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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 | 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 3x 3x 3x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 20x 8x 20x 12x 12x 20x 54x 16x 16x 38x 38x 38x 38x 54x 20x 20x 20x 60x 60x 60x 60x 60x 60x 60x 60x 60x 60x 60x 60x 60x 60x 60x 60x 60x 20x 20x 18x 18x 18x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 54x 18x 54x 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 isRowMajor = require( '@stdlib/ndarray/base/assert/is-row-major-string' );
var sfill = require( '@stdlib/blas/ext/base/sfill' ).ndarray;
var sscal = require( '@stdlib/blas/base/sscal' ).ndarray;
var f32 = require( '@stdlib/number/float64/base/to-float32' );
// MAIN //
/**
* Performs the matrix-vector operation `y = α*A*x + β*y` where `α` and `β` are scalars, `x` and `y` are `N` element vectors, and `A` is an `N` by `N` symmetric matrix supplied in packed form.
*
* @private
* @param {string} order - storage layout
* @param {string} uplo - specifies whether the upper or lower triangular part of the symmetric matrix `A` is being supplied
* @param {NonNegativeInteger} N - number of elements along each dimension of `A`
* @param {number} alpha - scalar constant
* @param {Float32Array} AP - packed form of a symmetric matrix `A`
* @param {integer} strideAP - `AP` stride length
* @param {NonNegativeInteger} offsetAP - starting index for `AP`
* @param {Float32Array} x - first input array
* @param {integer} strideX - `x` stride length
* @param {NonNegativeInteger} offsetX - starting `x` index
* @param {number} beta - scalar constant
* @param {Float32Array} y - second input array
* @param {integer} strideY - `y` stride length
* @param {NonNegativeInteger} offsetY - starting `y` index
* @returns {Float32Array} `y`
*
* @example
* var Float32Array = require( '@stdlib/array/float32' );
*
* var AP = new Float32Array( [ 1.0, 2.0, 3.0, 4.0, 5.0, 6.0 ] );
* var x = new Float32Array( [ 1.0, 1.0, 1.0 ] );
* var y = new Float32Array( [ 1.0, 1.0, 1.0 ] );
*
* sspmv( 'column-major', 'lower', 3, 1.0, AP, 1, 0, x, 1, 0, 1.0, y, 1, 0 );
* // y => <Float32Array>[ 7.0, 12.0, 15.0 ]
*/
function sspmv( order, uplo, N, alpha, AP, strideAP, offsetAP, x, strideX, offsetX, beta, y, strideY, offsetY ) { // eslint-disable-line max-params, max-len
var isrm;
var tmp1;
var tmp2;
var iap;
var ix0;
var ix1;
var iy0;
var iy1;
var i1;
var i0;
var kk;
// y = beta*y
if ( beta !== 1.0 ) {
if ( beta === 0.0 ) {
sfill( N, 0.0, y, strideY, offsetY );
} else {
sscal( N, beta, y, strideY, offsetY );
}
}
if ( alpha === 0.0 ) {
return y;
}
isrm = isRowMajor( order );
kk = offsetAP;
// Form: y = α*A*x + y
if ( ( !isrm && uplo === 'upper' ) || ( isrm && uplo === 'lower' ) ) {
ix1 = offsetX;
iy1 = offsetY;
for ( i1 = 0; i1 < N; i1++ ) {
tmp1 = f32( alpha * x[ ix1 ] );
tmp2 = f32( 0.0 );
ix0 = offsetX;
iy0 = offsetY;
iap = kk;
for ( i0 = 0; i0 < i1; i0++ ) {
y[ iy0 ] += f32( tmp1 * AP[ iap ] );
tmp2 = f32( tmp2 + f32( AP[ iap ] * x[ ix0 ] ) );
ix0 += strideX;
iy0 += strideY;
iap += strideAP;
}
y[ iy1 ] += f32( f32( tmp1*AP[ iap ] ) + f32( alpha*tmp2 ) );
ix1 += strideX;
iy1 += strideY;
kk += ( i1 + 1 ) * strideAP;
}
return y;
}
// ( !isrm && uplo === 'lower' ) || ( isrm && uplo === 'upper' )
ix1 = offsetX;
iy1 = offsetY;
for ( i1 = 0; i1 < N; i1++ ) {
tmp1 = f32( alpha * x[ ix1 ] );
tmp2 = f32( 0.0 );
y[ iy1 ] += f32( tmp1 * AP[ kk ] );
iap = kk;
ix0 = ix1;
iy0 = iy1;
for ( i0 = i1+1; i0 < N; i0++ ) {
ix0 += strideX;
iy0 += strideY;
iap += strideAP;
y[ iy0 ] += f32( tmp1 * AP[ iap ] );
tmp2 = f32( tmp2 + f32( AP[ iap ] * x[ ix0 ] ) );
}
y[ iy1 ] += f32( alpha * tmp2 );
ix1 += strideX;
iy1 += strideY;
kk += ( N - i1 ) * strideAP;
}
return y;
}
// EXPORTS //
module.exports = sspmv;
|