AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5,048 Commits 3 Branches 0 Tags
cd92bd7feed141d24da4d7a50e2b24eb3993d3cd
Commit Graph

5048 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Evgeny Mankov 1bf6deb149 [HIPIFY][tests] Add occupancy test 2019-09-02 17:54:06 +03:00
Evgeny Mankov 9f3a90e174 Merge pull request #1383 from emankov/hipify-clang 
[HIPIFY][fix] Fix for upcoming LLVM 10.0
 2019-09-01 18:16:24 +03:00
Evgeny Mankov ce4140f94d [HIPIFY][fix] Fix for upcoming LLVM 10.0 2019-09-01 18:15:03 +03:00
Rahul Garg 521a162870 Merge pull request #1378 from ssahasra/no-as 
remove obsolete test for OCKL Asynchronous Streams
 2019-08-30 19:05:37 -07:00
Jenkins 6c776daba1 Merge 'master' into 'amd-master' 
Change-Id: I85682ce0d64ef617489640f6f16bafff2a698585
 2019-08-30 18:18:49 -04:00
Sameer Sahasrabuddhe 70023c9075 remove obsolete test for OCKL Asynchronous Streams 
The implementation for OCKL AS was recently removed from the device
library since that feature is now superseded by hostcall.
 2019-08-30 20:41:29 +05:30
Evgeny Mankov 57760c6a57 Merge pull request #1375 from emankov/hipify-clang 
[HIPIFY][DNN] cuDNN 7.6.3 support
 2019-08-30 17:26:29 +03:00
foreman d484ac0098 P4 to Git Change 1991227 by cpaquot@cpaquot-ocl-lc-lnx on 2019/08/29 17:26:37 
SWDEV-193938 - [HIP] Use fine grained pool for hipHostRegister

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#69 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.cpp#43 edit
 2019-08-29 17:35:38 -04:00
Evgeny Mankov b45c26361d [HIPIFY][DNN] cuDNN 7.6.3 support 2019-08-29 19:55:38 +03:00
Evgeny Mankov 5d0b628142 Merge pull request #1372 from emankov/master 
[HIPIFY][#207][fix] Translate all preprocessor's conditional blocks
 2019-08-29 10:30:05 +03:00
Yaxun (Sam) Liu c404312ffe Fix sample 11_texture_driver for hip-clang (#1370) 2019-08-29 01:03:20 +00:00
Yaxun (Sam) Liu b046ec698b Do not change opt level for -g for hip-clang (#1369) 
Currently hipcc uses -O3 for hip-clang by default but uses -O0 if -g is used. This
causes surprise for users since -g should not affect default opt level.
 2019-08-29 01:03:11 +00:00
Sarbojit2019 0722704f35 Updated hipErrorString and CUDAErrorTohipError (#1365) 2019-08-29 01:02:59 +00:00
Sarbojit2019 5c4f78bac3 [HIP] Reclaiming hipLaunchKernel API (#1353) 
* [HIP] Reclaiming hipLaunchKernel API

* Reclaiming hipLaunchKernel : Incorporated review comments

* Incorporated review comments

* Removed hipLaunchKernel Macro from nvcc path
 2019-08-29 01:02:41 +00:00
satyanveshd f807cc1a7b [sample] add new cookbook sample - occupancy (#1352) 
* occupancy.cpp with Makefile

* occupancy sample changes according tothe comments

* Changes according to the review comments

* Occupancy Sample Changes

* Changes according to review comments
 2019-08-29 01:01:49 +00:00
mshivama d75dc4eb29 Device side support for Cooperative Group feature (#1202) 
* first cut of the header implementation of cooperative group feature

* add diclarations for device library functions

* fixed various compile time issues in the CG headers

* enabled copy construction and copy assignment

* fixed a minor bug related to conditional compilation macro

* fixed few more CG constructor issues and added a unit testcase

* fixed typo

* extended unit testcase

* compute size of partitioned CG from mask

* bit of code refactoring

* removed boilerplate code

* fixed few of the review comments by Brian

* Changes to the sigantures of few grid and multi-grid related OCKL functions

* changes to declarations of OCKL functions related to CG feature

* removed all the block level support as it is not planned for 2.9

* Have taken care of review comments by Brian

* Have taken care of review comments by Brian

* removed unused functions which were initially intended to use in block level cg support
 2019-08-29 01:01:25 +00:00
Evgeny Mankov 24be21495d [HIPIFY][#207][fix] Translate all preprocessor's conditional blocks 
+ Start to translate preprocessor's false conditional blocks too:
  based on clang's https://reviews.llvm.org/D66597;
  available only starting from LLVM 10.0 or trunk.
+ Option -skip-excluded-preprocessor-conditional-blocks for skipping excluded conditional blocks:
  the default behavior for hipify-clang built with LLVM < 10.0;
  false by default for hipify-clang built with LLVM 10 or trunk.
+ Add 4 preprocessor unit tests, 2 of which are LLVM 10.0 only
+ Update couple of existing tests by setting -skip-excluded-preprocessor-conditional-blocks option:
  update lit testing accordingly
 2019-08-28 21:17:35 +03:00
Evgeny Mankov 1ab81d9ce6 Merge pull request #1371 from emankov/master 
[HIPIFY][cmake] Minor refactoring
 2019-08-28 20:42:41 +03:00
Evgeny Mankov eeb4452b23 [HIPIFY][cmake] Minor refactoring 
1. Fix setting std c++ (11|14)
2. Get rid of WIN32, use MSVC instead
3. Use VERSION_GREATER_EQUAL and VERSION_MAJOR instead of logical expressions
 2019-08-28 20:40:10 +03:00
foreman dd07e24c2b P4 to Git Change 1990032 by cpaquot@cpaquot-ocl-lc-lnx on 2019/08/27 20:20:36 
SWDEV-145570 - [HIP] Add missing HIP_INIT_API macros and more debug printf.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#39 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_stream.cpp#23 edit
 2019-08-27 20:26:25 -04:00
Jenkins 1518155479 Merge 'master' into 'amd-master' 
Change-Id: I082d987c30677ca9dc117f6825811584c7c6d262
 2019-08-27 06:25:11 -04:00
Maneesh Gupta 5d95ffa010 [packaging] update soft-links that already exist (#1364) 
Change-Id: Ibe9840802b1765094ef998edf2210e95404cb989
 2019-08-26 23:41:14 -04:00
Jenkins 73fcedc603 Merge 'master' into 'amd-master' 
Change-Id: I89845b0c0d8a6196b291803106d891d2996dd363
 2019-08-26 18:06:50 -04:00
foreman b05d95cb8e P4 to Git Change 1989149 by kjayapra@0_HIPWS_P2P_ROCM on 2019/08/26 15:30:45 
SWDEV-188177 - Adding ihipTexture APIs to hip_hcc.def.in

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#21 edit
 2019-08-26 15:44:58 -04:00
foreman 3cb2dd541a P4 to Git Change 1989089 by kjayapra@0_HIPWS_P2P_ROCM on 2019/08/26 14:24:21 
SWDEV-198194 - Delete vars at __hipUnregisterFatBinary.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_internal.hpp#39 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#40 edit
 2019-08-26 14:32:48 -04:00
Rahul Garg 905891645c Merge pull request #1367 from mhbliao/hliao/master/swdev-201262 
[hcc] Fix previous replacement of `result_of_t`.
 2019-08-26 09:17:58 -07:00
Michael LIAO 63e47e525b [hcc] Fix previous replacement of result_of_t. 
- `result_of_t` is defined as the shortcut of
  ```
  template< class T >
  using result_of_t = typename result_of<T>::type;
  ```
 2019-08-26 10:58:38 -04:00
Jenkins 78cfbf69f2 Merge 'master' into 'amd-master' 
Change-Id: I4f54ac4fd1993ab9dfca9aa34a153e9eb86f45ae
 2019-08-26 05:10:22 -04:00
ramcherukuri 3a6ca29815 moving result_of_t to result_of 2019-08-24 08:59:58 -04:00
foreman d3bbe46d39 P4 to Git Change 1988496 by cpaquot@cpaquot-ocl-lc-lnx on 2019/08/23 19:43:16 
SWDEV-199002 - [HIP] Add hipExtLaunchMultiKernelMultiDevice to in files.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#20 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#22 edit
 2019-08-23 19:46:27 -04:00
Evgeny Mankov 9c25434615 Merge pull request #1360 from emankov/master 
[HIPIFY][cmake] Explicitly set c++14
 2019-08-23 19:40:53 +03:00
Evgeny Mankov e1d4f8510a [HIPIFY][cmake] Explicitly set c++14 
[Reason] LLVM became c++14 last week due to the following change:

37508d3dd94b0154861a90b1909d17b01400df99
Replace llvm::integer_sequence and friends with the C++14 standard version
 2019-08-23 19:32:24 +03:00
foreman ffd74944fe P4 to Git Change 1988234 by kjayapra@3_HIPWS_TXT_ROCM on 2019/08/23 12:12:45 
SWDEV-201068 - Reverting back CL 1987582.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#84 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#98 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#96 edit
 2019-08-23 12:15:29 -04:00
Sarbojit2019 7257f23063 Added missing device prop fields into hipInfo sample (#1357) 
* Added prop.integrated into hipInfo sample

* Added missing deviceProp fileds in hipInfo
 2019-08-23 09:21:47 +00:00
Rahul Garg 0fd14a3e13 Make Bundled_code_header visible for hipRTC usage (#1359) 2019-08-23 09:20:02 +00:00
chrispaquot 344d150bf8 Set device before processing each one (#1358) 2019-08-23 09:19:50 +00:00
Aryan Salmanpour 5066700ace [hip] add initial implementation for hipLaunchCooperativeKernel API (#1339) 
* [hip] add initial implementation for hipLaunchCooperativeKernel API

* [hip] use total number of work groups to initialize the GWS resource

* [hip] use only one argument for init_gws kernel

* [hip] use the device associated with the stream for checking the device properties
 2019-08-23 09:19:35 +00:00
Rahul Garg 71559200c0 Fix memcpy with IPC slowness (#1321) 
* Fix memcpy with IPC slowness

* Make early erroneous returns

* Real Clean up

* Real Clean up++
 2019-08-23 09:19:18 +00:00
foreman 373d64478c P4 to Git Change 1987598 by gandryey@gera-win10 on 2019/08/22 13:29:18 
SWDEV-197289 - VDI tracing API integration in rocTracer
	- Add profiling activity callbacks for HIP API. The logic will utilize the  current profiling mechanism inside VDI

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_activity.cpp#1 add
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#19 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#21 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#246 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#341 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#426 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.hpp#145 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#148 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#64 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#83 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/activity.cpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/platform/activity.hpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#97 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#95 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/prof_protocol.h#1 add
 2019-08-22 13:48:47 -04:00
foreman 6577ecf5d3 P4 to Git Change 1987582 by cpaquot@cpaquot-ocl-lc-lnx on 2019/08/22 13:20:28 
SWDEV-185742 - [HIP] Add a svm path to avoid analyzing the mem objs
	and just memcpy the kernel args

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#82 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#96 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#94 edit
 2019-08-22 13:26:57 -04:00
foreman ea22166353 P4 to Git Change 1987529 by kjayapra@4_HIPWS_RCCM_ROCM on 2019/08/22 12:32:42 
SWDEV-200625 - Reverting back CL#1986255.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_internal.hpp#38 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#35 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#39 edit
 2019-08-22 12:41:42 -04:00
Evgeny Mankov eb5dd29872 Merge pull request #1355 from emankov/master 
[HIPIFY][fix] Set the correct exit value for hipify-clang if errors
 2019-08-22 01:41:23 +03:00
Jenkins ec8df015e0 Merge 'master' into 'amd-master' 
Change-Id: I1dd6af19c418181b78b67f4b47beaf82b19170fc
 2019-08-21 15:50:57 -04:00
Evgeny Mankov b863c1392c [HIPIFY][fix] Set the correct exit value for hipify-clang if errors. 
This fixes a hanging of unit tests.
 2019-08-21 21:36:53 +03:00
Evgeny Mankov 8fbbc663a5 Merge pull request #1354 from emankov/master 
[HIPIFY] CUDA 10.1 Update 2 support
 2019-08-21 21:07:57 +03:00
Evgeny Mankov 54fee7abdc [HIPIFY] CUDA 10.1 Update 2 support 2019-08-21 21:06:20 +03:00
Rahul Garg b3a0d4266b Remove -g from hipBusBandwidth makefile (#1351) 2019-08-21 10:01:31 +00:00
Maneesh Gupta c42075715b Packaging and versioning changes (#1348) 
- Fixes SWDEV-200435
- Brings versioning and packaging naming inline with rest of the ROCm
  components.
- Minor bug fixes.

Change-Id: I543a24bf18baffe74fa3ccac8c93bddba7231c5e
 2019-08-21 10:01:23 +00:00
Sarbojit2019 84de192c9b Compilation failure on nvcc path when using hipChannelFormatKind (#1345) 
Fix for github #1183 issue reported
 2019-08-21 10:01:03 +00:00
Jatin Chaudhary ac62d7a5c0 Using HSA API for hipMemsetAsync (#1346) 2019-08-21 10:00:10 +00:00