDA 10 is supported by cmake since 3.12.3.
2019-01-04 19:10:11 +03:00
Evgeny Mankov 51d74f447f Merge pull request #847 from emankov/master
[HIPIFY][cmake][win] check for Visual Studio version
2019-01-04 18:57:39 +03:00
emankov 207bbad778 [HIPIFY][cmake][win] check for Visual Studio version
hipify-clang could be built by Visual Studio 14 2015 or higher.

[Reason]
hipify-clang contains c++14 features which are not supported even by the latest VS 2013 and the Platform Toolset "Visual C++ Compiler Nov 2013 CTP".
2019-01-04 18:52:28 +03:00
Sameer Sahasrabuddhe 39574dba4c introduce test for asynchronous streams
This test is identical to the HCC tests under
tests/Unit/OCKL/AsyncStreams, but only for synchronous operation.
2019-01-04 05:51:50 -05:00
foreman 3fc7bb0329 P4 to Git Change 1726090 by chui@ocl-promo-incrementor on 2019/01/04 03:00:05
SWDEV-2 - Change OpenCL version number from 2807 to 2808.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2555 edit
2019-01-04 04:08:38 -05:00
Maneesh Gupta 92a556c20a Update INSTALL.md
- Improved install instructions for AMD-hcc and NVIDIA-nvcc.
- Removed redundant section related to HCC-Native-GCN-ISA.

Change-Id: I33a9e71d95df51dbdcade4a48834840146bdbe6f
2019-01-04 11:04:47 +05:30
Evgeny Mankov 9145eb9e95 Merge pull request #844 from emankov/master
[HIPIFY][tests] CUDA 7.0 is also supported
2019-01-04 01:34:14 +03:00
emankov 9808b22864 [HIPIFY][tests] CUDA 7.0 is also supported
+ Exclude 1 test for CUDA 7.0
+ Update README.md
2019-01-04 01:32:30 +03:00
foreman c65248d5a8 P4 to Git Change 1725828 by gandryey@gera-w8 on 2019/01/03 16:12:42
SWDEV-79445 - OCL generic changes and code clean-up
	- Add IS_LIGHTNING check for the rocr initialization, because currently for LC builds GPU_ENABLE_PAL is forced to 1.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#241 edit
2019-01-03 17:08:34 -05:00
foreman 0a5b58ddec P4 to Git Change 1725771 by gandryey@gera-w8 on 2019/01/03 14:33:02
SWDEV-79445 - OCL generic changes and code clean-up
	- Allow ROCr and PAL support from a single runtime binary. Runtime will use ROCr path by default with GPU_ENABLE_PAL=1 forcing PAL.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/build/Makefile.api#183 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#240 edit
2019-01-03 14:48:40 -05:00
foreman 63a1a63a75 P4 to Git Change 1725623 by gandryey@gera-w8 on 2019/01/03 10:32:08
SWDEV-79445 - OCL generic changes and code clean-up
	- Chnage the scope of SchedulerSourceCode variable

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#109 edit
2019-01-03 11:02:36 -05:00
Evgeny Mankov 944c3220d1 Merge pull request #843 from emankov/master
[HIPIFY][tests] Exclude CUDA 8.0 (9.0) tests if CUDA < 8.0 (9.0)
2019-01-03 18:08:48 +03:00
emankov 852bc8d545 [HIPIFY][tests] Exclude CUDA 8.0 (9.0) tests if CUDA < 8.0 (9.0) 2019-01-03 18:06:49 +03:00
Evgeny Mankov 1cb0dcad94 Merge pull request #842 from emankov/master
[HIPIFY][tests] Reduce cudaRegister.cu test
2019-01-03 17:19:11 +03:00
emankov 410f8f0b92 [HIPIFY][tests] Reduce cudaRegister.cu test 2019-01-03 17:17:21 +03:00
foreman 9faff0597a P4 to Git Change 1725484 by chui@ocl-promo-incrementor on 2019/01/03 03:00:30
SWDEV-2 - Change OpenCL version number from 2806 to 2807.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2554 edit
2019-01-03 04:46:04 -05:00
foreman 9b98cc97e6 P4 to Git Change 1725283 by gandryey@gera-lnx-rcf on 2019/01/02 19:03:17
SWDEV-79445 - OCL generic changes and code clean-up
	- Keep the body of all methods in the Program interface

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#97 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#44 edit
2019-01-02 19:27:19 -05:00
foreman ad54eb030b P4 to Git Change 1725257 by gandryey@gera-w8 on 2019/01/02 17:28:57
SWDEV-79445 - OCL generic changes and code clean-up
	- Move the constructor body of LightningProgram to the header

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#96 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#43 edit
2019-01-02 18:29:04 -05:00
foreman 01710a66ac P4 to Git Change 1725166 by gandryey@gera-w8 on 2019/01/02 15:41:59
SWDEV-79445 - OCL generic changes and code clean-up
	- Add dynamic switch between HSAIL and LC in ROCr path

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#108 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.hpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#95 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#42 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#71 edit
2019-01-02 16:03:55 -05:00
foreman 77c9dda5ba P4 to Git Change 1725088 by wchau@wchau_OCL_boltzmann on 2019/01/02 13:45:33
SWDEV-175381 - OCL Runtime produces invalid names for bitcode data objects

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#25 edit
2019-01-02 14:22:04 -05:00
foreman d548c36767 P4 to Git Change 1724879 by chui@ocl-promo-incrementor on 2019/01/02 03:00:29
SWDEV-2 - Change OpenCL version number from 2805 to 2806.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2553 edit
2019-01-02 03:12:47 -05:00
Maneesh Gupta 0e32ecf980 Merge pull request #841 from ROCm-Developer-Tools/rebase-pr827-to-master
Fix issues with prior iteration of 731
2019-01-01 20:22:57 +05:30
foreman eef3a29f21 P4 to Git Change 1724724 by chui@ocl-promo-incrementor on 2019/01/01 03:00:29
SWDEV-2 - Change OpenCL version number from 2804 to 2805.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2552 edit
2019-01-01 03:09:08 -05:00
Alex Voicu 3470692998 Hook into the creaky lazy-reinit machinery. Try to minimise race-risk. 2019-01-01 11:01:16 +05:30
Alex Voicu b2f76123b1 More blobs, more problems. 2019-01-01 11:01:07 +05:30
Alex Voicu 3e8f198b58 Start re-working 731 for 2.0. 2019-01-01 11:00:57 +05:30
Maneesh Gupta aa932d542a Merge pull request #818 from yxsamliu/fix-hip-config
Add default arguments for hipConfigureCall
2019-01-01 10:25:25 +05:30
Yaxun Sam Liu 57d1f6e6cb Use __dparm for default parameter 2018-12-31 13:07:19 -05:00
Maneesh Gupta 7647bdb664 Merge pull request #821 from gargrahul/remove_redundancy_memset3d_test
[dtest] Remove redundant arguments from hipMemset3D test
2018-12-31 15:32:19 +05:30
Evgeny Mankov 02de25e60b Merge pull request #840 from emankov/master
[HIPIFY][fix] Change system includes order
2018-12-29 22:12:06 +03:00
emankov 158b358c5b [HIPIFY][fix] Change system includes order
'include/cuda_wrappers' should go first.
2018-12-29 22:10:00 +03:00
Evgeny Mankov e93a97b14e Merge pull request #839 from emankov/master
[HIPIFY] Add system includes for packaged hipify-clang to use it with…
2018-12-29 22:06:29 +03:00
emankov e9589e3330 [HIPIFY] Add system includes for packaged hipify-clang to use it without the necessity of installing clang
Header files in those dirs are an integral part of clang, which includes wrapper headers for CUDA.
There is no need in checking those dirs.

[Reasons]
1. clang will not take into account empty or irrelevant include dirs;
2. Packages for different clang versions will have different header files in the above dirs.
2018-12-29 21:53:18 +03:00
Evgeny Mankov 9718a42ebc Merge pull request #838 from emankov/master
[HIPIFY] Get rid of setting '--cuda-gpu-arch='
2018-12-29 20:44:42 +03:00
emankov 6f6228cf36 [HIPIFY] Get rid of setting '--cuda-gpu-arch='
[Reasons]
+ We don't compile kernel code at least for now as HIP kernel syntax is almost equal CUDA's;
+ clang always includes PTX in its binaries, so e.g. a binary compiled with --cuda-gpu-arch= would be forwards-compatible with e.g. sm_35 GPUs.
2018-12-29 19:48:28 +03:00