AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность

Граф коммитов

  • 822743845c Fix float2int rounding functions Maneesh Gupta 2017-11-23 09:57:24 +05:30
  • 2e043b7c0e Fix float2int rounding functions Maneesh Gupta 2017-11-23 09:57:24 +05:30
  • 4c96882366 Fix float2int rounding functions Maneesh Gupta 2017-11-23 09:57:24 +05:30
  • 36951c298d Remove leftover comment. Alex Voicu 2017-11-22 19:37:03 +00:00
  • dfa532db98 Remove leftover comment. Alex Voicu 2017-11-22 19:37:03 +00:00
  • acc05cdff7 Remove leftover comment. Alex Voicu 2017-11-22 19:37:03 +00:00
  • 08f252e4bf Remove leftover comment. Alex Voicu 2017-11-22 19:37:03 +00:00
  • d7e1419d8b Merge pull request #263 from ChrisKitching/headers Evgeny Mankov 2017-11-22 21:24:21 +03:00
  • 6bddac1cfa Merge pull request #263 from ChrisKitching/headers Evgeny Mankov 2017-11-22 21:24:21 +03:00
  • 52b93658a9 Merge pull request #263 from ChrisKitching/headers Evgeny Mankov 2017-11-22 21:24:21 +03:00
  • 4e92a034d0 Merge pull request #263 from ChrisKitching/headers Evgeny Mankov 2017-11-22 21:24:21 +03:00
  • b3439f48c2 Add debug message in PMC trace Amber Lin 2017-11-21 11:47:25 -05:00
  • 6f7b55f2d8 Add debug message in PMC trace Amber Lin 2017-11-21 11:47:25 -05:00
  • 198f7e4168 P4 to Git Change 1485337 by todli@todli-win-opencl-kv1 on 2017/11/21 18:53:38 foreman 2017-11-21 18:58:23 -05:00
  • 4e0baa79b3 P4 to Git Change 1485337 by todli@todli-win-opencl-kv1 on 2017/11/21 18:53:38 foreman 2017-11-21 18:58:23 -05:00
  • b5c6043d6e P4 to Git Change 1485325 by gandryey@gera-lnx-rcf on 2017/11/21 18:10:36 foreman 2017-11-21 18:17:45 -05:00
  • 0e496d9c9f P4 to Git Change 1485325 by gandryey@gera-lnx-rcf on 2017/11/21 18:10:36 foreman 2017-11-21 18:17:45 -05:00
  • 7486e8e29f Fix unconditional unmap in fmm_map_to_gpu_nodes Oak Zeng 2017-11-20 10:57:37 -05:00
  • 061db45fe2 Fix unconditional unmap in fmm_map_to_gpu_nodes Oak Zeng 2017-11-20 10:57:37 -05:00
  • 84d88b8e1a Properly control lifecycle of ptr info objects Oak Zeng 2017-11-20 16:15:29 -05:00
  • f06e887725 Properly control lifecycle of ptr info objects Oak Zeng 2017-11-20 16:15:29 -05:00
  • f9b177c0b3 Modify the set component of the memcpy test (unclear why there is a memset component to begin with). Alex Voicu 2017-11-21 17:52:01 +00:00
  • 0755f1fc26 Modify the set component of the memcpy test (unclear why there is a memset component to begin with). Alex Voicu 2017-11-21 17:52:01 +00:00
  • d8db534805 Modify the set component of the memcpy test (unclear why there is a memset component to begin with). Alex Voicu 2017-11-21 17:52:01 +00:00
  • 4131b47134 Modify the set component of the memcpy test (unclear why there is a memset component to begin with). Alex Voicu 2017-11-21 17:52:01 +00:00
  • 212afdf56b Fixed review comments Rahul Garg 2017-11-21 21:19:06 +05:30
  • 38029f2849 Fixed review comments Rahul Garg 2017-11-21 21:19:06 +05:30
  • 13879387e5 Fixed review comments Rahul Garg 2017-11-21 21:19:06 +05:30
  • 56862b1c35 Fixed review comments Rahul Garg 2017-11-21 21:19:06 +05:30
  • 31deac0768 This corrects how addresses are formed for symbols which reside in shared objects. For this case, the .value component of an ELF symbol holds the offset from the base VA where the shared object was loaded. Thus, to correctly obtain the VA of the object refered by the symbol, we must add the offset to the VA where the shared object is loaded. We were already doing this correctly for symbols denoting functions, but we were incorrect for those denoting objects. Alex Voicu 2017-11-21 13:15:13 +00:00
  • fb1021cc0a This corrects how addresses are formed for symbols which reside in shared objects. For this case, the .value component of an ELF symbol holds the offset from the base VA where the shared object was loaded. Thus, to correctly obtain the VA of the object refered by the symbol, we must add the offset to the VA where the shared object is loaded. We were already doing this correctly for symbols denoting functions, but we were incorrect for those denoting objects. Alex Voicu 2017-11-21 13:15:13 +00:00
  • d71132de7c This corrects how addresses are formed for symbols which reside in shared objects. For this case, the .value component of an ELF symbol holds the offset from the base VA where the shared object was loaded. Thus, to correctly obtain the VA of the object refered by the symbol, we must add the offset to the VA where the shared object is loaded. We were already doing this correctly for symbols denoting functions, but we were incorrect for those denoting objects. Alex Voicu 2017-11-21 13:15:13 +00:00
  • 5e16ee0d1f This corrects how addresses are formed for symbols which reside in shared objects. For this case, the .value component of an ELF symbol holds the offset from the base VA where the shared object was loaded. Thus, to correctly obtain the VA of the object refered by the symbol, we must add the offset to the VA where the shared object is loaded. We were already doing this correctly for symbols denoting functions, but we were incorrect for those denoting objects. Alex Voicu 2017-11-21 13:15:13 +00:00
  • ca62d35d13 Merge 'master' into 'amd-master' Jenkins 2017-11-21 04:10:37 -06:00
  • c0f413a07a Merge 'master' into 'amd-master' Jenkins 2017-11-21 04:10:37 -06:00
  • 232a6cfdd0 Merge 'master' into 'amd-master' Jenkins 2017-11-21 04:10:37 -06:00
  • 619fce9daf Merge 'master' into 'amd-master' Jenkins 2017-11-21 04:10:37 -06:00
  • 7933dae277 P4 to Git Change 1484863 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/21 03:00:05 foreman 2017-11-21 03:11:16 -05:00
  • e7579ebca0 P4 to Git Change 1484863 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/21 03:00:05 foreman 2017-11-21 03:11:16 -05:00
  • 1b359db390 Changed function hipMemcpy_2D to hipMemcpyParam2D Rahul Garg 2017-11-21 12:36:24 +05:30
  • 3d2e40a5df Changed function hipMemcpy_2D to hipMemcpyParam2D Rahul Garg 2017-11-21 12:36:24 +05:30
  • dc2c56c43d Changed function hipMemcpy_2D to hipMemcpyParam2D Rahul Garg 2017-11-21 12:36:24 +05:30
  • 24307fe5c4 Changed function hipMemcpy_2D to hipMemcpyParam2D Rahul Garg 2017-11-21 12:36:24 +05:30
  • 03552f2e94 Changed function hipMemcpy_2D to hipMemcpyParam2D Rahul Garg 2017-11-21 12:36:24 +05:30
  • 9866fa250d Changed function hipMemcpy_2D to hipMemcpyParam2D Rahul Garg 2017-11-21 12:36:24 +05:30
  • 1366b2d5ae Refactor the __device__ versions of memset and memcpy to be less awkward i.e. not return nullptr as opposed to the destination pointer (it can only be assumed it was done for maximum confusion) and actually unroll as they claim to. Change all of the {to, from}Symbol functions to use hipModuleGetGlobal, as opposed to hc::accelerator::get_symbol_address which is no longer valid with module based dispatch. Alex Voicu 2017-11-21 02:40:34 +00:00
  • f8c1c1b38e Refactor the __device__ versions of memset and memcpy to be less awkward i.e. not return nullptr as opposed to the destination pointer (it can only be assumed it was done for maximum confusion) and actually unroll as they claim to. Change all of the {to, from}Symbol functions to use hipModuleGetGlobal, as opposed to hc::accelerator::get_symbol_address which is no longer valid with module based dispatch. Alex Voicu 2017-11-21 02:40:34 +00:00
  • 45ff3c31c4 Refactor the __device__ versions of memset and memcpy to be less awkward i.e. not return nullptr as opposed to the destination pointer (it can only be assumed it was done for maximum confusion) and actually unroll as they claim to. Change all of the {to, from}Symbol functions to use hipModuleGetGlobal, as opposed to hc::accelerator::get_symbol_address which is no longer valid with module based dispatch. Alex Voicu 2017-11-21 02:40:34 +00:00
  • 9d088d2283 Refactor the __device__ versions of memset and memcpy to be less awkward i.e. not return nullptr as opposed to the destination pointer (it can only be assumed it was done for maximum confusion) and actually unroll as they claim to. Change all of the {to, from}Symbol functions to use hipModuleGetGlobal, as opposed to hc::accelerator::get_symbol_address which is no longer valid with module based dispatch. Alex Voicu 2017-11-21 02:40:34 +00:00
  • 1a0eaec2c6 P4 to Git Change 1484669 by wchau@wchau_WIN_OCL_HSA on 2017/11/20 17:33:26 foreman 2017-11-20 17:44:21 -05:00
  • d3a8bbdeb5 P4 to Git Change 1484669 by wchau@wchau_WIN_OCL_HSA on 2017/11/20 17:33:26 foreman 2017-11-20 17:44:21 -05:00
  • 98ea26e613 Clean-up some remaining noise in program_state.cpp. Alex Voicu 2017-11-20 22:41:46 +00:00
  • 24f8a93ff7 Clean-up some remaining noise in program_state.cpp. Alex Voicu 2017-11-20 22:41:46 +00:00
  • e8ca14848e Clean-up some remaining noise in program_state.cpp. Alex Voicu 2017-11-20 22:41:46 +00:00
  • 1824fb7698 Clean-up some remaining noise in program_state.cpp. Alex Voicu 2017-11-20 22:41:46 +00:00
  • acce35d21f _aqlprofile_start() API migration Evgeny 2017-11-16 10:11:44 -06:00
  • 86939368d1 _aqlprofile_start() API migration Evgeny 2017-11-16 10:11:44 -06:00
  • a62c1f5364 Use a default module search path if not already specified. Sean Keely 2017-11-17 21:35:11 -06:00
  • e81d04e11b Use a default module search path if not already specified. Sean Keely 2017-11-17 21:35:11 -06:00
  • f27cd5ad33 Correct ill-formed merge in earlier commit and adjust for differences with the new CUDA natural indexing mechanism. Alex Voicu 2017-11-20 16:33:52 +00:00
  • 27bc487635 Correct ill-formed merge in earlier commit and adjust for differences with the new CUDA natural indexing mechanism. Alex Voicu 2017-11-20 16:33:52 +00:00
  • 69f8043d12 Correct ill-formed merge in earlier commit and adjust for differences with the new CUDA natural indexing mechanism. Alex Voicu 2017-11-20 16:33:52 +00:00
  • 7d5a45ac1a Correct ill-formed merge in earlier commit and adjust for differences with the new CUDA natural indexing mechanism. Alex Voicu 2017-11-20 16:33:52 +00:00
  • 9cf73ef515 Re-sync with upstream. Alex Voicu 2017-11-20 15:34:50 +00:00
  • 30d90dab38 Re-sync with upstream. Alex Voicu 2017-11-20 15:34:50 +00:00
  • 3c936777aa Re-sync with upstream. Alex Voicu 2017-11-20 15:34:50 +00:00
  • c5f2b22d0d Re-sync with upstream. Alex Voicu 2017-11-20 15:34:50 +00:00
  • d2467747f1 Correct command in make package Amber Lin 2017-11-16 14:10:23 -05:00
  • 61d1c6ffac Correct command in make package Amber Lin 2017-11-16 14:10:23 -05:00
  • fdb4ea06f7 Merge pull request #264 from pzins/missing_end_marker Ben Sander 2017-11-20 06:08:01 -06:00
  • a1e0c96689 Merge pull request #264 from pzins/missing_end_marker Ben Sander 2017-11-20 06:08:01 -06:00
  • 6e332812fc Merge pull request #264 from pzins/missing_end_marker Ben Sander 2017-11-20 06:08:01 -06:00
  • e8ede28ec4 Merge pull request #264 from pzins/missing_end_marker Ben Sander 2017-11-20 06:08:01 -06:00
  • 9cee9705dc -Moved coGlobals in hipModule class (takes care of multi module case) -Used mutex scope for updating coGlobals Rahul Garg 2017-11-20 16:23:18 +05:30
  • eff09fcd86 -Moved coGlobals in hipModule class (takes care of multi module case) -Used mutex scope for updating coGlobals Rahul Garg 2017-11-20 16:23:18 +05:30
  • 97ee22c3f5 -Moved coGlobals in hipModule class (takes care of multi module case) -Used mutex scope for updating coGlobals Rahul Garg 2017-11-20 16:23:18 +05:30
  • f97c5f9a64 -Moved coGlobals in hipModule class (takes care of multi module case) -Used mutex scope for updating coGlobals Rahul Garg 2017-11-20 16:23:18 +05:30
  • 0479697c38 Merge 'master' into 'amd-master' Jenkins 2017-11-20 04:10:56 -06:00
  • b2c9b7af01 Merge 'master' into 'amd-master' Jenkins 2017-11-20 04:10:56 -06:00
  • 578fa476ae Merge 'master' into 'amd-master' Jenkins 2017-11-20 04:10:56 -06:00
  • 53b48673f3 Merge 'master' into 'amd-master' Jenkins 2017-11-20 04:10:56 -06:00
  • 02cbb93ec1 Merge pull request #266 from gargrahul/fix_half2_gfx900 Maneesh Gupta 2017-11-20 07:28:41 +05:30
  • 4477d3d314 Merge pull request #266 from gargrahul/fix_half2_gfx900 Maneesh Gupta 2017-11-20 07:28:41 +05:30
  • d807f528e6 Merge pull request #266 from gargrahul/fix_half2_gfx900 Maneesh Gupta 2017-11-20 07:28:41 +05:30
  • db378fbc9e Merge pull request #266 from gargrahul/fix_half2_gfx900 Maneesh Gupta 2017-11-20 07:28:41 +05:30
  • 9498ff3cae Merge pull request #265 from phani544/nvccTests Maneesh Gupta 2017-11-20 07:28:29 +05:30
  • 29c0ab8401 Merge pull request #265 from phani544/nvccTests Maneesh Gupta 2017-11-20 07:28:29 +05:30
  • 2bb78b3a69 Merge pull request #265 from phani544/nvccTests Maneesh Gupta 2017-11-20 07:28:29 +05:30
  • 1174534e85 Merge pull request #265 from phani544/nvccTests Maneesh Gupta 2017-11-20 07:28:29 +05:30
  • 809f575305 Fix test on cuda Ben Sander 2017-11-19 15:31:02 -06:00
  • aeadc3f18f Fix test on cuda Ben Sander 2017-11-19 15:31:02 -06:00
  • 1ec5bab716 Fix test on cuda Ben Sander 2017-11-19 15:31:02 -06:00
  • 59956a57ca Fix test on cuda Ben Sander 2017-11-19 15:31:02 -06:00
  • 80021d3c68 Merge branch 'feature_natural_indexing' of https://github.com/AlexVlx/HIP Ben Sander 2017-11-19 15:25:17 -06:00
  • a43262e699 Merge branch 'feature_natural_indexing' of https://github.com/AlexVlx/HIP Ben Sander 2017-11-19 15:25:17 -06:00
  • 64a169fd5c Merge branch 'feature_natural_indexing' of https://github.com/AlexVlx/HIP Ben Sander 2017-11-19 15:25:17 -06:00
  • 5a7a28ad29 Merge branch 'feature_natural_indexing' of https://github.com/AlexVlx/HIP Ben Sander 2017-11-19 15:25:17 -06:00
  • 6b1fb439f6 Temporarily disable P2P on nvidia (fails on dual GPU) Ben Sander 2017-11-19 15:21:37 -06:00
  • fc34fd6f03 Temporarily disable P2P on nvidia (fails on dual GPU) Ben Sander 2017-11-19 15:21:37 -06:00
  • dde41ae0aa Temporarily disable P2P on nvidia (fails on dual GPU) Ben Sander 2017-11-19 15:21:37 -06:00