Data Encoding for Low-Hamming-Weight Memory Bus Transfers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
External memory accesses in computing systems consume a significant amount of power, particularly due to the capacitance of the bus, and existing methods like bus-invert coding require additional hardware and decrease efficiency as the number of bits compared increases.
Innovation Solution
A method of encoding data values by mapping them to a pre-defined set of codes based on their probability distribution, reducing the Hamming Weight or number of bit flips, which can be transmitted over external buses without requiring additional bus lines or specialized memories, thus reducing power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If bus-invert coding is used to reduce transitions in transmitted data, then power consumption is reduced, but additional bus lines and specialized memories are required
Solution Approach 1:
The patent changes the parameter being optimized from transition reduction (bus-invert) to Hamming weight reduction. By mapping input values to codes with lower Hamming weight based on probability distribution, the invention reduces power consumption without requiring additional bus lines or specialized memory hardware.
Solution Approach 2:
The invention uses a pre-defined set of codes that can be stored in standard memory rather than requiring specialized memory hardware. The mapping from input values to these codes creates a virtual encoding system that works with conventional memory and bus structures.
2Measurement precision
If bus-invert coding compares more bits to determine inversion, then encoding accuracy improves, but efficiency decreases
Solution Approach 1:
The patent pre-defines a set of codes with known Hamming weights before encoding begins. This eliminates the need for real-time comparison of multiple bits to determine inversion, as the mapping to low Hamming weight codes is determined by pre-calculated probability distributions, significantly improving encoding efficiency.
Solution Approach 2:
The encoding system uses the probability distribution characteristics of the input data itself to determine the optimal code mapping. The system serves its own encoding needs by leveraging statistical properties of the data rather than requiring complex external control logic for bit comparison.
3Speed
If input values are mapped to codes with same bit-length, then transmission efficiency is maintained, but power reduction is limited
Solution Approach 1:
The patent introduces a new dimension to the encoding problem by considering Hamming weight as the optimization criterion instead of just transition reduction. This dimensional shift allows mapping to codes of the same bit-length that have lower Hamming weight, achieving both transmission efficiency and power reduction simultaneously.
Data Source
AI summary
Power consumption of read/write operations of a processor is reduced by encoding data values. An input value of a plurality of input values with a uniformly distributed random probability is mapped to one of a predefined set of codes, wherein the input value is mapped to a code that comprises more bits than the input value. The codes corresponding to the input value are outputted, wherein compared to an input value having a relatively low value, an input value having a relatively high value is mapped to a code of the pre-defined set of codes which either: (i) is closer to a target Hamming Weight, or (ii) has closer to a target number of bit flips within the code.