Граф коммитов

954 Коммитов

Автор SHA1 Сообщение Дата
Nico Trost 5802734f1b fixed loss of accuracy in hipCfma()
[ROCm/hip commit: 7bb5a14a4e]
2019-03-21 10:30:10 +01:00
Maneesh Gupta 1bc0e84e83 Merge pull request #972 from yxsamliu/global
Add declaration of symbol related API for VDI

[ROCm/hip commit: 6ade928535]
2019-03-20 05:12:21 +00:00
Maneesh Gupta 7892ca44b4 Merge pull request #973 from mhbliao/hliao/master/build
[Device Function] Fix typos.

[ROCm/hip commit: 87551e29f6]
2019-03-20 05:12:14 +00:00
eshcherb bbc63ad2ec adding prof primitives generator (#967)
* adding prof primitives generator

* minor change, renaming

* minor cosmetic changes, comments correcting and dead code removing

* minor changes and renaming

* minor chane, fixing comments


[ROCm/hip commit: 673cdeea55]
2019-03-20 05:11:40 +00:00
Siu Chi Chan 99c4f43a6c reimplement HIP_INIT as hip_impl::hip_init(), add hip_init() to some of the inlined API (#966)
* reimplement HIP_INIT as a function, expose it as hip_impl::hip_init()
so that it could be called from hipLaunchKernelGGL and other inlined
HIP functions

* Don't call hip_init from ihipPreLaunchKernel


[ROCm/hip commit: 24d08beef8]
2019-03-20 05:11:15 +00:00
Michael LIAO d0680ef1ee [Device Function] Fix typos.
[ROCm/hip commit: e51fa174c8]
2019-03-19 15:32:19 -04:00
Yaxun Sam Liu 4f094c4d21 Add declaration of symbol related API for VDI
[ROCm/hip commit: e9bc4034d8]
2019-03-19 11:11:49 -04:00
Maneesh Gupta 88761d52ce Merge pull request #965 from mhbliao/hliao/master/immarg
[Device Function] Support immediate argument.

[ROCm/hip commit: 4094824b9e]
2019-03-19 18:41:31 +05:30
Maneesh Gupta 173c910f5d Merge pull request #954 from mhbliao/master
[hip] Re-implement hipLaunchKernelGGL as macros.

[ROCm/hip commit: 91ebfadabf]
2019-03-19 18:39:27 +05:30
Michael LIAO f282ea815a [Device Function] Support immediate argument.
- `immarg`, immediate argument, is enabled on all AMDGPU intrinsics.
  Revise device functions using these intrinsics with immediate
  arguments.


[ROCm/hip commit: 950b6efe72]
2019-03-15 12:38:04 -04:00
Evgeny 36b5313d65 tracing callback layer update
[ROCm/hip commit: 31475c5ac8]
2019-03-14 22:43:52 -05:00
Maneesh Gupta 1d61f5ff58 Merge pull request #958 from aaronenyeshi/cxxabi-mismatch-workaround
CXX11 ABI Mismatch Workaround

[ROCm/hip commit: 419127172e]
2019-03-15 06:15:46 +05:30
Siu Chi Chan 151b288155 remove visibility hidden attribute
[ROCm/hip commit: 10d3084e20]
2019-03-13 11:58:32 -04:00
Evgeny 75d89bf129 adding memset32d
[ROCm/hip commit: 4ffe413cfd]
2019-03-11 21:28:27 -05:00
Siu Chi Chan ce064f942a minor cleanup
[ROCm/hip commit: cb9ea5cefc]
2019-03-11 19:51:57 +00:00
Siu Chi Chan ac10afb0f7 remove old style triple name
[ROCm/hip commit: d37f9e6b2d]
2019-03-11 19:51:51 +00:00
Siu Chi Chan fc9af438a4 move triple_to_hsa_isa into the header
[ROCm/hip commit: 824ee1aa72]
2019-03-11 19:51:44 +00:00
Siu Chi Chan 15061ddfcc Fix memory leak introduced by previous change to Agent_global.
Make Agent_global manage the lifetime of the name string


[ROCm/hip commit: bf1d48bf78]
2019-03-11 19:51:32 +00:00
Aaron Enye Shi 1e07be3ab3 Fix Agent_global variables failing hipTestDeviceSymbol
Issue: Header uses std::vector<Agent_global> agent_globals which is created by hip_module.cpp
  - Move iterator fails to copy Agent_global from library source into header version
  - Due to different versions of std::string name in struct Agent_global
Fix: Change Agent_global to use char* name instead of std::string name


[ROCm/hip commit: 00d24d254d]
2019-03-11 19:51:25 +00:00
Aaron Enye Shi 4b87bd25e8 Fix hash_for undefined reference in hipTestConstant test
Issue: mismatch undefined symbols in different user env
  - Binary expects modified return value std::string&
  - Fails to match libhip_hcc.so: return value is std::string& but doesn't match modified C++ env
Fix: Change return value to char*, create new key std::string in header from char*


[ROCm/hip commit: 23e9968752]
2019-03-11 19:51:18 +00:00
Michael Liao c0f6fa358f [hip] Re-implement hipLaunchKernelGGL as macros.
[ROCm/hip commit: 30185b4114]
2019-03-08 09:10:51 -05:00
Maneesh Gupta 645c29159c Merge pull request #951 from tycho/nvcc-hipDeviceSetCacheConfig
nvcc_detail/hip_runtime_api.h: add missing hipDeviceSetCacheConfig API

[ROCm/hip commit: 250bd58254]
2019-03-08 09:22:25 +05:30
Yaxun Sam Liu a431326408 Fix HIP/VDI build failure due to dlopen change
[ROCm/hip commit: 6e9e90addd]
2019-03-07 14:45:45 -05:00
Steven Noonan 17e2bfe3f8 nvcc_detail/hip_runtime_api.h: add missing hipDeviceSetCacheConfig API
Signed-off-by: Steven Noonan <steven@uplinklabs.net>


[ROCm/hip commit: ee750d5ea4]
2019-03-06 11:21:36 -08:00
Maneesh Gupta 3f5e937afc Merge pull request #949 from gargrahul/single_stream_concurrent_kernels
Add extension for kernel concurrency on same stream

[ROCm/hip commit: 352b17346c]
2019-03-06 17:34:54 +05:30
Alex Voicu 0c16497abd dlopen() fixes (#929)
* Initial attempt to switch over to internally linked state.

* Add missing CMake update.

* hipLaunchKernelGGLImpl must be inline as well. Ensure internal linkage.

* Ensure global retrieval uses internally linked state.

* Hide HC in the implementation. Minimise ADL woes.

* Strange software exists, and must be catered to.

* Use a less spammy mechanism for ensuring internal linkage / non-export.

* Remove leftover internal detail.


[ROCm/hip commit: ea0fcf3e61]
2019-03-06 17:31:44 +05:30
Rahul Garg 5d6fd17fbe Add extension for kernel concurrency on same stream
[ROCm/hip commit: 59081c69fc]
2019-03-06 12:55:39 +05:30
Maneesh Gupta 19b6b2b570 Update hip_runtime_api.h
Use hipCUResultTohipError instead of hipCUDAErrorTohipError in hipMemsetD32 & hipMemsetD32Async.

[ROCm/hip commit: 8db717c769]
2019-03-05 12:10:01 +05:30
Wen-Heng (Jack) Chung da589e38ed Address code review comments to use hipDeviceptr_t
[ROCm/hip commit: 5cbd28f29b]
2019-03-05 05:51:05 +00:00
Wen-Heng (Jack) Chung ea689f63ca Add implementation for NVCC path
[ROCm/hip commit: 0337b686ef]
2019-03-04 20:11:12 -08:00
Wen-Heng (Jack) Chung 0b7f38d100 Add hipMemsetD32 and hipMemsetD32Async
Add 2 extra memset functions which fills memory with integer-typed data

Also change the parameters of ihipMemset to better explain the semantic


[ROCm/hip commit: 7ebbbd3525]
2019-03-04 17:00:33 +00:00
Maneesh Gupta f0bb5690f1 Merge pull request #937 from yxsamliu/nan2
Fix nan for windows

[ROCm/hip commit: 07b0e9574c]
2019-02-28 07:14:27 +05:30
Yaxun Sam Liu 48ab0aa588 Fix nan for windows
[ROCm/hip commit: 278007218a]
2019-02-27 12:33:26 -05:00
Rahul Garg 67723bd3e7 Fix forceinline for non HCC compilation
[ROCm/hip commit: 55145feae6]
2019-02-26 07:50:09 +05:30
Maneesh Gupta 8f1b3d34f7 Fix signature for unsigned long long variant of atomicExch
This fixes #888

Change-Id: I2b2dc5ed1ff2a26083ad9d102eccac90f67801ae


[ROCm/hip commit: f0618df8f4]
2019-02-13 09:45:07 +05:30
Maneesh Gupta f18ddd57da Merge pull request #913 from aaronenyeshi/fix-texture-constant-addrspace
Fix texture using constant addrspace 4

[ROCm/hip commit: ca7a53b13d]
2019-02-13 08:59:01 +05:30
Maneesh Gupta 6d16a4b679 Merge pull request #912 from ROCm-Developer-Tools/remove-cpp-function-templates-for-malloc
Remove C++ function templates for hipMalloc and hipHostMalloc

[ROCm/hip commit: f9daeb1c51]
2019-02-13 08:58:26 +05:30
Aaron Enye Shi 1dad8c4329 Fix texture using constant addrspace 4
[ROCm/hip commit: 63b400beea]
2019-02-12 16:56:22 +00:00
Wen-Heng (Jack) Chung abd8e75c47 Introduce __HIP_DISABLE_CPP_FUNCTIONS__ macro to disable C++ wrappers
hipMalloc and hipHostMalloc are C++ function templates by default. In some
applications they need to discover the decltype of underlying C functions. In
this commit, a new macro __HIP_DISABLE_CPP_FUNCTIONS__ is introduced to
suppress the C++ function templates.

Existing HIP applications don't need to be changed. hipMalloc and hipHostMalloc
will behave just the same.

For new applications which depends on identifying decltypes of underlying C
functions, __HIP_DISABLE_CPP_FUNCTIONS__ shall be defined prior to including
HIP headers.


[ROCm/hip commit: eba3bd3082]
2019-02-11 09:33:15 -06:00
Maneesh Gupta 747433e1a0 Merge pull request #907 from yxsamliu/nan
Fix nan() for windows

[ROCm/hip commit: 87673d0750]
2019-02-11 11:24:12 +05:30
Yaxun Sam Liu a44cc818ce Fix nan() for windows
[ROCm/hip commit: ee4ce7ae49]
2019-02-07 17:29:36 -05:00
Yaxun Sam Liu ecfc886193 Fix hipcc and hip_vector_types.h for windows
Disable linux specific compilation and linking options for windows.

In hip_vector_types.h, hip-clang needs HIP's own implementation for vector types even
on windows. MSVC specific implementation is for building runtime itself, which is compiled
by MSVC.


[ROCm/hip commit: a474dc7579]
2019-02-07 11:07:50 -05:00
Yaxun Sam Liu f724c69c4e Fix build failure on windows due to vector type
[ROCm/hip commit: 43c144fe68]
2019-02-05 12:22:32 -05:00
Evgeny e33596b6cd return false if PROF_API is disabled
[ROCm/hip commit: cc5ff70b90]
2019-01-29 23:14:57 -06:00
Maneesh Gupta 3686db5456 Merge pull request #863 from aaronenyeshi/add-dot-instructions
Add Dot functions as amd_mixed_dot function

[ROCm/hip commit: 50a12f1ce1]
2019-01-29 06:01:01 +05:30
Aaron Enye Shi ba1452b664 Fix mixed dot for Jenkins rocm_2_0
[ROCm/hip commit: ede494bd5f]
2019-01-24 22:48:35 +00:00
Aaron Enye Shi 7e22b05339 Use correct OCKL native vector types
[ROCm/hip commit: 712a4cbdc2]
2019-01-22 22:31:19 +00:00
Aaron Enye Shi 67d0de2dba Allow hip-clang to use amd_mixed_dot as well
[ROCm/hip commit: 8bf588bdb1]
2019-01-22 16:21:16 +00:00
Evgeny 3f7ff3450e fixing HSA_INIT_API cid args
[ROCm/hip commit: 0164464bcc]
2019-01-16 23:45:44 -06:00
Maneesh Gupta 09fe2d6bc5 Map more instrincis to ocml native
Change-Id: I54e55d5902931bafdabd0956e4e8c1d7b39f7173


[ROCm/hip commit: dd9bea7d25]
2019-01-15 19:40:37 +05:30