EDBT 2026 Demo / reviewers in the wild / expert
Takahiro Takechi
dblp:27/318
· DBLP profile ↗
2ranked-venue papers
0as first author
0since 2021 · last 1986
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Systems, architecture and hardware · 2Software engineering, systems software and programming languages · 1
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Computer architecture, parallel and distributed computing, and storage systems
1 paper |
Parallel and multicore computing · 67% Hardware accelerators and domain-specific architectures · 33% |
Topics — the 3 heaviest of 3, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Parallel and multicore computing
parallel algorithms |
0.0 | 1 | 1986 | On Design of Rotary Array Communication and Wavefront-Driven Algorithms for Solving Large-Scale Band-Limited Matrix Equations · ISCA 1986 |
Hardware accelerators and domain-specific architectures
systolic array |
0.0 | 1 | 1986 | On Design of Rotary Array Communication and Wavefront-Driven Algorithms for Solving Large-Scale Band-Limited Matrix Equations · ISCA 1986 |
Parallel and multicore computing › parallel algorithms › parallel algorithm design
wavefront parallelism |
0.0 | 1 | 1986 | On Design of Rotary Array Communication and Wavefront-Driven Algorithms for Solving Large-Scale Band-Limited Matrix Equations · ISCA 1986 |
Methods — techniques the papers use, named apart from their topics
conjugate residual iteration · 0.0LU decomposition · 0.0
| Year | Publication | Venue | Position |
|---|---|---|---|
| 1986 | On Design of Rotary Array Communication and Wavefront-Driven Algorithms for Solving Large-Scale Band-Limited Matrix EquationsabstractThis paper proposes a design of matrix machines for solving large-scale band-limited matrix equations. The design provides a guide-line for specifying functionality of each processing element PE, array arrangements of PEs, communication structures and parallel algorithms. The basic feature of the design is (1) a rotary array arrangement of data-flow type PEs with the slant width 2B-1 and circumference Z, on which the diagonal strip of a band-limited matrix data is wound around, and (2) wavefront-sequential executions of tasks, each of which is consisted of a group of pipelined wavefronts and circulates around the rotary array. The wavefront algorithm first produces the Gaussian solution via LU decomposition and then its accuracy is improved by applying the incomplete LU (conjugate) residual iteration. Kenji Onaga, Takahiro Takechi |
ISCA | 2 |
| 1986 | A Wavefront Algorithm for LU Decomposition of a Partitioned Matrix on VLSI Processor Arrays
Kenji Onaga, Takahiro Takechi |
J. Parallel Distributed Comput. | 2 |