Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
PLDI
2011
ACM
9 years 7 months ago
Automatic CPU-GPU communication management and optimization
The performance beneļ¬ts of GPU parallelism can be enormous, but unlocking this performance potential is challenging. The applicability and performance of GPU parallelizations is...
Thomas B. Jablin, Prakash Prabhu, James A. Jablin,...
SC
1992
ACM
10 years 8 months ago
Compiler Code Transformations for Superscalar-Based High Performance Systems
Exploiting parallelism at both the multiprocessor level and the instruction level is an e ective means for supercomputers to achieve high-performance. The amount of instruction-le...
Scott A. Mahlke, William Y. Chen, John C. Gyllenha...
ACMMSP
2006
ACM
250views Hardware» more  ACMMSP 2006»
10 years 10 months ago
What do high-level memory models mean for transactions?
Many people have proposed adding transactions, or atomic blocks, to type-safe high-level programming languages. However, researchers have not considered the semantics of transacti...
Dan Grossman, Jeremy Manson, William Pugh
ICS
2009
Tsinghua U.
10 years 11 months ago
MPI-aware compiler optimizations for improving communication-computation overlap
Several existing compiler transformations can help improve communication-computation overlap in MPI applications. However, traditional compilers treat calls to the MPI library as ...
Anthony Danalis, Lori L. Pollock, D. Martin Swany,...
ICFP
2003
ACM
11 years 4 months ago
Compiler implementation in a formal logical framework
The task of designing and implementing a compiler can be a difficult and error-prone process. In this paper, we present proach based on the use of higher-order abstract syntax and...
Jason Hickey, Aleksey Nogin, Adam Granicz
books