Commit graph

962 Commits

Autor SHA1 Nachricht Datum
Jeff Daily 2845b4c4b8 load program state once per agent 2019-03-27 18:19:10 +00:00
Maneesh Gupta 178e3ecdca Merge pull request #990 from mhbliao/hliao/master/sw
SWDEV-184380 Fix hcc compilation
2019-03-27 05:23:26 +00:00
Michael LIAO d355122bf9 SWDEV-184380 Fix hcc compilation
- `hcc` has no builtin. Need to invoke LLVM intrinsic directly.
2019-03-26 15:20:17 -04:00
Michael LIAO 13655df76e [hip] Fix typo in macro hipLaunchKernel 2019-03-25 12:06:46 -04:00
Maneesh Gupta c20d233585 Merge pull request #970 from mangupta/swdev-172995
hipExtMallocWithFlags implementation
2019-03-25 07:46:53 +00:00
Maneesh Gupta 158eac9374 Merge pull request #982 from ROCm-Developer-Tools/hack_swdev-173477
HACK for SWDEV-173477
2019-03-22 09:14:38 +00:00
Wen-Heng (Jack) Chung cf7ad0f184 HACK for SWDEV-173477
For code objects with global symbols of length 0, ROCR runtime would
ignore them even though they exist in the symbol table. Therefore the
result from read_agent_globals() can't be trusted entirely.

As a workaround to tame applications which depend on the existence of
global symbols with length 0, always return hipSuccess here.

This behavior shall be reverted once ROCR runtime has been fixed to
address SWDEV-173477
2019-03-21 17:18:16 +00:00
Nico Trost 725486fb11 fixed loss of accuracy in hipCfma() 2019-03-21 10:30:10 +01:00
Maneesh Gupta ce72890dcf Merge pull request #972 from yxsamliu/global
Add declaration of symbol related API for VDI
2019-03-20 05:12:21 +00:00
Maneesh Gupta 54091b5273 Merge pull request #973 from mhbliao/hliao/master/build
[Device Function] Fix typos.
2019-03-20 05:12:14 +00:00
eshcherb 1229750546 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
2019-03-20 05:11:40 +00:00
Siu Chi Chan fa9495841b 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
2019-03-20 05:11:15 +00:00
Michael LIAO f42e84cef7 [Device Function] Fix typos. 2019-03-19 15:32:19 -04:00
Yaxun Sam Liu fb3241a000 Add declaration of symbol related API for VDI 2019-03-19 11:11:49 -04:00
Maneesh Gupta e7453483e2 Merge pull request #965 from mhbliao/hliao/master/immarg
[Device Function] Support immediate argument.
2019-03-19 18:41:31 +05:30
Maneesh Gupta 1500eec5f7 Merge pull request #954 from mhbliao/master
[hip] Re-implement hipLaunchKernelGGL as macros.
2019-03-19 18:39:27 +05:30
Maneesh Gupta e44de376f7 hipExtMallocWithFlags implementation
Change-Id: Iee9e119796472200b2933d5e23be60813f33bc75
2019-03-19 11:59:22 +05:30
Michael LIAO b74b4500c4 [Device Function] Support immediate argument.
- `immarg`, immediate argument, is enabled on all AMDGPU intrinsics.
  Revise device functions using these intrinsics with immediate
  arguments.
2019-03-15 12:38:04 -04:00
Evgeny 2aa88a4505 tracing callback layer update 2019-03-14 22:43:52 -05:00
Maneesh Gupta 23170f6af8 Merge pull request #958 from aaronenyeshi/cxxabi-mismatch-workaround
CXX11 ABI Mismatch Workaround
2019-03-15 06:15:46 +05:30
Siu Chi Chan 739d43c5d8 remove visibility hidden attribute 2019-03-13 11:58:32 -04:00
Evgeny 0586924ae6 adding memset32d 2019-03-11 21:28:27 -05:00
Siu Chi Chan 5044c9ba49 minor cleanup 2019-03-11 19:51:57 +00:00
Siu Chi Chan f54da9358b remove old style triple name 2019-03-11 19:51:51 +00:00
Siu Chi Chan 30053f6443 move triple_to_hsa_isa into the header 2019-03-11 19:51:44 +00:00
Siu Chi Chan fa564a5345 Fix memory leak introduced by previous change to Agent_global.
Make Agent_global manage the lifetime of the name string
2019-03-11 19:51:32 +00:00
Aaron Enye Shi fcde9fe3df 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
2019-03-11 19:51:25 +00:00
Aaron Enye Shi f8aca3159c 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*
2019-03-11 19:51:18 +00:00
Michael Liao f46d6cf249 [hip] Re-implement hipLaunchKernelGGL as macros. 2019-03-08 09:10:51 -05:00
Maneesh Gupta 44309ee879 Merge pull request #951 from tycho/nvcc-hipDeviceSetCacheConfig
nvcc_detail/hip_runtime_api.h: add missing hipDeviceSetCacheConfig API
2019-03-08 09:22:25 +05:30
Yaxun Sam Liu 2dc87b6019 Fix HIP/VDI build failure due to dlopen change 2019-03-07 14:45:45 -05:00
Steven Noonan 27d6755552 nvcc_detail/hip_runtime_api.h: add missing hipDeviceSetCacheConfig API
Signed-off-by: Steven Noonan <steven@uplinklabs.net>
2019-03-06 11:21:36 -08:00
Maneesh Gupta 3955f2c131 Merge pull request #949 from gargrahul/single_stream_concurrent_kernels
Add extension for kernel concurrency on same stream
2019-03-06 17:34:54 +05:30
Alex Voicu ed48847237 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.
2019-03-06 17:31:44 +05:30
Rahul Garg 263e82a67a Add extension for kernel concurrency on same stream 2019-03-06 12:55:39 +05:30
Maneesh Gupta 38b7a43b43 Update hip_runtime_api.h
Use hipCUResultTohipError instead of hipCUDAErrorTohipError in hipMemsetD32 & hipMemsetD32Async.
2019-03-05 12:10:01 +05:30
Wen-Heng (Jack) Chung 8b7baa0bd9 Address code review comments to use hipDeviceptr_t 2019-03-05 05:51:05 +00:00
Wen-Heng (Jack) Chung b46e684d2e Add implementation for NVCC path 2019-03-04 20:11:12 -08:00
Wen-Heng (Jack) Chung 392271f4db 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
2019-03-04 17:00:33 +00:00
Maneesh Gupta c1ff2c95a4 Merge pull request #937 from yxsamliu/nan2
Fix nan for windows
2019-02-28 07:14:27 +05:30
Yaxun Sam Liu 0ebe23512f Fix nan for windows 2019-02-27 12:33:26 -05:00
Rahul Garg 832142234b Fix forceinline for non HCC compilation 2019-02-26 07:50:09 +05:30
Maneesh Gupta fdbf84558c Fix signature for unsigned long long variant of atomicExch
This fixes #888

Change-Id: I2b2dc5ed1ff2a26083ad9d102eccac90f67801ae
2019-02-13 09:45:07 +05:30
Maneesh Gupta f1f9cc0d55 Merge pull request #913 from aaronenyeshi/fix-texture-constant-addrspace
Fix texture using constant addrspace 4
2019-02-13 08:59:01 +05:30
Maneesh Gupta 61d9553103 Merge pull request #912 from ROCm-Developer-Tools/remove-cpp-function-templates-for-malloc
Remove C++ function templates for hipMalloc and hipHostMalloc
2019-02-13 08:58:26 +05:30
Aaron Enye Shi eec46be762 Fix texture using constant addrspace 4 2019-02-12 16:56:22 +00:00
Wen-Heng (Jack) Chung f4e1f74e9e 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.
2019-02-11 09:33:15 -06:00
Maneesh Gupta 3112c52742 Merge pull request #907 from yxsamliu/nan
Fix nan() for windows
2019-02-11 11:24:12 +05:30
Yaxun Sam Liu fe5861770e Fix nan() for windows 2019-02-07 17:29:36 -05:00
Yaxun Sam Liu d0fc2d0f99 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.
2019-02-07 11:07:50 -05:00