sdsdot.js (2524B)
1 /** 2 * @license Apache-2.0 3 * 4 * Copyright (c) 2020 The Stdlib Authors. 5 * 6 * Licensed under the Apache License, Version 2.0 (the "License"); 7 * you may not use this file except in compliance with the License. 8 * You may obtain a copy of the License at 9 * 10 * http://www.apache.org/licenses/LICENSE-2.0 11 * 12 * Unless required by applicable law or agreed to in writing, software 13 * distributed under the License is distributed on an "AS IS" BASIS, 14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 15 * See the License for the specific language governing permissions and 16 * limitations under the License. 17 */ 18 19 'use strict'; 20 21 // MODULES // 22 23 var float64ToFloat32 = require( '@stdlib/number/float64/base/to-float32' ); 24 25 26 // VARIABLES // 27 28 var M = 5; 29 30 31 // MAIN // 32 33 /** 34 * Computes the dot product of two single-precision floating-point vectors with extended accumulation. 35 * 36 * @param {PositiveInteger} N - number of values over which to compute the dot product 37 * @param {number} scalar - scalar constant to add to dot product 38 * @param {Float32Array} x - first input array 39 * @param {integer} strideX - `x` stride length 40 * @param {Float32Array} y - second input array 41 * @param {integer} strideY - `y` stride length 42 * @returns {number} dot product of `x` and `y` 43 * 44 * @example 45 * var Float32Array = require( '@stdlib/array/float32' ); 46 * 47 * var x = new Float32Array( [ 4.0, 2.0, -3.0, 5.0, -1.0 ] ); 48 * var y = new Float32Array( [ 2.0, 6.0, -1.0, -4.0, 8.0 ] ); 49 * 50 * var z = sdsdot( x.length, 0.0, x, 1, y, 1 ); 51 * // returns -5.0 52 */ 53 function sdsdot( N, scalar, x, strideX, y, strideY ) { 54 var dot; 55 var ix; 56 var iy; 57 var m; 58 var i; 59 60 dot = scalar; 61 if ( N <= 0 ) { 62 return float64ToFloat32( dot ); 63 } 64 // Use unrolled loops if both strides are equal to `1`... 65 if ( strideX === 1 && strideY === 1 ) { 66 m = N % M; 67 68 // If we have a remainder, run a clean-up loop... 69 if ( m > 0 ) { 70 for ( i = 0; i < m; i++ ) { 71 dot += x[ i ] * y[ i ]; 72 } 73 } 74 if ( N < M ) { 75 return float64ToFloat32( dot ); 76 } 77 for ( i = m; i < N; i += M ) { 78 dot += ( x[i]*y[i] ) + ( x[i+1]*y[i+1] ) + ( x[i+2]*y[i+2] ) + ( x[i+3]*y[i+3] ) + ( x[i+4]*y[i+4] ); // eslint-disable-line max-len 79 } 80 return float64ToFloat32( dot ); 81 } 82 if ( strideX < 0 ) { 83 ix = ( 1-N ) * strideX; 84 } else { 85 ix = 0; 86 } 87 if ( strideY < 0 ) { 88 iy = ( 1-N ) * strideY; 89 } else { 90 iy = 0; 91 } 92 for ( i = 0; i < N; i++ ) { 93 dot += x[ ix ] * y[ iy ]; 94 ix += strideX; 95 iy += strideY; 96 } 97 return float64ToFloat32( dot ); 98 } 99 100 101 // EXPORTS // 102 103 module.exports = sdsdot;