SIMD for float threshold operation

Question

I would like to make some vector computation faster, and I believe that SIMD instructions for float comparison and manipulation could help, here is the operation:

Answer 1

You can use GCC's and Clang's vector extensions to implement a ternary select function (see https://stackoverflow.com/a/48538557/2542702).

#include 
#include 

#if defined(__clang__)
typedef  double double4 __attribute__ ((ext_vector_type(4)));
typedef int64_t   long4 __attribute__ ((ext_vector_type(4)));
#else
typedef  double double4 __attribute__ ((vector_size (sizeof(double)*4)));
typedef int64_t   long4 __attribute__ ((vector_size (sizeof(int64_t)*4)));
#endif

double4 select(long4 s, double4 a, double4 b) {
  double4 c;
  #if defined(__GNUC__) && !defined(__INTEL_COMPILER) && !defined(__clang__)
  c = s ? a : b;
  #else
  for(int i=0; i<4; i++) c[i] = s[i] ? a[i] : b[i];
  #endif
  return c;
}

void func(double* left, double* right, double* res, size_t size, double th, double drop) {
  size_t i;
  for (i = 0; i<(size&-4); i+=4) {
    double4 leftv = *(double4*)&left[i];
    double4 rightv = *(double4*)&right[i];
    *(double4*)&res[i] = select(rightv >= th, leftv, leftv - drop);
  }
  for(;i= th ? left[i] : (left[i] - drop);
}

https://godbolt.org/z/h4OKMl