Clock gating

About: Clock gating is a research topic. Over the lifetime, 7838 publications have been published within this topic receiving 107903 citations.

Apparatus and method for reading data from synchronous memory with skewed clock pulses

Abstract: A novel apparatus and method is disclosed to assure validity of data accessed from synchronous memory during a "read" operation, wherein the synchronous memory is operating synchronously at a high frequency system clock. The invention comprises a programmable delay module which generates a skewed clock signal which is used to clock in data read from the synchronous memory. The programmable delay module generates the skewed clock signal by adding programmable time delays to the system clock signal. The inserted delay increases the data valid window time available for the "read" operation and allows sufficient setup and hold time for valid data to be read by a memory controller.

Skew And Delay Optimization For Reliable Buffered Clock Trees

Abstract: Recenily, seveml design auiomaiion approaches for delay and skew minimization of clock nets have been proposed. These approaches are based upon varying the widths and lengths of the clock tree wires io minimize skew and sometimes delay. Most of these iechniques do noi consider the clock iree power dissipation, occupied area, or the reliabiliiy of ihe resvlts with regard to the ineviiable process variations. In this paper, concurreni buffer insertion and global wire width adjusimenis are used to reliably reduce both delay and power from that obtained for a reliable buflerless soluiion. Moreover, in spite of ihe belief ihai ihe mismaich in bufler delays can resuli in significant clock skew, our resulis show ihai buflers can actually reduce the process dependent skew for a reliable design.

A Design Approach for Fine-grained Run-Time Power Gating using Locally Extracted Sleep Signals

Abstract: Leakage power dissipation becomes a dominant component in operation power in nanometer devices. This paper describes a design methodology to implement runtime power gating in a fine-grained manner. We propose an approach to use sleep signals that are not off-chip but are extracted locally within the design. By utilizing enable signals in a gated clock design, we automatically partition the design into domains. We then choose the domains that will achieve the gain in energy savings by considering dynamic energy overhead due to turning on/off power switches. To help this decision we derive analytical formulas that estimate the break-even point. For the domains chosen, we create power gating structure by adding power switches and generating control logic to the switches. We experimentally built a design flow and evaluated with a synthesizable RTL code for a microprocessor and a 90nm CMOS device model both used in industry. Results from applying to a datapath showed that the break-even point that achieves the gain exists in the number of enables controlling the power switch. By applying the domains controlled by up to 3 enables achieved the active leakage savings by 83% at the area penalty by 20%.

A clock power model to evaluate impact of architectural and technology optimizations

Abstract: The clock distribution and generation circuitry forms a critical component of current synchronous digital systems and is known to consume at least a quarter of the power budget of existing microprocessors. We propose and validate a high level model for evaluating the energy dissipation of the clock generation and distribution circuitry, including both the dynamic and leakage power components. The validation results show that the model is reasonably accurate, with the average deviation being within 10% of SPICE simulations. Access to this model can enable further research at high-level design stages in optimizing the system clock power. To illustrate this, a few architectural modifications are considered and their effect on the clock subsystem and the total system power budget is assessed.

Power management system distinguishing between primary and secondary system activity

Abstract: A power management unit is provided that includes several states, each of which is associated with a different power management mode. Transitions between the states of the power management unit are dependent upon the type of activities detected. Upon reset of the computer system, the power management unit enters a ready state during which a CPU clock signal and a system clock signal are driven at their maximum frequencies. If no primary activities are detected over certain time periods, the power management unit successively transitions from the ready state to a doze state, then to a stand-by state, and then to a suspend state. During the doze state, the frequency of the CPU clock signal is slowed, and during the stand-by state, the CPU clock signal is stopped. During the suspend state, both the CPU clock signal and the system clock signal are stopped, and the power to selected circuit portions may be removed. If a secondary activity is detected when the power management unit is in the doze state or the ready state, the power management unit enters a transitory state during which both the CPU clock signal and the system clock signal are driven at maximum frequencies for a predetermined time duration. Subsequently, the power management unit reverts back to the previous power management state. Primary activities cause the power management unit to enter the ready state.