memory systems
play

Memory Systems Overview of the NAND Flash High- Speed Interfacing - PowerPoint PPT Presentation

Apr 15, 2023 •378 likes •841 views

IEE5008 Autumn 2012 Memory Systems Overview of the NAND Flash High- Speed Interfacing and Controller Architecture Nina Mitiukhina Electrical Engineering and Computer Science International Graduate Program National Chiao Tung University

  1. IEE5008 – Autumn 2012 Memory Systems Overview of the NAND Flash High- Speed Interfacing and Controller Architecture Nina Mitiukhina Electrical Engineering and Computer Science International Graduate Program National Chiao Tung University ninusyamit@gmail.com Chih-Yuan, Chang 2012 Nina, Mitiukhina 2012

  2. Outline  Introduction  NAND Flash Background  NAND Flash Device Operation  NAND Flash Interface  NAND Flash Controller Functions  The ONFI Standard  Challenge of designing ONFI 3.0  Overview of Specific NAND Flash Controller Features  Conclusions  Reference Nina, Mitiukhina 2 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  3. Introduction  NAND Flash enabling new markets Nina, Mitiukhina 3 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  4. Introduction  NAND Flash pricing converges with HDD Nina, Mitiukhina 4 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  5. Introduction  Price/performance positioning of different storage technologies  With the use of new sophisticated controllers, SSDs are getting closer to having best of both worlds – HDD costs and DRAM like performance Nina, Mitiukhina 5 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  6. Introduction  Growing need for higher speed interfacing NAND Nina, Mitiukhina 6 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  7. Introduction  Performance demand with a growth of storage interface Nina, Mitiukhina 7 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  8. Introduction  Comparison of the number of bits for various memory storage arrays Nina, Mitiukhina 8 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  9. NAND Flash Background  A little bit oh history: Toshiba’s Flash Memory chronicle Nina, Mitiukhina 9 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  10. NAND Flash Background  Inherent limitations of NAND Flash Technology  Shipped with a number of bad blocks  Requires a serialized data interface  After experiencing multiple erase cycles, is wearing down; reliability degradation Nina, Mitiukhina 10 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  11. NAND Flash Background  NAND SD vs. MMC Nina, Mitiukhina 11 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  12. NAND Flash Background  NAND vs. NOR Nina, Mitiukhina 12 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  13. NAND Flash Background  SLC vs. MLC  Complicated programming sequence Nina, Mitiukhina 13 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  14. NAND Flash Background  SLC vs. MLC  Smaller memory window between neighbouring levels Nina, Mitiukhina 14 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  15. NAND Flash Background  SLC vs. MLC  Degraded performance Nina, Mitiukhina 15 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  16. NAND Flash Background  Data Organization Nina, Mitiukhina 16 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  17. NAND Flash Device Operation  Block erase Nina, Mitiukhina 17 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  18. NAND Flash Device Operation  Read operation  Page opening (~ 50us)  Data transfer (~ 20ns) Nina, Mitiukhina 18 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  19. NAND Flash Device Operation  Write operation (part 1)  Incremental Step Pulse Programming plus verify scheme Nina, Mitiukhina 19 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  20. NAND Flash Device Operation  Write sequence (part 2)  Shift data in shift registers  Issue command to program data into page Nina, Mitiukhina 20 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  21. NAND Flash device Operation  Interleave access Data bandwidth: Data transfer time + Page access time Nina, Mitiukhina 21 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  22. NAND Flash Interface  NAND Flash Interface Evolution Nina, Mitiukhina 22 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  23. NAND Flash Interface  SDR Asynchronous vs. Toggle Mode DDR  Faster Operation Speed  Less Power Consumption Asynchronous Interface with bi-directional DQS signal for reads and writes Nina, Mitiukhina 23 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  24. NAND Flash Controller  Improves chip performance  Integrated controller  Smaller chip size  Cheaper cost  Dedicated (External) controller  Faster time to the market  More flexible design, large variety of compatible parts available on the market Nina, Mitiukhina 24 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  25. NAND Flash Controller  Example: Flexible ONFI 2.2 compliant Controller for High Capacity MLC and High-Speed Data Transfer Nina, Mitiukhina 25 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  26. NAND Flash Controller  Brief description of functional blocks:  DCU – Design Control Unit  Provide enable/disable signal to the DMA, SUI units, ECC module; provide control signal to NCU.  Execute boot sequence.  Interrupt controller.  SIU – Signalling Interface Unit  Coordinating interaction between the system interface and internal bus.  DMA – Direct Memory Access  Speeds up data transfer between a device on the system bus and a memory, decreasing system bus burden. Nina, Mitiukhina 26 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  27. NAND Flash Controller  Brief description of functional blocks (part 2):  FIFO – 32 bit wide module  Data transferring between input module and NCU when command sequence is executed.  NCU – NAND Controller Unit  Responsible for generation of the device access sequences.  ECC – Error Correction unit  Correction code calculation.  PHY  Provides DDR data interface for the new high-speed devices. Nina, Mitiukhina 27 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  28. NAND Flash Controller  Core implementation results  ASIC  FPGA (Altera vs. Xylinx) Nina, Mitiukhina 28 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  29. ONFI Standard Recognizing the need for a common NAND interface, the ONFI Workgroup formed in May 2006 . Today the ecosystem is comprised of NAND Flash users and suppliers, including more than 100 leading technology companies. Nina, Mitiukhina 29 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  30. ONFI Standard  Major changes in ONFI revisions Nina, Mitiukhina 30 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  31. Challenge of designing ONFI 3.0  Released on March 15, 2011  NV-DDR2 interface enabling 400MT/s  Differential signaling for DQS and RE  DQS latency adjustment  External Vref  On-Die-Termination  Reduced input voltage levels (SSTL_18)  Vpp enablement Nina, Mitiukhina 31 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  32. Challenge of designing ONFI 3.0  MLC, SLC performance Nina, Mitiukhina 32 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  33. Challenge of designing ONFI 3.0  Data Interface Support Nina, Mitiukhina 33 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  34. Challenge of designing ONFI 3.0  Differential Signaling  Twice the noise immunity of the single ended signaling  Reduced sensitivity to SSO (simultaneously switching output noise)  Electromagnetic Interference reduction  Enhanced Common Mode Noise tolerance Nina, Mitiukhina 34 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  35. Challenge of designing ONFI 3.0  DQS latency adjustment  Pre-toggles DQS until valid DQS is stabilized  Tighter control of duty ratio  Adjustable latency – from 1 to 4 cycles Nina, Mitiukhina 35 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  36. Challenge of designing ONFI 3.0  Signalling Features (Vref + SSTL_18)  SSTL_18 Signaling  > 200 MT/s only supported with 1.8 Vcc  Industry Standard compatible  Higher speed, lower power consumption  External Vref  Reduce effects from external GND bounce  Enables tighter setups/holds due to controlled voltage reference Nina, Mitiukhina 36 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  37. Challenge of designing ONFI 3.0  On-Die-Termination Challenge of designing ONFI 3.0 Nina, Mitiukhina 37 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  38. Overview of Specific NAND Flash Controller Features  Error Correction  Bad Block Management  Wear Leveling strategies Nina, Mitiukhina 38 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  39. Error Correction  ECC requirement range from 1-bit correction per 512 bytes to 40-bit per 1kbyte. , where N in the number of bits per block, E is the number of errors in a block and p is a bit error rate Nina, Mitiukhina 39 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  40. Error Correction  Overview of relative ECC strength Nina, Mitiukhina 40 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

  41. Bad Block Management  Skip Block Method  Algorithm creates the bad block table, data is stored in the next good block, skipping the bad block.  Reserve Block Method  Bad blocks are not skipped but replaced by good blocks by redirecting FTL to a known free good block. Nina, Mitiukhina 41 Chih-Yuan, Chang NCTU IEE5008 Memory Systems 2012

Recommend

Memory II. Memory improvement III. Problems with memory 3 systems/stages of Memory: memory

Memory II. Memory improvement III. Problems with memory 3 systems/stages of Memory: memory

Main Focus I. Memory as a process Memory II. Memory improvement III. Problems with memory 3 systems/stages of Memory: memory the process by which I. Sensory Memory information is - acquired, II. Short -Term Memory - stored,

169 views • 5 slides
Abstractions for Practical Systems Caching and the memory hierarchy Operating systems and the

Abstractions for Practical Systems Caching and the memory hierarchy Operating systems and the

CS 240 Stage 3 Abstractions for Practical Systems Caching and the memory hierarchy Operating systems and the process model Virtual memory Dynamic memory allocation Victory lap Memory Hierarchy: Cache Memory hierarchy Cache basics Locality

1.02k views • 49 slides
Operating Systems WT 2019/20 Memory Management Shared Memory Process 1 virtual memory most

Operating Systems WT 2019/20 Memory Management Shared Memory Process 1 virtual memory most

Operating Systems WT 2019/20 Memory Management Shared Memory Process 1 virtual memory most modern OSs provide a way for processes to share Physical memory memory compiler e.g. code pages for image executables Process 2 virtual

511 views • 29 slides
UMBC M A L F T U M B C I O M Y O T R 1 (April 10, 2000 12:36 pm) I E S R C

UMBC M A L F T U M B C I O M Y O T R 1 (April 10, 2000 12:36 pm) I E S R C

Systems Programming 8086/88 Memory Interface II CMPE 310 Memory Address Decoding The processor can usually address a memory space that is much larger than the memory space covered by an individual memory chip. In order to splice a memory device

713 views • 21 slides
Memory Consistency Don Porter 1 CSE 506: Opera.ng Systems Logical Diagram Binary Memory

Memory Consistency Don Porter 1 CSE 506: Opera.ng Systems Logical Diagram Binary Memory

CSE 506: Opera.ng Systems Memory Consistency Don Porter 1 CSE 506: Opera.ng Systems Logical Diagram Binary Memory Threads Formats Allocators User System Calls Kernel RCU File System Networking Sync Todays Lecture Memory Memory

306 views • 19 slides
1 Brenda Milner 1918 There are Two Major Forms of Long Term Memory Explicit (Declarative)

1 Brenda Milner 1918 There are Two Major Forms of Long Term Memory Explicit (Declarative)

The Study of Memory Has Two Parts: Cellular Mechanisms of Learning (1) The Systems Problem of Memory: Where in the brain is memory stored? and the Biological Basis of Individuality (2) The Molecular Problem of Memory: How is memory stored at

536 views • 8 slides
Distributed Shared Memory Shared memory : difficult to realize vs . easy to program with.

Distributed Shared Memory Shared memory : difficult to realize vs . easy to program with.

CSCE 613 : Operating Systems Memory Models CSCE 613: Interlude: Distributed Shared Memory Shared Memory Systems Consistency Models Distributed Shared Memory Systems page based shared-variable based Reading (old!):

679 views • 21 slides
Memory Systems Design & Programming CMPE 310 Memory Address Decoding The processor can

Memory Systems Design & Programming CMPE 310 Memory Address Decoding The processor can

Memory Systems Design & Programming CMPE 310 Memory Address Decoding The processor can usually address a memory space that is much larger than the memory space covered by an individual memory chip. In order to splice a memory device into

363 views • 21 slides
Memory Systems Memory speed has been slow compared to the speed of the processor A process

Memory Systems Memory speed has been slow compared to the speed of the processor A process

Computer Memory System Overview Historically, the limiting factor in a computers performance has been memory access time Memory Systems Memory speed has been slow compared to the speed of the processor A process could be

455 views • 7 slides
CS333 Intro to Operating Systems Jonathan Walpole Memory Management Memory Management Memory

CS333 Intro to Operating Systems Jonathan Walpole Memory Management Memory Management Memory

CS333 Intro to Operating Systems Jonathan Walpole Memory Management Memory Management Memory a linear array of bytes - Holds O.S. and programs (processes) - Each cell (byte) is named by a unique memory address Recall, processes are

576 views • 55 slides
CSC2/458 Parallel and Distributed Systems Parallel Memory Systems: Coherence Sreepathi Pai

CSC2/458 Parallel and Distributed Systems Parallel Memory Systems: Coherence Sreepathi Pai

CSC2/458 Parallel and Distributed Systems Parallel Memory Systems: Coherence Sreepathi Pai February 06, 2018 URCS Outline Introduction to Parallel Memory Systems Memory Systems in Parallel Processors Coherence Implementations in Hardware

571 views • 34 slides
CSC2/458 Parallel and Distributed Systems Parallel Memory Systems Consistency Sreepathi Pai

CSC2/458 Parallel and Distributed Systems Parallel Memory Systems Consistency Sreepathi Pai

CSC2/458 Parallel and Distributed Systems Parallel Memory Systems Consistency Sreepathi Pai February 8, 2018 URCS Outline Memory Consistency Programming on Relaxed Consistency Machines Memory Models for Languages Special Relativity

375 views • 36 slides
Memory Systems Design & Programming CMPE 310 Memory Types Two basic types: ROM:

Memory Systems Design & Programming CMPE 310 Memory Types Two basic types: ROM:

Memory Systems Design & Programming CMPE 310 Memory Types Two basic types: ROM: Read-only memory RAM: Read-Write memory Four commonly used memories: ROM Flash, EEPROM Static RAM (SRAM) Dynamic RAM (DRAM), SDRAM,

687 views • 12 slides
CHAPTER X MEMORY SYSTEMS READ MEMORY NOTES ON COURSE WEBPAGE (BELOW) REA D pp 399-426 ( 285-310 ),

CHAPTER X MEMORY SYSTEMS READ MEMORY NOTES ON COURSE WEBPAGE (BELOW) REA D pp 399-426 ( 285-310 ),

INTRO. TO COMP. ENG. CHAPTER X CHAPTER X-1 MEMORY SYSTEMS CHAPTER X MEMORY SYSTEMS READ MEMORY NOTES ON COURSE WEBPAGE (BELOW) REA D pp 399-426 ( 285-310 ), MANO AND KIME & www.ece.gatech.edu/

616 views • 34 slides
CHAPTER X MEMORY SYSTEMS READ MEMORY NOTES ON COURSE WEBPAGE CONSIDER READING PAGES 285-310 FROM

CHAPTER X MEMORY SYSTEMS READ MEMORY NOTES ON COURSE WEBPAGE CONSIDER READING PAGES 285-310 FROM

INTRO. TO COMP. ENG. CHAPTER X CHAPTER X-1 MEMORY SYSTEMS CHAPTER X MEMORY SYSTEMS READ MEMORY NOTES ON COURSE WEBPAGE CONSIDER READING PAGES 285-310 FROM MANO AND KIME OTHER USEFUL RAM MATERIAL AT ARS TECHNICA R.M. Dansereau; v.1.0

596 views • 33 slides
Memory Systems Survey on the Off-Chip Scheduling of Memory Accesses in the Memory Interface of

Memory Systems Survey on the Off-Chip Scheduling of Memory Accesses in the Memory Interface of

IEE5008 Autumn 2012 Memory Systems Survey on the Off-Chip Scheduling of Memory Accesses in the Memory Interface of GPUs Garrido Platero, Luis Angel EECS Graduate Program National Chiao Tung University luis.garrido.platero@gmail.com Luis

891 views • 36 slides
CSCI [4|6]730 Operating Systems Main Memory Maria Hybinette, UGA Maria Hybinette, UGA Memory

CSCI [4|6]730 Operating Systems Main Memory Maria Hybinette, UGA Maria Hybinette, UGA Memory

CSCI [4|6]730 Operating Systems Main Memory Maria Hybinette, UGA Maria Hybinette, UGA Memory Questions? What is main memory? How does multiple processes share memory space? Key is how do they refer to the memory addresses.

759 views • 31 slides
Embedded systems: Memory Mapped I/O Memory mapped I/O is a method of performing input/output

Embedded systems: Memory Mapped I/O Memory mapped I/O is a method of performing input/output

Embedded systems: Memory Mapped I/O Memory mapped I/O is a method of performing input/output operations between the central processing unit (CPU) and peripheral devices CPU CPU bus SPI MEMORY Module A Memory mapped I/O uses the same

228 views • 6 slides
? Group 6 ? ? CPU ? CPU Memory We want multiple processors to share memory

? Group 6 ? ? CPU ? CPU Memory We want multiple processors to share memory

Shared Memory Architecture Shared Memory Bus for Multiprocessor Systems Memory CPU ? Mat Laibowitz and Albert Chiou ? ? ? ? Group 6 ? ? CPU ? CPU Memory We want multiple processors to share memory Question: How do we

286 views • 5 slides
Virtual Memory Logical address space can therefore be much larger than physical address

Virtual Memory Logical address space can therefore be much larger than physical address

CSC 4103 - Operating Systems Background Spring 2007 Virtual memory separation of user logical memory from physical memory. Only part of the program needs to be in memory for Lecture - XIII execution. Virtual Memory Logical

309 views • 7 slides
Mnemo: Boosting Memory Cost Efficiency in Hybrid Memory Systems Thaleia Dimitra Doudali Ada

Mnemo: Boosting Memory Cost Efficiency in Hybrid Memory Systems Thaleia Dimitra Doudali Ada

Mnemo: Boosting Memory Cost Efficiency in Hybrid Memory Systems Thaleia Dimitra Doudali Ada Gavrilovska Problem Space Cost of memory dominates in the cloud. 60% - 85% of the hourly VM cost! Big Data Analytics Volatile Memory (DRAM)

535 views • 18 slides
Memory Questions? ! What is main memory? CSCI [4|6]730 ! How does multiple processes share memory

Memory Questions? ! What is main memory? CSCI [4|6]730 ! How does multiple processes share memory

Memory Questions? ! What is main memory? CSCI [4|6]730 ! How does multiple processes share memory Operating Systems space? Key is how do they refer to memory addresses? ! What is static and dynamic allocation? Main Memory ! What is

285 views • 10 slides
Distributed Systems - III What about distributed systems? No common clock or memory

Distributed Systems - III What about distributed systems? No common clock or memory

CSC 4103 - Operating Systems Distributed Coordination Spring 2007 Ordering events and achieving synchronization in centralized systems is easier. Lecture - XXIV We can use common clock and memory Distributed Systems - III What

286 views • 4 slides
x86 Memory Protec.on and Transla.on Don Porter 1 CSE 506: Opera.ng Systems Logical Diagram

x86 Memory Protec.on and Transla.on Don Porter 1 CSE 506: Opera.ng Systems Logical Diagram

CSE 506: Opera.ng Systems x86 Memory Protec.on and Transla.on Don Porter 1 CSE 506: Opera.ng Systems Logical Diagram Binary Memory Threads Formats Allocators User System Calls Kernel RCU File System Networking Sync Memory CPU

616 views • 50 slides

More recommend