Pausible Clocking: A First Step Toward Heterogeneous Systems æ
|
|
|
- Magdalene Hunter
- 10 years ago
- Views:
Transcription
1 Pausible Clocking: First Step Toward Heterogeneous Systems æ Kenneth Y. Yun yan P. Donohue Department of Electrical and Computer Engineering University of California, San Diego 9500 Gilman Drive La Jolla, C [email protected] bstract This paper describes a novel communication scheme, which is guaranteed to be free of synchronization failures, amongst multiple synchronous modules operating independently. In this scheme, communication between every pair of modules is done through an asynchronous channel; communication between a module and the is done using a requestacknowledge handshaking. Synchronization of handshaking signals to the local module clock is done in an unconventional way [17, 15, 3, 12, 5] the local clock built out of a ring oscillator is paused or stretched, if necessary, to ensure that the handshaking signal satisfies setup and hold time constraints with respect to the local clock. We constructed a test bed consisting of two synchronous modules with pausible clocking control and an asynchronous on a MOSIS1:2çm CMOS chip. The resulting system functions reliably up to the local clock frequency of 220MHz (according to SPICE simulation) the maximum clock rate is limited by the ring oscillator, not the pausible clocking control. Preliminary test results indicate that the fabricated chips operate correctly as simulated. 1. Introduction The next generation digital VLSI systems will necessarily be based on system-on-chip concepts, in order to satisfy unrelenting demands for higher performance and also to accommodate smaller packaging and low power requirements for mobile applications. These on-chip systems will consist of multiple independently synchronized domains: some may be clocked domains, such as synchronous processor cores, while others may be clockless (asynchronous) domains, such as peripheral controllers. These chip designs will resemble today s complex board-level designs. Onchip modules will be held together by interface glue logic which must facilitate high speed communication between synchronous modules operating at different clock frequenæ This research was supported in part by a gift from Intel Corporation. cies, between synchronous and asynchronous modules, and between asynchronous modules. The key difference between today s board-level designs and the future systemon-chip designs is the speed at which communications take place. first step toward such heterogeneous system design on chip is a reliable high-speed communication scheme among multiple synchronousmodules operating independently. We examined a variety of communication schemes that attempt to mitigate synchronization failure without sacrificing communication throughput. They generally fall into one of two categories: (1) brute-force synchronization of communication signals to each module s free-running clock with an acceptable level of synchronization failure; (2) adjustment of individual synchronous module s local clock, when necessary, to avoid synchronization failure. The first category includes methods such as the wellknown double-latching scheme and a natural extension of the double-latching scheme called pipeline synchronization [16]. These methods reduce the probability of synchronization failure to an acceptable level by repeatedly resynchronizing communication signals with back-to-back latches. These methods are simple and inexpensive to implement, but a major drawback is the latency of communication. The methods in the second category [17, 15, 3, 12, 5] generally rely on stopping or stretching each synchronous module s local clock to guarantee that communication signals never violate setup and hold time constraints with respect to the local clock. lthough these methods are robust and do not incur long communication latency, they involve designing a special clocking circuit, unfamiliar to most designers. The simplest example using this scheme one can conceive is a synchronous module communicating with an asynchronous peripheral. In this system, the synchronous module latches the handshaking signals from the asynchronous module by stopping or stretching its own clock, when necessary. In this paper, we describe a general method of communication between two synchronous modules operating in-
2 sender Synchronous Module 1 σ σ ρ ρ receiver Synchronous Module 2 (a) 1 T1 G2 (a) One way communication 2 T2 sender receiver Synch Module 1 1ρ 1ρ 1σ 1σ 2σ 2σ 2ρ 2ρ sender receiver Synch Module 2 (b) rbiter 1 2 C G (b) Bidirectional communication G2 C Figure 1: Two synchronous modules communicating via an asynchronous channel. dependently, i.e., at different clock frequencies or phases, based on the pausible clocking scheme as shown in figure 1. Synchronous modules communicate with each other via an asynchronous used as a communication channel. The interfaces between the synchronous modules and the are pausible clocking control () circuits, i.e., the handshaking signals from the are sampled by the pausible clock of each synchronous module. lthough selftimed s have been used for communication between synchronous modules elsewhere [6], they have not been utilized in communication between synchronous modules operating independently at different clock frequencies. In order to validate this scheme, we implemented a test bed consisting of two synchronous modules with pausible clocking control and an asynchronous on a MOSIS 1:2çm CMOS chip. The resulting system functions reliably up to a local clock frequency of 220MHz the upper bound on the local clock rate is due to the ring oscillator, not the pausible clocking control. The rest of this paper is organized as follows: section 2 reviews mutual exclusion element and arbiter, key components used in the circuit; section 3 describes the design and implementation of the unit; section 4 describes several system configurations using this scheme and limitations; section 5 describes the experimental results; section 6 concludes the paper with some remarks on the future system design. 2. Background: Mutual Exclusion and rbiter In this section, we briefly review the concepts of the mutual exclusion element and the arbiter. mutual exclusion Figure 2: (a) CMOS mutual exclusion element circuit; (b) rbiter circuit using. element [15, 14] is a circuit (see figure 2a) that that allows one request to pass through at a time on a first come first serve basis. When two inputs arrive simultaneously, it selects one to pass through arbitrarily. n arbiter [10, 9, 4, 14, 8, 13] is a circuit that propagates one request at a time (as does the ) but also acknowledges the requesters with grant signals as well. The circuit used in our design is shown below (figure 2b). The symbol C represents C-element,a self-timed latch which raises its output when both inputs become high, lowers its output when both inputs become low, and keeps the old value if the inputs have different polarities. The detailed circuit behavior of both circuits is explained clearly in many texts and journals, so we will not elaborate here. However, an interesting characteristic of the should be noted [2, 7]. The closer the arrival times of the rising transitions of two inputs are, the longer it takes for the internal analog difference circuit to resolve the metastability [2, 11], hence the latency becomes longer. In order to effectively use the circuit in our design, we simulated our design in 1:2çm CMOS with SPICE. ll PMOS transistors in our design have W=L =12ç=2ç, and all NMOS transistors have W=L =6ç=2ç. Themean latency from input to output versus the difference in input arrival times is shown in figure 3. The rise time of both inputs was set to 1ns for the simulation, which is typical for 1:2çm technology. 3. Design of Pausible Clocking Control The pausible clocking control is a scheme to avoid synchronization failure by adjusting the local clock. synchronization failure at the module interface occurs when the arrival times of an external signal transition and a sampling
3 Latency (ns) ρ 1 S ρ ρ setup Difference in input arrival times (ns) 0.8 paused Figure 5: timing (one way communication). Figure 3: Mutual exclusion element mean latency versus difference in input arrival times. edge of the clock are indistinguishable by the sampling latch at the module boundary. In our scheme, the synchronization failure is circumvented by pausing or stretching the local module clock when necessary. ρ ρ FSM Sρ FSM 1 ing Oscillator Figure 4: eceiver for one way communication. block diagram of the receiver is shown in figure 4. This scheme uses a mutual exclusion element () to force the temporal separation of the sampling edges of the clock and external signal transitions. Because s require that requesters competing for shared resources must be persistent, the clock input to the must be stretched when it loses the arbitration. ring oscillator is used instead of a crystal oscillator in order to be able to adjust the duration of off-phases of the clock. The local module clock,, is a buffered version of one of the outputs of the. It normally has a 50% duty cycle, except when the clock input loses the arbitration, in which case the off-phase of the clock is stretched. s shown in figure 5, one-way communication, for which the synchronous module is the receiver, is straight-forward. request event from the is forwarded to the mutual exclusion element () via the asynchronous finite state machine (FSM). If is low when 1 rises, then the immediately raises G 1, which prompts the FSM to generate an event on S ç. This event is effectively synchronized to, i.e., guaranteed not to induce a synchronization failure when sampled by the FSM, under a reasonable timing assumption as described below. Note that may rise before the lowers G 1, but the will not allow to rise until G 1 becomes low. On the other hand, if is already high when 1 rises, the assertion of G 1 is stalled until is lowered. s soon as falls, the raises G 1 and the FSM generates an event on S ç. clk may actually rise at about the same time 1 rises. In such situations the situations in which temporal separation of 1 and becomes blurred the simply tosses a coin to determine which signal to service first. If wins the coin toss, then rises first and G 1 remains low until falls (whichhappensshortlyafter falls). On the other hand, if 1 wins, then the raises G 1 first and blocks from rising. In order to prevent from stalling indefinitely (until the next toggling of the request, ç ), the FSM lowers 1 immediately after G 1 rises, which in turn causes G 1 to fall allowing to rise. The does not differentiate rising edges of ç from falling edges both edges enable 1 to be asserted and G 1 to be asserted as a result. In fact, the FSM effectively performs a two-phase to four-phase conversion from ç to 1 and a four to two-phase conversion from G 1 to S ç.this conversion is independent of whether a two-phase or fourphase communication protocol is used between the and the synchronous module. It is merely done so that both edges of S ç are synchronized to. 1 ρ G S ρ ρ 1 ρ 1 G 1 1 G S ρ 1 ρ 1 G 1 Figure 6: timing constraint.
4 In order for the synchronous FSM that generates ç to recognize the change in S ç, we need to ensure that S ç must satisfy setup and hold time constraints with respect to. s illustrated in figure 6, in order to recognize S ç (S ç,) 1 reliably, the path from G 1 to S ç (S ç,) must be shorter than the path from G 1 to 1, to G 1, to by at least the data setup time for the FSM latches. This is easily satisfied because G 1 to S ç (S ç,) delay is a simple generalized C-element delay (transitions on S ç are directly triggered by G 1 ),whichismuchlessthanthe delay from G 1 to 1, to G 1, to ρ 1 1 S ρ ρ 1 ρ Sρ Sρ weak reset 1 For bidirectional communication, the synchronous module must interface with two s as shown in figure 1b. s illustrated in figure 8, two handshaking signals must be synchronized to the local clock: the request from the sending and the acknowledge from the receiving. In order to simplify the interface to the, our design uses an arbiter to select just one external signal to pass through at a time. Synchronization of the handshaking signals is done in the same way as for one-way communication. (a) ing configuration with synchronous nodes only S ρ weak S ρ sync Module Figure 7: asynchronous finite state machine specification and implementation. Sync Module Sync Module The asynchronous finite state machine (see figure 7) is specified in burst-mode [19, 18] and synthesized using the 3D-gC synthesis tool [20]. This burst-mode state machine has two inputs ( ç, G 1 ) and two outputs ( 1, S ç ). In state 0, when ç rises, the machine raises 1 and goes to state 1. In state 1, the machines waits for G 1 to rise; when it does, the machine lowers 1 and raises S ç concurrently and goes to state 2. When G 1 falls in state 2, the machine transitions to state 3. The machine transitions through states 4 and 5 and back to 0, as ç, triggers a sequence of signal transitions ending with G 1,. ρ σ 1 FSM ρ FSM S ρ 2 FSM σ FSM S σ G2 rbiter α Gα ing Oscillator Figure 8: for bidirectional communication. 1 We use a and a, to denote rising and falling transitions of a respectively. (b) Heterogeneous ring configuration Figure 9: (a) heterogeneous message-passing multiprocessor using s; (b) heterogeneous system with a mixture of asynchronous and synchronous modules. 4. System Configurations and Limitations Using the pausible clocking scheme, it is conceivable that one can construct a heterogeneous multi-processor system with point-to-point links between every pair of nodes. Each link is a bidirectional as shown in figure 1. However, as fanouts from and fanins to each node increase, the arbiter block becomes larger making the system impractical. However, we assert that it is possible to construct a ring configuration as shown in figure 9a similar to the systems proposed in Scalable Coherent Interface (SCI) specification [1]. In this structure, messages are always transmitted to one side and received from the other side, so that only one level of arbitration is required. major advantage of our ring configuration over other proposed systems, such as SCI system, is that it is a truly heterogeneous system with each node operating at its own speed. nother typical system configuration would be a mixture of asynchronous and synchronous modules as shown in figure 9b.
5 ing Oscillator Sender 2 s ρ eceiver 1 ing Oscillator G2 FSM S s FSM s ρ FSM Sρ FSM Figure 10: One way test configuration. Systems-on-chip should be designed with as many reusable components as possible. Standard modules, such as CPU cores, should be reused with little or no modification, because these modules are highly optimized for performance and sensitive to timing variation. For the systems proposed in this paper, ideally, the pausible clocking control circuit should simply replace a portion of the system clock generation unit. However, for the state-of-the-art microprocessors, the system clock is produced by a phase locked loop (PLL). We cannot adjust the phase of the output of a PLL instantaneously in an analog fashion, as required in our pausible clocking control. Thus a ring oscillator should be used in place of a PLL. Then we lose control of the nominal frequency. Tuning the ring oscillator frequency would require more control pins and hence are more expensive. (However, the ring oscillator in this case does have an advantage that its frequency drift closely tracks logic components on the chip, e.g., if logic components slow down due to an increase in operating temperature, then so does the ring oscillator.) Furthermore, anything in the clock path designed to generate multiple frequencies andor to minimize jitter creates a problem for pausible clocking. 5. Experimental esults We performed extensive SPICE simulations of two modules connected via an asynchronous as shown in figure 10, after backannotating the layout parasitics into the schematic using Mentor Graphics ccusim. We varied the depth of the between 1 and 4. The performance of the appears to be independent of the depth of the. The inclusion of the is for a generic reason of smoothening the bursty data transfer between two modules operating at different clock rates, not to enhance the performance of the s. The first timing trace (figure 11) shows a receiver module operating at 217MHz. The first event on ç (a rising transition) is acknowledged normally without pausing. The second event (a falling transition) causes to be paused for about 1.8ns. The second timing trace (figure 12) shows a simulation p 1 Sp p nalog Trace 4.50e-08 e e e e e e-08 TI (sec) Figure 11: simulation trace illustrating a clock pause ( = 217 MHz). result of one-way communication between two modules operating at different clock frequencies. In this simulation, the sender module operates at 135MHz and the receiver at 217MHz. The sender FSM is simply a rising edge-triggered flip-flop followed by an inverter. t the first rising edge of 2 after the system reset signal turns off, the sender FSM generates a request to the by raising s. The responds immediately by raising s. The sender FSM samples the synchronized version of this signal (S s )at the next rising edge of 2 and lowers s. s long as the responds to the sender s request signal immediately, there is no jitter (pausing) on 2 because s is synchronizedto 2. The receiver FSM is a rising edgetriggered flip-flop. When a request from the sender reaches the receiver through the, it is acknowledged at the next rising edge of 1. Because the request signal toggles independently of 1, 1 pauses occasionally to synchronize the request. Because the receiver operates at higher clock frequency than the sender, the never fills up, so the sender never slows down in this simulation.
6 p p 1 s s 2 nalog Trace 3.000e e-08 0e e e e e e e e-07 TI (sec) Figure 12: One way communication simulation trace (1 = 217 MHz; 2 = 135MHz). 6. Conclusion We presented a new communication scheme, which is based on the pausible clocking scheme, for multiple synchronous modules operating independently. In order to prove its feasibility, we constructed a test bed consisting of two synchronous modules with the pausible clocking control and an asynchronous on a MOSIS 1:2çm CMOS chip. The resulting system functions reliably up to the local clock frequency of 220MHz (according to SPICE simulation) the maximum clock rate is limited by the ring oscillator, not the pausible clocking control. t the time of publication, preliminary test results indicate that the fabricated chips operate correctly as simulated. In the future, we plan to investigate a larger system, a heterogeneous ring configuration with a mixture of synchronous and asynchronous modules. In addition, we will investigate a new oscillator design (other than simple ring oscillator designs). cknowledgment The authors would like to thank Charles Dike of Intel Corporation for pointing out real-world problems associated with implementing pausible clocking control for microprocessor cores. eferences [1] IEEE Standard Scalable coherent interface (SCI). [2] T. J. Chaney and C. E. Molnar. nomalous behavior of synchronizer and arbiter circuits. IEEE Transactions on Computers, C-22(4): , pril [3] Daniel M. Chapiro. Globally-synchronous Locally- Synchronous Systems. PhD thesis, Stanford University, October [4] P. Corsini. Speed-independent asynchronous arbiter. IEE journal on Computers and Digital Techniques, 2(5): , October [5] G. Gopalakrishnan and L. Josephson. Towards amalgamating the synchronous and asynchronous styles. In TU-93. [6] Mark. Greenstreet. Implementing a STI chip. In Proc. International Conf. Computer Design (ICCD), pages IEEE Computer Society Press, October [7] Lindsay Kleeman. Service and Metastability Performance of rbiters. PhD thesis, Dept. of Electrical and Computer Eng., Univ. of Newcastle, ustralia, ugust [8] lain J. Martin. On Seitz s arbiter. Technical eport 5212:T:86, Caltech Computer Science, [9]. C. Pearce, J.. Field, and W. D. Little. synchronous arbiter module. IEEE Transactions on Computers, 24: , September [10] W. W. Plummer. synchronous arbiters. IEEE Transactions on Computers, 21(1):37 42, January [11] Fred U. osenberger and Charles E. Molnar. Comments on metastability of CMOS latchflip-flop. IEEE Journal of Solid-State Circuits, 27(1): , January eply by obert W. Dutton pages of same issue. [12] Fred U. osenberger, Charles E. Molnar, Thomas J. Chaney, and Ting-Pien Fang. Q-modules: Internally clocked delayinsensitive modules. IEEE Transactions on Computers, C- 37(9): , September [13] T. Sakurai. Optimization of CMOS arbiter and synchronizer circuits with submicron MOSFETs. IEEE Journal of Solid- State Circuits, 23(4): , ugust [14] Charles L. Seitz. Ideas about arbiters. Lambda, 1(1, First Quarter):10 14, [15] Charles L. Seitz. System timing. In Carver. Mead and Lynn. Conway, editors, Introduction to VLSI Systems, chapter 7. ddison-wesley, [16] Jakov N. Seizovic. Pipeline synchronization. In Proc. International Symposium on dvanced esearch in synchronous Circuits and Systems, pages 87 96, November [17] M. J. Stucki and J.. Cox Jr. Synchronization strategies. In Charles L. Seitz, editor, Proceedings of the First Caltech Conference on Very Large Scale Integration, pages , [18] K. Y. Yun. Synthesis of synchronous Controllers for Heterogeneous Systems. PhD thesis, Stanford University, ugust Technical eport CSL-T [19] K. Y. Yun, D. L. Dill, and S. M. Nowick. Synthesis of 3D asynchronous state machines. In Proc. International Conf. Computer Design (ICCD), pages IEEE Computer Society Press, October [20] Kenneth Y. Yun. utomatic synthesis of extended burstmode circuits using generalized C-elements. To appear in EUODC-96.
Clocking. Figure by MIT OCW. 6.884 - Spring 2005 2/18/05 L06 Clocks 1
ing Figure by MIT OCW. 6.884 - Spring 2005 2/18/05 L06 s 1 Why s and Storage Elements? Inputs Combinational Logic Outputs Want to reuse combinational logic from cycle to cycle 6.884 - Spring 2005 2/18/05
Topics of Chapter 5 Sequential Machines. Memory elements. Memory element terminology. Clock terminology
Topics of Chapter 5 Sequential Machines Memory elements Memory elements. Basics of sequential machines. Clocking issues. Two-phase clocking. Testing of combinational (Chapter 4) and sequential (Chapter
A Pausible Bisynchronous FIFO for GALS Systems
2015 Symposium on Asynchronous Circuits and Systems A Pausible Bisynchronous FIFO for GALS Systems Ben Keller*, Ma@hew FojCk*, Brucek Khailany* *NVIDIA CorporaCon University of California, Berkeley May
Sequential Logic: Clocks, Registers, etc.
ENEE 245: igital Circuits & Systems Lab Lab 2 : Clocks, Registers, etc. ENEE 245: igital Circuits and Systems Laboratory Lab 2 Objectives The objectives of this laboratory are the following: To design
Lecture 10: Sequential Circuits
Introduction to CMOS VLSI esign Lecture 10: Sequential Circuits avid Harris Harvey Mudd College Spring 2004 Outline q Sequencing q Sequencing Element esign q Max and Min-elay q Clock Skew q Time Borrowing
Lecture 11: Sequential Circuit Design
Lecture 11: Sequential Circuit esign Outline Sequencing Sequencing Element esign Max and Min-elay Clock Skew Time Borrowing Two-Phase Clocking 2 Sequencing Combinational logic output depends on current
Demystifying Data-Driven and Pausible Clocking Schemes
Demystifying Data-Driven and Pausible Clocking Schemes Robert Mullins Computer Architecture Group Computer Laboratory, University of Cambridge ASYNC 2007, 13 th IEEE International Symposium on Asynchronous
Low latency synchronization through speculation
Low latency synchronization through speculation D.J.Kinniment, and A.V.Yakovlev School of Electrical and Electronic and Computer Engineering, University of Newcastle, NE1 7RU, UK {David.Kinniment,Alex.Yakovlev}@ncl.ac.uk
Timing Methodologies (cont d) Registers. Typical timing specifications. Synchronous System Model. Short Paths. System Clock Frequency
Registers Timing Methodologies (cont d) Sample data using clock Hold data between clock cycles Computation (and delay) occurs between registers efinition of terms setup time: minimum time before the clocking
Flip-Flops, Registers, Counters, and a Simple Processor
June 8, 22 5:56 vra235_ch7 Sheet number Page number 349 black chapter 7 Flip-Flops, Registers, Counters, and a Simple Processor 7. Ng f3, h7 h6 349 June 8, 22 5:56 vra235_ch7 Sheet number 2 Page number
Clock Distribution in RNS-based VLSI Systems
Clock Distribution in RNS-based VLSI Systems DANIEL GONZÁLEZ 1, ANTONIO GARCÍA 1, GRAHAM A. JULLIEN 2, JAVIER RAMÍREZ 1, LUIS PARRILLA 1 AND ANTONIO LLORIS 1 1 Dpto. Electrónica y Tecnología de Computadores
PROGETTO DI SISTEMI ELETTRONICI DIGITALI. Digital Systems Design. Digital Circuits Advanced Topics
PROGETTO DI SISTEMI ELETTRONICI DIGITALI Digital Systems Design Digital Circuits Advanced Topics 1 Sequential circuit and metastability 2 Sequential circuit - FSM A Sequential circuit contains: Storage
Design and Implementation of an On-Chip timing based Permutation Network for Multiprocessor system on Chip
Design and Implementation of an On-Chip timing based Permutation Network for Multiprocessor system on Chip Ms Lavanya Thunuguntla 1, Saritha Sapa 2 1 Associate Professor, Department of ECE, HITAM, Telangana
Asynchronous IC Interconnect Network Design and Implementation Using a Standard ASIC Flow
Asynchronous IC Interconnect Network Design and Implementation Using a Standard ASIC Flow Bradley R. Quinton Dept. of Electrical and Computer Engineering University of British Columbia [email protected]
TRUE SINGLE PHASE CLOCKING BASED FLIP-FLOP DESIGN
TRUE SINGLE PHASE CLOCKING BASED FLIP-FLOP DESIGN USING DIFFERENT FOUNDRIES Priyanka Sharma 1 and Rajesh Mehra 2 1 ME student, Department of E.C.E, NITTTR, Chandigarh, India 2 Associate Professor, Department
Lizy Kurian John Electrical and Computer Engineering Department, The University of Texas as Austin
BUS ARCHITECTURES Lizy Kurian John Electrical and Computer Engineering Department, The University of Texas as Austin Keywords: Bus standards, PCI bus, ISA bus, Bus protocols, Serial Buses, USB, IEEE 1394
Introduction to CMOS VLSI Design (E158) Lecture 8: Clocking of VLSI Systems
Harris Introduction to CMOS VLSI Design (E158) Lecture 8: Clocking of VLSI Systems David Harris Harvey Mudd College [email protected] Based on EE271 developed by Mark Horowitz, Stanford University MAH
EE552. Advanced Logic Design and Switching Theory. Metastability. Ashirwad Bahukhandi. (Ashirwad Bahukhandi) [email protected]
EE552 Advanced Logic Design and Switching Theory Metastability by Ashirwad Bahukhandi (Ashirwad Bahukhandi) [email protected] This is an overview of what metastability is, ways of interpreting it, the issues
Sequential Logic Design Principles.Latches and Flip-Flops
Sequential Logic Design Principles.Latches and Flip-Flops Doru Todinca Department of Computers Politehnica University of Timisoara Outline Introduction Bistable Elements Latches and Flip-Flops S-R Latch
PowerPC Microprocessor Clock Modes
nc. Freescale Semiconductor AN1269 (Freescale Order Number) 1/96 Application Note PowerPC Microprocessor Clock Modes The PowerPC microprocessors offer customers numerous clocking options. An internal phase-lock
EE 42/100 Lecture 24: Latches and Flip Flops. Rev B 4/21/2010 (2:04 PM) Prof. Ali M. Niknejad
A. M. Niknejad University of California, Berkeley EE 100 / 42 Lecture 24 p. 1/20 EE 42/100 Lecture 24: Latches and Flip Flops ELECTRONICS Rev B 4/21/2010 (2:04 PM) Prof. Ali M. Niknejad University of California,
S. Venkatesh, Mrs. T. Gowri, Department of ECE, GIT, GITAM University, Vishakhapatnam, India
Power reduction on clock-tree using Energy recovery and clock gating technique S. Venkatesh, Mrs. T. Gowri, Department of ECE, GIT, GITAM University, Vishakhapatnam, India Abstract Power consumption of
Alpha CPU and Clock Design Evolution
Alpha CPU and Clock Design Evolution This lecture uses two papers that discuss the evolution of the Alpha CPU and clocking strategy over three CPU generations Gronowski, Paul E., et.al., High Performance
路 論 Chapter 15 System-Level Physical Design
Introduction to VLSI Circuits and Systems 路 論 Chapter 15 System-Level Physical Design Dept. of Electronic Engineering National Chin-Yi University of Technology Fall 2007 Outline Clocked Flip-flops CMOS
Architectural Level Power Consumption of Network on Chip. Presenter: YUAN Zheng
Architectural Level Power Consumption of Network Presenter: YUAN Zheng Why Architectural Low Power Design? High-speed and large volume communication among different parts on a chip Problem: Power consumption
BURST-MODE communication relies on very fast acquisition
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II: EXPRESS BRIEFS, VOL. 52, NO. 8, AUGUST 2005 437 Instantaneous Clockless Data Recovery and Demultiplexing Behnam Analui and Ali Hajimiri Abstract An alternative
Lecture 7: Clocking of VLSI Systems
Lecture 7: Clocking of VLSI Systems MAH, AEN EE271 Lecture 7 1 Overview Reading Wolf 5.3 Two-Phase Clocking (good description) W&E 5.5.1, 5.5.2, 5.5.3, 5.5.4, 5.5.9, 5.5.10 - Clocking Note: The analysis
Switched Interconnect for System-on-a-Chip Designs
witched Interconnect for ystem-on-a-chip Designs Abstract Daniel iklund and Dake Liu Dept. of Physics and Measurement Technology Linköping University -581 83 Linköping {danwi,dake}@ifm.liu.se ith the increased
Nexus: An Asynchronous Crossbar Interconnect for Synchronous System-on-Chip Designs
Nexus: An Asynchronous Crossbar Interconnect for Synchronous System-on-Chip Designs Andrew Lines Fulcrum Microsystems 26775 Malibu Hills Road, Calabasas, CA 9131 lines@fulcrummicrocom Abstract Asynchronous
7. Latches and Flip-Flops
Chapter 7 Latches and Flip-Flops Page 1 of 18 7. Latches and Flip-Flops Latches and flip-flops are the basic elements for storing information. One latch or flip-flop can store one bit of information. The
Quality of Service (QoS) for Asynchronous On-Chip Networks
Quality of Service (QoS) for synchronous On-Chip Networks Tomaz Felicijan and Steve Furber Department of Computer Science The University of Manchester Oxford Road, Manchester, M13 9PL, UK {felicijt,sfurber}@cs.man.ac.uk
White Paper Understanding Metastability in FPGAs
White Paper Understanding Metastability in FPGAs This white paper describes metastability in FPGAs, why it happens, and how it can cause design failures. It explains how metastability MTBF is calculated,
Sequential Circuits. Combinational Circuits Outputs depend on the current inputs
Principles of VLSI esign Sequential Circuits Sequential Circuits Combinational Circuits Outputs depend on the current inputs Sequential Circuits Outputs depend on current and previous inputs Requires separating
Latch Timing Parameters. Flip-flop Timing Parameters. Typical Clock System. Clocking Overhead
Clock - key to synchronous systems Topic 7 Clocking Strategies in VLSI Systems Peter Cheung Department of Electrical & Electronic Engineering Imperial College London Clocks help the design of FSM where
LOW POWER DESIGN OF DIGITAL SYSTEMS USING ENERGY RECOVERY CLOCKING AND CLOCK GATING
LOW POWER DESIGN OF DIGITAL SYSTEMS USING ENERGY RECOVERY CLOCKING AND CLOCK GATING A thesis work submitted to the faculty of San Francisco State University In partial fulfillment of the requirements for
Measuring Metastability
Measuring Metastability Sandeep Mandarapu Department of Electrical and Computer Engineering, VLSI Design Research Laboratory, Southern Illinois University Edwardsville, Illinois, USA, 62025 ECE595: Masters
Design and analysis of flip flops for low power clocking system
Design and analysis of flip flops for low power clocking system Gabariyala sabadini.c PG Scholar, VLSI design, Department of ECE,PSNA college of Engg and Tech, Dindigul,India. Jeya priyanka.p PG Scholar,
Power Reduction Techniques in the SoC Clock Network. Clock Power
Power Reduction Techniques in the SoC Network Low Power Design for SoCs ASIC Tutorial SoC.1 Power Why clock power is important/large» Generally the signal with the highest frequency» Typically drives a
Computer Network. Interconnected collection of autonomous computers that are able to exchange information
Introduction Computer Network. Interconnected collection of autonomous computers that are able to exchange information No master/slave relationship between the computers in the network Data Communications.
An On-chip Security Monitoring Solution For System Clock For Low Cost Devices
An On-chip Security Monitoring Solution For System Clock For Low Cost Devices Frank Vater Innovations for High Performance Microelectronics Im Technologiepark 25 15236 Frankfurt (Oder), Germany [email protected]
Multiple clock domains
DESIGNING A ROBUST USB SERIAL INTERFACE ENGINE(SIE) What is the SIE? A typical function USB hardware interface is shown in Fig. 1. USB Transceiver USB Serial Interface Engine Status Control Data Buffers/
CS311 Lecture: Sequential Circuits
CS311 Lecture: Sequential Circuits Last revised 8/15/2007 Objectives: 1. To introduce asynchronous and synchronous flip-flops (latches and pulsetriggered, plus asynchronous preset/clear) 2. To introduce
DS2187 Receive Line Interface
Receive Line Interface www.dalsemi.com FEATURES Line interface for T1 (1.544 MHz) and CEPT (2.048 MHz) primary rate networks Extracts clock and data from twisted pair or coax Meets requirements of PUB
Latches, the D Flip-Flop & Counter Design. ECE 152A Winter 2012
Latches, the D Flip-Flop & Counter Design ECE 52A Winter 22 Reading Assignment Brown and Vranesic 7 Flip-Flops, Registers, Counters and a Simple Processor 7. Basic Latch 7.2 Gated SR Latch 7.2. Gated SR
Master/Slave Flip Flops
Master/Slave Flip Flops Page 1 A Master/Slave Flip Flop ( Type) Gated latch(master) Gated latch (slave) 1 Gate Gate GATE Either: The master is loading (the master in on) or The slave is loading (the slave
A New Paradigm for Synchronous State Machine Design in Verilog
A New Paradigm for Synchronous State Machine Design in Verilog Randy Nuss Copyright 1999 Idea Consulting Introduction Synchronous State Machines are one of the most common building blocks in modern digital
Managing High-Speed Clocks
Managing High-Speed s & Greg Steinke Director, Component Applications Managing High-Speed s Higher System Performance Requires Innovative ing Schemes What Are The Possibilities? High-Speed ing Schemes
8 Gbps CMOS interface for parallel fiber-optic interconnects
8 Gbps CMOS interface for parallel fiberoptic interconnects Barton Sano, Bindu Madhavan and A. F. J. Levi Department of Electrical Engineering University of Southern California Los Angeles, California
WEEK 8.1 Registers and Counters. ECE124 Digital Circuits and Systems Page 1
WEEK 8.1 egisters and Counters ECE124 igital Circuits and Systems Page 1 Additional schematic FF symbols Active low set and reset signals. S Active high set and reset signals. S ECE124 igital Circuits
PROGETTO DI SISTEMI ELETTRONICI DIGITALI. Digital Systems Design. Digital Circuits Advanced Topics
PROGETTO DI SISTEMI ELETTRONICI DIGITALI Digital Systems Design Digital Circuits Advanced Topics 1 Sequential circuit and metastability 2 Sequential circuit A Sequential circuit contains: Storage elements:
The Future of Multi-Clock Systems
NEL FREQUENCY CONTROLS, INC. 357 Beloit Street P.O. Box 457 Burlington,WI 53105-0457 Phone:262/763-3591 FAX:262/763-2881 Web Site: www.nelfc.com Internet: [email protected] The Future of Multi-Clock Systems
Engr354: Digital Logic Circuits
Engr354: igital Circuits Chapter 7 Sequential Elements r. Curtis Nelson Sequential Elements In this chapter you will learn about: circuits that can store information; Basic cells, latches, and flip-flops;
Modeling Sequential Elements with Verilog. Prof. Chien-Nan Liu TEL: 03-4227151 ext:34534 Email: [email protected]. Sequential Circuit
Modeling Sequential Elements with Verilog Prof. Chien-Nan Liu TEL: 03-4227151 ext:34534 Email: [email protected] 4-1 Sequential Circuit Outputs are functions of inputs and present states of storage elements
ZL30136 GbE and Telecom Rate Network Interface Synchronizer
be and Telecom Rate Network Interface Synchronizer Features rovides synchronous clocks for network interface cards that support synchronous Ethernet (SyncE) in addition to telecom interfaces (T1/E1, DS3/E3,
MPC8245/MPC8241 Memory Clock Design Guidelines: Part 1
Freescale Semiconductor AN2164 Rev. 4.1, 03/2007 MPC8245/MPC8241 Memory Clock Design Guidelines: Part 1 by Esther C. Alexander RISC Applications, CPD Freescale Semiconductor, Inc. Austin, TX This application
Flip-Flops and Sequential Circuit Design. ECE 152A Winter 2012
Flip-Flops and Sequential Circuit Design ECE 52 Winter 22 Reading ssignment Brown and Vranesic 7 Flip-Flops, Registers, Counters and a Simple Processor 7.5 T Flip-Flop 7.5. Configurable Flip-Flops 7.6
Flip-Flops and Sequential Circuit Design
Flip-Flops and Sequential Circuit Design ECE 52 Winter 22 Reading ssignment Brown and Vranesic 7 Flip-Flops, Registers, Counters and a Simple Processor 7.5 T Flip-Flop 7.5. Configurable Flip-Flops 7.6
NTE2053 Integrated Circuit 8 Bit MPU Compatible A/D Converter
NTE2053 Integrated Circuit 8 Bit MPU Compatible A/D Converter Description: The NTE2053 is a CMOS 8 bit successive approximation Analog to Digital converter in a 20 Lead DIP type package which uses a differential
Lecture 10 Sequential Circuit Design Zhuo Feng. Z. Feng MTU EE4800 CMOS Digital IC Design & Analysis 2010
EE4800 CMOS igital IC esign & Analysis Lecture 10 Sequential Circuit esign Zhuo Feng 10.1 Z. Feng MTU EE4800 CMOS igital IC esign & Analysis 2010 Sequencing Outline Sequencing Element esign Max and Min-elay
Multi-GHz Systems Clocking Invited Paper
Multi-GHz Systems ing Invited Paper Vojin G. Oklobdzija, Fellow IEEE Department of Electrical Engineering, University of California, Davis [email protected] http://www.ece.ucdavis.edu/acsel Abstract:
CHAPTER 11 LATCHES AND FLIP-FLOPS
CHAPTER 11 LATCHES AND FLIP-FLOPS This chapter in the book includes: Objectives Study Guide 11.1 Introduction 11.2 Set-Reset Latch 11.3 Gated D Latch 11.4 Edge-Triggered D Flip-Flop 11.5 S-R Flip-Flop
ETEC 2301 Programmable Logic Devices. Chapter 10 Counters. Shawnee State University Department of Industrial and Engineering Technologies
ETEC 2301 Programmable Logic Devices Chapter 10 Counters Shawnee State University Department of Industrial and Engineering Technologies Copyright 2007 by Janna B. Gallaher Asynchronous Counter Operation
Lesson 12 Sequential Circuits: Flip-Flops
Lesson 12 Sequential Circuits: Flip-Flops 1. Overview of a Synchronous Sequential Circuit We saw from last lesson that the level sensitive latches could cause instability in a sequential system. This instability
EE 459/500 HDL Based Digital Design with Programmable Logic. Lecture 16 Timing and Clock Issues
EE 459/500 HDL Based Digital Design with Programmable Logic Lecture 16 Timing and Clock Issues 1 Overview Sequential system timing requirements Impact of clock skew on timing Impact of clock jitter on
Design Verification & Testing Design for Testability and Scan
Overview esign for testability (FT) makes it possible to: Assure the detection of all faults in a circuit Reduce the cost and time associated with test development Reduce the execution time of performing
TIMING-DRIVEN PHYSICAL DESIGN FOR DIGITAL SYNCHRONOUS VLSI CIRCUITS USING RESONANT CLOCKING
TIMING-DRIVEN PHYSICAL DESIGN FOR DIGITAL SYNCHRONOUS VLSI CIRCUITS USING RESONANT CLOCKING BARIS TASKIN, JOHN WOOD, IVAN S. KOURTEV February 28, 2005 Research Objective Objective: Electronic design automation
Control 2004, University of Bath, UK, September 2004
Control, University of Bath, UK, September ID- IMPACT OF DEPENDENCY AND LOAD BALANCING IN MULTITHREADING REAL-TIME CONTROL ALGORITHMS M A Hossain and M O Tokhi Department of Computing, The University of
Clocks Basics in 10 Minutes or Less. Edgar Pineda Field Applications Engineer Arrow Components Mexico
Clocks Basics in 10 Minutes or Less Edgar Pineda Field Applications Engineer Arrow Components Mexico Presentation Overview Introduction to Clocks Clock Functions Clock Parameters Common Applications Summary
Sequential Circuit Design
Sequential Circuit Design Lan-Da Van ( 倫 ), Ph. D. Department of Computer Science National Chiao Tung University Taiwan, R.O.C. Fall, 2009 [email protected] http://www.cs.nctu.edu.tw/~ldvan/ Outlines
Computer Aided Design of Home Medical Alert System
Computer Aided Design of Home Medical Alert System Submitted to The Engineering Honors Committee 119 Hitchcock Hall College of Engineering The Ohio State University Columbus, Ohio 43210 By Pei Chen Kan
Experiment # 9. Clock generator circuits & Counters. Eng. Waleed Y. Mousa
Experiment # 9 Clock generator circuits & Counters Eng. Waleed Y. Mousa 1. Objectives: 1. Understanding the principles and construction of Clock generator. 2. To be familiar with clock pulse generation
ECEN689: Special Topics in High-Speed Links Circuits and Systems Spring 2010
ECEN689: Special Topics in High-Speed Links Circuits and Systems Spring 2010 Lecture 25: Clocking Architectures Sam Palermo Analog & Mixed-Signal Center Texas A&M University Announcements Project Preliminary
CHARGE pumps are the circuits that used to generate dc
INTERNATIONAL JOURNAL OF DESIGN, ANALYSIS AND TOOLS FOR CIRCUITS AND SYSTEMS, VOL. 1, NO. 1, JUNE 2011 27 A Charge Pump Circuit by using Voltage-Doubler as Clock Scheme Wen Chang Huang, Jin Chang Cheng,
A high-speed interconnect network using ternary logic
Downloaded from orbit.dtu.dk on: Dec 19, 2015 A high-speed interconnect network using ternary logic Madsen, Jens Kargaard; Long, S. I. Published in: Proceedings of the 25th International Symposium on Multiple-Valued
Serial port interface for microcontroller embedded into integrated power meter
Serial port interface for microcontroller embedded into integrated power meter Mr. Borisav Jovanović, Prof. dr. Predrag Petković, Prof. dr. Milunka Damnjanović, Faculty of Electronic Engineering Nis, Serbia
Timing Errors and Jitter
Timing Errors and Jitter Background Mike Story In a sampled (digital) system, samples have to be accurate in level and time. The digital system uses the two bits of information the signal was this big
Clock- and data-recovery IC with demultiplexer for a 2.5 Gb/s ATM physical layer controller
Downloaded from orbit.dtu.dk on: Jan 04, 2016 Clock and datarecovery IC with demultiplexer for a 2.5 Gb/s ATM physical layer controller Hansen, Flemming; Salama, C.A.T. Published in: Proceedings of the
150127-Microprocessor & Assembly Language
Chapter 3 Z80 Microprocessor Architecture The Z 80 is one of the most talented 8 bit microprocessors, and many microprocessor-based systems are designed around the Z80. The Z80 microprocessor needs an
Glitch Free Frequency Shifting Simplifies Timing Design in Consumer Applications
Glitch Free Frequency Shifting Simplifies Timing Design in Consumer Applications System designers face significant design challenges in developing solutions to meet increasingly stringent performance and
Interconnection Networks
Advanced Computer Architecture (0630561) Lecture 15 Interconnection Networks Prof. Kasim M. Al-Aubidy Computer Eng. Dept. Interconnection Networks: Multiprocessors INs can be classified based on: 1. Mode
Switch Fabric Implementation Using Shared Memory
Order this document by /D Switch Fabric Implementation Using Shared Memory Prepared by: Lakshmi Mandyam and B. Kinney INTRODUCTION Whether it be for the World Wide Web or for an intra office network, today
Hardware Implementation of Improved Adaptive NoC Router with Flit Flow History based Load Balancing Selection Strategy
Hardware Implementation of Improved Adaptive NoC Rer with Flit Flow History based Load Balancing Selection Strategy Parag Parandkar 1, Sumant Katiyal 2, Geetesh Kwatra 3 1,3 Research Scholar, School of
A Survey on Sequential Elements for Low Power Clocking System
Journal of Computer Applications ISSN: 0974 1925, Volume-5, Issue EICA2012-3, February 10, 2012 A Survey on Sequential Elements for Low Power Clocking System Bhuvana S ECE Department, Avinashilingam University
Chapter 5. Sequential Logic
Chapter 5 Sequential Logic Sequential Circuits (/2) Combinational circuits: a. contain no memory elements b. the outputs depends on the current inputs Sequential circuits: a feedback path outputs depends
RETRIEVING DATA FROM THE DDC112
RETRIEVING DATA FROM THE by Jim Todsen This application bulletin explains how to retrieve data from the. It elaborates on the discussion given in the data sheet and provides additional information to allow
Memory Elements. Combinational logic cannot remember
Memory Elements Combinational logic cannot remember Output logic values are function of inputs only Feedback is needed to be able to remember a logic value Memory elements are needed in most digital logic
Clock Recovery in Serial-Data Systems Ransom Stephens, Ph.D.
Clock Recovery in Serial-Data Systems Ransom Stephens, Ph.D. Abstract: The definition of a bit period, or unit interval, is much more complicated than it looks. If it were just the reciprocal of the data
Set-Reset (SR) Latch
et-eset () Latch Asynchronous Level sensitive cross-coupled Nor gates active high inputs (only one can be active) + + Function 0 0 0 1 0 1 eset 1 0 1 0 et 1 1 0-? 0-? Indeterminate cross-coupled Nand gates
Computer Systems Structure Input/Output
Computer Systems Structure Input/Output Peripherals Computer Central Processing Unit Main Memory Computer Systems Interconnection Communication lines Input Output Ward 1 Ward 2 Examples of I/O Devices
Lecture-3 MEMORY: Development of Memory:
Lecture-3 MEMORY: It is a storage device. It stores program data and the results. There are two kind of memories; semiconductor memories & magnetic memories. Semiconductor memories are faster, smaller,
Chapter 13: Verification
Chapter 13: Verification Prof. Ming-Bo Lin Department of Electronic Engineering National Taiwan University of Science and Technology Digital System Designs and Practices Using Verilog HDL and FPGAs @ 2008-2010,
Jitter Transfer Functions in Minutes
Jitter Transfer Functions in Minutes In this paper, we use the SV1C Personalized SerDes Tester to rapidly develop and execute PLL Jitter transfer function measurements. We leverage the integrated nature
Low Power AMD Athlon 64 and AMD Opteron Processors
Low Power AMD Athlon 64 and AMD Opteron Processors Hot Chips 2004 Presenter: Marius Evers Block Diagram of AMD Athlon 64 and AMD Opteron Based on AMD s 8 th generation architecture AMD Athlon 64 and AMD
Serial Communications
Serial Communications 1 Serial Communication Introduction Serial communication buses Asynchronous and synchronous communication UART block diagram UART clock requirements Programming the UARTs Operation
