A 45-nm 37.3 GOPS/W Heterogeneous Multi-Core SOC with 16/32 Bit Instruction-Set General-Purpose Core
نویسندگان
چکیده
We built a 12.4 mm × 12.4 mm, 45-nm CMOS, chip that integrates eight 648-MHz general purpose cores, two matrix processor (MX-2) cores, four flexible engine (FE) cores and media IP (VPU5) to establish heterogeneous multi-core chip architecture. The general purpose core had its IPC (instructions per cycle) performance enhanced by adding 32-bit instructions to the existing 16-bit fixed-length instruction set and executing up to two 32-bit instructions per cycle. Considering these five-toseven years of embedded LSI and increasing trend of access-master within LSI, we predict that the memory usage of single core will not exceed 32-bit physical area (i.e. 4 GB), but chip-total memory usage will exceed 4 GB. Based on this prediction, the physical address was expanded from 32-bit to 40-bit. The fabricated chip was tested and a parallel operation of eight general purpose cores and four FE cores and eight data transfer units (DTU) is obtained on AAC (Advanced Audio Coding) encode processing. key words: heterogeneous, instruction set, MMU
منابع مشابه
Writing Efficient Programs for the Motorola M.CORE Architecture
1. INTRODUCTION The M.CORE architecture is the latest addition to Motorola's 32 bit RISC family. This paper discusses several programming techniques that can be applied to the M.CORE architecture to yield better performance and code density. The techniques discussed in this paper are not specific to any given compiler and should be applicable any M.CORE processor. This paper is organized as fol...
متن کاملScalable Core-Based Methodology and Synthesizable Core for Systematic Design
Abstract— The strong demand for complex and high performance embedded system-on-chip (SoC) requires quick turn around design methodology and high performance cores. Thus, there is a clear need for new methodologies supporting efficient and fast design of these systems on complex platforms implementing both hardware and software modules. In this paper, we describe a novel scalable core-based (SC...
متن کاملA BDTI Analysis of the Analog Devices ADSP-BF5xx
Introduction The ADSP-BF5xx (Blackfin) is a family of 16-bit fixed-point dual-MAC processors from Analog Devices. The ADSP-BF5xx combines features typical of low-power DSPs with features traditionally associated with general-purpose processors, such as privilege modes and memory protection. The ADSP-BF5xx targets power-sensitive applications, such as cell phones; applications that require the f...
متن کاملHASHI: An Application Specific Instruction Set Extension for Hashing
Hashing is one of the most relevant operations within query processing. Almost all core database operators like groupby, selections, or different join implementations rely on highly efficient hash implementations. In this paper, we present a way to significantly improve performance and energy efficiency of hash operations using specialized instruction set extensions for the Tensilica Xtensa LX5...
متن کاملOptimizing the Control Hierarchy of an ECC Coprocessor Design on an FPGA Based SoC Platform
Most hardware/software codesigns of Elliptic Curve Cryptography only have one central control unit, typically a 32 bit or 8 bit processor core. With the ability of integrating several soft processor cores into one FPGA fabric, we can have a hierarchy of controllers in one SoC design. Compared to the previous codesigns trying to optimize the communication overhead between the central control uni...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- IEICE Transactions
دوره 94-C شماره
صفحات -
تاریخ انتشار 2011