saxpy.js (2456B)
1 /** 2 * @license Apache-2.0 3 * 4 * Copyright (c) 2018 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 = 4; 29 30 31 // MAIN // 32 33 /** 34 * Multiplies a vector `x` by a constant and adds the result to `y`. 35 * 36 * @param {PositiveInteger} N - number of elements 37 * @param {number} alpha - scalar 38 * @param {Float32Array} x - input array 39 * @param {integer} strideX - `x` stride length 40 * @param {Float32Array} y - destination array 41 * @param {integer} strideY - `y` stride length 42 * @returns {Float32Array} `y` 43 * 44 * @example 45 * var Float32Array = require( '@stdlib/array/float32' ); 46 * 47 * var x = new Float32Array( [ 1.0, 2.0, 3.0, 4.0, 5.0 ] ); 48 * var y = new Float32Array( [ 1.0, 1.0, 1.0, 1.0, 1.0 ] ); 49 * var alpha = 5.0; 50 * 51 * saxpy( x.length, alpha, x, 1, y, 1 ); 52 * // y => <Float32Array>[ 6.0, 11.0, 16.0, 21.0, 26.0 ] 53 */ 54 function saxpy( N, alpha, x, strideX, y, strideY ) { 55 var ix; 56 var iy; 57 var m; 58 var i; 59 if ( N <= 0 || alpha === 0.0 ) { 60 return y; 61 } 62 // Use unrolled loops if both strides are equal to `1`... 63 if ( strideX === 1 && strideY === 1 ) { 64 m = N % M; 65 66 // If we have a remainder, run a clean-up loop... 67 if ( m > 0 ) { 68 for ( i = 0; i < m; i++ ) { 69 y[ i ] += float64ToFloat32( alpha * x[ i ] ); 70 } 71 } 72 if ( N < M ) { 73 return y; 74 } 75 for ( i = m; i < N; i += M ) { 76 y[ i ] += float64ToFloat32( alpha * x[ i ] ); 77 y[ i+1 ] += float64ToFloat32( alpha * x[ i+1 ] ); 78 y[ i+2 ] += float64ToFloat32( alpha * x[ i+2 ] ); 79 y[ i+3 ] += float64ToFloat32( alpha * x[ i+3 ] ); 80 } 81 return y; 82 } 83 if ( strideX < 0 ) { 84 ix = (1-N) * strideX; 85 } else { 86 ix = 0; 87 } 88 if ( strideY < 0 ) { 89 iy = (1-N) * strideY; 90 } else { 91 iy = 0; 92 } 93 for ( i = 0; i < N; i++ ) { 94 y[ iy ] += float64ToFloat32( alpha * x[ ix ] ); 95 ix += strideX; 96 iy += strideY; 97 } 98 return y; 99 } 100 101 102 // EXPORTS // 103 104 module.exports = saxpy;