Re: [ANN] sgminer v5 - optimized X11/X13/NeoScrypt/Lyra2RE/etc. kernel-switch miner

.....This is worth 20KH/s on my 280X......from 343KHs to 363KH/s at 1020MHz clock
.....now somebody needs to find 20KH/s more for me....

change the XORBytesInPlace call from

Code:

XORBytesInPlace(B + bufidx, input, BLAKE2S_OUT_SIZE);

Code:

XORBytesInPlace(B + bufidx, input, bufidx);

and change the function itself to perform some byte alignment checking

Code:

//
// a bit of byte alignment checking goes a long ways...
//
void XORBytesInPlace(void *restrict dst, const void *restrict src, uint mod)
{
switch(mod % 4)
{
case 0:
#pragma unroll 2
for(int i = 0; i < 4; i+=2)
{
((uint2 *)dst)[i] ^= ((uint2 *)src)[i];
((uint2 *)dst)[i+1] ^= ((uint2 *)src)[i+1];
}
break;

case 2:
#pragma unroll 8
for(int i = 0; i < 16; i+=2)
{
((uchar2 *)dst)[i] ^= ((uchar2 *)src)[i];
((uchar2 *)dst)[i+1] ^= ((uchar2 *)src)[i+1];
}
break;

default:
#pragma unroll 8
for(int i = 0; i < 31; i+=4)
{
((uchar *)dst)[i] ^= ((uchar *)src)[i];
((uchar *)dst)[i+1] ^= ((uchar *)src)[i+1];
((uchar *)dst)[i+2] ^= ((uchar *)src)[i+2];
((uchar *)dst)[i+3] ^= ((uchar *)src)[i+3];
}
}
}