Abstract: A computer model is trained to classify regions of a space (e.g., a pixel of an image or a voxel of a point cloud) according to a multi-label classification. To improve the model's accuracy, the model's self-confidence is determined with respect to its own predictions of regions in a training space. The self-confidence is determined based on the class predictions, such as a difference between the highest-predicted class and a second-highest-predicted class. When these are similar, it may reflect areas for potential improvement by focusing training on these low-confidence areas. Additional training may be performed by including modified training data in subsequent training iterations that focuses on low-confidence areas. As another example, additional training may be performed using the self-confidence to modify a classification loss used to refine parameters of the model.

Abstract: Systems, apparatuses and methods may provide for technology that decodes data via an instruction that indicates a number of rulebooks to be processed, an input feature size, an output feature size, and a plurality of feature map base addresses, rearranges spatially distributed voxel output feature maps in the decoded data based on weight planes, and performs a channel-wise multiply-accumulate (MAC) operation on the rearranged spatially distributed voxel output feature maps to obtain an output, wherein the channel-wise MAC operation is performed as partial accumulations by a plurality of processing elements.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve in-memory multiply and accumulate operations. An example apparatus includes a first multiplexer in a subarray of memory, the first multiplexer to receive first values representative of a column of a lookup table (LUT) including entries to represent products of four-bit numbers and return second values from an intersection of a row and the column of the LUT based on a first element of a first operand; shift and adder logic in the subarray, the shift and adder logic to shift the second values based on at least one of the first element of the first operand or a first element of a second operand; and accumulation storage in the subarray, the accumulation storage to store at least the shifted second values.

Abstract: Systems, apparatuses and methods provide technology for optimizing processing of sparse data, such as 3D pointcloud data sets. The technology may include generating a locality-aware rulebook based on an input unstructured sparse data set, such as a 3D pointcloud data set, the locality-aware rulebook storing spatial neighborhood information for active voxels in the input unstructured sparse data set, computing an average receptive field (ARF) value based on the locality aware rulebook, and determining, from a plurality of tile size and loop order combinations, a tile size and loop order combination for processing the unstructured sparse data based on the computed ARF value. The technology may also include providing the locality-aware rulebook and the tile size and loop order combination to a compute engine such as a neural network, the compute engine to process the unstructured sparse data using the locality aware rulebook and the tile size and loop order combination.

Abstract: An apparatus to facilitate accelerating neural networks with low precision-based multiplication and exploiting sparsity in higher order bits is disclosed. The apparatus includes a processor comprising a re-encoder to re-encode a first input number of signed input numbers represented in a first precision format as part of a machine learning model, the first input number re-encoded into two signed input numbers of a second precision format, wherein the first precision format is a higher precision format than the second precision format. The processor further includes a multiply-add circuit to perform operations in the first precision format using the two signed input numbers of the second precision format; and a sparsity hardware circuit to reduce computing on zero values at the multiply-add circuit, wherein the processor to execute the machine learning model using the re-encoder, the multiply-add circuit, and the sparsity hardware circuit.

Abstract: A disclosed apparatus to multiply matrices includes a compute engine. The compute engine includes multipliers in a two dimensional array that has a plurality of array locations defined by columns and rows. The apparatus also includes a plurality of adders in columns. A broadcast interconnect between a cache and the multipliers broadcasts a first set of operand data elements to multipliers in the rows of the array. A unicast interconnect unicasts a second set of operands between a data buffer and the multipliers. The multipliers multiply the operands to generate a plurality of outputs, and the adders add the outputs generated by the multipliers.

Abstract: Systems and methods for a hardware accelerated matrix decomposition matrix decomposition circuit are described herein. This matrix decomposition circuit splits matrix decomposition operations into parallel operation circuits and serial operation circuits, and joins the parallel and serial operation circuits using specific dependency handling logic for efficient parallel execution. This provides fast matrix decomposition with low power consumption, reduced memory footprint, and reduced memory bandwidth.

Abstract: Systems and methods for matrix-solve applications include a memory-optimized hardware acceleration (HWA) solution with scalable architecture (i.e. specialized circuitry) for HWA matrix-solve operations. The matrix-solve solutions described herein may include a scalable hardware architecture with parallel processing (e.g., “within column” processing), which provides the ability to compute several output values in parallel. The HWA matrix-solve solutions described herein may include simultaneous multi-column processing, which provides a lower execution cycle count and a reduced total number of memory accesses. This HWA matrix-solve provides a low latency and energy-efficient matrix-solve solutions, which may be used to reduce energy consumption and improve performance in various matrix-based applications, such as computer vision, SLAM, AR/VR/mixed-reality, machine learning, data analytics, and other matrix-based applications.

Abstract: Systems and methods for a hardware accelerated matrix decomposition matrix decomposition circuit are described herein. This matrix decomposition circuit splits matrix decomposition operations into parallel operation circuits and serial operation circuits, and joins the parallel and serial operation circuits using specific dependency handling logic for efficient parallel execution. This provides fast matrix decomposition with low power consumption, reduced memory footprint, and reduced memory bandwidth.

Abstract: Systems and methods for matrix-solve applications include a memory-optimized hardware acceleration (HWA) solution with scalable architecture (i.e. specialized circuitry) for HWA matrix-solve operations. The matrix-solve solutions described herein may include a scalable hardware architecture with parallel processing (e.g., “within column” processing), which provides the ability to compute several output values in parallel. The HWA matrix-solve solutions described herein may include simultaneous multi-column processing, which provides a lower execution cycle count and a reduced total number of memory accesses. This HWA matrix-solve provides a low latency and energy-efficient matrix-solve solutions, which may be used to reduce energy consumption and improve performance in various matrix-based applications, such as computer vision, SLAM, AR/VR/mixed-reality, machine learning, data analytics, and other matrix-based applications.