PGI User Forum
 SearchSearch   MemberlistMemberlist     RegisterRegister   ProfileProfile    Log inLog in 

CUDA-x86.

Performance problem with SSE intrinsics

 
Post new topic   Reply to topic    PGI User Forum Forum Index -> Performance and Benchmarking
View previous topic :: View next topic  
Author Message
MattD



Joined: 20 Aug 2007
Posts: 6
Location: Greenville, TX
PostPosted: Mon Aug 27, 2007 8:52 am    Post subject: Performance problem with SSE intrinsics Reply with quote
I'm running some simple code using SSE intrinsics to get the hang of the things. And I'm having some performance problems. For a simple calculation: \vector{r} = \sqrt( \vector{x}.^2 + \vector{y}.^2 ) the version with SSE intrinsics is actually running ~2x _slower_.

I'm pretty sure it's not a simple coding issue (althought it may be a simple versioning issue?). Running the same source with gcc, the SSE version runs ~40% faster (about what I was expecting).

Is there something different that I need to do with pgcc to get the expected behavior? Any thoughts appreciated.

FYI, I'm using: pgcc 7.0-7 64-bit target on x86-64 Linux

Code snippets, compilation commands, and outputs below:

Code:

[delaquil@head Cforpost]$ tail -14 Cmain.c

 start = clock();
  ComputeArrayC( pArray1, pArray2, pResult, nSize );
 end = clock();
 cpu_time = ((double) (end - start)) / CLOCKS_PER_SEC;
 printf ("Regular C elapsed time: %f seconds.\n", cpu_time );

 start = clock();
  ComputeArrayCSSE( pArray1SSE, pArray2SSE, pResultSSE, nSize );
 end = clock();
 cpu_time = ((double) (end - start)) / CLOCKS_PER_SEC;
 printf ("C with SSE elapsed time: %f seconds.\n", cpu_time );

}
[delaquil@head Cforpost]$ /bin/cat Ctest.c
#include <math.h>
void ComputeArrayC(
        float* pArray1,
        float* pArray2,
        float* pResult,
        int nSize)
{
 int i;

 float* pSource1 = pArray1;
 float* pSource2 = pArray2;
 float* pDest = pResult;

 for ( i = 0; i < nSize; i++ )
 {
  *pDest = (float)sqrt((*pSource1) * (*pSource1) +
                       (*pSource2) * (*pSource2)) + 0.5f;

  pSource1++;
  pSource2++;
  pDest++;
 }
}
[delaquil@head Cforpost]$ /bin/cat CtestSSE.c
#include<xmmintrin.h>
void ComputeArrayCSSE(
        float* pArray1,
        float* pArray2,
        float* pResult,
        int nSize)
{

 int i;
 int nLoop = nSize / 4;

 __m128 m1, m2, m3, m4;

 __m128* pSrc1 = (__m128*) pArray1;
 __m128* pSrc2 = (__m128*) pArray2;
 __m128* pDest = (__m128*) pResult;

 __m128 m0_5 = _mm_set_ps1(0.5f);

 for ( i = 0; i < nLoop; i++ )
 {
  m1 = _mm_mul_ps(*pSrc1, *pSrc1);
  m2 = _mm_mul_ps(*pSrc2, *pSrc2);
  m3 = _mm_add_ps(m1, m2);
  m4 = _mm_sqrt_ps(m3);
  *pDest = _mm_add_ps(m4, m0_5);

  pSrc1++;
  pSrc2++;
  pDest++;
 }
}
[delaquil@head Cforpost]$ pgcc -O4 -Mvect=sse Cmain.c Ctest.c CtestSSE.c aligned_malloc.c
Cmain.c:
Ctest.c:
CtestSSE.c:
aligned_malloc.c:
[delaquil@head Cforpost]$ ./a.out
Regular C elapsed time: 0.140000 seconds.
C with SSE elapsed time: 0.310000 seconds.
[delaquil@head Cforpost]$ gcc -lm -O4 -msse -msse2 Cmain.c Ctest.c CtestSSE.c aligned_malloc.c
[delaquil@head Cforpost]$ ./a.out
Regular C elapsed time: 0.100000 seconds.
C with SSE elapsed time: 0.060000 seconds.
[delaquil@head Cforpost]$
[/code]
Back to top
View user's profile
mkcolg



Joined: 30 Jun 2004
Posts: 4996
Location: The Portland Group Inc.
PostPosted: Tue Aug 28, 2007 11:33 am    Post subject: Reply with quote
Hi Matt,

I passed this on to the engineers who develop our intrinsic libraries since they are very interest in any performance issues. However, when they tried some arbitrary size arrays with random data, they did not see the performance issue. Would it be possible to obtain the full source? If large, please send to trs@pgroup.com and have customer service forward it to me.

Thanks,
Mat
Back to top
View user's profile
mkcolg



Joined: 30 Jun 2004
Posts: 4996
Location: The Portland Group Inc.
PostPosted: Tue Aug 28, 2007 2:59 pm    Post subject: Reply with quote
Hi Matt,

I forwarded your code to engineering and they have been able to reproduce the performance problem. I have created a technical problem report, TPR#4285, and hopefully will be able to address the issue shortly.

Thank you for bringing this to our attention!
Mat
Back to top
View user's profile
Display posts from previous:   
Post new topic   Reply to topic    PGI User Forum Forum Index -> Performance and Benchmarking All times are GMT - 7 Hours
Page 1 of 1

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum


Powered by phpBB © 2001, 2002 phpBB Group