The compilation time is too long for Intel FPGA OpenCL

[myg]

I am trying to compile a HLS project with Intel SDK for OpenCL 20.3 on DE10 PRO. This project used to take 5~6 hours to compile on Intel SDK for OpenCL 19.4 on Arria10, but it has taken more than 17 hours of compilation now. The resource consumption in Linux is shown below.

It seems that the resource used is not that much.

The latest file generated in compilation is shown below.

It seems that routing has been finished successfully. But after top.fit.route.rpt generated, 5 hours has been consumed with no refresh in any file.

I want to know if it is usual to take such a long time in compilation and how can I reduce the compilation time in this flow. 

[BoonBengT_Intel · Accepted solution]

Hi @myg,

Thank you for posting in Intel community forum, hope all is well and apologies for the delayed in response.

Unfortunately the compilation time would depends on multiple factors such as complexity of design or system required which the design are compiled with.

Hence would suggest the following, which is to check on the minimal recommended required specs for the system to compile which hopefully will shorten the compilation time, more details are in the links below:

- https://www.intel.com/content/www/us/en/docs/programmable/683472/24-3-1/disk-space-and-memory-requirements.html

Hope that clarify

Note: Intel OpenCL technology has been deprecated and would advise to move to oneAPI.

Best Wishes

BB

[FDJKL]

The OpenCL compiler isn't very smart and there are many language features it doesn't handle properly. For example, in some versions array initializers (int a[N] = {0}) made it go into an infinite loop. It also seems to have problems synthesizing half precision floats.

[BoonBengT_Intel]

Hi @FDJKL,

Thank you for the interest in the OpenCL compiler, unfortunately the software has been deprecated and would advise to move to oneAPI.

However the floating point error does have different cause, example the dynamic range of the floating point used, the sequence of the operands or memory order of the floating point data. Hence there could be many cause.

Perhaps if you could if you face such challenges, please do post a separate thread and we would try our best to advise on that.

Hope that clarify.

Best Wishes

BB

[BoonBengT_Intel]

Hi @myg,

Good to know that you have found the solution, with no further clarification on this thread, it will be transitioned to community support for further help on doubts in this thread. Please login to ‘ https://supporttickets.intel.com/s/?language=en_US’, view details of the desire request, and post a feed/response within the next 15 days to allow me to continue to support you. After 15 days, this thread will be transitioned to community support. The community users will be able to help you on your follow-up questions.

Thank you for the questions and as always pleasure having you here.

Best Wishes

BB