Intel oneAPI 1.0 Officially Released

[grok]

I believe one of their aims is to make your code debuggable on CPU, for example even if you write your C++ code in a form intended for FPGA.
I believe another of their aims is to encourage you to move much of your code to their library calls which will eventually have optimizations for their different accelerator targets.

also for using the AVX512 feature soup. Tiger Lake laptops, new *-lake Xeons have stuff that would go unused. It's rather out of hand for users.

[jayN]

also for using the AVX512 feature soup. Tiger Lake laptops, new *-lake Xeons have stuff that would go unused. It's rather out of hand for users.

Yes, and soon TGL NUC boxes, I see, and Rocket Lake desktop chips with avx512. Also the Sept 2 TGL benchmarks show they that there is simd advantage in use of the TGL embedded Xe-LP gpu.

But also, from this article, perhaps amd avx2 simd could also benefit, which would be news to me.

[jayN]

I see a news story that oneAPI support for Radeon is being added.

https://arstechnica.com/gadgets/2020/09/intel-heidelberg-university-team-up-to-bring-radeon-gpu-support-to-ai/

[Michael]

I see a news story that oneAPI support for Radeon is being added.

Was already covered yesterday - https://www.phoronix.com/scan.php?pa...MD-Radeon-GPUs