Граф коммитов

3864 Коммитов

Автор SHA1 Сообщение Дата
Evgeny Mankov 321c0f2a9e Merge pull request #1384 from emankov/master
[HIPIFY][tests] Add occupancy test
2019-09-02 17:56:16 +03:00
Evgeny Mankov 608331250e [HIPIFY][tests] Add occupancy test 2019-09-02 17:54:06 +03:00
Evgeny Mankov 3001fb4c09 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 8eb7d53cec [HIPIFY][fix] Fix for upcoming LLVM 10.0 2019-09-01 18:15:03 +03:00
Rahul Garg 30b7557d55 Merge pull request #1378 from ssahasra/no-as
remove obsolete test for OCKL Asynchronous Streams
2019-08-30 19:05:37 -07:00
Sameer Sahasrabuddhe 68c133bd78 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library since that feature is now superseded by hostcall.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 a5cc936a2d Merge pull request #1375 from emankov/hipify-clang
[HIPIFY][DNN] cuDNN 7.6.3 support
2019-08-30 17:26:29 +03:00
Evgeny Mankov a0a98790f0 [HIPIFY][DNN] cuDNN 7.6.3 support 2019-08-29 19:55:38 +03:00
Evgeny Mankov 451721a821 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 793b18c0b1 Fix sample 11_texture_driver for hip-clang (#1370) 2019-08-29 01:03:20 +00:00
Yaxun (Sam) Liu 19a9b15306 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 b5ff9e71ed Updated hipErrorString and CUDAErrorTohipError (#1365) 2019-08-29 01:02:59 +00:00
Sarbojit2019 1ae43cbeba [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 d2df21e58c [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 f74903851e 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 32f22a0117 [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 7b9f2a8471 Merge pull request #1371 from emankov/master
[HIPIFY][cmake] Minor refactoring
2019-08-28 20:42:41 +03:00
Evgeny Mankov e3eb62ac4b [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
Maneesh Gupta b92c16f4d9 [packaging] update soft-links that already exist (#1364)
Change-Id: Ibe9840802b1765094ef998edf2210e95404cb989
2019-08-26 23:41:14 -04:00
Rahul Garg 15426394d5 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 c84628f420 [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
ramcherukuri 6ea9e2b249 moving result_of_t to result_of 2019-08-24 08:59:58 -04:00
Evgeny Mankov 2079f17d26 Merge pull request #1360 from emankov/master
[HIPIFY][cmake] Explicitly set c++14
2019-08-23 19:40:53 +03:00
Evgeny Mankov 7f5635d3ff [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
Sarbojit2019 919bb6c74d 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 d367fdf28c Make Bundled_code_header visible for hipRTC usage (#1359) 2019-08-23 09:20:02 +00:00
chrispaquot d0b11deb7f Set device before processing each one (#1358) 2019-08-23 09:19:50 +00:00
Aryan Salmanpour 32ce882d6e [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 a786728939 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
Evgeny Mankov 9498724732 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
Evgeny Mankov 3d07393003 [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 1e13e37785 Merge pull request #1354 from emankov/master
[HIPIFY] CUDA 10.1 Update 2 support
2019-08-21 21:07:57 +03:00
Evgeny Mankov 8293f9a706 [HIPIFY] CUDA 10.1 Update 2 support 2019-08-21 21:06:20 +03:00
Rahul Garg 900590967d Remove -g from hipBusBandwidth makefile (#1351) 2019-08-21 10:01:31 +00:00
Maneesh Gupta e50f05f3f2 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 684801fc1d 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 9bbd09b04f Using HSA API for hipMemsetAsync (#1346) 2019-08-21 10:00:10 +00:00
kpyzhov d81267ae15 Corrected declaration of __ockl_clz_u64() (#1340) 2019-08-20 12:06:36 +00:00
Sarbojit2019 f106375a34 [hipcc] Fix for uninitialized variables on nvcc path
Fixes #1186
2019-08-20 12:06:22 +00:00
Maneesh Gupta fa891c7a21 [ci] Enable tests on ROCm 2.7 (#1337)
Change-Id: I06fb58b48af7f52f309f659969bb42bf9e8e9faf
2019-08-20 12:05:30 +00:00
Yaxun (Sam) Liu 68a59ddbe8 Fix missing decl for hip-clang
Add back decl for hipHccModuleLaunchKernel and hipExtModuleLaunchKernel for HIP/VDI only
2019-08-19 18:27:13 -04:00
mhbliao 282f06014e [hip] Allow from/to half conversion on host side. (#1334) 2019-08-16 02:13:59 +00:00
Rahul Garg a0cc627c42 Fix build issues seen with hip-clang path (#1331) 2019-08-16 02:13:45 +00:00
Yaxun (Sam) Liu c4655d167e Fix assert for windows. (#1329)
MSVC assert.h has no guard for include once. The macro assert overrides
device assert definition. Do not include it for device compilation.
2019-08-16 02:13:33 +00:00
Rahul Garg fbc9f7e20a Add hipMemcpy3DAsync (#1320)
* Add hipMemcpy3DAsync

* Fix CI build error

* Move back stream resolution to internal function

* Remove stream redefinition and check
2019-08-16 02:13:16 +00:00
Rahul Garg c741ad3c80 [dtests] refactor windows specific changes (#1313)
* [dtests] refactor windows specific changes

* Refactor hipMemoryAllocateCoherentDriver - PR- 1309

* Fix missing z in _putenv_s

* Revert "Fix missing z in _putenv_s"

This reverts commit 099a1b20a5c75c5f122d57c0ad2bca01745cdc9c.

* Refactor changes from PR 1299

* Update hipEnvVarDriver.cpp
2019-08-16 02:13:00 +00:00
Rahul Garg 7f9de881cb Fix undefined identifier issue for hipExtModuleLaunchKernel 2019-08-14 16:46:32 -04:00
Maneesh Gupta 3634695737 [hit] Add support for specifying dependencies in HIT syntax (#1323) 2019-08-14 11:30:42 +00:00
Sarbojit2019 c4618f2c3b [HIP] Fix for hipArray_t failure on nvcc path
Fixes SWDEV-148407
2019-08-14 11:30:06 +00:00
Rahul Garg d90c66f5bf [docs] Attribute details for launch kernel greater than 256 (#1319)
* Add attribute detail for kernel launch group > 256

* Add example
2019-08-14 11:29:04 +00:00