Abstract: A processing unit, method, and medium for decompressing or generating textures within a graphics processing unit (GPU). The textures are compressed with a variable-rate compression scheme such as JPEG. The compressed textures are retrieved from system memory and transferred to local cache memory on the GPU without first being decompressed. A table is utilized by the cache to locate individual blocks within the compressed texture. A decompressing shader processor receives compressed blocks and then performs on-the-fly decompression of the blocks. The decompressed blocks are then processed as usual by a texture consuming shader processor of the GPU.

Abstract: Methods and systems are disclosed for frequency transitioning in a memory interface system. Techniques disclosed include receiving a signal indicative of a change in operating frequency, into a new frequency, in a processing unit interfacing with memory via the memory interface system; switching the system from a normal mode of operation into a transition mode of operation; updating control and state register (CSR) banks of respective transceivers of the system through a mission bus used during the normal mode of operation; and operating the system in the new frequency.

Abstract: A technique for processing qubits in a quantum computing device is provided. The technique includes determining that, in a first cycle, a first quantum processing region is to perform a first quantum operation that does not use a qubit that is stored in the first quantum processing region, identifying a second quantum processing region that is to perform a second quantum operation at a second cycle that is later than the first cycle, wherein the second quantum operation uses the qubit, determining that between the first cycle and the second cycle, no quantum operations are performed in the second quantum processing region, and moving the qubit from the first quantum processing region to the second quantum processing region.

Abstract: Apparatuses, systems and methods for efficiently generating a package substrate. A semiconductor fabrication process (or process) fabricates each of a first glass package substrate and a second glass package substrate with a redistribution layer on a single side of a respective glass wafer. The process flips the second glass package substrate upside down and connects the glass wafers of the first and second glass package substrates together using a wafer bonding technique. In some implementations, the process uses copper-based wafer bonding. The resulting bonding between the two glass wafers contains no air gap, no underfill, and no solder bumps. Afterward, the side of the first glass package substrate opposite the glass wafer is connected to at least one integrated circuit. Additionally, the side of the second glass package substrate opposite the glass wafer is connected to a component on the motherboard through pads on the motherboard.

Abstract: Described herein is a technique for performing operations for a bounding volume hierarchy. The techniques include: for a bounding box with quantized orientation, the bounding box being part of a bounding volume hierarchy, rotating a ray according to the quantized orientation to generate a rotated ray; performing an intersection test against the bounding box with the rotated ray; and according to the results of the intersection test, continuing traversal of the bounding volume hierarchy.

Abstract: The disclosed voltage regulator includes multiple voltage converter circuits. Each of the voltage converter circuits can be configured to operate at respective switching frequencies to deliver current to an output supply voltage. The voltage regulator can include a control circuit that regulates the output supply voltage using the voltage converter circuits. Various other methods and systems are also disclosed.

Abstract: A uniform cache for fast data access including a plurality of compute units (CUs) and a plurality of LO caches with an arrangement in a network configuration where each one of CUs is surrounded by a first group of the plurality of LO caches and each of the plurality of LO caches is surrounded by a LO cache group and CU group. One of CUs, upon a request for data, queries the surrounding first group of LO caches to satisfy the request. If the first group of LO caches fails to satisfy the data request, the first group of the plurality of LO caches queries a second group of adjacent LO caches to satisfy the request. If the second group of adjacent LO caches fails to satisfy the data request, the second group of adjacent LO caches propagating the query to the next group of LO caches.

Abstract: A method and apparatus for managing a controller includes indicating, by a processor of a first device, to the controller of a second device to enter a second power state from a first power state. The controller of the second device responds to the processor of the first device with a confirmation. The processor of the first device transmits a signal to the controller of the second device to enter the second power state. Upon receiving a wake event, the controller of the second device exits the second device from the second power state to the first power state.

Abstract: An apparatus and method for providing efficient floor planning, power, and performance tradeoffs of memory accesses. A dual read port and single write port memory bit cell uses two asymmetrical read access circuits for conveying stored data on two read bit lines. The two read bit lines are pre-charged to different voltage reference levels. The layout of the memory bit cell places the two read bit lines on an opposed edge from the single write bit line. The layout uses a dummy gate placed over both p-type diffusion and n-type diffusion between the edges. The layout has a same number of p-type transistors as n-type transistors despite using asymmetrical read access circuits. The layout also has a contacted gate pitch that is one more than the number of p-type transistors.

Abstract: An apparatus and method for supporting communication during error handling in a computing system. A computing system includes a first partition and a second partition, each capable of performing error management based on a respective machine check architecture (MCA). When a host processor in the first partition detects an error that requires information from processor cores of the second partition, the host processor generates an access request with a target address pointing to a storage location in a memory of the second partition, not the first partition. When the host processor receives the requested error log information from the second partition, the host processor completes processing of the error. To support the host processor in generating the target address for the access request, during an earlier bootup operation, the second partition communicates the hardware topology of the second partition to the host processor.

Abstract: A processing device is provided which comprises memory configured to store data and a processor. The processor comprises a plurality of MACs configured to perform matrix multiplication of elements of a first matrix and elements of a second matrix. The processor also comprises a plurality of logic devices configured to sum values of bits of product exponents values of the elements of the first matrix and second matrix and determine keep bit values for product exponents values to be kept for matrix multiplication. The processor also comprises a plurality of multiplexor arrays each configured to receive bits of the elements of the first matrix and the second matrix and the keep bit values and provide data for selecting which elements of the first matrix and the second matrix values are provided to the MACs for matrix multiplication.

Abstract: An integrated circuit (IC) includes a debug controller, a debug state machine (DSM), and an extended performance monitor counter (EPMC). The debug controller that selectively outputs debug data on a debug interconnect. The DSM identifies an event based on the debug data and an event list and outputs a DSM indication that identifies the event. The EPMC indicates a plurality of detected events including the identified event. The EPMC indicates the identified event in response to the DSM indication.

Abstract: The disclosed computer-implemented method for tracking miss requests using data cache tags can include generating a data cache miss request associated with data requested in connection with a cacheline and allocating a miss address buffer entry for the miss request. Additionally, the method can include, setting a fill-pending flag associated with the cacheline in response to the data associated with the data cache miss request being absent from a first data cache, and de-allocating the miss address buffer entry. In the event that another load or store operation requests the same data associated with the cacheline while the fill-pending flag is set, the method can include monitoring for a fill response associated with the miss request until the fill response is received. Upon receipt of the fill response, the method can include re-setting the fill-pending flag associated with the cacheline.

Abstract: A memory controller includes a command queue with multiple entry stacks, each with a plurality of entries holding memory access commands, one or more parameter indicators each holding a respective characteristic common to the plurality of entries, and a head indicator designating a current entry for arbitration. An arbiter has a single command input for each entry stack. A command queue loader circuit receives incoming memory access commands and loads entries of respective entry stacks with memory access commands having the respective characteristic of each of the one or more parameter indicators in common.

Abstract: A technique for performing ray tracing operations is provided.

Abstract: A disclosed technique includes obtaining input video at a first resolution; upscaling the input video to a second resolution that is higher than the first resolution, using an encoder having a low complexity enhancement video coding encoder that omits at least one component, to generate upscaled video; and encoding the upscaled video using the encoder to generate encoded output video.

Abstract: Systems, apparatuses, and methods for implementing a low power parallel matrix multiply pipeline are disclosed. In one embodiment, a system includes at least first and second vector register files coupled to a matrix multiply pipeline. The matrix multiply pipeline comprises a plurality of dot product units. The dot product units are configured to calculate dot or outer products for first and second sets of operands retrieved from the first vector register file. The results of the dot or outer product operations are written back to the second vector register file. The second vector register file provides the results from the previous dot or outer product operations as inputs to subsequent dot or outer product operations. The dot product units receive the results from previous phases of the matrix multiply operation and accumulate these previous dot or outer product results with the current dot or outer product results.

Abstract: A memory system uses error detection codes to detect when errors have occurred in a region of memory. A count of the number of errors is kept and a notification is output in response to the number of errors satisfying a threshold value. The notification is an indication to a host (e.g., a program accessing or managing a machine learning system) that the threshold number of errors have been detected in the region of memory. As long as the number of errors that have been detected in the region of memory remains under the threshold number no notification need be output to the host.

Abstract: Systems, apparatuses, and methods for performing color channel correlation detection are disclosed. A compression engine performs a color channel transform on an original set of pixel data to generate a channel transformed set of pixel data. An analysis unit determines whether to compress the channel transformed set of pixel data or the original set of pixel data based on performing a comparison of the two sets of pixel data. In one scenario, the channel transformed set of pixel data is generated by calculating the difference between a first pixel component and a second pixel component for each pixel of the set of pixel data. The difference is then compared to the original first pixel component for each pixel. If the difference is less than or equal to the original for a threshold number of pixels, then the analysis unit decides to apply the color channel transform prior to compression.

Abstract: Data reuse cache techniques are described. In one example, a load instruction is generated by an execution unit of a processor unit. In response to the load instruction, data is loaded by a load-store unit for processing by the execution unit and is also stored to a data reuse cache communicatively coupled between the load-store unit and the execution unit. Upon receipt of a subsequent load instruction for the data from the execution unit, the data is loaded from the data reuse cache for processing by the execution unit.