Distributed ECC Memory Channels for Low-Overhead RAIM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Redundant Array of Independent/Inexpensive Memory (RAIM) designs require excessive resources and overhead for fault-tolerant and error correction functionalities, leading to high power consumption and cost, especially in environments prone to memory failures due to high integration density or harsh conditions like high altitudes and astronomical radiation.
Innovation Solution
The proposed RAIM memory system reduces the number of ECC memory devices by distributing ECC symbols across multiple channels and data memory devices, allowing each memory module to generate sufficient ECC symbols to support RAIM functionalities without dedicated ECC DIMMs, thereby optimizing resource usage and reducing overhead.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional RAIM designs use dedicated ECC memory devices for fault-tolerant functionalities, then reliability is improved, but device complexity and resource overhead increase
Solution Approach 1:
The patent merges data storage and ECC functionality into the same memory channel by allowing data memory devices to carry both data and ECC symbols. This eliminates the need for separate dedicated ECC memory devices, reducing resource overhead while maintaining fault-tolerance capabilities through the distributed RAIM architecture.
Solution Approach 2:
Data memory devices are designed to perform multiple functions: storing data and generating/carrying ECC symbols for error correction. This multi-functionality reduces the need for specialized ECC-only memory devices, thereby reducing device complexity and resource overhead while preserving reliability.
2Reliability
If conventional RAIM designs provide high performance and reliability functionalities, then reliability is improved, but power consumption increases
Solution Approach 1:
By combining data and ECC symbols in the same memory channel and using the same physical memory devices for both purposes, the patent reduces the total number of active memory components. This reduction directly lowers power consumption while maintaining the fault-tolerance functionality through efficient use of existing resources.
3Reliability
If conventional RAIM designs use extra resources for error correction, then reliability is improved, but manufacturing cost increases
Solution Approach 1:
The patent merges ECC functionality into existing data memory channels, eliminating the need for separate ECC memory modules. This reduces the total component count and simplifies the manufacturing process, thereby reducing manufacturing costs while maintaining error correction capabilities through the distributed RAIM architecture.
4Reliability
If conventional RAIM designs allocate dedicated ECC memory devices, then fault-tolerance is improved, but memory bandwidth efficiency decreases
Solution Approach 1:
By merging data and ECC symbols into the same memory channel and using the same physical memory devices, the patent eliminates redundant data transmission paths. This improves memory bandwidth efficiency by utilizing existing channel capacity for dual purposes (data and ECC) rather than dedicating separate channels, while maintaining fault-tolerance through the RAIM error correction mechanism.
Data Source
AI summary
A memory system includes memory modules having a number of sets of memory devices including data memory devices for data and error correction code (ECC). The ECC memory devices carry ECC symbols in order to facilitate Redundant Array of Independent Memory (RAIM) functionalities for the memory modules. A host receives and decodes the ECC symbols and executes RAIM operations. The host and the memory modules are coupled by a number of channels, one channel per each set of the memory devices.