Commit Graph

1500 Commits

Author SHA1 Message Date
foreman 9cd2db67f6 P4 to Git Change 1589476 by axie@axie-rocm-opencl on 2018/08/03 15:54:24
SWDEV-79445 - OCL generic changes and code clean-up
	- Optimize setup of kernel arguments.
	- Add HW ABI support in the abstraction layer
	- Remove arguments parsing loop from the kernel launch. Memory processing will be responsible for dependency tracking and  patching of arguments.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15400/

	Tests:
	1. ./run_conformance.py ./opencl_conformance_tests_reallyquick.csv CL_DEVICE_TYPE_GPU for openCL 1.2: OpenCL-GL sharing failed. This is not a regression.
	2. ./ocltst -m oclruntime.so -A oclruntime.exclude
	3. ./run_conformance.py opencl_conformance_tests_lightning.csv CL_DEVICE_TYPE_GPU : PASS
	4. teamcity test: http://ocltc.amd.com:8111/viewModification.html?modId=104598&personal=true&buildTypeId=&tab=vcsModificationBuilds&show_all_builds=true

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#39 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.hpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#34 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#60 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#17 edit
2018-08-03 16:05:12 -04:00
foreman 9fb27ccc8b P4 to Git Change 1588199 by gandryey@gera-w8 on 2018/08/01 11:53:29
SWDEV-155434 - Add SQTT instrumentation tokens for OpenCL dispatches for RGP support
	- Fix the build.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#119 edit
2018-08-01 12:30:25 -04:00
foreman 19968ab78a P4 to Git Change 1588181 by gandryey@gera-w8 on 2018/08/01 11:39:16
SWDEV-155434 - Add SQTT instrumentation tokens for OpenCL dispatches for RGP support
	- Switch to the workgroup size report for the dispatch info.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#118 edit
2018-08-01 11:53:18 -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 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
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 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
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
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
foreman 75423e4972 P4 to Git Change 1582940 by gandryey@gera-w8 on 2018/07/19 15:09:58
SWDEV-159255 - [CQE OCL][ocltst][WIN] [DTB-Blocker] OCLMemoryInfo[0] a sub-test of ocltst oclruntime module is failed while running whole module and getting pass while running alone this test due to faulty CL#1576247
	- Reduce extra size acceptance for the cache look-up, so it will satisfy the test condition.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#69 edit
2018-07-19 15:36:34 -04:00
foreman 8c44442f90 P4 to Git Change 1582433 by gandryey@gera-w8 on 2018/07/18 17:23:28
SWDEV-155438 - Produce RGP Queue Timings chunk for OpenCL RGP files
	- Register SDMA queue in order to get SDMA timing. The RGP trace capture with SDMA may cause a HW hang occasionally

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#115 edit
2018-07-18 18:14:56 -04:00
foreman 7899017d49 P4 to Git Change 1582337 by vsytchen@vsytchen-win10 on 2018/07/18 15:21:49
SWDEV-79445 - OCL generic changes and code clean-up

	1. std::bind2nd is deprecated in c++11 and removed in c++17. Use a range based for loop without any functor instead.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15430/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#59 edit
2018-07-18 15:41:11 -04:00
foreman 509d540374 P4 to Git Change 1581723 by todli@todli-win-opencl-kv1 on 2018/07/17 17:45:23
SWDEV-152361 - Fixed writeBuffer, writeBufferRect and copyBufferRect paths for ExternalPhysical memory in GPU backend, so that SDI copy can sync with writeMarker correctly in Linux.
	http://ocltc.amd.com/reviews/r/15420/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#131 edit
2018-07-17 18:11:43 -04:00
foreman 77bd31536a P4 to Git Change 1580823 by gandryey@gera-w8 on 2018/07/16 11:48:51
SWDEV-154474 - [Task]: TAN Dual Realtime Queue Enhancement For Radeon Rays
	- Use the new enum for RT1

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#423 edit
2018-07-16 12:05:32 -04:00
foreman 017d0f3e03 P4 to Git Change 1580351 by vsytchen@vsytchen-win10 on 2018/07/13 14:54:15
SWDEV-158585 - [ROCm] OCLPinnedMemory test is giving VM fault

	1. If host ptr is present, use the CopyBuffer path instead of the ReadBuffer path

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15403/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#58 edit
2018-07-13 15:05:05 -04:00
foreman 494b22221b P4 to Git Change 1580345 by gandryey@gera-lnx-rcf on 2018/07/13 14:50:14
SWDEV-154474 - [Task]: TAN Dual Realtime Queue Enhancement For Radeon Rays
	- Fix linux build error

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#33 edit
2018-07-13 15:00:01 -04:00
foreman 6b409a027b P4 to Git Change 1580311 by gandryey@gera-w8 on 2018/07/13 14:24:01
SWDEV-154474 - [Task]: TAN Dual Realtime Queue Enhancement For Radeon Rays
	- Add support for the second RT queue

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_command.cpp#16 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#422 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#97 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#114 edit
2018-07-13 14:32:29 -04:00
foreman 0b08fa4a4e P4 to Git Change 1579735 by gandryey@gera-w8 on 2018/07/12 14:22:40
SWDEV-158730 - [CQE OCL][ocltst][WIN] OCLMemoryInfo[1] a sub-test of ocltst oclruntime module is failed
	- Update free memory calculation for APU systems. There is still an issue in GSL with multiple alloc/free passes

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#595 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#96 edit
2018-07-12 14:31:30 -04:00
foreman 96d0ddb728 P4 to Git Change 1579667 by gandryey@gera-w8 on 2018/07/12 12:31:33
SWDEV-155438 - Produce RGP Queue Timings chunk for OpenCL RGP files
	- Collect command buffer timing
	- Capture 50 dispatches by default

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.hpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#113 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#54 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#291 edit
2018-07-12 12:40:04 -04:00
foreman 3fb9ab0d90 P4 to Git Change 1577773 by gandryey@gera-w8 on 2018/07/09 13:10:36
SWDEV-155438 - Produce RGP Queue Timings chunk for OpenCL RGP files
	- Enable queue timing

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#4 edit
2018-07-09 13:22:19 -04:00
foreman bd06a268cc P4 to Git Change 1577743 by jatang@jatang-opencl-hsa-stg5 on 2018/07/09 11:44:49
SWDEV-126897 - Fix enqueue_block_capture_event_profiling_info_after_execution test.

	Need to set eng_clk.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#26 edit
2018-07-09 11:54:21 -04:00
foreman 2caff650a9 P4 to Git Change 1577357 by gandryey@gera-w8 on 2018/07/06 17:44:59
SWDEV-158017 - CL_DEVICE_GLOBAL_FREE_MEMORY_AMD doesn't work correctly on PAL backend
	- Adjust system memory calculation for APU systems

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#594 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.hpp#89 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#95 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#26 edit
2018-07-06 17:53:44 -04:00
foreman e2b18eda3e P4 to Git Change 1576542 by jatang@jatang-opencl-hsa-stg5 on 2018/07/05 09:29:34
SWDEV-126897 - Remove un-necessary synchronize() for Device Enqueue in LC/ROCm path.

	We don't need it since we have a hsa_signal_wait_acquire() to wait for the scheduler to finish. Moreover, synchronize() sends a barrier packet that could get stuck for some reason.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#25 edit
2018-07-05 09:39:08 -04:00
foreman 7e185b873e P4 to Git Change 1576247 by gandryey@gera-w8 on 2018/07/04 16:55:54
SWDEV-158017 - CL_DEVICE_GLOBAL_FREE_MEMORY_AMD doesn't work correctly on PAL backend
	- Change the free memory detection to account possible memory allocation with oversubscription.
	- Make sure resource cache isn't counted as allocated memory

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#593 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#244 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.hpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#68 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#25 edit
2018-07-04 17:04:53 -04:00
foreman 6e589b7de6 P4 to Git Change 1576209 by vsytchen@vsytchen-win10 on 2018/07/04 15:37:58
SWDEV-79445 - OCL generic changes and code clean-up

	1. Purge redundant AllocMapTarget function

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15346/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_memobj.cpp#84 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#223 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#309 edit
2018-07-04 15:50:23 -04:00
foreman 0bc34b7062 P4 to Git Change 1576208 by vsytchen@vsytchen-win10 on 2018/07/04 15:36:47
SWDEV-154903 - [Vega10][PAL] clSVMAlloc is failing to create allocations greater than 2GB

	1. Uncommit coarse grain SVM from system memory when calling clEnqueueSVMUnmap

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15336/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.cpp#133 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.cpp#133 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.hpp#106 edit
2018-07-04 15:45:29 -04:00
foreman 1c17b90822 P4 to Git Change 1575517 by gandryey@gera-w8 on 2018/07/03 11:55:33
SWDEV-133815 - PAL support for Linux Pro w/OpenCL 2.0 support
	- Reenable OCL2.0 support on Linux.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#53 edit
2018-07-03 12:03:24 -04:00
foreman a5bf56e9bc P4 to Git Change 1573627 by skudchad@skudchad_test2_win_opencl on 2018/06/27 18:26:38
SWDEV-145570 - [HIP] Report 64KB LDS for Linux

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15296/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#52 edit
2018-06-27 18:36:59 -04:00
foreman 7bb3d41155 P4 to Git Change 1573623 by gandryey@gera-w8 on 2018/06/27 18:23:10
SWDEV-155433 - Add OpenCL API type for RGP files generated from OpenCL
	- Add API type events to the SQTT

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#93 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#30 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.hpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#112 edit
2018-06-27 18:32:23 -04:00
foreman 717c0e3e6c P4 to Git Change 1572945 by jatang@jatang-opencl-hsa-stg5 on 2018/06/26 16:09:41
SWDEV-155654 - TDR\BSOD observed while running Nuke Performance Benchmark test on Hawaii Asics.

	Need to support the new power-related appprofile parameters for gfx8 ASICs.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuappprofile.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuappprofile.hpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#592 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#183 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.h#64 edit
2018-06-26 16:18:18 -04:00
foreman c7bbeca0d5 P4 to Git Change 1572344 by jatang@jatang-opencl-hsa-stg5 on 2018/06/25 13:05:15
SWDEV-126897 - Enable 'OPENCL_VERSION=210' in LC/ROCm path.

	For testing purpose.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#91 edit
... //depot/stg/opencl/drivers/opencl/tests/conformance/devel/2.0/test_conformance/device_execution/main.c#10 edit
2018-06-25 13:16:30 -04:00
foreman 75b68a5dac P4 to Git Change 1571962 by skeely@skeely_HSA_linux on 2018/06/22 17:51:21
SWDEV-157321 - Mesa interop interface update.

	Interop in/out structs and header updated to match version at git://anongit.freedesktop.org/mesa/mesa
	Mostly minor changes, cleans up include structure avoiding GLX on Windows.

	Larger change is version tracking (now by numbers rather than struct size),
	added a field to mesa_glinterop_export_out giving the size of data written to out_driver_data,
	and corrected spelling of mesa_glinterop_export_out::internal_format.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/mesa_glinterop.h#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocglinterop.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocglinterop.hpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.cpp#36 edit
2018-06-22 18:00:13 -04:00
foreman 64fd3e50a0 P4 to Git Change 1570202 by gandryey@gera-w8 on 2018/06/19 13:58:38
SWDEV-155436 - Write dispatch dimensions to COMPUTE registers for OpenCL support for RGP
	- Add the dispatch dimensions to the RGP trace

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.hpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#111 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#290 edit
2018-06-19 14:06:00 -04:00
foreman 8d82c5e97b P4 to Git Change 1570053 by jatang@jatang-opencl-hsa-stg5 on 2018/06/19 09:47:32
SWDEV-155306 - Restore ClockMode when the last queue is destroyed.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#110 edit
2018-06-19 09:53:09 -04:00
foreman 1e1aa59aed P4 to Git Change 1569647 by gandryey@gera-lnx-rcf-lc on 2018/06/18 14:04:00
SWDEV-79445 - OCL generic changes and code clean-up
	 -Following CL#1568521. Correct LDS size look-up.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#57 edit
2018-06-18 14:15:59 -04:00
foreman f6d8feabeb P4 to Git Change 1568521 by gandryey@gera-w8 on 2018/06/14 17:43:52
SWDEV-79445 - OCL generic changes and code clean-up
	- Change LDS setup to account the size, since LC forces 4 bytes for LDS offsets always

	http://ocltc.amd.com/reviews/r/15197/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#130 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#327 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#109 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.hpp#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#34 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#25 edit
2018-06-14 17:51:35 -04:00
foreman c149902a4d P4 to Git Change 1568474 by asalmanp@asalmanp-ocl-stg on 2018/06/14 16:29:06
SWDEV-132899 - [OCL][GFX10] OCLGLDepthTex[0] and OCLGLDepthTex[4] subtests of OCLTST/OCLGL are failing on gfx10 Emulator
	extending the Depth24_Stencil8 workaround for gfx10 based on gfx10 Image SRDs

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15194/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#67 edit
2018-06-14 16:39:10 -04:00
foreman b7b121fa27 P4 to Git Change 1567935 by gandryey@gera-w8 on 2018/06/13 16:49:10
SWDEV-79445 - OCL generic changes and code clean-up
	- Remove array of hidden parameters. Hidden parameters will be placed together with OCL kernel arguments.

	http://ocltc.amd.com/reviews/r/15178/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#222 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#308 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#326 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#55 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#33 edit
2018-06-13 17:09:22 -04:00
foreman 1eb9ba3640 P4 to Git Change 1567812 by jatang@jatang-opencl-hsa-stg4 on 2018/06/13 12:23:13
SWDEV-126897 - Change OCL version in ROCm/LC path back to 1.2.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#89 edit
2018-06-13 12:38:01 -04:00
foreman ec029f4a40 P4 to Git Change 1567789 by gandryey@gera-w8 on 2018/06/13 11:45:56
SWDEV-79445 - OCL generic changes and code clean-up
	Following CL#1567428. Fix "pass by reference" logic:
	- Make sure we add the offset to the struct location
	- Adjust assert condition

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#54 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#108 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#31 edit
2018-06-13 12:01:00 -04:00
foreman 1f1b062117 P4 to Git Change 1567767 by jatang@jatang_rocm_lc2 on 2018/06/13 11:06:09
SWDEV-126897 - Support OpenCL Device Enqueue on ROCm.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#24 edit
2018-06-13 11:41:03 -04:00
foreman 1be400ff01 P4 to Git Change 1567428 by gandryey@gera-w8 on 2018/06/12 18:39:23
SWDEV-79445 - OCL generic changes and code clean-up
	- Optimize setup of kernel arguments. Stage 2.
	- Add HW ABI support in the abstraction layer
	- Remove arguments parsing loop from the kernel launch. Memory processing will be responsible for dependency tracking and  patching of arguments.

	http://ocltc.amd.com/reviews/r/15122/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#221 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#307 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#325 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#53 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#17 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#107 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#53 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#30 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#95 edit
2018-06-12 18:57:20 -04:00
foreman 6321912698 P4 to Git Change 1567349 by jatang@jatang_rocm_lc2 on 2018/06/12 16:09:03
SWDEV-126897 - Support OpenCL Device Enqueue on ROCm.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.hpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdefs.hpp#17 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#35 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.hpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsched.hpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocschedcl.cpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#33 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.hpp#13 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#16 edit
2018-06-12 16:17:29 -04:00
foreman aa7316a8eb P4 to Git Change 1564341 by gandryey@gera-w8 on 2018/06/05 16:37:09
SWDEV-79445 - OCL generic changes and code clean-up
	- Follwoing CL#1564298. Delete the old array

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#421 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#106 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#55 edit
2018-06-05 16:44:03 -04:00
foreman 1130565901 P4 to Git Change 1564298 by gandryey@gera-w8 on 2018/06/05 15:43:17
SWDEV-79445 - OCL generic changes and code clean-up
	- Add reallocation logic for memory dependency. SVM path can send the amount of SVM ptrs over the max size of arguments

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#420 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#105 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#54 edit
2018-06-05 15:48:18 -04:00
foreman 4214c42b59 P4 to Git Change 1562960 by skudchad@skudchad_test2_win_opencl on 2018/06/01 14:46:26
SWDEV-145570 - [HIP] - Rename SVManager to be more genric. The same functionality can be used for HIP without needing additonal map

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15054/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_memobj.cpp#83 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#220 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#306 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#591 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#419 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#92 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#104 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#53 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#29 edit
2018-06-01 14:57:43 -04:00
foreman 97223251ca P4 to Git Change 1562330 by gandryey@gera-w8 on 2018/05/31 14:48:10
SWDEV-79445 - OCL generic changes and code clean-up
	- Restore reatain/release methods in the device object, removed in CL#1398097. There is a crash in the old SHOC11_DeviceMemory test on TC.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#305 edit
2018-05-31 14:55:04 -04:00
foreman d703ef373a P4 to Git Change 1561847 by gandryey@gera-w8 on 2018/05/30 17:34:28
SWDEV-79445 - OCL generic changes and code clean-up
	- Replace resize(0) with clear() for std::vector. Clear() should preserve the original memory for data.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#103 edit
2018-05-30 18:48:09 -04:00
foreman b8a9cdb20e P4 to Git Change 1561794 by gandryey@gera-w8 on 2018/05/30 16:14:30
SWDEV-79445 - OCL generic changes and code clean-up
	- Move memory sync logic to processMemObjectsHSA() to simplify the arguments setup

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#102 edit
2018-05-30 16:22:34 -04:00