Community
cancel
Showing results for 
Search instead for 
Did you mean: 
KTeo1
Novice
791 Views

Reproducing the same results in Quartus

We ran a typical hello world example with aoc. By observing the commands in quartus_sh_compile.log, e.g. quartus_sh xxxx, we try to reproduce the same results by doing the same in Quartus. However, we are unable to do so. We compare the log to see what are the differences.

 

The main and earliest difference was this below.

pll_difference.png

The log on the right is the original. The PLL clock ratio parameters are different when we rerun it. (See the one on the left)

 

Is there something we missed?

 

thanks

0 Kudos
5 Replies
Rahul_S_Intel1
Employee
129 Views

Hi, May I know any PLL you are using or any clocking circuitry you are using in code. Regards, RS
KTeo1
Novice
129 Views

Hi, we just used a hello world downloaded from the Intel website. The code is as attached.

 

 

Dr_FPGA
Novice
129 Views

Intel OpenCL compilation flow includes several attempts to improve kernel clock frequency in post_flow.tcl calling the PLL frequency adjustment script: source "$sdk_root/ip/board/bsp/adjust_plls.tcl". Running this script may result in different PLL settings depending on primarily utilizaiton of FPGA and speedgrade. If nothing has changed in your compiles including your CPU, this is indeed strange result. But in general, you may have different number of workgroups or compute units in FPGA. As the utilization of FPGA grows the maximum frequency tends to go down which may explain the different multiply and divide ratio. If your applicaition requires a fixed repeatable frequency it is quite easy to change the script to your local copy which does only one attempt. BTW this will save you some compile time too.

KTeo1
Novice
129 Views

Thanks "Doc"! That explains a lot. Let me go check this out and report back!

KTeo1
Novice
129 Views

Hi, we found 1 occurence of the adjust_pll.tcl in the the post_flow_pr.tcl.

 

source $::env(INTELFPGAOCLSDKROOT)/ip/board/bsp/adjust_plls_a10.tcl

 

But after commenting it out, it seems like the pll changes are made much earlier (before even running this script). However, in the pre_flow tcl, we can't find any mention of adjust_plls tcl anywhere.

Any idea how it is linked?