Method and apparatus for reordering in a non-uniform compute device

Beard, Jonathan Curtis; Elsasser, Wendy; Wang, Shibo

Title: Method and apparatus for reordering in a non-uniform compute device

Abstract

A data processing apparatus includes a multi-level memory system, one or more first processing unit coupled to the memory system at a first level and one or more second processing units each coupled to the memory system at a second level. A first reorder buffer maintains data order during execution of instructions by the first and second processing units and a second reorder buffer maintains data order during execution of the instructions by an associated second processing unit. An entry in the first reorder buffer is configured, dependent upon an indicator bit, as an entry for a single instruction or a pointer to an entry in the second reorder buffer. An entry in the second reorder buffer includes instruction block start and end addresses and indicators of input and output register. Instructions are released to a processing unit when all inputs, as indicated by the reorder buffers, are available.

Inventors:: Beard, Jonathan Curtis; Elsasser, Wendy; Wang, Shibo

Issue Date:: 2019-10-15

Research Org.:: ARM Limited, Cambridge (United Kingdom)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1600162

Patent Number(s):: 10445094

Application Number:: 15/166,467

Assignee:: ARM Limited (Cambridge, GB)

Patent Classifications (CPCs):: G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y02 - TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE Y02D - CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THIR OWN ENERGY USE

Show more

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F2212/62 - Details of cache specific to multiprocessor cache arrangements
G06F9/3855 - {Reordering, e.g. using a queue, age tags}
G06F9/32 - Address formation of the next instruction, e.g. by incrementing the instruction counter
G06F9/3004 - {to perform operations on memory}
G06F15/7821 - {Tightly coupled to memory, e.g. computational memory, smart memory, processor in memory}
G06F9/3005 - {to perform operations for flow control}
G06F2212/452 - Instruction code
G06F12/0875 - with dedicated cache, e.g. instruction or stack
G06F12/0893 - Caches characterised by their organisation or structure
G06F12/0811 - with multilevel cache hierarchies
G06F9/30098 - {Register arrangements}

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y02 - TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE Y02D - CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THIR OWN ENERGY USE
Y02D10/00 - Energy efficient computing

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F12/084 - with a shared cache
G06F9/3836 - {Instruction issuing, e.g. dynamic instruction scheduling, out of order instruction execution}

Show less

Resource Type:: Patent

Resource Relation:: Patent File Date: 05/27/2016

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Beard, Jonathan Curtis, Elsasser, Wendy, and Wang, Shibo. Method and apparatus for reordering in a non-uniform compute device.  United States: N. p., 2019. 
        Web.

Copy to clipboard


                    Beard, Jonathan Curtis, Elsasser, Wendy, & Wang, Shibo. Method and apparatus for reordering in a non-uniform compute device.  United States.

Copy to clipboard


                    Beard, Jonathan Curtis, Elsasser, Wendy, and Wang, Shibo. Tue .  
        "Method and apparatus for reordering in a non-uniform compute device".  United States.  https://www.osti.gov/servlets/purl/1600162.

Copy to clipboard


                    
@article{osti_1600162,

  title        = {Method and apparatus for reordering in a non-uniform compute device},

  author       = {Beard, Jonathan Curtis and Elsasser, Wendy and Wang, Shibo},

  abstractNote = {A data processing apparatus includes a multi-level memory system, one or more first processing unit coupled to the memory system at a first level and one or more second processing units each coupled to the memory system at a second level. A first reorder buffer maintains data order during execution of instructions by the first and second processing units and a second reorder buffer maintains data order during execution of the instructions by an associated second processing unit. An entry in the first reorder buffer is configured, dependent upon an indicator bit, as an entry for a single instruction or a pointer to an entry in the second reorder buffer. An entry in the second reorder buffer includes instruction block start and end addresses and indicators of input and output register. Instructions are released to a processing unit when all inputs, as indicated by the reorder buffers, are available.},

  doi          = {},

  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2019},

  month        = {10}

}

Copy to clipboard

Patent:

View Patent

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Progressive sharing during a collaboration session
patent, November 2016

Liu, Guangbing; Sheng, Hailei; Wang, Qing
US Patent Document 9,489,659
URL: http://patft.uspto.gov/netacgi/nph-Parser?patentnumber=9489659

Non-stalling circular counterflow pipeline processor with recorder buffer
patent, February 2004

Janik, Kenneth J.; Lu, Shih-Lien L.; Miller, Michael F.
US Patent Document 6,691,222
URL: http://patft.uspto.gov/netacgi/nph-Parser?patentnumber=6691222

System and method for adjusting to drive specific criteria
patent, October 2013

Vitalo, Michael Joseph; Gosha, Michael Baines
US Patent Document 8,555,053
URL: http://patft.uspto.gov/netacgi/nph-Parser?patentnumber=8555053

Configurable processor system unit
patent, October 2002

Winegarden, Steven P.; Reynolds, Bart; Fox, Brian Edward
US Patent Document 6,467,009
URL: http://patft.uspto.gov/netacgi/nph-Parser?patentnumber=6467009

Secondary reorder buffer microprocessor
patent, September 2003

Kahle, James
US Patent Document 6,629,233
URL: http://patft.uspto.gov/netacgi/nph-Parser?patentnumber=6629233

Method of executing programs in a network
patent, August 1999

Johnson, William J.
US Patent Document 5,938,722
URL: http://patft.uspto.gov/netacgi/nph-Parser?patentnumber=5938722

Cache coherency protocol for a data processing system including a multi-level memory hierarchy
patent, February 2001

Arimilli, Ravi; Dodson, John Steven; Lewis, Jerry Don
US Patent Document 6,192,451
URL: http://patft.uspto.gov/netacgi/nph-Parser?patentnumber=6192451

Similar Records in DOE Patents and OSTI.GOV collections:

Dielectrophoresis device and method having non-uniform arrays for manipulating particles

Patent Cummings, Eric B [Livermore, CA]; Fintschenko, Yolanda [Livermore, CA]; Simmons, Blake [San Francisco, CA]

Microfluidic devices according to embodiments of the present invention include an inlet port, an outlet port, and a channel or chamber having a non-uniform array of insulating features on one or more surfaces. Electrodes are provided for generation of a spatially non-uniform electric field across the array. A voltage source, which may be an A.C. and/or a D.C. voltage source may be coupled to the electrodes for the generation of the electric field.
Full Text Available
Photovoltaic healing of non-uniformities in semiconductor devices

Patent Karpov, Victor G.; Roussillon, Yann; Shvydka, Diana; ...

A method of making a photovoltaic device using light energy and a solution to normalize electric potential variations in the device. A semiconductor layer having nonuniformities comprising areas of aberrant electric potential deviating from the electric potential of the top surface of the semiconductor is deposited onto a substrate layer. A solution containing an electrolyte, at least one bonding material, and positive and negative ions is applied over the top surface of the semiconductor. Light energy is applied to generate photovoltage in the semiconductor, causing a redistribution of the ions and the bonding material to the areas of aberrant electricmore » « less
Full Text Available
Apparatus and method for controlling plating uniformity

Patent Hachman Jr., John T.; Kelly, James J.; West, Alan C.

The use of an insulating shield for improving the current distribution in an electrochemical plating bath is disclosed. Numerical analysis is used to evaluate the influence of shield shape and position on plating uniformity. Simulation results are compared to experimental data for nickel deposition from a nickel--sulfamate bath. The shield is shown to improve the average current density at a plating surface.
Full Text Available
Method and apparatus for fabricating ceramic and metal components via additive manufacturing with uniform layered radiation drying

Patent Leu, Ming C.; Ghazanfari, Amir; Li, Wenbin; ...

A freeform extrusion fabrication process for producing three-dimensional ceramic, metal and functionally gradient composite objects, including the steps of filling a plurality of paste sources with a respective plurality of aqueous paste compositions, operationally connecting respective syringes containing respective aqueous paste compositions to a mixing chamber, moving a first aqueous paste composition from a first respective paste source into the mixing chamber, moving a second aqueous paste composition from a second respective paste source into the mixing chamber, mixing the first and second aqueous paste compositions to define a first admixture having a first admixture composition, extruding the first admixturemore » « less
Full Text Available
Method and apparatus for making uniform pellets for fusion reactors

Patent Budrick, Ronald G [Ann Arbor, MI]; King, Frank T [Hillsboro, OR]; Martin, Alfred J [Ann Arbor, MI]; ...

A method and apparatus for making uniform pellets for laser driven fusion reactors which comprises selection of a quantity of glass frit which has been accurately classified as to size within a few micrometers and contains an occluded material, such as urea, which gasifies and expands when heated. The sized particles are introduced into an apparatus which includes a heated vertical tube with temperatures ranging from 800.degree. C to 1300.degree. C. The particles are heated during the drop through the tube to molten condition wherein the occluded material gasifies to form hollow microspheres which stabilize in shape and plunge intomore » « less
Full Text Available

Similar Records

Title: Method and apparatus for reordering in a non-uniform compute device

Abstract

Citation Formats

Progressive sharing during a collaboration session patent, November 2016

Non-stalling circular counterflow pipeline processor with recorder buffer patent, February 2004

System and method for adjusting to drive specific criteria patent, October 2013

Configurable processor system unit patent, October 2002

Secondary reorder buffer microprocessor patent, September 2003

Method of executing programs in a network patent, August 1999

Cache coherency protocol for a data processing system including a multi-level memory hierarchy patent, February 2001

Progressive sharing during a collaboration session
patent, November 2016

Non-stalling circular counterflow pipeline processor with recorder buffer
patent, February 2004

System and method for adjusting to drive specific criteria
patent, October 2013

Configurable processor system unit
patent, October 2002

Secondary reorder buffer microprocessor
patent, September 2003

Method of executing programs in a network
patent, August 1999

Cache coherency protocol for a data processing system including a multi-level memory hierarchy
patent, February 2001