Non-Volatile Memory Dummy Programming Without Host Data Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing NAND memory devices require frequent data transfer from the host to the NAND device for every word line during dummy programming, which degrades performance and efficiency due to increased communication and limited programming cycles.
Innovation Solution
A method and system for a non-volatile memory device that allows programming with dummy data without transferring data from the host for every word line by using preexisting latched data or randomly generated data, which is repeatedly written to additional pages of a new block until each page is filled.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is transferred from host to NAND device for every word line during dummy programming, then the NAND device can be programmed with dummy data, but communication overhead increases and performance degrades
Solution Approach 1:
The patent applies preliminary action by pre-generating dummy data patterns (such as 0x55, 0xAA, 0x00, 0xFF) within the NAND device's internal buffer before the actual programming operation. This allows the device to use internally generated data rather than requiring continuous data transfer from the host for every word line, thereby reducing communication overhead and improving programming performance while maintaining reliability
Solution Approach 2:
The patent implements self-service by enabling the NAND device to autonomously generate and use dummy data for programming operations without requiring continuous host intervention. The device uses its own internal resources (buffer and data generation capability) to fulfill the dummy programming requirement, eliminating the need for repeated data transfers and reducing the workload on the host-device communication interface
2Reliability
If data is transferred from host to NAND device for every word line, then complete data programming is achieved, but energy consumption increases
Solution Approach 1:
The patent applies preliminary action by pre-generating dummy data patterns within the NAND device's internal buffer before the programming operation begins. This eliminates the need for repeated data transfers from the host during word line programming, significantly reducing energy consumption associated with communication while ensuring complete data programming is still achieved through the internally generated dummy data
Solution Approach 2:
The patent implements self-service by enabling the NAND device to autonomously generate and use dummy data for programming operations without requiring continuous host intervention. The device uses its own internal resources (buffer and data generation capability) to fulfill the dummy programming requirement, eliminating the need for repeated data transfers and reducing the workload on the host-device communication interface
3Productivity
If repeated data transfers are performed for every word line, then dummy data programming is completed, but communication overhead increases
Solution Approach 1:
The patent applies preliminary action by pre-generating dummy data patterns (such as 0x55, 0xAA, 0x00, 0xFF) within the NAND device's internal buffer before the actual programming operation. This allows the device to use internally generated data rather than requiring continuous data transfer from the host for every word line, thereby reducing communication overhead and improving programming performance
Solution Approach 2:
The patent implements self-service by enabling the NAND device to autonomously generate and use dummy data for programming operations without requiring continuous host intervention. The device uses its own internal resources (buffer and data generation capability) to fulfill the dummy programming requirement, eliminating the need for repeated data transfers and reducing the workload on the host-device communication interface
Data Source
AI summary
A method of operating a non-volatile memory device is provided. The device includes a latch, a page buffer and blocks, each of which includes pages. The method includes: receiving a page command for a write operation corresponding to a page of one of the blocks; receiving a write command for writing data to the page buffer; latching preexisting latched data or random data generated as latched data; writing the latched data to a page of a new block from among the plurality of blocks that corresponds to a page address based on the write command; and repeatedly updating the page address and repeatedly writing the latched data to additional pages corresponding to each updated page address until each page of the new block has been written to.