a36ef232f2
P4 to Git Change 1561039 by gandryey@gera-w8 on 2018/05/29 13:29:24
...
SWDEV-79445 - OCL generic changes and code clean-up
- Move modified_ fleld initialization to fix g++ compilation
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#36 edit
2018-05-29 13:50:48 -04:00
51a4d1865c
P4 to Git Change 1561015 by gandryey@gera-w8 on 2018/05/29 13:10:06
...
SWDEV-79445 - OCL generic changes and code clean-up
Optimize memory dependency tracking logic:
1. Add modified_ filed to the event object to track memory writes into device memory.
2. Check memory dependency only if a write operation is currently requested or previously performed.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#35 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#66 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#100 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#52 edit
2018-05-29 13:18:29 -04:00
dabe2fda39
Fix runTest return type
2018-05-29 16:18:14 +05:30
28c878f266
Fix tex2D tests for result value
2018-05-29 16:03:37 +05:30
366a0a97ca
HIP test case for 1D texture fetch ( #424 )
2018-05-29 14:08:01 +05:30
48b7b4a4ad
Merge pull request #473 from gargrahul/add_tex1d_nvcc
...
Add 1d texture types for NVCC path
2018-05-29 13:54:34 +05:30
616c2272b0
P4 to Git Change 1560741 by johtaylo@johtaylo-jtincrementor2-increment on 2018/05/29 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2664 to 2665.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2412 edit
2018-05-29 03:10:40 -04:00
c059619e2c
GCC only supports power-of-2 component counts, so round up to next square.
2018-05-29 01:22:26 +01:00
c1e910d666
P4 to Git Change 1560456 by gandryey@gera-w8 on 2018/05/28 14:41:37
...
SWDEV-154862 - [CQE OCL][DTB][DTB-BLOCKER][Perf][QR][G] Upto 13% Performance drop observed while running CLFFT subtests due to Faulty CL #1559246
- Disable command queue notification if the event is on the same queue.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_common.hpp#22 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#27 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl.cpp#59 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_lqdflash_amd.cpp#24 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_memobj.cpp#82 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_profile_amd.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_sdi_amd.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_thread_trace_amd.cpp#9 edit
2018-05-28 14:56:22 -04:00
3699e74857
Add 1d texture types for NVCC path
2018-05-28 15:02:06 +05:30
176867f31b
P4 to Git Change 1560058 by johtaylo@johtaylo-jtincrementor2-increment on 2018/05/27 03:00:36
...
SWDEV-2 - Change OpenCL version number from 2663 to 2664.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2411 edit
2018-05-27 03:08:19 -04:00
b33876ee4d
Update math_functions.h
...
CUDA also has a function named labs.
2018-05-26 16:22:10 -04:00
61ff40a1cf
Update math_functions.cpp
...
CUDA also has a function named labs.
2018-05-26 16:21:14 -04:00
0f4a135e5f
Add missing alias half / half2 aliases
2018-05-26 12:10:50 +01:00
f2d23cbd01
P4 to Git Change 1560039 by johtaylo@johtaylo-jtincrementor2-increment on 2018/05/26 03:00:04
...
SWDEV-2 - Change OpenCL version number from 2662 to 2663.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2410 edit
2018-05-26 03:14:00 -04:00
b127488ea9
Adding double/long int signatures for abs
...
Adding overloads for abs that are found in cuda's math_functions.
2018-05-26 00:41:24 -04:00
13f37d550f
Adding double/long int signatures for abs
...
Adding overloads for abs that are found in cuda's math_functions.
2018-05-26 00:40:14 -04:00
9c43970a27
Add more function declarations to hip-clang
2018-05-25 16:18:46 -04:00
544adec793
Missing bits.
2018-05-25 20:15:04 +01:00
25ac508214
Missing bits.
2018-05-25 20:12:21 +01:00
40dad93426
Move converting constructor from _Float16 under macro guard. Refactor.
2018-05-25 19:46:41 +01:00
4e1c25c90d
P4 to Git Change 1559770 by gandryey@gera-w8 on 2018/05/25 12:44:43
...
SWDEV-79445 - OCL generic changes and code clean-up
- Switch to USWC memory for command buffers
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#99 edit
2018-05-25 12:49:57 -04:00
f53e86e1b8
Add math function declaration for hip-clang
2018-05-25 12:22:16 -04:00
ace88c8b63
P4 to Git Change 1559533 by johtaylo@johtaylo-jtincrementor2-increment on 2018/05/25 03:00:15
...
SWDEV-2 - Change OpenCL version number from 2661 to 2662.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2409 edit
2018-05-25 03:10:30 -04:00
be77b7fac1
P4 to Git Change 1559383 by gandryey@gera-w8 on 2018/05/24 18:38:36
...
SWDEV-79445 - OCL generic changes and code clean-up
- Remove memory reallocation interfaces. It was used for AMDIL path with HW constant buffers support. It seems AMDIL with SI+ doesn't enable HW const buffers.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#303 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#589 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#166 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#324 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.hpp#129 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.cpp#132 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.hpp#52 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#29 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#16 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.cpp#21 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.hpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#29 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.hpp#105 edit
2018-05-24 18:49:01 -04:00
e9039d398e
P4 to Git Change 1559366 by gandryey@gera-w8 on 2018/05/24 18:06:45
...
SWDEV-79445 - OCL generic changes and code clean-up
- Combine validateMemory() and arguments capture() under a single function. Rename validateMemory() in NDRangeKernelCommand class to captureAndValidate()
http://ocltc.amd.com/reviews/r/14964/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#22 edit
2018-05-24 18:12:49 -04:00
3ac03daffc
P4 to Git Change 1559366 by gandryey@gera-w8 on 2018/05/24 18:06:45
...
SWDEV-79445 - OCL generic changes and code clean-up
- Combine validateMemory() and arguments capture() under a single function. Rename validateMemory() in NDRangeKernelCommand class to captureAndValidate()
http://ocltc.amd.com/reviews/r/14964/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#22 edit
2018-05-24 18:12:49 -04:00
73dd22dba8
P4 to Git Change 1559366 by gandryey@gera-w8 on 2018/05/24 18:06:45
...
SWDEV-79445 - OCL generic changes and code clean-up
- Combine validateMemory() and arguments capture() under a single function. Rename validateMemory() in NDRangeKernelCommand class to captureAndValidate()
http://ocltc.amd.com/reviews/r/14964/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#22 edit
2018-05-24 18:12:49 -04:00
f095889106
P4 to Git Change 1559253 by gandryey@gera-w8 on 2018/05/24 15:44:23
...
SWDEV-79445 - OCL generic changes and code clean-up
- Following CL#1558704. Fix a regression with AMDIL path. Allocate default device sampler
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#588 edit
2018-05-24 15:56:10 -04:00
34f6e5c3cd
P4 to Git Change 1559246 by gandryey@gera-w8 on 2018/05/24 15:30:37
...
SWDEV-79445 - OCL generic changes and code clean-up
- Notify command queues about waiting events before command submission. That allows to issue a marker earlier to avoid extra latency when other jobs can be submitted before a notification in the worker thread.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_common.hpp#21 edit
2018-05-24 15:36:09 -04:00
27e0566c3a
Use 64x4 grid dims
2018-05-24 23:51:52 +05:30
aed2653857
Clean up and fix remaining bytes copy
2018-05-24 23:30:27 +05:30
9cdb308045
P4 to Git Change 1559149 by skudchad@skudchad_test2_win_opencl on 2018/05/24 11:54:02
...
SWDEV-145570 - [HIP] - Implement hipMemcpy2DToArray.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/14953/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#29 edit
2018-05-24 12:01:44 -04:00
bcea58f07f
P4 to Git Change 1559096 by gandryey@gera-w8 on 2018/05/24 10:34:47
...
SWDEV-79445 - OCL generic changes and code clean-up
- Remove obsolete logic for aliased kernels, since it was a pre-SI optimization
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#418 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#98 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#21 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#93 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.hpp#44 edit
2018-05-24 10:45:00 -04:00
59a046dd2d
Update hipTestHalf to actually test behaviour. Add missing hipHostfree.
2018-05-24 13:55:30 +01:00
f2a86f3e1c
Remove vestigial inline LLVMIR.
2018-05-24 12:46:14 +01:00
53a7c61e9b
Fix memcpy2d kernel dims
2018-05-24 17:00:12 +05:30
a245f46203
P4 to Git Change 1558894 by johtaylo@johtaylo-jtincrementor2-increment on 2018/05/24 03:00:04
...
SWDEV-2 - Change OpenCL version number from 2660 to 2661.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2408 edit
2018-05-24 03:11:44 -04:00
96b4618d26
Correct remaining bytes in copy 2d kernel
2018-05-24 08:27:24 +05:30
affe06135d
P4 to Git Change 1558704 by gandryey@gera-w8 on 2018/05/23 17:20:01
...
SWDEV-79445 - OCL generic changes and code clean-up
- ABI clean-up. Stage 1: Separate kernel arguments and OCL objects. OCL objects will be passed in the new arrays of mem objects, samplers and device queue objects. The kernel arguments will contain GPU virtual addresses.
http://ocltc.amd.com/reviews/r/14881/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#302 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#129 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#323 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.hpp#128 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.hpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#417 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#50 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#97 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.hpp#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#86 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#20 edit
2018-05-23 17:24:32 -04:00
2176dc3b19
P4 to Git Change 1558704 by gandryey@gera-w8 on 2018/05/23 17:20:01
...
SWDEV-79445 - OCL generic changes and code clean-up
- ABI clean-up. Stage 1: Separate kernel arguments and OCL objects. OCL objects will be passed in the new arrays of mem objects, samplers and device queue objects. The kernel arguments will contain GPU virtual addresses.
http://ocltc.amd.com/reviews/r/14881/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#302 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#129 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#323 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.hpp#128 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.hpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#417 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#50 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#97 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.hpp#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#86 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#20 edit
2018-05-23 17:24:32 -04:00
05fc09fe2c
P4 to Git Change 1558617 by vsytchen@vsytchen-win10 on 2018/05/23 15:39:19
...
SWDEV-153682 - Report cl_amd_planar_yuv extension in OpenCL
1. Enable cl_amd_planar_yuv extension for mainline.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/14948/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#301 edit
2018-05-23 15:50:44 -04:00
113c711b81
P4 to Git Change 1558526 by skudchad@skudchad_test2_win_opencl on 2018/05/23 13:34:33
...
SWDEV-145570 - [HIP] Implement hipPointerGetAttributes.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/14938/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#28 edit
2018-05-23 13:40:52 -04:00
a8a9f3bdc5
Merge branch 'feature_use_Float16' of https://github.com/ROCm-Developer-Tools/HIP into feature_use_Float16
2018-05-23 17:58:13 +01:00
ecefdd6541
Missing commit.
2018-05-23 17:57:47 +01:00
36e805cf76
Re-factor half support to match CUDA whilst exploiting native support.
2018-05-23 17:57:09 +01:00
4bff7e6b91
P4 to Git Change 1558428 by vsytchen@vsytchen-win10 on 2018/05/23 10:55:37
...
SWDEV-153051 - Maya 2018 unable to load OpenCL device on Vega 10 Lnx-Pro
1. Enable SVM on Lnx-Pro
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#89 edit
2018-05-23 12:19:25 -04:00
2c3d1498d4
Optimize memcpy2D kernel use
2018-05-23 14:43:47 +05:30
99d43874e6
P4 to Git Change 1558153 by johtaylo@johtaylo-jtincrementor2-increment on 2018/05/23 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2659 to 2660.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2407 edit
2018-05-23 03:10:21 -04:00
f17ee3da60
P4 to Git Change 1557880 by vsytchen@vsytchen-win10 on 2018/05/22 14:37:35
...
SWDEV-153682 - Report cl_amd_planar_yuv extension in OpenCL
ReviewBoardURL = http://ocltc.amd.com/reviews/r/14917/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#300 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.cpp#360 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/dx/OCLDX11Common.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/dx/OCLDX11Common.h#2 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/dx/OCLDX11NV12.cpp#4 delete
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/dx/OCLDX11NV12.h#2 delete
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/dx/OCLDX11YUY2.cpp#1 add
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/dx/OCLDX11YUY2.h#1 add
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/dx/TestList.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/dx/build/Makefile.dx#2 edit
2018-05-22 14:44:23 -04:00
foreman
Rahul Garg
lthakur
Maneesh Gupta
Alex Voicu
Jorghi12
Yaxun (Sam) Liu