AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
13 453 коммитов 3 Ветки 0 Теги
d4275741ba9c0ea5d72294de061f99ab884bf0d4
Граф коммитов

12735 Коммитов

Автор SHA1 Сообщение Дата
foreman 162c2c9ff1 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


[ROCm/clr commit: b8a9cdb20e]
 2018-05-30 16:22:34 -04:00
Rahul Garg b58a81f80e Fixed texture obj 1Dfetch test 
[ROCm/clr commit: 7cfd059919]
 2018-05-30 21:54:51 +05:30
Yaxun (Sam) Liu 999df03229 Add more function declarations for hip-clang 
[ROCm/clr commit: 27fe2283d6]
 2018-05-30 06:51:03 -04:00
Yaxun (Sam) Liu 859b4f218a Drop --amdgpu-target= options for hip-clang 
They are replaced by --cuda-gpu-arch= options elsewhere


[ROCm/clr commit: 3609e6f3b2]
 2018-05-30 06:47:44 -04:00
Maneesh Gupta 92757a7033 Merge pull request #469 from yxsamliu/fun 
Add math function declaration for hip-clang

[ROCm/clr commit: e5b8358b05]
 2018-05-30 15:01:27 +05:30
foreman b70fc13a52 P4 to Git Change 1561407 by johtaylo@johtaylo-jtincrementor2-increment on 2018/05/30 03:00:07 
SWDEV-2 - Change OpenCL version number from 2665 to 2666.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2413 edit


[ROCm/clr commit: 7a0c50c4c5]
 2018-05-30 03:08:52 -04:00
Maneesh Gupta 5108258a02 Merge pull request #477 from mangupta/hipfuncgetattr_nvcc 
Add signature for hipFuncGetAttributes to nvcc_details

[ROCm/clr commit: ab579ae0e3]
 2018-05-30 12:29:03 +05:30
Rahul Garg 6126733ebe Fixed tex1dFetch test 
[ROCm/clr commit: 3b0842e70a]
 2018-05-30 11:42:01 +05:30
Maneesh Gupta cd912ecf7f [dtests] Fix nvcc path build errors in hipFuncGetAttributes.tst 
Change-Id: I000bed69162897f7b6edd733ed6e9acc93beb0ed


[ROCm/clr commit: e2842f2f28]
 2018-05-30 11:26:11 +05:30
Maneesh Gupta b04a576c12 Add signature for hipFuncGetAttributes to nvcc_details 
Change-Id: I06d5b50028fcfe3ea9d81f749b02be6b094c0977


[ROCm/clr commit: a923cac5d5]
 2018-05-30 11:24:48 +05:30
Rahul Garg a4aa29f24b Fix hipBindTexture on NVCC path 
[ROCm/clr commit: d74353b112]
 2018-05-30 10:59:07 +05:30
foreman 6cf9698d6a P4 to Git Change 1561359 by todli@todli-win-opencl-kv1 on 2018/05/30 01:19:53 
SWDEV-152361 - add memory reference to MainEngine queue before initializing BusAddressable memory

	http://ocltc.amd.com/reviews/r/14978/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#101 edit


[ROCm/clr commit: 818a6d46d2]
 2018-05-30 01:27:28 -04:00
Maneesh Gupta 5d5afbf558 Merge pull request #475 from gargrahul/fix_tex2d_tests 
Fix tex2D tests for result value

[ROCm/clr commit: d2cfa6e5e2]
 2018-05-30 08:34:51 +05:30
Maneesh Gupta b074d762fa Merge pull request #472 from Jorghi12/patch-3 
Adding double/long int signatures for abs

[ROCm/clr commit: 3327a9a2de]
 2018-05-30 08:32:14 +05:30
Maneesh Gupta c510903a32 Merge pull request #471 from Jorghi12/patch-4 
Adding double/long int signatures for abs

[ROCm/clr commit: fde0613554]
 2018-05-30 08:31:32 +05:30
Maneesh Gupta 7bf1ca2fd6 Merge pull request #465 from gargrahul/optimize_memcpy2d 
Optimize memcpy2D kernel use

[ROCm/clr commit: fb23ccab58]
 2018-05-30 08:31:16 +05:30
foreman beb46a0a30 P4 to Git Change 1561216 by gandryey@gera-w8 on 2018/05/29 18:05:31 
SWDEV-79445 - OCL generic changes and code clean-up
	- Remove parent_ field from the device object, since it was used for subdevices only.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_device.cpp#72 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#219 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#304 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#590 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#91 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.hpp#45 edit


[ROCm/clr commit: 0680df2550]
 2018-05-29 18:13:40 -04:00
foreman 5a5440390d P4 to Git Change 1561216 by gandryey@gera-w8 on 2018/05/29 18:05:31 
SWDEV-79445 - OCL generic changes and code clean-up
	- Remove parent_ field from the device object, since it was used for subdevices only.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_device.cpp#72 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#219 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#304 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#590 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#91 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.hpp#45 edit


[ROCm/clr commit: 12315470b7]
 2018-05-29 18:13:40 -04:00
foreman 43b1be9b7b 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


[ROCm/clr commit: a36ef232f2]
 2018-05-29 13:50:48 -04:00
foreman fc8c13f7a6 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


[ROCm/clr commit: 51a4d1865c]
 2018-05-29 13:18:29 -04:00
Rahul Garg 914abf8c41 Fix runTest return type 
[ROCm/clr commit: dabe2fda39]
 2018-05-29 16:18:14 +05:30
Rahul Garg 51f21711a7 Fix tex2D tests for result value 
[ROCm/clr commit: 28c878f266]
 2018-05-29 16:03:37 +05:30
lthakur 53dc974461 HIP test case for 1D texture fetch (#424) 
[ROCm/clr commit: 366a0a97ca]
 2018-05-29 14:08:01 +05:30
foreman 93e9f2ab8c 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


[ROCm/clr commit: 616c2272b0]
 2018-05-29 03:10:40 -04:00
Alex Voicu 377b028628 GCC only supports power-of-2 component counts, so round up to next square. 
[ROCm/clr commit: c059619e2c]
 2018-05-29 01:22:26 +01:00
foreman 191b65b155 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


[ROCm/clr commit: c1e910d666]
 2018-05-28 14:56:22 -04:00
Rahul Garg f40b06757c Add 1d texture types for NVCC path 
[ROCm/clr commit: 3699e74857]
 2018-05-28 15:02:06 +05:30
foreman 5f9d181406 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


[ROCm/clr commit: 176867f31b]
 2018-05-27 03:08:19 -04:00
Jorghi12 8a2d7a25b1 Update math_functions.h 
CUDA also has a function named labs.

[ROCm/clr commit: b33876ee4d]
 2018-05-26 16:22:10 -04:00
Jorghi12 9b43fd84d0 Update math_functions.cpp 
CUDA also has a function named labs.

[ROCm/clr commit: 61ff40a1cf]
 2018-05-26 16:21:14 -04:00
Alex Voicu 0a2d514cf8 Add missing alias half / half2 aliases 
[ROCm/clr commit: 0f4a135e5f]
 2018-05-26 12:10:50 +01:00
foreman a10a7a4cfb 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


[ROCm/clr commit: f2d23cbd01]
 2018-05-26 03:14:00 -04:00
Jorghi12 43d55a79e4 Adding double/long int signatures for abs 
Adding overloads for abs that are found in cuda's math_functions.

[ROCm/clr commit: b127488ea9]
 2018-05-26 00:41:24 -04:00
Jorghi12 fbbaedfdea Adding double/long int signatures for abs 
Adding overloads for abs that are found in cuda's math_functions.

[ROCm/clr commit: 13f37d550f]
 2018-05-26 00:40:14 -04:00
Yaxun (Sam) Liu c7d481a812 Add more function declarations to hip-clang 
[ROCm/clr commit: 9c43970a27]
 2018-05-25 16:18:46 -04:00
Alex Voicu badea56b4f Missing bits. 
[ROCm/clr commit: 544adec793]
 2018-05-25 20:15:04 +01:00
Alex Voicu 0dfdaf1808 Missing bits. 
[ROCm/clr commit: 25ac508214]
 2018-05-25 20:12:21 +01:00
Alex Voicu 7a480af716 Move converting constructor from _Float16 under macro guard. Refactor. 
[ROCm/clr commit: 40dad93426]
 2018-05-25 19:46:41 +01:00
foreman b711ac621d 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


[ROCm/clr commit: 4e1c25c90d]
 2018-05-25 12:49:57 -04:00
Yaxun (Sam) Liu 494f7f6a38 Add math function declaration for hip-clang 
[ROCm/clr commit: f53e86e1b8]
 2018-05-25 12:22:16 -04:00
foreman 687b6d3290 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


[ROCm/clr commit: ace88c8b63]
 2018-05-25 03:10:30 -04:00
foreman 362cecebe0 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


[ROCm/clr commit: be77b7fac1]
 2018-05-24 18:49:01 -04:00
foreman 8e925ae2a8 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


[ROCm/clr commit: e9039d398e]
 2018-05-24 18:12:49 -04:00
foreman e6bfc8fbed 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


[ROCm/clr commit: 3ac03daffc]
 2018-05-24 18:12:49 -04:00
foreman fd627bea6d 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


[ROCm/clr commit: 73dd22dba8]
 2018-05-24 18:12:49 -04:00
foreman 91e6e15a1e 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


[ROCm/clr commit: f095889106]
 2018-05-24 15:56:10 -04:00
foreman 4378898d00 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


[ROCm/clr commit: 34f6e5c3cd]
 2018-05-24 15:36:09 -04:00
Rahul Garg 0ab5c9d6f1 Use 64x4 grid dims 
[ROCm/clr commit: 27e0566c3a]
 2018-05-24 23:51:52 +05:30
Rahul Garg 439655d213 Clean up and fix remaining bytes copy 
[ROCm/clr commit: aed2653857]
 2018-05-24 23:30:27 +05:30
foreman bf393cab7a 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


[ROCm/clr commit: 9cdb308045]
 2018-05-24 12:01:44 -04:00