Intel Corporation

Mike B Macpherson

Abhishek R Appu

Joydeep Ray

Altug Koker

Linda L Hurd

Dukhwan Kim

John Charles Weast

Xiaoming Chen

Ping Tak Tang

Michael S Strickland

Anbang Yao

Sara S Baghsorkhi

Elmoustapha Ould-Ahmed-Vall

Liwei Ma

Feng Chen

Ben J Ashbaugh

Kevin Nealis

Barath Lakshmanan

Prasoonkumar Surti

Tatiana Shpeisman

Balaji Vembu

Vasanth Ranganathan

Justin E Gottschlich

Sanjeev S Jahagirdar

Narayan Srinivasa

Nadathur Rajagopalan Satish

Chandrasekaran Sakthivel

Farshad Akhbari

Kamal Sinha

Rajkishore Barik

Brian T Lewis

Murali Sundaresan

Narayan Biswal

Stanley J Baran

Gokcen Cilingir

Nilesh V Shah

Barnan Das

Archie Sharma

Mayuresh M Varerkar

Jeremy Bottleson

Sherine Abdelhak

Dhawal Srivastava

Jingyi Jin

Neelay Pandit

Praneetha Kotha

Eriko Nurvitadhi

Nicolas C Galoppo Von Borries

Tsung-Han Lin

Stephen Junkins

Jeffrey R Jackson

Leonard Truong

Subramaniam M Maiyuran

Varghese George

Guei-Yuan Lueh

Jorge E Parra

Chandra S Gurram

Supratim Pal

Ashutosh Garg

Shubra Marwaha

Timothy R Bauer

Shubh Shah

Konrad Trifunovic

Weiyu Chen

Junjie Gu

Hong Bin Liao

Anhang Yao

A mechanism is described for detecting, at training time, information related to one or more tasks to be performed by the one or more processors according to a training dataset for a neural network, analyzing the information to determine one or more portions of hardware of a processor of the one or more processors that is configurable to support the one or more tasks, configuring the hardware to pre-select the one or more portions to perform the one or more tasks, while other portions of the hardware remain available for other tasks, and monitoring utilization of the hardware via a hardware unit of the graphics processor and, via a scheduler of the graphics processor, adjusting allocation of the one or more tasks to the one or more portions of the hardware based on the utilization.

Coordination and increased utilization of graphics processors during inference

One embodiment provides a general-purpose graphics processing unit comprising a dynamic precision floating-point unit including a control unit having precision tracking hardware logic to track an available number of bits of precision for computed data relative to a target precision, wherein the dynamic precision floating-point unit includes computational logic to output data at multiple precisions.

Compute optimizations for low precision machine learning operations

A mechanism is described for facilitating efficient training of neural networks at computing devices. A method of embodiments, as described herein, includes detecting one or more inputs for training of a neural network, and introducing randomness in floating point (FP) numbers to prevent overtraining of the neural network, where introducing randomness includes replacing less-significant low-order bits of operand and result values with new low-order bits during the training of the neural network.

Training with adaptive runtime and precision profiling

In an example, an apparatus comprises a compute engine comprising a high precision component and a low precision component; and logic, at least partially including hardware logic, to receive instructions in the compute engine; select at least one of the high precision component or the low precision component to execute the instructions; and apply a gate to at least one of the high precision component or the low precision component to execute the instructions. Other embodiments are also disclosed and claimed.

Dynamic precision for neural network compute operations

One embodiment provides a multi-chip module accelerator usable to execute tensor data processing operations a multi-chip module. The multi-chip module may include a memory stack including multiple memory dies and parallel processor circuitry communicatively coupled to the memory stack. The parallel processor circuitry may include multiprocessor cores to execute matrix multiplication and accumulate operations. The matrix multiplication and accumulate operations may include floating-point operations that are configurable to include two-dimensional matrix multiply and accumulate operations involving inputs that have differing floating-point precisions. The floating-point operations may include a first operation at a first precision and a second operation at a second precision. The first operation may include a multiply having at least one 16-bit floating-point input and the second operation may include an accumulate having a 32-bit floating-point input.

An apparatus to facilitate compute optimization is disclosed. The apparatus includes a mixed precision core including mixed-precision execution circuitry to execute one or more of the mixed-precision instructions to perform a mixed-precision dot-product operation comprising to perform a set of multiply and accumulate operations.

Compute optimization mechanism

A library of machine learning primitives is provided to optimize a machine learning model to improve the efficiency of inference operations. In one embodiment a trained convolutional neural network (CNN) model is processed into a trained CNN model via pruning, convolution window optimization, and quantization.

Convolutional neural network optimization mechanism

A method of embodiments, as described herein, includes detecting thread groups relating to machine learning associated with one or more processing devices. The method may further include facilitating barrier synchronization of the thread groups across multiple dies such that each thread in a thread group is scheduled across a set of compute elements associated with the multiple dies, where each die represents a processing device of the one or more processing devices, the processing device including a graphics processor.

Barriers and synchronization for machine learning at autonomous machines

One embodiment provides an apparatus comprising a memory stack including multiple memory dies and a parallel processor including a plurality of multiprocessors. Each multiprocessor has a single instruction, multiple thread (SIMT) architecture, the parallel processor coupled to the memory stack via one or more memory interfaces. At least one multiprocessor comprises a multiply-accumulate circuit to perform multiply-accumulate operations on matrix data in a stage of a neural network implementation to produce a result matrix comprising a plurality of matrix data elements at a first precision, precision tracking logic to evaluate metrics associated with the matrix data elements and indicate if an optimization is to be performed for representing data at a second stage of the neural network implementation, and a numerical transform unit to dynamically perform a numerical transform operation on the matrix data elements based on the indication to produce transformed matrix data elements at a second precision.

An apparatus to facilitate optimization of a convolutional neural network (CNN) is disclosed. The apparatus includes optimization logic to receive a CNN model having a list of instructions and including pruning logic to optimize the list of instructions by eliminating branches in the list of instructions that comprise a weight value of 0.

A graphics processor can include a processing cluster array including a plurality of processing clusters coupled with the plurality of memory controllers, each processing cluster of the plurality of processing clusters including a plurality of streaming multiprocessors, the processing cluster array configured for partitioning into a plurality of partitions. The plurality of partitions include a first partition including a first plurality of streaming multiprocessors configured to perform operations for a first neural network, The operations for the first neural network are isolated to the first partition. The plurality of partitions also include a second partition including a second plurality of streaming multiprocessors configured to perform operations for a second neural network. The operations for the second neural network are isolated to the second partition and protected from operations performed for the first neural network.

Graphics neural network processor, method, and system

A mechanism is described for facilitating inference coordination and processing utilization for machine learning. A method of embodiments, as described herein, includes limiting execution of workloads for the respective contexts of a plurality of contexts to a specified subset of a plurality of processing resources of a processing system according to physical resource slices of the processing system that are associated with the respective contexts of the plurality of contexts.

Embodiments provide systems and methods which facilitate optimization of a convolutional neural network (CNN). One embodiment provides for a non-transitory machine-readable medium storing instructions that cause one or more processors to perform operations comprising processing a trained convolutional neural network (CNN) to generate a processed CNN, the trained CNN having weights in a floating-point format. Processing the trained CNN includes quantizing the weights in the floating-point format to generate weights in an integer format. Quantizing the weights includes generating a quantization table to enable non-uniform quantization of the weights and quantizing the weights from the floating-point format to the integer format using the quantization table. The operations additionally comprise performing an inference operation utilizing the processed CNN with the integer format weights.

A mechanism is described for facilitating sharing of data and compression expansion of models at autonomous machines. A method of embodiments, as described herein, includes detecting a first processor processing information relating to a neural network at a first computing device, where the first processor comprises a first graphics processor and the first computing device comprises a first autonomous machine. The method further includes facilitating the first processor to store one or more portions of the information in a library at a database, where the one or more portions are accessible to a second processor of a computing device.

Efficient sharing and compression expansion of data across processing systems

Growing community of inventors

Portland, OR, United States of America

Mike B Macpherson