AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,488 Commits 3 Branches 0 Tags
65bb22eefc620392cbcdf8f03beb61690acc71d3
Commit Graph

1488 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Maneesh Gupta 65bb22eefc Disable broken tests on hcc path 
Change-Id: Id6234da576566faa32d5fdf42dca6d6267596823
 2017-03-15 12:03:44 +05:30
Maneesh Gupta 4ae1ea8143 hipcc: Fix warning when HCC_AMDGPU_TARGET is not defined 
Change-Id: I5cc6b0e9fb23ec78152d8bcfe9e7511e2fe91055
 2017-03-15 12:03:05 +05:30
Maneesh Gupta 1337ed9159 Merge branch 'amd-master' into amd-develop 
Change-Id: I01a77c34e11b1b02cb20e11b105741f6bd383543
 2017-03-15 09:56:45 +05:30
Rahul Garg 913867fe6a hipMemsetD8 support for HIP/NVCC path 
Change-Id: I48eee8266afd7b45a12d5ce2c4849b687a006c0f
 2017-03-14 23:49:21 +05:30
Rahul Garg 1aba3c4375 Added hipMemsetD8 
Change-Id: I6a230a036c9c46c72a77d5f93c16ce8a00c3f837
 2017-03-14 22:11:34 +05:30
Wen-Heng (Jack) Chung 77e21dc09f Revert "Changes to HIP to cope with Promote-free HCC" 
This reverts commit efb9b9e86c.

Change-Id: I20a9bab3883ad09913b320210344d37599cb8fcd
 2017-03-14 22:59:27 +08:00
Maneesh Gupta 0f861fbba5 Merge branch 'amd-develop' into amd-master 
Change-Id: I8921e67e352e35e4c496e78a797fb309279ab7d0
 2017-03-14 15:57:53 +05:30
Maneesh Gupta 9f5a11a3fb 4_shfl and 5_2dshfl samples are unsupported on gfx701 
Change-Id: I81eb880350f25e89573ba14c62b549c6c43f8c91
 2017-03-14 15:56:18 +05:30
Maneesh Gupta 63074e24d9 default to gfx803 instead of fatbin if no arch specified 
Change-Id: I83d56c6ede11c356d383b09d7eb3a5f08c8d8c84
 2017-03-14 14:34:25 +05:30
Maneesh Gupta 13ab31ba34 hipcc: Support targets specified via HCC_AMDGPU_TARGET 
Change-Id: I69fda40d9f666325d377f4b4335e7ee693069214
 2017-03-14 14:29:30 +05:30
Maneesh Gupta db1bd201cd Add gfx900 support 
Change-Id: I3be2fbdcb6d3fa776c4fe668586c67245a1323f2
 2017-03-14 13:51:38 +05:30
Maneesh Gupta 675dd1cedf Merge branch 'amd-master' into amd-develop 2017-03-14 13:44:41 +05:30
Aditya Atluri c8969811db make sure the inter-thread intrinsics are working post hawaii 
Change-Id: I30ea5284c2160276f5bc0f937dfd386ca8640ce8
 2017-03-13 11:16:05 -05:00
Ben Sander e7d6a34327 Update hiphostregister test. 
Move check to correct place.
 2017-03-12 09:51:33 -05:00
Ben Sander 524e007db5 Refactor registered memory calls. 2017-03-11 09:18:27 -06:00
Ben Sander f022bd651f Add first step to a "registerd" mode in hipBusBandwidth. 2017-03-11 09:18:27 -06:00
Ben Sander 0a554f4dc1 Update hipHostRegister debug and pointerTracker debug and notes 2017-03-11 09:18:27 -06:00
Ben Sander 94c85fd4fc Fix copying of registered memory. 
Set device properly so copying can recover context.
Enhance test to catch this case.
 2017-03-11 09:18:27 -06:00
Aditya Atluri e79dd9f9c6 fixed warning raised by g++ using hip_vector_types.h 
Change-Id: I9e7cdfc8b28b03b690eecd068529cf7629296d68
 2017-03-10 15:14:26 -06:00
Rahul Garg 32d8a58f18 IPC supported using ROCR APIs 
Change-Id: I0a353b1240098f4b20fa266a871f5f5826290af9
 2017-03-10 23:45:28 +05:30
pensun 37ed319a20 update porting guide for updated __HIP_DEVICE_COMPILE__ 
Change-Id: I0f025d354f76e2d728231bf112a77e8c8fcacc8c
 2017-03-10 10:01:12 -06:00
Aditya Atluri 1567d20aa8 Added architecture guards around __shfl, dpp and ds_permute device functions 
Change-Id: I10f9b08618fbf25b61c1932278fc5759e41c0d66
 2017-03-10 08:40:59 -06:00
Rahul Garg 6d815f84d1 Fix for HCSWAP-128, make 5_2dshfl cookbook sample only for fiji 
Change-Id: I8869c28151bca1bd47a053a2808e93a801d16d00
 2017-03-10 10:29:52 +05:30
Aditya Atluri 60f8908ad8 make 4_shfl cookbook sample only for fiji 
1. __shfl is not supported on hawaii gfx701

Change-Id: Iac09f5d30ee0674b8f58a6e74ec5c49b02be32ad
 2017-03-09 08:52:50 -06:00
pensun 7290cb07ec fix typo in hip_porting_guide 
Change-Id: I42553d9a4de2901dfdd57384b52a04e8fb22edde
 2017-03-08 23:37:50 -06:00
pensun 7488d8c7fa add inline to all hip_complex operators 
Change-Id: Ifba5966c297cbc9299c39ecfc45c7296003ebb5d
 2017-03-08 14:06:13 -06:00
Ben Sander 439e37ab76 Fix bug in hipModuleGetFunction. 
Modules with > 1 function didn't return the function correctly.
Also fix coding convention issues
 2017-03-08 13:52:38 -06:00
Maneesh Gupta 7a59103cea Disable hipMemPtrGetInfo test on nvcc path 
Change-Id: I864e571314abfe5ae614e6792c86d7b457c920ee
 2017-03-08 16:16:08 +05:30
Aditya Atluri 5009bfb2df fixed atan2f arguments 
Change-Id: I0bb621e94d57594c3899e51d0c34ef43306cead0
 2017-03-07 14:06:03 -06:00
Aditya Atluri 1546732604 Added new API, hipMemPtrGetInfo 
1. This API returns memory allocation size of pointer
2. Added test to check its functionality

Change-Id: I87976d817b5a6ca5530336c09e7cb0420601cb2c
 2017-03-07 13:46:29 -06:00
Wen-Heng (Jack) Chung efb9b9e86c 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
 2017-03-08 01:32:59 +08:00
Aditya Atluri f86f3b3b33 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
 2017-03-07 11:24:32 -06:00
Maneesh Gupta 5ba13f6963 Merge branch 'amd-develop' into amd-master 
Change-Id: I393d1a8c7c5cdb2ca63098bf81ff9b98ea5e7b16
 2017-03-07 14:41:30 +05:30
Maneesh Gupta 12e8d635aa FindHIP: better handling for custom HCC_HOME 
Change-Id: Ica267de11cde58d1e759cd1fd053b699649ea76a
 2017-03-07 14:40:04 +05:30
Ben Sander d572e0616e Modify memcpy and memset to follow C/C++ standard: 
- memcpy src is const
    - memset val is int
 2017-03-06 16:38:22 -06:00
Rahul Garg c8e985f83c Removed hsakmt headers 
Change-Id: I4ffc95d5823489195ebc5638226b49ea2995f603
 2017-03-06 22:37:05 +05:30
Siu Chi Chan 910df3d80f fix hcc version detection in hipcc 
Change-Id: I880be03ad67e99280a259369bfe25488bf53f0bd
 2017-03-06 15:34:30 +05:30
Siu Chi Chan c3126bab8a fix hcc version string extraction 
Change-Id: Ie209b6deae55c779a577aaccb1bc21f969f69e14
 2017-03-06 15:33:43 +05:30
Maneesh Gupta aca015c47d CMakeLists: Create test targets only if HIP install location is writable 
Change-Id: I79f28884b0f117f2824ca8877c25b586bce62e5b
 2017-03-06 15:32:21 +05:30
Evgeny Mankov aa2fc24482 [HIP] [DOC] Update CUDA_Runtime_API_functions_supported_by_HIP 
+ update all Cuda 7.5 RT API enum values.
 2017-03-03 22:05:23 +03:00
Evgeny Mankov 749803c849 [HIPIFY] Sync HIPIFY with HIP by enum values. 
+ all Cuda 7.5 RT API enum values are synced.
+ a few missing functions are added.
+ CONV_EXEC type is added for Execution control functions and data types.
 2017-03-03 21:59:05 +03:00
Evgeny Mankov 6421a1e79e [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).
 2017-03-01 23:04:34 +03:00
Aditya Atluri e7ccc995ee changed __half enabling from 4 to >3 
Change-Id: Id974c6d5326e87a4c5941f831c5bb2747cdebd2d
 2017-02-28 17:13:29 -06:00
pensun fd610e497b Define __HIPCC__ flag at compile time when using HIPCC on HCC path 
Change-Id: I5e967e0e2327264d5d3b0ca705c2504fcd33d75e
 2017-02-28 16:20:48 -06:00
Evgeny Mankov f9ad2dca7e [HIP] Add missing Device attribute on nvcc path. 
+ missing cudaDevAttrComputeCapabilityMinor case as added for hipDeviceGetAttribute query for hipDeviceAttributeComputeCapabilityMinor.
 2017-02-28 18:40:13 +03:00
pensun ac4b7e3f91 update hip_porting_guide regarding platform depended macros 
Change-Id: I3029c6ae6cb280500bba294925ed6e9dc9dcc94d
 2017-02-28 07:33:01 -06:00
Maneesh Gupta 0672b19264 packaging script changes for hip_hcc 
Change-Id: I06cce6048204315a891e3a12638a3067644cfb43
 2017-02-28 12:02:53 +05:30
pensun df9cbb6067 remove extra spaces for hip_common.h platform defines 
Change-Id: Ie0e39256abba307429985371671cde01f5ea2cc9
 2017-02-27 12:55:22 -06:00
Rahul Garg bddd6b73c0 Context management related changes in HIP. 
-
-Contexts across threads are listed under device
-Device reset cleans up all contexts and re-initializes _primaryCtx

Change-Id: Ie1cfbb26d43a8dc6869be3e6ebaf7344ce374643
 2017-02-27 15:24:17 +05:30
Maneesh Gupta 4a6166cd86 Fix nvcc path samples that include math_functions.h 
Change-Id: I94bb577b93983535178d8f0dcae57aaa72871534
 2017-02-27 13:20:05 +05:30