MFU substitution algorithm: automaton model, synthesis and assessment of the hardware implementation

Main Article Content

Vadym Puidenko
https://orcid.org/0000-0002-6393-034X

Abstract

The substitution policy of the MFU (Most Frequently Used) algorithm is extending to the associative translation look-a-side buffer architecture. The hit event in the translation look-a-side buffer should call the event of fixing and using the corresponding element in the multitude of the data unit, which was addressed. The miss event should involve certain hardware logic to allow the processor core to make a decision about of the most frequently used element substitution in the data unit, taking into account the analysis of events fixing on access to certain elements at the hit events. The paper has developed automaton model of the policy with combinatorial approach of comparative analysis for fixed events of access. The automaton model is described by the corresponding discrete functions and the structural block diagram of the algorithm. The automaton model which was created and algorithmized caused the synthesis of the hardware substitution policy of the MFU algorithm for q - directed associative translation look-a-side buffer. The synthesis was founded on the mathematical apparatus of combinatorial synthesis of determining the enabled conditions for selecting q - directions. The result of the synthesis was logical equations of selection for q - directions with technical scheme solution of the substitution policy hardware and the detailed diagram block of the control algorithm. The synthesized hardware solution made it possible to make an assessment of complexity according to Quine by the number of poles of the circuit and by the total number of gates, that is allow to compute the probability of failure-free operation during the time of failures up to 100,000 hours with a probability of failures in 10-7 for a one gate. The paper also contains an assessment of the productivity for the developed hardware solution as for the miss event, as for the hit event.

Article Details

How to Cite
Puidenko, V. (2020). MFU substitution algorithm: automaton model, synthesis and assessment of the hardware implementation. Advanced Information Systems, 4(4), 57–63. https://doi.org/10.20998/2522-9052.2020.4.08
Section
Methods of information systems synthesis
Author Biography

Vadym Puidenko, Kharkiv RadioTechnical College, Kharkiv

Deputy Director of Production and Training, Expert of the higher category

References

Puidenko, V. and Kharchenko, V. (2020), “The Pseudo LRU Hardware Complexity Decreasing for Associative Cache Memory and Translation Look-a-Side Buffer”, CERes Journal, Vol. 6, Is. 1, pp. 142-153.

Sabarinathan, Sayiraman, Senthil Kumar, Dayalan and Shanmugavel Mani, Subbiah (2002), A Framework for MF-LRU (Most Frequently-Least Recently Used) Replacement Policy, available at:

https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.618.3125&rep=rep1&type=pdf

Hsin-Chuan, Chen and Jen-Shiun, Chiang (2007), “A high-performance sequential MRU cache using valid-bit assistant search algorithm”, Journal of Circuits, Systems, and Computers, Vol. 16, No. 4, pp. 613–626.

Sudarshan, T.S.B. Rahil Abbas, Mir and Vijayalakshmi, S. (2017), “Highly Efficient LRU Implementations for High Associativity Cache Memory”, Birla Institute of Technology and Science, Pilani, Rajasthan 330331 INDIA.

Safaa S., Omran and Ibrahim A., Amory (2018), “Implementation of LRU Replacement Policy for Reconfigurable Cache Memory Using FPGA”, 2018 International Conference on Advanced Science and Engineering, Kurdistan Region, Iraq, November, 12-14, pp.13-18.

Jaafar, Alghazo, Adil, Akaaboune and Nazeih, Botros (2004), “Cache Replacement Algorithm Records”, 2004 International Workshop on Memory Technology, Design and Testing, Illinois, USA, August, pp.19-24.

Alejandro, Valero, Julio, Sahuquillo, Salvador, Petit, Pedro, Lopez, and Jose, Duato (2019), “MRU-Tour-based Replacement Algorithms for Last-Level Caches”, Conference: 23rd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), Vitória (Brazil), DOI: https://doi.org/10.1109/SBAC-PAD.2011.13

Burhan U.l. Islam, Khan, Rashidah, Olanrewaju, Roohie, Naaz Mir, Abdul Raouf, Khan and Yusoff, S.H. (2017), “A Computationally Efficient P-LRU based Optimal Cache Heap Object Replacement Policy”, Int. Journal of Advanced Computer Science and Applications, Vol. 8, No. 1, pp. 128-139, DOI: https://doi.org/10.14569/IJACSA.2017.080118

Swadhesh, Kumar and Singh, P.K. (2016), “An Overview of Modern Cache Memory and Performance Analysis of Replacement Policies”, 2nd IEEE International Conference on Engineering and Technology, India, pp. 4145-4148, DOI: https://doi.org/10.1109/ICETECH.2016.7569243