Skip to content

Commit

Permalink
feat: add C ndarray implementation for blas/base/scopy
Browse files Browse the repository at this point in the history
PR-URL: #2913
Ref: #2039
Co-authored-by: Athan Reines <kgryte@gmail.com>
Reviewed-by: Athan Reines <kgryte@gmail.com> 
Signed-off-by: Athan Reines <kgryte@gmail.com>
  • Loading branch information
aman-095 and kgryte committed Sep 17, 2024
1 parent f51140f commit 08f39b4
Show file tree
Hide file tree
Showing 12 changed files with 424 additions and 92 deletions.
134 changes: 134 additions & 0 deletions lib/node_modules/@stdlib/blas/base/scopy/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,140 @@ 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/base/scopy.h"
```

#### c_scopy( N, \*X, strideX, \*Y, strideY )

Copies values from `X` into `Y`.

```c
const float x[] = { 1.0f, 2.0f, 3.0f, 4.0f };
float y[] = { 0.0f, 0.0f, 0.0f, 0.0f };

c_scopy( 4, x, 1, y, 1 );
```
The function accepts the following arguments:
- **N**: `[in] CBLAS_INT` number of indexed elements.
- **X**: `[in] float*` input array.
- **strideX**: `[in] CBLAS_INT` index increment for `X`.
- **Y**: `[out] float*` output array.
- **strideY**: `[in] CBLAS_INT` index increment for `Y`.
```c
void c_scopy( const CBLAS_INT N, const float *X, const CBLAS_INT strideX, float *Y, const CBLAS_INT strideY );
```

#### c_scopy_ndarray( N, \*X, strideX, offsetX, \*Y, strideY, offsetY )

Copies values from `x` into `y` using alternative indexing semantics.

```c
const float x[] = { 1.0f, 2.0f, 3.0f, 4.0f, 5.0f };
float y[] = { 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };

c_scopy_ndarray( 3, x, 1, 2, y, 1, 2 );
```
The function accepts the following arguments:
- **N**: `[in] CBLAS_INT` number of indexed elements.
- **X**: `[in] float*` input array.
- **strideX**: `[in] CBLAS_INT` index increment for `X`.
- **offsetX**: `[in] CBLAS_INT` starting index for `X`.
- **Y**: `[out] float*` output array.
- **strideY**: `[in] CBLAS_INT` index increment for `Y`.
- **offsetY**: `[in] CBLAS_INT` starting index for `Y`.
```c
void c_scopy_ndarray( const CBLAS_INT N, const float *X, const CBLAS_INT strideX, const CBLAS_INT offsetX, float *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/base/scopy.h"
#include <stdio.h>

int main( void ) {
// Create strided arrays:
const float x[] = { 1.0f, 2.0f, 3.0f, 4.0f, 5.0f, 6.0f, 7.0f, 8.0f };
float y[] = { 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f, 0.0f };

// Specify the number of elements:
const int N = 4;

// Specify stride lengths:
const int strideX = 2;
const int strideY = -2;

// Copy elements:
c_scopy( N, x, strideX, y, strideY );

// Print the result:
for ( int i = 0; i < 8; i++ ) {
printf( "y[ %i ] = %f\n", i, y[ i ] );
}

// Copy elements:
c_scopy_ndarray( N, x, strideX, 0, y, strideY, 6 );

// Print the result:
for ( int i = 0; i < 8; i++ ) {
printf( "y[ %i ] = %f\n", i, y[ i ] );
}
}
```
</section>
<!-- /.examples -->
</section>
<!-- /.c -->
<!-- Section for related `stdlib` packages. Do not manually edit this section, as it is automatically populated. -->
<section class="related">
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -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 y[ len ];
Expand All @@ -120,6 +120,39 @@ 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 ];
float y[ len ];
double t;
int i;

for ( i = 0; i < len; i++ ) {
x[ i ] = ( rand_float()*20000.0f ) - 10000.0f;
y[ i ] = 0.0f;
}
t = tic();
for ( i = 0; i < iterations; i++ ) {
c_scopy_ndarray( len, x, 1, 0, y, 1, 0 );
if ( y[ 0 ] != y[ 0 ] ) {
printf( "should not return NaN\n" );
break;
}
}
elapsed = tic() - t;
if ( y[ 0 ] != y[ 0 ] ) {
printf( "should not return NaN\n" );
}
return elapsed;
}

/**
* Main execution sequence.
*/
Expand All @@ -142,7 +175,14 @@ 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 );
}
Expand Down
8 changes: 8 additions & 0 deletions lib/node_modules/@stdlib/blas/base/scopy/examples/c/example.c
Original file line number Diff line number Diff line change
Expand Up @@ -38,4 +38,12 @@ int main( void ) {
for ( int i = 0; i < 8; i++ ) {
printf( "y[ %i ] = %f\n", i, y[ i ] );
}

// Copy elements:
c_scopy_ndarray( N, x, strideX, 0, y, strideY, 6 );

// Print the result:
for ( int i = 0; i < 8; i++ ) {
printf( "y[ %i ] = %f\n", i, y[ i ] );
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@
#ifndef SCOPY_H
#define SCOPY_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.
*/
Expand All @@ -32,7 +34,12 @@ extern "C" {
/**
* Copies values from `x` into `y`.
*/
void c_scopy( const int N, const float *X, const int strideX, float *Y, const int strideY );
void API_SUFFIX(c_scopy)( const CBLAS_INT N, const float *X, const CBLAS_INT strideX, float *Y, const CBLAS_INT strideY );

/**
* Copies values from `x` into `y` using alternative indexing semantics.
*/
void API_SUFFIX(c_scopy_ndarray)( const CBLAS_INT N, const float *X, const CBLAS_INT strideX, const CBLAS_INT offsetX, float *Y, const CBLAS_INT strideY, const CBLAS_INT offsetY );

#ifdef __cplusplus
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@
#ifndef SCOPY_CBLAS_H
#define SCOPY_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.
*/
Expand All @@ -32,7 +34,7 @@ extern "C" {
/**
* Copies values from `x` into `y`.
*/
void cblas_scopy( const int N, const float *X, const int strideX, float *Y, const int strideY );
void API_SUFFIX(cblas_scopy)( const CBLAS_INT N, const float *X, const CBLAS_INT strideX, float *Y, const CBLAS_INT strideY );

#ifdef __cplusplus
}
Expand Down
15 changes: 2 additions & 13 deletions lib/node_modules/@stdlib/blas/base/scopy/lib/ndarray.native.js
Original file line number Diff line number Diff line change
Expand Up @@ -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( './scopy.native.js' );
var addon = require( './../src/addon.node' );


// MAIN //
Expand All @@ -49,16 +47,7 @@ var addon = require( './scopy.native.js' );
* // y => <Float32Array>[ 1.0, 2.0, 3.0, 4.0, 5.0 ]
*/
function scopy( N, x, strideX, offsetX, y, strideY, offsetY ) {
var viewX;
var viewY;

offsetX = minViewBufferIndex( N, strideX, offsetX );
offsetY = minViewBufferIndex( N, strideY, offsetY );

viewX = offsetView( x, offsetX );
viewY = offsetView( y, offsetY );

addon( N, viewX, strideX, viewY, strideY );
addon.ndarray( N, x, strideX, offsetX, y, strideY, offsetY );
return y;
}

Expand Down
Loading

1 comment on commit 08f39b4

@stdlib-bot
Copy link
Contributor

Choose a reason for hiding this comment

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

Coverage Report

Package Statements Branches Functions Lines
blas/base/scopy $\color{green}414/414$
$\color{green}+100.00\%$
$\color{green}29/29$
$\color{green}+100.00\%$
$\color{green}4/4$
$\color{green}+100.00\%$
$\color{green}414/414$
$\color{green}+100.00\%$

The above coverage report was generated for the changes in this push.

Please sign in to comment.