+ Press n or j to go to the next uncovered block, b, p or k for the previous block. +
+ +| File | ++ | Statements | ++ | Branches | ++ | Functions | ++ | Lines | ++ |
|---|---|---|---|---|---|---|---|---|---|
| index.js | +
+
+ |
+ 100% | +69/69 | +100% | +3/3 | +100% | +0/0 | +100% | +69/69 | +
| main.js | +
+
+ |
+ 100% | +35/35 | +100% | +1/1 | +100% | +0/0 | +100% | +35/35 | +
| native.js | +
+
+ |
+ 100% | +35/35 | +100% | +1/1 | +100% | +0/0 | +100% | +35/35 | +
| ndarray.js | +
+
+ |
+ 100% | +134/134 | +100% | +14/14 | +100% | +1/1 | +100% | +134/134 | +
| ndarray.native.js | +
+
+ |
+ 89.47% | +51/57 | +100% | +1/1 | +0% | +0/1 | +89.47% | +51/57 | +
| ssumpw.js | +
+
+ |
+ 100% | +85/85 | +100% | +13/13 | +100% | +1/1 | +100% | +85/85 | +
| ssumpw.native.js | +
+
+ |
+ 94.23% | +49/52 | +100% | +1/1 | +0% | +0/1 | +94.23% | +49/52 | +
+ Press n or j to go to the next uncovered block, b, p or k for the previous block. +
+ +| 1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33 +34 +35 +36 +37 +38 +39 +40 +41 +42 +43 +44 +45 +46 +47 +48 +49 +50 +51 +52 +53 +54 +55 +56 +57 +58 +59 +60 +61 +62 +63 +64 +65 +66 +67 +68 +69 +70 | 3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +2x +3x +1x +1x +3x +3x +3x +3x +3x +3x +3x + | /**
+* @license Apache-2.0
+*
+* Copyright (c) 2024 The Stdlib Authors.
+*
+* Licensed under the Apache License, Version 2.0 (the "License");
+* you may not use this file except in compliance with the License.
+* You may obtain a copy of the License at
+*
+* http://www.apache.org/licenses/LICENSE-2.0
+*
+* Unless required by applicable law or agreed to in writing, software
+* distributed under the License is distributed on an "AS IS" BASIS,
+* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+* See the License for the specific language governing permissions and
+* limitations under the License.
+*/
+
+'use strict';
+
+/**
+* Compute the sum of single-precision floating-point strided array elements using pairwise summation.
+*
+* @module @stdlib/blas/ext/base/ssumpw
+*
+* @example
+* var Float32Array = require( '@stdlib/array/float32' );
+* var ssumpw = require( '@stdlib/blas/ext/base/ssumpw' );
+*
+* var x = new Float32Array( [ 1.0, -2.0, 2.0 ] );
+* var N = x.length;
+*
+* var v = ssumpw( N, x, 1 );
+* // returns 1.0
+*
+* @example
+* var Float32Array = require( '@stdlib/array/float32' );
+* var ssumpw = require( '@stdlib/blas/ext/base/ssumpw' );
+*
+* var x = new Float32Array( [ 2.0, 1.0, 2.0, -2.0, -2.0, 2.0, 3.0, 4.0 ] );
+*
+* var v = ssumpw.ndarray( 4, x, 2, 1 );
+* // returns 5.0
+*/
+
+// MODULES //
+
+var join = require( 'path' ).join;
+var tryRequire = require( '@stdlib/utils/try-require' );
+var isError = require( '@stdlib/assert/is-error' );
+var main = require( './main.js' );
+
+
+// MAIN //
+
+var ssumpw;
+var tmp = tryRequire( join( __dirname, './native.js' ) );
+if ( isError( tmp ) ) {
+ ssumpw = main;
+} else {
+ ssumpw = tmp;
+}
+
+
+// EXPORTS //
+
+module.exports = ssumpw;
+
+// exports: { "ndarray": "ssumpw.ndarray" }
+ |
+ Press n or j to go to the next uncovered block, b, p or k for the previous block. +
+ +| 1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33 +34 +35 +36 | 1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x + | /** +* @license Apache-2.0 +* +* Copyright (c) 2020 The Stdlib Authors. +* +* Licensed under the Apache License, Version 2.0 (the "License"); +* you may not use this file except in compliance with the License. +* You may obtain a copy of the License at +* +* http://www.apache.org/licenses/LICENSE-2.0 +* +* Unless required by applicable law or agreed to in writing, software +* distributed under the License is distributed on an "AS IS" BASIS, +* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +* See the License for the specific language governing permissions and +* limitations under the License. +*/ + +'use strict'; + +// MODULES // + +var setReadOnly = require( '@stdlib/utils/define-nonenumerable-read-only-property' ); +var ssumpw = require( './ssumpw.js' ); +var ndarray = require( './ndarray.js' ); + + +// MAIN // + +setReadOnly( ssumpw, 'ndarray', ndarray ); + + +// EXPORTS // + +module.exports = ssumpw; + |
+ Press n or j to go to the next uncovered block, b, p or k for the previous block. +
+ +| 1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33 +34 +35 +36 | 1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x + | /** +* @license Apache-2.0 +* +* Copyright (c) 2020 The Stdlib Authors. +* +* Licensed under the Apache License, Version 2.0 (the "License"); +* you may not use this file except in compliance with the License. +* You may obtain a copy of the License at +* +* http://www.apache.org/licenses/LICENSE-2.0 +* +* Unless required by applicable law or agreed to in writing, software +* distributed under the License is distributed on an "AS IS" BASIS, +* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +* See the License for the specific language governing permissions and +* limitations under the License. +*/ + +'use strict'; + +// MODULES // + +var setReadOnly = require( '@stdlib/utils/define-nonenumerable-read-only-property' ); +var ssumpw = require( './ssumpw.native.js' ); +var ndarray = require( './ndarray.native.js' ); + + +// MAIN // + +setReadOnly( ssumpw, 'ndarray', ndarray ); + + +// EXPORTS // + +module.exports = ssumpw; + |
+ Press n or j to go to the next uncovered block, b, p or k for the previous block. +
+ +| 1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33 +34 +35 +36 +37 +38 +39 +40 +41 +42 +43 +44 +45 +46 +47 +48 +49 +50 +51 +52 +53 +54 +55 +56 +57 +58 +59 +60 +61 +62 +63 +64 +65 +66 +67 +68 +69 +70 +71 +72 +73 +74 +75 +76 +77 +78 +79 +80 +81 +82 +83 +84 +85 +86 +87 +88 +89 +90 +91 +92 +93 +94 +95 +96 +97 +98 +99 +100 +101 +102 +103 +104 +105 +106 +107 +108 +109 +110 +111 +112 +113 +114 +115 +116 +117 +118 +119 +120 +121 +122 +123 +124 +125 +126 +127 +128 +129 +130 +131 +132 +133 +134 +135 | 3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +73x +73x +73x +73x +73x +73x +73x +73x +73x +73x +73x +73x +73x +73x +73x +73x +2x +2x +73x +2x +2x +69x +73x +7x +7x +7x +26x +26x +26x +7x +7x +73x +34x +34x +34x +34x +34x +34x +34x +34x +34x +34x +34x +34x +34x +468x +468x +468x +468x +468x +468x +468x +468x +468x +468x +34x +34x +34x +34x +34x +2x +2x +2x +34x +34x +28x +28x +28x +28x +73x +3x +3x +3x +3x +3x + | /**
+* @license Apache-2.0
+*
+* Copyright (c) 2024 The Stdlib Authors.
+*
+* Licensed under the Apache License, Version 2.0 (the "License");
+* you may not use this file except in compliance with the License.
+* You may obtain a copy of the License at
+*
+* http://www.apache.org/licenses/LICENSE-2.0
+*
+* Unless required by applicable law or agreed to in writing, software
+* distributed under the License is distributed on an "AS IS" BASIS,
+* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+* See the License for the specific language governing permissions and
+* limitations under the License.
+*/
+
+'use strict';
+
+// MODULES //
+
+var float64ToFloat32 = require( '@stdlib/number/float64/base/to-float32' );
+var floor = require( '@stdlib/math/base/special/floor' );
+
+
+// VARIABLES //
+
+// Blocksize for pairwise summation (NOTE: decreasing the blocksize decreases rounding error as more pairs are summed, but also decreases performance. Because the inner loop is unrolled eight times, the blocksize is effectively `16`.):
+var BLOCKSIZE = 128;
+
+
+// MAIN //
+
+/**
+* Computes the sum of single-precision floating-point strided array elements using pairwise summation.
+*
+* ## Method
+*
+* - This implementation uses pairwise summation, which accrues rounding error `O(log2 N)` instead of `O(N)`. The recursion depth is also `O(log2 N)`.
+*
+* ## References
+*
+* - Higham, Nicholas J. 1993. "The Accuracy of Floating Point Summation." _SIAM Journal on Scientific Computing_ 14 (4): 783–99. doi:[10.1137/0914050](https://doi.org/10.1137/0914050).
+*
+* @param {PositiveInteger} N - number of indexed elements
+* @param {Float32Array} x - input array
+* @param {integer} stride - stride length
+* @param {NonNegativeInteger} offset - starting index
+* @returns {number} sum
+*
+* @example
+* var Float32Array = require( '@stdlib/array/float32' );
+*
+* var x = new Float32Array( [ 2.0, 1.0, 2.0, -2.0, -2.0, 2.0, 3.0, 4.0 ] );
+*
+* var v = ssumpw( 4, x, 2, 1 );
+* // returns 5.0
+*/
+function ssumpw( N, x, stride, offset ) {
+ var ix;
+ var s0;
+ var s1;
+ var s2;
+ var s3;
+ var s4;
+ var s5;
+ var s6;
+ var s7;
+ var M;
+ var s;
+ var n;
+ var i;
+
+ if ( N <= 0 ) {
+ return 0.0;
+ }
+ if ( N === 1 || stride === 0 ) {
+ return x[ offset ];
+ }
+ ix = offset;
+ if ( N < 8 ) {
+ // Use simple summation...
+ s = 0.0;
+ for ( i = 0; i < N; i++ ) {
+ s = float64ToFloat32( s + x[ ix ] );
+ ix += stride;
+ }
+ return s;
+ }
+ if ( N <= BLOCKSIZE ) {
+ // Sum a block with 8 accumulators (by loop unrolling, we lower the effective blocksize to 16)...
+ s0 = x[ ix ];
+ s1 = x[ ix+stride ];
+ s2 = x[ ix+(2*stride) ];
+ s3 = x[ ix+(3*stride) ];
+ s4 = x[ ix+(4*stride) ];
+ s5 = x[ ix+(5*stride) ];
+ s6 = x[ ix+(6*stride) ];
+ s7 = x[ ix+(7*stride) ];
+ ix += 8 * stride;
+
+ M = N % 8;
+ for ( i = 8; i < N-M; i += 8 ) {
+ s0 = float64ToFloat32( s0 + x[ ix ] );
+ s1 = float64ToFloat32( s1 + x[ ix+stride ] );
+ s2 = float64ToFloat32( s2 + x[ ix+(2*stride) ] );
+ s3 = float64ToFloat32( s3 + x[ ix+(3*stride) ] );
+ s4 = float64ToFloat32( s4 + x[ ix+(4*stride) ] );
+ s5 = float64ToFloat32( s5 + x[ ix+(5*stride) ] );
+ s6 = float64ToFloat32( s6 + x[ ix+(6*stride) ] );
+ s7 = float64ToFloat32( s7 + x[ ix+(7*stride) ] );
+ ix += 8 * stride;
+ }
+ // Pairwise sum the accumulators:
+ s = float64ToFloat32( float64ToFloat32( float64ToFloat32(s0+s1) + float64ToFloat32(s2+s3) ) + float64ToFloat32( float64ToFloat32(s4+s5) + float64ToFloat32(s6+s7) ) ); // eslint-disable-line max-len
+
+ // Clean-up loop...
+ for ( i; i < N; i++ ) {
+ s = float64ToFloat32( s + x[ ix ] );
+ ix += stride;
+ }
+ return s;
+ }
+ // Recurse by dividing by two, but avoiding non-multiples of unroll factor...
+ n = floor( N/2 );
+ n -= n % 8;
+ return float64ToFloat32( ssumpw( n, x, stride, ix ) + ssumpw( N-n, x, stride, ix+(n*stride) ) ); // eslint-disable-line max-len
+}
+
+
+// EXPORTS //
+
+module.exports = ssumpw;
+ |
+ Press n or j to go to the next uncovered block, b, p or k for the previous block. +
+ +| 1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33 +34 +35 +36 +37 +38 +39 +40 +41 +42 +43 +44 +45 +46 +47 +48 +49 +50 +51 +52 +53 +54 +55 +56 +57 +58 | 1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x +1x + + + + + + +1x +1x +1x +1x +1x + | /**
+* @license Apache-2.0
+*
+* Copyright (c) 2024 The Stdlib Authors.
+*
+* Licensed under the Apache License, Version 2.0 (the "License");
+* you may not use this file except in compliance with the License.
+* You may obtain a copy of the License at
+*
+* http://www.apache.org/licenses/LICENSE-2.0
+*
+* Unless required by applicable law or agreed to in writing, software
+* distributed under the License is distributed on an "AS IS" BASIS,
+* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+* See the License for the specific language governing permissions and
+* limitations under the License.
+*/
+
+'use strict';
+
+// MODULES //
+
+var minViewBufferIndex = require( '@stdlib/strided/base/min-view-buffer-index' );
+var offsetView = require( '@stdlib/strided/base/offset-view' );
+var addon = require( './ssumpw.native.js' );
+
+
+// MAIN //
+
+/**
+* Computes the sum of single-precision floating-point strided array elements using pairwise summation.
+*
+* @param {PositiveInteger} N - number of indexed elements
+* @param {Float32Array} x - input array
+* @param {integer} stride - stride length
+* @param {NonNegativeInteger} offset - starting index
+* @returns {number} sum
+*
+* @example
+* var Float32Array = require( '@stdlib/array/float32' );
+*
+* var x = new Float32Array( [ 2.0, 1.0, 2.0, -2.0, -2.0, 2.0, 3.0, 4.0 ] );
+*
+* var v = ssumpw( 4, x, 2, 1 );
+* // returns 5.0
+*/
+function ssumpw( N, x, stride, offset ) {
+ var view;
+ offset = minViewBufferIndex( N, stride, offset );
+ view = offsetView( x, offset );
+ return addon( N, view, stride );
+}
+
+
+// EXPORTS //
+
+module.exports = ssumpw;
+ |
+ Press n or j to go to the next uncovered block, b, p or k for the previous block. +
+ +| 1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33 +34 +35 +36 +37 +38 +39 +40 +41 +42 +43 +44 +45 +46 +47 +48 +49 +50 +51 +52 +53 +54 +55 +56 +57 +58 +59 +60 +61 +62 +63 +64 +65 +66 +67 +68 +69 +70 +71 +72 +73 +74 +75 +76 +77 +78 +79 +80 +81 +82 +83 +84 +85 +86 | 2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +2x +14x +14x +14x +14x +14x +14x +2x +2x +14x +2x +2x +14x +2x +14x +8x +8x +14x +7x +7x +7x +26x +26x +26x +7x +7x +3x +14x +2x +2x +2x +2x +2x + | /**
+* @license Apache-2.0
+*
+* Copyright (c) 2020 The Stdlib Authors.
+*
+* Licensed under the Apache License, Version 2.0 (the "License");
+* you may not use this file except in compliance with the License.
+* You may obtain a copy of the License at
+*
+* http://www.apache.org/licenses/LICENSE-2.0
+*
+* Unless required by applicable law or agreed to in writing, software
+* distributed under the License is distributed on an "AS IS" BASIS,
+* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+* See the License for the specific language governing permissions and
+* limitations under the License.
+*/
+
+'use strict';
+
+// MODULES //
+
+var float64ToFloat32 = require( '@stdlib/number/float64/base/to-float32' );
+var sum = require( './ndarray.js' );
+
+
+// MAIN //
+
+/**
+* Computes the sum of single-precision floating-point strided array elements using pairwise summation.
+*
+* ## Method
+*
+* - This implementation uses pairwise summation, which accrues rounding error `O(log2 N)` instead of `O(N)`. The recursion depth is also `O(log2 N)`.
+*
+* ## References
+*
+* - Higham, Nicholas J. 1993. "The Accuracy of Floating Point Summation." _SIAM Journal on Scientific Computing_ 14 (4): 783–99. doi:[10.1137/0914050](https://doi.org/10.1137/0914050).
+*
+* @param {PositiveInteger} N - number of indexed elements
+* @param {Float32Array} x - input array
+* @param {integer} stride - stride length
+* @returns {number} sum
+*
+* @example
+* 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 );
+* // returns 1.0
+*/
+function ssumpw( N, x, stride ) {
+ var ix;
+ var s;
+ var i;
+
+ if ( N <= 0 ) {
+ return 0.0;
+ }
+ if ( N === 1 || stride === 0 ) {
+ return x[ 0 ];
+ }
+ if ( stride < 0 ) {
+ ix = (1-N) * stride;
+ } else {
+ ix = 0;
+ }
+ if ( N < 8 ) {
+ // Use simple summation...
+ s = 0.0;
+ for ( i = 0; i < N; i++ ) {
+ s = float64ToFloat32( s + x[ ix ] );
+ ix += stride;
+ }
+ return s;
+ }
+ return sum( N, x, stride, ix );
+}
+
+
+// EXPORTS //
+
+module.exports = ssumpw;
+ |
+ Press n or j to go to the next uncovered block, b, p or k for the previous block. +
+ +| 1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33 +34 +35 +36 +37 +38 +39 +40 +41 +42 +43 +44 +45 +46 +47 +48 +49 +50 +51 +52 +53 | 3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x +3x + + + +3x +3x +3x +3x +3x + | /**
+* @license Apache-2.0
+*
+* Copyright (c) 2020 The Stdlib Authors.
+*
+* Licensed under the Apache License, Version 2.0 (the "License");
+* you may not use this file except in compliance with the License.
+* You may obtain a copy of the License at
+*
+* http://www.apache.org/licenses/LICENSE-2.0
+*
+* Unless required by applicable law or agreed to in writing, software
+* distributed under the License is distributed on an "AS IS" BASIS,
+* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+* See the License for the specific language governing permissions and
+* limitations under the License.
+*/
+
+'use strict';
+
+// MODULES //
+
+var addon = require( './../src/addon.node' );
+
+
+// MAIN //
+
+/**
+* Computes the sum of single-precision floating-point strided array elements using pairwise summation.
+*
+* @param {PositiveInteger} N - number of indexed elements
+* @param {Float32Array} x - input array
+* @param {integer} stride - stride length
+* @returns {number} sum
+*
+* @example
+* 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 );
+* // returns 1.0
+*/
+function ssumpw( N, x, stride ) {
+ return addon( N, x, stride );
+}
+
+
+// EXPORTS //
+
+module.exports = ssumpw;
+ |