SSD Computation Accelerator for Autonomous Proof of Space
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory sub-systems face challenges in efficiently generating proof of space plots for cryptocurrency networks, requiring significant computational resources and energy, especially when the host system is in a low power mode or disconnected, leading to impractical data storage and energy consumption.
Innovation Solution
Incorporating a computation accelerator, such as a Multiply-Accumulate (MAC) unit, within the memory sub-system to perform computationally intensive operations like plot generation, allowing the memory sub-system to operate autonomously and reduce the burden on the host system, enabling efficient proof of space activities even when the host is in a low power mode.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the host system performs proof of space computations, then the computational resources and processing power are utilized, but the energy consumption increases and the host system cannot operate in low power mode
Solution Approach 1:
The proof of space computation system is segmented into two independent parts: the host system that provides storage space and the separate computation accelerator that performs cryptographic operations. This allows the host system to remain in low power mode while the accelerator handles computational tasks independently.
Solution Approach 2:
A computation accelerator acts as an intermediary component between the host system and the proof of space protocol. The accelerator receives storage space from the host, performs the computational work independently, and returns results, thereby mediating the energy-intensive operations without burdening the host system.
2Use of energy by moving object
If the host system is disconnected or in low power mode, then energy consumption is reduced, but the memory sub-system cannot perform plot generation autonomously
Solution Approach 1:
The computation accelerator is designed to autonomously perform proof of space computations using storage space provided by the host system. It independently executes cryptographic hash functions and plot generation algorithms without requiring the host system to be active or connected, enabling self-service operation.
Solution Approach 2:
The host system pre-provides storage space to the computation accelerator before disconnection or low power mode. The accelerator then uses this pre-provided space to perform computations autonomously, allowing the host to disconnect without affecting the ongoing proof of space activities.
3Productivity
If conventional memory sub-systems perform proof of space activities, then the storage space is utilized, but the computational load and energy consumption become impractical
Solution Approach 1:
The system segments computational responsibilities by separating storage functions (handled by the host memory sub-system) from computation functions (handled by the dedicated computation accelerator). This division reduces the complexity burden on any single component while maintaining overall system productivity.
Solution Approach 2:
The patent replaces the general-purpose mechanical computing system (host CPU) with a specialized computation accelerator designed specifically for cryptographic operations. This substitution reduces computational complexity requirements by using hardware optimized for hash function calculations rather than general-purpose processing.
Data Source
AI summary
A memory sub-system, such as a solid state drive (SSD), having host interface configured to receive at least read commands and write commands from an external host system. The SSD has memory cells formed on at least one integrated circuit die, and a processing device configured to control executions of the read commands to retrieve data from the memory cells and executions the write commands to store data into the memory cells. The SSD has a computation accelerator adapted to accelerate computations involved in generation of proof of space plots, such as computations of Basic Linear Algebra Subprograms (BLAS), multiplication and accumulation operations, and cryptographic operations.