Scalable Multi-Port Memory via 2R1W Bank Assembly

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing multi-port memory designs for Ethernet switch chips face challenges in achieving high core frequencies and scalability due to large area overhead and high power consumption, particularly when expanding from 4 slices to 8 or more, and require complex control logics and additional resources.

Innovation Solution

A data processing method and system that constructs a 2-read n-write multi-port memory unit by assembling 2R1W memories in parallel, allowing data to be written and read efficiently across multiple ports using a combination of spatial and time division techniques, including XOR operations, to minimize resource usage and enhance scalability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the number of memory ports is increased to support more slices (e.g., from 4 to 8), then the processing capacity and bandwidth are improved, but the area overhead and power consumption increase significantly

Engineering Contradiction:
Improveprocessing capacityVSAvoidarea overhead
Core Design Contradiction:
ProductivityVSArea of stationary object

Solution Approach 1:

The memory system is divided into multiple banks, where each bank is a independent 2R1W memory unit. This segmentation allows the system to support multiple write ports by distributing write operations across different banks, thereby increasing processing capacity without proportionally increasing the area overhead of a single memory unit.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a single-port memory architecture to a multi-port architecture by adding the bank dimension. Instead of increasing the port count of a single memory unit, the system uses multiple banks arranged in a dimensional structure, allowing multiple simultaneous write operations while maintaining reasonable area overhead per unit.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Productivity

If the number of memory ports is increased to support more slices, then the processing capacity is improved, but the power consumption increases significantly

Engineering Contradiction:
Improveprocessing capacityVSAvoidpower consumption
Core Design Contradiction:
ProductivityVSUse of energy by stationary object

Solution Approach 1:

The memory system is divided into multiple banks, where each bank is an independent 2R1W memory unit. This segmentation allows the system to support multiple write ports by distributing write operations across different banks, thereby increasing processing capacity without proportionally increasing the area overhead of a single memory unit.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a single-port memory architecture to a multi-port architecture by adding the bank dimension. Instead of increasing the port count of a single memory unit, the system uses multiple banks arranged in a dimensional structure, allowing multiple simultaneous write operations while maintaining reasonable area overhead per unit.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Adaptability or versatility

If customized design methods are used to increase SRAM ports, then the port functionality is improved, but the design cycle and complexity increase

Engineering Contradiction:
Improveport functionalityVSAvoiddesign complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges multiple 2R1W memory units into a bank structure that collectively provides multi-port functionality. By combining simple 2R1W units with control logic, the system achieves n-write capability without requiring complex customized memory designs, thereby reducing design complexity while maintaining adaptability.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The 2R1W memory unit serves as a universal building block that can be replicated and configured to create memory systems with different numbers of write ports. This multi-functional approach allows the same basic unit to support various port configurations, reducing design complexity compared to creating customized memory designs for each port requirement.

Inventive Principle:
Principle #6Universality (Multi-functionality)

4Adaptability or versatility

If algorithm design is used to construct multi-port memory, then the design flexibility is improved, but the resource overhead and processing time increase

Engineering Contradiction:
Improvedesign flexibilityVSAvoidresource overhead
Core Design Contradiction:
Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The patent merges multiple 2R1W memory units into a bank structure that collectively provides multi-port functionality. By combining simple 2R1W units with control logic, the system achieves n-write capability without requiring complex customized memory designs, thereby reducing design complexity while maintaining adaptability.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The 2R1W memory unit serves as a universal building block that can be replicated and configured to create memory systems with different numbers of write ports. This multi-functional approach allows the same basic unit to support various port configurations, reducing design complexity compared to creating customized memory designs for each port requirement.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10818325B2Data processing method and data processing system for scalable multi-port memory
Publication Date: 2020.10.27 SUZHOU CENTEC COMM CO LTD
  • US10818325B2 patent drawing
  • US10818325B2 patent drawing
  • US10818325B2 patent drawing

AI summary

The present invention discloses a data processing method and system for a scalable multi-port memory. The multi-port memory is a 2-read n-write multi-port memory unit. The method comprises: assembling two 2R1W memories into one Bank memory unit; assembling n/2 Bank memory units in depth into a hardware architecture of one 2-read n-write multi-port memory unit; under one clock cycle, when data is written into the 2-read n-write multi-port memory unit, if the size of the data is less than or equal to the bit width of the 2R1W memory, writing the data into different 2R1W memories respectively; and if the size of the data is greater than the bit width of the 2R1W memory, waiting for a second clock cycle, and when the second clock cycle comes, writing the high and low bits of the written data into the two 2R1W memories of one Bank memory unit respectively.