Partnering with NVIDIA and Microsoft, this four-day CUDA training course is designed for GPU Programmers in the oil-and-gas industry who are looking to develop comprehensive skills in writing and optimizing applications that fully leverage the many-core processing capabilities of the GPU.
Partnering with NVIDIA and Microsoft, this four-day CUDA training course is designed for GPU Programmers who are looking to develop comprehensive skills in writing and optimizing applications that fully leverage the many-core processing capabilities of the GPU.
We describe our FE-gMG solver, a finite element geometric multigrid approach for problems relying on unstructured grids. We augment our GPU- and multicore-oriented implementation technique based on cascades of sparse matrix-vector multiplication by applying strong smoothers. In particular, we employ Sparse Approximate Inverse (SPAI) and Stabilised Approximate Inverse (SAINV) techniques. We focus on presenting the numerical efficiency of our smoothers in combination with low- and high-order finite element spaces as well as the hardware efficiency of the FE-gMG. For a representative problem and computational grids in 2D and 3D, we achieve a speedup of an average of 5 on a single GPU over a multithreaded CPU code in our benchmarks. In addition, our strong smoothers can deliver a speedup of 3-5 depending on the element space, compared to simple Jacobi smoothing. This can even be enhanced to a factor of 7 when combining the usage of Approximate Inverse-based smoothers with clever sorting of the degrees of freedom. In total the FE-gMG solver can outperform a simple, (multicore-)CPU-based multigrid by a total factor of over 40.
(Markus Geveler, Dirk Ribbrock, Dominik Göddeke, Peter Zajac and Stefan Turek: “Towards a complete FEM-based simulation toolkit on GPUs: Unstructured Grid Finite Element Geometric Multigrid solvers with strong smoothers based on Sparse Approximate Inverses”, accepted for publication in Computers and Fluids, 2011. [preprint])
VMD is a popular molecular visualization and analysis program used by thousands of researchers worldwide. VMD accelerates many of the most computationally demanding visualization and analysis features using GPU computing techqniques, resulting in improved performance and new capabilities beyond what is possible using only conventional multi-core CPUs. VMD 1.9.1 advances these capabilities further with a CUDA implementation of the new QuickSurf molecular surface representation, enabling smooth interactive animation of moderate sized biomolecular complexes consisting of a few hundred thousand to one million atoms, and allowing interactive display of molecular surfaces for static structures of very large complexes containing tens of millions of atoms, e.g. large virus capsids.
More information: http://www.ks.uiuc.edu/Research/vmd/vmd-1.9.1/
Today NVIDIA released CUDA 4.1, including a new CUDA Toolkit, SDK, Visual Profiler, Parallel Nsight IDE and NVIDIA device driver.
CUDA 4.1 makes it easier to accelerate scientific research with GPUs with key features including
- a redesigned Visual Profiler with automated performance analysis and expert guidance;
- a new LLVM-based compiler that generates up to 10% faster code; and
- 1000+ new imaging and signal processing functions in the NPP library.
The CuSparse library included with CUDA 4.1 has a new tridiagonal solver and 2x faster sparse matrix-vector multiplication using the ELL hybrid format, and the CuRand library included with CUDA 4.1 has two new random number generators. Read the rest of this entry »
PyCOOL (Cosmological Object-Oriented Lattice code) is a fast GPU accelerated program that solves the evolution of interacting scalar fields in an expanding universe with symplectic algorithms. The program has been written with the intention to hit a sweet spot of speed, accuracy and user friendliness. This is achieved by using the Python language with the PyCUDA interface to make a program that is very easy to adapt to different scalar field models. The program is publicly available under GNU General Public License at. See the PyCOOL website for more information.
The SpeedIt team recently compared and benchmarked the SpMV performance of CUSPARSE 4.0, CUSP 0.2.0 and SpeedIT 2.0 on 23 randomly chosen matrices from University Florida Matrix Collection. Comparisons were done on a Tesla C2050 in single and double precision. The full report is available at http://wp.me/p1ZihD-1.
Partnering with NVIDIA and Microsoft, this four day course is designed for Programmers who are looking to develop comprehensive skills in writing and optimizing applications that fully leverage the multi-core processing capabilities of the GPU.
Delivered by Acceleware’s Developers, who provide real world experience and examples, the training comprises classroom lectures and hands-on tutorials. Each student will be supplied with a laptop equipped with NVIDIA GPUs for the duration of the course. Small class sizes maximize learning and ensure a personal educational experience.
Register before January 13 and receive $250 off your course fee!
Enter promotional code AXTEB2012
HOOMD-blue performs general-purpose particle dynamics simulations on a single workstation, taking advantage of NVIDIA GPUs to attain a level of performance equivalent to many cores on a fast cluster. Flexible and configurable, HOOMD-blue is currently being used for coarse-grained molecular dynamics simulations of nano-materials, glasses, and surfactants, dissipative particle dynamics simulations (DPD) of polymers, and crystallization of metals.
HOOMD-blue 0.10.0 adds many new features. Highlights include: Read the rest of this entry »
In this paper we investigate the use of distributed graphics processing unit (GPU)-based architectures to accelerate pipelined wavefront applications—a ubiquitous class of parallel algorithms used for the solution of a number of scientific and engineering applications. Specifically, we employ a recently developed port of the LU solver (from the NAS Parallel Benchmark suite) to investigate the performance of these algorithms on high-performance computing solutions from NVIDIA (Tesla C1060 and C2050) as well as on traditional clusters (AMD/InfiniBand and IBM BlueGene/P).
Benchmark results are presented for problem classes A to C and a recently developed performance model is used to provide projections for problem classes D and E, the latter of which represents a billion-cell problem. Our results demonstrate that while the theoretical performance of GPU solutions will far exceed those of many traditional technologies, the sustained application performance is currently comparable for scientific wavefront applications. Finally, a breakdown of the GPU solution is conducted, exposing PCIe overheads and decomposition constraints. A new k-blocking strategy is proposed to improve the future performance of this class of algorithm on GPU-based architectures.
(Pennycook, S.J., Hammond, S.D., Mudalige, G.R., Wright, S.A. and Jarvis, S.A.: “On the Acceleration of Wavefront Applications using Distributed Many-Core Architectures”, The Computer Journal (in press) [DOI] [PREPRINT])