AI/rocm-systems
2
0
Rozštěpit 0
Zdrojový kód Úkoly Pull requesty Akce Balíčky Projekty Vydání Wiki Aktivita
1 557 Commity 3 Větve 0 Značky
950dfd28d6bf00a84577dfa999da7f169af500a3
Graf commitů

512 Commity

Autor SHA1 Zpráva Datum
Aditya Atluri 950dfd28d6 fixed header structure for complex data types 
Change-Id: I16bf19005d933f42e8c8603c5d0b2df8ea3ad04f


[ROCm/clr commit: 1358bd8f07]
 2017-04-06 16:43:26 -05:00
Sun, Peng 9d6a04d334 GGL update, add while 0 guard for hipLaunchKernel API 
Change-Id: Ie48ef8ca2ab5e26a51febfcd92417902c33fbf66


[ROCm/clr commit: 49a38da6e3]
 2017-04-06 10:48:11 -05:00
Aditya Atluri d1c334df66 added __host__ for complex functions and corrected memset and memcpy test 
Change-Id: I9ffefb7a0025aa111a54d20d2766982df15532e7


[ROCm/clr commit: 42739c37ef]
 2017-04-06 09:29:44 -05:00
Sun, Peng 388f35c67a add extra guard to grid_launch_GGL header 
Change-Id: I120619c08ea2d084804fcb1639efbe6c4648dde9


[ROCm/clr commit: 335e107f5f]
 2017-04-05 22:25:41 -05:00
Sun, Peng e342bbc7fb Add more include header file for GGL, to make it self-compilable 
Change-Id: I833cb194784450fb86e7961a7f9fe196ce3c7da5


[ROCm/clr commit: 2ca9eec9fc]
 2017-04-03 11:16:35 -05:00
Maneesh Gupta 5f99f3811b Enable promote free HCC by default 
Change-Id: I5f82a8d958dd675a8a46d9d17458c71321daab7c


[ROCm/clr commit: cea13c34c3]
 2017-04-03 11:18:30 +05:30
Sun, Peng 0e23f09b47 Fix warpSize, for related issue in hipeigen and torch 
Change-Id: Ic66b24923a363304dca189011869ba7a0a6f8895


[ROCm/clr commit: a7d7797781]
 2017-04-01 15:42:53 -05:00
Sun, Peng 5a4ac0929f GGL update, fix for thread-safe access to streams (accelerator_views). 
Change-Id: I6dd329a85b3ba7de23d52823febee0c53857a981


[ROCm/clr commit: df4cee1a57]
 2017-04-01 14:50:39 -05:00
Aditya Atluri e3d3cacebc Fixed copyright and header names 
Change-Id: Id595c65ea3b7289e87be4c42db5d8a31905a4fdd


[ROCm/clr commit: 3859f59189]
 2017-03-31 12:40:29 -05:00
Aditya Atluri e54234667c fixed header names 
Change-Id: I21650d6398187d3767b28e8ac81b2642d3b89a0e


[ROCm/clr commit: 614e7db513]
 2017-03-31 12:18:55 -05:00
Aditya Atluri 3651cb672a 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/clr commit: 1cead6a4cd]
 2017-03-31 12:11:34 -05:00
Sun, Peng ace18c6a57 remove extra GGL header info 
Change-Id: I09f0d1b64a7a31eb2e926f19b69b7bafbacc7787


[ROCm/clr commit: e3a4547703]
 2017-03-30 18:16:56 -05:00
Sun, Peng 56b2c7d82e Rename hipLaunchKernelV3 to hipLaunchKernelGGL 
Change-Id: I303daae006db41e9b04eb591e0b09b2717a7cf66


[ROCm/clr commit: 9983fdb9e2]
 2017-03-30 18:10:17 -05:00
Sun, Peng 8b91454077 Enable GGL as the default kernel launch method 
Change-Id: I8022d126ee28ff7e4d9a96209e399d4243d39d8b


[ROCm/clr commit: c081099de1]
 2017-03-30 13:36:46 -05:00
Sun, Peng bf84371e0d Update GGL to fix one Torch build issue 
Change-Id: I95a2a335902e3c368ed29f075ac72eabbb64c97e


[ROCm/clr commit: a32f50b5c7]
 2017-03-29 09:03:21 -05:00
sunway513 d64768262f resolve GGL merge conflicts 
Change-Id: I7a5ec3696cf2dd1a77b1686536a1cb84cbfed66e


[ROCm/clr commit: 6f38d0f55e]
 2017-03-27 22:46:41 -05:00
Rahul Garg 30eb97392a Fix for MemcpyFromSymbol on HIP/NVCC path 
Change-Id: Ice38307f72870ae468cbf0861e104f0fa46dfd56


[ROCm/clr commit: 41f0ebebf0]
 2017-03-27 00:35:10 +05:30
Rahul Garg 8a5d4a6ab8 Added support for Primary Context Management APIs 
Change-Id: I70f91b4492e112dd8e12ecf511fdc18a27944a06


[ROCm/clr commit: 33a8cdc6d3]
 2017-03-26 23:45:54 +05:30
Sun, Peng feae5cda6b update GGL implementation to use hipLaunchKernel 
Change-Id: Ibc08185c814bb07d54f3e68016b10eb7b9f2bf4b


[ROCm/clr commit: 4ca09e977d]
 2017-03-21 15:46:56 -05:00
Sun, Peng 962ac22fe0 Update GGL implementation to extended overload set for make_lambda_wrapper 
Change-Id: I949f113671ddf155db8689e8a7f23d415839a7b5


[ROCm/clr commit: 6b9be30b70]
 2017-03-21 15:46:44 -05:00
Sun, Peng db4bedeafc revert workaround for square sample and update doc on GGL 
Change-Id: I731c68ca4111e7dc2e45bef51c4cad2c23fc81f8


[ROCm/clr commit: 14f8c7cf74]
 2017-03-21 10:26:09 -05:00
Sun, Peng cb31fbab62 merge Alex' GGL fix for non-specialized kernel function launch 
Change-Id: Idbf7ca669c38ee5c0f654bcabdd1b498abb29f69


[ROCm/clr commit: e21d4f03f1]
 2017-03-20 16:34:24 -05:00
Aditya Atluri 35d829773d added support for lgammaf and lgamma 
1. Implementation inside HIP

Change-Id: I657263b7276a57c56081d3336fef816b5f204eff


[ROCm/clr commit: 52859a8a40]
 2017-03-17 18:26:10 -05:00
Sun, Peng d5f632f271 Disable additional debug warning message 
Change-Id: Ic5c374589bfad387a7c4c5346430a490e2c6e2a7


[ROCm/clr commit: 2585812fba]
 2017-03-17 15:03:03 -05:00
pensun a8c91ca379 Change the #define of GENERIC_GRID_LAUNCH to take valueat compilation, disable warning messages 
Change-Id: Ic6c011529e26de359bcda1e7083727e7ee52887b


[ROCm/clr commit: faf0fbebe9]
 2017-03-17 14:59:34 -05:00
pensun 9c9a9bb330 Initial integration with Alex' Generic Grid Launch 
Change-Id: I559afb80e9e39ec0d119bb3bf3b85ef9e448caf6


[ROCm/clr commit: ad882222b0]
 2017-03-17 14:59:34 -05:00
Ben Sander 7466b4005b Move USE_PROMOTE_FREE_HCC 
[ROCm/clr commit: 20ea5e179f]
 2017-03-17 12:04:13 -05:00
Ben Sander e0171505b4 Add __device__ to needful functions for promote-free. 
[ROCm/clr commit: 92fd4c8f10]
 2017-03-17 11:19:48 -05:00
Ben Sander 572be5449d Add USE_PROMOTE_FREE_HCC for smooth transition to new HCC caps. 
ADDRESS_SPACE_1 defines


[ROCm/clr commit: f4256cb57c]
 2017-03-17 11:04:39 -05:00
Ben Sander c81fb24611 Add simple device-side assert macro 
Currently swallows asserts but will compile.


[ROCm/clr commit: c9f64bbd2d]
 2017-03-17 10:25:56 -05:00
Maneesh Gupta d43640c77c Merge branch 'amd-master' into amd-develop 
Change-Id: I01a77c34e11b1b02cb20e11b105741f6bd383543


[ROCm/clr commit: e3aa3d7ba6]
 2017-03-15 09:56:45 +05:30
Rahul Garg 6e4f693cd8 hipMemsetD8 support for HIP/NVCC path 
Change-Id: I48eee8266afd7b45a12d5ce2c4849b687a006c0f


[ROCm/clr commit: 09d1a46139]
 2017-03-14 23:49:21 +05:30
Rahul Garg 4443b7520c Added hipMemsetD8 
Change-Id: I6a230a036c9c46c72a77d5f93c16ce8a00c3f837


[ROCm/clr commit: dccf9e2aa9]
 2017-03-14 22:11:34 +05:30
Wen-Heng (Jack) Chung 54f40acc7a Revert "Changes to HIP to cope with Promote-free HCC" 
This reverts commit 9591c5a447.

Change-Id: I20a9bab3883ad09913b320210344d37599cb8fcd


[ROCm/clr commit: 17af837120]
 2017-03-14 22:59:27 +08:00
Maneesh Gupta 8d526e796e Merge branch 'amd-master' into amd-develop 
[ROCm/clr commit: 0853c8ac2e]
 2017-03-14 13:44:41 +05:30
Aditya Atluri 725f20ab1e make sure the inter-thread intrinsics are working post hawaii 
Change-Id: I30ea5284c2160276f5bc0f937dfd386ca8640ce8


[ROCm/clr commit: af56898ea0]
 2017-03-13 11:16:05 -05:00
Ben Sander 49d7ea94f5 Refactor registered memory calls. 
[ROCm/clr commit: b7acb85fa8]
 2017-03-11 09:18:27 -06:00
Aditya Atluri c8a1b6bc30 fixed warning raised by g++ using hip_vector_types.h 
Change-Id: I9e7cdfc8b28b03b690eecd068529cf7629296d68


[ROCm/clr commit: a47066153f]
 2017-03-10 15:14:26 -06:00
Rahul Garg b2b8361763 IPC supported using ROCR APIs 
Change-Id: I0a353b1240098f4b20fa266a871f5f5826290af9


[ROCm/clr commit: 3af487007b]
 2017-03-10 23:45:28 +05:30
pensun a49f5c7e1d update porting guide for updated __HIP_DEVICE_COMPILE__ 
Change-Id: I0f025d354f76e2d728231bf112a77e8c8fcacc8c


[ROCm/clr commit: 1a2844e3a3]
 2017-03-10 10:01:12 -06:00
Aditya Atluri a816a9eb54 Added architecture guards around __shfl, dpp and ds_permute device functions 
Change-Id: I10f9b08618fbf25b61c1932278fc5759e41c0d66


[ROCm/clr commit: 046ec0375b]
 2017-03-10 08:40:59 -06:00
pensun 3152223be6 add inline to all hip_complex operators 
Change-Id: Ifba5966c297cbc9299c39ecfc45c7296003ebb5d


[ROCm/clr commit: 14a5d3c80d]
 2017-03-08 14:06:13 -06:00
Aditya Atluri c861d10d1e Added new API, hipMemPtrGetInfo 
1. This API returns memory allocation size of pointer
2. Added test to check its functionality

Change-Id: I87976d817b5a6ca5530336c09e7cb0420601cb2c


[ROCm/clr commit: 7b7d53f875]
 2017-03-07 13:46:29 -06:00
Wen-Heng (Jack) Chung 9591c5a447 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/clr commit: 0005dd5f66]
 2017-03-08 01:32:59 +08:00
Aditya Atluri 106030f2c6 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/clr commit: 9f575721aa]
 2017-03-07 11:24:32 -06:00
Ben Sander 115631e210 Modify memcpy and memset to follow C/C++ standard: 
- memcpy src is const
    - memset val is int


[ROCm/clr commit: 8e50134d31]
 2017-03-06 16:38:22 -06:00
Evgeny Mankov 460971e93c [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/clr commit: 430856ca35]
 2017-03-01 23:04:34 +03:00
Aditya Atluri b430c3be71 changed __half enabling from 4 to >3 
Change-Id: Id974c6d5326e87a4c5941f831c5bb2747cdebd2d


[ROCm/clr commit: 37bc29e44b]
 2017-02-28 17:13:29 -06:00
pensun 077e789db5 Define __HIPCC__ flag at compile time when using HIPCC on HCC path 
Change-Id: I5e967e0e2327264d5d3b0ca705c2504fcd33d75e


[ROCm/clr commit: be95cc914f]
 2017-02-28 16:20:48 -06:00
Evgeny Mankov 8c237b0837 [HIP] Add missing Device attribute on nvcc path. 
+ missing cudaDevAttrComputeCapabilityMinor case as added for hipDeviceGetAttribute query for hipDeviceAttributeComputeCapabilityMinor.


[ROCm/clr commit: 47a27e6b17]
 2017-02-28 18:40:13 +03:00