Commit Graph

13197 Commits

Author SHA1 Message Date
Evgeny Mankov 2319a9dcf3 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP 2019-01-09 16:39:48 +03:00
Evgeny Mankov d765f8c334 Merge pull request #854 from emankov/master
[HIPIFY][cmake] Add cmake versioning depending on CUDA version
2019-01-09 16:39:30 +03:00
Evgeny Mankov 5dba4e74cb Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP 2019-01-09 14:03:40 +03:00
Evgeny Mankov d160c7285c [HIPIFY][cmake] Add cmake versioning depending on CUDA version 2019-01-09 13:59:48 +03:00
Maneesh Gupta d3a5502f17 Merge pull request #853 from ROCm-Developer-Tools/hip-module-hash-fix
Introduce hash key to HIP module implementation
2019-01-09 16:28:50 +05:30
foreman ca14911693 P4 to Git Change 1727825 by chui@ocl-promo-incrementor on 2019/01/09 03:00:06
SWDEV-2 - Change OpenCL version number from 2811 to 2812.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2559 edit
2019-01-09 03:12:22 -05:00
Wen-Heng (Jack) Chung 6e68d44220 Introduce hash key to HIP module implementation
A hash calculated via FNV-1a algorithm is introduced in ihipModule_t, the
internal of hipModule_t. The hash is used by HIP module APIs such as

- read_agent_global_from_module

to determine whether the agent-scope globals for a module have been iterated.

This commit fixes one issue that applications which load / unload modules
frequently would occasionally fail. After deep investigation of the issue it
turns out the old implementation in read_agent_global_from_module uses
hipModule_t as the key, which is not robust enough, as hipModule_t instances
are allocated dynamically so there are cases that one memory address may be
used by multiple hipModule_t instances. The real solution is to introduce a
uniquely identifiable hash for the code object associated with the HIP module.
And that's the rationale behind this commit.
2019-01-08 17:33:40 +00:00
foreman 3574cc00d3 P4 to Git Change 1727393 by gandryey@gera-w8 on 2019/01/08 11:35:08
SWDEV-79445 - OCL generic changes and code clean-up
	- Allow LC to execute 64bit GPU binaries with 32 bit OCL runtime.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#122 edit
2019-01-08 12:13:48 -05:00
foreman 697a5c68ca P4 to Git Change 1727393 by gandryey@gera-w8 on 2019/01/08 11:35:08
SWDEV-79445 - OCL generic changes and code clean-up
	- Allow LC to execute 64bit GPU binaries with 32 bit OCL runtime.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#122 edit
2019-01-08 12:13:48 -05:00
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