Memory Device Cache Read Timing Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional memory devices face inefficiencies in data transfer operations during cache read operations, where discharge and data transfer are typically sequential, leading to prolonged data output times due to the need for separate completion of discharge and transfer processes.

Innovation Solution

The memory device and method allow for simultaneous discharge and data transfer operations based on the receipt of a cache read command, determining whether to initiate data transfer before, during, or after the discharge operation, thereby optimizing the timing to reduce overall read operation time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If discharge operation and data transfer operation are performed sequentially, then each operation can be completed reliably, but the total operation time is prolonged

Engineering Contradiction:
Improveoperation reliabilityVSAvoidread operation time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent merges the discharge operation and data transfer operation into a single simultaneous execution phase. The control logic coordinates both operations to occur concurrently during the read cycle, eliminating the sequential waiting time while maintaining proper signal timing and data integrity through synchronized control signals.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent prepares data in the page buffer before the discharge operation completes by initiating the data transfer operation in advance. The control logic determines the optimal timing to start data transfer such that it overlaps with the discharge operation, allowing data to be ready for output before the discharge phase fully completes.

Inventive Principle:
Principle #10Preliminary action

2Stability of the object's composition

If discharge operation is completed before data transfer operation, then data stability is ensured, but data output efficiency is reduced

Engineering Contradiction:
Improvedata stabilityVSAvoiddata output efficiency
Core Design Contradiction:
Stability of the object's compositionVSProductivity

Solution Approach 1:

The patent dynamically adjusts the timing of data transfer operation based on the discharge operation status. The control logic monitors the discharge phase and initiates data transfer at the optimal moment, allowing flexible timing adjustment to balance data stability requirements with efficiency goals, rather than following a fixed sequential order.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent maintains continuous useful action by overlapping the data transfer operation with the discharge operation. Instead of having idle time between discharge completion and data transfer initiation, the system keeps both operations running concurrently, maximizing resource utilization and eliminating wasted time while maintaining data integrity through proper control signaling.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentUS11056162B2Memory device and method of operating the same
Publication Date: 2021.07.06 SK HYNIX INC
  • US11056162B2 patent drawing
  • US11056162B2 patent drawing
  • US11056162B2 patent drawing

AI summary

Provided herein is a memory device and a method of operating the same. The memory device may include a memory cell array including a plurality of memory cells, page buffers coupled to the memory cell array through respective bit lines and a control logic configured to control so that, during a read operation, data stored in the memory cell array is sensed and stored in the page buffers, and the data stored in the page buffers is output to an external device, wherein the control logic controls a time point at which a discharge operation is to be performed after the sensing of the data, and a time point at which a data transfer operation between latches included in each of the page buffers is to be performed, in response to a read command received from the external device.