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

PR-URL: #3285 Reviewed-by: Muhammad Haris <[email protected]> Reviewed-by: Philipp Burckhardt <[email protected]> Signed-off-by: Snehil Shah <[email protected]>
stdlib-js · Dec 1, 2024 · c83f108 · kgryte · Dec 3, 2024 · kgryte
1 parent 1242bbf
commit c83f108
Show file tree

Hide file tree

Showing 19 changed files with 480 additions and 261 deletions.
diff --git a/lib/node_modules/@stdlib/blas/ext/base/ssumpw/README.md b/lib/node_modules/@stdlib/blas/ext/base/ssumpw/README.md
@@ -36,27 +36,26 @@ limitations under the License.
 var ssumpw = require( '@stdlib/blas/ext/base/ssumpw' );
 ```
 
-#### ssumpw( N, x, stride )
+#### ssumpw( N, x, strideX )
 
 Computes the sum of single-precision floating-point strided array elements using pairwise summation.
 
 ```javascript
 var Float32Array = require( '@stdlib/array/float32' );
 
 var x = new Float32Array( [ 1.0, -2.0, 2.0 ] );
-var N = x.length;
 
-var v = ssumpw( N, x, 1 );
+var v = ssumpw( x.length, x, 1 );
 // returns 1.0
 ```
 
 The function has the following parameters:
 
 -   **N**: number of indexed elements.
 -   **x**: input [`Float32Array`][@stdlib/array/float32].
--   **stride**: index increment for `x`.
+-   **strideX**: stride length for `x`.
 
-The `N` and stride parameters determine which elements in the strided array are accessed at runtime. For example, to compute the sum of every other element in `x`,
+The `N` and stride parameters determine which elements in the strided array are accessed at runtime. For example, to compute the sum of every other element:
 
 ```javascript
 var Float32Array = require( '@stdlib/array/float32' );
@@ -81,25 +80,24 @@ var v = ssumpw( 4, x1, 2 );
 // returns 5.0
 ```
 
-#### ssumpw.ndarray( N, x, stride, offset )
+#### ssumpw.ndarray( N, x, strideX, offsetX )
 
 Computes the sum of single-precision floating-point strided array elements using pairwise summation and alternative indexing semantics.
 
 ```javascript
 var Float32Array = require( '@stdlib/array/float32' );
 
 var x = new Float32Array( [ 1.0, -2.0, 2.0 ] );
-var N = x.length;
 
-var v = ssumpw.ndarray( N, x, 1, 0 );
+var v = ssumpw.ndarray( x.length, x, 1, 0 );
 // returns 1.0
 ```
 
 The function has the following additional parameters:
 
--   **offset**: starting index for `x`.
+-   **offsetX**: starting index for `x`.
 
-While [`typed array`][mdn-typed-array] views mandate a view offset based on the underlying `buffer`, the `offset` parameter supports indexing semantics based on a starting index. For example, to calculate the sum of every other value in `x` starting from the second value
+While [`typed array`][mdn-typed-array] views mandate a view offset based on the underlying buffer, the offset parameter supports indexing semantics based on a starting index. For example, to calculate the sum of every other element starting from the second element:
 
 ```javascript
 var Float32Array = require( '@stdlib/array/float32' );
@@ -147,6 +145,123 @@ console.log( v );
 
 <!-- /.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/ssumpw.h"
+```
+
+#### stdlib_strided_ssumpw( N, \*X, strideX )
+
+Computes the sum of single-precision floating-point strided array elements using pairwise summation.
+
+```c
+const float x[] = { 1.0f, -2.0f, 2.0f };
+
+double v = stdlib_strided_ssumpw( 3, x, 1 );
+// returns 1.0
+```
+
+The function accepts the following arguments:
+
+-   **N**: `[in] CBLAS_INT` number of indexed elements.
+-   **X**: `[in] float*` input array.
+-   **strideX**: `[in] CBLAS_INT` stride length for `X`.
+
+```c
+double stdlib_strided_ssumpw( const CBLAS_INT N, const float *X, const CBLAS_INT strideX );
+```
+
+#### stdlib_strided_ssumpw_ndarray( N, \*X, strideX, offsetX )
+
+Computes the sum of single-precision floating-point strided array elements using pairwise summation and alternative indexing semantics.
+
+```c
+const float x[] = { 1.0f, -2.0f, 2.0f };
+
+double v = stdlib_strided_ssumpw_ndarray( 3, x, 1, 0 );
+// returns 1.0
+```
+
+The function accepts the following arguments:
+
+-   **N**: `[in] CBLAS_INT` number of indexed elements.
+-   **X**: `[in] float*` input array.
+-   **strideX**: `[in] CBLAS_INT` stride length for `X`.
+-   **offsetX**: `[in] CBLAS_INT` starting index for `X`.
+
+```c
+double stdlib_strided_ssumpw_ndarray( const CBLAS_INT N, const float *X, const CBLAS_INT strideX, const CBLAS_INT offsetX );
+```
+
+</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/ssumpw.h"
+#include <stdio.h>
+
+int main( void ) {
+    // Create a strided array:
+    const float x[] = { 1.0f, 2.0f, 3.0f, 4.0f, 5.0f, 6.0f, 7.0f, 8.0f };
+
+    // Specify the number of elements:
+    const int N = 4;
+
+    // Specify the stride length:
+    const int strideX = 2;
+
+    // Compute the sum:
+    float v = stdlib_strided_ssumpw( N, x, strideX );
+
+    // Print the result:
+    printf( "sum: %f\n", v );
+}
+```
+
+</section>
+
+<!-- /.examples -->
+
+</section>
+
+<!-- /.c -->
+
 * * *
 
 <section class="references">

diff --git a/lib/node_modules/@stdlib/blas/ext/base/ssumpw/benchmark/c/benchmark.length.c b/lib/node_modules/@stdlib/blas/ext/base/ssumpw/benchmark/c/benchmark.length.c
@@ -94,7 +94,7 @@ static float rand_float( 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;
 	float x[ len ];
 	float v;
@@ -107,6 +107,7 @@ static double benchmark( int iterations, int len ) {
 	v = 0.0f;
 	t = tic();
 	for ( i = 0; i < iterations; i++ ) {
+		// cppcheck-suppress uninitvar
 		v = stdlib_strided_ssumpw( len, x, 1 );
 		if ( v != v ) {
 			printf( "should not return NaN\n" );
@@ -120,6 +121,40 @@ static double benchmark( int iterations, int len ) {
 	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;
+	float x[ len ];
+	double v;
+	double t;
+	int i;
+
+	for ( i = 0; i < len; i++ ) {
+		x[ i ] = ( rand_float()*20000.0f ) - 10000.0f;
+	}
+	v = 0.0f;
+	t = tic();
+	for ( i = 0; i < iterations; i++ ) {
+		// cppcheck-suppress uninitvar
+		v = stdlib_strided_ssumpw_ndarray( len, x, 1, 0 );
+		if ( v != v ) {
+			printf( "should not return NaN\n" );
+			break;
+		}
+	}
+	elapsed = tic() - t;
+	if ( v != v ) {
+		printf( "should not return NaN\n" );
+	}
+	return elapsed;
+}
+
 /**
 * Main execution sequence.
 */
@@ -142,7 +177,18 @@ 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/ssumpw/docs/repl.txt b/lib/node_modules/@stdlib/blas/ext/base/ssumpw/docs/repl.txt
@@ -1,10 +1,10 @@
 
-{{alias}}( N, x, stride )
+{{alias}}( N, x, strideX )
     Computes the sum of single-precision floating-point strided array elements
     using pairwise summation.
 
-    The `N` and `stride` parameters determine which elements in the strided
-    array are accessed at runtime.
+    The `N` and stride parameters determine which elements in the strided array
+    are accessed at runtime.
 
     Indexing is relative to the first index. To introduce an offset, use a typed
     array view.
@@ -19,8 +19,8 @@
     x: Float32Array
         Input array.
 
-    stride: integer
-        Index increment.
+    strideX: integer
+        Stride length.
 
     Returns
     -------
@@ -34,7 +34,7 @@
     > {{alias}}( x.length, x, 1 )
     1.0
 
-    // Using `N` and `stride` parameters:
+    // Using `N` and stride parameters:
     > x = new {{alias:@stdlib/array/float32}}( [ -2.0, 1.0, 1.0, -5.0, 2.0, -1.0 ] );
     > {{alias}}( 3, x, 2 )
     1.0
@@ -46,12 +46,12 @@
     -1.0
 
 
-{{alias}}.ndarray( N, x, stride, offset )
+{{alias}}.ndarray( N, x, strideX, offsetX )
     Computes the sum of single-precision floating-point strided array 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
+    buffer, the offset parameter supports indexing semantics based on a
     starting index.
 
     Parameters
@@ -62,10 +62,10 @@
     x: Float32Array
         Input array.
 
-    stride: integer
-        Index increment.
+    strideX: integer
+        Stride length.
 
-    offset: integer
+    offsetX: integer
         Starting index.
 
     Returns

diff --git a/lib/node_modules/@stdlib/blas/ext/base/ssumpw/docs/types/index.d.ts b/lib/node_modules/@stdlib/blas/ext/base/ssumpw/docs/types/index.d.ts
@@ -27,7 +27,7 @@ interface Routine {
 	*
 	* @param N - number of indexed elements
 	* @param x - input array
-	* @param stride - stride length
+	* @param strideX - stride length
 	* @returns sum
 	*
 	* @example
@@ -38,15 +38,15 @@ interface Routine {
 	* var v = ssumpw( x.length, x, 1 );
 	* // returns 1.0
 	*/
-	( N: number, x: Float32Array, stride: number ): number;
+	( N: number, x: Float32Array, strideX: number ): number;
 
 	/**
 	* Computes the sum of single-precision floating-point strided array elements using pairwise summation and alternative indexing semantics.
 	*
 	* @param N - number of indexed elements
 	* @param x - input array
-	* @param stride - stride length
-	* @param offset - starting index
+	* @param strideX - stride length
+	* @param offsetX - starting index
 	* @returns sum
 	*
 	* @example
@@ -57,15 +57,15 @@ interface Routine {
 	* var v = ssumpw.ndarray( x.length, x, 1, 0 );
 	* // returns 1.0
 	*/
-	ndarray( N: number, x: Float32Array, stride: number, offset: number ): number;
+	ndarray( N: number, x: Float32Array, strideX: number, offsetX: number ): number;
 }
 
 /**
 * Computes the sum of single-precision floating-point strided array elements using pairwise summation.
 *
 * @param N - number of indexed elements
 * @param x - input array
-* @param stride - stride length
+* @param strideX - stride length
 * @returns sum
 *
 * @example

diff --git a/lib/node_modules/@stdlib/blas/ext/base/ssumpw/examples/c/example.c b/lib/node_modules/@stdlib/blas/ext/base/ssumpw/examples/c/example.c
@@ -17,21 +17,20 @@
 */
 
 #include "stdlib/blas/ext/base/ssumpw.h"
-#include <stdint.h>
 #include <stdio.h>
 
 int main( void ) {
 	// Create a strided array:
-	const float x[] = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0 };
+	const float x[] = { 1.0f, 2.0f, 3.0f, 4.0f, 5.0f, 6.0f, 7.0f, 8.0f };
 
 	// Specify the number of elements:
-	const int64_t N = 4;
+	const int N = 4;
 
 	// Specify the stride length:
-	const int64_t stride = 2;
+	const int strideX = 2;
 
 	// Compute the sum:
-	float v = stdlib_strided_ssumpw( N, x, stride );
+	float v = stdlib_strided_ssumpw( N, x, strideX );
 
 	// Print the result:
 	printf( "sum: %f\n", v );