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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 | 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 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 4x 58x 54x 54x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 58x 53x 58x 11x 11x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 21x 21x 21x 21x 21x 21x 21x 33x 33x 33x 11x 11x 47x 58x 35x 58x 18x 18x 18x 18x 58x 58x 58x 58x 58x 66x 66x 66x 66x 66x 66x 66x 66x 58x 40x 40x 40x 40x 40x 40x 40x 58x 58x 58x 18x 18x 29x 58x 23x 58x 18x 18x 18x 58x 58x 58x 58x 58x 40x 40x 40x 40x 58x 18x 18x 18x 58x 66x 66x 66x 66x 66x 66x 66x 66x 66x 58x 58x 58x 58x 58x 18x 18x 11x 11x 58x 33x 33x 33x 33x 33x 21x 21x 21x 21x 33x 12x 12x 12x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 33x 11x 58x 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 f32 = require( '@stdlib/number/float64/base/to-float32' );
var reinterpret = require( '@stdlib/strided/base/reinterpret-complex64' );
var muladd = require( '@stdlib/complex/float32/base/mul-add' ).assign;
// MAIN //
/**
* Performs one of the matrix-vector operations `x = A*x`, or `x = A**T*x`, or `x = A**H*x`, where `x` is an `N` element complex vector and `A` is an `N` by `N` unit, or non-unit, upper or lower triangular complex matrix, supplied in packed form.
*
* @private
* @param {string} order - storage layout
* @param {string} uplo - specifies whether `A` is an upper or lower triangular matrix
* @param {string} trans - specifies whether `A` should be transposed, conjugate-transposed, or not transposed
* @param {string} diag - specifies whether `A` has a unit diagonal
* @param {NonNegativeInteger} N - number of elements along each dimension of `A`
* @param {Complex64Array} AP - packed form of a symmetric matrix `A`
* @param {integer} strideAP - `AP` stride length
* @param {NonNegativeInteger} offsetAP - starting index for `AP`
* @param {Complex64Array} x - input vector
* @param {integer} strideX - `x` stride length
* @param {NonNegativeInteger} offsetX - starting index for `x`
* @returns {Complex64Array} `x`
*
* @example
* var Complex64Array = require( '@stdlib/array/complex64' );
*
* var AP = new Complex64Array( [ 1.0, 1.0, 2.0, 2.0, 4.0, 4.0, 3.0, 3.0, 5.0, 5.0, 6.0, 6.0 ] );
* var x = new Complex64Array( [ 1.0, 1.0, 2.0, 2.0, 3.0, 3.0 ] );
*
* ctpmv( 'row-major', 'lower', 'no-transpose', 'non-unit', 3, AP, 1, 0, x, 1, 0 );
* // x => <Complex64Array>[ 0.0, 2.0, 0.0, 20.0, 0.0, 62.0 ]
*/
function ctpmv( order, uplo, trans, diag, N, AP, strideAP, offsetAP, x, strideX, offsetX ) { // eslint-disable-line max-params, max-len
var nonunit;
var viewAP;
var viewX;
var retmp;
var imtmp;
var isrm;
var sign;
var rex;
var imx;
var rea;
var ima;
var iap;
var ix0;
var ix1;
var sap;
var kk;
var ox;
var sx;
var i1;
var i0;
// Layout
isrm = isRowMajor( order );
// Diagonal
nonunit = ( diag === 'non-unit' );
// Reinterpret arrays to raw numeric views
viewAP = reinterpret( AP, 0 );
viewX = reinterpret( x, 0 );
// Adjust sign to account for conjugation
if ( trans === 'conjugate-transpose' ) {
sign = -1;
} else {
sign = 1;
}
// Vector indexing base
ox = offsetX * 2;
kk = offsetAP * 2;
// Vector strides
sx = strideX * 2;
sap = strideAP * 2;
if (
( !isrm && uplo === 'upper' && trans === 'no-transpose' ) ||
( isrm && uplo === 'lower' && trans !== 'no-transpose' )
) {
ix1 = ox;
for ( i1 = 0; i1 < N; i1++ ) {
retmp = viewX[ ix1 ];
imtmp = viewX[ ix1 + 1 ];
iap = kk;
ix0 = ox;
for ( i0 = 0; i0 < i1; i0++ ) {
rea = viewAP[ iap ];
ima = sign * viewAP[ iap + 1 ];
rex = viewX[ ix0 ];
imx = viewX[ ix0 + 1 ];
muladd( rea, ima, retmp, imtmp, rex, imx, viewX, 1, ix0 );
iap += sap;
ix0 += sx;
}
if ( nonunit ) {
rea = viewAP[ iap ];
ima = sign * viewAP[ iap + 1 ];
rex = viewX[ ix0 ];
imx = viewX[ ix0 + 1 ];
viewX[ ix0 ] = f32( ( rea * rex ) - ( ima * imx ) );
viewX[ ix0 + 1 ] = f32( ( rea * imx ) + ( ima * rex ) );
}
ix1 += sx;
kk += ( i1 + 1 ) * sap;
}
return x;
}
if (
( !isrm && uplo === 'lower' && trans === 'no-transpose' ) ||
( isrm && uplo === 'upper' && trans !== 'no-transpose' )
) {
kk += ( ( N * ( N + 1 ) / 2 ) - 1 ) * sap;
ox += ( N - 1 ) * sx;
ix1 = ox;
for ( i1 = N - 1; i1 >= 0; i1-- ) {
retmp = viewX[ ix1 ];
imtmp = viewX[ ix1 + 1 ];
iap = kk;
ix0 = ox;
for ( i0 = N - 1; i0 > i1; i0-- ) {
rea = viewAP[ iap ];
ima = sign * viewAP[ iap + 1 ];
rex = viewX[ ix0 ];
imx = viewX[ ix0 + 1 ];
muladd( rea, ima, retmp, imtmp, rex, imx, viewX, 1, ix0 );
iap -= sap;
ix0 -= sx;
}
if ( nonunit ) {
rea = viewAP[ iap ];
ima = sign * viewAP[ iap + 1 ];
rex = viewX[ ix0 ];
imx = viewX[ ix0 + 1 ];
viewX[ ix0 ] = f32( ( rea * rex ) - ( ima * imx ) );
viewX[ ix0 + 1 ] = f32( ( rea * imx ) + ( ima * rex ) );
}
ix1 -= sx;
kk -= ( N - i1 ) * sap;
}
return x;
}
if (
( !isrm && uplo === 'upper' && trans !== 'no-transpose' ) ||
( isrm && uplo === 'lower' && trans === 'no-transpose' )
) {
kk += ( ( N * ( N + 1 ) / 2 ) - 1 ) * sap;
ix1 = ox + ( ( N - 1 ) * sx );
for ( i1 = N - 1; i1 >= 0; i1-- ) {
rex = viewX[ ix1 ];
imx = viewX[ ix1 + 1 ];
iap = kk;
ix0 = ix1;
if ( nonunit ) {
rea = viewAP[ iap ];
ima = sign * viewAP[ iap + 1 ];
retmp = f32( ( rea * rex ) - ( ima * imx ) );
imtmp = f32( ( rea * imx ) + ( ima * rex ) );
} else {
retmp = rex;
imtmp = imx;
}
for ( i0 = i1 - 1; i0 >= 0; i0-- ) {
ix0 -= sx;
iap -= sap;
rea = viewAP[ iap ];
ima = sign * viewAP[ iap + 1 ];
rex = viewX[ ix0 ];
imx = viewX[ ix0 + 1 ];
retmp += f32( ( rea * rex ) - ( ima * imx ) );
imtmp += f32( ( rea * imx ) + ( ima * rex ) );
}
viewX[ ix1 ] = retmp;
viewX[ ix1 + 1 ] = imtmp;
ix1 -= sx;
kk -= ( i1 + 1 ) * sap;
}
return x;
}
// ( !isrm && uplo === 'lower' && trans !== 'no-transpose' ) || ( isrm && uplo === 'upper' && trans === 'no-transpose' )
ix1 = ox;
for ( i1 = 0; i1 < N; i1++ ) {
rex = viewX[ ix1 ];
imx = viewX[ ix1 + 1 ];
iap = kk;
ix0 = ix1;
if ( nonunit ) {
rea = viewAP[ iap ];
ima = sign * viewAP[ iap + 1 ];
retmp = f32( ( rea * rex ) - ( ima * imx ) );
imtmp = f32( ( rea * imx ) + ( ima * rex ) );
} else {
retmp = rex;
imtmp = imx;
}
for ( i0 = i1+1; i0 < N; i0++ ) {
ix0 += sx;
iap += sap;
rea = viewAP[ iap ];
ima = sign * viewAP[ iap + 1 ];
rex = viewX[ ix0 ];
imx = viewX[ ix0 + 1 ];
retmp += f32( ( rea * rex ) - ( ima * imx ) );
imtmp += f32( ( rea * imx ) + ( ima * rex ) );
}
viewX[ ix1 ] = retmp;
viewX[ ix1 + 1 ] = imtmp;
ix1 += sx;
kk += ( N - i1 ) * sap;
}
return x;
}
// EXPORTS //
module.exports = ctpmv;
|