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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | 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 1x 1x 1x 1x 1x 1x 1x 1x 1x | /**
* @license Apache-2.0
*
* Copyright (c) 2025 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' );
var reinterpret = require( '@stdlib/strided/base/reinterpret-complex128' );
var floor = require( '@stdlib/math/base/special/floor' );
var zswap = require( '@stdlib/blas/base/zswap' ).ndarray;
// VARIABLES //
var BLOCK_SIZE = 32;
// MAIN //
/**
* Performs a series of row interchanges on a matrix `A` using pivot indices stored in `IPIV`.
*
* @private
* @param {PositiveInteger} N - number of columns in `A`
* @param {Complex128Array} A - input matrix
* @param {integer} strideA1 - stride of the first dimension of `A`
* @param {integer} strideA2 - stride of the second dimension of `A`
* @param {NonNegativeInteger} offsetA - index offset for `A`
* @param {NonNegativeInteger} k1 - index of first row to interchange
* @param {NonNegativeInteger} k2 - index of last row to interchange
* @param {integer} inck - direction in which to apply pivots (-1 to apply pivots in reverse order; otherwise, apply in provided order)
* @param {Int32Array} IPIV - vector of pivot indices
* @param {integer} strideIPIV - `IPIV` stride length
* @param {NonNegativeInteger} offsetIPIV - index offset for `IPIV`
* @returns {Complex128Array} permuted matrix `A`
*
* @example
* var Int32Array = require( '@stdlib/array/int32' );
* var Complex128Array = require( '@stdlib/array/complex128' );
*
* var IPIV = new Int32Array( [ 2, 0, 1 ] );
* var A = new Complex128Array( [ 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0 ] );
*
* zlaswp( 2, A, 2, 1, 0, 0, 2, 1, IPIV, 1, 0 );
* // A => <Complex128Array>[ 5.0, 6.0, 7.0, 8.0, 1.0, 2.0, 3.0, 4.0, 9.0, 10.0, 11.0, 12.0 ]
*/
function zlaswp( N, A, strideA1, strideA2, offsetA, k1, k2, inck, IPIV, strideIPIV, offsetIPIV ) { // eslint-disable-line max-len, max-params
var nrows;
var viewA;
var n32;
var tmp;
var row;
var ia1;
var ia2;
var ip;
var i;
var j;
var k;
var n;
var o;
// Compute the number of rows to be interchanged:
if ( inck > 0 ) {
nrows = k2 - k1;
} else {
nrows = k1 - k2;
}
nrows += 1;
// If the order is row-major, we can delegate to the Level 1 routine `zswap` for interchanging rows...
if ( isRowMajor( [ strideA1, strideA2 ] ) ) {
ip = offsetIPIV;
for ( i = 0, k = k1; i < nrows; i++, k += inck ) {
row = IPIV[ ip ];
if ( row !== k ) {
zswap( N, A, strideA2, offsetA+(k*strideA1), A, strideA2, offsetA+(row*strideA1) ); // eslint-disable-line max-len
}
ip += strideIPIV;
}
return A;
}
viewA = reinterpret( A, 0 );
strideA1 *= 2;
strideA2 *= 2;
offsetA *= 2;
// If the order is column-major, we need to use loop tiling to ensure efficient cache access when accessing matrix elements...
n32 = floor( N/BLOCK_SIZE ) * BLOCK_SIZE;
if ( n32 !== 0 ) {
for ( j = 0; j < n32; j += BLOCK_SIZE ) {
ip = offsetIPIV;
for ( i = 0, k = k1; i < nrows; i++, k += inck ) {
row = IPIV[ ip ];
if ( row !== k ) {
ia1 = offsetA + ( k*strideA1 );
ia2 = offsetA + ( row*strideA1 );
for ( n = j; n < j+BLOCK_SIZE; n++ ) {
o = n * strideA2;
tmp = viewA[ ia1+o ];
viewA[ ia1+o ] = viewA[ ia2+o ];
viewA[ ia2+o ] = tmp;
tmp = viewA[ ia1+o+1 ];
viewA[ ia1+o+1 ] = viewA[ ia2+o+1 ];
viewA[ ia2+o+1 ] = tmp;
}
}
ip += strideIPIV;
}
}
}
if ( n32 !== N ) {
ip = offsetIPIV;
for ( i = 0, k = k1; i < nrows; i++, k += inck ) {
row = IPIV[ ip ];
if ( row !== k ) {
ia1 = offsetA + ( k*strideA1 );
ia2 = offsetA + ( row*strideA1 );
for ( n = n32; n < N; n++ ) {
o = n * strideA2;
tmp = viewA[ ia1+o ];
viewA[ ia1+o ] = viewA[ ia2+o ];
viewA[ ia2+o ] = tmp;
tmp = viewA[ ia1+o+1 ];
viewA[ ia1+o+1 ] = viewA[ ia2+o+1 ];
viewA[ ia2+o+1 ] = tmp;
}
}
ip += strideIPIV;
}
}
return A;
}
// EXPORTS //
module.exports = zlaswp;
|