Memory Controller Channel Groups to Reduce Access Latency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing memory controller architectures face increased latency due to congestion in memory access request/response buffers, particularly as transfer rates increase, leading to bottlenecks that adversely affect system performance.

Innovation Solution

Implementing a memory controller architecture with multiple independent memory access request/response buffer sets and caches, organized into channel groups, allowing concurrent operation to manage non-overlapping physical address ranges and reduce latency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If a single memory access request/response buffer is used, then the device complexity is low, but latency increases due to congestion at higher transfer rates

Engineering Contradiction:
Improvememory access latencyVSAvoidbuffer architecture complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The patent divides the memory access request/response buffer into multiple independent buffer sets, where each buffer set handles specific memory channels or address ranges. This segmentation allows concurrent access operations to proceed in parallel without interfering with each other, thereby reducing latency and congestion while maintaining manageable complexity through modular organization.

Inventive Principle:
Principle #1Segmentation

2Productivity

If multiple independent buffer sets are implemented, then latency is reduced through concurrent operations, but device complexity increases

Engineering Contradiction:
Improvememory access throughputVSAvoidbuffer architecture complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The buffer is segmented into multiple independent sets that can operate concurrently, enabling parallel processing of memory access requests. This increases productivity by allowing multiple channels to access memory simultaneously without contention, while the modular segmented structure keeps complexity manageable through clear separation of functions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension of parallelism by organizing buffers into multiple sets that operate independently across different memory channels or address spaces. This dimensional expansion from a single sequential buffer to multiple parallel buffers enables concurrent operations, significantly improving throughput and productivity.

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

3Reliability

If memory channels are organized into channel groups with independent buffers, then congestion is reduced, but the device complexity increases

Engineering Contradiction:
Improvememory access reliabilityVSAvoidcontroller architecture complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

Memory channels are segmented into distinct channel groups, each with its own dedicated buffer set. This segmentation isolates congestion to specific channels rather than affecting the entire memory subsystem, thereby improving reliability by ensuring that failures or bottlenecks in one channel do not propagate to others. The modular architecture manages complexity through clear channel-group associations.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20250298749A1Memory controller architecture
Publication Date: 2025.09.25 MICRON TECHNOLOGY INC
  • US20250298749A1 patent drawing
  • US20250298749A1 patent drawing
  • US20250298749A1 patent drawing

AI summary

An apparatus can include a plurality of memory devices and a memory controller coupled to the plurality of memory devices via a plurality of memory channels. The plurality of memory channels are organized as a plurality of channel groups. The memory controller comprises a plurality of memory access request/response buffer sets, and each memory access request/response buffer set of the plurality of memory access request/response buffer sets corresponds to a different one of the plurality of channel groups.