The static members __HIP_Coordinates::x, ::y and ::z must be defined
outside the class. Otherwise, linker throws `undefined reference error`
when these definitions are needed in the HIP application.
Change-Id: Iabc09744b478c22e4b13cf9824877ec9cfdd4f7a
This makes hipLaunchKernelGGL take a variable argument list, that will be
expanded before being fed to hipLaunchKernelGGLInternal.
This is different from 961717879d.
We try to accomodate the case when a kernel template has multiple
type parameters.
Change-Id: I87577d402c92b0f3b51e298f8293f4065e1f6de8
- HIP-Clang follows the standard assert definition by providing
`__assert_fail`. But, `assert` macro is added as an HCC-specific
workaround due to the missing implementation. Only enable that on the
HCC compilation to avoid unexpected behaviors on HIP-Clang
compilation.
Change-Id: I1c9a707baff9b85c30faef58c52ebfe07e3fc3fc
This makes hipLaunchKernelGGL take a variable argument list, that will be
expanded before being fed to hipLaunchKernelGGLInternal.
Change-Id: Id76e2bf91acd5d68f56a24fc39f219f2eeb06d33
Currently std::complex and some other std functions require uses to
include hip_runtime.h before any other headers to work, which is not
reliable.
changes are made in clang to fix this issue:
https://reviews.llvm.org/D81176
which requires hipcc and HIP headers to make corresponding changes.
This patch will make sure the clang change will not break
HIP/ROCclr during this transition.
After the transition is done, we can remove explicitly setting
include path for HIP-Clang and HIP header in hipcc and hip config
cmake files and rely on clang driver to set it automatically.
Change-Id: I5d226861c2560ffa6c5ab17343a43cc378048061
* Disable device side malloc
Currently device side malloc is not working and takes excessive
device memory.
Disable it for now until a working malloc is implemented.
Change-Id: I1ad908c1c53a83752383b4be96688a848642c699
HIP-Clang cuda_wrapper headers require clang include path before standard C++ include path.
However libc++ include path requires to be before clang include path.
To workaround this, we pass -isystem with the parent directory of clang include
path instead of the clang include path itself.
There are now two implementations of printf in HIP:
1. The implemenation for HCC is controlled by the HC_FEATURE_PRINTF
macro, and it works only with the HCC compiler used in combination
with the HCC runtime.
2. The implementation for hip-clang requires the VDI runtime, and is
always enabled with that combination.
Fixes SWDEV-218626 and SWDEV-218629
Changes:
- Revert "`static inline` in a header, just like excess sugar in a diet, causes bloat (#1692)"
This reverts commit be70b9f7e7.
- Revert "Fix rocFFT build failure (#1777)"
This reverts commit 753277422a.
* [hip] implement the hipExtLaunchMultiKernelMultiDevice API
* add a guard to check the HCC version for acquire_locked_hsa_queue() API which was introdued in HCC for ROCm 2.5
* modified code based on the requested changes
* changes to lock all streams before launching kernels for each device and unlock them after the dispatches
* check each stream to be valid before starting to lock all the streams
- Separate the definition of `__HCC_OR_HIP_CLANG__`, `__HCC_ONLY__`, and
`__HIP_CLANG_ONLY__` into hip_common.h so that it could be included in
hip_fp16.h, which may be included separately in app.
Move remaining function definitions from device_util.cpp to hip_runtime.h header. We can now remove the static library completely as device_util.cpp was the last file part of target hip::hip_device .
Do not decay function pointer type of the kernel argument passed to hipLaunchKernelGGL
and hipLaunchKernel, otherwise some type information is lost which may cause
type inference failure for the template.
This issue caused compilation error of FeatureLPPooling in Caffe2/PyTorch and this patch
fixes that.
Aaron En Ye Shi
Julia Jiang
Vladislav Sytchenko
mshivama
Rahul Garg
Jatin Chaudhary
Ronak Chauhan
Daniil Fukalov
Michael LIAO
Yaxun (Sam) Liu
Maneesh Gupta
Sameer Sahasrabuddhe
Sameer Sahasrabuddhe
Alex Voicu
Michael LIAO
Sarbojit2019
Jatin Chaudhary
Aryan Salmanpour
Michael Liao