Tesla Bio Workbench
Tesla Bio Workbench
Supermicro Read more
Register for bio workbench seminars ::

Petapath, NVIDIA and Supermicro would like to invite researches, students and industrial users to a series of free seminars and workshops dedicated to the Bio Workbench. New dates are being added for September so please register to be kept informed.
The seminars will principally cover using AMBER 11's CUDA accelerated PMEMD. Read more about the seminars here

Email address *:
Salutation (Dr/Mr/Ms etc.) *:
Full name *:
Organisation *:
Contact number:
Submit PMEMD data:   (We will benchmark a limited number of user submitted test cases.)
Receive future mailings   (We would like to inform you about forthcoming seminars.)

* = required
More science, more quickly ::

NVIDIA® have always recognised the value of building an open software ecosystem that allows users to make use of GPU accelerated applications with the minimum of effort. The NVIDIA Tesla™ Bio Workbench is a new and critically important part of this ecosystem, specifically addressing users in the Life Sciences and Computational Chemistry. The Bio Workbench enables biophysicists and computational chemists to push the boundaries of biochemical research in a practical and cost effective way.


By harnessing the performance of Tesla Computing Solutions, it can turn a standard PC into a computational laboratory capable of running complex bioscience, particularly Molecular Dynamics and Quantum Chemistry codes. These include well established codes such as AMBER and other newer codes written from the ground up to support GPUs. All offer substantial improvements in throughput, enabling users to obtain more results more quickly. Bio Workbench codes can also be run on GPU equipped clusters.


The most exciting member of the Bio Workbench is the newly released AMBER 11, which is a significant upgrade over earlier versions. PMEMD (Particle Mesh Ewald Molecular Dynamics) with both explicit solvent PME and implicit solvent GB simulations now has a GPU accelerated version running on NVIDIA Tesla hardware using CUDA™. This implementation of PMEMD has been developed in close conjunction with NVIDIA and has has been tested and optimised for both the Tesla T10 series as well as the latest generation of the Tesla T20 ('Fermi').

Click here to download details on the Bio Workbench seminars.

Click here to download details on the Bio Station solution from Petapath and Supermicro.
How Petapath can help you ::

We have a wealth of experience in developing highly optimised and accelerated applications. If you need a heterogeneous implementation, we understand what is needed to develop a balanced system for you and your customers.

  • Expert knowledge of heterogeneous
    (GPU accelerated) systems
  • CUDA and OpenCL Consulting Services
  • CUDA and OpenCL Training Services
  • Optimisation specalists with extensive experience using:
    • C/C++, OpenMP, MPI, Pthreads, Intel MKL and Thread Building Blocks etc.

We have also recently completed running an "Introduction to GPU Computing" training day for NVIDIA Tesla Preferred Partners (TPP) in the UK.

 NVIDIA Tesla platform guide ::

The NVIDIA® Tesla™ 10 and 20-series GPU computing processors are hardware platforms designed for enterprise and technical computing.

The Tesla 20-series delivers features essential for the high performance and technical compute, such as ECC memory support and almost an order of magitude more double precision compute capability than current x86 processors.

Read more...

NVIDIA CUDA architecture ::

CUDA is NVIDIA's parallel computing architecture which enables the developers and users alike to harness the immense computing capabilities of modern GPUs (graphics processing unit).

The CUDA parallel hardware architecture is accompanied by the CUDA parallel programming model where the developer can choose to express the parallelism of their software in high-level languages such as C, C++, Fortran or driver APIs such as OpenCL™ and DirectX™ 11 Compute Shaders.

Read more...