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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 3x 28x 28x 28x 28x 28x 28x 28x 4x 4x 24x 28x 2x 2x 22x 28x 2x 2x 20x 20x 20x 20x 28x 12x 12x 12x 12x 4x 10x 10x 10x 10x 4x 12x 4x 4x 12x 140x 140x 140x 140x 140x 140x 140x 140x 8x 8x 28x 24x 24x 24x 24x 8x 28x 3x 3x 3x 3x 3x | /**
* @license Apache-2.0
*
* Copyright (c) 2026 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 saxpy = require( '@stdlib/blas/base/saxpy' ).ndarray;
var sscal = require( '@stdlib/blas/base/sscal' ).ndarray;
var f32 = require( '@stdlib/number/float64/base/to-float32' );
// VARIABLES //
var M = 5;
// MAIN //
/**
* Multiplies a single-precision floating-point strided array `x` by a constant and adds the result to a single-precision floating-point strided array `y` multiplied by a constant.
*
* @param {PositiveInteger} N - number of indexed elements
* @param {number} alpha - first scalar constant
* @param {Float32Array} x - input array
* @param {integer} strideX - `x` stride length
* @param {NonNegativeInteger} offsetX - starting `x` index
* @param {number} beta - second scalar constant
* @param {Float32Array} y - output array
* @param {integer} strideY - `y` stride length
* @param {NonNegativeInteger} offsetY - starting `y` index
* @returns {Float32Array} output array
*
* @example
* var Float32Array = require( '@stdlib/array/float32' );
*
* var x = new Float32Array( [ 1.0, 2.0, 3.0, 4.0, 5.0 ] );
* var y = new Float32Array( [ 2.0, 3.0, 4.0, 5.0, 6.0 ] );
*
* saxpby( x.length, 5.0, x, 1, 0, 2.0, y, 1, 0 );
* // y => <Float32Array>[ 9.0, 16.0, 23.0, 30.0, 37.0 ]
*/
function saxpby( N, alpha, x, strideX, offsetX, beta, y, strideY, offsetY ) {
var ix;
var iy;
var m;
var i;
if ( N <= 0 ) {
return y;
}
// Fast path: when alpha = 0.0, delegate to sscal (y = beta * y)
if ( alpha === 0.0 ) {
return sscal( N, beta, y, strideY, offsetY );
}
// Fast path: when beta = 1.0, delegate to saxpy (y = alpha * x + y)
if ( beta === 1.0 ) {
return saxpy( N, alpha, x, strideX, offsetX, y, strideY, offsetY );
}
ix = offsetX;
iy = offsetY;
// Use loop unrolling 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++ ) {
y[ iy ] = f32( f32( alpha * x[ ix ] ) + f32( beta * y[ iy ] ) );
ix += strideX;
iy += strideY;
}
}
if ( N < M ) {
return y;
}
for ( i = m; i < N; i += M ) {
y[ iy ] = f32( f32( alpha * x[ ix ] ) + f32( beta * y[ iy ] ) );
y[ iy+1 ] = f32( f32( alpha * x[ ix+1 ] ) + f32( beta * y[ iy+1 ] ) );
y[ iy+2 ] = f32( f32( alpha * x[ ix+2 ] ) + f32( beta * y[ iy+2 ] ) );
y[ iy+3 ] = f32( f32( alpha * x[ ix+3 ] ) + f32( beta * y[ iy+3 ] ) );
y[ iy+4 ] = f32( f32( alpha * x[ ix+4 ] ) + f32( beta * y[ iy+4 ] ) );
ix += M;
iy += M;
}
return y;
}
for ( i = 0; i < N; i++ ) {
y[ iy ] = f32( f32( alpha * x[ ix ] ) + f32( beta * y[ iy ] ) );
ix += strideX;
iy += strideY;
}
return y;
}
// EXPORTS //
module.exports = saxpby;
|