AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,560 Commits 3 Branches 0 Tags
cbfc58660ea9f04184fff4d940013848cf0cfc7e
Commit Graph

514 Commits

Author SHA1 Message Date
Ben Sander cbfc58660e Finish adding start/stop event support to hipHccModuleLaunchKernel. 
Change interface to use hipEvent_t rather than hipEvent_t*

Change-Id: I259062dc087a13d51dc27f84e1e8861f332a104d


[ROCm/hip commit: 6656d33f75]
 2017-04-06 21:02:50 -05:00
sunway513 7502166e5a Improve documentation for hipModuleLaunch functions. 
Change-Id: I0e22621e499775740c3301347b7416d5f98c2414


[ROCm/hip commit: 5995965558]
 2017-04-06 21:02:50 -05:00
Aditya Atluri 6c7450d414 fixed header structure for complex data types 
Change-Id: I16bf19005d933f42e8c8603c5d0b2df8ea3ad04f


[ROCm/hip commit: 0a07382d92]
 2017-04-06 16:43:26 -05:00
Sun, Peng 9d1a5f886e GGL update, add while 0 guard for hipLaunchKernel API 
Change-Id: Ie48ef8ca2ab5e26a51febfcd92417902c33fbf66


[ROCm/hip commit: ad18bf3b29]
 2017-04-06 10:48:11 -05:00
Aditya Atluri 26f6ce992d added __host__ for complex functions and corrected memset and memcpy test 
Change-Id: I9ffefb7a0025aa111a54d20d2766982df15532e7


[ROCm/hip commit: 6dff2714e9]
 2017-04-06 09:29:44 -05:00
Sun, Peng 72238e2119 add extra guard to grid_launch_GGL header 
Change-Id: I120619c08ea2d084804fcb1639efbe6c4648dde9


[ROCm/hip commit: 1a8ea82497]
 2017-04-05 22:25:41 -05:00
Sun, Peng 5c46c8920c Add more include header file for GGL, to make it self-compilable 
Change-Id: I833cb194784450fb86e7961a7f9fe196ce3c7da5


[ROCm/hip commit: a92cdbaf29]
 2017-04-03 11:16:35 -05:00
Maneesh Gupta c8214a5b20 Enable promote free HCC by default 
Change-Id: I5f82a8d958dd675a8a46d9d17458c71321daab7c


[ROCm/hip commit: 822fc802a0]
 2017-04-03 11:18:30 +05:30
Sun, Peng dd0aa2c9e3 Fix warpSize, for related issue in hipeigen and torch 
Change-Id: Ic66b24923a363304dca189011869ba7a0a6f8895


[ROCm/hip commit: c82c84949c]
 2017-04-01 15:42:53 -05:00
Sun, Peng 7559427041 GGL update, fix for thread-safe access to streams (accelerator_views). 
Change-Id: I6dd329a85b3ba7de23d52823febee0c53857a981


[ROCm/hip commit: b1ed910942]
 2017-04-01 14:50:39 -05:00
Aditya Atluri fcb4331a6a Fixed copyright and header names 
Change-Id: Id595c65ea3b7289e87be4c42db5d8a31905a4fdd


[ROCm/hip commit: 1ef7222c3a]
 2017-03-31 12:40:29 -05:00
Aditya Atluri 7635e0a57e fixed header names 
Change-Id: I21650d6398187d3767b28e8ac81b2642d3b89a0e


[ROCm/hip commit: e0133e627d]
 2017-03-31 12:18:55 -05:00
Aditya Atluri ccf799c453 added new api hipHccModuleLaunchKernel 
1. hipHccModuleLaunchKernel is same as hipModuleLaunchKernel with OpenCL workitem model
2. Added copy right
3. Fixed header naming

Change-Id: I6a7c35a3566e2f8d3f5056613e34193775d4b236


[ROCm/hip commit: b9091ba818]
 2017-03-31 12:11:34 -05:00
Sun, Peng 799a81029c remove extra GGL header info 
Change-Id: I09f0d1b64a7a31eb2e926f19b69b7bafbacc7787


[ROCm/hip commit: 071f19521c]
 2017-03-30 18:16:56 -05:00
Sun, Peng c9dc0cf010 Rename hipLaunchKernelV3 to hipLaunchKernelGGL 
Change-Id: I303daae006db41e9b04eb591e0b09b2717a7cf66


[ROCm/hip commit: f4efa422bf]
 2017-03-30 18:10:17 -05:00
Sun, Peng 7a0c077800 Enable GGL as the default kernel launch method 
Change-Id: I8022d126ee28ff7e4d9a96209e399d4243d39d8b


[ROCm/hip commit: cfc2d455e1]
 2017-03-30 13:36:46 -05:00
Sun, Peng 381a67f256 Update GGL to fix one Torch build issue 
Change-Id: I95a2a335902e3c368ed29f075ac72eabbb64c97e


[ROCm/hip commit: d067c884be]
 2017-03-29 09:03:21 -05:00
sunway513 6e01fb345b resolve GGL merge conflicts 
Change-Id: I7a5ec3696cf2dd1a77b1686536a1cb84cbfed66e


[ROCm/hip commit: 43f76be76e]
 2017-03-27 22:46:41 -05:00
Rahul Garg be8d979d08 Fix for MemcpyFromSymbol on HIP/NVCC path 
Change-Id: Ice38307f72870ae468cbf0861e104f0fa46dfd56


[ROCm/hip commit: 1d18006ab4]
 2017-03-27 00:35:10 +05:30
Rahul Garg 397088203d Added support for Primary Context Management APIs 
Change-Id: I70f91b4492e112dd8e12ecf511fdc18a27944a06


[ROCm/hip commit: ecc0e14cf7]
 2017-03-26 23:45:54 +05:30
Sun, Peng 0215445fa0 update GGL implementation to use hipLaunchKernel 
Change-Id: Ibc08185c814bb07d54f3e68016b10eb7b9f2bf4b


[ROCm/hip commit: 91274394dc]
 2017-03-21 15:46:56 -05:00
Sun, Peng 38feccc1d2 Update GGL implementation to extended overload set for make_lambda_wrapper 
Change-Id: I949f113671ddf155db8689e8a7f23d415839a7b5


[ROCm/hip commit: ec04521617]
 2017-03-21 15:46:44 -05:00
Sun, Peng c5b6222d62 revert workaround for square sample and update doc on GGL 
Change-Id: I731c68ca4111e7dc2e45bef51c4cad2c23fc81f8


[ROCm/hip commit: 329e2182d6]
 2017-03-21 10:26:09 -05:00
Sun, Peng b5e6670807 merge Alex' GGL fix for non-specialized kernel function launch 
Change-Id: Idbf7ca669c38ee5c0f654bcabdd1b498abb29f69


[ROCm/hip commit: d09afd23b8]
 2017-03-20 16:34:24 -05:00
Aditya Atluri 5d1ae81def added support for lgammaf and lgamma 
1. Implementation inside HIP

Change-Id: I657263b7276a57c56081d3336fef816b5f204eff


[ROCm/hip commit: d9f0bd25be]
 2017-03-17 18:26:10 -05:00
Sun, Peng 90e79afc24 Disable additional debug warning message 
Change-Id: Ic5c374589bfad387a7c4c5346430a490e2c6e2a7


[ROCm/hip commit: e7689e9e6e]
 2017-03-17 15:03:03 -05:00
pensun 81622d1263 Change the #define of GENERIC_GRID_LAUNCH to take valueat compilation, disable warning messages 
Change-Id: Ic6c011529e26de359bcda1e7083727e7ee52887b


[ROCm/hip commit: 30d5f4ea10]
 2017-03-17 14:59:34 -05:00
pensun 762090f564 Initial integration with Alex' Generic Grid Launch 
Change-Id: I559afb80e9e39ec0d119bb3bf3b85ef9e448caf6


[ROCm/hip commit: 33c38de407]
 2017-03-17 14:59:34 -05:00
Ben Sander e10e2bd267 Move USE_PROMOTE_FREE_HCC 
[ROCm/hip commit: 8cbe310870]
 2017-03-17 12:04:13 -05:00
Ben Sander 8d5c39fd52 Add __device__ to needful functions for promote-free. 
[ROCm/hip commit: 29232ff283]
 2017-03-17 11:19:48 -05:00
Ben Sander a9ec705ee4 Add USE_PROMOTE_FREE_HCC for smooth transition to new HCC caps. 
ADDRESS_SPACE_1 defines


[ROCm/hip commit: e85c167171]
 2017-03-17 11:04:39 -05:00
Ben Sander 25e4ace28b Add simple device-side assert macro 
Currently swallows asserts but will compile.


[ROCm/hip commit: ecd8179a71]
 2017-03-17 10:25:56 -05:00
Maneesh Gupta 366a5e09a1 Merge branch 'amd-master' into amd-develop 
Change-Id: I01a77c34e11b1b02cb20e11b105741f6bd383543


[ROCm/hip commit: 1337ed9159]
 2017-03-15 09:56:45 +05:30
Rahul Garg 03c6de6968 hipMemsetD8 support for HIP/NVCC path 
Change-Id: I48eee8266afd7b45a12d5ce2c4849b687a006c0f


[ROCm/hip commit: 913867fe6a]
 2017-03-14 23:49:21 +05:30
Rahul Garg 0bfd692b59 Added hipMemsetD8 
Change-Id: I6a230a036c9c46c72a77d5f93c16ce8a00c3f837


[ROCm/hip commit: 1aba3c4375]
 2017-03-14 22:11:34 +05:30
Wen-Heng (Jack) Chung 508ad44c7c Revert "Changes to HIP to cope with Promote-free HCC" 
This reverts commit 9043ba55db.

Change-Id: I20a9bab3883ad09913b320210344d37599cb8fcd


[ROCm/hip commit: 77e21dc09f]
 2017-03-14 22:59:27 +08:00
Maneesh Gupta 5191fc0c5c Merge branch 'amd-master' into amd-develop 
[ROCm/hip commit: 675dd1cedf]
 2017-03-14 13:44:41 +05:30
Aditya Atluri 99ab69e1b5 make sure the inter-thread intrinsics are working post hawaii 
Change-Id: I30ea5284c2160276f5bc0f937dfd386ca8640ce8


[ROCm/hip commit: c8969811db]
 2017-03-13 11:16:05 -05:00
Ben Sander 71fc982cbe Refactor registered memory calls. 
[ROCm/hip commit: 524e007db5]
 2017-03-11 09:18:27 -06:00
Aditya Atluri 7f0f1e4ae8 fixed warning raised by g++ using hip_vector_types.h 
Change-Id: I9e7cdfc8b28b03b690eecd068529cf7629296d68


[ROCm/hip commit: e79dd9f9c6]
 2017-03-10 15:14:26 -06:00
Rahul Garg 4954d140d4 IPC supported using ROCR APIs 
Change-Id: I0a353b1240098f4b20fa266a871f5f5826290af9


[ROCm/hip commit: 32d8a58f18]
 2017-03-10 23:45:28 +05:30
pensun 4d748e3cd7 update porting guide for updated __HIP_DEVICE_COMPILE__ 
Change-Id: I0f025d354f76e2d728231bf112a77e8c8fcacc8c


[ROCm/hip commit: 37ed319a20]
 2017-03-10 10:01:12 -06:00
Aditya Atluri b0c2ac0a90 Added architecture guards around __shfl, dpp and ds_permute device functions 
Change-Id: I10f9b08618fbf25b61c1932278fc5759e41c0d66


[ROCm/hip commit: 1567d20aa8]
 2017-03-10 08:40:59 -06:00
pensun e18aaa955f add inline to all hip_complex operators 
Change-Id: Ifba5966c297cbc9299c39ecfc45c7296003ebb5d


[ROCm/hip commit: 7488d8c7fa]
 2017-03-08 14:06:13 -06:00
Aditya Atluri fe81d08987 Added new API, hipMemPtrGetInfo 
1. This API returns memory allocation size of pointer
2. Added test to check its functionality

Change-Id: I87976d817b5a6ca5530336c09e7cb0420601cb2c


[ROCm/hip commit: 1546732604]
 2017-03-07 13:46:29 -06:00
Wen-Heng (Jack) Chung 9043ba55db Changes to HIP to cope with Promote-free HCC 
Squashed commit of the following:

commit c111b5bd10d7c2a5b0b1ad8b07f6e81185b47b39
Author: Wen-Heng (Jack) Chung <whchung@gmail.com>
Date:   Sat Mar 4 17:06:46 2017 +0800

    Use __device__ for all variables and functions to be used in kernel path

    Abolish __device and adopt [[hc]] in HIP implementation, so __device__ can be
    used on all HIP applications, no matter they are variables or functions.

    Change-Id: I20ca25857ce3bc3e42a5ebf65cafea2c8492f4c7

commit 30c0e4e4701bbf6bd9a7182e0320a71ff73d3a83
Author: Wen-Heng (Jack) Chung <whchung@gmail.com>
Date:   Thu Mar 2 12:14:11 2017 +0800

    XXX FIXME get around LDS spills caused in Promote-free HCC

    hipDynamicShared2 uses all 64KB of LDS for computation. But in Promote-free HCC
    there are cases where LDS spills would occur, which would make the test case to
    hang.

    In this workaround commit we reduce the size of dynamic LDS used to get around
    this known issue, and will revert this commit when LDS spills are resolved in
    HCC.

    Change-Id: If648b36200a4f9143951a8129192bcb7ed0bef5e

commit e803173be2d73e2f132a7ff7f61e7a20b4083d34
Author: Wen-Heng (Jack) Chung <whchung@gmail.com>
Date:   Wed Mar 1 21:41:41 2017 +0800

    Fix math functions which take pointer arguments

    Change-Id: I332c997e640edbc44824691e2a9434c6b3dadefa

commit de590c469e213c42090ff83dbd060f25bb1d6047
Author: Wen-Heng (Jack) Chung <whchung@gmail.com>
Date:   Wed Mar 1 18:38:54 2017 +0800

    Changes to cope with Promote-free HCC

    - abolish usage of address_space GNU attribute
    - use __device in file-scope global variables which would be accessed by GPU kernels
    - temporarily disable some math functions which take pointer arguments

    Change-Id: I730311dee848e20e763e35cd3980317fce0dce0d

Change-Id: I1f6b970b53b9401eeaaab08f04a7b9fed0fb8cf0


[ROCm/hip commit: efb9b9e86c]
 2017-03-08 01:32:59 +08:00
Aditya Atluri 6cbeeb8e59 added new field to hipDeviceProp_t structure gcnArch. 
1. It is an integer containing gfx values 701, 801, 802, 803
2. On NV path, it is zero

Change-Id: I2b4c7f48981d0214d8c6b1905d2cc85b16203419


[ROCm/hip commit: f86f3b3b33]
 2017-03-07 11:24:32 -06:00
Ben Sander 0dd1393f97 Modify memcpy and memset to follow C/C++ standard: 
- memcpy src is const
    - memset val is int


[ROCm/hip commit: d572e0616e]
 2017-03-06 16:38:22 -06:00
Evgeny Mankov b8fbb0ea23 [HIP] [FIX] Memcpy Async functions on nvcc path. 
+ in hipMemcpyDtoDAsync: cuMemcpyDtoD -> cuMemcpyDtoDAsync
+ in hipMemcpyDtoHAsync: cuMemcpyDtoH -> cuMemcpyDtoHAsync

P.S.
"The types CUstream and cudaStream_t are identical and may be used interchangeably", thus explicit c-like type cast is not needed, aka CUstream(stream).


[ROCm/hip commit: 6421a1e79e]
 2017-03-01 23:04:34 +03:00
Aditya Atluri 921825f7b5 changed __half enabling from 4 to >3 
Change-Id: Id974c6d5326e87a4c5941f831c5bb2747cdebd2d


[ROCm/hip commit: e7ccc995ee]
 2017-02-28 17:13:29 -06:00