How to use DPC++ compiler for CPU with JIT support and SIMD code generation ? #6998
lohika-denis-kotov
started this conversation in
General
Replies: 1 comment 9 replies
-
One comment on technical side how it could be done. cgh.parallel_for<class Fillbuffer>(
accessor.get_range(), [=](cl::sycl::id<1> WIid1, cl::sycl::id<2> WIid2, cl::sycl::id<3> WIid3) {
// Fill buffer with indexes
}); |
Beta Was this translation helpful? Give feedback.
9 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I have a question how to use DPC++ compiler for CPU with JIT support and SIMD code generation ?
It is need for some of the projects, for example https://github.com/openvinotoolkit/openvino/tree/master/src/plugins/intel_cpu plugin ...
I have not found the option for DPC++ compiler for such feature.
Closest what I have found is https://www.intel.com/content/www/us/en/develop/documentation/oneapi-dpcpp-cpp-compiler-dev-guide-and-reference/top/compiler-reference/compiler-options/code-generation-options/arch.html#arch, but this option is only available for Windows !!
Have somebody know how to do it ?
Beta Was this translation helpful? Give feedback.
All reactions