Memory Block calculations

ptrSrc = start of source memory block ptrDst = start of destination memory block Constant=(2^15) For i = 0 to blocksize-1 Float = PeekFloat(ptrSrc) PokeLong(ptrDst,Float*Constant) ptrSrc+(i*4) : ptrDst+(i*4) next

It's not completely clear for me whether those should be constants or variables in your pseudo-code:
ptrSrc
ptrDst
Constant
blocksize

If those are variables, than that's perhaps what he meant:

Code:

mov esi,[ptrSrc]
mov edi,[ptrDst]
mov ecx,[blocksize]
sub esi,ecx
sub edi,ecx
movss xmm1,[constant]
unpckps xmm1,xmm1
movlhps xmm1,xmm1

.MulLoop:
movups xmm0,[esi+ecx]
mulps xmm0,xmm1
movups [edi+ecx],xmm0
add ecx,16
jnc .MulLoop

Note: Both Src and Dst must be a multiple of 16 byte long, and should be aligned on a 16byte boundary to speed it up, so you can use this code:

Code:

mov esi,[ptrSrc]
mov edi,[ptrDst]
mov ecx,[blocksize]
sub esi,ecx
sub edi,ecx
movss xmm1,[constant]
unpckps xmm1,xmm1
movlhps xmm1,xmm1

.MulLoop:
movaps xmm0,[esi+ecx]
mulps xmm0,xmm1
movaps [edi+ecx],xmm0 ; .1)
add ecx,16
jnc .MulLoop

If you know that your floats aren't to be used anytime soon, you can also replace the line 1.) with "movntps [edi+ecx],xmm0".
If that isn't fast enough, you can further unroll the loop and process multiple multiplications at once, in different registers, like this, but data must be 64byte aligned than:

Code:

mov esi,[ptrSrc]
mov edi,[ptrDst]
mov ecx,[blocksize]
sub esi,ecx
sub edi,ecx
movss xmm7,[constant]
unpckps xmm7,xmm7
movlhps xmm7,xmm7

.MulLoop:
movaps xmm0,[esi+ecx]
mulps xmm0,xmm7
movaps xmm1,[esi+ecx+16]
mulps xmm1,xmm7
movaps xmm2,[esi+ecx+32]
mulps xmm2,xmm7
movaps xmm3,[esi+ecx+48]
mulps xmm3,xmm7
movaps [edi+ecx],xmm0 ;1.)
movaps [edi+ecx+16],xmm0 ;1.)
movaps [edi+ecx+32],xmm0 ;1.)
movaps [edi+ecx+48],xmm0 ;1.)
add ecx,64
jnc .MulLoop

It all just depends on how much data you have to process.