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: 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: 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: 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: 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 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 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: 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 technique for operating a memory system is disclosed. The technique includes performing a first request, by a first memory client, to access data at a first memory address, wherein the first memory address refers to data in a first memory section that is coupled to the first memory client via a direct memory connection; servicing the first request via the direct memory connection; performing a second request, by the first client, to access data at a second memory address, wherein the second memory address refers to data in a second memory section that is coupled to the first client via a cross connection; and servicing the second request via the cross connection.

Abstract: Memories that are configurable to operate in either a banked mode or a bit-separated mode. The memories include a plurality of memory banks; multiplexing circuitry; input circuitry; and output circuitry. The input circuitry inputs at least a portion of a memory address and configuration information to the multiplexing circuitry. The multiplexing circuitry generates read data by combining a selected subset of data corresponding to the address from each of the plurality of memory banks, the subset selected based on the configuration information, if the configuration information indicates a bit-separated mode. The multiplexing circuitry generates the read data by combining data corresponding to the address from one of the memory banks, the one of the memory banks selected based on the configuration information, if the configuration information indicates a banked mode. The output circuitry outputs the generated read data from the memory.

Abstract: Systems, devices, and methods for direct memory access. A system direct memory access (SDMA) device disposed on a processor die sends a message which includes physical addresses of a source buffer and a destination buffer, and a size of a data transfer, to a data fabric device. The data fabric device sends an instruction which includes the physical addresses of the source and destination buffer, and the size of the data transfer, to first agent devices. Each of the first agent devices reads a portion of the source buffer from a memory device at the physical address of the source buffer. Each of the first agent devices sends the portion of the source buffer to one of second agent devices. Each of the second agent devices writes the portion of the source buffer to the destination buffer.

Abstract: A coherency management device receives requests to read data from or write data to an address in a main memory. On a write, if the data includes zero data, an entry corresponding to the memory address is created in a cache directory if it does not already exist, is set to an invalid state, and indicates that the data includes zero data. The zero data is not written to main memory or a cache. On a read, the cache directory is checked for an entry corresponding to the memory address. If the entry exists in the cache directory, is invalid, and includes an indication that data corresponding to the memory address includes zero data, the coherency management device returns zero data in response to the request without fetching the data from main memory or a cache.

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: A disclosed technique includes determining a plurality of per-pixel variable rate shading rates for a plurality of fragments; determining a coarse variable shading rate for a coarse variable rate shading area based on the plurality of per-pixel variable rate shading rates; and shading one or more fragments based on the plurality of fragments and based on the coarse variable shading rate.

Abstract: A method for managing operational costs associated with distributed computing. The method includes: creating, via a graphical user interface (GUI), a distributed computing team; linking a digital team wallet to the distributed computing team, wherein the digital team wallet is linked to a currency account; adding a member to the distributed computing team; allowing the member to purchase compute resource access from a plurality of compute resource providers using the digital team wallet; and notifying a team manager when funds in the digital team wallet reduce to at least a team threshold value.

Abstract: A method for operating a system including a voltage regulating power supply includes sensing a local voltage on a first node of the system and a remote voltage on a second node of the system. The first node and the second node are in a conductive path coupled to a load of the system. The first node is closer to a power stage of the voltage regulating power supply than the second node. The second node is closer to the load than the first node. The method includes detecting a load release event based on the local voltage, the remote voltage, and at least one predetermined threshold value.

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.

Abstract: One or more processing units, such as a graphics processing unit (GPU), execute an application. A resource manager selectively allocates a first memory portion or a second memory portion to the processing units based on memory access characteristics. The first memory portion has a first latency that is lower that a second latency of the second memory portion. In some cases, the memory access characteristics indicate a latency sensitivity. In some cases, hints included in corresponding program code are used to determine the memory access characteristics. The memory access characteristics can also be determined by monitoring memory access requests, measuring a cache miss rate or a row buffer miss rate for the monitored memory access requests, and determining the memory access characteristics based on the cache miss rate or the row buffer miss rate.

Abstract: Data are serially communicated over an interconnect between an encoder and a decoder. The encoder includes a first training unit to count a frequency of symbol values in symbol blocks of a set of N number of symbol blocks in an epoch. A circular shift unit of the encoder stores a set of most-recently-used (MRU) amplitude values. An XOR unit is coupled to the first training unit and the first circular shift unit as inputs and to the interconnect as output. A transmitter is coupled to the encoder XOR unit and the interconnect and thereby contemporaneously sends symbols and trains on the symbols. In a system, a device includes a receiver and decoder that receive, from the encoder, symbols over the interconnect. The decoder includes its own training unit for decoding the transmitted symbols.