Optimizing GGML/llama.cpp for Gen9 iGPU — Need oneAPI 2022.1 for SYCL Compilation

Migrating to SYCL

One-stop forum for getting assistance migrating your existing code to SYCL

Optimizing GGML/llama.cpp for Gen9 iGPU — Need oneAPI 2022.1 for SYCL Compilation

55 Views

Hi all,

I'm working on SYCL compilation for GGML/llama.cpp on Coffee Lake Gen9 iGPU (i7-8850H + UHD 630). This is our only available test hardware, and we have zero budget for new hardware or support subscriptions.

The blocker:

oneAPI 2024.2+ don't support Gen9 in ocloc (AOT compiler)
Intel's docs indicate Gen9 support ended after 2022.x
Need oneAPI 2022.1 to proceed with SYCL validation

What I need:

Access to oneAPI Base Toolkit 2022.1 download
Or guidance on how to obtain it

Community help:

Has anyone successfully obtained oneAPI 2022.1?
Know the right way to request this from Intel?

Thanks for any guidance!

Link Copied

0 Replies

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.