Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
4,382
Data Layout ยท Walkthrough Application
"... Abstract Performance of interactive graphics walkthrough systems depends on the time taken to fetch the required data from the secondary storage to main memory. It has been earlier established that a large frac-tion of this fetch time is spent on seeking the data on the hard disk. In order to reduce ..."
Abstract
- Add to MetaCart
to reduce this seek time, redun-dant data storage has been proposed in the literature, but the redundancy factors of those layouts are pro-hibitively high. In this paper, we develop a cost model for the seek time of a layout. Based on this cost model, we propose an elegant algorithm that computes a re
Data layouts for object-oriented programs
- SIGMETRICS Perform. Eval. Rev
"... Object-oriented programs rely heavily on objects and pointers, making them vulnerable to slowdowns from cache and TLB misses. The cache and TLB behavior depends on the data layout of objects in memory. There are many possible data layouts with different impacts on performance, but it is not known wh ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
Object-oriented programs rely heavily on objects and pointers, making them vulnerable to slowdowns from cache and TLB misses. The cache and TLB behavior depends on the data layout of objects in memory. There are many possible data layouts with different impacts on performance, but it is not known
Automatic Data Layout for High-Performance Fortran
- IN PROCEEDINGS OF SUPERCOMPUTING '95
, 1994
"... High Performance Fortran (HPF) is rapidly gaining acceptance as a language for parallel programming. The goal of HPF is to provide a simple yet ecient machine independent parallel programming model. Besides the algorithm selection, the data layout choice is the key intellectual step in writing an ec ..."
Abstract
-
Cited by 73 (3 self)
- Add to MetaCart
High Performance Fortran (HPF) is rapidly gaining acceptance as a language for parallel programming. The goal of HPF is to provide a simple yet ecient machine independent parallel programming model. Besides the algorithm selection, the data layout choice is the key intellectual step in writing
Map Data Layout.
"... rtunity to take advantage of available indexes in the data repository. Moreover, in the case where the operation is a selection or an aggregate operation, evaluating the operation in the data repository can significant reduce the overhead of data transfer between the data repository and Conquest. To ..."
Abstract
- Add to MetaCart
rtunity to take advantage of available indexes in the data repository. Moreover, in the case where the operation is a selection or an aggregate operation, evaluating the operation in the data repository can significant reduce the overhead of data transfer between the data repository and Conquest
Data layout, Staggered Dslash
"... (QCD) application used to simulate four-dimensional SU(3) lattice gauge theory, is one of the largest compute cycle users at the national supercomputing centers. The code is scalable to thousands of processors, however its per-processor peak floating-point performance remains low [see the performanc ..."
Abstract
- Add to MetaCart
on GPUs, such as the fermion force, gauge force and fat link computation. The most expensive operation in the CG solver is the dslash operation Data for spinors and gauge links is rearranged on the host before it is copied to the device memory to enable coalesced memory access We have implemented
Custom data layout for memory parallelism
- In Proc. Intl. Symp. Code Gen. Opt
, 2004
"... In this paper, we describe a generalized approach to deriving a custom data layout in multiple memory banks for array-based computations, to facilitate high-bandwidth parallel memory accesses in modern architectures where multiple memory banks can simultaneously feed one or more functional units. We ..."
Abstract
-
Cited by 7 (2 self)
- Add to MetaCart
In this paper, we describe a generalized approach to deriving a custom data layout in multiple memory banks for array-based computations, to facilitate high-bandwidth parallel memory accesses in modern architectures where multiple memory banks can simultaneously feed one or more functional units
Tile Size Selection Using Cache Organization and Data Layout
, 1995
"... When dense matrix computations are too large to fit in cache, previous research proposes tiling to reduce or eliminate capacity misses. This paper presents a new algorithm for choosing problem-size dependent tile sizes based on the cache size and cache line size for a direct-mapped cache. The algori ..."
Abstract
-
Cited by 231 (2 self)
- Add to MetaCart
high cache efficiency. Compiler optimizations to improve data locality for uniprocessors is increas...
Permutation Development Data Layout (PDDL)
"... Declustered data organizations in disk arrays (RAIDs) achieve less-intrusive reconstruction of data after a disk failure. We present PDDL, a new data layout for declustered disk arrays. PDDL layouts exist for a large variety of disk array configurations with a distributed spare disk. PDDL declustere ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Declustered data organizations in disk arrays (RAIDs) achieve less-intrusive reconstruction of data after a disk failure. We present PDDL, a new data layout for declustered disk arrays. PDDL layouts exist for a large variety of disk array configurations with a distributed spare disk. PDDL
Automatic Data Layout for Distributed Memory Machines
, 1995
"... The goal of languages like Fortran D or High Performance Fortran (HPF) is to provide a simple yet efficient machine-independent parallel programming model. Besides the algorithm selection, the data layout choice is the key intellectual challenge in writing an efficient program in such languages. The ..."
Abstract
-
Cited by 34 (5 self)
- Add to MetaCart
The goal of languages like Fortran D or High Performance Fortran (HPF) is to provide a simple yet efficient machine-independent parallel programming model. Besides the algorithm selection, the data layout choice is the key intellectual challenge in writing an efficient program in such languages
Results 1 - 10
of
4,382
