How to optimize the kernel, FPGA takes much more time than CPU

Intel® Quartus® Prime Software

Intel® Quartus® Prime Design Software, Design Entry, Synthesis, Simulation, Verification, Timing Analysis, System Design (Platform Designer, formerly Qsys)

How to optimize the kernel, FPGA takes much more time than CPU

1,281 Views

The algorithm implementated by FPGA take much more time than the one by CPU.I have no idea how to optimized the kernel according to the report.In the kernel,main work is the calcultion of floating point multiplication and power.How to improve the performance of FPGA?Thanks a lot.

The structure transfers data between host and FPGA is :

typedef struct

{

double S;

double X;

double u;

double e_rt_p;

double e_rt_q;

int CP;

}struct_A

and the screen displays:

............

MMD INFO : Link currently operating at 8 GT/s.

MMD INFO : Link operating at Gen 3 with 8 lanes.

MMD INFO : Expected peak bandwidth = 8000 MB/s

............

Report is:

https://alteraforum.com/forum/attachment.php?attachmentid=14561&stc=1

(Virus scan in progress ...)

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.