feat: add C ndarray API and refactor blas/ext/base/dcusumpw

PR-URL: #2981 Co-authored-by: Athan Reines <[email protected]> Reviewed-by: Athan Reines <[email protected]> Signed-off-by: Athan Reines <[email protected]>
stdlib-js · Oct 3, 2024 · 3bd3f48 · 3bd3f48 · stdlib-bot · Oct 3, 2024
1 parent ca2fbd0
commit 3bd3f48
Show file tree

Hide file tree

Showing 15 changed files with 313 additions and 125 deletions.
diff --git a/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/README.md b/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/README.md
@@ -115,7 +115,7 @@ The function has the following additional parameters:
 -   **offsetX**: starting index for `x`.
 -   **offsetY**: starting index for `y`.
 
-While [`typed array`][mdn-typed-array] views mandate a view offset based on the underlying `buffer`, `offsetX` and `offsetY` parameters support indexing semantics based on a starting indices. For example, to calculate the cumulative sum of every other value in the strided input array starting from the second value and to store in the last `N` elements of the strided output array starting from the last element
+While [`typed array`][mdn-typed-array] views mandate a view offset based on the underlying buffer, offset parameters support indexing semantics based on starting indices. For example, to calculate the cumulative sum of every other value in the strided input array starting from the second value and to store in the last `N` elements of the strided output array starting from the last element
 
 ```javascript
 var Float64Array = require( '@stdlib/array/float64' );
@@ -149,12 +149,13 @@ dcusumpw.ndarray( 4, 0.0, x, 2, 1, y, -1, y.length-1 );
 <!-- eslint no-undef: "error" -->
 
 ```javascript
-var discreteUniform = require( '@stdlib/random/base/discrete-uniform' ).factory;
-var filledarrayBy = require( '@stdlib/array/filled-by' );
+var discreteUniform = require( '@stdlib/random/array/discrete-uniform' );
 var Float64Array = require( '@stdlib/array/float64' );
 var dcusumpw = require( '@stdlib/blas/ext/base/dcusumpw' );
 
-var x = filledarrayBy( 10, 'float64', discreteUniform( 0, 100 ) );
+var x = discreteUniform( 10, -100, 100, {
+    'dtype': 'float64'
+});
 var y = new Float64Array( x.length );
 
 console.log( x );
@@ -168,8 +169,138 @@ console.log( y );
 
 <!-- /.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
+#include "stdlib/blas/ext/base/dcusumpw.h"
+```
+
+#### stdlib_strided_dcusumpw( N, sum, \*X, strideX, \*Y, strideY )
+
+Computes the cumulative sum of double-precision floating-point strided array elements using pairwise summation.
+
+```c
+const double x[] = { 1.0, 2.0, 3.0, 4.0 };
+double y[] = { 0.0, 0.0, 0.0, 0.0 };
+
+stdlib_strided_dcusumpw( 4, 0.0, x, 1, y, 1 );
+```
+
+The function accepts the following arguments:
+
+-   **N**: `[in] CBLAS_INT` number of indexed elements.
+-   **sum**: `[in] double` initial sum.
+-   **X**: `[in] double*` input array.
+-   **strideX**: `[in] CBLAS_INT` index increment for `X`.
+-   **Y**: `[out] double*` output array.
+-   **strideY**: `[in] CBLAS_INT` index increment for `Y`.
+
+```c
+void stdlib_strided_dcusumpw( const CBLAS_INT N, const double sum, const double *X, const CBLAS_INT strideX, double *Y, const CBLAS_INT strideY );
+```
+
+<!-- lint disable maximum-heading-length -->
+
+#### stdlib_strided_dcusumpw_ndarray( N, sum, \*X, strideX, offsetX, \*Y, strideY, offsetY )
+
+<!-- lint enable maximum-heading-length -->
+
+Computes the cumulative sum of double-precision floating-point strided array elements using pairwise summation and alternative indexing semantics.
+
+```c
+const double x[] = { 1.0, 2.0, 3.0, 4.0 }
+double y[] = { 0.0, 0.0, 0.0, 0.0 }
+
+stdlib_strided_dcusumpw_ndarray( 4, 0.0, x, 1, 0, y, 1, 0 );
+```
+
+The function accepts the following arguments:
+
+-   **N**: `[in] CBLAS_INT` number of indexed elements.
+-   **sum**: `[in] double` initial sum.
+-   **X**: `[in] double*` input array.
+-   **strideX**: `[in] CBLAS_INT` index increment for `X`.
+-   **offsetX**: `[in] CBLAS_INT` starting index for `X`.
+-   **Y**: `[out] double*` output array.
+-   **strideY**: `[in] CBLAS_INT` index increment for `Y`.
+-   **offsetY**: `[in] CBLAS_INT` starting index for `Y`.
+
+```c
+void stdlib_strided_dcusumpw_ndarray( const CBLAS_INT N, const double sum, const double *X, const CBLAS_INT strideX, const CBLAS_INT offsetX, double *Y, const CBLAS_INT strideY, const CBLAS_INT offsetY );
+```
+
+</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
+#include "stdlib/blas/ext/base/dcusumpw.h"
+#include <stdio.h>
+
+int main( void ) {
+    // Create strided arrays:
+    const double x[] = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0 };
+    double y[] = { 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 };
+
+    // Specify the number of elements:
+    const int N = 4;
+
+    // Specify stride lengths:
+    const int strideX = 2;
+    const int strideY = -2;
+
+    // Compute the cumulative sum:
+    stdlib_strided_dcusumpw( N, 0.0, x, strideX, y, strideY );
+
+    // Print the result:
+    for ( int i = 0; i < 8; i++ ) {
+        printf( "y[ %d ] = %lf\n", i, y[ i ] );
+    }
+}
+```
+
+</section>
+
+<!-- /.examples -->
+
+</section>
+
+<!-- /.c -->
+
 <section class="references">
 
 ## References

diff --git a/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/benchmark.js b/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/benchmark.js
@@ -21,8 +21,7 @@
 // MODULES //
 
 var bench = require( '@stdlib/bench' );
-var uniform = require( '@stdlib/random/base/uniform' ).factory;
-var filledarrayBy = require( '@stdlib/array/filled-by' );
+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 Float64Array = require( '@stdlib/array/float64' );
@@ -32,7 +31,9 @@ var dcusumpw = require( './../lib/dcusumpw.js' );
 
 // VARIABLES //
 
-var rand = uniform( -10.0, 10.0 );
+var options = {
+	'dtype': 'float64'
+};
 
 
 // FUNCTIONS //
@@ -45,7 +46,7 @@ var rand = uniform( -10.0, 10.0 );
 * @returns {Function} benchmark function
 */
 function createBenchmark( len ) {
-	var x = filledarrayBy( len, 'float64', rand );
+	var x = uniform( len, -100, 100, options );
 	var y = new Float64Array( len );
 	return benchmark;
 

diff --git a/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/benchmark.native.js b/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/benchmark.native.js
@@ -22,8 +22,7 @@
 
 var resolve = require( 'path' ).resolve;
 var bench = require( '@stdlib/bench' );
-var uniform = require( '@stdlib/random/base/uniform' ).factory;
-var filledarrayBy = require( '@stdlib/array/filled-by' );
+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 Float64Array = require( '@stdlib/array/float64' );
@@ -33,7 +32,9 @@ var pkg = require( './../package.json' ).name;
 
 // VARIABLES //
 
-var rand = uniform( -10.0, 10.0 );
+var options = {
+	'dtype': 'float64'
+};
 var dcusumpw = tryRequire( resolve( __dirname, './../lib/dcusumpw.native.js' ) );
 var opts = {
 	'skip': ( dcusumpw instanceof Error )
@@ -50,7 +51,7 @@ var opts = {
 * @returns {Function} benchmark function
 */
 function createBenchmark( len ) {
-	var x = filledarrayBy( len, 'float64', rand );
+	var x = uniform( len, -100, 100, options );
 	var y = new Float64Array( len );
 	return benchmark;
 

diff --git a/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/benchmark.ndarray.js b/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/benchmark.ndarray.js
@@ -21,8 +21,7 @@
 // MODULES //
 
 var bench = require( '@stdlib/bench' );
-var uniform = require( '@stdlib/random/base/uniform' ).factory;
-var filledarrayBy = require( '@stdlib/array/filled-by' );
+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 Float64Array = require( '@stdlib/array/float64' );
@@ -32,7 +31,9 @@ var dcusumpw = require( './../lib/ndarray.js' );
 
 // VARIABLES //
 
-var rand = uniform( -10.0, 10.0 );
+var options = {
+	'dtype': 'float64'
+};
 
 
 // FUNCTIONS //
@@ -45,7 +46,7 @@ var rand = uniform( -10.0, 10.0 );
 * @returns {Function} benchmark function
 */
 function createBenchmark( len ) {
-	var x = filledarrayBy( len, 'float64', rand );
+	var x = uniform( len, -100, 100, options );
 	var y = new Float64Array( len );
 	return benchmark;
 

diff --git a/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/benchmark.ndarray.native.js b/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/benchmark.ndarray.native.js
@@ -22,8 +22,7 @@
 
 var resolve = require( 'path' ).resolve;
 var bench = require( '@stdlib/bench' );
-var uniform = require( '@stdlib/random/base/uniform' ).factory;
-var filledarrayBy = require( '@stdlib/array/filled-by' );
+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 Float64Array = require( '@stdlib/array/float64' );
@@ -33,7 +32,9 @@ var pkg = require( './../package.json' ).name;
 
 // VARIABLES //
 
-var rand = uniform( -10.0, 10.0 );
+var options = {
+	'dtype': 'float64'
+};
 var dcusumpw = tryRequire( resolve( __dirname, './../lib/ndarray.native.js' ) );
 var opts = {
 	'skip': ( dcusumpw instanceof Error )
@@ -50,7 +51,7 @@ var opts = {
 * @returns {Function} benchmark function
 */
 function createBenchmark( len ) {
-	var x = filledarrayBy( len, 'float64', rand );
+	var x = uniform( len, -100, 100, options );
 	var y = new Float64Array( len );
 	return benchmark;
 

diff --git a/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/c/benchmark.length.c b/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/benchmark/c/benchmark.length.c
@@ -94,13 +94,16 @@ static double rand_double( void ) {
 * @param len          array length
 * @return elapsed time in seconds
 */
-static double benchmark( int iterations, int len ) {
+static double benchmark1( int iterations, int len ) {
 	double elapsed;
-	double x[ len ];
-	double y[ len ];
+	double *x;
+	double *y;
 	double t;
 	int i;
 
+	x = (double *)malloc( len * sizeof(double) );
+	y = (double *)malloc( len * sizeof(double) );
+
 	for ( i = 0; i < len; i++ ) {
 		x[ i ] = ( rand_double() * 20000.0 ) - 10000.0;
 		y[ i ] = 0.0;
@@ -118,6 +121,47 @@ static double benchmark( int iterations, int len ) {
 	if ( y[ len-1 ] != y[ len-1 ] ) {
 		printf( "should not return NaN\n" );
 	}
+	free( x );
+	free( y );
+	return elapsed;
+}
+
+/**
+* Runs a benchmark.
+*
+* @param iterations   number of iterations
+* @param len          array length
+* @return elapsed time in seconds
+*/
+static double benchmark2( int iterations, int len ) {
+	double elapsed;
+	double *x;
+	double *y;
+	double t;
+	int i;
+
+	x = (double *)malloc( len * sizeof(double) );
+	y = (double *)malloc( len * sizeof(double) );
+
+	for ( i = 0; i < len; i++ ) {
+		x[ i ] = ( rand_double() * 20000.0 ) - 10000.0;
+		y[ i ] = 0.0;
+	}
+	t = tic();
+	for ( i = 0; i < iterations; i++ ) {
+		x[ 0 ] += 1.0;
+		stdlib_strided_dcusumpw_ndarray( len, 0.0, x, 1, 0, y, 1, 0 );
+		if ( y[ 0 ] != y[ 0 ] ) {
+			printf( "should not return NaN\n" );
+			break;
+		}
+	}
+	elapsed = tic() - t;
+	if ( y[ len-1 ] != y[ len-1 ] ) {
+		printf( "should not return NaN\n" );
+	}
+	free( x );
+	free( y );
 	return elapsed;
 }
 
@@ -143,7 +187,18 @@ int main( void ) {
 		for ( j = 0; j < REPEATS; j++ ) {
 			count += 1;
 			printf( "# c::%s:len=%d\n", NAME, len );
-			elapsed = benchmark( iter, len );
+			elapsed = benchmark1( iter, len );
+			print_results( iter, elapsed );
+			printf( "ok %d benchmark finished\n", count );
+		}
+	}
+	for ( i = MIN; i <= MAX; i++ ) {
+		len = pow( 10, i );
+		iter = ITERATIONS / pow( 10, i-1 );
+		for ( j = 0; j < REPEATS; j++ ) {
+			count += 1;
+			printf( "# c::%s:ndarray:len=%d\n", NAME, len );
+			elapsed = benchmark2( iter, len );
 			print_results( iter, elapsed );
 			printf( "ok %d benchmark finished\n", count );
 		}

diff --git a/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/docs/repl.txt b/lib/node_modules/@stdlib/blas/ext/base/dcusumpw/docs/repl.txt
@@ -3,7 +3,7 @@
     Computes the cumulative sum of double-precision floating-point strided array
     elements using pairwise summation.
 
-    The `N` and `stride` parameters determine which elements in the strided
+    The `N` and stride parameters determine which elements in the strided
     arrays are accessed at runtime.
 
     Indexing is relative to the first index. To introduce an offset, use a typed
@@ -66,8 +66,8 @@
     elements using pairwise summation and alternative indexing semantics.
 
     While typed array views mandate a view offset based on the underlying
-    buffer, the `offset` parameter supports indexing semantics based on a
-    starting index.
+    buffer, offset parameters support indexing semantics based on starting
+    indices.
 
     Parameters
     ----------