time-to-botec

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

ndarray.js (2563B)

      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 {NonNegativeInteger} offsetX - starting `x` index
     41 * @param {Float32Array} y - destination array
     42 * @param {integer} strideY - `y` stride length
     43 * @param {NonNegativeInteger} offsetY - starting `y` index
     44 * @returns {Float32Array} `y`
     45 *
     46 * @example
     47 * var Float32Array = require( '@stdlib/array/float32' );
     48 *
     49 * var x = new Float32Array( [ 1.0, 2.0, 3.0, 4.0, 5.0 ] );
     50 * var y = new Float32Array( [ 1.0, 1.0, 1.0, 1.0, 1.0 ] );
     51 * var alpha = 5.0;
     52 *
     53 * saxpy( x.length, alpha, x, 1, 0, y, 1, 0 );
     54 * // y => <Float32Array>[ 6.0, 11.0, 16.0, 21.0, 26.0 ]
     55 */
     56 function saxpy( N, alpha, x, strideX, offsetX, y, strideY, offsetY ) {
     57 	var ix;
     58 	var iy;
     59 	var m;
     60 	var i;
     61 	if ( N <= 0 || alpha === 0.0 ) {
     62 		return y;
     63 	}
     64 	ix = offsetX;
     65 	iy = offsetY;
     66 
     67 	// Use unrolled loops if both strides are equal to `1`...
     68 	if ( strideX === 1 && strideY === 1 ) {
     69 		m = N % M;
     70 
     71 		// If we have a remainder, run a clean-up loop...
     72 		if ( m > 0 ) {
     73 			for ( i = 0; i < m; i++ ) {
     74 				y[ iy ] += float64ToFloat32( alpha * x[ ix ] );
     75 				ix += strideX;
     76 				iy += strideY;
     77 			}
     78 		}
     79 		if ( N < M ) {
     80 			return y;
     81 		}
     82 		for ( i = m; i < N; i += M ) {
     83 			y[ iy ] += float64ToFloat32( alpha * x[ ix ] );
     84 			y[ iy+1 ] += float64ToFloat32( alpha * x[ ix+1 ] );
     85 			y[ iy+2 ] += float64ToFloat32( alpha * x[ ix+2 ] );
     86 			y[ iy+3 ] += float64ToFloat32( alpha * x[ ix+3 ] );
     87 			ix += M;
     88 			iy += M;
     89 		}
     90 		return y;
     91 	}
     92 	for ( i = 0; i < N; i++ ) {
     93 		y[ iy ] += float64ToFloat32( alpha * x[ ix ] );
     94 		ix += strideX;
     95 		iy += strideY;
     96 	}
     97 	return y;
     98 }
     99 
    100 
    101 // EXPORTS //
    102 
    103 module.exports = saxpy;