Intel Corp v. Alacritech Inc

1. Case Identification

• Case #: IPR2018-00226
• Patent #: 7,124,205
• Filed: November 21, 2017
• Petitioner(s): Intel Corporation
• Patent Owner(s): Alacritech, Inc.
• Challenged Claims: 1, 4-8, 11, and 13

2. Patent Overview

• Title: Network Interface Device That Fast-Path Processes Solicited Session Layer Read Commands
• Brief Description: The ’205 patent describes a network interface device (NID) designed to accelerate data transfers between a host computer and a network. The NID offloads protocol processing from the host's CPU by using a "fast-path" to handle certain network packets, specifically responses to session layer read commands, thereby reducing host CPU and bus load.

3. Grounds for Unpatentability

Ground 1: Obviousness over Thia and SMB - Claims 1, 4, 5, 8, 11, and 13 are obvious over Thia in view of SMB.

• Prior Art Relied Upon: Thia ("A Reduced Operation Protocol Engine (ROPE) for a Multiple-Layer Bypass Architecture," 1995) and SMB ("Protocols for X/Open PC Interworking: SMB, Version 2," 1992).
• Core Argument for this Ground:
  • Prior Art Mapping: Petitioner argued that Thia disclosed the core architecture of the challenged claims: a network interface device that offloads protocol processing from a host computer. Thia taught a "bypass concept" with a "fast-path" for data transfer, where a Reduced Operation Protocol Engine (ROPE) chip on the network adapter handles predictable data packets, while packets failing a "bypass test" are sent to the host's standard multi-layer protocol stack for "slow-path" processing. This system was explicitly designed for the OSI reference model, which includes session and transport layers. Petitioner contended that SMB was a well-known, publicly available technical standard defining a session layer file-sharing protocol (Server Message Block) that operated within the OSI model and included solicited read commands (e.g., SMBread). Combining the two references, Thia's fast-path architecture would be applied to process SMB's session layer read commands, directly mapping onto the limitations of independent claims 1 and 8.
  • Motivation to Combine: Petitioner asserted multiple motivations. A person of ordinary skill in the art (POSITA) would combine Thia's performance-enhancing bypass system with a popular, real-world file-sharing protocol like SMB to create a practical, high-performance product. Applying Thia to SMB would improve SMB's performance by offloading significant processing to a dedicated network device. Conversely, adding support for a widely-used protocol like SMB would improve Thia's functionality and market acceptance.
  • Expectation of Success: A POSITA would have a high expectation of success because both Thia and SMB were explicitly designed for or compatible with the OSI model. Thia itself stated that its architecture provided an "easy migration path for existing systems," such as those using the SMB protocol.

Ground 2: Obviousness over Thia, SMB, and Carmichael - Claims 6 and 7 are obvious over Thia in view of SMB and Carmichael.

• Prior Art Relied Upon: Thia (1995 article), SMB (1992 technical standard), and Carmichael (Patent 5,894,560).
• Core Argument for this Ground:
  • Prior Art Mapping: This ground built upon the combination of Thia and SMB from Ground 1 and added Carmichael to address limitations in dependent claims 6 and 7 related to data handling. Specifically, these claims required that data from a response comprising multiple packets be placed into the destination memory "together in a substantially contiguous manner" (claim 6) and sequentially (claim 7). Petitioner argued that while Thia taught using Direct Memory Access (DMA) to transfer data to host memory, Carmichael specifically taught an improved method for controlling I/O devices to transfer blocks of data to host memory in a "contiguous" manner using physical region descriptor (PRD) tables. A POSITA would have understood that a file transfer response (as in SMB) would often comprise multiple packets. Carmichael taught how to efficiently manage the DMA transfer of such data blocks into contiguous memory.
  • Motivation to Combine: The primary motivation was to improve the efficiency of the combined Thia/SMB system. The system of Thia is directed at improving data processing speed, and Carmichael is directed at improving efficiency in transferring data to memory. A POSITA would recognize that incorporating Carmichael's efficient DMA management would be a logical and predictable improvement to the Thia/SMB combination, ensuring that the performance gains from protocol offloading were not lost during the final data transfer to host memory. Carmichael's compatibility with common operating systems like UNIX, for which SMB was also intended, made the combination straightforward.
  • Expectation of Success: The combination was argued to be a predictable integration of known technologies to achieve a known goal. Combining Thia's protocol offload, SMB's file transfer protocol, and Carmichael's efficient DMA data placement would predictably result in a fast-path system with efficient memory transfers.

4. Relief Requested

• Petitioner requested the institution of an inter partes review and the cancellation of claims 1, 4-8, 11, and 13 of the ’205 patent as unpatentable.