AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
12 326 коммитов 3 Ветки 0 Теги
c4e5952687aa0d609a1c083c249e75babe0a67e6
Граф коммитов

11608 Коммитов

Автор SHA1 Сообщение Дата
foreman dc9db4eb3e P4 to Git Change 1611775 by gandryey@gera-ocl-lc on 2018/09/27 18:02:54 
SWDEV-79445 - OCL generic changes and code clean-up
	Program compilation clean-up. Step#6:
	- Move the second linkImpl() method to the abstraciton layer
	- Create the new setKernel virtual interface for the backend specific setup

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#320 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.hpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#41 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#79 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#35 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#57 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#91 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#40 edit


[ROCm/clr commit: 8bbcc1c38a]
 2018-09-27 18:15:24 -04:00
foreman c4c871ba6c P4 to Git Change 1611614 by wchau@wchau_OCL_boltzmann on 2018/09/27 12:54:16 
SWDEV-164014 - OCLPerfCounters results in "LLVM ERROR: out of memory"
	- use generic hsa_ven_amd_aqlprofile_pfn_t to point to extension function table

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccounters.hpp#3 edit


[ROCm/clr commit: 5616270bbd]
 2018-09-27 13:15:51 -04:00
foreman ef66c429a4 P4 to Git Change 1611613 by gandryey@gera-w8 on 2018/09/27 12:54:08 
SWDEV-79445 - OCL generic changes and code clean-up
	Program compilation clean-up. Step#5:
	- Move the first linkImpl() method to the abstraciton layer. Utilize the new method in GPU/PAL/ROCr backends

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.cpp#244 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.hpp#77 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#78 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#34 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#39 edit


[ROCm/clr commit: e428107060]
 2018-09-27 13:10:59 -04:00
Evgeny Mankov 821b36d636 [HIPIFY][cmake] CUDA 10.0 is not supported. 
[ROCm/clr commit: 4e7b330037]
 2018-09-27 19:05:22 +03:00
foreman 58b8d2fc4b P4 to Git Change 1611372 by chui@ocl-promo-incrementor on 2018/09/27 02:56:48 
SWDEV-2 - Change OpenCL version number from 2746 to 2747.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2494 edit


[ROCm/clr commit: aa557b6fdc]
 2018-09-27 03:07:08 -04:00
foreman 7edb3642a2 P4 to Git Change 1611191 by wchau@wchau_OCL_boltzmann on 2018/09/26 17:00:31 
SWDEV-164014 - OCLPerfCounters results in "LLVM ERROR: out of memory"
	- replace deprecated  'hsa_system_get_extension_table()' call with 'hsa_system_get_major_extension_table() with table size of “hsa_ven_amd_aqlprofile_1_00_pfn_t”

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccounters.hpp#2 edit


[ROCm/clr commit: b1eed992e1]
 2018-09-26 17:14:11 -04:00
foreman dfe67fa6da P4 to Git Change 1611180 by gandryey@gera-ocl-lc on 2018/09/26 16:54:02 
SWDEV-79445 - OCL generic changes and code clean-up
	- Fix Ellesmere compilation with LC path. Switch to multiple device info fields to support LC and HSAIL at the same time

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#110 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#77 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#33 edit


[ROCm/clr commit: 42e7f37f69]
 2018-09-26 17:10:57 -04:00
Wen-Heng (Jack) Chung 73fc21f717 Keep the map which tracks GPU kernel symbols to grow monotonically 
[ROCm/clr commit: e257de95f3]
 2018-09-26 19:49:02 +00:00
Wen-Heng (Jack) Chung 1e956fcd70 Improve performance of re-initialization logic 
Keep track of shared libaries already discovered. Do not build HSA executables
for them.


[ROCm/clr commit: 060b3c0bf8]
 2018-09-26 19:48:56 +00:00
Wen-Heng (Jack) Chung 4e0f0b3e89 HIP program state re-initialization logic 
This commit is to support kernels dynamically loaded thru means such as
dlopen() after HIP runtime initializes.


[ROCm/clr commit: 319f007bf1]
 2018-09-26 19:48:47 +00:00
Evgeny Mankov e9acd2671d [HIPIFY][docs] Fix typos in Readme.md 
[ROCm/clr commit: 6056686796]
 2018-09-26 17:26:25 +03:00
Evgeny Mankov a4c3741ec7 Merge pull request #690 from emankov/hipBLAS 
[HIPIFY][doc] Update README.md due to new LLVM 7.0.0 and CUDA 10.0 re…

[ROCm/clr commit: e879118d87]
 2018-09-26 17:05:47 +03:00
Evgeny Mankov 298ca9b3cd [HIPIFY][doc] Update README.md due to new LLVM 7.0.0 and CUDA 10.0 releases. 
[ROCm/clr commit: a7e75c72ee]
 2018-09-26 17:01:59 +03:00
Rahul Garg e0efc8a09e Return hipSuccess when sizeBytes=0 in hipMemset 
[ROCm/clr commit: bd27310127]
 2018-09-26 12:47:36 +05:30
foreman ac219d7500 P4 to Git Change 1610802 by chui@ocl-promo-incrementor on 2018/09/26 02:57:16 
SWDEV-2 - Change OpenCL version number from 2745 to 2746.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2493 edit


[ROCm/clr commit: e17b448874]
 2018-09-26 03:05:06 -04:00
Maneesh Gupta 27986e6788 Merge pull request #685 from ROCm-Developer-Tools/hip-trig-return 
Improve hip_trig test case

[ROCm/clr commit: 802520f5f1]
 2018-09-26 09:50:48 +05:30
foreman e2a6a8e8ba P4 to Git Change 1610640 by gandryey@gera-w8 on 2018/09/25 17:34:09 
SWDEV-79445 - OCL generic changes and code clean-up
	Program compilation clean-up. Step#4:
	- Add common method FindGlobalVarSize() and metadata setup to the abstraction layer

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.hpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#76 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#89 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#38 edit


[ROCm/clr commit: 40bfc4cf20]
 2018-09-25 17:47:26 -04:00
foreman 17234d5abb P4 to Git Change 1610625 by gandryey@gera-w8 on 2018/09/25 17:00:40 
SWDEV-79445 - OCL generic changes and code clean-up
	- Fix RGP capture. Add the engine mask.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#7 edit


[ROCm/clr commit: f24fdb6d53]
 2018-09-25 17:14:51 -04:00
Aaron Enye Shi 4d59fbbcbe Use sinf and cosf from ocml device libs 
Using llvm_amdgcn builtin fails to produce accurate values, we should move to using the ocml device library versions.


[ROCm/clr commit: eeb6c11050]
 2018-09-25 19:31:39 +00:00
foreman 909f353400 P4 to Git Change 1610499 by skudchad@skudchad-lnx on 2018/09/25 14:43:35 
SWDEV-145570 - [HIP] - Map hipinfo sample from HIP mirror so that we have the same hipinfo

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_peer.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/tools/hipinfo/CMakeLists.txt#2 edit
... //depot/stg/opencl/drivers/opencl/tools/hipinfo/build/Makefile.hipinfo#2 edit
... //depot/stg/opencl/drivers/opencl/tools/hipinfo/hipinfo.cpp#2 delete


[ROCm/clr commit: 8d912e037a]
 2018-09-25 15:01:11 -04:00
foreman addd208e25 P4 to Git Change 1610376 by gandryey@gera-w8 on 2018/09/25 11:50:37 
SWDEV-79445 - OCL generic changes and code clean-up
	- Fix HIP failures

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#5 edit


[ROCm/clr commit: 90339a205f]
 2018-09-25 12:03:21 -04:00
Aaron Enye Shi 20e9391cfb Use trig functions from ocml instead 
[ROCm/clr commit: 04ed44f074]
 2018-09-25 15:58:36 +00:00
foreman 7cf7b1d6eb P4 to Git Change 1610362 by gandryey@gera-w8 on 2018/09/25 11:39:08 
SWDEV-79445 - OCL generic changes and code clean-up
	- Attempt to fix HIP failures with VDI/ROCm

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#4 edit


[ROCm/clr commit: dfe166ffc1]
 2018-09-25 11:48:56 -04:00
Evgeny Mankov 2a6861aa64 Merge pull request #687 from emankov/hipBLAS 
[HIPIFY][BLAS] Add support of hipblasGemmEx and corresponding types

[ROCm/clr commit: d12c1f7eff]
 2018-09-25 18:48:06 +03:00
Evgeny Mankov 11dde91716 [HIPIFY][BLAS] Add support of hipblasGemmEx and corresponding types 
TODO (hipBLAS/HIP): rename hipblasDatatype_t to hipDataType_t and move it from hipBLAS to HIP, as Data types are used not only in BLAS library.


[ROCm/clr commit: 65035fa485]
 2018-09-25 18:46:23 +03:00
Evgeny Mankov 37b1248da2 [HIPIFY][docs] Update CUDNN_API_supported_by_HIP.md 
[ROCm/clr commit: f627d9a9a2]
 2018-09-25 16:50:40 +03:00
foreman 68a8442e48 P4 to Git Change 1610187 by chui@ocl-promo-incrementor on 2018/09/25 02:56:08 
SWDEV-2 - Change OpenCL version number from 2744 to 2745.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2492 edit


[ROCm/clr commit: 6b4875aad1]
 2018-09-25 03:13:52 -04:00
foreman 0821f2167f P4 to Git Change 1610043 by gandryey@gera-w8 on 2018/09/24 18:08:36 
SWDEV-79445 - OCL generic changes and code clean-up
	Program compilation clean-up. Step#3:
	- Move getCompilationStagesFromBinary and getNextCompilationStageFromBinary to the abstraction layer.
	- Share the same functionality across GSL, PAL and ROCr backends

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.hpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.cpp#243 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.hpp#76 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#39 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#75 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#37 edit


[ROCm/clr commit: dee2f4bd71]
 2018-09-24 18:21:56 -04:00
Aaron Enye Shi 4bbfaf06b5 Fix missing HIP_ASSERT in hip_trig 
[ROCm/clr commit: bc5de031a5]
 2018-09-24 15:01:24 +00:00
foreman e6bd08e537 P4 to Git Change 1609737 by chui@ocl-promo-incrementor on 2018/09/24 02:56:48 
SWDEV-2 - Change OpenCL version number from 2743 to 2744.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2491 edit


[ROCm/clr commit: 3f52205ed1]
 2018-09-24 03:05:55 -04:00
Maneesh Gupta 0d75b78a5a Merge pull request #683 from ROCm-Developer-Tools/hip-float-rounded 
Disable non-default-rounded functions

[ROCm/clr commit: ad008c5e3f]
 2018-09-24 09:32:52 +05:30
foreman 10daea455a P4 to Git Change 1609674 by chui@ocl-promo-incrementor on 2018/09/22 02:56:48 
SWDEV-2 - Change OpenCL version number from 2742 to 2743.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2490 edit


[ROCm/clr commit: 0485435543]
 2018-09-22 03:08:01 -04:00
foreman 457ada789a P4 to Git Change 1609437 by kzhuravl@kzhuravl-fiji-ocllc-2 on 2018/09/21 15:26:55 
SWDEV-79445 - Follow up for CL 1609403: clinfo: return EXIT_SUCCESS on success, EXIT_FAILURE on failure:

	 - Purge status
	 - Return EXIT_SUCCESS

Affected files ...

... //depot/stg/opencl/drivers/opencl/tools/clinfo/clinfo.cpp#7 edit


[ROCm/clr commit: 016454cd01]
 2018-09-21 15:34:52 -04:00
Aaron Enye Shi f4fc30ccc7 Improve hip_trig test case 
Hip_trig is failing but returning a passing value on HIP-Clang.  Also update with debug output and free arrays used.

[ROCm/clr commit: afef6a3ece]
 2018-09-21 15:28:10 -04:00
foreman 66b72cf9b7 P4 to Git Change 1609403 by kzhuravl@kzhuravl-fiji-ocllc-2 on 2018/09/21 14:35:36 
SWDEV-79445 - clinfo: return EXIT_SUCCESS on success, EXIT_FAILURE on failure.

Affected files ...

... //depot/stg/opencl/drivers/opencl/tools/clinfo/clinfo.cpp#6 edit


[ROCm/clr commit: d4ffba0544]
 2018-09-21 14:44:45 -04:00
foreman 7d875491ac P4 to Git Change 1609107 by chui@ocl-promo-incrementor on 2018/09/21 02:56:52 
SWDEV-2 - Change OpenCL version number from 2741 to 2742.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2489 edit


[ROCm/clr commit: 5f85745b21]
 2018-09-21 03:07:49 -04:00
Maneesh Gupta 4219d3d796 Merge pull request #684 from ROCm-Developer-Tools/mangupta-patch-2 
[ci] Renable nvcc testing

[ROCm/clr commit: 5468e01d04]
 2018-09-21 11:05:45 +05:30
Maneesh Gupta 203e3dd5d5 Update hipTestFMA.cpp 
[ROCm/clr commit: a4bdbe0aaf]
 2018-09-21 11:00:08 +05:30
Maneesh Gupta e300bdf211 [ci] Renable nvcc testing 
Change-Id: I7d720b41a3ddc99453fee8b9be30494bfec3a808


[ROCm/clr commit: cc4e8c7e8b]
 2018-09-21 10:11:31 +05:30
foreman c5b9715a6b P4 to Git Change 1608975 by gandryey@gera-w8 on 2018/09/20 18:14:01 
SWDEV-79445 - OCL generic changes and code clean-up
	Program compilation clean-up. Follwoing CL#1608319:
	- Switch HSAIL GSL path to the common compilation method

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpucompiler.cpp#160 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#168 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#332 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.cpp#242 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.hpp#75 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#74 edit


[ROCm/clr commit: dbe7f3201d]
 2018-09-20 18:26:16 -04:00
Aaron Enye Shi 646de2e876 Disable non-default-rounded functions 
Device library has removed the non-default-rounded functions, so hipFloatMath will fail to build. These include the removal of __ocml_sqrt_rte, __ocml_sqrt_rtn, __ocml_sqrt_rtp, and __ocml_sqrt_rtz. As seen here: https://github.com/RadeonOpenCompute/ROCm-Device-Libs/commit/2fc04e10e1354edee331ce700f98a60f8255effb . Disable these function tests for now, until they are re-enabled, or deleted completely.

[ROCm/clr commit: a3dea28c9d]
 2018-09-20 16:33:32 -04:00
Maneesh Gupta f648d28bcb Merge pull request #614 from ROCm-Developer-Tools/fma 
Add overloading resolution functions for fma

[ROCm/clr commit: 7cec85e1ae]
 2018-09-20 13:38:03 +05:30
foreman d98750b0bb P4 to Git Change 1608510 by chui@ocl-promo-incrementor on 2018/09/20 02:56:50 
SWDEV-2 - Change OpenCL version number from 2740 to 2741.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2488 edit


[ROCm/clr commit: c48abf1c3d]
 2018-09-20 03:08:58 -04:00
Maneesh Gupta f742125288 Update hipTestFMA.cpp 
Fix the test so that it works on nvcc path as well.

[ROCm/clr commit: e614aac0da]
 2018-09-20 11:23:51 +05:30
Maneesh Gupta 1e11b0352b Merge pull request #682 from aaronenyeshi/hip-config-files 
Create separate config files for hcc and clang

[ROCm/clr commit: ff8bdd0375]
 2018-09-20 11:21:31 +05:30
foreman ca5028dfd4 P4 to Git Change 1608381 by skudchad@skudchad-lnx on 2018/09/19 19:40:29 
SWDEV-145570 - [HIP] - Fix HIP build break caused by CL#1608319

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.hpp#107 edit


[ROCm/clr commit: 6313e9af46]
 2018-09-19 19:49:37 -04:00
foreman 1238139fab P4 to Git Change 1608319 by gandryey@gera-lnx-rcf-lc on 2018/09/19 16:55:11 
SWDEV-79445 - OCL generic changes and code clean-up
	Program compilation clean-up. Step#2:
	- Combine PAL and ROCr implementations of compilation under common methods in device::Program for HSAIL and LC.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#319 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.hpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.hpp#74 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#26 delete
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#34 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#73 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#30 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#46 delete
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#36 edit


[ROCm/clr commit: e132af9cad]
 2018-09-19 17:06:20 -04:00
Aaron Enye Shi ee366fad74 Create separate config files for hcc and clang 
The state of HIP_COMPILER is not passing into config files, therefore config files cannot use if statements to determine dependency. For HIP-Clang, we should remove find_dependency(hcc), so we create separate config files depending on compiler path. This fixes issue in apps that uses hip-config.cmake.


[ROCm/clr commit: 73a5ea0f9f]
 2018-09-19 18:29:56 +00:00
Yaxun Sam Liu 2f6bee46f9 Silent warnings about duplicate static keyword 
static is already in __DEVICE__, so should be removed.


[ROCm/clr commit: cfa71293ce]
 2018-09-19 10:39:45 -04:00
Yaxun Sam Liu a7b03bee08 Add fma function with float and _Float16 arguments 
[ROCm/clr commit: a8bed200b7]
 2018-09-19 09:59:33 -04:00