This is how I use ARM NEON intrinsics to speed up division and square root operations...

#include "arm_neon.h"

// approximative quadword float inverse square root
static inline float32x4_t invsqrtv(float32x4_t x) {
    float32x4_t sqrt_reciprocal = vrsqrteq_f32(x);
    
    return vrsqrtsq_f32(x * sqrt_reciprocal, sqrt_reciprocal) * sqrt_reciprocal;
}
        
// approximative quadword float square root
static inline float32x4_t sqrtv(float32x4_t x) {
    return x * invsqrtv(x);
}
            
// approximative quadword float inverse
static inline float32x4_t invv(float32x4_t x) {
    float32x4_t reciprocal = vrecpeq_f32(x);
    reciprocal = vrecpsq_f32(x, reciprocal) * reciprocal;
                                
    return reciprocal;
}
                                    
// approximative quadword float division
static inline float32x4_t divv(float32x4_t x, float32x4_t y) {
    float32x4_t reciprocal = vrecpeq_f32(y);
    reciprocal = vrecpsq_f32(y, reciprocal) * reciprocal;
                                                
    return x * invv(y);
}

// accumulate four quadword floats
static inline float accumv(float32x4_t x) {
    static const float32x2_t f0 = vdup_n_f32(0.0f);
    return vget_lane_f32(vpadd_f32(f0, vget_high_f32(x) + vget_low_f32(x)), 1);
}

posted at: 10:39 | path: /programming | permanent link