Sciweavers

177 search results - page 3 / 36
» Minimal Data Dependence Abstractions for Loop Transformation...
Sort
View
99
Voted
CC
2003
Springer
15 years 2 months ago
Early Control of Register Pressure for Software Pipelined Loops
Abstract. The register allocation in loops is generally performed after or during the software pipelining process. This is because doing a conventional register allocation at firs...
Sid Ahmed Ali Touati, Christine Eisenbeis
MICRO
2000
IEEE
176views Hardware» more  MICRO 2000»
14 years 9 months ago
An Advanced Optimizer for the IA-64 Architecture
level of abstraction, compared with the program representation for scalar optimizations. For example, loop unrolling and loop unrolland-jam transformations exploit the large regist...
Rakesh Krishnaiyer, Dattatraya Kulkarni, Daniel M....
TJS
2008
113views more  TJS 2008»
14 years 9 months ago
Improving the parallelism of iterative methods by aggressive loop fusion
Abstract. Traditionally, loop nests are fused only when the data dependences in the loop nests are not violated. This paper presents a new loop fusion algorithm that is capable of ...
Jingling Xue, Minyi Guo, Daming Wei
APLAS
2005
ACM
15 years 3 months ago
Transformation to Dynamic Single Assignment Using a Simple Data Flow Analysis
This paper presents a novel method to construct a dynamic single assignment (DSA) form of array-intensive, pointer-free C programs (or in any other procedural language). A program ...
Peter Vanbroekhoven, Gerda Janssens, Maurice Bruyn...
CASES
2009
ACM
15 years 4 months ago
Optimal loop parallelization for maximizing iteration-level parallelism
This paper solves the open problem of extracting the maximal number of iterations from a loop that can be executed in parallel on chip multiprocessors. Our algorithm solves it opt...
Duo Liu, Zili Shao, Meng Wang, Minyi Guo, Jingling...