hi,
i decided to have a look at SIMD intrinsics instructions but there is a lt of documentation but i cannot find exemple.
So i decide once again to ask question about how to use SIMD with exemple.
i need only 2 exemple. Than i think a should be able to mixte practique et knowledge.
the first axemple is how to do when (*in1) are INT array . the traitment is inside this append in loop (*in1)[x] - (*in1)[y], the intrincis should be VSUB if i read correctky and VABS. But i need the syntaxe code.
ONE:
int diff1 = std::abs((*in1)[x].raw_col_min - (*in1)[y].raw_col_min); int diff2 = std::abs((*in1)[x].min - (*in1)[y].min); int diff3 = std::abs((*in1)[x].raw_col_max - (*in1)[y].raw_col_max); int diff4 = std::abs((*in1)[x].max - (*in1)[y].max); int diff5 = std::abs((*in1)[x].raw_col_min - (*in1)[y].raw_col_max); int diff6 = std::abs((*in1)[x].min - (*in1)[y].max); int diff7 = std::abs((*in1)[x].raw_col_max - (*in1)[y].raw_col_min); int diff8 = std::abs((*in1)[x].max - (*in1)[y].min);
and
TWO :
int diff1 = std::abs((*in1)[x].raw_col_min - (*in1)[y].raw_col_min); int diff2 = std::abs((*in1)[x].min - (*in1)[y].min); int diff3 = std::abs((*in1)[x].raw_col_max - (*in1)[y].raw_col_max); int diff4 = std::abs((*in1)[x].max - (*in1)[y].max);
FOUR:
int diff1 = std::abs((*in1)[x].raw_col_min - (*in1)[y].raw_col_min); int diff2 = std::abs((*in1)[x].min - (*in1)[y].min);
and how to do
if ( (diff1 < 9 && diff2 < 9 && diff3 < 9 && diff4 < 9) || (diff5 < 5 && diff6 < 5 && diff7 < 5 && diff8 < 5) ){
if ( (diff1 < 9 && diff2 < 9 && diff3 < 9 && diff4 < 9) ){
if ( (diff1 < 9 || diff2 < 9) && (diff3 < 9 || diff4 < 9) ){
i think that would be enough. Than i should be able to find my way. Or i will come back to you. ;))
Thanks a lot in advence.
PS: i work with médiatek 9200+ and Mali-G715-Immortalis MC11 r1p2
The main challenge with this code in terms of vectorizability is that you have a dependent chain where one loop iteration can change the value of rupture used by the next loop iteration. This makes vectorizing by packing multiple iterations (structure of arrays style) difficult, and that means you end up trying to vectorize single iterations. This causes quite a lot of scalar code in the loop to handle the addressing and the update of rupture, which erodes the benefit of SIMD quite quickly.
In my vectorized version, the core inner loop is implemented in ~10 neon instructions but the overall inner loop is about 30 instructions because of the loop overhead and scalar update of rupture, so the scalar bits are eroding a lot of possible gains. There is also not that much computation vs the amount of memory accesses being made, so it's quite possible you are ending up load limited.