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: Data routing for efficient decompressor use is described. In accordance with the described techniques, a cache controller receives requests from multiple requestors for elements of data stored in a compressed format in a cache. The requests include at least a first request from a first requestor and a second request from a second requestor. A decompression routing system identifies a redundant element of data requested by both the first requestor and the second requestor and causes decompressors to decompress the requested elements of data. The decompression includes performing a single decompression of the redundant element. After the decompression, the decompression routing system routes the decompressed elements to the plurality of requestors, which includes routing the decompressed redundant element to both the first requestor and the second requestor.

Abstract: Selecting between basic and global persistent flush modes is described. In accordance with the described techniques, a system includes a data fabric in electronic communication with at least one cache and a controller configured to select between operating in a global persistent flush mode and a basic persistent flush mode based on an available flushing latency of the system, control the at least one cache to flush dirty data to the data fabric in response to a flush event trigger while operating in the global persistent flush mode, and transmit a signal to switch control to an application to flush the dirty data from the at least one cache to the data fabric while operating in the basic persistent flush mode.

Abstract: Methods and apparatus for synchronizing data transfers across clock domains for using heads-up indications. An integrated circuit includes a first-in first-out buffer (FIFO); a memory controller configured to operate in a first clock domain and coupled to the FIFO, the first clock domain associated with a first clock signal; a data fabric configured to operate in a second clock domain and coupled to the FIFO, the second clock domain associated with a second clock signal, a second frequency of the second clock signal being different from a first frequency of the first clock signal; and a controller coupled to the FIFO. In some instances, the controller determines a phase relationship between the first clock signal and the second clock signal; monitors one or more first clock edges of the first clock signal and one or more second clock edges of the second clock signal; and sends a first heads-up signal to the memory controller.

Abstract: A processing device is provided which includes memory and a processor. The processor is configured to receive an input image having a first resolution, generate at least one linear down-sampled version of the input image via a linear upscaling network, generate at least one non-linear down-sampled version of the input image via a non-linear upscaling network, extract a first feature map from the at least one linear down-sampled version of the input image, and extract a second feature map from the at least one non-linear down-sampled version of the input image. The processor is also configured to convert the at least one linear down-sampled version of the input image and the at least one non-linear down-sampled version of the input image into pixels of an output image having a second resolution higher than the first resolution using the first feature map and the second feature map.

Abstract: A memory module includes register selection logic to select alternate local source and/or destination registers to process PIM commands. The register selection logic uses an address-based register selection approach to select an alternate local source and/or destination register based upon address data specified by a PIM command and a split address maintained by a memory module. The register selection logic may alternatively use a register data-based approach to select an alternate local source and/or destination register based upon data stored in one or more local registers. A PIM-enabled memory module configured with the register selection logic described herein is capable of selecting an alternate local source and/or destination register to process PIM commands at or near the PIM execution unit where the PIM commands are executed.

Abstract: An exemplary computing device includes a plurality of circuits and/or a plurality of in-situ monitors configured to generate outputs that indicate one or more operating conditions of the circuits. The computing device also includes a system management unit configured to detect a potentially faulty voltage-to-frequency ratio implemented by one of the circuits based at least in part on one or more of the outputs. The system management unit is also configured to modify the potentially faulty voltage-to-frequency ratio based at least in part on one or more of the outputs. Various other devices, systems, and methods are also disclosed.

Abstract: A system and method for automatically generating placement of vias within redistribution layers of a semiconductor package are described. In various implementations, a user defines attributes to use for automatic via generation in redistribution layers of a semiconductor package. The circuitry of a processor of a computing device used by the user executes instructions of an automatic redistribution layer (RDL) via generator. The automatic via generator uses the attributes, data indicative of the RDL netlist of signal routes within the RDL, and RDL mask layout data representing the signal masks of the metal layers within the RDL. The processor generates placement of vias for in the RDL based on the attributes and an identification of overlapping regions between metal layers.

Abstract: Systems, apparatuses, and methods for efficiently processing memory requests are disclosed. A computing system includes at least one processing unit coupled to a memory. Circuitry in the processing unit determines a memory request becomes a long-latency request based on detecting a translation lookaside buffer (TLB) miss, a branch misprediction, a memory dependence misprediction, or a precise exception has occurred. The circuitry marks the memory request as a long-latency request such as storing an indication of a long-latency request in an instruction tag of the memory request. The circuitry uses weighted criteria for scheduling out-of-order issue and servicing of memory requests. However, the indication of a long-latency request is not combined with other criteria in a weighted sum. Rather, the indication of the long-latency request is a separate value. The circuitry prioritizes memory requests marked as long-latency requests over memory requests not marked as long-latency requests.

Abstract: In some implementations, a processor includes a plurality of parallel instruction pipes, a register file includes at least one shared read port configured to be shared across multiple pipes of the plurality of parallel instruction pipes. Control logic controls multiple parallel instruction pipes to read from the at least one shared read port. In certain examples, the at least one shared register file read port is coupled as a single read port for one of the parallel instruction pipes and as a shared register file read port for a plurality of other parallel instruction pipes.

Abstract: A multi-die processor semiconductor package includes a first base integrated circuit (IC) die configured to provide, based at least in part on an indication of a configuration of a first plurality of compute dies 3D stacked on top of the first base IC die, a unique power domain to each of the first plurality of compute dies. In some embodiments, the semiconductor package also includes a second base IC die including a second plurality of compute dies 3D stacked on top of the second base IC die and an interconnect communicably coupling the first base IC die to the second base IC die.

Abstract: Methods, systems, and devices maintain state information in a shadow tag memory for a plurality of cachelines in each of a plurality of private caches, with each of the private caches being associated with a corresponding one of multiple processing cores. One or more cache probes are generated based on a write operation associated with one or more cachelines of the plurality of cachelines, such that each of the cache probes is associated with cachelines of a particular private cache of the multiple private caches, the particular private cache being associated with an indicated processing core. Transmission of the cache probes to the particular private cache is prevented until, responsive to a scope acquire operation from the indicated processing core, the cache probes are released for transmission to the respectively associated cachelines in the particular private cache.

Abstract: A method for controlling a data processing system includes detecting a droop in a power supply voltage of a functional circuit of the data processing system greater than a programmable droop threshold. An operation of the data processing system is throttled according to a programmable step size, a programmable assertion time, and a programmable de-assertion time in response to detecting the droop.

Abstract: An oscillator circuit is provided that adapts to voltage supply variations. The circuit first and second delays lines connected inputs of an edge detector, one delay line supplied by a reference voltage and the other with a drooping supply voltage. The edge detector generates an output clock based on a relationship between the inputs. The output clock applied to the signal inputs of the first and second delay lines. The output clock has a voltage dependent frequency performance curve with a slope dependent at least on the second delay line delay and a delay of the edge detector. At least one of the first delay line, the second delay line, and the edge detector delay are adjusted to change the slope of the performance curve.

Abstract: A semiconductor package for skew matching in a die-to-die interface, including: a first die; a second die aligned with the first die such that each connection point of a first plurality of connection points of the first die is substantially equidistant to a corresponding connection point of a second plurality of connection points of the second die; and a plurality of connection paths of a substantially same length, wherein each connection path of the plurality of connection paths couples a respective connection point of the first plurality of connection points to the corresponding connection point of the second plurality of connection points.

Abstract: A multiply-accumulate computation is performed using digital logic circuits. To perform the computation, a plurality of target signals are received at a respective plurality of ripple counters. The counter outputs of the respective ripple counters are scaled by setting stop count values. Counter outputs of the respective ripple counters are adjusted with respective constant values by setting counter reset values at the respective ripple counters. Each count pulses of the target signals for an adjusted period. The count values of the ripple counters are summed. The results may be used to calculate an average value for an adaptive voltage and frequency scaling process.

Abstract: The disclosed device for packet coalescing includes detecting a trigger condition for initiating packet coalescing of packet traffic and sending, to an endpoint device, a notification to start packet coalescing. The device can observe a status in response to starting the packet coalescing and report a performance of the packet coalescing. A system can include a controller that detects a trigger condition for packet coalescing and notifies an endpoint device via a notification register. The controller can read a status register to report, based on the read status, a packet coalescing performance. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A memory controller monitors memory command selected for dispatch to the memory and sends commands controlling a read clock state. A memory includes a read clock circuit and a mode register. The read clock circuit has an output for providing a hybrid read clock signal in response to a clock signal and a read clock mode signal. The read clock circuit provides the hybrid read clock signal as a free-running clock signal that toggles continuously, and as a strobe signal that is active only in response to the memory receiving a read command.

Abstract: An apparatus, such as a graphical processing unit (GPU), includes one or more processors configured to determine a plurality of first locality information of a received wave at a processing unit and to select a first processing element of a plurality of processing elements, the first processing unit having a plurality of second locality information from a previous wave that matches the plurality of first locality information to execute the received wave.

Abstract: A method, system, and non-transitory computer readable storage medium for rasterizing primitives are disclosed. The method, system, and non-transitory computer readable storage medium includes: generating a primitive batch from a sequence of one or more primitives, wherein the primitive batch includes primitives sorted into one or more row groups based on which row of a plurality of rows each primitive intersects; and processing each row group, the processing for each row group including: identifying one or more primitive column intercepts for each of the one or more primitives in the row group, wherein each combination of primitive column intercept and row identifies a bin; and rasterizing the one or more primitives that intersect the bin.