Intel Corporation

Rahul R Shah

Venkatraman Iyer

William R Halleck

Arvind A Kumar

Darren S Jue

Debendra Das Sharma

Aaron T Spink

Fulvio Spagna

Robert G Blankenship

Raj K Ramanujan

Yen-Cheng Liu

Simon P Johnson

Robert J Safranek

Herbert H Hum

Ashish Gupta

Vedaraman Geetha

Bahaa Fahim

Jeffrey Charles Swanson

Robert H Beers

Jeff Willey

Sitaraman V Iyer

William Harry Nale

Abhishek Das

Yuvraj S Dhillon

Robert A Maddox

Eric M Lee

Sanjay Dabral

Theodore Zale Schoenborn

Tim Frodsham

Mrittika Ganguli

David Stewart Dunning

David Sonnier

Maurice B Steinman

Stephen T Palermo

Naveen Cherukuri

William G Burroughs

Edwin Verplanke

Shrikant M Shah

Eduard Roytman

Abhishek Khade

Gage Eads

Abhirupa Layek

Sarita Maini

Bradley Chaddick

Allen Jay Baum

Niall D McDonnell

Mahalingam Nagarajan

Kambiz R Munshi

Jian Xu

Ronald L Bedard

Ren Wang

Mahesh U Wagh

Andrew J Herdrich

Sameh Gobriel

Jeffrey D Chamberlain

Daniel S Froelich

Michelle C Jen

Yipeng Wang

Bruce Richardson

Chetan Hiremath

Muraleedhara Herur Navada

Hongjun Ni

Priya Autee

Chris D Matthews

John Mangan

Chenmin Sun

Praveen Mosur

Omkar Maslekar

Niall Mcdonnell

Chris C Gianos

Methods, apparatus, systems, and articles of manufacture are disclosed for dynamic load balancing for multi-core computing environments. An example apparatus includes a first and a plurality of second cores of a processor, and circuitry in a die of the processor separate from the first and the second cores, the circuitry to enqueue identifiers in one or more queues in the circuitry associated with respective ones of data packets of a packet flow, allocate one or more of the second cores to dequeue first ones of the identifiers in response to a throughput parameter of the first core not satisfying a throughput threshold to cause the one or more of the second cores to execute one or more operations on first ones of the data packets, and provide the first ones to one or more data consumers to distribute the first data packets.

Dynamic load balancing for multi-core computing environments

Methods, apparatus, systems, and articles of manufacture are disclosed for hardware queue scheduling for multi-core computing environments. An example apparatus includes a first core and a second core of a processor, and circuitry in a die of the processor, at least one of the first core or the second core included in the die, the at least one of the first core or the second core separate from the circuitry, the circuitry to enqueue an identifier to a queue implemented with the circuitry, the identifier associated with a data packet, assign the identifier in the queue to a first core of the processor, and in response to an execution of an operation on the data packet with the first core, provide the identifier to the second core to cause the second core to distribute the data packet.

Hardware queue scheduling for multi-core computing environments

Examples described herein include a device interface; a first set of one or more processing units; and a second set of one or more processing units. In some examples, the first set of one or more processing units are to perform heavy flow detection for packets of a flow and the second set of one or more processing units are to perform processing of packets of a heavy flow. In some examples, the first set of one or more processing units and second set of one or more processing units are different. In some examples, the first set of one or more processing units is to allocate pointers to packets associated with the heavy flow to a first set of one or more queues of a load balancer and the load balancer is to allocate the packets associated with the heavy flow to one or more processing units of the second set of one or more processing units based, at least in part on a packet receive rate of the packets associated with the heavy flow.

Packet processing load balancer

A physical layer (PHY) is coupled to a serial, differential link that is to include a number of lanes. The PHY includes a transmitter and a receiver to be coupled to each lane of the number of lanes. The transmitter coupled to each lane is configured to embed a clock with data to be transmitted over the lane, and the PHY periodically issues a blocking link state (BLS) request to cause an agent to enter a BLS to hold off link layer flit transmission for a duration. The PHY utilizes the serial, differential link during the duration for a PHY associated task selected from a group including an in-band reset, an entry into low power state, and an entry into partial width state.

High performance interconnect

Examples described herein relate to a manner of demoting multiple cache lines to shared memory. In some examples, a shared cache is accessible by at least two processor cores and a region of the cache is larger than a cache line and is designated for demotion from the cache to the shared cache. In some examples, the cache line corresponds to a memory address in a region of memory. In some examples, an indication that the region of memory is associated with a cache line demote operation is provided in an indicator in a page table entry (PTE). In some examples, the indication that the region of memory is associated with a cache line demote operation is based on a command in an application executed by a processor. In some examples, the cache is an level 1 (L1) or level 2 (L2) cache.

Cache line demote infrastructure for multi-processor pipelines

Systems, methods, and apparatuses including a Physical layer (PHY) block coupled to a Media Access Control layer (MAC) block via a PHY/MAC interface. Each of the PHY and MAC blocks include a plurality of Physical Interface for PCI Express (PIPE) registers. The PHY/MAC interface includes a low pin count PIPE interface comprising a small set of wires coupled between the PHY block and the MAC block. The MAC block is configured to multiplex command, address, and data over the low pin count PIPE interface to access the plurality of PHY PIPE registers, and the PHY block is configured to multiplex command, address, and data over the low pin count PIPE interface to access the plurality of MAC PIPE registers. The PHY block may also be selectively configurable to implement a PIPE architecture to operate in a PIPE mode and a serialization and deserialization (SERDES) architecture to operate in a SERDES mode.

Bimodal PHY for low latency in high speed interconnects

An apparatus includes an agent to facilitate communication in one of two or more modes, where a first of the two or more modes involves communication over links including a first number of lanes and a second of the two or more modes involves communication over links including a second number of lanes, and the first number is greater than the second number. The apparatus further includes a memory including data to indicate which of the two or modes applies to a particular link and a multiplexer to reverse lane numbering on links including either the first number of lanes or the second number of lanes.

High speed interconnect with channel extension

Bimodal phy for low latency in high speed interconnects

Systems, methods, and apparatuses including a Physical layer (PHY) block coupled to a Media Access Control layer (MAC) block via a PHY/MAC interface. Each of the PHY and MAC blocks include a plurality of Physical Interface for PCI Express (PIPE) registers. The PHY/MAC interface includes a low pin count PIPE interface comprising a small set of wires coupled between the PHY block and the MAC block. The low pin count PIPE interface is configured to transfer register commands between the PHY and MAC blocks over the small set of wires in a time-multiplexed manner to support read and write access of the PHY and MAC PIPE registers. The PHY block may also be selectively configurable to implement a PIPE architecture when operating in a PIPE mode and a serialization and deserialization (SERDES) architecture when operating in a SERDES mode.

An exit pattern is sent to initiate exit from a partial width state, where only a portion of the available lanes of a link are used to transmit data and the remaining lanes are idle. The exit pattern is sent on the idle lanes, the exit pattern including an electrical ordered set (EOS), one or more fast training sequences (FTS), a start of data sequence (SDS), and a partial fast training sequence (FTSp). The SDS includes a byte number field to indicate a number of a bytes measured from a previous control interval of the link, and an end of the SDS is sent to coincide with a clean flit boundary on the active lanes. The partial width state is exited based on the exit pattern and data is sent on all available lanes following the exit from the partial width state.

High performance interconnect link state transitions

Growing community of inventors

Marlborough, MA, United States of America

Rahul R Shah