Abstract: A method for manufacturing a three-dimensional integrated circuit includes attaching a first side of a first die to a first carrier wafer. The method includes preparing a second side of the first die to generate a prepared second side of the first die. The method includes attaching the prepared second side of the first die to a second carrier wafer. The method includes removing the first carrier wafer from the first side of the first die to form a transitional three-dimensional integrated circuit. The method includes attaching a third carrier wafer to a first side of the transitional three-dimensional integrated circuit. The method includes attaching a first side of the second die to a second side of the transitional three-dimensional integrated circuit.

Abstract: Systems, apparatuses, and methods for optimizing neural network training with a first-in, last-out (FILO) buffer are disclosed. A processor executes a training run of a neural network implementation by performing multiple passes and adjusting weights of the neural network layers on each pass. Each training phase includes a forward pass and a backward pass. During the forward pass, each layer, in order from first layer to last layer, stores its weights in the FILO buffer. An error is calculated for the neural network at the end of the forward pass. Then, during the backward pass, each layer, in order from last layer to first layer, retrieves the corresponding weights from the FILO buffer. Gradients are calculated based on the error so as to update the weights of the layer for the next pass through the neural network.

Abstract: Systems, apparatuses, and methods for proactively managing inter-processor network links are disclosed. A computing system includes at least a control unit and a plurality of processing units. Each processing unit of the plurality of processing units includes a compute module and a configurable link interface. The control unit dynamically adjusts a clock frequency and a link width of the configurable link interface of each processing unit based on a data transfer size and layer computation time of a plurality of layers of a neural network so as to reduce execution time of each layer. By adjusting the clock frequency and the link width of the link interface on a per-layer basis, the overlapping of communication and computation phases is closely matched, allowing layers to complete more quickly.

Abstract: Automatic voltage reconfiguration in a computer processor including one or more cores includes executing one or more user-specified workloads; determining, based on the user-specified workloads, a respective minimum safe voltage for each core of one or more cores; and modifying a respective voltage configuration for each core of the one or more cores based on the respective minimum safe voltage.

Abstract: A method, computer system, and a non-transitory computer-readable storage medium for performing primitive batch binning are disclosed. The method, computer system, and non-transitory computer-readable storage medium include techniques for generating a primitive batch from a plurality of primitives, computing respective bin intercepts for each of the plurality of primitives in the primitive batch, and shading the primitive batch by iteratively processing each of the respective bin intercepts computed until all of the respective bin intercepts are processed.

Abstract: A computer vision processing device is provided which comprises memory configured to store data and a processor. The processor is configured to store captured image data in a first buffer and acquire access to the captured image data in the first buffer when the captured image data is available for processing. The processor is also configured to execute a first group of operations in a processing pipeline, each of which processes the captured image data accessed from the first buffer and return the first buffer for storing next captured image data when a last operation of the first group of operations executes.

Abstract: Various computing network messaging techniques and apparatus are disclosed. In one aspect, a method of computing is provided that includes executing a first thread and a second thread. A message is sent from the first thread to the second thread. The message includes a domain descriptor that identifies a first location of the first thread and a second location of the second thread.

Abstract: Systems, apparatuses, and methods for performing efficient memory accesses for a computing system are disclosed. In various embodiments, a computing system includes a computing resource and a memory controller coupled to a memory device. The computing resource selectively generates a hint that includes a target address of a memory request generated by the processor. The hint is sent outside the primary communication fabric to the memory controller. The hint conditionally triggers a data access in the memory device. When no page in a bank targeted by the hint is open, the memory controller processes the hint by opening a target page of the hint without retrieving data. The memory controller drops the hint if there are other pending requests that target the same page or the target page is already open.

Abstract: A technique for processing images is disclosed. The technique includes determining depth information for an image; identifying a depth threshold; and modifying content of the image based on a comparison of the depth information and the depth threshold.

Abstract: A system and method for laying out power grid connections for standard cells are described. In various implementations, gate metal is placed over non-planar vertical conducting structures, which are used to form non-planar devices (transistors). Gate contacts connect gate metal to gate extension metal (GEM) above the gate metal. GEM is placed above the gate metal and makes a connection with gate metal through the one or more gate contacts. Gate extension contacts are formed on the GEM above the active regions. Similar to gate contacts, gate extension contacts are formed with a less complex fabrication process than using a self-aligned contacts process. Gate extension contacts connect GEM to an interconnect layer such as a metal zero layer. Gate extension contacts are aligned vertically with one of the non-planar vertical conducting structures. Therefore, in an implementation, one or more gate extension contacts are located above the active region.

Abstract: Systems, apparatuses, and methods for performing efficient memory accesses for a computing system are disclosed. A computing system includes one or more clients for processing applications. A memory controller transfers traffic between the memory controller and two channels, each connected to a memory device. A client sends a 64-byte memory request with an indication specifying that there are two 32-byte requests targeting non-contiguous data within a same page. The memory controller generates two addresses, and sends a single command and the two addresses to two channels to simultaneously access non-contiguous data in a same page.

Abstract: A method of controlling a cache is disclosed. The method comprises receiving a request to allocate a portion of memory to store data. The method also comprises directly mapping a portion of memory to an assigned contiguous portion of the cache memory when the request to allocate a portion of memory to store the data includes a cache residency request that the data continuously resides in cache memory. The method also comprises mapping the portion of memory to the cache memory using associative mapping when the request to allocate a portion of memory to store the data does not include a cache residency request that data continuously resides in the cache memory.

Abstract: Systems, apparatuses, and methods for implementing as part of a processor pipeline a reprogrammable execution unit capable of executing specialized instructions are disclosed. A processor includes one or more reprogrammable execution units which can be programmed to execute different types of customized instructions. When the processor loads a program for execution, the processor loads a bitfile associated with the program. The processor programs a reprogrammable execution unit with the bitfile so that the reprogrammable execution unit is capable of executing specialized instructions associated with the program. During execution, a dispatch unit dispatches the specialized instructions to the reprogrammable execution unit for execution.

Abstract: A power supply detection circuit for an integrated circuit (IC) includes a reference voltage circuit and a comparator circuit. The reference voltage circuit produces a reference voltage from the supply voltage at a reference voltage node. The comparator circuit includes a first p-type metal oxide semiconductor (PMOS) transistor with a source coupled to a positive supply terminal, a gate receiving the reference voltage, and a drain connected to a comparator output terminal. A first n-type metal oxide semiconductor (NMOS) transistor has a drain connected to the comparator output terminal, a source connected to the negative supply terminal, and a gate receiving a second voltage that varies relative to the supply voltage. A second PMOS transistor has a source coupled to the positive supply terminal, a gate connected to the reference voltage node, and a drain providing the second voltage and coupled to a filter.

Abstract: A set of entries in a branch prediction structure for a set of second blocks are accessed based on a first address of a first block. The set of second blocks correspond to outcomes of one or more first branch instructions in the first block. Speculative prediction of outcomes of second branch instructions in the second blocks is initiated based on the entries in the branch prediction structure. State associated with the speculative prediction is selectively flushed based on types of the branch instructions. In some cases, the branch predictor can be accessed using an address of a previous block or a current block. State associated with the speculative prediction is selectively flushed from the ahead branch prediction, and prediction of outcomes of branch instructions in one of the second blocks is selectively initiated using non-ahead accessing, based on the types of the one or more branch instructions.

Abstract: Systems, apparatuses, and methods for performing efficient video transmission are disclosed. In a video processing system, a transmitter identifies multiple planes in a scene. The transmitter renders and compresses each of the multiple planes with a combination of a corresponding compression level and a resolution, which is different from a combination of compression level and resolution of any other plane. For each plane, the transmitter inserts, in multi-plane information, data such as identification of the plane, a location in the video frame for the plane, and one or more of a resolution and compression level for the plane. The transmitter conveys the rendered and compressed planes along with the multi-plane information to a receiver. The receiver decodes each of the planes and insets each of the planes on any lower resolution planes of the multiple planes.

Abstract: A method and apparatus of protecting a memory from a write attack includes dividing a cacheline of memory into a plurality of sub-blocks. A codeword is generated from at least one sub-block of the plurality of sub-blocks and a complement of the at least one sub-block. One of the generated codewords is selected, wherein the selected codeword is used for storage in memory.

Abstract: A processor includes two or more branch target buffer (BTB) tables for branch prediction, each BTB table storing entries of a different target size or width or storing entries of a different branch type. Each BTB entry includes at least a tag and a target address. For certain branch types that only require a few target address bits, the respective BTB tables are narrower thereby allowing for more BTB entries in the processor separated into respective BTB tables by branch instruction type. An increased number of available BTB entries are stored in a same or a less space in the processor thereby increasing a speed of instruction processing. BTB tables can be defined that do not store any target address and rely on a decode unit to provide it. High value BTB entries have dedicated storage and are therefore less likely to be evicted than low value BTB entries.

Abstract: A processing device comprises a memory configured to store data and a processor. The processor is configured to control an exposure timing of a rolling shutter image sensor and an IR illumination timing of an object, by an IR light emitter, by switching between a first operation mode and a second operation mode. In the first operation mode, a sequence of video frames, each having a plurality of pixel lines, comprises a frame in which each pixel line is exposed to IR light emitted by the IR light emitter; a frame which is partially exposed to the IR light and a frame in which no pixel line is exposed to the IR light. In the second operation mode, alternating video frames of the sequence comprise one of a frame in which each pixel line is exposed to the IR light and a frame in which no pixel line is exposed to the IR light.

Abstract: A method includes receiving a write request for writing incoming data to a target memory line and, in response to the write request, comparing the incoming data with existing data in the target memory line to determine a number of a first type of state transition. The method further includes, in response to determining that the number of the first type of state transition for the write request exceeds a threshold, prior to writing the incoming data to the target memory line, storing adjacent data from each of a set of memory lines adjacent to the target memory line, and after writing the incoming data to the target memory line, writing the stored data to the set of adjacent memory lines.