Designing of processor-time optimal systolic arrays for band matrix-vector multiplication
نویسندگان
چکیده
منابع مشابه
Processor-time-optimal systolic arrays
Minimizing the amount of time and number of processors needed to perform an application reduces the application's fabrication cost and operation costs. A directed acyclic graph (dag) model of algorithms is used to de ne a time-minimal schedule and a processor-time-minimal schedule. We present a technique for nding a lower bound on the number of processors needed to achieve a given schedule of a...
متن کاملAn introduction to processor-time-optimal systolic arrays
We consider computations suitable for systolic arrays, often called regular array computations or systems of uniform recurrence relations. In such computations, the tasks to be computed are viewed as the nodes of a directed acyclic graph (dag), where the data dependencies are represented as arcs. A processor-time-minimal schedule measures the minimum number of processors needed to extract the m...
متن کاملFPGA Implementation of Optimal Planar Systolic Arrays for Orthogonal Matrix Multiplication
In this paper, optimal 2-D Systolic Arrays for orthogonal matrix multiplication, as much as the corresponding hardware implementation is investigated. The selected platform is a FPGA (Field Programmable Gate Array) device since, in systolic computing, FPGAs can be used as dedicated computers in order to perform certain computations at very high frequencies. The description language used as an e...
متن کاملPerformance of an embedded optical vector matrix multiplication processor architecture
An embedded architecture of optical vector matrix multiplier (OVMM) is presented. The embedded architecture is aimed at optimising the data flow of vector matrix multiplier (VMM) to promote its performance. Data dependence is discussed when the OVMM is connected to a cluster system. A simulator is built to analyse the performance according to the architecture. According to the simulation, Amdah...
متن کاملHyper-Systolic Matrix Multiplication
A novel parallel algorithm for matrix multiplication is presented. The hyper-systolic algorithm makes use of a one-dimensional processor abstraction. The procedure can be implemented on all types of parallel systems. It can handle matrix-vector multiplications as well as transposed matrix products.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computers & Mathematics with Applications
سال: 1996
ISSN: 0898-1221
DOI: 10.1016/0898-1221(96)00100-9