time-to-botec

Benchmark sampling in different programming languages
Log | Files | Refs | README

daxpy.js (2243B)


      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 // VARIABLES //
     22 
     23 var M = 4;
     24 
     25 
     26 // MAIN //
     27 
     28 /**
     29 * Multiplies a vector `x` by a constant and adds the result to `y`.
     30 *
     31 * @param {PositiveInteger} N - number of elements
     32 * @param {number} alpha - scalar
     33 * @param {Float64Array} x - input array
     34 * @param {integer} strideX - `x` stride length
     35 * @param {Float64Array} y - destination array
     36 * @param {integer} strideY - `y` stride length
     37 * @returns {Float64Array} `y`
     38 *
     39 * @example
     40 * var Float64Array = require( '@stdlib/array/float64' );
     41 *
     42 * var x = new Float64Array( [ 1.0, 2.0, 3.0, 4.0, 5.0 ] );
     43 * var y = new Float64Array( [ 1.0, 1.0, 1.0, 1.0, 1.0 ] );
     44 * var alpha = 5.0;
     45 *
     46 * daxpy( x.length, alpha, x, 1, y, 1 );
     47 * // y => <Float64Array>[ 6.0, 11.0, 16.0, 21.0, 26.0 ]
     48 */
     49 function daxpy( N, alpha, x, strideX, y, strideY ) {
     50 	var ix;
     51 	var iy;
     52 	var m;
     53 	var i;
     54 	if ( N <= 0 || alpha === 0.0 ) {
     55 		return y;
     56 	}
     57 	// Use unrolled loops if both strides are equal to `1`...
     58 	if ( strideX === 1 && strideY === 1 ) {
     59 		m = N % M;
     60 
     61 		// If we have a remainder, run a clean-up loop...
     62 		if ( m > 0 ) {
     63 			for ( i = 0; i < m; i++ ) {
     64 				y[ i ] += alpha * x[ i ];
     65 			}
     66 		}
     67 		if ( N < M ) {
     68 			return y;
     69 		}
     70 		for ( i = m; i < N; i += M ) {
     71 			y[ i ] += alpha * x[ i ];
     72 			y[ i+1 ] += alpha * x[ i+1 ];
     73 			y[ i+2 ] += alpha * x[ i+2 ];
     74 			y[ i+3 ] += alpha * x[ i+3 ];
     75 		}
     76 		return y;
     77 	}
     78 	if ( strideX < 0 ) {
     79 		ix = (1-N) * strideX;
     80 	} else {
     81 		ix = 0;
     82 	}
     83 	if ( strideY < 0 ) {
     84 		iy = (1-N) * strideY;
     85 	} else {
     86 		iy = 0;
     87 	}
     88 	for ( i = 0; i < N; i++ ) {
     89 		y[ iy ] += alpha * x[ ix ];
     90 		ix += strideX;
     91 		iy += strideY;
     92 	}
     93 	return y;
     94 }
     95 
     96 
     97 // EXPORTS //
     98 
     99 module.exports = daxpy;