Memory allocation using graphs

GB2612160BActive Publication Date: 2026-04-15NVIDIA CORP
View PDF 0 Cites -1 Cited by

Patent Information

Authority / Receiving Office
GB · GB
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-06-15
Publication Date
2026-04-15

AI Technical Summary

Technical Problem

Existing memory allocation techniques for data structures representing operations and dependencies are inefficient, requiring additional computing resources and not effectively utilizing memory outside of these structures, particularly in parallel computing platforms like CUDA.

Method used

The use of graph code nodes, such as MemAlloc and MemFree nodes, within a data structure to manage memory allocation and deallocation, allowing for efficient memory management by representing operations and dependencies, and enabling reuse and sharing of physical memory across graphs.

Benefits of technology

This approach improves memory allocation efficiency by reducing synchronization requirements and allowing for effective reuse and sharing of memory, exceeding the available memory on a GPU, while maintaining proper ownership and validation of allocated memory.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Apparatuses, systems, and techniques to generate one or more graph code nodes to allocate memory 102 108 118. In at least one embodiment, one or more graph code nodes to allocate memory 102 108 118 are generated, based on, for example, CUDA or other parallel computing platform code.
Need to check novelty before this filing date? Find Prior Art