Efficient Design Space Exploration at System Level with Automatic Profiler Instrumentation
スポンサーリンク
概要
- 論文の詳細を見る
As the complexity of embedded systems grows, design space exploration at a system level plays a more important role than before. In the system-level design, system designers start from describing functionalities of the system as processes and channels, and then decide mapping of them to various Processing Elements (PEs) including processors and dedicated hardware modules. A mapping decision is evaluated by simulation or FPGA-based prototyping. Designers iterate mapping and evaluation until all design requirements are met. We have developed two profilers, a process profiler and a memory profiler, for FPGA-based performance analysis of design candidates. The process profiler records a trace of process activations, while the memory profiler records a trace of channel accesses. According to mapping of processes to PEs, the profilers are automatically configured and instrumented into FPGA-based system prototypes by a system-level design tool that we have developed. Designers therefore need to manually modify neither the system description nor the profilers upon each change of process mapping. In order to demonstrate the effectiveness of our profilers, two case studies are conducted where the profiles are used for design space exploration of AES encryption and MPEG4 decoding systems.
著者
-
Honda Shinya
Graduate School Of Information Science Nagoya University
-
Takada Hiroaki
Graduate School Of Information Science Nagoya University
-
Tomiyama Hiroyuki
College Of Science And Engineering Ritsumeikan University
-
Ando Yuki
Graduate School Of Information Science Nagoya University
-
Shibata Seiya
Graduate School Of Information Science Nagoya University
-
ANDO Yuki
Graduate School of Information Science, Nagoya University
関連論文
- A realization of RPC in embedded component systems (システムLSI設計技術・組込みシステム・組込技術とネットワークに関するワークショップETNET2008)
- Effective hardware task context switching in Virtex-4 FPGAs (VLSI設計技術)
- Effective hardware task context switching in Virtex-4 FPGAs (コンピュータシステム)
- Effective hardware task context switching in Virtex-4 FPGAs (リコンフィギャラブルシステム)
- Efficient Design Space Exploration at System Level with Automatic Profiler Instrumentation
- Integrated Scheduling in a Real-Time Embedded Hypervisor
- Task migration for energy savings in multiprocessor real-time systems (VLSI設計技術)
- A dynamic algorithm for energy savings in DEPS framework (組込みシステム)
- Power Management for Idle Time in the Presence of Periodic Interrupt Services
- Power Management for Idle Time in the Presence of Periodic Interrupt Services
- Power Management for Idle Time in the Presence of Periodic Interrupt Services
- Power Management for Idle Time in the Presence of Periodic Interrupt Services
- A realization of RPC in embedded component systems (コンピュータシステム・組込技術とネットワークに関するワークショップETNET2008)
- A realization of RPC in embedded component systems (ディペンダブルコンピューティング・組込技術とネットワークに関するワークショップETNET2008)
- Effective Scheduling Algorithms for I/O Blocking with a Multi-Frame Task Model
- An Effective GA-Based Scheduling Algorithm for FlexRay Systems
- A Realization of RPC in Embedded Component Systems
- Inter-OS Communications for a Real-Time Dual-OS Monitor
- Inter-OS Communications for a Real-Time Dual-OS Monitor
- Partitioning of Behavioral Descriptions with Exploiting Function-Level Parallelism
- Function-Level Partitioning of Sequential Programs for Efficient Behavioral Synthesis
- Function Call Optimization for Efficient Behavioral Synthesis
- An RTOS-Based Design and Validation Methodology for Embedded Systems(System Programs)
- RTOS-Centric Cosimulator for Embedded System Design
- Static Task Scheduling Algorithms Based on Greedy Heuristics for Battery-Powered DVS Systems
- Automatic Communication Synthesis with Hardware Sharing for Multi-Processor SoC Design
- Preemptive Hardware Multitasking on Dynamically Partially Reconfigurable FPGAs : Hardware and Reconfiguration Layers
- A Fast Performance Estimation Framework for System-Level Design Space Exploration (System LSI Design Methodology Vol.5)
- Partitioning and Allocation of Scratch-Pad Memory for Energy Minimization of Priority-Based Preemptive Multi-Task Systems
- A Novel Framework for Effective Preemptive Hardware Multitasking on FPGAs
- Integrated Scheduling for a Reliable Dual-OS Monitor
- Integrated Scheduling for a Reliable Dual-OS Monitor
- Embedded System Covalidation with RTOS Model and FPGA
- Efficient Algorithms for Extracting Pareto-optimal Hardware Configurations in DEPS Framework
- A Fast Performance Estimation Framework for System-Level Design Space Exploration
- Worst Case Response Time Analysis for Messages in Controller Area Network with Gateway
- Proposal and Quantitative Analysis of the CHStone Benchmark Program Suite for Practical C-based High-level Synthesis
- A Channel-based Communication/Synchronization Model for SW-HW Multitasking on Dynamically Partially Reconfigurable FPGAs
- A Channel-based Communication/Synchronization Model for SW-HW Multitasking on Dynamically Partially Reconfigurable FPGAs
- A Channel-based Communication/Synchronization Model for SW-HW Multitasking on Dynamically Partially Reconfigurable FPGAs