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: Techniques for performing phase detect operations are described. The techniques include obtaining first measurements with a set of half-shield phase-detect sensors; obtaining second measurements with a set of non-phase detect sensors that are not configured as phase-detect sensor; and determining a phase difference based on the first measurements and the second measurements.

Abstract: A disclosed method for making efficient picks of micro-operations for execution includes selecting a first set of micro-operations that are ready for execution during a certain clock cycle. The method also includes selecting a second set of micro-operations that are ready for execution during the certain clock cycle. The method additionally includes replacing one or more of the complex micro-operations included in the first set of micro-operations with one or more simple micro-operations included in the second set of micro-operations due at least in part to a number of complex micro-operations included in the first set of micro-operations exceeding a set of complex resources capable of executing the complex micro-operations. Various other apparatuses, systems, and methods are also disclosed.

Abstract: A data processor is adapted to couple to a memory. The data processor includes a memory operation array, a power engine, and an initialization circuit. The memory operation array includes a command portion and a data portion. The power engine has an input for receiving power state change request signals and an output for providing memory operations responsive to instructions stored in the command portion. The initialization circuit populates the data portion such that consecutive memory operations are separated by an amount corresponding to a predetermined minimum timing parameter.

Abstract: The disclosed system may include a processor configured to encode, using an encoding scheme that reduces a number of bits needed to represent one or more instructions from a set of instructions in an instruction buffer represented by a dependency matrix, a dependency indicating that a child instruction represented in the dependency matrix depends on a parent instruction represented in the dependency matrix. The processor may also be configured to store the encoded dependency in the dependency matrix and dispatch instructions in the instruction buffer based at least on decoding one or more dependencies stored in the dependency matrix for the instructions. Various other methods, systems, and computer-readable media are also disclosed.

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: Methods and systems are disclosed for processing a vector by a vector processor. Techniques disclosed include receiving predicated instructions by a scheduler, each of which is associated with an opcode, a vector of elements, and a predicate. The techniques further include executing the predicated instructions. Executing a predicated instruction includes compressing, based on an index derived from a predicate of the instruction, elements in a vector of the instruction, where the elements in the vector are contiguously mapped, then, after the mapped elements are processed, decompressing the processed mapped elements, where the processed mapped elements are reverse mapped based on the index.

Abstract: Methods and systems are disclosed for managing the power consumed by cores of a system on chip (SoC). Techniques disclosed include obtaining application information that is indicative of an application being executed on the cores, detecting a workload associated with the application, and limiting one or more operating frequencies of the cores responsive to the detection of the workload. Techniques disclosed also include profiling the detected workload and limiting the one or more operating frequencies of the cores based on the profiling.

Abstract: Methods and systems are disclosed for managing performance states of a data fabric of a system on chip (SoC). Techniques disclosed include determining a performance state of the data fabric based on data fabric bandwidth utilizations of respective components of the SoC. A metric, characteristic of a workload centric to cores of the SoC, is derived from hardware counters, and, based on the metric, it is determined whether to alter the performance state.

Abstract: An intermediate representation (IR) controller is described that, for a given intermediate representation (IR) primitive, selects a hardware compute unit of a plurality of hardware compute units. In a non-limiting example, the IR controller receives an input that specifies an IR primitive, a device mask indicating a type of hardware circuitry to be used to process the primitive, and a goal vector specifying a goal in the processing of the primitive. The IR controller also collects data describing power consumption by respective hardware compute units and completion times for processing respective IR primitives. This data is maintained as implementation profiles that describe operation of respective hardware compute units in processing respective IR primitives, e.g., as histograms. The implementation profiles are then leveraged by the IR controller to select hardware compute units for execution of subsequent IR primitives.

Abstract: The disclosed system may include a processor configured to detect that a data unit size for an instruction is smaller than a register. The processor may allocate a first portion of the register to the instruction in a manner that leaves a second portion of the register available for allocating to an additional instruction. The processor may also track the register as a split register. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Systems and methods are disclosed for scheduling a data link training by a controller. The system and method include receiving an indication that a physical layer of a data link is not transferring data and initiating a training process of the physical layer of the data link in response to the indication that the physical layer of the data link is not transferring data. In one aspect, the indication that the physical layer of a data link is not transferring data is an indication that the physical layer of the data link is in a low power state. In another aspect, the indication that the physical layer of a data link is not transferring data is an indication that a data transfer has been completed.

Abstract: A random-access memory (RAM) includes a plurality of memory banks, a memory channel interface circuit, and a metadata processing circuit. The memory channel interface circuit couples to a memory channel adapted for coupling to a memory controller. The metadata processing circuit is connected to the memory channel interface circuit and receiving a poison bit sent over the memory channel associated with a write command and write data for the write command. The RAM, responsive to the poison bit indicating that the write data is poisoned, stores at least one of: the poison bit and a code indicating a value of the poison bit in a selected memory bank.

Abstract: In accordance with described techniques for DRAM row management for processing in memory, a plurality of instructions are obtained for execution by a processing in memory component embedded in a dynamic random access memory. An instruction is identified that last accesses a row of the dynamic random access memory, and a subsequent instruction is identified that first accesses an additional row of the dynamic random access memory. A first command is issued to close the row and a second command is issued to open the additional row after the row is last accessed by the instruction.

Abstract: Techniques for generating a depth map are described. The techniques include obtaining a set of phase difference measurements with a phase detect sensor, and generating a depth map based on the set of phase difference measurements, utilizing a first set of calibration data correlating phase difference measurements with lens defocus data and a second set of calibration data correlating lens positions with object distances.

Abstract: An approach is provided for implementing memory profiling aggregation. A hardware aggregator provides memory profiling aggregation by controlling the execution of a plurality of hardware profilers that monitor memory performance in a system. For each hardware profiler of the plurality of hardware profilers, a hardware counter value is compared to a threshold value. When a threshold value is satisfied, execution of a respective hardware profiler of the plurality of hardware profilers is initiated to monitor memory performance. Multiple hardware profilers of the plurality of hardware profilers may execute concurrently and each generate a result counter value. The result counter values generated by each hardware profiler of the plurality of hardware profilers are aggregated to generate an aggregate result counter value. The aggregate result counter value is stored in memory that is accessible by a software processes for use in optimizing memory-management policy decisions.

Abstract: A system and method for efficiently creating layout for memory bit cells are described. In various implementations, cells of a library use Cross field effect transistors (FETs) that include vertically stacked gate all around (GAA) transistors with conducting channels oriented in an orthogonal direction between them. The channels of the vertically stacked transistors use opposite doping polarities. One or more of these cells use a dual polarity local interconnect power connection to receive a voltage reference level from a backside bus. For example, a power supply reference voltage level is received by a p-type device from a backside bus where the connection traverses both a p-type local interconnect layer and an n-type local interconnect layer.

Abstract: A technique for operating a cache is disclosed. The technique includes recording access data for a first set of memory accesses of a first frame; identifying parameters for a second set of memory accesses of a second frame subsequent to the first frame, based on the access data; and applying the parameters to the second set of memory accesses.

Abstract: Methods, devices, and systems for retrieving information based on cache miss prediction. A prediction that a cache lookup for the information will miss a cache is made based on a history table. The cache lookup for the information is performed based on the request. A main memory fetch for the information is begun before the cache lookup completes, based on the prediction that the cache lookup for the information will miss the cache. In some implementations, the prediction includes comparing a first set of bits stored in the history table with a second set of bits stored in the history table. In some implementations, the prediction includes comparing at least a portion of an address of the request for the information with a set of bits in the history table.

Abstract: The graphics processing unit (GPU) of a processing system transitions to a low-power state between frame rendering operations according to an inter-frame power off process, where GPU state information is stored on retention hardware. The retention hardware can include retention random access memory (RAM) or retention flip-flops. The retention hardware is operable in an active mode and a retention mode, where read/write operations are enabled at the retention hardware in the active mode and disabled in the retention mode, but data stored on the retention hardware is still retained in the retention mode. The retention hardware is placed in the retention state between frame rendering operations. The GPU transitions from its low-power state to its active state upon receiving an indication that a new frame is ready to be rendered and is restored using the GPU state information stored at the retention hardware.