sambean ·
How about having the xor command activated (^) for the the code and asm modules? This would also give us a logical 'not' command (y = x^x), two birds with one stone (edit- no it wont!! but there's the andnps command which will)...
Sam
From the original SynthMaker forum (2004–2014), with its members’ names and dates.
sambean ·
How about having the xor command activated (^) for the the code and asm modules? This would also give us a logical 'not' command (y = x^x), two birds with one stone (edit- no it wont!! but there's the andnps command which will)...
Sam
infuzion ·
the ASM command in question is funny enough, xorps http://www.cpuid.com/search.php3?id=15
There are also a few other ASM requests by me & others: shufps //Shuffle Single-FP movhlps //Move High Single-FP to Low {faster AMD vs Intel} movhps //Move High Packed Single-FP movlps //Move Low Packed Single-FP
& a few other 64bit commands + SSE2=64bit audio, SSE3=faster FFT... please
cheers
infuzion ·
le bumpe Four by Four Matrix Mixer
infuzion ·
Not to belabor a point, but I was just reading in AMD's optimizing doc that it is faster to flip a sign bit & clear a register using XOR.
Also, in addition to the opcodes mentioned in my post above, the following are needed for the 4x4 matrix multiply please: imul neg movntps unpcklps
cheers
Wrote something here? To have a post removed or your name hidden, write to [email protected].