17954540. High Performance Memory Allocator simplified abstract (GOOGLE LLC)

From WikiPatents
Jump to navigation Jump to search

High Performance Memory Allocator

Organization Name

GOOGLE LLC

Inventor(s)

Abhishek Agarwal of Santa Clara CA (US)

Srinivas Vaduvatha of San Jose CA (US)

Weiwei Jiang of Santa Clara CA (US)

Hugh McEvoy Walsh of Los Gatos CA (US)

Weihuang Wang of Los Gatos CA (US)

Jiazhen Zheng of Santa Clara CA (US)

Ajay Venkatesan of Milpitas CA (US)

High Performance Memory Allocator - A simplified explanation of the abstract

This abstract first appeared for US patent application 17954540 titled 'High Performance Memory Allocator

Simplified Explanation

The patent application describes a memory allocator for assigning contiguous memory space for data packets in on-chip memory of a network interface card.

  • The memory allocator includes a plurality of sub-allocators that correspond to a structure of entries, where each entry represents a quanta of memory allocation.
  • The sub-allocators are organized in decreasing size in the memory allocator based on the amount of memory quanta they can allocate.

Potential Applications

This technology could be applied in various networking devices and systems where efficient memory allocation for data packets is crucial, such as routers, switches, and network servers.

Problems Solved

1. Efficient memory allocation: The memory allocator helps in efficiently assigning memory space for data packets in on-chip memory, optimizing the overall performance of the network interface card. 2. Contiguous memory allocation: By assigning contiguous memory space, the technology reduces fragmentation and improves data packet processing speed.

Benefits

1. Improved performance: The memory allocator enhances the performance of the network interface card by efficiently managing memory allocation. 2. Reduced fragmentation: Contiguous memory allocation reduces fragmentation, leading to smoother data packet processing.

Potential Commercial Applications

"Memory Allocator for Efficient Data Packet Processing in Network Interface Cards"

Possible Prior Art

One possible prior art could be memory allocation techniques used in network devices and systems prior to the development of this memory allocator.

Unanswered Questions

How does the memory allocator handle memory allocation requests from multiple data packets simultaneously?

The patent application does not provide specific details on how the memory allocator manages concurrent memory allocation requests.

What impact does the memory allocator have on the power consumption of the network interface card?

The patent application does not address the potential impact of the memory allocator on the power consumption of the network interface card.


Original Abstract Submitted

Aspects of the disclosure are directed to a memory allocator for assigning contiguous memory space for data packets in on-chip memory of a network interface card. The memory allocator includes a plurality of sub-allocators that correspond to a structure of entries, where each entry represents a quanta of memory allocation. The sub-allocators are organized in decreasing size in the memory allocator based on the amount of memory quanta they can allocate.