Intel Corporation

Ramadass Nagarajan

Jose Niell

Joydeep Ray

Michael T Klinglesmith

David J Harriman

Ravishankar Iyer

Blaise B Fanning

Ioannis T Schoinas

Daniel Cutter

Sridhar Lakshmanamurthy

Lakshminarayana Pappu

Jorge E Parra

Robert P Adler

Robert De Gruijl

Vinit Mathew Abraham

Peter J Elardo

Siddhartha Chhabra

Uday R Savagaonkar

Debra Bernstein

Mahesh S Natu

Men Long

Jeremy J Shrall

Alpa T Narendra Trivedi

Derek T Bachand

Stanley Steve Kulick

Robert Milstrey

Ravi Kolagotla

James A Coleman

Ganesh Kumar

Deepak Limaye

Erik Hallnor

Quang T Le

Carlos Ornelas

Edgar Borrayo

Eric A Geisler

Ezra N Harrington

Abhishek Reddy Pamu

Michael Todd Frederick

In one embodiment, a device includes: an interface circuit to couple the device to a host via a link, where in a first mode the interface circuit is to be configured as an integrated switch controller and in a second mode the interface circuit is to be configured as a link controller; and a fabric coupled to the interface circuit, the fabric to couple to a plurality of hardware circuits, where the fabric is to be dynamically configured for one of the first mode or the second mode based on link training of the link. Other embodiments are described and claimed.

System, method, apparatus and architecture for dynamically configuring device fabrics

An apparatus comprises a first tile comprising a first instance of a plurality of global endpoints and a first instance of a plurality of local networks comprising a plurality of local endpoints; and an interconnect network of the first tile to couple to an interconnect network of a second tile, the second tile comprising a second instance of the plurality of global endpoints and a second instance of the plurality of local networks comprising the plurality of local endpoints; wherein the interconnect network utilizes an address space comprising unique identifiers for the plurality of global endpoints of the first and second tiles; and non-unique identifiers for the plurality of local endpoints of the first and second tiles, wherein non-unique identifiers are reused in multiple local networks of the plurality of local networks of the first and second tiles.

Interconnect network for multi-tile system on chips

In one embodiment, a system on chip includes a first endpoint to issue a non-posted memory write transaction to a memory and a Peripheral Component Interconnect (PCI)-based fabric including control logic to direct the non-posted memory write transaction to the memory, receive a completion for the non-posted memory write transaction from the memory and route the completion to the first endpoint. Other embodiments are described and claimed.

Method, apparatus and system for handling non-posted memory write transactions in a fabric

In an example, a system-on-a-chip comprises a plurality of multi-core processors, such as four dual-core processors for eight total cores. Each of the processors connects to shared resources such as memory and peripherals via a shared uncore fabric. Because each input bus for each core can include hundreds of data lines, the number of lines into the shared uncore fabric can become prohibitive. Thus, inputs from each core are multiplexed, such as in a two-to-one configuration. The multiplexing may be a non-blocking, queued (such as FIFO) multiplexing to ensure that all packets from all cores are delivered to the uncore fabric. In certain embodiment, some smaller input lines may be provided to the uncore fabric non-multiplexed, and returns (outputs) from the uncore fabric to the cores may also be non-multiplexed.

Low overhead hierarchical connectivity of cache coherent agents to a coherent fabric

Described is an apparatus which comprises: an Intellectual Property (IP) block; control logic operable to send a first command to the IP block to cause the first IP block to enter a first power state from a second power state; and a communicating fabric coupled to the IP block and to the control logic, the communicating fabric to send multiple packets with a first header from the IP block to the control logic after the first command is processed by the IP block, wherein the multiple packets are associated with multiple registers which are identified as registers whose contents are to be saved.

Apparatus and method for saving and restoring data for power saving in a processor

Selected portions of an uncore fabric of a system-on-a-chip (SoC) or other embedded system are divided into two independent pipelines. Each pipeline operates independently of the other pipeline, and each accesses only one-half of the system memory, such as even or odd addresses in an interleaved memory. However, the two pipelines are tightly coupled to maintain coherency of the fabric. Coupling may be accomplished, for example, by a shared clock that is one-half of the base clock cycle for the fabric. Each incoming address may be processed by a deterministic hash, assigned to one of the pipelines, processed through memory, and then passed to a credit return.

Tightly-coupled distributed uncore coherent fabric

In an example, a shared uncore memory fabric of a system-on-a-chip (SoC) is configured to provide real-time power management. The SoC may include a power management agent to inform the shared fabric that the processing cores and peripherals will be idle for a time, and to negotiate a power-saving state. The uncore fabric may also include a local power manager that detects when no access requests have been received for a time, such as when cores are operating from cache. The shared fabric may then unilaterally enter a power-saving state, and remain in that state until an access request is received. In the power-saving state, power and/or clocks are gated, and the fabric's state is stored in retention cells. When a new access request is received, an ungated controller may handle preliminary processing while the local power manager restores the state and powers up the shared fabric.

Power management in an uncore fabric

Dynamic heterogeneous hashing function technology for balancing memory requests between multiple memory channels is described. A processor includes functional units and multiple memory channels, and a memory controller unit (MCU) coupled between them. The MCU includes a general-purpose hashing function block that defines a default interleaving sequence for memory requests to alternately access the multiple memory channels and multiple specific-purpose hashing function blocks that define different interleaving sequences for the memory requests to alternately access the multiple memory channels. The MCU also includes a hashing-function selection block. The hashing-function selection block is operable to select one of the specific-purpose hashing function blocks or the general-purpose hashing function block for a current memory request in view of a requesting functional unit originating the current memory request.

Dynamic heterogeneous hashing functions in ranges of system memory addressing space

In an embodiment, a shared memory fabric is configured to receive memory requests from multiple agents, where at least some of the requests have an associated order identifier and a deadline value to indicate a maximum latency prior to completion of the memory request. Responsive to the requests, the fabric is to arbitrate between the requests based at least in part on the deadline values. Other embodiments are described and claimed.

Method, apparatus, system for representing, specifying and using deadlines

In an embodiment, a shared memory fabric is configured to receive memory requests from multiple agents, where at least some of the requests have an associated deadline value to indicate a maximum latency prior to completion of the memory request. Responsive to the requests, the fabric is to arbitrate between the requests based at least in part on the deadline values. Other embodiments are described and claimed.

Arbitrating memory accesses via a shared memory fabric

A processor is described that includes one or more processing cores. The processor includes a memory controller to interface with a system memory having a protected region and a non protected region. The processor includes a protection engine to protect against active and passive attacks. The processor includes an encryption/decryption engine to protect against passive attacks. The protection engine includes bridge circuitry coupled between the memory controller and the one or more processing cores. The bridge circuitry is also coupled to the protection engine and the encryption/decryption engine. The bridge circuitry is to route first requests directed to the protected region to the protection engine and to route second requests directed to the non protected region to the encryption/decryption engine.

Bridging circuitry between a memory controller and request agents in a system having multiple system memory protection schemes

Dynamic heterogeneous hashing function technology for balancing memory requests between multiple memory channels is described. A processor includes functional units and multiple memory channels, and a memory controller unit (MCU) coupled between them. The MCU includes a dynamic heterogeneous hashing module (DHHM) that includes multiple specific-purpose hashing function blocks that define different interleaving sequences for memory requests to alternately access the multiple memory channels. The DHHM also includes a hashing-function selection block. The hashing-function selection block is operable to identify a requesting functional unit originating a current memory request and to select one of the specific-purpose hashing function blocks for the current memory request in view of the requesting functional unit.

Method, apparatus and system for handling address conflicts in distributed memory fabrics. Memory access requests originating from caching agents and Input/Output (I/O) agents in a computer system are serviced concurrently through use of a distributed memory fabric architecture employing parallel pipelines while maintaining memory coherency for cachelines associated with the caching agents and enforcing memory access ordering for memory access requests originating from I/O agents.

Method, apparatus, system for handling address conflicts in a distributed memory fabric architecture

In one embodiment, a fabric of a processor such as a system on a chip includes at least one data buffer including a plurality of entries each to store data to be transferred to and from a plurality of agents and to and from a memory, a request tracker to maintain track of pending requests to be output to an ordered domain of the fabric, and an output throttle logic to control allocation into the ordered domain between write transactions from a core agent and read completion transactions from the memory. Other embodiments are described and claimed.

Growing community of inventors

Portland, OR, United States of America

Ramadass Nagarajan