IP Verse

Hardware Defined Anything In A Platform With Swappable Pods, Message Interface, Sandboxes And Memory Superposition

Patent No. US10873753 (titled "Hardware Defined Anything In A Platform With Swappable Pods, Message Interface, Sandboxes And Memory Superposition") was filed by Xtreamedge Inc on Jul 15, 2018.

What is this patent about?

’753 is related to the field of data processing systems, particularly those requiring flexible and reconfigurable hardware. The background acknowledges the limitations of software-based systems for high-speed data processing and the expense and time associated with redesigning dedicated hardware for each new application or standard, especially in areas like video processing where standards evolve rapidly. The patent aims to provide a solution that bridges the gap between software flexibility and hardware performance.

The underlying idea behind ’753 is to create a modular and reconfigurable data processing platform. This is achieved by using swappable pods or cards within a chassis, interconnected by a messaging interface network. Each pod or card can contain hardware or software modules, and crucially, some pods/cards have sections for user-defined hardware or software. This allows users to customize the system for specific data flow processing architectures.

The claims of ’753 focus on a platform comprising swappable pods or cards within a chassis, interconnected by a messaging interface network. The independent claims emphasize the user-configurability of the pods/cards to implement data flow processing architectures. A key aspect is the messaging-based communication using packets with headers that uniquely identify each module, instance, and type within the system, enabling direct addressing and communication between hardware and software components.

In practice, the invention allows for a highly adaptable system where users can insert, remove, or replace pods/cards to tailor the hardware to specific data processing tasks. The Module Messaging Interface (MMI) network facilitates communication between these modules, routing data packets based on the header information. This allows for a distributed processing architecture where different modules can perform specialized functions in a data pipeline.

The invention differentiates itself from traditional processor-centric systems by prioritizing hardware acceleration and direct module-to-module communication. Unlike systems where processors control all data flow, this platform allows for offloading tasks to dedicated hardware modules, reducing latency and improving throughput. The inclusion of user-definable sections within the pods/cards further enhances flexibility, enabling users to implement custom hardware or software functions tailored to their specific needs, such as video transcoding or stream processing.

How does this patent fit in bigger picture?

Technical landscape at the time

In the late 2010s when ’753 was filed, at a time when video processing was typically implemented using software or dedicated hardware, systems commonly relied on centralized processors rather than distributed hardware modules, and when hardware or software constraints made reconfigurable data flow architectures non-trivial.

Novelty and Inventive Step

The claims were rejected under 35 U.S.C. 103 as being unpatentable over prior art. Claims 2, 5, 7, 9, 12, 14, 16, 18, and 20 were objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form. The prosecution record does NOT describe the technical reasoning or specific claim changes that led to allowance.

Claims

This patent contains 17 claims, with independent claims 1, 7, and 13. The independent claims focus on a platform, a method, and a computer-readable medium for data flow processing using swappable pods or cards. The dependent claims generally elaborate on specific features, configurations, and applications of the platform and method described in the independent claims.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Data flow processing architectures
(Claim 1, Claim 7, Claim 13)		“Embodiments of a single or multi-chassis server with a variety of flexible features for hardware-defined and software-defined functionality in data streaming and data processing systems, including video, are herein disclosed. The server or system is user-configurable and user-reconfigurable, with user-definable hardware modules and user-definable software modules, to implement data flow processing architectures. Multiple examples are shown of data flow processing architectures that can be configured from MMI network coupled hardware and software modules in pods and/or cards, in various embodiments.”Arrangements of hardware and software modules configured to process data in a specific sequence.
Memory superposition
(Claim 7)		“Some embodiments use memory superposition, where multiple types of memory, for example multiple types of RAM (random-access memory), are used in a specified data flow.”Using multiple types of memory in a specified data flow.
Messaging interface network
(Claim 1, Claim 7, Claim 13)		“Various combinations of hardware modules, software modules and memories of various types are coupled through a Module Message Interface (MMI) network that supports communication directly among modules. A header on Module Message Interface packets specifies chassis, board, module, instance and type identifiers, so that packets in the MMI network are routed to a hardware or software module in a pod or card in the chassis or one of multiple chassis.”A network that couples hardware and software modules and supports communication directly among modules.
Swappable pods or cards
(Claim 1, Claim 7, Claim 13)		“Embodiments of a single or multi-chassis server with a variety of flexible features for hardware-defined and software-defined functionality in data streaming and data processing systems, including video, are herein disclosed. Pods and cards are removable, insertable, replaceable and optionally hot-swappable in the chassis. A pod may refer to a module for bulk storage for any type of data and may optionally be referred to as a module or a card.”Removable, insertable, and replaceable modules within a chassis that can contain hardware or software modules.
User-definable hardware modules
(Claim 1, Claim 7, Claim 13)		“The server or system is user-configurable and user-reconfigurable, with user-definable hardware modules and user-definable software modules, to implement data flow processing architectures. An FPGA (field programmable gate array), PLD (programmable logic device), ASIC (application specific integrated circuit), or some hybrid of FPGA/PLD/ASIC, which can be used in pods and cards, has a bridge with an MMI router, and one or more sandboxes for user-defined electronic circuits, optionally including processors.”Hardware modules that can be configured by the user to implement specific data flow processing architectures.

Litigation Cases New

US Latest litigation cases involving this patent.

Case NumberFiling DateTitle
4:25-cv-09567Nov 6, 2025Concurrent Ventures, LLC v. Advanced Micro Devices, Inc.
1:24-cv-00335Mar 29, 2024Concurrent Ventures, Llc V. Advanced Micro Devices, Inc.

Patent Family

Patent Family

File Wrapper

The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.

  • Date

    Description

  • Get instant alerts for new documents

US10873753

XTREAMEDGE INC
Application Number
US16035675
Filing Date
Jul 15, 2018
Status
Granted
Expiry Date
Jul 15, 2038
External Links
Slate, USPTO, Google Patents