Janet M Tseng

US Patent:

20190042304, Feb 7, 2019

Filed:

Dec 3, 2017

Appl. No.:

15/829938

Inventors:

- Santa Clara CA, US
Janet Tseng - Portland OR, US
Tsung-Yuan Tai - Portland OR, US

Assignee:

Intel Corporation - Santa Clara CA

International Classification:

G06F 9/48
H04L 12/851

Abstract:

Methods, apparatus, systems, and software for architectures and mechanisms to accelerate tuple-space search with integrated GPUs (Graphic Processor Units). One of the architectures employs GPU-side lookup table sorting, under which local and global hit count histograms are maintained for work groups, and sub-tables containing rules for tuple matching are re-sorted based on the relative hit rates of the different sub-tables. Under a second architecture, two levels of parallelism are implemented: packet-level parallelism and lookup table-parallelism. Under a third architecture, dynamic two-level parallel processing with pre-screen is implemented. Adaptive decision making mechanisms are also disclosed to select which architecture is optimal in view of multiple considerations, including application preferences, offered throughput, and available GPU resources. The architectures leverage utilization of both processor cores and GPU processing elements to accelerate tuple-space searches, including searches using wildcard masks.

US Patent:

20190044869, Feb 7, 2019

Filed:

Aug 17, 2018

Appl. No.:

15/999133

Inventors:

- Santa Clara CA, US
Ren Wang - Portland OR, US
Janet Tseng - Portland OR, US
Tsung-Yuan Tai - Portland OR, US

International Classification:

H04L 12/851
H04L 12/931
H04L 12/713
H04L 12/26
H04L 29/08
G06F 11/34

Abstract:

Technologies for classifying network flows using adaptive virtual routing include a network appliance with one or more processors. The network appliance is configured to identify a set of candidate classification algorithms from a plurality of classification algorithm designs to perform a flow classification operation and deploy each of the candidate classification algorithms to a processor. Additionally the network appliance is configured to monitor a performance level of each of the deployed candidate classification algorithms and identify a candidate classification algorithm of the deployed candidate classification algorithms with the highest performance level. The network appliance is further configured to deploy the identified candidate classification algorithm with the highest performance level on each of the one or more processors that are configured to perform the flow classification operation. Other embodiments are described herein.

US Patent:

20180270309, Sep 20, 2018

Filed:

Oct 2, 2017

Appl. No.:

15/722698

Inventors:

- SANTA CLARA CA, US
JANET TSENG - PORTLAND OR, US
REN WANG - PORTLAND OR, US
JUN NAKAJIMA - SAN RAMON CA, US
TSUNG-YUAN TAI - PORTLAND OR, US

Assignee:

INTEL CORPORATION - SANTA CLARA CA

International Classification:

H04L 29/08
H04L 12/835
H04L 12/713
H04L 12/721
H04L 12/725
H04L 12/26

Abstract:

Various embodiments are generally directed to techniques for improving the efficiency of exchanging packets between pairs of VMs within a communications server. An apparatus may include a processor component; a network interface to couple the processor component to a network; a virtual switch to analyze contents of at least one packet of a set of packets to be exchanged between endpoint devices through the network and the communications server, and to route the set of packets through one or more virtual servers of multiple virtual servers based on the contents; and a transfer component of a first virtual server of the multiple virtual servers to determine whether to route the set of packets to the virtual switch or to transfer the set of packets to a second virtual server of the multiple virtual servers in a manner that bypasses the virtual switch based on a routing rule.

US Patent:

20170061566, Mar 2, 2017

Filed:

Aug 26, 2015

Appl. No.:

14/836142

Inventors:

- Santa Clara CA, US
Shinae Woo - Portland OR, US
Janet Tseng - Portland OR, US
Tsung-Yuan C. Tai - Portland OR, US

International Classification:

G06T 1/20
H04L 12/931
H04L 12/26
H04L 12/911
H04L 29/08

Abstract:

Technologies for offloading an application for processing a network packet to a graphics processing unit (GPU) of a network device. The network device is configured to determine resource criteria of the application and available resources of the GPU. The network device is further configured to determine whether the available GPU resources are sufficient to process the application based on the resource criteria of the application and the available GPU resources. Additionally, the network device is configured to determine one or more estimated GPU performance metrics based on the resource criteria of the application and the available GPU resources to determine whether to offload the application to the GPU. Other embodiments are described and claimed.

US Patent:

20170054659, Feb 23, 2017

Filed:

Aug 20, 2015

Appl. No.:

14/830862

Inventors:

- Santa Clara CA, US
JANET TSENG - PORTLAND OR, US
REN WANG - PORTLAND OR, US
JUN NAKAJIMA - SAN RAMON CA, US
TSUNG-YUAN TAI - PORTLAND OR, US

Assignee:

Intel Corporation - Santa Clara CA

International Classification:

H04L 12/931
H04L 12/741
H04L 12/813
H04L 29/08
H04L 12/26

Abstract:

Various embodiments are generally directed to techniques for improving the efficiency of exchanging packets between pairs of VMs within a communications server. An apparatus may include a processor component; a network interface to couple the processor component to a network; a virtual switch to analyze contents of at least one packet of a set of packets to be exchanged between endpoint devices through the network and the communications server, and to route the set of packets through one or more virtual servers of multiple virtual servers based on the contents; and a transfer component of a first virtual server of the multiple virtual servers to determine whether to route the set of packets to the virtual switch or to transfer the set of packets to a second virtual server of the multiple virtual servers in a manner that bypasses the virtual switch based on a routing rule.