公开(公告)号：US20230018857A1

公开(公告)日：2023-01-19

申请号：US17947642

申请日：2022-09-19

申请人： Martin Power ,  Conor Byrne ,  Niall Hanrahan ,  Deepak Abraham Mathaikutty ,  Arnab Raha ,  Raymond Jit-Hung Sung ,  David Thomas Bernard ,  Kevin Brady ,  Martin-Thomas Grymel

发明人： Martin Power ,  Conor Byrne ,  Niall Hanrahan ,  Deepak Abraham Mathaikutty ,  Arnab Raha ,  Raymond Jit-Hung Sung ,  David Thomas Bernard ,  Kevin Brady ,  Martin-Thomas Grymel

IPC分类号： G06N3/04 ,  G06N3/08

摘要： Sparsity processing within a compute block can be done on unpacked data. The compute block includes a sparsity decoder that generates a combined sparsity vector from an activation sparsity vector and a weight sparsity vector. The activation sparsity vector indicates positions of non-zero valued activations in an activation context. The weight sparsity vector indicates positions of non-zero valued weights in a weight context. The combined sparsity vector comprises one or more zero valued bits and one or more non-zero valued bits. The sparsity decoder may determine the position of a non-zero valued bit in the combined sparsity vector and determine an address for the non-zero valued activation and the non-zero valued weight based on the position of the non-zero valued bit. The non-zero valued activation and the non-zero valued weight may be provided to a PE for performing MAC operations.

公开(公告)号：US20230008622A1

公开(公告)日：2023-01-12

申请号：US17934265

申请日：2022-09-22

申请人： Richard Boyd ,  David Thomas Bernard ,  Deepak Abraham Mathaikutty ,  Martin Power ,  Niall Hanrahan

发明人： Richard Boyd ,  David Thomas Bernard ,  Deepak Abraham Mathaikutty ,  Martin Power ,  Niall Hanrahan

IPC分类号： G06F9/50 ,  G06F7/544 ,  G06F7/50

摘要： An DNN accelerator may perform 1×N kernel decomposition to decompose a convolutional kernel into kernel vectors, each of which includes multiple weights. Through the kernel decomposition, a weight operand may be generated from a filter. The DNN accelerator converts an input tensor into input operands. An input operand includes activations and has the same size as the weight operand. The DNN accelerator may read a first activation in the input operand from memory to an internal memory of a first PE and read a second activation in the input operand from the memory to an internal memory of a second PE. The first PE may receive the second activation from the second PE through activation broadcasting between the two PEs and perform MAC operations on the input operand and weight operand. The second PE may perform MAC operations on another input operand in the input tensor and the weight operand.

公开(公告)号：US09955934B2

公开(公告)日：2018-05-01

申请号：US13879647

申请日：2011-10-17

申请人： Mani Vembar ,  Thomas Bernard Ivanc ,  Sunny Virmani

发明人： Mani Vembar ,  Thomas Bernard Ivanc ,  Sunny Virmani

IPC分类号： A61B6/00 ,  A61B6/03

CPC分类号： A61B6/481 ,  A61B6/03 ,  A61B6/032 ,  A61B6/467 ,  A61B6/486 ,  A61B6/507 ,  A61B6/541 ,  A61B6/542

摘要： A method includes dynamically varying a data acquisition sample rate between at least two data acquisition sample rates during a contrast enhanced perfusion scan based on a level of contrast in image data generated during the scan. A system includes a computed tomography scanner and a console that controls the scanner based on a scan protocol, wherein the console dynamically varies a data acquisition sample rate of scanner during a contrast enhanced perfusion scan based on a level of contrast in the image data generated during the scan. A method for optimizing dose of a scan includes reducing a data acquisition sampling rate during at least a sub-portion of the scan in which a state of interest is not being scanned.

公开(公告)号：US08989032B2

公开(公告)日：2015-03-24

申请号：US13494158

申请日：2012-06-12

申请人： Shaun Noel Missett ,  Berkay Baykal ,  Christopher Thomas Bernard

发明人： Shaun Noel Missett ,  Berkay Baykal ,  Christopher Thomas Bernard

IPC分类号： H04L12/761 ,  H04L1/00 ,  H04L12/26

CPC分类号： H04L43/0835 ,  H04L43/16

摘要： Systems and methods for measuring frame loss in multipoint networks are provided. In one embodiment, a method for calculating frame loss in a multipoint network is provided. The method comprises: synchronizing local PM frame count bin boundaries across a multipoint network; collecting a first sample of frame count data at a network manager from a first local PM frame count bin for each VLAN Endpoint on the multipoint network; and calculating a frame loss for the multipoint network by accounting for frame ingress and frame egress from the multipoint network based on the first sample of frame count data; wherein the first sample of frame count data is associated with a first period of time defined by the local PM frame count bin boundaries.

摘要翻译： 提供了多点网络中测量帧丢失的系统和方法。 在一个实施例中，提供了一种用于计算多点网络中的帧丢失的方法。 该方法包括：在多点网络上同步本地PM帧计数bin边界; 在多点网络上的每个VLAN端点从第一本地PM帧计数bin在网络管理器处收集帧计数数据的第一采样; 以及基于所述第一帧采样数据计算来自所述多点网络的帧入口和帧出口来计算所述多点网络的帧丢失; 其中所述帧计数数据的所述第一样本与由所述本地PM帧计数器边界定义的第一时间段相关联。

公开(公告)号：US20130211245A1

公开(公告)日：2013-08-15

申请号：US13879647

申请日：2011-10-17

申请人： Mani Vembar ,  Thomas Bernard Ivanc ,  Sunny Virmani

发明人： Mani Vembar ,  Thomas Bernard Ivanc ,  Sunny Virmani

IPC分类号： A61B6/00 ,  A61B6/03

CPC分类号： A61B6/481 ,  A61B6/03 ,  A61B6/032 ,  A61B6/467 ,  A61B6/486 ,  A61B6/507 ,  A61B6/541 ,  A61B6/542

摘要： A method includes dynamically varying a data acquisition sample rate between at least two data acquisition sample rates during a contrast enhanced perfusion scan based on a level of contrast in image data generated during the scan. A system includes a computed tomography scanner and a console that controls the scanner based on a scan protocol, wherein the console dynamically varies a data acquisition sample rate of scanner during a contrast enhanced perfusion scan based on a level of contrast in the image data generated during the scan. A method for optimizing dose of a scan includes reducing a data acquisition sampling rate during at least a sub-portion of the scan in which a state of interest is not being scanned.

摘要翻译： 一种方法包括基于在扫描期间生成的图像数据中的对比度，在对比度增强灌注扫描期间在至少两个数据采集采样率之间动态地改变数据采集采样率。 系统包括计算机断层摄影扫描仪和基于扫描协议控制扫描仪的控制台，其中控制台基于在对比度增强灌注扫描期间产生的图像数据中的对比度的水平来动态地改变扫描仪的数据采集采样率 扫描。 用于优化扫描剂量的方法包括在扫描的至少一部分的扫描期间降低数据采集采样率，其中感兴趣的状态未被扫描。

公开(公告)号：US20080162968A1

公开(公告)日：2008-07-03

申请号：US11648235

申请日：2006-12-29

申请人： Thomas Bernard Breen ,  James Daniel Phelan

发明人： Thomas Bernard Breen ,  James Daniel Phelan

IPC分类号： G06F1/32

CPC分类号： G06F1/3203 ,  G01S5/0294

摘要： A method and system are disclosed for adjusting a wake interval in a telematics device having a charge sensor. The telematics device cyclically provides full power from a power supply during a wake duration, and limited power from the power supply during the wake interval. A charge level for a battery of the power supply is determined using the charge sensor. The wake interval is adjusted based on the charge level.

摘要翻译： 公开了一种用于调节具有电荷传感器的远程信息处理设备中的唤醒间隔的方法和系统。 远程信息处理设备在唤醒期间循环地提供来自电源的全部功率，以及在唤醒间隔期间来自电源的有限功率。 使用充电传感器确定电源的电池的充电水平。 唤醒间隔根据充电水平进行调整。

公开(公告)号：US20080157944A1

公开(公告)日：2008-07-03

申请号：US11648236

申请日：2006-12-29

申请人： Thomas Bernard Breen

发明人： Thomas Bernard Breen

IPC分类号： G08B21/00 ,  G08B1/08

CPC分类号： G08G1/20

摘要： A method and apparatus for binding a first wireless communication unit installed on a first asset and a second wireless communication unit installed on a second asset, wherein the first asset is connected to the second asset by electrical power lines. The method and system can be used for binding a wireless communication unit of a tractor and a wireless communication unit on a trailer. The method monitors the current in the auxiliary power connection between the assets. By transmitting and detecting power pulses through the auxiliary power line, the wireless communication units can ensure that the two assets are attached and therefore it would be proper to establish a wireless connection between the two wireless communication units. The number of power pulses can be used to identify differing devices. Such method can also be used to detect an open fuse or circuit breaker. In the case of an open fuse, voltages can be used in place of power pulses to complete the binding process.

摘要翻译： 一种用于绑定安装在第一资产上的第一无线通信单元和安装在第二资产上的第二无线通信单元的方法和装置，其中所述第一资产通过电力线连接到所述第二资产。 该方法和系统可用于将拖拉机的无线通信单元和拖车上的无线通信单元绑定。 该方法监视资产之间的辅助电力连接中的电流。 通过通过辅助电力线发送和检测功率脉冲，无线通信单元可以确保两个资产被附接，因此在两个无线通信单元之间建立无线连接是合适的。 功率脉冲数可用于识别不同的设备。 这种方法也可用于检测开路保险丝或断路器。 在开路保险丝的情况下，可以使用电压代替电源脉冲来完成绑定过程。

公开(公告)号：USD541115S1

公开(公告)日：2007-04-24

申请号：US29252330

申请日：2006-01-23

申请人： Timothy Corcoran Repp ,  Thomas Bernard Murphy

设计人： Timothy Corcoran Repp ,  Thomas Bernard Murphy

公开(公告)号：US2524858A

公开(公告)日：1950-10-10

申请号：US5812148

申请日：1948-11-03

申请人： THOMAS BERNARD S

发明人： THOMAS BERNARD S

IPC分类号： B29C45/26 ,  B29C45/27

CPC分类号： B29C45/2701 ,  B29C45/26 ,  Y10S425/051

公开(公告)号：US20230017662A1

公开(公告)日：2023-01-19

申请号：US17946231

申请日：2022-09-16

申请人： Sudheendra Kadri ,  Darren Crews ,  Deepak Abraham Mathaikutty ,  Andrea Deidda ,  Arnab Raha ,  Kevin Brady ,  David Thomas Bernard

发明人： Sudheendra Kadri ,  Darren Crews ,  Deepak Abraham Mathaikutty ,  Andrea Deidda ,  Arnab Raha ,  Kevin Brady ,  David Thomas Bernard

IPC分类号： G06N3/063 ,  G06F13/28

摘要： An DNN accelerator includes a DMA engine that can rearrange weight data layout. The DMA engine may read a weight tensor from a memory (e.g., DRAM). The weight tensor includes weights arranged in a 3D matrix. The DMA engine may partition the weight tensor into a plurality of virtual banks based on a structure of a PE array, e.g., based on the number of activated PE columns in the PE array. Then the DMA engine may partition a virtual bank into a plurality of virtual sub-banks. The DMA engine may also identify data blocks from different ones of the plurality of virtual sub-banks. A data block may include a plurality of input channels and may have a predetermined spatial size and storage size. The DMA engine form a linear data structure by interleaving the data blocks. The DMA engine can write the linear data structure into another memory (e.g., SRAM).