Optimisations Techniques for the Automatic ISA Customisation Algorithm
スポンサーリンク
概要
- 論文の詳細を見る
This article introduces some improvements to the already proposed custom instruction candidates selection for the automatic ISA customisation problem targeting reconfigurable processors. It introduces new opportunities to prune the search space, and a technique based on dynamic programming to check the independence between groups. The proposed new algorithm yields one order less measured number of convexity checks than the related work for the same inputs and outputs.
- The Institute of Electronics, Information and Communication Engineersの論文
- 2012-02-01
著者
-
Murakami Kazuaki
Department Of Computer Science And Communication Engineering Kyushu University
-
TROUVE Antoine
Department of Informatics, Kyushu University
関連論文
- Quantitative Evaluation of State-Preserving Leakage Reduction Algorithm for L1 Data Caches
- Improving Performance and Energy Saving in a Reconfigurable Processor via Accelerating Control Data Flow Graphs
- Character Projection Mask Set Optimization for Enhancing Throughput of MCC Projection Systems
- Reliable Cache Architectures and Task Scheduling for Multiprocessor Systems
- Architectural-Level Soft-Error Modeling for Estimating Reliability of Computer Systems(VLSI Design Technology,VLSI Technology toward Frontiers of New Market)
- A Reconfigurable Functional Unit with Conditional Execution for Multi-Exit Custom Instructions
- Temperature-Aware Configurable Cache to Reduce Energy in Embedded Systems
- The potential of temperature-aware configurable cache on energy reduction (計算機アーキテクチャ)
- The potential of temperature-aware configurable cache on energy reduction (集積回路)
- Custom Instructions with Multiple Exits : Generation and Execution
- Custom Instructions with Multiple Exits : Generation and Execution
- A Reconfigurable Functional Unit for Adaptable Custom Instructions
- A Reconfigurable Functional Unit for Adaptable Custom Instructions(集積回路技術とアーキテクチャ技術の協調・融合へ向けた,プロセッサ,並列処理,システムLSIアーキテクチャ及び一般)
- An Adaptive Dynamic Extensible Processor
- Performance Models for MPI Collective Communications with Network Contention
- Instruction Encoding for Reducing Power Consumption of I-ROMs Based on Execution Locality
- Trends in High-Performance, Low-Power Cache Memory Architectures
- Omitting Cache Look-up for High-Performance, Low-Power Microprocessors(Special Issue on High-Performance and Low-Power Microprocessors)
- Hyperscalar Processor Architecture and the Preliminary Performance Evaluation
- PPRAM (Parallel Processing RAM) : A Merged-DRAM/Logic System-LSI Architecture
- A Message-Pool-Based Parallel Operating System for the Kyushu University Reconfigurable Parallel Processor : Parallel Creation of Multiple Threads
- Optimisations Techniques for the Automatic ISA Customisation Algorithm