http://www.revolutionanalytics.com/products/enterprise-performance.php
NEED MORE SPEED?
Benchmarks show Revolution R Enterprise is significantly faster than open source R for many real-world computations. Linked with high-performance multi-threaded math libraries, Revolution R Enterprise automatically reduces computation times when using multi-core and multi-processor hardware.Quick Links:
- Revolutionary Performance — Speed Up Your Performance with Revolution R!
- Revolution R Enterprise ‘Big Data’ Benchmarks Whitepaper
Take immediate advantage of:
- Significant speed enhancements over open source R.
- 64-Bit Scalability: Analyze larger data sets on 64-bit Windows and Linux systems.
- Parallel Processing Power: Reduce computation time for simulations, optimizations, segmented data analysis and more.
Revolution R 5.0 Performance Benchmarks
The benchmarks on this page demonstrate the performance of Revolution R 6.0 compared to the base version of R-2.14.2, available from the R Project. The test system was an Intel® Xeon® Processor X3440 (2.53 GHz) with 8GB System RAM running 32-bit Windows Server 2008 R2 SP1.One of the differences between Revolution R products and base R is the ability to leverage multithreading and processor capabilities on all x86 platforms to increase performance. Thus, the more cores available to Revolution R, the higher your performance for many operations.
Revolution Analytics has created these tests to simulate common real-world computations.
Base R 2.14.2 | Revolution R (1-core) | Revolution R (4-core) | Speedup (4 core) | |
Matrix Multiply | 175.4 sec | 28.9 sec | 9.3 sec | 17.9x |
Cholesky Factorization | 25.5 sec | 4.6 sec | 1.3 sec | 18.7x |
Singular Value Decomposition | 58.7 sec | 16.8 sec | 7.2 sec | 7.1x |
Principal Components Analysis | 228.4 sec | 50.8 sec | 19.4 sec | 10.8x |
Linear Discriminant Analysis | 189.1 sec | 73.7 sec | 52.3 sec | 2.6x |
More information: