Abstract: Embodiments described herein provide a processing apparatus comprising compute circuitry to generate neural network data for a convolutional neural network (CNN) and write the neural network data to a memory buffer. The compute circuitry additionally includes a direct memory access (DMA) controller including a hardware codec having encode circuitry and a decode circuitry. The DMA controller reads the neural network data from the memory buffer, encode the neural network data via the encode circuit, writes encoded neural network data to a memory device coupled with the processing apparatus, writes metadata for the encoded neural network data to the memory device coupled with the processing apparatus, and decodes encoded neural network data via the decode circuit in response to a request from the compute circuitry.

Abstract: Embodiments described herein provide a processing apparatus comprising compute circuitry to generate neural network data for a convolutional neural network (CNN) and write the neural network data to a memory buffer. The compute circuitry additionally includes a direct memory access (DMA) controller including a hardware codec having encode circuitry and a decode circuitry. The DMA controller reads the neural network data from the memory buffer, encode the neural network data via the encode circuit, writes encoded neural network data to a memory device coupled with the processing apparatus, writes metadata for the encoded neural network data to the memory device coupled with the processing apparatus, and decodes encoded neural network data via the decode circuit in response to a request from the compute circuitry.

Abstract: An apparatus to facilitate execution of non-linear functions operations is disclosed. The apparatus comprises accelerator circuitry including a compute grid having a plurality of processing elements to execute neural network computations, store values resulting from the neural network computations, and perform piecewise linear (PWL) approximations of one or more non-linear functions using the stored values as input data.

Abstract: Hardware accelerators for accelerated grouped convolution operations. A first buffer of a hardware accelerator may receive a first row of an input feature map (IFM) from a memory. A first group comprising a plurality of tiles may receive a first row of the IFM. A plurality of processing elements of the first group may compute a portion of a first row of an output feature map (OFM) based on the first row of the IFM and a kernel. A second buffer of the accelerator may receive a third row of the IFM from the memory. A second group comprising a plurality of tiles may receive the third row of the IFM. A plurality of processing elements of the second group may compute a portion of a third row of the OFM based on the third row of the IFM and the kernel as part of a grouped convolution operation.

Abstract: One embodiment provides a compute apparatus to perform machine learning operations, the compute apparatus comprising a hardware accelerator including a compute unit to perform a Winograd convolution, the compute unit configurable to perform the Winograd convolution for a first kernel size using a transform associated with a second kernel size.

Abstract: Embodiments described herein provide a processing apparatus comprising compute circuitry to generate neural network data for a convolutional neural network (CNN) and write the neural network data to a memory buffer. The compute circuitry additionally includes a direct memory access (DMA) controller including a hardware codec having encode circuitry and a decode circuitry. The DMA controller reads the neural network data from the memory buffer, encode the neural network data via the encode circuit, writes encoded neural network data to a memory device coupled with the processing apparatus, writes metadata for the encoded neural network data to the memory device coupled with the processing apparatus, and decodes encoded neural network data via the decode circuit in response to a request from the compute circuitry.

Abstract: Embodiments described herein provide a processing apparatus comprising compute logic to generate neural network data for a convolutional neural network (CNN) and write the neural network data to a memory buffer. The compute logic additionally includes a direct memory access (DMA) controller including a hardware codec having an encode unit and a decode unit, the DMA controller to read the neural network data from the memory buffer, encode the neural network data via the encode unit, write encoded neural network data to a memory device coupled with the processing apparatus, write metadata for the encoded neural network data to the memory device coupled with the processing apparatus, and decode encoded neural network data via the decode unit in response to a request from the compute logic.

Abstract: One embodiment provides a compute apparatus to perform machine learning operations, the compute apparatus comprising a hardware accelerator including a compute unit to perform a Winograd convolution, the compute unit configurable to perform the Winograd convolution for a first kernel size using a transform associated with a second kernel size.

Abstract: An apparatus to facilitate execution of non-linear functions operations is disclosed. The apparatus comprises accelerator circuitry including a compute grid having a plurality of processing elements to execute neural network computations, store values resulting from the neural network computations, and perform piecewise linear (PWL) approximations of one or more non-linear functions using the stored values as input data.

Abstract: An apparatus to facilitate acceleration of machine learning operations is disclosed. The apparatus comprises accelerator circuitry including a first set of processing elements to perform first computations including matrix multiplication operations, a second set of processing elements to perform second computations including sum of elements of weights and offset multiply operations and a third set of processing elements to perform third computations including sum of elements of inputs and offset multiply operations, wherein the second and third computations are performed in parallel with the first computations.

Abstract: Embodiments described herein provide a processing apparatus comprising compute logic to generate output feature map data for a convolutional neural network (CNN) and write the feature map data to a memory buffer; a direct memory access (DMA) controller including a feature map encoder, the DMA controller to read the feature map data from the memory buffer, encode the feature map data using one of multiple encode algorithms, and write encoded feature map data to memory coupled with the processing apparatus; and wherein the compute logic is to read the encoded feature map data from the memory in an encoded format and decode the encoded feature map data while reading the encoded feature map data.

Abstract: Hardware accelerators for accelerated grouped convolution operations. A first buffer of a hardware accelerator may receive a first row of an input feature map (IFM) from a memory. A first group comprising a plurality of tiles may receive a first row of the IFM. A plurality of processing elements of the first group may compute a portion of a first row of an output feature map (OFM) based on the first row of the IFM and a kernel. A second buffer of the accelerator may receive a third row of the IFM from the memory. A second group comprising a plurality of tiles may receive the third row of the IFM. A plurality of processing elements of the second group may compute a portion of a third row of the OFM based on the third row of the IFM and the kernel as part of a grouped convolution operation.

Abstract: A mechanism is described for facilitating efficient memory layout for enabling smart data compression in machine learning environments. A method of embodiments, as described herein, includes facilitating dividing an initial tile representing an image into primary multiple tiles such that each tile of the primary multiple tiles is regarded as an independent image as processed by one or more processors of a computing device. The method may further include computing the primary multiple tiles into secondary multiple tiles compatible in size of a local buffer. The method may further include merging the multiple secondary multiple tiles into a final tile representing the image, and compressing the final tile.

Abstract: An apparatus to facilitate acceleration of machine learning operations is disclosed. The apparatus comprises accelerator circuitry including a first set of processing elements to perform first computations including matrix multiplication operations, a second set of processing elements to perform second computations including sum of elements of weights and offset multiply operations and a third set of processing elements to perform third computations including sum of elements of inputs and offset multiply operations, wherein the second and third computations are performed in parallel with the first computations.

Abstract: Embodiments described herein provide a processing apparatus comprising compute logic to generate neural network data for a convolutional neural network (CNN) and write the neural network data to a memory buffer. The compute logic additionally includes a direct memory access (DMA) controller including a hardware codec having an encode unit and a decode unit, the DMA controller to read the neural network data from the memory buffer, encode the neural network data via the encode unit, write encoded neural network data to a memory device coupled with the processing apparatus, write metadata for the encoded neural network data to the memory device coupled with the processing apparatus, and decode encoded neural network data via the decode unit in response to a request from the compute logic.

Abstract: A mechanism is described for facilitating efficient memory layout for enabling smart data compression in machine learning environments. A method of embodiments, as described herein, includes facilitating dividing an initial tile representing an image into primary multiple tiles such that each tile of the primary multiple tiles is regarded as an independent image as processed by one or more processors of a computing device. The method may further include computing the primary multiple tiles into secondary multiple tiles compatible in size of a local buffer. The method may further include merging the multiple secondary multiple tiles into a final tile representing the image, and compressing the final tile.

Abstract: One embodiment provides a compute apparatus to perform machine learning operations, the compute apparatus comprising a hardware accelerator including a compute unit to perform a Winograd convolution, the compute unit configurable to perform the Winograd convolution for a first kernel size using a transform associated with a second kernel size.

Abstract: Embodiments described herein provide a processing apparatus comprising compute logic to generate output feature map data for a convolutional neural network (CNN) and write the feature map data to a memory buffer; a direct memory access (DMA) controller including a feature map encoder, the DMA controller to read the feature map data from the memory buffer, encode the feature map data using one of multiple encode algorithms, and write encoded feature map data to memory coupled with the processing apparatus; and wherein the compute logic is to read the encoded feature map data from the memory in an encoded format and decode the encoded feature map data while reading the encoded feature map data.

Abstract: In one embodiment, an apparatus comprises: a controller to communicate data having a format according to a first communication protocol, the controller comprising a Mobile Industry Processor Interface (MIPI)-compatible controller; an interface circuit coupled to the controller to receive the data, convert the data and communicate the converted data to a physical unit of a second communication protocol, the converted data having a format according to the second communication protocol; and the physical unit coupled to the interface circuit to receive and serialize the converted data and output the serialized converted data to a destination. Other embodiments are described and claimed.

Abstract: An automatic phase detection circuit for generating an internal synchronization signal when two clock input signals achieve a certain phase relationship. No external reference signal is required. The logic state of one clock is sampled on the active edge of the other clock and stored in a shift register. The content of the shift register is compared to a pre-defined signature and a sync signal is generated when the content matches the pre-defined signature. A mask register may be used to define which bits of the shift register and pre-defined signature are compared.