A Resource-Shared VLIW Processor for Low-Power On-Chip Multiprocessing in the Nanometer Era(Digital, <Special Section>Low-Power LSI and Low-Power IP)
スポンサーリンク
概要
- 論文の詳細を見る
We propose a low-power resource-shared VLIW processor (RSVP) for future leaky nanometer process technologies. It consists of several single-way independent processor units (IPUs) that share parallel processor resources. Each IPU works as a variable-way VLIW processor sharing the parallel resources according to priorities of given tasks. RSVP allocates shared parallel resources to the IPUs cycle by cycle. It can minimize the number of NOPs that is wasting power. The performance per power (P^3) of a 4-parallel 4-way RSVP that corresponds to four 4way VLIWs is 3.7% better than a conventional 4-parallel 4-way VLIW multiprocessor in the current 90 nm process. We estimate that the RSVP achieves 36% less leakage power and 28% better P^3 in the future 25 nm process. We have fabricated an RSVP test chip that contains two IPU and a shared resource equivalent to two 2way VLIWs in a 180nm process. It is functional at 100 MHz clock speed and its power is 130 mW.
- 社団法人電子情報通信学会の論文
- 2005-04-01
著者
-
Kobayashi Kazutoshi
Graduate School Of Informatics Kyoto University
-
Kobayashi Kazutoshi
Kyoto Univ. Kyoto‐shi Jpn
-
Katsuki Kazuya
Department Of Communications And Computer Engineering Graduate School Of Informatics Kyoto Universit
-
Onodera Hidetoshi
Graduate School Of Informatics Kyoto University
-
ARAMOTO Masao
Graduate School of Informatics, Kyoto University
-
Aramoto Masao
Graduate School Of Informatics Kyoto University:(present Address)renesas Technology
関連論文
- Spreading Code Assignment for Multicarrier CDMA System over Frequency-Selective Fading Channels(Terrestrial Radio Communications)
- Inter-Code Interference and Optimum Spreading Sequence in Frequency-Selective Rayleigh Fading Channels on Uplink MC-CDMA(Signal Processing for Communications)(Digital Signal Processing)
- Instruction-Level Power Estimation Method by Considering Hamming Distance of Registers(Selected Papers from the 16th Workshop on Circuits and Systems in Karuizawa)
- A 90nm 48×48 LUT-Based FPGA Enhancing Speed and Yield Utilizing Within-Die Delay Variations(Low-Power and High-Performance VLSI Circuit Technology,VLSI Technology toward Frontiers of New Market)
- A 90nm LUT Array for Speed and Yield Enhancement by Utilizing Within-Die Delay Variations(Digital,Low-Power, High-Speed LSIs and Related Technologies)
- A Resource-Shared VLIW Processor for Low-Power On-Chip Multiprocessing in the Nanometer Era(Digital, Low-Power LSI and Low-Power IP)
- A Leakage Reduction Scheme for Sleep Transistors with Decoupling Capacitors in the Deep Submicron Era(Electronic Circuits)
- D-10-5 An Instruction Decomposition Scheme to Aid Fine-Grained Online Recovery in Pipeline Processor
- C-12-60 Accurate Individual Gate Delay Measurement to Study Within-die Variations
- Analytical Model of Static Noise Margin in CMOS SRAM for Variation Consideration
- An Area/Delay Efficient Dual-Modular Flip-Flop with Higher SEU/SET Immunity
- Score-Level Fusion of Phase-Based and Feature-Based Fingerprint Matching Algorithms
- A Robust 3D Face Recognition Algorithm Using Passive Stereo Vision
- Architecture and Performance Evaluation of a New Functional Memory : Functional Memory for Addition (Special Section on VLSI Design and CAD Algorithms)
- A Real-Time Low-Rate Video Compression Algorithm Using Multi-Stage Hierarchical Vector Quantization (Special Section on VLSI for Digital Signal Processing)
- High-Accuracy Estimation of Image Rotation Using 1D Phase-Only Correlation
- A Passive 3D Face Recognition System and Its Performance Evaluation
- A Palmprint Recognition Algorithm Using Phase-Only Correlation
- A Fingerprint Matching Algorithm Using Phase-Only Correlation(Digital Signal Processing for Pattern Recognition)(Applications and Implementations of Digital Signal Processing)
- An Auction Protocol Preserving Privacy of Losing Bids with a Secure Value Comparison Scheme (Applications) (Cryptography and Information Security)
- B-5-83 Evaluation of Inter-code Interference on Uplink MC-CDMA
- High-Accuracy Subpixel Image Registration Based on Phase-Only Correlation(Digital Signal Processing)
- An Efficient Motion Estimation Algorithm Using a Gyro Sensor(Video/Image Coding)(Applications and Implementations of Digital Signal Processing)
- Variation-Tolerance of a 65-nm Error-Hardened Dual-Modular-Redundancy Flip-Flop Measured by Shift-Register-Based Monitor Structures
- Higher-Order Effect of Source--Drain Series Resistance on Saturation Drain Current in Sub-20 nm Metal--Oxide--Semiconductor Field-Effect Transistors
- NBTI-Induced Delay Degradation Analysis of FPGA Routing Structures
- A Radiation-Hard Redundant Flip-Flop to Suppress Multiple Cell Upset by Utilizing the Parasitic Bipolar Effect