Server-processor hybrid system for processing data

• US 9,135,073 B2
• Filed: 11/15/2007
• Issued: 09/15/2015
• Est. Priority Date: 11/15/2007
• Status: Expired due to Fees

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Kim, Moon J., Moulic, James R., Krishnamurthy, Rajaram B.
• Primary Examiner(s): Nawaz, Asad
• Assistant Examiner(s): Ansari, Najeebuddin
• Application Number:
  US11/940,506
• Publication Number:
  US 20090132638A1
• Time in Patent Office: 2,861 Days
• Field of Search: 709/202, 709/203, 709/219, 709222-228, 709/201
• US Class Current: 1/1
• CPC Class Codes: G06F 11/0709 in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
• CPC Class Codes: G06F 2209/509 Offload
• CPC Class Codes: G06F 9/50 Allocation of resources, e.g. of the central processing unit [CPU]
• CPC Class Codes: G06F 9/5005 to service a request
• CPC Class Codes: G06F 9/5044 considering hardware capabilities
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/51 Discovery or management thereof, e.g. service location protocol [SLP] or web services

Abstract

The present invention relates to a server-processor hybrid system that comprises (among other things) a set (one or more) of front-end servers (e.g., mainframes) and a set of back-end application optimized processors. Moreover, implementations of the invention provide a server and processor hybrid system and method for distributing and managing the execution of applications at a fine-grained level via an I/O-connected hybrid system. This method allows one system to be used to manage and control the system functions, and one or more other systems to co-processor.

Claims

1. A server-processor hybrid system for processing data, comprising:

a set of front-end servers configured to receive the data from an external source;

a set of back-end application optimized processors configured to receive the data from the set of front-end servers, process the data, and return processed data to the set of front-end servers, each of the set of back-end application optimized processors comprising;

a power processing element (PPE);

an element interconnect bus (EIB) coupled to the PPE; and

a set of special purpose engines (SPEs) coupled to the EIB, wherein the set of front-end servers performs a specific processor selection function in order to select one of the set of SPEs to process the data;

a staging storage device configured to store the received data prior to the set of back-end application optimized processors processing the data;

a processed data storage device, separate from the staging storage device, configured to store the processed data from the set of back-end application optimized processors; and

an interface within at least one of the set of front-end servers having a set of network interconnects, the interface connecting the set of front-end servers with the set of back-end application optimized processors, the interface configured to;

communicate the data received from the external source, from the set of front-end servers to the set of back-end application optimized processors by selectively invoking a push model or a pull model, and

communicate the processed data from at least one of the processed data storage device and the back-end application optimized processors, to the set of front-end servers by selectively invoking the push model or the pull model,

wherein the push model is selectively invoked when the data to be transmitted;

has a predefined length, has a latency bound, or is smaller than a predefined Push Threshold (PT), and

the pull model is selectively invoked when the data to be transmitted;

is a stream, does not have a predefined length, exceeds the predefined PT, or does not have a latency bound.

2. The front-end server-processor hybrid system of claim 1, the interface being an input/output (I/O) cage.

3. The front-end server-processor hybrid system of claim 1, the interface being embodied on each of the set of front-end servers.

4. The front-end server-processor hybrid system of claim 1, further comprising a web content server, portal, an application, an application accelerator and a database accelerator.

5. The server-processor hybrid system of claim 1, wherein the interface is further configured to:

send a control message across a control path that is separate from a path across which the data received from the external source and the processed data are sent,

wherein a first connection ID is required for the control path and a second connection ID is required for the path across which the data received from the external source and the processed data are sent.

6. The server-processor hybrid system of claim 1, wherein the interface is further configured to:

send a control message across a same path across which the data received from the external source and the processed data are sent,

wherein a single connection ID is used for both the control message and the data.