A design of EPIC type processor based on MIPS architecture
Pages 59 - 63
Abstract
This paper proposes an EPIC (Explicitly Parallel Instruction Computing Architecture) type processor based on MIPS. VLIW processors can execute multiple instructions simultaneously, but due to dependency of instructions, it is often impossible to execute maximum parallel execution. As a result, program contains many NOP instructions. EPIC processor can reduce NOP instructions by changing number of instructions to be executed simultaneously. To implement EPIC type processor, five bit field is embedded in the machine instruction code. For comparison, a 5-stage pipeline processor (basic processor), and a Very Long Instruction Word (VLIW) processor are designed. The proposed processors are described in hardware description language (VHDL) and implemented using FPGA. Operations are confirmed by software Tera Term. Processors are evaluated for instruction parallelism and program size using bubble sort program. It is confirmed that the proposed processor is 1.9 times faster than the basic processor. In addition, the program size of the proposed processor is 64 bytes, the basic processor is 56 bytes, and the VLIW processor is 80 bytes.
References
[1]
Harris DM and Harris SL Digital design and computer architecture 2009 Tokyo Shoeisha
[2]
Hennessy JL and Patterson DA Computer architecture: a quantitative approach 5/E 2014 USA Morgan Kaufmann
[3]
Chu WWS, Dimond RG, Perrott S et al. (2004) Customisable EPIC Processor: Architecture and Tools. Proceedings Design, Automation and Test in Europe Conference and Exhibition, Paris, France, Vol. 3, pp 236–241
[4]
Nakada T, Kataoka A, and Nakashima Y An instruction scheduling method with VLIW instruction queue for superscalar processors Inf Process Soc Jpn 2009 2 2 48-62
[5]
Tyson, Romas AL, SI P, et al. (2009) A pipelined double-issue MIPS based processor architecture. International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Kanazawa, Japan, Dec 7–9, 2009, pp 583–586
[6]
Santos R, Azevedo R, Araujo G (2006) 2D-VLIW: an architecture based on the geometry of computation. IEEE 17th International Conference on Application-specific Systems, Architectures and Processors (ASAP), steamboat Springs, CO, USA, 11–13 Sept, 2006, pp 87–94
[7]
Darsch A, Andre´ Seznec (2004) IATO: a flexible EPIC simulation environment. Proceedings of the 16th Symposium on Computer Architecture and High Performance Computing, Foz do Iguacu, PR, Brazil, 27–29 Oct. 2004, pp 58–65
[8]
Kobayashi Y, Kobayashi S, Sakanushi K, et al. HDL generation method for configurable VLIW processor J Inf Process (JIP) 2004 45 5 1311-1320
[9]
Komatsu H, Koseki A, Suzuki E, et al. Parallel executing mechanisms in the extended VLIW processor GIFT J Inf Process (JIP) 1993 34 12 2599-2611
[10]
Colwell RP, Nix RP, O’Donnell JJ, et al. A VLIW architecture for a trace scheduling compiler IEEE Trans Comput 1988 37 8 967-979
[11]
Brandon A, Hoozemans J, Straten J et al. (2015) A sparse VLIW instruction encoding scheme compatible with generic binaries, 2015 International Conference on ReConFigurable Computing and FPGAs (ReConFig), Mexico City, Mexico, 7–9 Dec 2015
[12]
Hübener B, Sievers G, Jungeblut T (2014) CoreVA: a configurable resource-efficient VLIW processor architecture, 2014 12th IEEE International Conference on Embedded and Ubiquitous Computing, Milano, Italy, 26–28 Aug 2014, pp 9–16
[13]
Sharangpani H and Arora K Itanium processor microarchitecture IEEE Micro 2000 20 5 24-43
Index Terms
- A design of EPIC type processor based on MIPS architecture
Index terms have been assigned to the content through auto-classification.
Recommendations
An Improved Pipelined Processor Architecture Eliminating Branch and Jump Penalty
ICCEA '10: Proceedings of the 2010 Second International Conference on Computer Engineering and Applications - Volume 01Control dependencies are one of the major limitations to increase the performance of pipelined processors. This paper deals with eliminating penalties in pipelined processor. We present our discussion in the light of MIPS pipelined processor ...
Design of FPGA Based Instruction Fetch & Decode Module of 32-bit RISC (MIPS) Processor
CSNT '11: Proceedings of the 2011 International Conference on Communication Systems and Network TechnologiesIn this paper, we analyze MIPS instruction format instruction data path decoder module function and design theory based on RISC CPU instruction set. Furthermore, we design instruction fetch (IF) module of 32-bit CPU based on RISC CPU instruction set. ...
Code size minimization and retargetable assembly for custom EPIC and VLIW instruction formats
PICO is a fully automated system for designing the architecture and the microarchitecture of VLIW and EPIC processors. A serious concern with this class of processors, due to their very long instructions, is their code size. One focus of this paper is ...
Comments
Information & Contributors
Information
Published In
© International Society of Artificial Life and Robotics (ISAROB) 2019.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 February 2020
Accepted: 23 August 2019
Received: 23 April 2019
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 11 Feb 2025