On the use of fuzzy techniques in cache memory management Chun-Fu Kung System Laboratory, Department of Computer Engineering and Science, Yuan-Ze University,

Slides:



Advertisements
Similar presentations
Fuzzy Inference Systems
Advertisements

AI – CS364 Fuzzy Logic Fuzzy Logic 3 03 rd October 2006 Dr Bogdan L. Vrusias
Smart Shopper A Consumer Decision Support System Using Type-2 Fuzzy Logic Systems Ling Gu 2003 Fall CSc8810.
Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”
Using one level of Cache:
Virtual Memory Chapter 8.
How caches take advantage of Temporal locality
Virtual Memory Chapter 8. Hardware and Control Structures Memory references are dynamically translated into physical addresses at run time –A process.
Application of Learning Methodologies in Control of Power Electronics Drives J. L. da Silva Neto, L.G. Rolim, W. I. Suemitsu, L. O. A. P. Henriques, P.J.
Memory Problems Prof. Sin-Min Lee Department of Mathematics and Computer Sciences.
Fuzzy Logic E. Fuzzy Inference Engine. “antecedent” “consequent”
Improving Proxy Cache Performance: Analysis of Three Replacement Policies John Dilley and Martin Arlitt IEEE internet computing volume3 Nov-Dec 1999 Chun-Fu.
Virtual Memory Chapter 8.
1 Virtual Memory Chapter 8. 2 Hardware and Control Structures Memory references are dynamically translated into physical addresses at run time –A process.
1 Chapter 8 Virtual Memory Virtual memory is a storage allocation scheme in which secondary memory can be addressed as though it were part of main memory.
Defuuzification Techniques for Fuzzy Controllers Chun-Fu Kung System Laboratory, Department of Computer Engineering and Science, Yuan-Ze University, Taiwan,
Teachers Name : Suman Sarker Telecommunication Technology Subject Name : Computer Controller System & Robotics Subject Code : 6872 Semester :7th Department.
Maninder Kaur CACHE MEMORY 24-Nov
Presented By Ali Rıza KONAN Bogazici University
Fuzzy Rules 1965 paper: “Fuzzy Sets” (Lotfi Zadeh) Apply natural language terms to a formal system of mathematical logic
7-1 Chapter 7 - Memory Principles of Computer Architecture by M. Murdocca and V. Heuring © 1999 M. Murdocca and V. Heuring Principles of Computer Architecture.
7-1 Chapter 7 - Memory Department of Information Technology, Radford University ITEC 352 Computer Organization Principles of Computer Architecture Miles.
Computer Architecture and Operating Systems CS 3230: Operating System Section Lecture OS-8 Memory Management (2) Department of Computer Science and Software.
CSCI 232© 2005 JW Ryder1 Cache Memory Organization Direct Mapping Fully Associative Set Associative (very popular) Sector Mapping.
Computer Architecture Lecture 26 Fasih ur Rehman.
Virtual Memory Chapter 8. Hardware and Control Structures Memory references are dynamically translated into physical addresses at run time –A process.
Computer Science and Engineering Copyright by Hesham El-Rewini Advanced Computer Architecture CSE 8383 January Session 2.
Course presentation: FLA Fuzzy Logic and Applications 4 CTI, 2 nd semester Doru Todinca in Courses presentation.
1 Control Unit Operation and Microprogramming Chap 16 & 17 of CO&A Dr. Farag.
Fuzzy Inference Systems. Fuzzy inference (reasoning) is the actual process of mapping from a given input to an output using fuzzy logic. The process involves.
“Principles of Soft Computing, 2 nd Edition” by S.N. Sivanandam & SN Deepa Copyright  2011 Wiley India Pvt. Ltd. All rights reserved. CHAPTER 12 FUZZY.
Time Parallel Simulations I Problem-Specific Approach to Create Massively Parallel Simulations.
Evaluating Content Management Techniques for Web Proxy Caches Martin Arlitt, Ludmila Cherkasova, John Dilley, Rich Friedrich and Tai Jin Proceeding on.
11 Intro to cache memory Kosarev Nikolay MIPT Nov, 2009.
1 Fuzzy Versus Quantitative Association Rules: A Fair Data-Driven Comparison Shih-Ming Bai and Shyi-Ming Chen Department of Computer Science and Information.
Unit1: Modeling & Simulation Module5: Logic Simulation Topic: Unknown Logic Value.
Lectures 8 & 9 Virtual Memory - Paging & Segmentation System Design.
Cache Miss-Aware Dynamic Stack Allocation Authors: S. Jang. et al. Conference: International Symposium on Circuits and Systems (ISCAS), 2007 Presenter:
CAM Content Addressable Memory
1 An Execution-Driven Simulation Tool for Teaching Cache Memories in Introductory Computer Organization Courses Salvador Petit, Noel Tomás Computer Engineering.
1 Contents Memory types & memory hierarchy Virtual memory (VM) Page replacement algorithms in case of VM.
Dinner for Two. Fuzzify Inputs Apply Fuzzy Operator.
1 University of Maryland Using Information About Cache Evictions to Measure the Interactions of Application Data Structures Bryan R. Buck Jeffrey K. Hollingsworth.
Two Dimensional Highly Associative Level-Two Cache Design
CAM Content Addressable Memory
Expert System Structure
Cache Memory Presentation I
Fuzzy Logics.
Fuzzy logic Introduction 3 Fuzzy Inference Aleksandar Rakić
Virtual Memory Chapter 8.
Fuzzy System Structure
Dr. Unnikrishnan P.C. Professor, EEE
An Introduction to Cache Design
Interconnect with Cache Coherency Manager
Module IV Memory Organization.
CPSC 457 Operating Systems
Performance metrics for caches
Performance metrics for caches
Miss Rate versus Block Size
Virtual Memory Overcoming main memory size limitation
Dr. Unnikrishnan P.C. Professor, EEE
Contents Memory types & memory hierarchy Virtual memory (VM)
Part of knowledge base of fuzzy logic expert system for exercise control of diabetics
Chapter Five Large and Fast: Exploiting Memory Hierarchy
Module IV Memory Organization.
Fuzzy Inference Systems
Performance metrics for caches
Fuzzy Logic KH Wong Fuzzy Logic v.9a.
Chapter Contents 7.1 The Memory Hierarchy 7.2 Random Access Memory
Overview Problem Solution CPU vs Memory performance imbalance
Presentation transcript:

On the use of fuzzy techniques in cache memory management Chun-Fu Kung System Laboratory, Department of Computer Engineering and Science, Yuan-Ze University, Taiwan, Republic of China 2000/7/12 Hassan Diab, Ulrich Furbach, Hassan Tabbara

Outline Introduction Implementation Simulation Results Conclusion

Introduction Cache memories (CM) are high-speed buffers which are inserted between the processor and main memory (MM) to capture those portions of the contents of MM. The swapping of information between MM and CM requires a replacement algorithm (RA) to select a block frame (BF) to replace. Four placement policies: direct, fully associative, set associative, and sector mapping.

Sector mapping MM is partitioned into a number of sectors, each composed of a number of blocks. CM is partitioned into sector frames, each composed of a set of BFs. Only the block that caused the cache miss is brought into the cache, and the remaining BFs in that sector are flagged as invalid. The advantage of the mapping is that it reduce the cost of the map since it requires relatively few tags.

FL and FC Fuzzy logic (FL) and fuzzy control (FC) has proved to be a powerful tool when it is applied to ill-defined and complex systems. The basic concept underlying FL is that of a linguistic variable. FL systems deal with fuzzy consequents and/or fuzzy antecedents.

Implementation The FLRA used is composed of a 3-input and 1-output control system. The inputs are the frequency of reference (FREF), the CM hit ratio (HR), and the sector age (AGE). The output is the block replacement index (BRI), calculated for each BF.

Implementation (cont.) Step 1. Fuzzify inputs Step 2. Apply fuzzy operator Step 3. Apply implication Step 4. Aggregate all outputs Step 5. Defuzzify

Begin Word required in CM? Sector that this block belong in CM? Is there a place for a new sector in CM? Use the RA to selected a sector to replace Move the required block to CM Move the required Block from MM to CM Increment FREF by one Read word from CM Increment FREF by one Read the word required From the block End Y N Y Y N N

Results Use the same load: 30% read, 20% write and 10% jump The CM is composed of 64 words per block

Results (cont.) Load1: 15% read, 10% write and 5% jump Load1: 15% read, 5% write and 5% jump Load1: 5% read, 5% write and 5% jump CM: 16 words/block, 16 blocks/sector and 256 sectors

Conclusion We presented a fuzzy logic replacement algorithm (FLRA) for sector-mapped cache memory organization. These 24 fuzzy inference rules may be tuned further using expert knowledge to attain a further improvement in the performance.