Recently, I find the ippsMean_32fc function is not accurate enough with ippAlgHintAccurate or ippAlgHintNone mode on AVX support machine. And I have verified that it can work well on none-AVX machine or ippAlgHintFast mode on AVX machine. So I just want to know if this is a bug of IPP library. If it is, when it can be fixed? Because it will affect the stability of our product on AVX platform.
My test code is:
#include "ipp.h"
#include <stdlib.h>
#include <stdio.h>
int main(int argc, char *argv[])
{
const int dataLen = 1000;
float *data = new float[dataLen*2];
for(int i = 0; i<dataLen*2; ++i) data = (float)rand() / RAND_MAX;
float resAcc[2] = {0.0f, 0.0f};
float resFast[2] = {0.0f, 0.0f};
float resNone[2] = {0.0f, 0.0f};
Ipp32fc *pData = (Ipp32fc*)data;
Ipp32fc *pResAcc = (Ipp32fc*)resAcc;
Ipp32fc *pResFast = (Ipp32fc*)resFast;
Ipp32fc *pResNone = (Ipp32fc*)resNone;
ippsMean_32fc(pData, dataLen, pResAcc, ippAlgHintAccurate);
ippsMean_32fc(pData, dataLen, pResFast, ippAlgHintFast);
ippsMean_32fc(pData, dataLen, pResNone, ippAlgHintNone);
printf("Accurate: %f, %f\n", ((float*)pResAcc)[0], ((float*)pResAcc)[1]);
printf("Fast: %f, %f\n", ((float*)pResFast)[0], ((float*)pResFast)[1]);
printf("None: %f, %f\n", ((float*)pResNone)[0], ((float*)pResNone)[1]);
return 0;
}
AVX platform output:
Accurate: 0.497964, 0.496415
Fast: 0.496592, 0.496415
None: 0.497964, 0.496415
non-AVX platform output:
Accurate: 0.496592, 0.496415
Fast: 0.496592, 0.496415
None: 0.496592, 0.496415
My IPP version should be v7.0.x which is contained in Intel® Parallel Composer 2011 Update 9
