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 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: 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: 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: 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: 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: 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: 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: 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: 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.

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: A clock driver with duty cycle correction includes a first driver circuit, a second driver circuit, and a correction logic circuit. The first driver circuit performs duty cycle correction on a clock input signal and has parameters selected for a first frequency range of the clock input signal. The second driver circuit is nested with the first driver circuit and performs duty cycle correction on the clock input signal with parameters selected for a second frequency range of the clock input signal lower than the first frequency range. The correction logic circuit provides correction signals to a selected one of the first driver circuit and the second driver circuit. The clock driver provides a duty cycle corrected clock signal from the selected one of the first driver circuit and the second driver circuit based on a selected frequency range of the clock input signal.

Abstract: A data processing system includes a plurality of coherent masters, a plurality of coherent slaves, and a coherent data fabric. The coherent data fabric has upstream ports coupled to the plurality of coherent masters and downstream ports coupled to the plurality of coherent slaves for selectively routing accesses therebetween. The coherent data fabric includes a probe filter and a directory cleaner. The probe filter is associated with at least one of the downstream ports and has a plurality of entries that store information about each entry. The directory cleaner periodically scans the probe filter and selectively removes a first entry from the probe filter after the first entry is scanned.

Abstract: A memory controller includes a command queue, a memory interface queue, at least one storage queue, and a replay control circuit. The command queue has a first input for receiving memory access commands. The memory interface queue receives commands selected from the command queue and couples to a heterogeneous memory channel which is coupled to at least one non-volatile storage class memory (SCM) module. The at least one storage queue stores memory access commands that are placed in the memory interface queue. The replay control circuit detects that an error has occurred requiring a recovery sequence, and in response to the error, initiates the recovery sequence. In the recovery sequence, the replay control circuit transmits selected memory access commands from the at least one storage queue by grouping non-volatile read commands together separately from all pending volatile reads, volatile writes, and non-volatile writes.

Abstract: Techniques for performing multi-sample anti-aliasing operations are provided. The techniques include detecting an instruction for a multi-sample anti-aliasing load operation; determining a sampling rate of source data for the load operation, data storage format of the source data, and loading mode indicating whether the load operation requests same or different color components, or depth data; and based on the determined sampling rate, data storage format, and loading mode, load data from a multi-sample source into a register.

Abstract: A computing device is provided which comprises memory and a processor in communication with the memory. The processor is configured to autonomously acquire input parameter values, comprising one of monitored device input parameter values from a component of the computing device and monitored user input parameter values. The processor is also configured to select, from a plurality of modes of operation, a mode of operation comprising parameter settings which are determined based on the acquired input parameter values, each of the plurality of modes of operation comprising different parameter settings configured to control the computing device to operate at a different level of performance. The processor is also configured to control operation of the computing device by tuning the parameter settings of the computing device according to the selected mode of operation comprising the determined parameter settings.

Abstract: An exemplary system includes and/or represents an agent and a machine check architecture. In one example, the machine check architecture includes and/or represents at least one circuit configured to report errors via at least one reporting register. In this example, the machine check architecture also includes and/or represents at least one error-injection register configured to cause the circuit to inject at least one fabricated error report into the reporting register in response to a write operation performed by the agent on at least one bit of the error-injection register. Various other devices, systems, and methods are also disclosed.

Abstract: A data processor includes a plurality of requestors, a plurality of responders, and a data fabric. The data fabric is for routing requests between the plurality of requestors and the plurality of responders and has a plurality of non-operational power states including a normal C-state and a light-weight C-state. The light-weight C-state has lower entry and exit latencies than the normal C-state. The data fabric monitors traffic through the data fabric and places the data fabric in the light-weight C-state in response to detecting an idle traffic state.

Abstract: A disclosed technique includes clock gating a plurality of data elements of a first clock domain of a scan dump network; outputting data from a plurality of data elements of a second clock domain of the scan dump network; clock gating the plurality of data elements of the second clock domain; and outputting data from the plurality of data elements of the first clock domain.

Abstract: A method for enhanced forward rendering is disclosed which includes a depth pre-pass, light culling and a final shading. The depth pre-pass minimizes the cost of final shading by avoiding high pixel overdraw. The light culling stage calculates a list of light indices overlapping a pixel. The light indices are calculated on a per-tile basis, where the screen has been split into units of tiles. The final shading evaluates materials using information stored for each light. The forward rendering method may be executed on a processor, such as a single graphics processing unit (GPU) for example.