Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Open Design of Dual Core Risc-V Multicore Processor

View through CrossRef
RISC-V set architecture has a significant effect on processor technology due to open instructions that enable researchers to build and enhance computing systems. So, in this paper, an open-source multicore RISC-V processor is implemented. The design is based on an open-source single RvCore processor (Taiga). Two cores of Taiga are integrated considering cache coherence, interconnect, and memory synchronization problems. Therefore, a solution has been developed to achieve data coherence between implemented caches and the main memory; its architecture is mainly based on snoopy protocol. Additionally, a hardware customized peripheral unit has been developed to achieve the synchronization process among working cores. For more consistent and highly controlled memory storage, main memory unit has been designed in dual-port based on AXI protocol in interface, and 4096 lines and word addressable unit. The processor has been implemented in System Verilog HDL. Moreover, extensive testing of the system on various test benches was conducted to assure correct functionality. Hence, the performance of the system has been assessed using standard multicore benchmark (CoreMark). The processor performance has been shown to be comparable to state-of-the-art results.
Title: Open Design of Dual Core Risc-V Multicore Processor
Description:
RISC-V set architecture has a significant effect on processor technology due to open instructions that enable researchers to build and enhance computing systems.
So, in this paper, an open-source multicore RISC-V processor is implemented.
The design is based on an open-source single RvCore processor (Taiga).
Two cores of Taiga are integrated considering cache coherence, interconnect, and memory synchronization problems.
Therefore, a solution has been developed to achieve data coherence between implemented caches and the main memory; its architecture is mainly based on snoopy protocol.
Additionally, a hardware customized peripheral unit has been developed to achieve the synchronization process among working cores.
For more consistent and highly controlled memory storage, main memory unit has been designed in dual-port based on AXI protocol in interface, and 4096 lines and word addressable unit.
The processor has been implemented in System Verilog HDL.
Moreover, extensive testing of the system on various test benches was conducted to assure correct functionality.
Hence, the performance of the system has been assessed using standard multicore benchmark (CoreMark).
The processor performance has been shown to be comparable to state-of-the-art results.

Related Results

Innovations in Multicore Network Processor Design for Enhanced Performance
Innovations in Multicore Network Processor Design for Enhanced Performance
The rapid expansion of network traffic, driven by the proliferation of internet-connected devices and the growing demand for high-speed data transmission, has intensified the need ...
Evaluation of Intel i7 Core Processor
Evaluation of Intel i7 Core Processor
The Intel Nehalem microarchitecture that encompasses the Core i7 class of processors uses a 45nm fabrication process for different processors in the Core i7 family. Besides using t...
Implementation of 64-Bit RISC Processor Using Vedic Multiplier
Implementation of 64-Bit RISC Processor Using Vedic Multiplier
Abstract: In this project, 64 bit RISC processor designed with Vedic multiplier design. Reduced Instruction Set Computer (RISC) is a design which presents better performances, high...
Design of a dual-issue RISC-V processor
Design of a dual-issue RISC-V processor
Abstract A dual-issue 32-bit RISC-V processor is designed and reported. In order to evaluate the performance of the dual-issue processor, a single-issue processor ba...
Probabilistically time-analyzable complex processor designs
Probabilistically time-analyzable complex processor designs
Industry developing Critical Real-Time Embedded Systems (CRTES), such as Aerospace, Space, Automotive and Railways, faces relentless demands for increased guaranteed processor perf...
Efficient data movement in large-scale heterogeneous systems
Efficient data movement in large-scale heterogeneous systems
(English) Modern computer systems have become universally heterogeneous. Computer architects have addressed the slowdown of Moore’s Law and the end of Dennard scaling by incorporat...
FPGA and ASIC accelerators for genome data analysis
FPGA and ASIC accelerators for genome data analysis
(English) The continuous progress of Moore’s Law in improving single-threaded performance (execution time) through clock frequency and process node improvements has slowed down du...

Back to Top