SpeedIT Tools: Beyond Acceleration

Official Release

admin — Sat, 17 Jul 2010 23:07:34 +0000

SpeedIT V1.0 has been officially released. See speedit.vratis.com for details.

Update

admin — Fri, 21 May 2010 17:32:55 +0000

Currently, we are preparing the official release. Stay tuned, the web site should be available in a week or two. Apart from that we have started to implement other, more sophisticated solvers.

Thank you for all your interest and helping us with the testing.

SpeedIT eXtreme – Reference Manual

admin — Tue, 23 Mar 2010 11:50:59 +0000

SpeedIT eXtreme – Programmer’s Guide

admin — Tue, 23 Mar 2010 11:47:48 +0000

Release 0.9

admin — Thu, 04 Mar 2010 05:24:02 +0000

We announce that the SpeedIT Toolkit 0.9 has been released. The library has been internally deployed, tested and validated in a real scenario (blood flow in aortic bifurcation, data came from IT’IS Foundation, Switzerland).

If you are interested in our development send us an email at info vratis.com

Testing solvers

admin — Thu, 11 Feb 2010 08:07:50 +0000

Currently we are in the process of testing our iterative solvers (BICGSTAB and CG) with or without preconditioners. The tests are being performed on the same benchmark set of matrices and will include the following tests: for a given matrix we will measure the performance (GFLOPS and speed-up) as a function of iterations that are needed to find a stable solution. The results will be compared to standard CPU implementation of the mentioned solvers, for example in MKL library.

Preliminary tests

admin — Mon, 04 Jan 2010 20:48:45 +0000

Since around 90% of the computational time is devoted to Sparce Matrix Vector Multiplication we focused on testing this operation in the first place. The attached chart presents our results for 23 different matrices with different size, number of NNZ and the structure. As you can see, the performance depends strongly on the matrix structure. This is the reason why we decided to have two seperate kernels for two types of matrices: sparse and denser ones. Please also note that because of the memory transfers & PCIe bottleneck it is not worth to use our solvers only for few iterations.

Perfomance of SpMV Multiplication in Double Precision

Perfomance of SpMV Multiplication in Single Precision

Speed-up GPU vs. CPU

Methodology

Peak performance was calculated as a mean value from 10 runs with the same experimental conditions.
Benchmark matrices where collected from University of Florida Sparse Matrix Collection in CSR format.
Not all of the matrices could be loaded to GPU memory due to its limitations.
CPU denotes a SpMV operation from Intel Math Kernel Library.
GPU denotes our SpMV kernel.
CPU machine: AMD Athlon(tm) 64 X2 Processor 3800+ working at 2010.373 MHz with 3 GB DDR 400 MH (Dual Channel, bandwidth 6,4 GB/s) and Nforce 4 SLI chipset.
GPU machine: NVIDIA GeForce GTX295 (480 SP) with 1792 MB GDDR3 (896 bits) 999 MHz and 223.8 GB/s bandwith on PCI-Express 2.0.
Bandwidth for ONE device measured with utility bandwidthTest from CUDA SDK:
System: Ubuntu 9.10 64bit, NVidia driver version: 190.42, CUDA ver. 2.3

Benchmark Matrices from University of Florida Sparse Matrix Collection

SpeedIT Tools

admin — Thu, 10 Dec 2009 17:02:14 +0000

The SpeedIT Tools library provides a set of accelerated solvers for sparse linear systems of equations. Manifold acceleration, e.g. more than an order of magnitude, is achieved with a single reasonably priced NVIDIA Graphics Processing Unit (GPU) that supporst CUDA and proprietary advanced optimisation techniques. The library can be used in a wide spectrum of domains arising from problems with underlying 2D and 3D geometry, such as computational fluid dynamics, electromagnetics, thermodynamics, materials, acoustics, computer vision and graphics, robotics, semiconductor devices and structural engineering. The library can be also used for problems without defined geometry such as quantum chemistry, statistics, power networks and other graphs and chemical process simulation. All computations are performed with single or double floating point precision. Two linear system solvers and two preconditioners are supplied.