AI/rocm-systems
2
0
Форк 0
Код Задачі Запити на злиття Дії Пакети Проєкти Релізи Вікі Активність
4 189 Коміти 3 Гілки 0 Теги
e73927caeeb7b40dfd0be42d7a3db0e7762fc6dd
Графік комітів

1112 Коміти

Автор SHA1 Повідомлення Дата
Alex Voicu 69e74c3e96 Add support for extended launch syntax. (#1530) 
* Add support for extended launch syntax.

* Add unit test.

* Fix typo

* hipExtLaunchKernelGGL lives in hip_ext.h

Change-Id: Ice32dab0d43475fda65c6a910c11416871a8f2ff

* [dtest] remove redundant include from hipModuleGetGlobal dtest
 2019-11-16 22:24:07 -08:00
Michael LIAO d6ff22510e Remove redundant declarations. 
- The revised `hip/hip_ext.h` have that declarations.
 2019-11-07 10:11:22 -05:00
Alex Voicu 5530c15cc3 Remove native vector support from the GCC case, since it never worked (#1637) 2019-11-07 13:19:14 +05:30
ansurya e07926ce0f Fixed texture 2D mapping for pitched arrays & 3D Texture read (#1415) 
Texture 2D image mapping for pitched arrays:
github issue: Texture Object's Buffer seems to be Misaligned #886
JIRA ticket: SWDEV-199313

SWDEV-151670 : Fixed issue with 3D texture with 4 components
SWDEV-151671 : Issue with 2D layered texture with 4 components
 2019-11-07 13:17:46 +05:30
Rahul Garg 579a4f36fa Rename hip/hip_hcc.h to hip/hip_ext.h (#1341) 
* Rename hip/hip_hcc.h to hip/hip_ext.h

* Deprecate hip_hcc.h
 2019-11-07 13:17:10 +05:30
Alex Voicu b9faa9f8ae Remove leftover noise. 2019-11-06 02:46:21 +02:00
Alex Voicu e5bd00d06b __half2 should walk like CUDA and talk like CUDA 2019-11-06 02:43:04 +02:00
Michael LIAO a7f311cc14 Use portable macro for deprecation message. 2019-11-05 11:51:00 -05:00
Rahul Garg 54fab7c35c Deprecate HIP Markers (#1622) 
* Deprecate HIP markers

* Deprecate profiler start/stop
 2019-11-05 12:32:59 +05:30
Alex Voicu 99b9d5449f Separate volatile for clarity. Handle assignment. 2019-11-02 22:02:08 +02:00
Alex Voicu ee5097f2c2 Accessors should work even when oddly volatile. 2019-11-01 22:18:01 +02:00
Rahul Garg ba8105e0cd Merge pull request #1515 from ansurya/tex_unbind_issue_fix 
Fix undefined ref to hipUnbindTexture for texture types
 2019-10-30 17:54:15 -07:00
Michael LIAO 5c8a7521f4 [HIP] Correct headers and add missing function templates for hip-clang. 
- Fix 2 runtime API prototypes
  `hipOccupancyMaxActiveBlocksPerMultiprocessor` and
  `hipOccupancyMaxActiveBlocksPerMultiprocessorWithFlags`
- Add missing function templates of them in hip-clang.
 2019-10-29 22:00:11 -04:00
Rahul Garg e4a1e44162 Revert "Fix occupany APIs (#1560)" 
This reverts commit af351d7e1b.
 2019-10-29 11:41:08 -07:00
Anusha Godavarthy Surya 03623cc3f1 Merge branch 'master' into tex_unbind_issue_fix 2019-10-25 15:54:25 +05:30
Anusha Godavarthy Surya 5f47e99ffe merge from master 2019-10-25 15:52:09 +05:30
Alex Voicu dabd939048 Add missing operators, fix GCC compilation. (#1589) 2019-10-25 15:44:24 +05:30
Alex Voicu a855a13c22 Fix deadlock, remove old __sync_* use. (#1584) 
This fixes a deadlock introduced by the switch to TTAS loops, and is therefore mildly urgent (to prevent the CI from hoovering in the broken code).
 2019-10-25 15:44:17 +05:30
Rahul Garg 356765a223 Add hipMemcpy2DfromArray (#1510) 
Adds hipMemcpy2DFromArray and hipMemcpy2DFromArrayAsync equivalent to cudaMemcpy2DFromArray and cudaMemcpy2DFromArrayAsync.
 2019-10-25 15:43:33 +05:30
Anusha Godavarthy Surya 259d8b4cdf Merge branch 'master' into tex_unbind_issue_fix 2019-10-25 15:36:55 +05:30
Anusha Godavarthy Surya ce04bdaa1a Fixed CI build failure 2019-10-25 12:21:41 +05:30
gandryey 81952ce5a7 Hip vdi profiling header (#1577) 
Add HIP-VDI profiling interface for GPU timing collection.
 2019-10-24 17:45:42 +05:30
Alex Voicu 9ba25b42c8 Make CAS loops use the TTAS idiom. (#1573) 
* Make CAS loops use the TTAS idiom.

* More efficient re-formulation of TTAS.

* Fix typo.

* The typo was not quite a typo
 2019-10-24 17:45:20 +05:30
satyanveshd af351d7e1b Fix occupany APIs (#1560) 
Addresses SWDEV-205006
 2019-10-24 17:44:47 +05:30
searlmc1 c4a51f3679 Improve performance of v2 arg handling (#1539) 
* Improve performance of v2 arg handling

* Missing change to `std::string`
 2019-10-24 17:44:05 +05:30
Alex Voicu 4a635add45 Improve scalar access into vector types. (#1531) 
The improvement is based on the ideas here: https://t0rakka.silvrback.com/simd-scalar-accessor. It yields significantly better ISA when the base's .xyzw members are used.
 2019-10-24 17:43:49 +05:30
Vladislav Sytchenko 0b52c1d9d8 Update the declarations of hipMemsetD8, hipMemsetD8Async, hipMemsetD16, hipMemsetD16Async. These functions are type aware and take in as their third argument the number of elements in the buffer, not the buffer size. Change the name of this argument from sizeBytes to count to align with the above description. 2019-10-15 14:18:42 -04:00
Evgeny Mankov 28c23a7b1a [HIP] Fix typo in a comment 2019-10-11 15:20:58 +03:00
Evgeny Mankov 337b7ce06a [HIP][fix] Prefix libraryPropertyType to fix build of rocFFT and TensorFlow 2019-10-11 15:18:08 +03:00
Evgeny Mankov 94eb4155dd [HIP] Introduce library_types.h as a common header for libs (#1509) 
* [HIP] Introduce library_types.h as a common header for libs

[Reason]
Currently, hipFFT, hipBLAS and other HIP libs use their own data types, prefixed with HIPFFT or HIPBLAS, whereas in CUDA those types are common and declared in library_types.h

[TODO]
Switch hipFFT, hipBLAS and other HIP libs to use common library_types.h.

* [HIP] Move include for library_types.h to hip_runtime.h

[Reason]
Repeat CUDA's behaviour, where library_types.h is included in cuda_runtime.h
 2019-10-10 19:57:28 +05:30
Philip Salzmann 9ababa4276 Fix uninitialized var in hipDeviceGetAttribute (#1497) 
This fixes the usage of an uninitialized cdattr variable in hipDeviceGetAttribute for the CUDA backend when taking the switch default, as detailed in #1317.

Note that the directed_tests/runtimeApi/device/hipGetDeviceAttribute.tst test fails for me, but it already did before applying this patch. Let's see what CI says!
 2019-10-04 13:39:19 +05:30
Rahul Garg bec725dec2 Add texref get APIs support (#1471) 
Added support for -
    hipTexRefGetArray
    hipTexRefGetAddressMode
    hipTexRefGetAddress
 2019-10-04 13:38:45 +05:30
Sarbojit2019 58a476abc2 Removed definition of abs(), real() & imag() from hip_complex.h (#1448) 
Addresses SWDEV-201461.
 2019-10-04 13:38:02 +05:30
ansurya ba9c6e13e4 Added new Memory API's (#1399) 
Added new memory API's hipMemAllocPitch, hipMemAllocHost, hipMemsetD16, hipMemsetD16Async, hipMemsetD8Async
Modified to support all scenarios hipMemcpyParam2DAsync, hipMemcpyParam2D.
 2019-10-04 13:36:31 +05:30
Yaxun (Sam) Liu 56193a7828 Fix cast of __half for HIP-clang (#1475) 2019-09-30 10:40:42 +05:30
satyanveshd 4b413739a9 Map clock64() to __builtin_readcyclecounter() (#1473) 
Fixes SWDEV-203215.
 2019-09-30 10:40:31 +05:30
eshcherb 8234da33b9 to include hip_prof_str.h under USE_PROF_API macro (#1470) 2019-09-30 10:39:41 +05:30
Alex Voicu ab8fe8a3d8 Optimise the gridDim.n * blockDim.m idiom (#1468) 2019-09-30 10:39:23 +05:30
Yaxun (Sam) Liu 3c80389584 Add new kernel launching API for hip-clang 2019-09-26 20:15:24 -04:00
Sarbojit2019 0fa42af08c [HIP] Add tccDriver info in hipDeviceProp 
Fixes #1433.
 2019-09-26 13:53:33 +05:30
mhbliao 1f8c3bbd3b [HIP] Remove a circular including. (#1418) 2019-09-16 08:32:47 +00:00
ansurya ceb734b917 Added new device attributes (#1377) 
* Added new device attributes

* updated comment

* updated with new device attributes supported
 2019-09-16 08:31:30 +00:00
mhbliao 119ee4b671 [hip] Stop using noduplicate and replace it with convergent. (#1390) 2019-09-05 10:03:43 +00:00
Yaxun (Sam) Liu 8fe8fc18c0 Do not include cuda wappers for OMP for hip-clang (#1382) 2019-09-03 05:13:59 +00:00
Sarbojit2019 e1f9e08ea7 Removed hipLaunchKernel macro got missed in Merge (#1374) 2019-09-03 05:13:07 +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
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