Abstract: Methods, apparatus, systems, and articles of manufacture to load data into an accelerator are disclosed. An example apparatus includes data provider circuitry to load a first section and an additional amount of compressed machine learning parameter data into a processor engine. Processor engine circuitry executes a machine learning operation using the first section of compressed machine learning parameter data. A compressed local data re-user circuitry determines if a second section is present in the additional amount of compressed machine learning parameter data. The processor engine circuitry executes a machine learning operation using the second section when the second section is present in the additional amount of compressed machine learning parameter data.

Abstract: Methods and systems include a neural network system that includes a neural network accelerator. The neural network accelerator includes multiple processing engines coupled together to perform arithmetic operations in support of an inference performed using the deep neural network system. The neural network accelerator also includes a schedule-aware tensor data distribution circuitry or software that is configured to load tensor data into the multiple processing engines in a load phase, extract output data from the multiple processing engines in an extraction phase, reorganize the extracted output data, and store the reorganized extracted output data to memory.

Abstract: Methods, systems, articles of manufacture, and apparatus are disclosed to decode zero-value-compression data vectors. An example apparatus includes: a buffer monitor to monitor a buffer for a header including a value indicative of compressed data; a data controller to, when the buffer includes compressed data, determine a first value of a sparse select signal based on (1) a select signal and (2) a first position in a sparsity bitmap, the first value of the sparse select signal corresponding to a processing element that is to process a portion of the compressed data; and a write controller to, when the buffer includes compressed data, determine a second value of a write enable signal based on (1) the select signal and (2) a second position in the sparsity bitmap, the second value of the write enable signal corresponding to the processing element that is to process the portion of the compressed data.

Abstract: Methods, systems, articles of manufacture, and apparatus are disclosed to decode zero-value-compression data vectors. An example apparatus includes: a buffer monitor to monitor a buffer for a header including a value indicative of compressed data; a data controller to, when the buffer includes compressed data, determine a first value of a sparse select signal based on (1) a select signal and (2) a first position in a sparsity bitmap, the first value of the sparse select signal corresponding to a processing element that is to process a portion of the compressed data; and a write controller to, when the buffer includes compressed data, determine a second value of a write enable signal based on (1) the select signal and (2) a second position in the sparsity bitmap, the second value of the write enable signal corresponding to the processing element that is to process the portion of the compressed data.

Abstract: Systems, apparatuses and methods may provide for replacing floating point matrix multiplication operations with an approximation algorithm or computation in applications that involve sparse codes and neural networks. The system may replace floating point matrix multiplication operations in sparse code applications and neural network applications with an approximation computation that applies an equivalent number of addition and/or subtraction operations.

Abstract: Systems, apparatuses and methods may provide for replacing floating point matrix multiplication operations with an approximation algorithm or computation in applications that involve sparse codes and neural networks. The system may replace floating point matrix multiplication operations in sparse code applications and neural network applications with an approximation computation that applies an equivalent number of addition and/or subtraction operations.

Abstract: Systems, apparatuses and methods may provide for replacing floating point matrix multiplication operations with an approximation algorithm or computation in applications that involve sparse codes and neural networks. The system may replace floating point matrix multiplication operations in sparse code applications and neural network applications with an approximation computation that applies an equivalent number of addition and/or subtraction operations.

Abstract: Systems, apparatuses and methods may provide for multi-precision multiply-accumulate (MAC) technology that includes a plurality of arithmetic blocks, wherein the plurality of arithmetic blocks each contain multiple multipliers, and wherein the logic is to combine multipliers one or more of within each arithmetic block or across multiple arithmetic blocks. In one example, one or more intermediate multipliers are of a size that is less than precisions supported by arithmetic blocks containing the one or more intermediate multipliers.

Abstract: Methods, apparatus, systems, and articles of manufacture to load data into an accelerator are disclosed. An example apparatus includes data provider circuitry to load a first section and an additional amount of compressed machine learning parameter data into a processor engine. Processor engine circuitry executes a machine learning operation using the first section of compressed machine learning parameter data. A compressed local data re-user circuitry determines if a second section is present in the additional amount of compressed machine learning parameter data. The processor engine circuitry executes a machine learning operation using the second section when the second section is present in the additional amount of compressed machine learning parameter data.

Abstract: Embodiments of the present disclosure are directed toward techniques and configurations enhancing the performance of hardware (HW) accelerators. Disclosed embodiments include static MAC scaling arrangement, which includes architectures and techniques for scaling the performance per unit of power and performance per area of HW accelerators. Disclosed embodiments also include dynamic MAC scaling arrangement, which includes architectures and techniques for dynamically scaling the number of active multiply-and-accumulate (MAC) within an HW accelerator based on activation and weight sparsity. Other embodiments may be described and/or claimed.

Abstract: Systems, apparatuses and methods identify a plurality of registers that are associated with a system-on-chip. The plurality of registers includes a first portion dedicated to write operations and a second portion dedicated to read operations. The technology writes data to the first portion of the plurality of registers, and transfers the data from the first portion to the second portion.

Abstract: Systems, apparatuses and methods may provide for technology that identify an assignment of weights of a workload to a plurality of processing elements, where the workload is to be associated with a neural network. The technology generates a representation that is to represent whether each of the weights is a zero value or a non-zero value. The technology further stores the representation into partitions of a storage structure based on the assignment of the weights, where the partitions are each to be dedicated to a different one of the processing elements.

Abstract: Systems, apparatuses and methods may provide for replacing floating point matrix multiplication operations with an approximation algorithm or computation in applications that involve sparse codes and neural networks. The system may replace floating point matrix multiplication operations in sparse code applications and neural network applications with an approximation computation that applies an equivalent number of addition and/or subtraction operations.

Abstract: Methods and systems include a neural network system that includes a neural network accelerator comprising. The neural network accelerator includes multiple processing engines coupled together to perform arithmetic operations in support of an inference performed using the deep neural network system. The neural network accelerator also includes a schedule-aware tensor data distribution circuitry or software that is configured to load tensor data into the multiple processing engines in a load phase, extract output data from the multiple processing engines in an extraction phase, reorganize the extracted output data, and store the reorganized extracted output data to memory.

Abstract: Systems, apparatuses and methods may provide for replacing floating point matrix multiplication operations with an approximation algorithm or computation in applications that involve sparse codes and neural networks. The system may replace floating point matrix multiplication operations in sparse code applications and neural network applications with an approximation computation that applies an equivalent number of addition and/or subtraction operations.

Abstract: Methods, systems, articles of manufacture, and apparatus are disclosed to decode zero-value-compression data vectors. An example apparatus includes: a buffer monitor to monitor a buffer for a header including a value indicative of compressed data; a data controller to, when the buffer includes compressed data, determine a first value of a sparse select signal based on (1) a select signal and (2) a first position in a sparsity bitmap, the first value of the sparse select signal corresponding to a processing element that is to process a portion of the compressed data; and a write controller to, when the buffer includes compressed data, determine a second value of a write enable signal based on (1) the select signal and (2) a second position in the sparsity bitmap, the second value of the write enable signal corresponding to the processing element that is to process the portion of the compressed data.

Abstract: Example apparatus disclosed herein include an array of processor elements, the array including rows each having a first number of processor elements and columns each having a second number of processor elements. Disclosed example apparatus also include configuration registers to store descriptors to configure the array to implement a layer of a convolutional neural network based on a dataflow schedule corresponding to one of multiple tensor processing templates, ones of the processor elements to be configured based on the descriptors to implement the one of the tensor processing templates to operate on input activation data and filter data associated with the layer of the convolutional neural network to produce output activation data associated with the layer of the convolutional neural network. Disclosed example apparatus further include memory to store the input activation data, the filter data and the output activation data associated with the layer of the convolutional neural network.

Abstract: Systems, apparatuses and methods may provide for replacing floating point matrix multiplication operations with an approximation algorithm or computation in applications that involve sparse codes and neural networks. The system may replace floating point matrix multiplication operations in sparse code applications and neural network applications with an approximation computation that applies an equivalent number of addition and/or subtraction operations.

Abstract: In an embodiment, a method is provided. The method includes managing user-level threads on a first instruction sequencer in response to executing user-level instructions on a second instruction sequencer that is under control of an application level program. A first user-level thread is run on the second instruction sequencer and contains one or more user level instructions. A first user level instruction has at least 1) a field that makes reference to one or more instruction sequencers or 2) implicitly references with a pointer to code that specifically addresses one or more instruction sequencers when the code is executed.

Abstract: Embodiments of the invention provide a method of creating, based on an operating-system-scheduled thread running on an operating-system-visible sequencer and using an instruction set extension, a persistent user-level thread to run on an operating-system-sequestered sequencer independently of context switch activities on the operating-system-scheduled thread. The operating-system-scheduled thread and the persistent user-level thread may share a common virtual address space. Embodiments of the invention may also provide a method of causing a service thread running on an additional operating-system-visible sequencer to provide operating system services to the persistent user-level thread. Embodiments of the invention may further provide apparatus, system, and machine-readable medium thereof.