On 01/25/2018 15:37 UTC, Wuweijia wrote:
Function1:
bool CDynamicScheduling::GetProcLoop(
int& nBegin,
int& nEndPlusOne)
{
int curr = __sync_fetch_and_add(&m_nCurrent, m_nStep);
How large is 'm_nStep'? [Are you sure?]
The overhead expense of switching threads in valgrind would be reduced
by making m_nStep as large as possible. It looks like the code
in Function2 would produce the same values regardless.
if (curr > m_nEnd)
{
return false;
}
nBegin = curr;
int limit = m_nEnd + 1;
Local variable 'limit' is unused. By itself this is unimportant,
but it might be a clue to something that is not shown here.
nEndPlusOne = curr + m_nStep;
return true;
}
Function2:
....
int beginY, endY;
while (pDS->GetProcLoop(beginY, endY)){
for (y = beginY; y < endY; y++){
for(x = 0; x < dstWDiv2-7; x+=8){
vtmp0 = vld2q_u16(&pSrc[(y<<1)*srcStride+(x<<1)]);
vtmp1 = vld2q_u16(&pSrc[((y<<1)+1)*srcStride+(x<<1)]);
I hope the actual source contains a comment such as:
Compute pDst[] as the rounded average of non-overlapping 2x2 blocks of
pixels in pSrc[].
vst1q_u16(&pDst[y*dstStride+x], (vtmp0.val[0] + vtmp0.val[1] + vtmp1.val[0]
+ vtmp1.val[1] + vdupq_n_u16(2)) >> vdupq_n_u16(2));
}
for(; x < dstWDiv2; x++){
pDst[y*dstStride+x] = (pSrc[(y<<1)*srcStride+(x<<1)] + pSrc[(y<<1)*srcStride+(x<<1)+1] +
pSrc[((y<<1)+1)*srcStride+(x<<1)] + pSrc[((y<<1)+1)*srcStride+((x<<1)+1)] + 2) >> 2;
}
}
}
return;
}
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
Valgrind-users mailing list
Valgrind-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/valgrind-users
