Please wait a minute...
购物车 申请加入邮件组 English
高级检索 图表检索
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

邮发代号 80-970

2019 Impact Factor: 1.275

热点文章  |  下载排行  |  浏览排行
在线投稿 免费RSS订阅
Frontiers of Computer Science  2025, Vol. 19 Issue (1): 191103   https://doi.org/10.1007/s11704-023-3239-x
  本期目录
RVAM16: a low-cost multiple-ISA processor based on RISC-V and ARM Thumb
Libo HUANG, Jing ZHANG, Ling YANG, Sheng MA, Yongwen WANG, Yuanhu CHENG()
College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China
 全文: PDF(13942 KB)   HTML
Abstract：

The rapid development of ISAs has brought the issue of software compatibility to the forefront in the embedded field. To address this challenge, one of the promising solutions is the adoption of a multiple-ISA processor that supports multiple different ISAs. However, due to constraints in cost and performance, the architecture of a multiple-ISA processor must be carefully optimized to meet the specific requirements of embedded systems. By exploring the RISC-V and ARM Thumb ISAs, this paper proposes RVAM16, which is an optimized multiple-ISA processor microarchitecture for embedded devices based on hardware binary translation technique. The results show that, when running non-native ARM Thumb programs, RVAM16 achieves a significant speedup of over 2.73× with less area and energy consumption compared to using hardware binary translation alone, reaching more than 70% of the performance of native RISC-V programs.
Key words： multiple-ISA processor    architecture    binary translation    RISC-V    embedded
收稿日期: 2023-03-23      出版日期: 2024-03-18
Corresponding Author(s): Yuanhu CHENG   
 引用本文:   
. [J]. Frontiers of Computer Science, 2025, 19(1): 191103.
Libo HUANG, Jing ZHANG, Ling YANG, Sheng MA, Yongwen WANG, Yuanhu CHENG. RVAM16: a low-cost multiple-ISA processor based on RISC-V and ARM Thumb. Front. Comput. Sci., 2025, 19(1): 191103.
 链接本文:  
https://academic.hep.com.cn/fcs/CN/10.1007/s11704-023-3239-x
https://academic.hep.com.cn/fcs/CN/Y2025/V19/I1/191103
Technique Pros Cons
Multi-core Independent performance for different ISAs High hardware cost
Multi-decoder Same performance for different ISAs Complex pipeline
HBT Low hardware cost Lower performance for non-native ISA
Tab.1  
Fig.1  
Fig.2  
ARM Thumb registers (encoding) RISC-V registers (encoding)
R0−R7 (000−111) R16−R23 (10000−10111)
R8−R12 (1000−1100) R24−R28 (11000−11100)
SP (1101) R29 (11101)
LR (1110) R30 (11110)
PC (1111) PC/R31 (11111)
Tab.2  
Fig.3  
Fig.4  
Fig.5  
Instruction category Instruction Translation ratio
Without optimization With optimization
Move MOV Rd, Rm 1 1
MOV PC, Rm 1 1
MOV Rd, PC 2 2
MOVS Rd, Rm 4 1
MOVS Rd, imm 4 1
Add ADD Rd, SP, imm 1 1
ADD Rd, Rd, Rm 1 1
ADD Rd, Rd, PC 2 2
ADD PC, PC, Rm 3 3
ADR Rd, <label> 3 3
ADDS Rd, Rd, imm 8 1
ADDS Rd, Rm, Rn 9 1
ADDS Rd, Rm, imm 9 1
ADCS Rd, Rd, Rm 16 1
Subtract SUB SP, SP, imm 2 2
SUBS Rd, Rm, Rn 17 1
SBCS Rd, Rd, Rm 17 1
RSBS Rd, Rm, 0 17 1
SUBS Rd, Rm, imm 18 1
SUBS Rd, Rd, imm 18 1
Multiply MUL Rd, Rm, Rd 4 1
Compare CMN Rm, imm 8 1
CMP Rm, Rn 16 1
CMP Rn, imm 17 2
Logic LOPaRd, Rd, Rm 4 1
BICS Rd, Rd, Rm 5 2
Shift SOPbRd, Rd, Rm 8 1
SOPbRd, Rm, imm 9 1
RORS Rd, Rd, Rm 10 6
Load LDRIc Rd, Rm, imm 1 1
LDRRd Rd, Rm, Rn 2 2
LDR Rd, <label> 3 3
LDM Rm, registers ne ne
Store STRXf Rd, Rm, imm 1 1
STRXf Rd, Rm, Rn 2 2
STM Rm, registers ne ne
Stack POP registers ne ne
PUSH registers ne ne
Branch BXXg 1 1
BGT 4 1
BLE 4 1
Extend EOP Rd, Rm 2 2
Reverse REVSH Rd, Rm 5 5
REV Rd, Rm 11 11
REV16 Rd, Rm 11 11
Tab.3  
Fig.6  
Fig.7  
Real case Kernel program Execution time
RISC-V Thumb
Communication program UART 1.10 1.23
Temperature control system Sensor access 1.19 1.38
Flash control system Flash access 1.50 1.53
Tab.4  
Name Technique Native ISA Non-native ISA Slowdown
Software QEMU [6] DBT X86/ARM/Other RISC-V 7.07× [12]
QEMU DBT RISC-V X86 more than 3.50× [23]
RV8 [9] DBT X86 RISC-V 2.60×
Lupori et al. [12] SBT X86/ARM RISC-V 1.12×/1.35×
Hardware Capella et al. [18] HBT + extended MIPS MIPS X86/ARM/PowerPC about 1.57×/2.03×/2.22×
HBT HBT RISC-V ARM 4.89×
RVAM16 HBT + hardware optimization RISC-V ARM 1.40×
Tab.5  
Core Area (μm2) Benchmark (Target ISA) Power (mW) Relative energy
Static Dynamic Total
RVAM16 24269.28 Dhrystone (RISC-V) 1.69 1.51 3.20 0.84
CoreMark (RISC-V) 1.69 1.59 3.28 0.90
Dhrystone (ARM Thumb) 1.71 1.70 3.41 1.25
CoreMark (ARM Thumb) 1.70 1.78 3.48 1.26
RISC-V + HBT 26658.41 Dhrystone (RISC-V) 1.86 1.48 3.34 0.87
CoreMark (RISC-V) 1.86 1.55 3.41 0.94
Dhrystone (ARM Thumb) 1.87 1.77 3.64 3.65
CoreMark (ARM Thumb) 1.87 1.71 3.58 5.59
Base RISC-V Core 20757.91 Dhrystone (RISC-V) 1.37 1.42 2.79 0.73
CoreMark (RISC-V) 1.36 1.53 2.89 0.79
Ibex 32802.67 Dhrystone (RISC-V) 2.29 2.70 4.99 0.93
CoreMark (RISC-V) 2.29 3.26 5.55 1.04
Cortex-M0 26264.45 Dhrystone (ARM Thumb) 2.41 1.80 4.21 1.00
CoreMark (ARM Thumb) 2.41 1.85 4.26 1.00
Tab.6  
Fig.8  
  
  
  
  
  
  
1 T, Adegbija A, Rogacs C, Patel A Gordon-Ross . Microprocessor optimizations for the internet of things: a survey. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018, 37( 1): 7–20
2 K, Saso Y Hara-Azumi . Simple instruction-set computer for area and energy-sensitive IoT edge devices. In: Proceedings of the 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP). 2018, 1−4
3 K, Saso Y Hara-Azumi . Revisiting simple and energy efficient embedded processor designs toward the edge computing. IEEE Embedded Systems Letters, 2020, 12( 2): 45–49
4 R L, Sites A, Chernoff M B, Kirk M P, Marks S G Robinson . Binary translation. Communications of the ACM, 1993, 36( 2): 69–81
5 Apple Inc. About the Rosetta translation environment. See developer.apple.com/documentation/apple-silicon/about-the-rosetta-translation-environment website, Accessed: 2023
6 F Bellard . QEMU, a fast and portable dynamic translator. In: Proceedings of the USENIX Annual Technical Conference. 2005, 41−46
7 D Y, Hong C C, Hsu P C, Yew J J, Wu W C, Hsu P, Liu C M, Wang Y C Chung . HQEMU: a multi-threaded and retargetable dynamic binary translator on multicores. In: Proceedings of the 10th International Symposium on Code Generation and Optimization. 2012, 104−113
8 B, Ilbeyi D, Lockhart C Batten . Pydgin for RISC-V: a fast and productive instruction-set simulator. In: Proceedings of the 3rd RISC-V Workshop. 2016
9 M, Clark B Hoult . rv8: a high performance RISC-V to x86 binary translator. In: Proceedings of the 1st Workshop on Computer Architecture Research with RISC-V (CARRV). 2017
10 C, Sabri L, Kriaa S L Azzouz . Comparison of IoT constrained devices operating systems: a survey. In: Proceedings of the 14th International Conference on Computer Systems and Applications (AICCSA). 2017, 369−375
11 B Y, Shen J Y, Chen W C, Hsu W Yang . LLBT: an LLVM-based static binary translator. In: Proceedings of 2012 International Conference on Compilers, Architectures and Synthesis for Embedded Systems. 2012, 51−60
12 L, Lupori V, Rosario E Borin . Towards a high-performance RISC-V emulator. In: Proceedings of 2018 Symposium on High Performance Computing Systems (WSCAD). 2018, 213−220
13 A, Venkat D M Tullsen . Harnessing ISA diversity: design of a heterogeneous-ISA chip multiprocessor. In: Proceedings of the 41st International Symposium on Computer Architecture (ISCA). 2014, 121−132
14 A, Venkat H, Basavaraj D M Tullsen . Composite-ISA cores: enabling multi-ISA heterogeneity using a single ISA. In: Proceedings of 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). 2019, 42−55
15 J, Balkind K, Lim M, Schaffner F, Gao G, Chirkov A, Li A, Lavrov T M, Nguyen Y, Fu F, Zaruba K, Gulati L, Benini D Wentzlaff . BYOC: a ”bring your own core” framework for heterogeneous-ISA research. In: Proceedings of the 25th International Conference on Architectural Support for Programming Languages and Operating Systems. 2020, 699−714
16 S, Rokicki E, Rohou S Derrien . Hybrid-DBT: hardware/software dynamic binary translation targeting VLIW. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2019, 38( 10): 1872–1885
17 F M, Capella M, Brandalero L, Carro A C S Beck . A multiple-ISA reconfigurable architecture. Design Automation for Embedded Systems, 2015, 19( 4): 329–344
18 J, Fajardo M B, Rutzig L, Carro A C S Beck . Towards a multiple-ISA embedded system. Journal of Systems Architecture, 2013, 59( 2): 103–119
19 K, Chai F, Wolff C Papachristou . XBT: FPGA accelerated binary translation. In: Proceedings of IEEE National Aerospace and Electronics Conference. 2021, 365−372
20 S, Rokicki E, Rohou S Derrien . Hardware-accelerated dynamic binary translation. In: Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE). 2017, 1062−1067
21 A, Waterman K Asanovic . The RISC-V instruction set manual: volume I: unprivileged ISA. 2019
22 ARM. ARM® Cortex®-M0 DesignStartTM RTL Testbench: user guide . 2015
23 W, Wang X, Liu J, Yu J, Li Z, Mao Z, Li C, Ding C Zhang . The design and building of openKylin on RISC-V architecture. In: Proceedings of the 15th International Conference on Advanced Computer Theory and Engineering (ICACTE). 2022, 88−91
[1] FCS-23239-OF-LH_suppl_1 Download
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed