Abstract: Implementations described herein identify and exploit opportunities for offloading search-time and/or index-time operations to programmed offloading hardware accelerators (POHAs). An event-based data intake and query system is implemented in an enterprise core that is in communication with the POHAs over network interfaces. The system receives search requests associated with search-time operations classified into off-loadable operations and non-off-loadable operations. Non-off-loadable operations are distributed to local processing resources, and off-loadable operations are distributed to the POHAs for offloaded processing. The system can post-process both the locally processed and offload-processed results to generate search results responsive to at least some of the received search requests.

Abstract: Systems and methods of propagating data within an integrated circuit includes: identifying a coarse data propagation path for distinct subsets of data of an input dataset that includes: setting inter-core data movements for the distinct subsets of data, the inter-core data movements defining a predetermined propagation of a given subset of data between two or more of a plurality of cores of an integrated circuit array of the integrated circuit; identifying a granular data propagation path for each distinct subset of data that includes: setting intra-core data movements for each distinct subset of data, the intra-core data movements defining a predetermined propagation of the given subset of data within one or more of the plurality of cores of the integrated circuit array of the integrated circuit; enabling a flow of the input dataset within the integrated circuit based on the coarse data propagation path and the granular propagation path.

Abstract: An accelerated processor structure on a programmable integrated circuit device includes a processor and a plurality of configurable digital signal processors (DSPs). Each configurable DSP includes a circuit block, which in turn includes a plurality of multipliers. The accelerated processor structure further includes a first bus to transfer data from the processor to the configurable DSPs, and a second bus to transfer data from the configurable DSPs to the processor.

Abstract: A method includes incrementing a counter with transmission of a process data from a first processor to a second processor, periodically decrementing the counter, if the counter is greater than a predetermined floor threshold value, wherein a period is a predetermined time interval; and stalling the first processor, if the counter is above a configurable load threshold value, so as to re-schedule the transmission of the process data from the first processor to the second processor.

Abstract: In an embodiment, the present invention includes a processor having an execution logic to execute instructions and a control transfer termination (CTT) logic coupled to the execution logic. This logic is to cause a CTT fault to be raised if a target instruction of a control transfer instruction is not a CTT instruction. Other embodiments are described and claimed.

Abstract: According to some example embodiments of the present disclosure, in a method for a memory lookup mechanism in a high-bandwidth memory system, the method includes: using a memory die to conduct a multiplication operation using a lookup table (LUT) methodology by accessing a LUT, which includes floating point operation results, stored on the memory die; sending, by the memory die, a result of the multiplication operation to a logic die including a processor and a buffer; and conducting, by the logic die, a matrix multiplication operation using computation units.

Abstract: The present disclosure includes apparatuses and methods related to mask patterns generated in memory from seed vectors. An example method includes performing operations on a plurality of data units of a seed vector and generating, by performance of the operations, a vector element in a mask pattern.

Abstract: A system may include a plurality of processors and a coprocessor. A plurality of coprocessor context priority registers corresponding to a plurality of contexts supported by the coprocessor may be included. The plurality of processors may use the plurality of contexts, and may program the coprocessor context priority register corresponding to a context with a value specifying a priority of the context relative to other contexts. An arbiter may arbitrate among instructions issued by the plurality of processors based on the priorities in the plurality of coprocessor context priority registers. In one embodiment, real-time threads may be assigned higher priorities than bulk processing tasks, improving bandwidth allocated to the real-time threads as compared to the bulk tasks.

Abstract: The present application discloses a computing device that can provide a low-power, highly capable computing platform for computational imaging. The computing device can include one or more processing units, for example one or more vector processors and one or more hardware accelerators, an intelligent memory fabric, a peripheral device, and a power management module. The computing device can communicate with external devices, such as one or more image sensors, an accelerometer, a gyroscope, or any other suitable sensor devices.

Abstract: Example embodiments of the present application provide an instruction executing method and apparatus, an electronic device, and a computer-readable storage medium that may be applied in the field of artificial intelligence. The instruction executing method may include: executing an instruction sequence that includes memory instructions and non-memory instructions, the instructions in the sequence executed starting to be executed in order; determining that execution of a first memory instruction needs to be completed before a second memory instruction starts to be executed, the second memory instruction being a next memory instruction following the first memory instruction in the instruction sequence; and executing non-memory instructions between the first memory instruction and the second memory instruction without executing the second memory instruction, during a cycle of executing the first memory instruction.

Abstract: Technology for fusing certain load instructions and compare-immediate instructions in a computer processor having a load-store architecture with respect to transferring data between memory and registers of the computer processor. In some embodiments the load and compare-immediate instructions are consecutive. In some embodiments, the instructions are only merged if: (i) the respective RA and RT fields of the two instructions match; (ii) the immediate field of the compare-immediate instruction has a certain value, or falls within a range of certain values; and/or (iii) the instructions are received in a consecutive manner.

Abstract: Some embodiments of the present disclosure provide an associatively indexed circular buffer (ACB). The ACB may be viewed as a dynamically allocatable memory structure that offers in-order data access (say, first-in-first-out, or “FIFO”) or random order data access at a fixed, relatively low latency. The ACB includes a data store of non-contiguous storage. To manage the pushing of data to, and popping data from, the data store, the ACB includes a contiguous pointer generator, a content addressable memory (CAM) and a free pool.

Abstract: Methods and systems for executing an application data flow graph on a set of computational nodes are disclosed. The computational nodes can each include a programmable controller from a set of programmable controllers, a memory from a set of memories, a network interface unit from a set of network interface units, and an endpoint from a set of endpoints. A disclosed method comprises configuring the programmable controllers with instructions. The method also comprises independently and asynchronously executing the instructions using the set of programmable controllers in response to a set of events exchanged between the programmable controllers themselves, between the programmable controllers and the network interface units, and between the programmable controllers and the set of endpoints. The method also comprises transitioning data in the set of memories on the computational nodes in accordance with the application data flow graph and in response to the execution of the instructions.

Abstract: A system parses a very long instruction word (VLIW) to obtain an execution parameter. The system obtains a first sliding window width count, a first sliding window height count, a first feature map width count, and a first feature map height count that correspond to first target data. In accordance with a determination that the first sliding window width count falls within the sliding window width range, the first sliding window height count falls within the sliding window height range, (the first feature map width count falls within the feature map width range, and the first feature map height count falls within the feature map height range, the system determines an offset of the first target data. The system also obtains a starting address of the first target data, and adds the starting address to the offset to obtain a first target address of the first target data.

Abstract: A method for parallel processing of a data stream is provided. In the method, a data stream that includes a plurality of segments is received. A split operation is performed on the data stream based on a split buffer to split the plurality of segments into N sub-streams. Each of the N sub-streams includes one or more segments of the plurality of segments, the N being a positive integer. The split buffer includes an input indexed first in first out (iFIFO) buffer, the input iFIFO buffer being configured to receive the plurality of segments of the data stream and output the plurality of segments to N sub-input iFIFO buffers to generate the N sub-streams. N sub-processing tasks are performed on the N sub-streams to generate N processed sub-streams.

Abstract: A processor core executes a first process. The first process is associated with a first context tag that is generated based on context information controlled by an operating system or hypervisor of the processing system. A branch prediction structure selectively provides the processor core with access to an entry in the branch prediction structure based on the first context tag and a second context tag associated with the entry. The branch prediction structure selectively provides the processor core with access to the entry in response to the first process executing a branch instruction. Tagging entries in the branch prediction structure reduces, or eliminates, aliasing between information used to predict branches taken by different processes at a branch instruction.

Abstract: A processing element (PE) of a systolic array can perform neural networks computations on two or more data elements of an input data set using the same weight. Thus, two or more output data elements corresponding to an output data set may be generated. Based on the size of the input data set and an input data type, the systolic array can process a single data element or multiple data elements in parallel.

Abstract: Disclosed Methods, Apparatus, and articles of manufacture to dynamically enable and/or disable prefetchers are disclosed. An example apparatus include an interface to access telemetry data, the telemetry data corresponding to a counter of a core in a central processing unit, the counter corresponding to a first phase of a workload executed at the central processing unit; a prefetcher state selector to select a prefetcher state for a subsequent phase based on the telemetry data; and the interface to instruct the core in the central processing unit to operate in the subsequent phase according to the prefetcher state.

Abstract: In a method for parallel processing of a data stream, a processing task is received to process the data stream that includes a plurality of segments. A split operation is performed on the data stream to split the plurality of segments into N sub-streams. Each of the N sub-streams includes one or more segments of the plurality of segments. The N is a positive integer. N sub-processing tasks are performed on the N sub-streams to generate N processed sub-streams. A merge operation is performed on the N processed sub-streams based on a merge buffer to generate a merged output data stream. The merge buffer includes an output iFIFO buffer and N sub-output iFIFO buffers coupled to the output iFIFO buffer. The merged output data stream is identical to an output data stream that is generated when the processing task is applied directly to the data stream without the split operation.

Abstract: One embodiment provides for a compute apparatus comprising a decode unit to decode a single instruction into a decoded instruction that specifies multiple operands including a multi-bit input value and a ternary weight associated with a neural network and an arithmetic logic unit including a multiplier, an adder, and an accumulator register. To execute the decoded instruction, the multiplier is to perform a multiplication operation on the multi-bit input based on the ternary weight to generate an intermediate product and the adder is to add the intermediate product to a value stored in the accumulator register and update the value stored in the accumulator register.