Autonomous Memory Processing Apparatus Bandwidth Bottleneck

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Memory devices face bandwidth bottlenecks in CPU-based computing systems, limiting their ability to keep pace with increasing computer system performance, particularly in reading and writing operations.

Innovation Solution

An autonomous memory processing apparatus is introduced, comprising a packet parser, program counter, instruction memory, decode logic, register file, execution units, and a packet generator, which enables independent operation of memory devices by parsing and executing instructions, relieving bandwidth constraints through dynamic and parallel processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If memory devices operate autonomously with embedded processing apparatus, then processing efficiency and bandwidth utilization improve, but device complexity increases

Engineering Contradiction:
Improveprocessing efficiencyVSAvoiddevice complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent combines the processing apparatus directly within the memory device, merging storage and computation functions into a single integrated unit. This integration enables autonomous execution of instructions on stored data without external CPU intervention, improving processing efficiency while managing complexity through unified architecture design.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The memory device is equipped with an autonomous processing apparatus that can independently execute instructions and process data stored in its own memory arrays. This self-service capability allows the memory device to perform computations without constant CPU control, reducing bandwidth bottlenecks and improving overall system productivity.

Inventive Principle:
Principle #25Self-service

2Speed

If traditional CPU-based memory control is used, then device complexity remains low, but bandwidth bottlenecks limit processing speed

Engineering Contradiction:
ImprovebandwidthVSAvoidprocessing speed
Core Design Contradiction:
SpeedVSProductivity

Solution Approach 1:

The patent segments the processing functions from the central CPU and distributes them to individual memory devices through embedded processing apparatus. This segmentation allows parallel processing across multiple memory devices, increasing overall system throughput and reducing the bandwidth burden on the CPU-memory interface.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3077911B1Methods and systems for autonomous memory
Publication Date: 2022.05.04 MICRON TECHNOLOGY INC
  • EP3077911B1 patent drawingFigure 1
  • EP3077911B1 patent drawingFigure 2~3
  • EP3077911B1 patent drawingFigure 4

AI summary

A method, an apparatus, and a system have been disclosed. An embodiment of the method includes an autonomous memory device receiving a set of instructions, the memory device executing the set of instructions, combining the set of instructions with any data recovered from the memory device in response to the set of instructions into a packet, and transmitting the packet from the memory device.