Intel Corporation

Arm Limited

Tessil Thomas

Phani Kumar Kandula

Raj K Ramanujan

Bill Nale

Ajay Harikumar

Taarinya Polepeddi

Biju Puther Simon

Muthukumar Swaminathan

Baskaran Ganesan

Krishnakanth Venkata Sistla

Ian M Steiner

Sandeep Ahuja

Anitha Kona

Robin A Steinbrecher

Srikanth Balasubramanian

Keshavram N Murty

Sambaran Mitra

Satish Shrimali

Howard Chin

Mohan J Kumar

Stefan Rusu

Vivek Garg

Kai Cheng

Mrittika Ganguli

Keshavan K Tiruvallur

Debaleena Das

Arthur Brian Laughton

Ashley John Crawford

Narayanan Natarajan

Buck Gremel

Gururaj Shamanna

Timothy Y Kam

Michael Berktold

Ramesh Subashchandrabose

Chandra P Joshi

Lokesh Sharma

Jacob Joseph

Sankalan Prasad

Mandar R Ranade

Jamshed Jalal

Ankush Varma

Mahesh S Natu

Andrew Christopher Rose

Ramamurthy Krithivas

Alberto J Munoz

Madhu S Athreya

Jayakrishna Guddeti

Suresh Sugumar

Dominic William Brown

Kiran Singh Panesar

Christopher Vincent Severino

Henk G Neefs

Seow Chuan Lim

Chris Poirier

Anil S Keshavamurthy

Susan F Smith

Richard J Glass

Ling Cen

Junaid Thaliyil

Ramesh S

Vinila Rose

Pawan Chhabra

Andrew Joseph Rushing

Pavithra Sampath

Jaiber J John

Muthukumar P Swaminathan

Andrea Pellegrini

Randall L Jones

Sampath Dakshinamurthy

Vijayanand Naik

Achutha Kiran Kumar V Madhunapantula

Vishal Moondhra

Michael Wayne Garner

Jan-Peter Larsson

Nandakishore Sastry

David Guillen Fandos

Karthick Santhanam

Muthukuman P Swaminathan

Liana Christine Nicklaus

Hussam Mousa

Martin Mark T Rowland

The present disclosure provides a system and methods for transferring data across an interconnect. One method includes, at a request node, receiving, from a source high speed serial controller, a write request from a source, dividing the write request into sequences of smaller write requests each having a last identifier, and sending, to a home node, the sequences of smaller write requests; and, at the home node, sending, to a destination high speed serial controller, the sequences of smaller write requests for assembly into intermediate write requests that are transmitted to a destination. Each sequence of smaller write requests is assembled into an intermediate write request based on the last identifier.

Message protocol for a data processing system

In one embodiment, a processor includes at least one core to execute instructions, one or more thermal sensors associated with the at least one core, and a power controller coupled to the at least one core. The power controller has a control logic to receive temperature information regarding the processor and dynamically determine a maximum allowable average power limit based at least in part on the temperature information. The control logic may further maintain a static maximum base operating frequency of the processor regardless of a value of the temperature information. Other embodiments are described and claimed.

Controlling average power limits of a processor

A data processing apparatus is provided that includes communication circuitry to transmit an interconnect message to a root port using a physical address mapped to the root port. Translation circuitry encapsulates, within the interconnect message to the root port, a Peripheral Component Interconnect Express (PCIe) message to a destination, the PCIe message having routing information encoded as a PCIe bus number associated with the destination.

PCIe routing

In an embodiment, a processor includes at least one core and power management logic. The power management logic is to receive temperature data from a plurality of dies within a package that includes the processor, and determine a smallest temperature control margin of a plurality of temperature control margins. Each temperature control margin is to be determined based on a respective thermal control temperature associated with the die and also based on respective temperature data associated with the die. The power management logic is also to generate a thermal report that is to include the smallest temperature control margin, and to store the thermal report. Other embodiments are described and claimed.

Apparatus and method to provide a thermal parameter report for a multi-chip package

An apparatus is provided, connectable to a memory and one or more peripherals. The apparatus includes translation request circuitry to receive a translation request from one of the peripherals to translate an input address within an input domain to an output address within an output domain. Signing circuitry generates a signature of at least part of the output address using a private key. Translation response circuitry responds to the translation request by transmitting to the one of the peripherals a translation response, including the output address and the signature. Gateway circuitry receives access requests to the memory. Each of the access requests comprises a desired memory address in the output domain and a signature of the desired memory address. The gateway performs validation of the signature of the desired memory address using the private key and in response to the validation of a given access request failing, performs an error action.

Secure memory translations

A data processing apparatus is provided comprising first processing circuitry. Interrupt generating circuitry generates an outgoing interrupt in response to the first processing circuitry becoming unresponsive. Interrupt receiving circuitry receives an incoming interrupt, which indicates that second processing circuitry has become unresponsive, and in response to receiving the incoming interrupt, causes the data processing apparatus to access data managed by the second processing circuitry.

Responding to unresponsive processing circuitry

An apparatus and method are provided for processing flush requests within a packet network. The apparatus comprises a requester device within the packet network arranged to receive a flush request generated by a remote agent requesting that one or more data items be flushed to a point of persistence. The requester device translates the flush request into a packet-based flush command conforming to a packet protocol of the packet network. A completer device within the packet network that is coupled to a persistence domain incorporating the point of persistence is arranged to detect receipt of the packet-based flush command, and then trigger a flush operation within the persistence domain to flush the one or more data items to the point of persistence. This provides a fast, hardware-based, mechanism for performing a flush operation within a persistence domain without needing to trigger software in the persistence domain to handle the flush to the point of persistence.

Apparatus and method for processing flush requests within a packet network

An apparatus includes a first device configured to generate a transaction request targeted to a first address, a switch, coupled to the first device and configured to the route the transaction request, a port coupled to the peripheral switch and the data processing network, and a system memory management unit, coupled to the port. The system memory management unit is configured for receiving an address query for the first address from the peripheral port translating the first address to a second address, accessing attributes of a device associated with the second address and responding to the query. Access validation for the transaction request is confirmed or denied dependent upon the second address and the attributes of the device associated with the second address. The first device may be a peripheral device, the switch may be a peripheral switch and the port may be a peripheral port.

System architecture with query based address translation for access validation

An apparatus and method are provided for handling address decoding in a system-on-chip (SoC). The SoC has processing circuitry for performing data processing operations, a first plurality of devices, and an interconnect to couple the processing circuitry to the first plurality of devices. The first plurality of devices are a first level of devices within a hierarchical structure of devices forming a device network. Those devices communicate using a device communication protocol which also provides an enumeration mechanism to enable software executed on the processing circuitry to discover and configure the devices within the network. The system address space provides a pool of addresses that are reserved for allocation to the first plurality of devices. An address decoder of the SoC has a device address decoder to maintain, for each device in the first plurality of devices, an indication of which addresses within the pool are allocated to that device. Hence, when a request is issued by the processing circuitry identifying an address within the pool of addresses, the device address decoder can be used to determine the appropriate device within the first plurality of devices that the request is directed to. The device address decoder is exposed to the software as a device of the device network so as to enable the software executing on the processing circuitry to discover and configure the device address decoder using the enumeration mechanism. As a result, the allocation of the pool of addresses amongst the first plurality of devices can be dynamically reconfigured under software control.

Apparatus and method for handling address decoding in a system-on-chip

A semiconductor chip comprising memory controller circuitry having interface circuitry to couple to a memory channel. The memory controller includes first logic circuitry to implement a first memory channel protocol on the memory channel. The first memory channel protocol is specific to a first volatile system memory technology. The interface also includes second logic circuitry to implement a second memory channel protocol on the memory channel. The second memory channel protocol is specific to a second non volatile system memory technology. The second memory channel protocol is a transactional protocol.

Memory channel that supports near memory and far memory access

The present disclosure is directed to capability determination for computing resource allocation. A device may comprise a management engine (ME) to determine device information for use in generating an enhanced universally unique identifier (UUID) based on a UUID corresponding to the device. The ME may interact with equipment in the device to obtain the device information, and may augment the UUID using at least part of the device information. Device information may include a device media access control (MAC) address, a central processing unit (CPU) identification (ID) for at least one CPU in the device and a device capability ID. The capability ID may be generated utilizing capability information obtained from the equipment, and may be encoded into the capability ID based on tables that describe different capabilities. The device may provide the enhanced UUID to a group agent that may group the device with other devices comprising similar capabilities.

Capability determination for computing resource allocation

A method of operating a cache and corresponding apparatus are provided. The cache is capable of being only partially powered, and a decision to reduce the proportion of the cache which is currently powered is made based on calculating a memory bandwidth equivalent of expending the current active cache leakage power on memory access. The cache hit bandwidth is compared against this memory bandwidth equivalent and when the cache hit bandwidth is less than the memory bandwidth equivalent, the proportion of the cache which is currently powered is reduced. A analogous decision may also be made and based on calculating a cache hit bandwidth equivalent for an increment increase in cache leakage power, and when the cache miss bandwidth exceeds the cache hit bandwidth equivalent, the proportion of the cache which is currently powered is increased.

Cache power management

Growing community of inventors

Bengaluru, India

Tessil Thomas