|NVIDIA GPU Test Drive Program
Benchmark AMBER, NAMD and more!
|2X in 4 Weeks!
Accelerate your code with directives-based compilers. No GPU experience required.
Directives based compilers allow you to gain valuable speedups on code that hasn't been ported to GPUs. With GPU directives, you can accelerate your Fortran code by simply inserting compiler hints into your code and the compiler will automatically map compute-intensive portions of your code to the GPU.
Register with NVIDIA and PGI for the free directives-based compiler trial
Determine where your application spends most time
Insert compiler directive pragma/comments
Secure hardware, either Microway remote systems or in-house GPUs
Recompile your application using PGI Accelerator compiler
Watch the speedup!
Visit NVIDIA's OpenACC page for additional details
Why GPUs for AMBER and NAMD?
"With Tesla M2090 GPUs, AMBER users in university departments can obtain application performance that outstrips what is even possible with extensive supercomputing access."
-Ross Walker, Assistant Research Professor at San Diego Computer Center
Learn more about Performance
Tesla GPU Accelerated Applications
NVIDIA® Tesla™ GPU Processors accelerate many common scientific codes. AMBER, NAMD and MATLAB are just a few of the applications enjoying significant speed-ups.
Try today on advanced, fully integrated hardware
Whether you are an AMBER or NAMD user or have in-house GPU-enabled applications, we are offering you remote benchmarking time on our latest hardware. This includes NVIDIA Tesla K20 GPUs with over 3X the performance of previous Tesla GPUs.
See how fast your code can run
To log in and test your code, register below. After registration, you will receive an email with instructions.
For any questions, please email firstname.lastname@example.org.
Implement as fast as you are ready
If you are pleased with cluster performance and have immediate need, you can purchase the benchmarked hardware and have it ship inside of 72 hours.
If you require a longer process, we're happy to build an equivalent cluster or design a custom configuration to meet your needs.