Topic: -- Optimized poclbm kernel! Another 5 Mhash/s -- (Read 2112 times)

if (H.y == 0)
{
                output[OUTPUT_SIZE] = output[nonce.y & OUTPUT_MASK] = nonce.y;
}
else if (H.x == 0)
{
                output[OUTPUT_SIZE] = output[nonce.x & OUTPUT_MASK] = nonce.x;
}

if (H.x == 0)
        {
                output[OUTPUT_SIZE] = output[nonce.x & OUTPUT_MASK] = nonce.x;
}
  else if (H.y == 0)
{
                output[OUTPUT_SIZE] = output[nonce.y & OUTPUT_MASK] = nonce.y;
}

#1:
Before:
H = 0xb0edbdd0 + K[ 0] +  W0; D = 0xa54ff53a + H; H = H + 0x08909ae5U;

After:
H = W0 + 4228417613; D = W0 + 2563236514;

#2:
Before:
D = D1 + (rotr(A, 6) ^ rotr(A, 11) ^ rotr(A, 25)) + Ch(A, B1, C1) + K[ 4] +  0x80000000;

After:
D = D1 + (rotr(A, 6) ^ rotr(A, 11) ^ rotr(A, 25)) + Ch(A, B1, C1);
+ Put Constant K[ 4] + 0x80000000 into python pre-calculation
-> self.state2[3] = np.uint32(self.state2[3]+3109470811);

#3:
Before:
H = ....   K[60] + W12;
H+=0x5be0cd19U;
if (H == 0)

After:
if (H == 325071597)

#4:
Before:
        if (H.x == 0)
        {
                output[OUTPUT_SIZE] = output[nonce.x & OUTPUT_MASK] = nonce.x;
        }
        else if (H.y == 0)
        {
                output[OUTPUT_SIZE] = output[nonce.y & OUTPUT_MASK] = nonce.y;
        }

After:
        if (H.x == 0)
        {
                output[OUTPUT_SIZE] = output[nonce.x & OUTPUT_MASK] = nonce.x;
        }
        if (H.y == 0)
        {
                output[OUTPUT_SIZE] = output[nonce.y & OUTPUT_MASK] = nonce.y;
        }

Why abort checking if we found a result? Unlikely, but we could have found two: This adds almost no overhead.

#5:
Lots of small changes (some of them were optimized by the compiler before, but anyway)