𝔖 Bobbio Scriptorium
✦   LIBER   ✦

An even faster systolic array for matrix multiplication

✍ Scribed by Abdelhamid Benaini; Yves Robert

Publisher
Elsevier Science
Year
1989
Tongue
English
Weight
307 KB
Volume
12
Category
Article
ISSN
0167-8191

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

VLSI systolic arrays for band matrix mul
VLSI systolic arrays for band matrix multiplication
✍ G. Alia 📂 Article 📅 1983 🏛 Elsevier Science 🌐 English ⚖ 771 KB

The advent of VLSI technology has deeply modified the design of digital systems. The structure of special algorithms is now close to the structure of communication and computing resources on the silicon chip. Modular and regular structures allow parallel VLSI algorithms with good figures of complexi

Mapping matrix multiplication algorithm
Mapping matrix multiplication algorithm onto fault-tolerant systolic array
✍ N.M. Stojanović; E.I. Milovanović; I. Stojmenović; T.. Milovanović; T.I. Tokić 📂 Article 📅 2004 🏛 Elsevier Science 🌐 English ⚖ 891 KB

An approach to design fault-tolerant hexagonal systolic array (SA) for multiplication of rectangular matrices is described. The approach comprises three steps. First, redundancies are introduced at the computational level by deriving three equivalent algorithms but with disjoint index spaces. Second

Matrix-vector multiplication on a fixed-
Matrix-vector multiplication on a fixed-size linear systolic array
✍ E.I Milovanović; M.K Stojc̆ev; N.M Novaković; I.Z̆ Milovanović; T.I Tokić 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 956 KB

This paper considers the multiplication of matrix A = (aik)n×n by vector b = (bk)n×l on the bidirectional linear systolic array (BLSA) comprised of p \_~ In/2] processing elements. To accomplish this matrix, A is partitioned into quasi-diagonal blocks. Each block contains p quasidiagonals. To avoid