公开(公告)号：US10908962B1

公开(公告)日：2021-02-02

申请号：US15944062

申请日：2018-04-03

Applicant: Apple Inc.

Inventor： Francesco Rossi ,  Kutty Banerjee

IPC: G06F9/50 ,  G06F9/54 ,  G06F9/451 ,  G06F17/15 ,  G06T1/20

Abstract: The embodiments disclosed herein relate to the field of graphics processing and, without limitation, to techniques to enable efficient sharing of a graphics processing unit (GPU) between user interface (UI) graphics operations and intense compute operations. In certain embodiments, intense compute operations, such as long accumulations, are divided into multiple pieces. A scheduler is added to force context switching if an intense compute operation is blocking timely execution of a UI graphics operation. The division of the intense compute operation is tuned so that the GPU compute queue can drain during approximately the same time required to perform a context switch on the GPU.

公开(公告)号：US10789694B1

公开(公告)日：2020-09-29

申请号：US16032938

申请日：2018-07-11

Applicant: Apple Inc.

Inventor： Bartlomiej W. Rymkowski ,  Francesco Rossi

IPC: G06K9/62 ,  G06T5/50 ,  G06N3/04 ,  G06T7/246

Abstract: Artistic styles extracted from one or more source images may be applied to one or more target images, e.g., in the form of stylized images and/or stylized video sequences. The extracted artistic style may be stored as a plurality of layers in a neural network, which neural network may be further optimized, e.g., via the fusion of various elements of the network's architectures. An optimized network architecture may be determined for each processing environment in which the network will be applied. The artistic style may be applied to the obtained images and/or video sequence of images using various optimization methods, such as the use of scalars to control the resolution of the unstylized and stylized images, temporal consistency constraints, as well as the use of dynamically adjustable or selectable versions of Deep Neural Networks (DNN) that are responsive to system performance parameters, such as available processing resources and thermal capacity.

公开(公告)号：US10585703B2

公开(公告)日：2020-03-10

申请号：US15721716

申请日：2017-09-29

Applicant: Apple Inc.

Inventor： Francesco Rossi ,  Gaurav Kapoor ,  Michael R. Siracusa ,  William B. March

IPC: G06F8/41 ,  G06F9/50 ,  G06N3/063 ,  G06N3/02

Abstract: The subject technology provides for dynamic task allocation for neural network models. The subject technology determines an operation performed at a node of a neural network model. The subject technology assigns an annotation to indicate whether the operation is better performed on a CPU or a GPU based at least in part on hardware capabilities of a target platform. The subject technology determines whether the neural network model includes a second layer. The subject technology, in response to determining that the neural network model includes a second layer, for each node of the second layer of the neural network model, determines a second operation performed at the node. Further the subject technology assigns a second annotation to indicate whether the second operation is better performed on the CPU or the GPU based at least in part on the hardware capabilities of the target platform.