Abstract: Systems, apparatuses and methods provide technology that compresses first data based on a first compression scheme to generate second data, where the first data is associated with a first machine learning model. The technology stores the second data into a memory, adjusts a first entry of a lookup table to correspond to the first compression scheme based on the first data being compressed based on the first compression scheme, provide the second data from the memory to processing elements of a processing array during execution of the first machine learning model, and decompresses, at the processing array, the second data based on the lookup table to obtain the first data.

Abstract: Three-dimensional application specific integrated circuit (IC) architecture is described herein. In one aspect, an IC may include a first die including: a first semiconductor layer; a plurality of processing elements (PEs) located on the first semiconductor layer; and a first interface region of the first semiconductor layer, electrically coupled to the plurality of PEs and configured to communicate electrical signals with the plurality of PEs; a second die including: a second semiconductor layer; a plurality of IC elements located on the second semiconductor layer; and a second interface region of the second semiconductor layer, electrically coupled to the plurality of IC elements and configured to communicate electrical signals to the plurality of IC elements, where the first interface region and the second interface region are electrically coupled to each other and configured to transmit electrical signals between the plurality of PEs and the plurality of IC elements.

Abstract: Embodiments include systems, methods, and computer-readable media for memory traffic management across a network of processing engines. An example method includes setting, at a processing engine prior to execution of a processing workload, a credit variable to an initial credit value, adding, at the processing engine during the execution of the processing workload, at a credit incrementing rate, a credit increment value to the credit variable, wherein the adding is omitted if the adding increases a current value of the credit variable above a maximum credit value, detecting, at the processing engine, a memory access request; blocking, at the processing engine, while the current value of the credit variable is less than a size of the memory access request, the memory access request, and issuing, from the processing engine, when the current value of the credit variable is equal to or greater than a size of the memory access request, the memory access request.

Abstract: Systems, apparatuses and methods provide technology that compresses first data based on a first compression scheme to generate second data, where the first data is associated with a first machine learning model. The technology stores the second data into a memory, adjusts a first entry of a lookup table to correspond to the first compression scheme based on the first data being compressed based on the first compression scheme, provide the second data from the memory to processing elements of a processing array during execution of the first machine learning model, and decompresses, at the processing array, the second data based on the lookup table to obtain the first data.

Abstract: Three-dimensional application specific integrated circuit (IC) architecture is described herein. In one aspect, an IC may include a first die including: a first semiconductor layer; a plurality of processing elements (PEs) located on the first semiconductor layer; and a first interface region of the first semiconductor layer, electrically coupled to the plurality of PEs and configured to communicate electrical signals with the plurality of PEs; a second die including: a second semiconductor layer; a plurality of IC elements located on the second semiconductor layer; and a second interface region of the second semiconductor layer, electrically coupled to the plurality of IC elements and configured to communicate electrical signals to the plurality of IC elements, where the first interface region and the second interface region are electrically coupled to each other and configured to transmit electrical signals between the plurality of PEs and the plurality of IC elements.

Abstract: A system including an array of processing elements, a plurality of periphery crossbars and a plurality of storage components is described. The array of processing elements is interconnected in a grid via a network on an integrated circuit. The periphery crossbars are connected to a plurality of edges of the array of processing elements. The storage components are connected to the periphery crossbars.

Abstract: A system comprises a processor coupled to a plurality of memory units. Each of the plurality of memory units includes a request processing unit and a plurality of memory banks. The processor includes a plurality of processing elements and a communication network communicatively connecting the plurality of processing elements to the plurality of memory units. At least a first processing element of the plurality of processing elements includes a control logic unit and a matrix compute engine. The control logic unit is configured to access data from the plurality of memory units using a dynamically programmable distribution scheme.

Abstract: A system including an array of processing elements, a plurality of periphery crossbars and a plurality of storage components is described. The array of processing elements is interconnected in a grid via a network on an integrated circuit. The periphery crossbars are connected to a plurality of edges of the array of processing elements. The storage components are connected to the periphery crossbars.

Abstract: A system comprises a processor coupled to a plurality of memory units. Each of the plurality of memory units includes a request processing unit and a plurality of memory banks. The processor includes a plurality of processing elements and a communication network communicatively connecting the plurality of processing elements to the plurality of memory units. At least a first processing element of the plurality of processing elements includes a control logic unit and a matrix compute engine. The control logic unit is configured to access data from the plurality of memory units using a dynamically programmable distribution scheme.

Abstract: A processor system comprises a plurality of processing elements. Each processing element includes a corresponding convolution processor unit configured to perform a portion of a groupwise convolution. The corresponding convolution processor unit determines multiplication results by multiplying each data element of a portion of data elements in a convolution data matrix with a corresponding data element in a corresponding groupwise convolution weight matrix. The portion of data elements in the convolution data matrix that are multiplied belong to different channels and different groups. For each specific channel of the different channels, the corresponding convolution processor unit sums together at least some of the multiplication results belonging to the same specific channel to determine a corresponding channel convolution result data element.

Abstract: A system comprises a data input vector unit, a weight input vector unit, and a plurality of calculation units. The data input vector unit is configured to concurrently receive elements of different rows of a first and second data matrix. The weight input vector unit is configured to receive a combined weight vector and at least in part concurrently provide obtained weight elements of a first and second weight matrix to a corresponding first and second group of calculation units. At least one calculation unit of each group of the first and second group of calculation units is configured to multiply elements from the data input vector unit with corresponding elements of the corresponding weight matrix from the weight input vector unit and sum together multiplication results of the corresponding calculation unit to at least in part determine a corresponding element in a first or second convolution result matrix.

Abstract: A processor system comprises a first and second group of registers and a hardware channel convolution processor unit. The first group of registers is configured to store data elements of channels of a portion of a convolution data matrix. Each register stores at least one data element from each channel. The second group of registers is configured to store data elements of convolution weight matrices including a separate convolution weight matrix for each channel. Each register stores at least one data element from each convolution weight matrix. The hardware channel convolution processor unit is configured to multiply each data element in the first group of registers with a corresponding data element in the second group of registers and sum together the multiplication results for each specific channel to determine corresponding channel convolution result data elements in a corresponding channel convolution result matrix.

Abstract: A system comprises a processor and a plurality of memory units. The processor is coupled to each of the plurality of memory units by a plurality of network connections. The processor includes a plurality of processing elements arranged in a two-dimensional array and a corresponding two-dimensional communication network communicatively connecting each of the plurality of processing elements to other processing elements on same axes of the two-dimensional array. Each processing element that is located along a diagonal of the two-dimensional array is configured as a request broadcasting master for a respective group of processing elements located along a same axis of the two-dimensional array.

Abstract: A system comprises a processor coupled to a plurality of memory units. Each of the plurality of memory units includes a request processing unit and a plurality of memory banks. Each request processing unit includes a plurality of decomposition units and a crossbar switch, the crossbar switch communicatively connecting each of the plurality of decomposition units to each of the plurality of memory banks. The processor includes a plurality of processing elements and a communication network communicatively connecting the plurality of processing elements to the plurality of memory units. At least a first processing element of the plurality of processing elements includes a control logic unit and a matrix compute engine. The control logic unit is configured to access the plurality of memory units using a dynamically programmable distribution scheme.

Abstract: A processor system comprises two groups of registers and a hardware channel convolution processor unit. The first group of registers is configured to store data elements of channels of a portion of a convolution data matrix. Each register stores at least one data element from each channel. The second group of registers is configured to store data elements of convolution weight matrices including a separate matrix for each channel. Each register stores at least one data element from each matrix. The hardware channel convolution processor unit is configured to multiply each data element in a first and second portion of the first group of registers with a corresponding data element in the second group of registers to determine corresponding multiplication results and sum together the multiplication results for each specific channel to determine two corresponding channel convolution result data elements in a corresponding channel convolution result matrix.

Abstract: A system comprises a matrix processor unit that includes a first type of register, a group of a second type of registers, and a plurality of calculation units. The first type of register is configured to concurrently store values from different rows of a first matrix. At least a portion of the first type of register is logically divided into groups of elements, and each of the groups corresponds to a different row of the first matrix. Each of the second type of registers is configured to concurrently store values from a plurality of different rows of a second matrix. Each of the calculation units corresponds to one of the second type of registers and is configured to at least in part determine a corresponding element in a result matrix of convoluting the second matrix with the first matrix.

Abstract: A processor system comprises a hardware channel convolution processor unit and dot product processor unit. The channel convolution processor unit is configured to perform depthwise convolution, including by multiplying each data element of a first group of data elements of a convolution data matrix with a corresponding data element of a second group of data elements of a plurality of depthwise convolution weight matrices and summing together, for each specific channel, multiplication results corresponding to the specific channel to determine one corresponding result data element in a corresponding channel convolution result matrix to calculate a portion of depthwise convolution results.

Abstract: A system comprises a data input vector unit, a weight input vector unit, and a plurality of calculation units of a matrix processor unit. The data input vector unit is configured to concurrently receive elements of different rows of a first and second data matrix. The weight input vector unit is configured to receive a combined weight vector and at least in part concurrently provide obtained weight elements of a first and second weight matrix to a corresponding first and second group of calculation units. Each calculation unit of the first and second group of calculation units is configured to multiply elements from the data input vector unit with elements of the corresponding weight matrix from the weight input vector unit and sum together multiplication results of the corresponding calculation unit to at least in part determine a corresponding element in a first or second convolution result matrix.

Abstract: A processor system comprises one or more logic units configured to receive a processor instruction identifying a first floating point number to be multiplied with a second floating point number. The floating point numbers are each decomposed into a group of a plurality of component numbers, wherein a number of bits used to represent each floating point number is greater than a number of bits used to represent any component number in each group of the plurality of component numbers. The component numbers of the first group are multiplied with the component numbers of the second group to determine intermediate multiplication results that are summed together to determine an effective result that represents a result of multiplying the first floating point number with the second floating point number.

Abstract: A processor system comprises one or more logic units configured to receive a processor instruction identifying a first floating point number to be multiplied with a second floating point number. The floating point numbers are each decomposed into a group of a plurality of component numbers, wherein a number of bits used to represent each floating point number is greater than a number of bits used to represent any component number in each group of the plurality of component numbers. The component numbers of the first group are multiplied with the component numbers of the second group to determine intermediate multiplication results that are summed together to determine an effective result that represents a result of multiplying the first floating point number with the second floating point number.