All files / sdsdot/lib ndarray.js

57.84% Statements 59/102
100% Branches 1/1
0% Functions 0/1
57.84% Lines 59/102

Press n or j to go to the next uncovered block, b, p or k for the previous block.

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 1031x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x 1x                                                                                       1x 1x 1x 1x 1x  
/**
* @license Apache-2.0
*
* Copyright (c) 2023 The Stdlib Authors.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
*    http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
 
'use strict';
 
// MODULES //
 
var f32 = require( '@stdlib/number/float64/base/to-float32' );
 
 
// VARIABLES //
 
var M = 5;
 
 
// MAIN //
 
/**
* Computes the dot product of two single-precision floating-point vectors with extended accumulation.
*
* @param {integer} N - number of indexed elements
* @param {number} scalar - scalar constant to add to dot product
* @param {Float32Array} x - first input array
* @param {integer} strideX - `x` stride length
* @param {NonNegativeInteger} offsetX - starting index for `x`
* @param {Float32Array} y - second input array
* @param {integer} strideY - `y` stride length
* @param {NonNegativeInteger} offsetY - starting index for `y`
* @returns {number} dot product
*
* @example
* var Float32Array = require( '@stdlib/array/float32' );
*
* var x = new Float32Array( [ 4.0, 2.0, -3.0, 5.0, -1.0 ] );
* var y = new Float32Array( [ 2.0, 6.0, -1.0, -4.0, 8.0 ] );
*
* var z = sdsdot( x.length, 0.0, x, 1, 0, y, 1, 0 );
* // returns -5.0
*/
function sdsdot( N, scalar, x, strideX, offsetX, y, strideY, offsetY ) {
	var dot;
	var ix;
	var iy;
	var m;
	var i;

	dot = scalar;
	if ( N <= 0 ) {
		return f32( dot );
	}
	ix = offsetX;
	iy = offsetY;

	// Use unrolled loops if both strides are equal to `1`...
	if ( strideX === 1 && strideY === 1 ) {
		m = N % M;

		// If we have a remainder, run a clean-up loop...
		if ( m > 0 ) {
			for ( i = 0; i < m; i++ ) {
				dot += x[ ix ] * y[ iy ];
				ix += 1;
				iy += 1;
			}
		}
		if ( N < M ) {
			return f32( dot );
		}
		for ( i = m; i < N; i += M ) {
			dot += ( x[ix]*y[iy] ) + ( x[ix+1]*y[iy+1] ) + ( x[ix+2]*y[iy+2] ) + ( x[ix+3]*y[iy+3] ) + ( x[ix+4]*y[iy+4] ); // eslint-disable-line max-len
			ix += M;
			iy += M;
		}
		return f32( dot );
	}
	for ( i = 0; i < N; i++ ) {
		dot += x[ ix ] * y[ iy ];
		ix += strideX;
		iy += strideY;
	}
	return f32( dot );
}
 
 
// EXPORTS //
 
module.exports = sdsdot;