Memory Repair Code Compression for Scalable Non-Volatile Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing implementations of non-volatile memory for memory repair, such as FuseROM, do not scale well with increasing device densities and decreasing device sizes, leading to inefficient use of memory space due to fixed repair code sizes and unused padding bits.
Innovation Solution
Implementing a non-volatile memory compression technique that adjusts the repair code length based on the actual number of usable bits per memory instance, using a compression parameter to reduce the size of repair codes stored in non-volatile memory, and employing a control wrapper to manage compression and decompression without impacting existing systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fixed-size repair codes are stored in non-volatile memory, then memory repair functionality is provided, but memory space is wasted due to unused padding bits
Solution Approach 1:
The patent changes the parameter of repair code length from fixed to variable. The repair code length is adjusted based on the actual number of usable bits per memory instance, eliminating the need for fixed-size allocation and reducing wasted memory space from padding bits.
Solution Approach 2:
The patent introduces dynamic adjustment of repair code size. A control wrapper dynamically manages compression and decompression of repair codes based on the specific memory instance configuration, allowing the system to adapt the repair code length to actual needs rather than using a static fixed size.
2Quantity of substance
If compression techniques are implemented to reduce repair code size, then area-efficient storage is achieved, but system complexity increases
Solution Approach 1:
The patent introduces a control wrapper as an intermediary component that manages the compression and decompression operations. This intermediary handles the complexity of variable-length encoding and decoding, isolating the compression logic from both the memory array and the external testing equipment, thereby containing the added complexity within a dedicated module.
Solution Approach 2:
The patent uses compression control data that essentially copies or references the compression parameters and original repair code length information. This allows the system to store compressed repair codes while maintaining the ability to reconstruct the original repair information without requiring complex decompression algorithms for every operation.
3Adaptability or versatility
If variable repair code lengths are used, then scalability with device density is improved, but compatibility with existing systems becomes challenging
Solution Approach 1:
The patent makes the control wrapper a universal component that can handle multiple memory instance types and configurations. It provides multi-functionality by supporting both compressed and uncompressed repair code formats, and can adapt to different memory densities and architectures, making the system compatible with existing and future memory designs.
Solution Approach 2:
The patent enables parameter changes in repair code length to match different device densities and memory configurations. By adjusting the repair code size parameter based on the actual number of usable bits, the system can scale from low-density to high-density devices while maintaining compatibility through the control wrapper's adaptive interface.
Data Source
AI summary
One example includes an integrated circuit (IC). The IC includes non-volatile memory and logic. The logic is configured to receive repair code associated with a memory instance and assign a compression parameter to the repair code based on a configuration of the memory instance. The logic is also configured to compress the repair code based on the compression parameter to produce compressed repair code and to provide compressed repair data that includes the compressed repair code and compression control data that identifies the compression parameter. A non-volatile memory controller is coupled between the non-volatile memory and the logic. The non-volatile memory controller is configured to transfer the compressed repair data to and/or from the non-volatile memory.