| Name |
Description |
| BenchmarkActivity |
|
| CommandLine |
Scimark_Csharp_Android: A Java numerical benchmark measuring performance of computational kernels for FFTs, Monte Carlo simulation, sparse matrix computations, Jacobi SOR, and dense LU matrix factorizations. |
| Constants |
|
| FFT |
Computes FFT's of complex, double precision data where n is an integer power of 2. This appears to be slower than the Radix2 method, but the code is smaller and simpler, and it requires no extra storage. |
| LU |
LU matrix factorization. (Based on TNT implementation.) Decomposes a matrix A into a triangular lower triangular factor (L) and an upper triangular factor (U) such that A = L*U. By convnetion, the main diagonal of L consists of 1's so that L and U can be stored compactly in a NxN matrix. |
| MonteCarlo |
Estimate Pi by approximating the area of a circle. How: generate N random numbers in the unit square, (0,0) to (1,1) and see how are within a radius of 1 or less, i.e. sqrt(x^2 + y^2) < r since the radius is 1.0, we can square both sides and avoid a sqrt() computation: x^2 + y^2 <= 1.0 this area under the curve is (Pi * r^2)/ 4.0, and the area of the unit of square is 1.0, so Pi can be approximated by # points with x^2+y^2 < 1 Pi =~ -------------------------- * 4.0 total # points |
| Random |
|
| Resource.Attribute |
|
| Resource.Drawable |
|
| Resource.Id |
|
| Resource.Layout |
|
| Resource.String |
|
| SOR |
|
| SparseCompRow |
|
| Stopwatch |
Provides a stopwatch to measure elapsed time. |
| kernel |
|