Abstract: 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.

Abstract: One embodiment provides a graphics processor comprising a memory controller and a graphics processing resource coupled with the memory controller. The graphics processing resource includes circuitry configured to execute an instruction to perform a matrix operation on first input including weight data and second input including input activation data, generate intermediate data based on a result of the matrix operation, quantize the intermediate data to a floating-point format determined based on a statistical distribution of first output data, and output, as second output data, quantized intermediate data in a determined floating-point format.

Abstract: The present disclosure discloses a display panel. The display panel includes a lighting test unit. The lighting test unit includes: signal input terminal sets, each including signal input terminals; shorting bar sets, each including shorting bars; and data signal line sets, each including data signal lines, where the signal input terminals are electrically connected to the shorting bars, the data signal lines are electrically connected to the shorting bars, and each shorting bar is connected end to end.

Abstract: One embodiment provides for a compute apparatus comprising a decode unit to decode a single instruction into a decoded instruction that specifies multiple operands including a multi-bit input value and a ternary weight associated with a neural network and an arithmetic logic unit including a multiplier, an adder, and an accumulator register. To execute the decoded instruction, the multiplier is to perform a multiplication operation on the multi-bit input based on the ternary weight to generate an intermediate product and the adder is to add the intermediate product to a value stored in the accumulator register and update the value stored in the accumulator register.

Abstract: A W-band E-plane waveguide bandpass filter includes a rectangular waveguide configured to feed a W-band signal, and a dielectric substrate. The dielectric substrate is inserted into the center of the waveguide. The dielectric substrate is provided with a spoof surface plasmon polariton (SSPP) array configured to transmit a TM-mode surface wave to achieve the bandpass filtering response.

Abstract: Methods and apparatus for processing of GNSS signals are presented. These include GNSS processing with obtaining GNSS data derived from signals received at a rover antenna, obtaining correction data, maintaining a time sequence of at least one rover position and at least one rover position difference with associated time tags, using the time sequence to determine at least one derived rover position by, starting from a position determined using corrections synchronous with rover data as an anchor position at a time tag, deriving a new anchor position for the time tag of the anchor position and at least one other estimated rover position at the time tag of the anchor position, and/or reporting the new anchor position and/or a new derived rover position.

Abstract: A rapid and automatic virus imaging and analysis system includes (i) electron optical sub-systems (EOSs), each of which has a large field of view (FOV) and is capable of instant magnification switching for rapidly scanning a virus sample; (ii) sample management sub-systems (SMSs), each of which automatically loads virus samples into one of the EOSs for virus sample scanning and then unloads the virus samples from the EOS after the virus sample scanning is completed; (iii) virus detection and classification sub-systems (VDCSs), each of which automatically detects and classifies a virus based on images from the EOS virus sample scanning; and (iv) a cloud-based collaboration sub-system for analyzing the virus sample scanning images, storing images from the EOS virus sample scanning, and storing and analyzing machine data associated with the EOSs, the SMSs, and the VDCSs.

Abstract: A W-band E-plane waveguide bandpass filter includes a rectangular waveguide configured to feed a W-band signal, and a dielectric substrate. The dielectric substrate is inserted into the center of the waveguide. The dielectric substrate is provided with a spoof surface plasmon polariton (SSPP) array configured to transmit a TM-mode surface wave to achieve the bandpass filtering response.

Abstract: The present invention provides an apparatus of charged-particle beam e.g. an electron microscope comprising a plasma generator for selectively cleaning BSE detector. In various embodiments, the plasma generator is located between a sample stage and a sample table having one or more openings or holes. The plasma generator generates plasma and distributes or dissipates the plasma through the openings of the sample table toward and onto surface of the BSE detector. Cleaning contaminants on the surface of the BSE detector frequently and selectively with in-situ generated plasma can prevent the detectors from performance deterioration such as losing resolution and contrast in imaging at high levels of magnification.

Abstract: The present invention provides an apparatus of electron beam comprising an electron gun with a pinnacle limiting plate having at least one current-limiting aperture. The pinnacle limiting plate is located between a bottom (or lowest) anode and a top (or highest) condenser within the electron gun. A current (ampere) of the electron beam that has passed through the current-limiting aperture remains the same (unchanged) after the electron beam travels through the top condenser and an electron optical column and arrives at a sample space. Electron-electron interaction of the electron beam is thus reduced.

Abstract: Aqueous hydrocortisone sodium phosphate and monothioglycerol formulations are disclosed.

Abstract: This disclosure provides a resource tapping method, a resource tapping apparatus and an electronic device, and relates to the field of computer technology, in particular to the technical field of artificial intelligence, such as deep learning and machine learning. A specific implementation is as follows: obtaining operation data in M resource dimensions of a target cabinet, the M resource dimensions including a power resource, where M is a positive integer; determining a target power over-allocation value of the target cabinet based on the operation data, the target power over-allocation value being used for indicating an allowable power increment on the basis of a power rating of the target cabinet; and determining, based on the target power over-allocation value, a first quantity of additional servers deployable in the target cabinet.

Abstract: A method operating a Graphics Processing Unit (GPU) memory can be provided by accessing specified training parameters used to train a Deep Neural Network (DNN) using a GPU with a local GPU memory, the specified training parameters including at least a specified batch size of samples configured to train the DNN. A sub-batch size of the samples can be defined that is less than or equal to the specified batch size of samples in response to determining that an available size of the local GPU memory is insufficient to store all data associated with training the DNN using one batch of the samples. Instructions configured to train the DNN using the sub-batch size can be defined so that an accuracy of the DNN trained using the sub-batch size is about equal to an accuracy of the DNN trained using the specified batch size of the samples.

Abstract: 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.

Abstract: 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.

Abstract: A rapid and automatic virus imaging and analysis system includes (i) electron optical sub-systems (EOSs), each of which has a large field of view (FOV) and is capable of instant magnification switching for rapidly scanning a virus sample; (ii) sample management sub-systems (SMSs), each of which automatically loads virus samples into one of the EOSs for virus sample scanning and then unloads the virus samples from the EOS after the virus sample scanning is completed; (iii) virus detection and classification sub-systems (VDCSs), each of which automatically detects and classifies a virus based on images from the EOS virus sample scanning; and (iv) a cloud-based collaboration sub-system for analyzing the virus sample scanning images, storing images from the EOS virus sample scanning, and storing and analyzing machine data associated with the EOSs, the SMSs, and the VDCSs.

Abstract: One embodiment provides for a graphics processing unit to accelerate machine-learning operations, the graphics processing unit comprising a multiprocessor having a single instruction, multiple thread (SIMT) architecture, the multiprocessor to execute at least one single instruction; and a first compute unit included within the multiprocessor, the at least one single instruction to cause the first compute unit to perform a two-dimensional matrix multiply and accumulate operation, wherein to perform the two-dimensional matrix multiply and accumulate operation includes to compute an intermediate product of 16-bit operands and to compute a 32-bit sum based on the intermediate product.

Abstract: An apparatus to facilitate neural network (NN) training is disclosed. The apparatus includes training logic to receive one or more network constraints and train the NN by automatically determining a best network layout and parameters based on the network constraints.

Abstract: Methods and apparatus relating to autonomous vehicle neural network optimization techniques are described. In an embodiment, the difference between a first training dataset to be used for a neural network and a second training dataset to be used for the neural network is detected. The second training dataset is authenticated in response to the detection of the difference. The neural network is used to assist in an autonomous vehicle/driving. Other embodiments are also disclosed and claimed.