-
1.发明公开公开(公告)号：US20230310995A1
公开(公告)日：2023-10-05
申请号：US17709904
申请日：2022-03-31
Applicant: Advanced Micro Devices, Inc. , ATI Technologies ULC
Inventor： Mehdi Saeedi , Ian Charles Colbert , Thomas Daniel Perry , Gabor Sines
IPC: A63F13/56
CPC classification number: A63F13/56
Abstract: Systems, apparatuses, and methods for detecting personal-space violations in artificial intelligence (AI) based non-player characters (NPCs) are disclosed. An AI engine creates a NPC that accompanies and/or interacts with a player controlled by a user playing a video game. During gameplay, measures of context-dependent personal space around the player and/or one or more NPCs are generated. A control circuit monitors the movements of the NPC during gameplay and determines whether the NPC is adhering to or violating the measures of context-dependent personal space. The control circuit can monitor the movements of multiple NPCs simultaneously during gameplay, keeping a separate score for each NPC. After some amount of time has elapsed, the scores of the NPCs are recorded, and then the scores are provided to a machine learning engine to retrain the AI engines controlling the NPCs.
-
公开(公告)号：US20230154100A1
公开(公告)日：2023-05-18
申请号：US17529916
申请日：2021-11-18
Applicant: ADVANCED MICRO DEVICES, INC. , ATI TECHNOLOGIES ULC
Inventor： Thomas Daniel Perry , Steven Tovey , Mehdi Saeedi , Andrej Zdravkovic , Zhuo Chen
CPC classification number: G06T15/005 , G06F9/4881 , G06N20/00
Abstract: Systems, methods, and techniques utilize reinforcement learning to efficiently schedule a sequence of jobs for execution by one or more processing threads. A first sequence of execution jobs associated with rendering a target frame of a sequence of frames is received. One or more reward metrics related to rendering the target frame are selected. A modified sequence of execution jobs for rendering the target frame is generated, such as by reordering the first sequence of execution jobs. The modified sequence is evaluated with respect to the selected reward metric(s); and rendering the target frame is initiated based at least in part on the evaluating of the modified sequence with respect to the one or more selected reward metric(s).
-
公开(公告)号：US11310496B2
公开(公告)日：2022-04-19
申请号：US16366959
申请日：2019-03-27
Applicant: ATI Technologies ULC
Inventor： Mehdi Saeedi , Boris Ivanovic
IPC: H04N19/00 , H04N19/117 , H04N19/196 , H04N19/154 , H04N19/176
Abstract: A technique for determining a quality value for a subject block of encoded video is provided. Contributing blocks, of the same frame and/or different frames of the subject block, are determined by identifying blocks likely to be a part of the same moving object or background as the subject block. A spatial and/or temporal filter is then applied to the quality values of the contributing blocks and an initial quality value of the subject block. With a spatial filter, quality values for contributing blocks from the same frame are combined and used to modify the quality value of the subject block. With a spatial filter, a temporal characteristic quality value for contributing blocks of one or more other frames (such as the immediately previous frame) is determined and then combined with a quality value representative of the subject block.
-
公开(公告)号：US11234004B2
公开(公告)日：2022-01-25
申请号：US16207893
申请日：2018-12-03
Applicant: ATI Technologies ULC
Inventor： Mehdi Saeedi , Boris Ivanovic
IPC: H04N19/176 , H04N19/159 , H04N19/196 , H04N19/124 , H04N19/149
Abstract: Systems, apparatuses, and methods for block type prediction leveraging block-based pixel activities are disclosed. A pre-encoder generates predictions of block types for the blocks of a video frame based on associated pixel activities. For each block, the pre-encoder calculates the difference between the pixel activities of the block of a current frame and the pixel activities of a corresponding block of a previous video frame. If the difference is less than a first threshold, the pre-encoder predicts that the block will be a skip block. If the difference is in between the first threshold and a second threshold, the pre-encoder predicts that the block will be a P-block. Otherwise, if the difference is greater than the second threshold, then the pre-encoder predicts that the block will be an I-block. The pre-encoder uses the predictions to select quantization parameter (QP) ranges for encoding the blocks of the video frame.
-
公开(公告)号：US11102488B2
公开(公告)日：2021-08-24
申请号：US16427482
申请日：2019-05-31
Applicant: ATI TECHNOLOGIES ULC
Inventor： Boris Ivanovic , Mehdi Saeedi , Edward G. Callway
IPC: H04N11/02 , H04N19/14 , H04N19/176 , H04N19/196 , H04N19/33
Abstract: A processing system analyzes pixel activity levels of blocks of a picture at a plurality of spatial scales and/or dynamic ranges to generate a multi-scale metric that indicates how bit allocation or assignment of a given quantization parameter (QP) will affect the perceptual quality of the block. Blocks that have similar multi-scale metrics are likely to be visually similar and to benefit from similar bit allocations or QPs. Based on the multi-scale metric, an encoder encodes each block of the picture with a QP and/or a number of bits.
-
Patent Agency Ranking
公开(公告)号：US20240095517A1
公开(公告)日：2024-03-21
申请号：US17949082
申请日：2022-09-20
Applicant: Advanced Micro Devices, Inc. , ATI Technologies ULC
Inventor： Mehdi Saeedi , Ian Charles Colbert , Ihab M. A. Amer
IPC: G06N3/08
CPC classification number: G06N3/08
Abstract: Methods and devices are provided for processing data using a neural network. Activations from a previous layer of the neural network are received by a layer of the neural network. Weighted values, to be applied to values of elements of the activations, are determined based on a spatial correlation of the elements and a task error output by the layer. The weighted values are applied to the values of the elements and a combined error is determined based on the task error and the spatial correlation.
-
公开(公告)号：US20230206537A1
公开(公告)日：2023-06-29
申请号：US17562884
申请日：2021-12-27
Applicant: Advanced Micro Devices, Inc. , ATI Technologies ULC
Inventor： Thomas Daniel Perry , Steven John Tovey , Mehdi Saeedi
CPC classification number: G06T15/005 , A63F13/52
Abstract: Systems, apparatuses, and methods for updating and optimizing task scheduling policies are disclosed. A new policy is obtained and updated at runtime by a client based on a server analyzing a wide spectrum of telemetry data on a relatively long time scale. Instead of only looking at the telemetry data from the client's execution of tasks for the previous frame, the server analyzes the execution times of tasks for multiple previous frames so as to determine a more optimal policy for subsequent frames. This mechanism enables making a more informed task scheduling policy decision as well as customizing the policy per application, game, and user without requiring a driver update. Also, this mechanism facilitates improved load balancing across the various processing engines, each of which has their own task queues. The improved load balancing is achieved by analyzing the telemetry data including resource utilization statistics for the different processing engines.
-
公开(公告)号：US11568248B2
公开(公告)日：2023-01-31
申请号：US16836785
申请日：2020-03-31
Applicant: ATI Technologies ULC
Inventor： Arash Hariri , Mehdi Saeedi , Boris Ivanovic , Gabor Sines
Abstract: A processing device for executing a machine learning neural network operation includes memory and a processor. The processor is configured to receive input data at a layer of the machine learning neural network operation, receive a plurality of sorted filters to be applied to the input data, apply the plurality of sorted filters to the input data to produce a plurality of different feature maps, compress the plurality of different feature maps according to a similarity of the feature maps relative to each other and store the plurality of different feature maps in the memory.
-
公开(公告)号：US20210243450A1
公开(公告)日：2021-08-05
申请号：US17236910
申请日：2021-04-21
Applicant: ATI Technologies ULC
Inventor： Mehdi Saeedi , Boris Ivanovic
IPC: H04N19/14 , H04N19/513 , H04N19/176
Abstract: Systems, apparatuses, and methods for implementing spatial block-level pixel activity extraction optimization leveraging motion vectors are disclosed. Control logic coupled to an encoder generates block-level pixel activity metrics for a new frame based on the previously calculated block-level pixel activity data from a reference frame. A cost is calculated for each block of a new frame with respect to a corresponding block of the reference frame. If the cost is less than a first threshold, then the control logic generates an estimate of a pixel activity metric for the block which is equal to a previously calculated pixel activity metric for a corresponding block of the reference frame. If the cost is greater than the first threshold but less than a second threshold, an estimate of the pixel activity metric is generated by extrapolating from the previously calculated pixel activity metric.
-
公开(公告)号：US20210185313A1
公开(公告)日：2021-06-17
申请号：US16715187
申请日：2019-12-16
Applicant: ATI Technologies ULC
Inventor： Boris Ivanovic , Mehdi Saeedi
IPC: H04N19/115 , G06N5/04 , H04N19/176 , H04N19/159
Abstract: Systems, apparatuses, and methods for using residual metrics for encoder rate control are disclosed. An encoder includes a mode decision unit for determining a mode to be used for generating a predictive block for each block of a video frame. For each block, control logic calculates a residual of the block by comparing an original version of the block to the predictive block. The control logic generates a residual metric based on the residual and based on the mode. The encoder's rate controller selects a quantization strength setting for the block based on the residual metric. Then, the encoder generates an encoded block that represents the input block by encoding the block with the selected quantization strength setting. Next, the encoder conveys the encoded block to a decoder to be displayed. The encoder repeats this process for each block of the frame.
-
-
-
-
-
-
-
-
-
Search Results
40
records
(took 0.023 seconds)
