Sciweavers

272 search results - page 36 / 55
» Code Transformations to Improve Memory Parallelism
Sort
View
CGO
2008
IEEE
14 years 3 months ago
Spice: speculative parallel iteration chunk execution
The recent trend in the processor industry of packing multiple processor cores in a chip has increased the importance of automatic techniques for extracting thread level paralleli...
Easwaran Raman, Neil Vachharajani, Ram Rangan, Dav...
CASES
2003
ACM
14 years 1 months ago
Exploiting bank locality in multi-bank memories
Bank locality can be defined as localizing the number of load/store accesses to a small set of memory banks at a given time. An optimizing compiler can modify a given input code t...
Guilin Chen, Mahmut T. Kandemir, Hendra Saputra, M...
SPIRE
2009
Springer
14 years 3 months ago
On Entropy-Compressed Text Indexing in External Memory
A new trend in the field of pattern matching is to design indexing data structures which take space very close to that required by the indexed text (in entropy-compressed form) an...
Wing-Kai Hon, Rahul Shah, Sharma V. Thankachan, Je...
CCGRID
2001
IEEE
14 years 9 days ago
KelpIO: A Telescope-Ready Domain-Specific I/O Library for Irregular Block-Structured Applications
To ameliorate the need to spend significant programmer time modifying parallel programs to achieve highperformance, while maintaining compact, comprehensible source codes, this pa...
Bradley Broom, Robert J. Fowler, Ken Kennedy
EUROPAR
2003
Springer
14 years 1 months ago
Compression in Data Caches with Compressible Field Isolation for Recursive Data Structures
We introduce a software/hardware scheme called the Field Array Compression Technique (FACT) which reduces cache misses due to recursive data structures. Using a data layout transfo...
Masamichi Takagi, Kei Hiraki