Abstract: A memory controller includes a command queue, an arbiter, and a controller. The controller is responsive to a repair signal for migrating data from a failing region of a memory to a buffer, generating at least one command to perform a post-package repair operation of the failing region, and migrating the data from the buffer to a substitute region of the memory. The controller migrates the data to and from the buffer by providing migration read requests and migration write requests, respectively, to the command queue. The arbiter uses the plurality of arbitration rules for both the read migration requests and the write migration requests, and the read access requests and the write access requests.

Abstract: Systems, apparatuses, and methods for implementing a low-power single-phase logic gate latch for clock-gating are disclosed. A latch circuit includes shared clocked transistors without including clock inverters. The shared clocked transistors include a P-type clocked transistor and an N-type clocked transistor, with the clock input coupled to the gate of the P-type clocked transistor and to the gate of the N-type clocked transistor. The P-type clocked transistor is coupled between first and second transistor stacks of the latch. The N-type clocked transistor is coupled to a source gate of a first stack N-type transistor gated by a data input and to a source gate of a second stack N-type transistor gated by the inverted data input. The latch has a lower clock pin capacitance than a traditional logic gate latch while also avoiding having clock inverters which reduces dynamic power consumption.

Abstract: A signal processing circuit includes an analog front-end circuit and a digital delay circuit. The analog circuit receives a clock signal and provides a compensated clock signal. The digital delay circuit is coupled to the analog front-end circuit and provides a compensated sample clock signal in response to delaying the compensated clock signal. The analog circuit measures a variation of a power supply voltage and adjusts a gain through the analog circuit according to a measured variation of the power supply voltage.

Abstract: Generating optimization instructions for data processing pipelines is described. A pipeline optimization system computes resource usage information that describes memory and compute usage metrics during execution of each stage of the data processing pipeline. The system additionally generates data storage information that describes how data output by each pipeline stage is utilized by other stages of the pipeline. The pipeline optimization system then generates the optimization instructions to control how memory operations are performed for a specific data processing pipeline during execution. In implementations, the optimization instructions cause a memory system to discard data (e.g., invalidate cache entries) without copying the discarded data to another storage location after the data is no longer needed by the pipeline. The optimization instructions alternatively or additionally control at least one of evicting, writing-back, or prefetching data to minimize latency during pipeline execution.

Abstract: Some implementations provide systems, devices, and methods for rendering a plurality of primitives of a frame, the plurality of primitives being divided into a plurality of batches of primitives and the frame being divided into a plurality of bins. For at least one batch of the plurality of batches the rendering includes, for each of the plurality of bins, rendering primitives of a first sub-batch rasterizing to that bin, and for each of the plurality of bins, rendering primitives of a second sub-batch rasterizing to that bin.

Abstract: The disclosed computer-implemented method includes receiving, by a first circuit subsystem, a hardware error signal and storing, in response to the hardware error signal, a signal state of the first circuit subsystem in a reset-persistent register. The method also includes sending, by the first circuit subsystem, the hardware error signal to a second circuit subsystem. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: An arbiter is operable to pick commands from a command queue for dispatch to a memory. The arbiter includes a traffic throttle circuit for mitigating excess power usage increases in coordination with one or more additional arbiters. The traffic throttle circuit includes a monitoring circuit and a throttle circuit. The monitoring circuit is for measuring a number of read and write commands picked by the arbiter and the one or more additional arbiters over a first predetermined period of time. The throttle circuit, responsive to a low activity state, limits a number of read and write commands issued by the arbiter during a second predetermined period of time.

Abstract: An integrated circuit device assembly including a graphene-coated heat spreader, including: a substrate; a die coupled to the substrate; and a heat spreader thermally coupled to the die, the heat spreader comprising: a body of thermally conductive metal defining a cavity at least partially surrounding the die; and a graphene layer contacting a surface of the body.

Abstract: A receiver is trained for receiving a signal over a data bus. A volatile memory is commanded over the data bus to place a selected pulse-amplitude modulation (PAM) driver in a mode with a designated steady output level. At a receiver circuit coupled to the selected PAM driver, a respective reference voltage associated with the designated steady output level is swept through a range of voltages and the respective reference voltage is compared to a voltage received from the PAM driver to determine a respective voltage level received from the PAM driver.

Abstract: Merging branch target buffer entries includes maintaining, in a branch target buffer, an entry corresponding to first branch instruction, where the entry identifies a first branch target address for the first branch instruction and a second branch target address for a second branch instruction; and accessing, based on the first branch instruction, the entry.

Abstract: A method for hierarchical work scheduling includes consuming a work item at a first scheduling domain having a local scheduler circuit and one or more workgroup processing elements. Consuming the work item produces a set of new work items. Subsequently, the local scheduler circuit distributes at least one new work item of the set of new work items to be executed locally at the first scheduling domain. If the local scheduler circuit of the first scheduling domain determines that the set of new work items includes one or more work items that would overload the first scheduling domain with work if scheduled for local execution, those work items are distributed to the next higher-level scheduler circuit in a scheduling domain hierarchy for redistribution to one or more other scheduling domains.

Abstract: Devices and methods for node traversal for ray tracing are provided, which comprise casting a first ray in a space comprising objects represented by geometric shapes, traversing, for the first ray, at least one first node of an accelerated hierarchy structure representing an approximate volume of a group of the geometric shapes and a second node representing a volume of one of the geometric shapes, casting a second ray in the space, selecting, for the second ray, a starting node of traversal based on locations of intersection of the first ray and the second ray and an identifier which identifies one or more nodes intersected by the first ray and traversing, for the second ray, the accelerated hierarchy structure beginning at the starting node of traversal.

Abstract: In accordance with described techniques for processing-in-memory (PIM) search stop control, a computing system or computing device includes a memory system that includes a stop condition check component, which receives an instruction that includes a programmed check value. The stop condition check component compares the programmed check value to outputs of a PIM component, and the stop condition check component initiates a stop instruction to stop the PIM component from processing subsequent computations based on an output of the PIM component matching the programmed check value.

Abstract: Systems, apparatuses, and methods for abstracting tasks in virtual memory identifier (VMID) containers are disclosed. A processor coupled to a memory executes a plurality of concurrent tasks including a first task. Responsive to detecting one or more instructions of the first task which correspond to a first operation, the processor retrieves a first identifier (ID) which is used to uniquely identify the first task, wherein the first ID is transparent to the first task. Then, the processor maps the first ID to a second ID and/or a third ID. The processor completes the first operation by using the second ID and/or the third ID to identify the first task to at least a first data structure. In one implementation, the first operation is a memory access operation and the first data structure is a set of page tables. Also, in one implementation, the second ID identifies a first application of the first task and the third ID identifies a first operating system (OS) of the first task.

Abstract: A disclosed computing device includes at least one prefetcher and a processing device communicatively coupled to the prefetcher. The processing device is configured to detect a throttling instruction that indicates a start of a throttling region. The computing device is further configured to prevent the prefetcher from being trained on one or more memory instructions included in the throttling region in response to the throttling instruction. Various other apparatuses, systems, and methods are also disclosed.

Abstract: Processor-guided execution of offloaded instructions using fixed function operations is disclosed. Instructions designated for remote execution by a target device are received by a processor. Each instruction includes, as an operand, a target register in the target device. The target register may be an architected virtual register. For each of the plurality of instructions, the processor transmits an offload request in the order that the instructions are received. The offload request includes the instruction designated for remote execution. The target device may be, for example, a processing-in-memory device or an accelerator coupled to a memory.

Abstract: A processing device is provided which comprises memory configured to store data and a processor configured to execute a forward activation of the neural network using a low precision floating point (FP) format, scale up values of numbers represented by the low precision FP format and process the scaled up values of the numbers as non-zero values for the numbers. The processor is configured to scale up the values of one or more numbers, via scaling parameters, to a scaled up value equal to or greater than a floor of a dynamic range of the low precision FP format. The scaling parameters are, for example, static parameters or alternatively, parameters determined during execution of the neural network.

Abstract: In accordance with the described techniques for aggregation and scheduling of accelerator executable tasks, an accelerator device includes a processing element array and a command processor to receive a plurality of fibers each including multiple tasks and dependencies between the multiple tasks. The command processor places a first fiber in a sleep pool based on a first task within the first fiber having an unresolved dependency, and the command processor further places a second fiber in a ready pool based on a second task within the second fiber having a resolved dependency. Based on the second fiber being in the ready pool, the command processor launches the second task to be executed by the processing element array.

Abstract: Systems and methods are disclosed for voltage droop mitigation associated with a voltage rail that supplies power to circuitry of a chiplet. Techniques disclosed include detecting an upcoming transmission of data packets that are to be transmitted through a physical layer of the chiplet. Then, before transmitting the data packets through the physical layer, throttling a rate of bandwidth utilization in the physical layer and transmitting, by the controller, the data packets through the physical layer.

Abstract: In accordance with the described techniques for leveraging processing in memory registers as victim buffers, a computing device includes a memory, a processing in memory component having registers for data storage, and a memory controller having a victim address table that includes at least one address of a row of the memory that is stored in the registers. The memory controller receives a request to access the row of the memory and accesses data of the row from the registers based on the address of the row being included in the victim address table.