Abstract: A convolutional neural network (CNN)-based signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.

Abstract: A system is provided. In some examples, the system includes a first peripheral circuit and a memory management circuit coupled to the first peripheral circuit. The memory management circuit comprises a first table that associates virtual identification values with address space select values. The system also includes a transaction mapper circuit coupled to the memory management circuit. The transaction mapper circuit comprises a second table that associates virtual identification values with bus-device-function values.

Abstract: An Ethernet switch and a switch microcontroller or CPU are integrated onto a system-on-a-chip (SoC). The Ethernet switch remains independently operating at full speed even though the remainder of the SoC is being reset or is otherwise nonoperational. The Ethernet switch is on a separated power and clock domain from the remainder of the integrated SoC. A warm reset signal is trapped by control microcontroller (MCU) to allow the switch CPU to isolate the Ethernet switch and save state. When the Ethernet switch is isolated and operating independently, the warm reset request is provided to the other entities on the integrated SoC. When warm reset is completed, the state is restored and the various DMA and flow settings redeveloped in the integrated SoC to allow return to normal operating condition.

Abstract: A method for processing RGB-Infrared (RGB-IR) sensor data is provided that includes receiving a raw RGB-IR image, determining whether to process the raw RGB-IR image in day mode or night mode, generating, when day mode is determined, an infrared (IR) subtracted raw Bayer image from the raw RGB-IR image and processing the IR subtracted raw Bayer image in an image signal processor (ISP), and generating, when night mode is determined, an IR image from the raw RGB-IR image.

Abstract: A system-on-chip (SoC) may be configured to enable a Multi-Chip Daisy Chain Topology using peripheral component interface express (PCIe). The SoC may include a processor, a local memory, a root complex operably connected to the processor and the local memory, and a multi-function endpoint controller. The root complex may obtain forwarding information to configure routing of transactions to one or more PCIe endpoint functions or to the local memory. The root complex may initialize, based on the forwarding information, access between a host and the one or more PCIe endpoint functions. The multi-function endpoint controller may obtain a descriptor and endpoint information to configure outbound portals for transactions to at least one remote host. The multi-function endpoint controller may establish a communication path between the host and a function out of a plurality of functions.

Abstract: In an example, a device includes a memory and a processor core coupled to the memory via a memory management unit (MMU). The device also includes a system MMU (SMMU) cross-referencing virtual addresses (VAs) with intermediate physical addresses (IPAs) and IPAs with physical addresses (PAs). The device further includes a physical address table (PAT) cross-referencing IPAs with each other and cross-referencing PAs with each other. The device also includes a peripheral virtualization unit (PVU) cross-referencing IPAs with PAs, and a routing circuit coupled to the memory, the SMMU, the PAT, and the PVU. The routing circuit is configured to receive a request comprising an address and an attribute and to route the request through at least one of the SMMU, the PAT, or the PVU based on the address and the attribute.

Abstract: An Adaptive Memory Mirroring Performance Accelerator (AMMPA) includes a centralized transaction handling block that dynamically maps the most frequently accessed memory regions into faster access memory. The technique creates shadow copies of the most frequently accessed memory regions in memory devices associated with lower latency. The regions for which shadow copies are provided are updated dynamically based on use, and the technique flexible for different memory hierarchies.

Abstract: In an advanced driver-assistance system (ADAS), RAW sensor image processing for a machine vision (MV) application is important. Due to different color, e.g., red/green/blue (RGB), color components, being focused by the lens at different locations in image plane, the lateral chromatic aberration phenomenon may sometimes be observed, which causes false color around edges in the final image output, especially for high contrast edges, which can impede MV applications. Disclosed herein are low-latency, efficient, optimized designs for chromatic aberration correction (CAC) components.

Abstract: An example apparatus includes: a first interface configured to couple to a processor core; a second interface configured to couple to a first memory configured to store an image that includes a set of slices; a third interface coupled to the first interface, the third interface configured to couple to a second memory; a direct memory access circuit coupled to the second interface and the third interface and configured to: receive a transaction from the second interface, wherein the transaction specifies a read of a slice of the set of slices; and based on the transaction: read the slice from the first memory; perform on-the-fly operations to the slice; and store the slice in the second memory.

Abstract: Systems, methods and devices that improve fault detection capability of an imaging/vision hardware accelerator are provided. One such system includes a hardware accelerator, a signature generator, a signature processor, and a controller. These components cooperate to generate first and second output frames based on first and second reference frames, respectively; generate a third output frame based on a use-case frame; generate first and second image signatures based on the first and second output frames, respectively; compare the first image signature to a stored first reference image signature and output a first result; and compare the second image signature to a stored second reference image signature and output a second result. The controller determines, based on the results, whether the hardware accelerator has a fault at either a first time or a second time. When no fault is detected at either time, the controller analyzes the use-case frame for designation as an adaptive reference frame.

Abstract: An image signal processor includes a first matrix processing circuit, a post processing circuit, a second matrix processing circuit, and a split visual and analytics circuit. The first matrix processing circuit is configured to receive a plurality of component images generated based on an image captured by an image sensor and generate a plurality of first matrix outputs based on the plurality of component images. The post processing circuit is configured to perform color conversion on the plurality of first matrix outputs to generate a first luminance component of the image and a chrominance component of the image. The second matrix processing circuit is configured to perform color conversion on the plurality of first matrix outputs to generate a second luminance component of the image and a saturation component of the image. The split visual and analytics circuit is configured to generate visual and analytic data of the image.

Abstract: The disclosure provides a sample adaptive offset (SAO) encoder. The SAO encoder includes a statistics collection (SC) block and a rate distortion optimization (RDO) block coupled to the SC block. The SC block receives a set of deblocked pixels and a set of original pixels. The SC block categorizes each deblocked pixel of the set of deblocked pixels in at least one of a plurality of band and edge categories. The SC block estimates an error in each category as difference between a deblocked pixel of the set of deblocked pixels and corresponding original pixel of the set of original pixels. The RDO block determines a set of candidate offsets associated with each category and selects a candidate offset with a minimum RD cost. The minimum RD cost is used by a SAO type block and a decision block to generate final offsets for the SAO encoder.

Abstract: A technique for determining regions and block sizes for configuring a perspective transformation engine including determining a set of scale ratios for images captured by a camera, generating a scale ratio image based on the set of scale ratios, determining a set of boundary ranges for the scale ratio image, generating a binary scale ratio image using the set of scale ratios of the scale ratio image, determining a set of regions based on the set of boundary ranges for the binary scale ratio image, determining a block size for each region of the determined set of regions, and outputting the determined set of regions and the determined block sizes.

Abstract: A method for error handling in a geometric correction engine (GCE) is provided that includes receiving configuration parameters by the GCE, generating, by the GCE in accordance with the configuration parameters, output blocks of an output frame based on corresponding blocks of an input frame, detecting, by the GCE, a run-time error during the generating, and reporting, by the GCE, an event corresponding to the run-time error.

Abstract: A method is provided that includes receiving pictures of a video sequence in a video encoder, and encoding the pictures to generate a compressed video bit stream that is transmitted to a video decoder in real-time, wherein encoding the pictures includes selecting a picture to be encoded as a delayed duplicate intra-predicted picture (DDI), wherein the picture would otherwise be encoded as an inter-predicted picture (P-picture), encoding the picture as an intra-predicted picture (I-picture) to generate the DDI, wherein the I-picture is reconstructed and stored for use as a reference picture for a decoder refresh picture, transmitting the DDI to the video decoder in non-real time, selecting a subsequent picture to be encoded as the decoder refresh picture, and encoding the subsequent picture in the compressed bit stream as the decoder refresh picture, wherein the subsequent P-picture is encoded as a P-picture predicted using the reference picture.

Abstract: In some examples, a system on chip (SOC) comprises a network switch configured to receive a packet and to identify a flow identifier (ID) corresponding to a header of the packet. The SOC comprises a direct memory access (DMA) controller coupled to the network switch, where the DMA controller is configured to divide the packet into first and second fragments based on the flow ID and to assign a first hardware queue to the first fragment and a second hardware queue to the second fragment, and wherein the DMA controller is further configured to assign memory regions to the first and second fragments based on the first and second hardware queues.

Abstract: Techniques including receiving a first set of values for processing by a machine learning (ML) network, storing a first portion of the first set of values in an on-chip memory, processing the first portion of the first set of values in a first layer of the ML network to generate a second portion of a second set of values, overwriting the stored first portion with the generated second portion, processing the second portion in a second layer of the ML network to generate a third portion of a third set of values, storing the third portion, repeating the steps of storing the first portion, processing the first portion, overwriting the stored first portion, processing the second portion, and storing the third portion for a fourth portion of the first set of values until all portions of the first set of values are processed to generate the third set of values.

Abstract: In the advanced driver-assistance systems (ADAS) field, RAW sensor image processing for machine vision (MV) applications can be of critical importance. Due to red/green/blue (RGB) image components being focused by the lens at different locations in image plane, the lateral chromatic aberration (LCA) phenomenon may sometimes be observed, which causes false color around edges in the final image output, especially for high contrast edges, which can impede MV applications. Disclosed herein are low-latency, efficient, optimized designs for chromatic aberration correction (CAC) modules.

Abstract: A system-on-chip (SoC) in which trace data is managed includes a first memory device, a first interface to couple the first memory to a second memory external to the system-on-chip, and a first processing resource coupled to the first interface and the first memory device. The first processing resource includes a data buffer and a first direct access memory (DMA) controller. The first DMA controller transmits data from the data buffer to the first interface over a first channel, and transmits the data from the data buffer with associated trace information for the data to the first memory device over a second channel.

Abstract: A video hardware engine with multi-threading functionality is disclosed. The video hardware engine includes a video hardware accelerator unit and a controller. The controller is coupled to the video hardware accelerator unit. The controller operates in an encode mode and a decode mode. In the encode mode, the controller receives a plurality of frames and encode attributes associated with each frame of the plurality of frames. The encode attributes associated with a frame of the plurality of frames is processed to generate encode parameters associated with the frame. The video hardware accelerator unit is configured to process the frame based on the encode parameters to generate an output. The output of the video hardware accelerator unit is processed to generate a compressed bit-stream and an encode status. In decode mode, the controller receives a compressed bit-stream and decode attributes and generates a plurality of frames and a decode status.