Using AVX intrinsics instead of SSE does not improve speed -- why?

user1158218 picture user1158218 · Jan 19, 2012 · Viewed 22.9k times · Source

I've been using Intel's SSE intrinsics for quite some time with good performance gains. Hence, I expected the AVX intrinsics to further speed-up my programs. This, unfortunately, was not the case until now. Probably I am doing a stupid mistake, so I would be very grateful if somebody could help me out.

I use Ubuntu 11.10 with g++ 4.6.1. I compiled my program (see below) with

g++ simpleExample.cpp -O3 -march=native -o simpleExample

The test system has a Intel i7-2600 CPU.

Here is the code which exemplifies my problem. On my system, I get the output

98.715 ms, b[42] = 0.900038 // Naive
24.457 ms, b[42] = 0.900038 // SSE
24.646 ms, b[42] = 0.900038 // AVX

Note that the computation sqrt(sqrt(sqrt(x))) was only chosen to ensure that memory bandwith does not limit execution speed; it is just an example.

simpleExample.cpp:

#include <immintrin.h>
#include <iostream>
#include <math.h> 
#include <sys/time.h>

using namespace std;

// -----------------------------------------------------------------------------
// This function returns the current time, expressed as seconds since the Epoch
// -----------------------------------------------------------------------------
double getCurrentTime(){
  struct timeval curr;
  struct timezone tz;
  gettimeofday(&curr, &tz);
  double tmp = static_cast<double>(curr.tv_sec) * static_cast<double>(1000000)
             + static_cast<double>(curr.tv_usec);
  return tmp*1e-6;
}

// -----------------------------------------------------------------------------
// Main routine
// -----------------------------------------------------------------------------
int main() {

  srand48(0);            // seed PRNG
  double e,s;            // timestamp variables
  float *a, *b;          // data pointers
  float *pA,*pB;         // work pointer
  __m128 rA,rB;          // variables for SSE
  __m256 rA_AVX, rB_AVX; // variables for AVX

  // define vector size 
  const int vector_size = 10000000;

  // allocate memory 
  a = (float*) _mm_malloc (vector_size*sizeof(float),32);
  b = (float*) _mm_malloc (vector_size*sizeof(float),32);

  // initialize vectors //
  for(int i=0;i<vector_size;i++) {
    a[i]=fabs(drand48());
    b[i]=0.0f;
  }

// +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
// Naive implementation
// +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
  s = getCurrentTime();
  for (int i=0; i<vector_size; i++){
    b[i] = sqrtf(sqrtf(sqrtf(a[i])));
  }
  e = getCurrentTime();
  cout << (e-s)*1000 << " ms" << ", b[42] = " << b[42] << endl;

// -----------------------------------------------------------------------------
  for(int i=0;i<vector_size;i++) {
    b[i]=0.0f;
  }
// -----------------------------------------------------------------------------

// +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
// SSE2 implementation
// +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
  pA = a; pB = b;

  s = getCurrentTime();
  for (int i=0; i<vector_size; i+=4){
    rA   = _mm_load_ps(pA);
    rB   = _mm_sqrt_ps(_mm_sqrt_ps(_mm_sqrt_ps(rA)));
    _mm_store_ps(pB,rB);
    pA += 4;
    pB += 4;
  }
  e = getCurrentTime();
  cout << (e-s)*1000 << " ms" << ", b[42] = " << b[42] << endl;

// -----------------------------------------------------------------------------
  for(int i=0;i<vector_size;i++) {
    b[i]=0.0f;
  }
// -----------------------------------------------------------------------------

// +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
// AVX implementation
// +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
  pA = a; pB = b;

  s = getCurrentTime();
  for (int i=0; i<vector_size; i+=8){
    rA_AVX   = _mm256_load_ps(pA);
    rB_AVX   = _mm256_sqrt_ps(_mm256_sqrt_ps(_mm256_sqrt_ps(rA_AVX)));
    _mm256_store_ps(pB,rB_AVX);
    pA += 8;
    pB += 8;
  }
  e = getCurrentTime();
  cout << (e-s)*1000 << " ms" << ", b[42] = " << b[42] << endl;

  _mm_free(a);
  _mm_free(b);

  return 0;
}

Any help is appreciated!

Answer

Norbert P. picture Norbert P. · Jan 19, 2012

This is because VSQRTPS (AVX instruction) takes exactly twice as many cycles as SQRTPS (SSE instruction) on a Sandy Bridge processor. See Agner Fog's optimize guide: instruction tables, page 88.

Instructions like square root and division don't benefit from AVX. On the other hand, additions, multiplications, etc., do.