ssumors.c (1694B)
1 /** 2 * @license Apache-2.0 3 * 4 * Copyright (c) 2020 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/ext/base/ssumors.h" 20 #include <stdint.h> 21 22 /** 23 * Computes the sum of single-precision floating-point strided array elements using ordinary recursive summation. 24 * 25 * @param N number of indexed elements 26 * @param X input array 27 * @param stride stride length 28 * @return output value 29 */ 30 float stdlib_strided_ssumors( const int64_t N, const float *X, const int64_t stride ) { 31 int64_t ix; 32 int64_t m; 33 int64_t i; 34 float sum; 35 36 sum = 0.0f; 37 if ( N <= 0 ) { 38 return sum; 39 } 40 if ( N == 1 || stride == 0 ) { 41 return X[ 0 ]; 42 } 43 // If the stride is equal to `1`, use unrolled loops... 44 if ( stride == 1 ) { 45 m = N % 6; 46 47 // If we have a remainder, run a clean-up loop... 48 if ( m > 0 ) { 49 for ( i = 0; i < m; i++ ) { 50 sum += X[ i ]; 51 } 52 } 53 if ( N < 6 ) { 54 return sum; 55 } 56 for ( i = m; i < N; i += 6 ) { 57 sum += X[i] + X[i+1] + X[i+2] + X[i+3] + X[i+4] + X[i+5]; 58 } 59 return sum; 60 } 61 if ( stride < 0 ) { 62 ix = (1-N) * stride; 63 } else { 64 ix = 0; 65 } 66 for ( i = 0; i < N; i++ ) { 67 sum += X[ ix ]; 68 ix += stride; 69 } 70 return sum; 71 }