By default hipcc passes -mllvm options to let HIP-Clang inline all device functions.
--hipcc-func-supp enables function support and disables inline all.
--hipcc-no-func-supp disable function support and enables inline all.
This is a temporary solution to match HCC behavior for performance.
This option is mainly for debugging purpose.
Change-Id: I0c44ac1812bb3cea5c3e5b6e14ebaa45919236f6
nvcc treats .c program as C program and .cpp program as C++ program.
Currently hipcc treats .c and .cpp programs as HIP programs.
It is desirable to let hipcc behave like nvcc.
Currently it is not feasible to let hipcc treat .cpp programs as C++ program
since there are too many HIP applications use .cpp as extension for HIP programs.
However we should be able let hipcc treat .c program C program since there
are few applications use .c as extensioin for HIP programs.
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.
Fixes SWDEV-207362,
The output file name should not contribute to picking up the right flags for the compiler. This fix solves issues when the output has conflicting extensions which confuses hipcc to treat them as the source files and add the required flags for them.
PS: Output file refers to the file followed by -o
Example: hipcc test.o -o test.hip will add the flags for .hip compilation ignoring the fact that it is an output file
Fixes SWDEV-226025,
Right now -x c++ can come before libhip_hcc.so which forces the compiler to treat libhip_hcc.so as a text file and generates a lot of gibberish unicode. This PR changes the order of flags ensuring that -x c++ and similar flags come after libhip_hcc.so
Hopefully, this will not have any negative side effect.
Currently there is a clang bug on Windows causing duplicate -mllvm options in clang -cc1.
Tempoarily disable -mllvm options for HIP-Clang on Windows until the bug is fixed.
Change-Id: I3a4393ba7745989398dc6c6001722837dad18704
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.
This is a quick workaround to match HCC behavior for performance since inlining usually
results in more optimization opportunities therefore better performance.
We will fine tuning inline threashold later.
Some PyTorch unit tests have regression. Disabling cov3 to allow more
time to debug and unblock PyTorch
Change-Id: Iba7f425ef3499c20c42ec45d9152b5d27ce97d03
- The known target checking should skip `gfx000` as well as it won't be
used in real compilation command formation. The avoid generating
annoying warning on `gfx000`.
* Fix hipcc warning related to hipVersion
* Rename hipVersion.h to hip_version.h
* Remove HIP_VERSION splitting
* Update .gitignore
- Ignore generated include/hip/hip_version.h
- Removed some stale entries
- Added executables from samples/1_Utils/*/ for consistency with bin/ entries.
HIP_VERSION_MAJOR, HIP_VERSION_MINOR, HIP_VERSION_PATCH and HIP_VERSION pre-processor macros are now defined in hipVersion.h instead of being set by hipcc.
+ Both Driver API and RT API are supported and synced with each other
+ Update *.md docs and hipify-perl accordingly
+ Add new conversion type "virtual_memory", introduced in Dirver API
+ Update *.md docs and hipify-perl accordingly
[Reason]
Starting with CUDA 10.1 all error codes are merged between Driver and RT APIs
[ToDo]
Do the same merge in HIP API as there is no need in distinguishing return codes by API
+ Add one matcher (will be more)
+ Update Maps and Statistics
+ Add cub_01.cu unit test
+ Update lit harness to support standalone CUB
+ Update README.md
+ Update hipify-perl (only CUB header is supported for now)
[IMPORTANT]
clang (and hipify-clang) works correctly only with official NVLabs version on GitHub.
Compilation of CUB from official CUDA release has conflicts with THRUST.
Thus, to compile CUB sources, option "-I" should be specified to the cloned CUB from NVLAB on GitHub.
Yaxun (Sam) Liu
Evgeny Mankov
Reshabh Sharma
Sameer Sahasrabuddhe
Rahul Garg
Maneesh Gupta
Sarbojit2019
Siu Chi Chan
Aryan Salmanpour
mhbliao
Michael LIAO
kpyzhov
paulfreddy
srinivamd