feat: add C ndarray implementation for sscal

Author: aman-095

lib/node_modules/@stdlib/blas/base/sscal/README.md

@@ -77,7 +77,7 @@ sscal( 3, 5.0, x1, 2 );
 // x0 => <Float32Array>[ 1.0, -10.0, 3.0, -20.0, 5.0, -30.0 ]
 ```
 
-If either `N` or `stride` is less than or equal to `0`, the function returns `x` unchanged.
+If either `N` is less than or equal to `0`, the function returns `x` unchanged.
 
 #### sscal.ndarray( N, alpha, x, stride, offset )
 
@@ -146,6 +146,133 @@ console.log( x );
 
 <!-- /.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/base/sscal.h"
+```
+
+#### c_sscal( N, alpha, \*X, stride )
+
+Multiplies each element of a single-precision floating-point vector by a constant.
+
+```c
+float x[] = { 1.0f, 2.0f, 3.0f, 4.0f };
+
+c_sscal( 4, 5.0f, x, 1 );
+```
+
+The function accepts the following arguments:
+
+-   **N**: `[in] CBLAS_INT` number of indexed elements.
+-   **alpha**: `[in] float` scalar constant.
+-   **X**: `[inout] float*` input array.
+-   **stride**: `[in] CBLAS_INT` index increment for `X`.
+
+```c
+void c_sscal( const CBLAS_INT N, const float alpha, float *X, const CBLAS_INT stride );
+```
+
+#### c_sscal_ndarray( N, alpha, \*X, stride, offset )
+
+Multiplies each element of a single-precision floating-point vector by a constant using alternative indexing semantics.
+
+```c
+float x[] = { 1.0f, 2.0f, 3.0f, 4.0f };
+
+c_sscal_ndarray( 4, 5.0f, x, 1, 0 );
+```
+
+The function accepts the following arguments:
+
+-   **N**: `[in] CBLAS_INT` number of indexed elements.
+-   **alpha**: `[in] float` scalar constant.
+-   **X**: `[inout] float*` input array.
+-   **stride**: `[in] CBLAS_INT` index increment for `X`.
+-   **offset**: `[in] CBLAS_INT` starting index for `X`.
+
+```c
+void c_sscal_ndarray( const CBLAS_INT N, const float alpha, float *X, const CBLAS_INT stride, const CBLAS_INT offset );
+```
+
+</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/base/sscal.h"
+#include <stdio.h>
+
+int main( void ) {
+    // Create a strided array:
+    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 = 8;
+
+    // Specify a stride:
+    const int stride = 1;
+
+    // Scale the vector:
+    c_sscal( N, 5.0f, x, stride );
+
+    // Print the result:
+    for ( int i = 0; i < 8; i++ ) {
+        printf( "x[ %i ] = %f\n", i, x[ i ] );
+    }
+
+    // Scale the vector:
+    c_sscal_ndarray( N, 5.0f, x, -stride, N-1 );
+
+    // Print the result:
+    for ( int i = 0; i < 8; i++ ) {
+        printf( "x[ %i ] = %f\n", i, x[ i ] );
+    }
+}
+```
+
+</section>
+
+<!-- /.examples -->
+
+</section>
+
+<!-- /.c -->
+
 <!-- Section for related `stdlib` packages. Do not manually edit this section, as it is automatically populated. -->
 
 <section class="related">

lib/node_modules/@stdlib/blas/base/sscal/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 ];
 	double t;
@@ -118,6 +118,30 @@ static double benchmark( int iterations, int len ) {
 	return elapsed;
 }
 
+static double benchmark2( int iterations, int len ) {
+	double elapsed;
+	float x[ len ];
+	double t;
+	int i;
+
+	for ( i = 0; i < len; i++ ) {
+		x[ i ] = ( rand_float()*200.0f ) - 100.0f;
+	}
+	t = tic();
+	for ( i = 0; i < iterations; i++ ) {
+		c_sscal_ndarray( len, 5.0f, x, 1, 0 );
+		if ( x[ 0 ] != x[ 0 ] ) {
+			printf( "should not return NaN\n" );
+			break;
+		}
+	}
+	elapsed = tic() - t;
+	if ( x[ 0 ] != x[ 0 ] ) {
+		printf( "should not return NaN\n" );
+	}
+	return elapsed;
+}
+
 /**
 * Main execution sequence.
 */
@@ -140,7 +164,14 @@ 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 ( 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 );
 		}

lib/node_modules/@stdlib/blas/base/sscal/docs/repl.txt

@@ -9,7 +9,7 @@
     Indexing is relative to the first index. To introduce an offset, use typed
     array views.
 
-    If `N <= 0` or `stride <= 0`, the function returns `x` unchanged.
+    If `N <= 0` the function returns `x` unchanged.
 
     Parameters
     ----------

lib/node_modules/@stdlib/blas/base/sscal/examples/c/example.c

@@ -36,4 +36,12 @@ int main( void ) {
 	for ( int i = 0; i < 8; i++ ) {
 		printf( "x[ %i ] = %f\n", i, x[ i ] );
 	}
+
+	// Scale the vector using alternative indexing semantics:
+	c_sscal_ndarray( N, 5.0f, x, -strideX, N-1 );
+
+	// Print the result:
+	for ( int i = 0; i < 8; i++ ) {
+		printf( "x[ %i ] = %f\n", i, x[ i ] );
+	}
 }

lib/node_modules/@stdlib/blas/base/sscal/include/stdlib/blas/base/sscal.h

@@ -22,6 +22,8 @@
 #ifndef SSCAL_H
 #define SSCAL_H
 
+#include "stdlib/blas/base/shared.h"
+
 /*
 * If C++, prevent name mangling so that the compiler emits a binary file having undecorated names, thus mirroring the behavior of a C compiler.
 */
@@ -32,7 +34,12 @@ extern "C" {
 /**
 * Multiplies each element of a single-precision floating-point vector by a constant.
 */
-void c_sscal( const int N, const float alpha, float *X, const int stride );
+void API_SUFFIX(c_sscal)( const CBLAS_INT N, const float alpha, float *X, const CBLAS_INT stride );
+
+/**
+* Multiplies each element of a single-precision floating-point vector by a constant using alternative indexing semantics.
+*/
+void API_SUFFIX(c_sscal_ndarray)( const CBLAS_INT N, const float alpha, float *X, const CBLAS_INT stride, const CBLAS_INT offset );
 
 #ifdef __cplusplus
 }

lib/node_modules/@stdlib/blas/base/sscal/include/stdlib/blas/base/sscal_cblas.h

@@ -22,6 +22,8 @@
 #ifndef SSCAL_CLBAS_H
 #define SSCAL_CBLAS_H
 
+#include "stdlib/blas/base/shared.h"
+
 /*
 * If C++, prevent name mangling so that the compiler emits a binary file having undecorated names, thus mirroring the behavior of a C compiler.
 */
@@ -32,7 +34,7 @@ extern "C" {
 /**
 * Multiplies each element of a single-precision floating-point vector by a constant.
 */
-void cblas_sscal( const int N, const float alpha, float *X, const int stride );
+void API_SUFFIX(cblas_sscal)( const CBLAS_INT N, const float alpha, float *X, const CBLAS_INT stride );
 
 #ifdef __cplusplus
 }

lib/node_modules/@stdlib/blas/base/sscal/lib/ndarray.js

@@ -39,9 +39,8 @@ var M = 5;
 * var Float32Array = require( '@stdlib/array/float32' );
 *
 * var x = new Float32Array( [ 1.0, -2.0, 3.0, -4.0, 5.0, -6.0 ] );
-* var alpha = 5.0;
 *
-* sscal( 3, alpha, x, 1, x.length-3 );
+* sscal( 3, 5.0, x, 1, x.length-3 );
 * // x => <Float32Array>[ 1.0, -2.0, 3.0, -20.0, 25.0, -30.0 ]
 */
 function sscal( N, alpha, x, stride, offset ) {

lib/node_modules/@stdlib/blas/base/sscal/lib/ndarray.native.js

@@ -20,9 +20,7 @@
 
 // MODULES //
 
-var minViewBufferIndex = require( '@stdlib/strided/base/min-view-buffer-index' );
-var offsetView = require( '@stdlib/strided/base/offset-view' );
-var addon = require( './sscal.native.js' );
+var addon = require( './../src/addon.node' );
 
 
 // MAIN //
@@ -47,13 +45,7 @@ var addon = require( './sscal.native.js' );
 * // x => <Float32Array>[ 1.0, -2.0, 3.0, -20.0, 25.0, -30.0 ]
 */
 function sscal( N, alpha, x, stride, offset ) {
-	var view;
-	offset = minViewBufferIndex( N, stride, offset );
-	if ( stride < 0 ) {
-		stride *= -1;
-	}
-	view = offsetView( x, offset );
-	addon( N, alpha, view, stride );
+	addon.ndarray( N, alpha, x, stride, offset );
 	return x;
 }
 

lib/node_modules/@stdlib/blas/base/sscal/lib/sscal.js

@@ -18,9 +18,10 @@
 
 'use strict';
 
-// VARIABLES //
+// MODULES //
 
-var M = 5;
+var stride2offset = require( '@stdlib/strided/base/stride2offset' );
+var ndarray = require( './ndarray.js' );
 
 
 // MAIN //
@@ -31,7 +32,7 @@ var M = 5;
 * @param {PositiveInteger} N - number of indexed elements
 * @param {number} alpha - scalar
 * @param {Float32Array} x - input array
-* @param {PositiveInteger} stride - index increment
+* @param {integer} stride - index increment
 * @returns {Float32Array} input array
 *
 * @example
@@ -43,39 +44,8 @@ var M = 5;
 * // x => <Float32Array>[ -10.0, 5.0, 15.0, -25.0, 20.0, 0.0, -5.0, -15.0 ]
 */
 function sscal( N, alpha, x, stride ) {
-	var i;
-	var m;
-
-	if ( N <= 0 || stride <= 0|| alpha === 1.0 ) {
-		return x;
-	}
-	// Use loop unrolling if the stride is equal to `1`...
-	if ( stride === 1 ) {
-		m = N % M;
-
-		// If we have a remainder, run a clean-up loop...
-		if ( m > 0 ) {
-			for ( i = 0; i < m; i++ ) {
-				x[ i ] *= alpha;
-			}
-		}
-		if ( N < M ) {
-			return x;
-		}
-		for ( i = m; i < N; i += M ) {
-			x[ i ] *= alpha;
-			x[ i+1 ] *= alpha;
-			x[ i+2 ] *= alpha;
-			x[ i+3 ] *= alpha;
-			x[ i+4 ] *= alpha;
-		}
-		return x;
-	}
-	N *= stride;
-	for ( i = 0; i < N; i += stride ) {
-		x[ i ] *= alpha;
-	}
-	return x;
+	var ox = stride2offset( N, stride );
+	return ndarray( N, alpha, x, stride, ox );
 }
 
 

lib/node_modules/@stdlib/blas/base/sscal/lib/sscal.native.js

@@ -31,7 +31,7 @@ var addon = require( './../src/addon.node' );
 * @param {PositiveInteger} N - number of indexed elements
 * @param {number} alpha - scalar
 * @param {Float32Array} x - input array
-* @param {PositiveInteger} stride - index increment
+* @param {integer} stride - index increment
 * @returns {Float32Array} input array
 *
 * @example