Intel Corporation

Marc Lupon

Fernando Latorre

Pedro Lopez

Grigorios Magklis

Ayose J Falcon

Enric Herrero Abellanas

Frederico C Pratas

Georgios Tournavitis

Raul Martinez

Enric Gibert Codina

Kyriakos A Stavrou

Sridhar Samudrala

Polychronis Xekalakis

Pedro Marcuello

Josep M Codina

David Roger Ditzel

Daniel Ortega

Demos Pavlou

Mirem Hyuseinova

Christos E Kotselidis

Crispin Gomez Requena

Antonio Gonzalez

Carlos Madriles

Alejandro Martinez Vicente

Naveen Neelakantam

David Pardo Keppel

Denis M Khartikov

Carlos Madriles Gimeno

Alejandro Vicente Martinez

Marti Torrents Lapuerta

Antonio Gonzelez

Ayose J Falcón

An apparatus and method are described for distributed and cooperative computation in artificial neural networks. For example, one embodiment of an apparatus comprises: an input/output (I/O) interface; a plurality of processing units communicatively coupled to the I/O interface to receive data for input neurons and synaptic weights associated with each of the input neurons, each of the plurality of processing units to process at least a portion of the data for the input neurons and synaptic weights to generate partial results; and an interconnect communicatively coupling the plurality of processing units, each of the processing units to share the partial results with one or more other processing units over the interconnect, the other processing units using the partial results to generate additional partial results or final results. The processing units may share data including input neurons and weights over the shared input bus.

Method and apparatus for distributed and cooperative computation in artificial neural networks

A processing device includes a processor core and a number of calculation modules that each is configurable to perform any one of operations for a convolutional neuron network system. A first set of the calculation modules are configured to perform convolution operations, a second set of the calculation modules are reconfigured to perform averaging operations, and a third set of the calculation modules are reconfigured to perform dot product operations.

Reconfigurable processing unit

Systems and methods for performing convolution operations. An example processing system comprises: a processing core; and a convolver unit to apply a convolution filter to a plurality of input data elements represented by a two-dimensional array, the convolver unit comprising a plurality of multipliers coupled to two or more sets of latches, wherein each set of latches is to store a plurality of data elements of a respective one-dimensional section of the two-dimensional array.

Processing device for performing convolution operations

A computer-readable storage medium, method and system for optimization-level aware branch prediction is described. A gear level is assigned to a set of application instructions that have been optimized. The gear level is also stored in a register of a branch prediction unit of a processor. Branch prediction is then performed by the processor based upon the gear level.

Instruction and logic for optimization level aware branch prediction

A processor includes a front end, a decoder, an allocator, and a retirement unit. The decoder includes logic to identify an end-of-live-range (EOLR) indicator. The EOLR indicator specifies an architectural register and a location in code for which the architectural register is unused. The allocator includes logic to scan for a mapping of the architectural register to a physical register, based upon the EOLR indicator. The allocator also includes logic to generate a request to disassociate the architectural register from the physical register. The retirement unit includes logic to disassociate the architectural register from the physical register.

Instruction and logic for bulk register reclamation

A combination of hardware and software collect profile data for asynchronous events, at code region granularity. An exemplary embodiment is directed to collecting metrics for prefetching events, which are asynchronous in nature. Instructions that belong to a code region are identified using one of several alternative techniques, causing a profile bit to be set for the instruction, as a marker. Each line of a data block that is prefetched is similarly marked. Events corresponding to the profile data being collected and resulting from instructions within the code region are then identified. Each time that one of the different types of events is identified, a corresponding counter is incremented. Following execution of the instructions within the code region, the profile data accumulated in the counters are collected, and the counters are reset for use with a new code region.

Propagating a prefetching profile bit from a prefetch queue to a data cache to indicate that a line was prefetched in response to an instruction within a code region

A storage device and method are described for performing convolution operations. For example, one embodiment of an apparatus to perform convolution operations comprises a plurality of processing units to execute convolution operations on input data and partial results; a unified scratchpad memory comprising a plurality of memory banks communicatively coupled to the plurality of processing units through a plurality of read/write ports, each of the plurality of memory banks partitioned to store both the input data and partial results; a control unit to allocate the input data and partial results to the memory banks to ensure a minimum quality of service in accordance with the specified number of read/write ports and the specified convolution operation to be performed.

Storage device and method for performing convolution operations

Disclosed is an apparatus and method to manage instruction cache prefetching from an instruction cache. A processor may comprise: a prefetch engine; a branch prediction engine to predict the outcome of a branch; and dynamic optimizer. The dynamic optimizer may be used to control: identifying common instruction cache misses and inserting a prefetch instruction from the prefetch engine to the instruction cache.

Managed instruction cache prefetching

Methods, apparatus, instructions and logic are disclosed providing double rounded combined floating-point multiply and add functionality as scalar or vector SIMD instructions or as fused micro-operations. Embodiments include detecting floating-point (FP) multiplication operations and subsequent FP operations specifying as source operands results of the FP multiplications. The FP multiplications and the subsequent FP operations are encoded as combined FP operations including rounding of the results of FP multiplication followed by the subsequent FP operations. The encoding of said combined FP operations may be stored and executed as part of an executable thread portion using fused-multiply-add hardware that includes overflow detection for the product of FP multipliers, first and second FP adders to add third operand addend mantissas and the products of the FP multipliers with different rounding inputs based on overflow, or no overflow, in the products of the FP multiplier. Final results are selected respectively using overflow detection.

Double rounded combined floating-point multiply and add

An error handling method includes identifying a code region eligible for cumulative multiply add (CMA) optimization and translating code region instructions into interpreter code instructions, which may include translating sequences of multiply add instructions in the code region instructions into fusion code including CMA instructions. Floating point (FP) exceptions generated by the fusion code may be monitored and at least a portion of the code region instructions may be re-translated to eliminate some or all fusion code if CMA intermediate rounding exceptions exceed a threshold.

Combined floating point multiplier adder with intermediate rounding logic

Growing community of inventors

Barcelona, Spain

Marc Lupon