Search For:

Displaying 1-5 out of 5 total
Modeling and Predicting Performance of High Performance Computing Applications on Hardware Accelerators
Found in: 2012 26th IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
By Mitesh R. Meswani,Laura Carrington,Didem Unat,Allan Snavely,Scott Baden,Stephen Poole
Issue Date:May 2012
pp. 1828-1837
Computers with hardware accelerators, also referred to as hybrid-core systems, speedup applications by offloading certain compute operations that can run faster on accelerators. Thus, it is not surprising that many of top500 supercomputers use accelerators...
 
Accelerating a 3D Finite-Difference Earthquake Simulation with a C-to-CUDA Translator
Found in: Computing in Science & Engineering
By Didem Unat,Jun Zhou,Yifeng Cui,Scott B. Baden,Xing Cai
Issue Date:May 2012
pp. 48-59
GPUs provide impressive computing power, but GPU programming can be challenging. Here, an experience in porting real-world earthquake code to Nvidia GPUs is described. Specifically, an annotation-based programming model, called Mint, and its accompanying s...
 
Modeling and predicting application performance on hardware accelerators
Found in: IEEE Workload Characterization Symposium
By Mitesh R. Meswani,Laura Carrington,Didem Unat,Allan Snavely,Scott Baden,Stephen Poole
Issue Date:November 2011
pp. 73
Systems with hardware accelerators speedup applications by offloading certain compute operations that can run faster on accelerators. Thus, it is not surprising that many of top500 supercomputers use accelerators. However, in addition to procurement cost, ...
 
An Adaptive Sub-sampling Method for In-memory Compression of Scientific Data
Found in: Data Compression Conference
By Didem Unat, Theodore Hromadka III, Scott B. Baden
Issue Date:March 2009
pp. 262-271
A
 
Mint: realizing CUDA performance in 3D stencil methods with annotated C
Found in: Proceedings of the international conference on Supercomputing (ICS '11)
By Didem Unat, Scott B. Baden, Xing Cai
Issue Date:May 2011
pp. 214-224
We present Mint, a programming model that enables the non-expert to enjoy the performance benefits of hand coded CUDA without becoming entangled in the details. Mint targets stencil methods, which are an important class of scientific applications. We have ...
     
 1