time-to-botec

Benchmark sampling in different programming languages
Log | Files | Refs | README

dasum.c (1533B)


      1 /**
      2 * @license Apache-2.0
      3 *
      4 * Copyright (c) 2018 The Stdlib Authors.
      5 *
      6 * Licensed under the Apache License, Version 2.0 (the "License");
      7 * you may not use this file except in compliance with the License.
      8 * You may obtain a copy of the License at
      9 *
     10 *    http://www.apache.org/licenses/LICENSE-2.0
     11 *
     12 * Unless required by applicable law or agreed to in writing, software
     13 * distributed under the License is distributed on an "AS IS" BASIS,
     14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     15 * See the License for the specific language governing permissions and
     16 * limitations under the License.
     17 */
     18 
     19 #include "stdlib/blas/base/dasum.h"
     20 #include <math.h>
     21 
     22 /**
     23 * Computes the sum of absolute values.
     24 *
     25 * @param N       number of elements to sum
     26 * @param X       input array
     27 * @param stride  stride length
     28 * @return        sum of absolute values
     29 */
     30 double c_dasum( const int N, const double *X, const int stride ) {
     31 	double sum;
     32 	int m;
     33 	int i;
     34 
     35 	sum = 0.0;
     36 	if ( N <= 0 || stride <= 0 ) {
     37 		return sum;
     38 	}
     39 	// If the stride is equal to `1`, use unrolled loops...
     40 	if ( stride == 1 ) {
     41 		m = N % 6;
     42 
     43 		// If we have a remainder, run a clean-up loop...
     44 		if ( m > 0 ) {
     45 			for ( i = 0; i < m; i++ ) {
     46 				sum += fabs( X[i] );
     47 			}
     48 		}
     49 		if ( N < 6 ) {
     50 			return sum;
     51 		}
     52 		for ( i = m; i < N; i += 6 ) {
     53 			sum += fabs( X[i] ) + fabs( X[i+1] ) + fabs( X[i+2] ) + fabs( X[i+3] ) + fabs( X[i+4] ) + fabs( X[i+5] );
     54 		}
     55 		return sum;
     56 	}
     57 	for ( i = 0; i < N*stride; i += stride ) {
     58 		sum += fabs( X[i] );
     59 	}
     60 	return sum;
     61 }