- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
My project is to develop an algorithm in c++ and deploy in intel FPGA for high speed performance.I could see that there are two softwares that could be used to achieve this.
1) Intel one API base toolkit and add on to Intel one API base toolkit for FPGA
2) Intel Quartus Prime Pro and Intel HLS compiler
May I know which one of these will be more advantageous to use in my case?
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thank you for posting in the Intel Communities. Since your question is related to FPGA we are moving this topic to the Intel® High Level Design community.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
If you are proficient in C++, then using DPC++/SYCL C++ is probably the best option. Do note that the performance you will achieve has little to do with which of Intel's tools you use since they (OpenCL, C/C++ HLS, DPC++/SYCL C++) all use the same compiler backend. The final performance pretty much completely depends on how you write your code and optimize it to map well to the architecture of an FPGA.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi @student1,
Thank you for posting in Intel community forum and hope all is well.
Please do let us know if there is any further clarification we can help with.
Best Wishes
BB
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@student1 Where do you plan the deployment ?
Do you have a FPGA Develpment Kit, if Yes you can try HLS
If you plan to use Devcould then use OneAPI
Best Wishes
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thanks for the reply.
I am planning to use intel PAC FPGA. May I know which one gives more control to the programmer in terms of 1) code parallelization 2) FPGA development?
Thank you.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi @student1,
As the interest you mention, would recommend OneAPI, as it provide more productivity and efficient for accelerator devices.
Best Wishes
BB
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi @student1,
Greetings, as we do not receive any further clarification on what is provided. Hence thread will now be transitioned to community support for further help on doubts in this thread. For new queries, please feel free to open a new thread and we will be right with you. Pleasure having you here.
Best Wishes
BB
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page