Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: add lapack/base/dptts2 #2625

Open
wants to merge 19 commits into
base: develop
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from 12 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
253 changes: 253 additions & 0 deletions lib/node_modules/@stdlib/lapack/base/dptts2/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,253 @@
<!--

@license Apache-2.0

Copyright (c) 2024 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.

-->

# dlaswp
Pranavchiku marked this conversation as resolved.
Show resolved Hide resolved

> Solve a tridiagonal system of the form `A * X = B` using `L * D * L ** T` factorization of `A`.

<section class = "usage">

## Usage

```javascript
var dptts2 = require( '@stdlib/lapack/base/dptts2' );
```

#### dptts2( order, N, NRHS, D, E, B, LDB )

Solves a tridiagonal system of the form `A * X = B` using `L * D * L ** T` factorization of `A`.

```javascript
var Float64Array = require( '@stdlib/array/float64' );

var D = new Float64Array( [ 1.0, 1.0, 1.0 ] );
var E = new Float64Array( [ 2.0, 3.0 ] );
var B = new Float64Array( [ 1.0, 2.0, 3.0, 4.0, 5.0, 6.0 ] );

dptts2( 'row-major', 3, 2, D, E, B, 2 );
// B => <Float64Array>[ 11.0, 38.0, -5.0, -18.0, 2.0, 6.0 ]
```

The function has the following parameters:

- **order**: storage layout.
- **N**: order of the tridiagonal matrix `A`.
- **NRHS**: number of right-hand sides i.e. the number of columns in `B`.
- **D**: array containing the diagonal elements of `A`.
- **E**: array containing the subdiagonal elements of `A`.
- **B**: input matrix stored in linear memory as a [`Float64Array`][mdn-float64array].
- **LDB**: stride of the first dimension of `B` (a.k.a., leading dimension of the matrix `B`).

Note that indexing is relative to the first index. To introduce an offset, use [`typed array`][mdn-typed-array] views.

<!-- eslint-disable stdlib/capitalized-comments -->

```javascript
var Float64Array = require( '@stdlib/array/float64' );

// Initial arrays...
var D0 = new Float64Array( [ 0.0, 1.0, 1.0, 1.0 ] );
var E0 = new Float64Array( [ 0.0, 2.0, 3.0 ] );
var B0 = new Float64Array( [ 0.0, 0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0 ] );

// Create offset views...
var D1 = new Float64Array( D0.buffer, D0.BYTES_PER_ELEMENT*1 ); // start at 1st element
var E1 = new Float64Array( E0.buffer, E0.BYTES_PER_ELEMENT*1 ); // start at 1st element
var B1 = new Float64Array( B0.buffer, B0.BYTES_PER_ELEMENT*2 ); // start at 2nd element

dptts2( 'row-major', 3, 2, D1, E1, B1, 2 );
// B0 => <Float64Array>[ 0.0, 0.0, 11.0, 38.0, -5.0, -18.0, 2.0, 6.0 ]
```

#### dptts2.ndarray( order, N, NRHS, D, sd, od, E, se, oe, B, sb1, sb2, ob )

Solves a tridiagonal system of the form `A * X = B` using `L * D * L ** T` factorization of `A` using alternative indexing semantics.

```javascript
var Float64Array = require( '@stdlib/array/float64' );

var D = new Float64Array( [ 1.0, 1.0, 1.0 ] );
var E = new Float64Array( [ 2.0, 3.0 ] );
var B = new Float64Array( [ 1.0, 2.0, 3.0, 4.0, 5.0, 6.0 ] );

dptts2.ndarray( 'row-major', 3, 2, D, 1, 0, E, 1, 0, B, 2, 1, 0 );
// B => <Float64Array>[ 11.0, 38.0, -5.0, -18.0, 2.0, 6.0 ]
```

The function has the following parameters:

- **order**: storage layout.
- **N**: order of the tridiagonal matrix `A`.
- **NRHS**: number of right-hand sides i.e. the number of columns in `B`.
- **D**: array containing the diagonal elements of `A`.
- **sd**: stride length for `D`.
- **od**: starting index for `D`.
- **E**: array containing the subdiagonal elements of `A`.
- **se**: stride length for `E`.
- **oe**: starting index for `E`.
- **B**: input matrix stored in linear memory as a [`Float64Array`][mdn-float64array].
- **sb1**: stride of first dimension of `B`.
- **sb2**: stride of second dimension of `B`.
- **ob**: starting index for `B`.

While [`typed array`][mdn-typed-array] views mandate a view offset based on the underlying buffer, the offset parameters support indexing semantics based on starting indices. For example,

<!-- eslint-disable max-len -->

```javascript
var Float64Array = require( '@stdlib/array/float64' );

var D = new Float64Array( [ 1.0, 1.0, 1.0 ] );
var E = new Float64Array( [ 2.0, 3.0 ] );
var B = new Float64Array( [ 0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0 ] );

dptts2.ndarray( 'row-major', 3, 2, D, 1, 0, E, 1, 0, B, 2, 1, 1 );
// B => <Float64Array>[ 0.0, 11.0, 38.0, -5.0, -18.0, 2.0, 6.0 ]
```

</section>

<!-- /.usage -->

<section class="notes">

## Notes

- `dptts2()` corresponds to [LAPACK][LAPACK] routine [`dptts2`][dptts2].

</section>

<!-- /.notes -->

<section class="examples">

## Examples

<!-- eslint no-undef: "error" -->

```javascript
var Float64Array = require( '@stdlib/array/float64' );
var dptts2 = require( '@stdlib/lapack/base/dptts2' );

var D = new Float64Array( [ 1.0, 1.0, 1.0 ] );
var E = new Float64Array( [ 2.0, 3.0 ] );
var B = new Float64Array( [ 1.0, 2.0, 3.0, 4.0, 5.0, 6.0 ] );

dptts2.ndarray( 'row-major', 3, 2, D, 1, 0, E, 1, 0, B, 2, 1, 0 );
console.log( B );
```

</section>

<!-- /.examples -->

<!-- C interface documentation. -->

* * *

<section class="c">

## C APIs

<!-- Section to include introductory text. Make sure to keep an empty line after the intro `section` element and another before the `/section` close. -->

<section class="intro">

</section>

<!-- /.intro -->

<!-- C usage documentation. -->

<section class="usage">

### Usage

```c
TODO
```

#### TODO

TODO.

```c
TODO
```

TODO

```c
TODO
```

</section>

<!-- /.usage -->

<!-- C API usage notes. Make sure to keep an empty line after the `section` element and another before the `/section` close. -->

<section class="notes">

</section>

<!-- /.notes -->

<!-- C API usage examples. -->

<section class="examples">

### Examples

```c
TODO
```

</section>

<!-- /.examples -->

</section>

<!-- /.c -->

<!-- Section for related `stdlib` packages. Do not manually edit this section, as it is automatically populated. -->

<section class="related">

</section>

<!-- /.related -->

<!-- Section for all links. Make sure to keep an empty line after the `section` element and another before the `/section` close. -->

<section class="links">

[lapack]: https://www.netlib.org/lapack/explore-html/

[dptts2]: https://www.netlib.org/lapack/explore-html/d5/d5d/group__ptts2_ga35fdfa6109e8f9cbfbde271814bf0b27.html#ga35fdfa6109e8f9cbfbde271814bf0b27

[mdn-float64array]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Float64Array

[mdn-typed-array]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/TypedArray

</section>

<!-- /.links -->
107 changes: 107 additions & 0 deletions lib/node_modules/@stdlib/lapack/base/dptts2/benchmark/benchmark.js
Original file line number Diff line number Diff line change
@@ -0,0 +1,107 @@
/**
* @license Apache-2.0
*
* Copyright (c) 2024 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 bench = require( '@stdlib/bench' );
var uniform = require( '@stdlib/random/array/uniform' );
var isnan = require( '@stdlib/math/base/assert/is-nan' );
var pow = require( '@stdlib/math/base/special/pow' );
var floor = require( '@stdlib/math/base/special/floor' );
var pkg = require( './../package.json' ).name;
var dptts2 = require( './../lib/dptts2.js' );


// VARIABLES //

var options = {
'dtype': 'float64'
};


// FUNCTIONS //

/**
* Creates a benchmark function.
*
* @private
* @param {PositiveInteger} len - array length
* @returns {Function} benchmark function
*/
function createBenchmark( len ) {
var B;
var D = uniform( len, -10.0, 10.0, options );
var E = uniform( len-1, -10.0, 10.0, options );

return benchmark;

/**
* Benchmark function.
*
* @private
* @param {Benchmark} b - benchmark instance
*/
function benchmark( b ) {
var z;
var i;

b.tic();
for ( i = 0; i < b.iterations; i++ ) {
B = uniform( len * len, -10.0, 10.0, options );
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do not allocate new arrays in benchmarks. Results will be tainted with non-relevant operations.

z = dptts2( 'row-major', len, len, D, E, B, len );
if ( isnan( z[ i%z.length ] ) ) {
b.fail( 'should not return NaN' );
}
}
b.toc();
if ( isnan( z[ i%z.length ] ) ) {
b.fail( 'should not return NaN' );
}
b.pass( 'benchmark finished' );
b.end();
}
}


// MAIN //

/**
* Main execution sequence.
*
* @private
*/
function main() {
var len;
var min;
var max;
var f;
var i;

min = 1; // 10^min
max = 5; // 10^max

for ( i = min; i <= max; i++ ) {
len = floor( pow( pow( 10, i ), 1.0/2.0 ) );
f = createBenchmark( len );
bench( pkg+':order=row-major:size='+(len*len), f );
}
}

main();
Loading
Loading