Community
cancel
Showing results for 
Search instead for 
Did you mean: 
YI_W_3
Employee
86 Views

how AVX512 does not show performance advantages

I am working on color space converter applications. i have tried AVX512,  AVX2 and got no significant performance improvement against SSE2.

i upload my test  tool, CPU information, compiler setting and my test result here. 

would you please  share me any comments? 

thanks

 

 

0 Kudos
1 Reply
Yuan_C_Intel
Employee
86 Views

Hi, Yale

I'd like to update the status of this issue as we discussed in emails. This was caused by memory bandwidth limit and latency for AVX512 when running in single thread.

Optimize the example with Openmp and run in parallel will make use of large L2 and L3 caches on SKL, and you will see the performance improvement from AVX512 over AVX2 and SSE.

$ ./VPTestBench

pbSrcY 0x7fd6cd06f040, pbOut1 0x7fd6c7182080 pbOut2 0x7fd6c9126100 pbOut3 0x7fd6cb0ca180

time cpu 965 sse2 95 avx2 89 avx512 82

 

Thanks

Yolanda

Reply