Sciweavers

407 search results - page 3 / 82
» Register-Sensitive Software Pipelining
Sort
View
EGH
2011
Springer
12 years 5 months ago
High-Performance Software Rasterization on GPUs
In this paper, we implement an efficient, completely software-based graphics pipeline on a GPU. Unlike previous approaches, we obey ordering constraints imposed by current graphi...
Samuli Laine, Tero Karras
PLDI
2005
ACM
13 years 11 months ago
Register allocation for software pipelined multi-dimensional loops
Software pipelining of a multi-dimensional loop is an important optimization that overlaps the execution of successive outermost loop iterations to explore instruction-level paral...
Hongbo Rong, Alban Douillet, Guang R. Gao
CGO
2010
IEEE
14 years 19 days ago
Decoupled software pipelining creates parallelization opportunities
Decoupled Software Pipelining (DSWP) is one approach to automatically extract threads from loops. It partitions loops into long-running threads that communicate in a pipelined man...
Jialu Huang, Arun Raman, Thomas B. Jablin, Yun Zha...
CGO
2009
IEEE
14 years 17 days ago
Software Pipelined Execution of Stream Programs on GPUs
—The StreamIt programming model has been proposed to exploit parallelism in streaming applications on general purpose multicore architectures. This model allows programmers to sp...
Abhishek Udupa, R. Govindarajan, Matthew J. Thazhu...
POPL
2010
ACM
14 years 3 months ago
A simple, verified validator for software pipelining
Software pipelining is a loop optimization that overlaps the execution of several iterations of a loop to expose more instruction-level parallelism. It can result in first-class p...
Jean-Baptiste Tristan, Xavier Leroy