Results 1 to 10 of about 17,828 (213)
Software prefetching for software pipelined loops [PDF]
Proceedings of the Thirty-First Hawaii International Conference on System Sciences, 1998 The paper investigates the interaction between software pipelining and different software prefetching techniques for VLIW machines. It is shown that processor stalls due to memory dependencies have a great impact into execution time. A novel heuristic is
González Colás, Antonio María +1 more
core +3 more sources
Hardware/software partitioning and pipelining [PDF]
Proceedings of the 34th annual conference on Design automation conference - DAC '97, 1997 For a given throughput constrained system-level specification, we present a design flow and an algorithm to select software(general purpose processors) and hardware components, and then partition and pipeline the specification amongstthe selected components.This is done so as to beat satisfythe throughput constraint at minimal hardware cost.Ourability ...
Smita Bakshi, Daniel D. Gajski
+5 more sources
Software pipelining: an effective scheduling technique for VLIW machines [PDF]
Proceedings of the ACM SIGPLAN 1988 conference on Programming language design and implementation, 1988 This paper shows that software pipelining is an effective and viable scheduling technique for VLIW processors. In software pipelining, iterations of a loop in the source program are continuously initiated at constant intervals, before the preceding iterations complete.
Monica S. Lam
openalex +3 more sources
Hardware implementation of FPGA-based spiking attention neural network accelerator [PDF]
PeerJ Computer ScienceSpiking neural networks (SNNs) are recognized as third-generation neural networks and have garnered significant attention due to their biological plausibility and energy efficiency.
Shiyong Geng +5 more
doaj +3 more sources
Load-store optimization for software pipelining [PDF]
ACM SIGARCH Computer Architecture News, 2000 Software pipelining can generate efficient schedules for loop by overlapping the execution of operations from different iterations in order to exploit maximum Instruction Level Parallelism (ILP). Code optimization can decrease total number of calculations and memory related operations.
Min Dai +2 more
openalex +4 more sources
Large-scale Distributed XML Database Based on Ant Colony Platform [PDF]
Jisuanji gongcheng, 2017 To solve the problems of inefficient queries,low concurrency,small database capacity and bad scalability of the existing NativeXML database,a large-scale distributed NativeXML database prototype is designed based on efficient and multi-purpose computing ...
ZHAO Jinming,QIAN Lei,WU Dong,HAO Ziyu
doaj +1 more source
PD5: a general purpose library for primer design software. [PDF]
PLoS ONE, 2013 Complex PCR applications for large genome-scale projects require fast, reliable and often highly sophisticated primer design software applications. Presently, such applications use pipelining methods to utilise many third party applications and this ...
Michael C Riley +3 more
doaj +1 more source
Migration and Optimization of AMBER Software Based on Sunway TaihuLight [PDF]
Jisuanji gongcheng, 2020 As the mainstream Molecular Dynamics(MD) simulation software,AMBER is widely used for researches in the microscopic movements in molecular systems.In order to use the massive computing resources of Sunway TaihuLight to accelerate the AMBER-based ...
PENG Long, CHEN Junshi, AN Hong
doaj +1 more source
A General Parallel Convolution Algorithm for Sunway Taihu Light [PDF]
Jisuanji gongcheng, 2019 The parallel convolution algorithm in the deep learning library of Sunway Taihu Light has the problem of batch limitation,and the traditional gemm convolution algorithm is inefficient for its hardware architecture.In order to solve the above problems,a ...
SHU Jiaming, AN Hong, WU Zheng, CHEN Junshi
doaj +1 more source
Convolutional Neural Network Model Compression Method for Software—Hardware Co-Design
Information, 2022 Owing to their high accuracy, deep convolutional neural networks (CNNs) are extensively used. However, they are characterized by high complexity. Real-time performance and acceleration are required in current CNN systems. A graphics processing unit (GPU)
Seojin Jang, Wei Liu, Yongbeom Cho
doaj +1 more source