PTAB

IPR2017-01402

Intel Corp v. Alacritech Inc

Log In
Key Events
Petition
petition

1. Case Identification

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 (NIC) designed to accelerate data transfers by offloading protocol processing from a host computer's CPU. The NIC identifies incoming data packets that are responses to specific session layer read commands and processes them on a "fast-path," bypassing the host's conventional protocol stack and placing the data directly into memory to reduce CPU load and improve system performance.

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 taught the core architecture of the challenged claims, including a network interface device with a specialized chip (the “ROPE” chip) that performs fast-path processing for certain data packets, bypassing the host computer’s standard, multi-layer protocol stack (“SPS” or slow-path). Thia’s fast-path mechanism uses header prediction to identify bypassable packets and Direct Memory Access (DMA) to place data into the host’s destination memory, thereby reducing the host CPU’s workload. Petitioner contended that while Thia provided the bypass architecture, it lacked a specific session layer protocol. The SMB reference, a well-known technical standard for a session layer file-sharing protocol, was argued to supply this missing element. SMB explicitly discloses “solicited read commands” (e.g., SMBread) for file access. The combination of Thia’s fast-path processing architecture with the widely used SMB protocol allegedly rendered independent claims 1 (apparatus) and 8 (method) obvious. Dependent claim 4, specifying SMB as the protocol, was met by the combination itself. Dependent claims 5 and 8, which recite slow-path processing by the host for certain packets, were allegedly taught by Thia’s disclosure that any packet failing the fast-path bypass test is routed to the host’s standard protocol stack for conventional processing.
    • Motivation to Combine: Petitioner asserted that a person of ordinary skill in the art (POSITA) would combine Thia’s efficient bypass architecture with a prevalent, real-world protocol like SMB to create a practical, high-performance product. This combination would predictably improve the performance of SMB-based file sharing by offloading processing to dedicated hardware and would broaden the market applicability of Thia's architecture.
    • Expectation of Success: A POSITA would have a high expectation of success, as both Thia and SMB were designed for use within the context of the OSI reference model and were thus inherently compatible. Thia itself stated it provided an "easy migration path for existing systems."

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, SMB, and Carmichael (Patent 5,894,560).
  • Core Argument for this Ground:
    • Prior Art Mapping: This ground built upon the combination of Thia and SMB to address dependent claims 6 and 7, which require placing data from multiple response packets into a destination memory in a "substantially contiguous manner." Petitioner argued that a file transfer response via SMB would naturally comprise multiple packets. The Thia/SMB combination uses DMA to transfer this data. Carmichael was introduced because it taught methods for improving DMA efficiency by using physical region descriptor (PRD) tables to manage the transfer of single, contiguous blocks of data between an I/O device and main memory. Petitioner asserted that adding Carmichael’s method for contiguous DMA transfers to the Thia/SMB system would result in placing data from a first packet and a second packet together in a substantially contiguous manner, as required by claim 6. For claim 7, which adds the limitation that the first data is placed into memory before the second packet is received, Petitioner argued that Carmichael taught the sequential transfer of data blocks, satisfying this temporal requirement.
    • Motivation to Combine: A POSITA, having combined Thia and SMB, would be motivated to further improve the system's efficiency, particularly the data transfer process. Carmichael was directed to improving DMA performance at minimal cost and was compatible with operating systems (e.g., UNIX) and protocols that also used SMB. Therefore, applying Carmichael’s teachings to optimize the DMA operations in the Thia/SMB system was presented as a logical and obvious design choice.
    • Expectation of Success: The result of the combination was predictable: a fast-path file-sharing system with more efficient DMA transfers for improved overall performance.

4. Relief Requested

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