Abstract: An apparatus to facilitate supporting 8-bit floating point format for parallel computing and stochastic rounding operations in a graphics architecture is disclosed. The apparatus includes a processor comprising: a decoder to decode an instruction fetched for execution into a decoded instruction, wherein the decoded instruction is a matrix instruction that is to operate on 8-bit floating point operands to perform a parallel dot product operation; a scheduler to schedule the decoded instruction and provide input data for the 8-bit floating point operands in accordance with an 8-bit floating data format indicated by the decoded instruction; and circuitry to execute the decoded instruction to perform 32-way dot-product using 8-bit wide dot-product layers, each 8-bit wide dot-product layer comprises one or more sets of interconnected multipliers, shifters, and adders, wherein each set of multipliers, shifters, and adders is to generate a dot product of the 8-bit floating point operands.

Abstract: An apparatus to facilitate conversion operations and special value use cases supporting 8-bit floating point format in a graphics architecture is disclosed. The apparatus includes a processor comprising a decoder to decode an instruction fetched for execution into a decoded instruction, wherein the decoded instruction to cause the processor to perform conversion operation corresponding to an 8-bit floating point format operand; a scheduler to schedule the decoded instruction and provide input data for an input operand of the conversion operation indicated by the decoded instruction; and conversion circuitry to execute the decoded instruction to perform the conversion operation to convert the input operand to an output operand in accordance with the 8-bit floating point format operand, the conversion circuitry comprising hardware circuitry to rescale, normalize, and convert the input operand to the output operand.

Abstract: Described herein is a graphics processor comprising a memory interface and a graphics processing cluster coupled with the memory interface. The graphics processing cluster includes a plurality of processing resources. A processing resource of the plurality of processing resources includes a source crossbar communicatively coupled with a register file, the source crossbar to reorder data elements of a source operand and a format conversion pipeline to convert a plurality of input data elements specified by the source operand from a first format of a plurality of datatype formats to a second format of the plurality of datatype formats, the plurality of datatype formats including integer and floating-point formats.

Abstract: Described herein is a graphics processor comprising a memory interface and a graphics processing cluster coupled with the memory interface. The graphics processing cluster includes a multi-lane parallel floating-point unit and a multi-lane parallel integer unit. The multi-lane parallel integer unit includes an integer pipeline including a plurality of parallel integer logic units configured to perform integer compute operations on a plurality of input data elements and a format conversion pipeline including a plurality of parallel format conversion units configured to convert a plurality of input data elements from a first one of a plurality of datatype formats to a second one of the plurality of datatype formats, the plurality of datatype formats including integer and floating-point formats.

Abstract: Described herein is a graphics processor comprising an instruction cache and a plurality of processing elements coupled with the instruction cache. The plurality of processing elements include functional units configured to provide an integer pipeline to execute instructions to perform operations on integer data elements. The integer pipeline including a first multiplier and a second multiplier, the first multiplier and the second multiplier configured to execute operations for a single instruction.

Abstract: Described herein is a graphics processor comprising a plurality of processing elements associated with performance monitoring circuitry. The performance monitoring circuitry is configurable to generate performance data for multiple concurrently executed workloads via flexible event filtering hardware that can isolate a data stream of performance events and display performance monitoring data that is specific to each of the multiple concurrently executed workloads. In one embodiment, performance monitoring for the separate workloads can be configured, for example, by filtering based on the respective contexts used to execute the workloads, the specific instructions executed respectively by the workloads, or the datatypes used respectively by the workloads.

Abstract: An apparatus to facilitate single precision support for systolic pipeline in a graphics environment is disclosed. The apparatus includes a processor comprising systolic array hardware including a plurality of data processing units, wherein the systolic array hardware is to: receive data for performance of a matrix multiplication operation in a first precision format; convert an original value of the data into two split values with a second precision format having a lower precision than the first precision format; perform the matrix multiplication operation using the two split values in the second precision format, the matrix multiplication operation comprising a split-term operation that utilizes two passes through the systolic array hardware with feedback wiring and local reduction; and generate an emulated result for the matrix multiplication operation in the first precision format.

Abstract: An apparatus to facilitate hardware enhancements for double precision systolic support is disclosed. The apparatus includes matrix acceleration hardware having double-precision (DP) matrix multiplication circuitry including a multiplier circuits to multiply pairs of input source operands in a DP floating-point format; adders to receive multiplier outputs from the multiplier circuits and accumulate the multiplier outputs in a high precision intermediate format; an accumulator circuit to accumulate adder outputs from the adders with at least one of a third global source operand on a first pass of the DP matrix multiplication circuitry or an intermediate result from the first pass on a second pass of the DP matrix multiplication circuitry, wherein the accumulator circuit to generate an accumulator output in the high precision intermediate format; and a down conversion and rounding circuit to down convert and round an output of the second pass as final result in the DP floating-point format.

Abstract: An apparatus to facilitate supporting vector multiply add with double accumulator access in a graphics environment is disclosed. The apparatus includes a processor comprising processing resources, the processing resources comprising multiplier circuitry to: receive operands for a matrix multiplication operation, wherein the operands comprising two source matrices to be multiplied as part of the matrix multiplication operation; and issue a multiply and add vector (MADV) instruction for the multiplication operation utilizing a double accumulator access output, wherein the MADV instruction to multiply two vectors of the two source matrices in a single floating point (FP) pipeline of the processor.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted, without terminating execution of the neural network.

Abstract: A Voltage Regulator Module (VRM) includes a first voltage rail circuit board oriented in a first plane having formed therein a first plurality of conductors and configured to produce a first rail voltage, a second voltage rail circuit board oriented in a second plane that is substantially parallel to the first plane having formed therein a second plurality of conductors and configured to produce a second rail voltage. The VRM also includes a first capacitor circuit board oriented in a third plane that is substantially perpendicular to the first plane and a second capacitor circuit board oriented in a fourth plane that is substantially parallel to the third plane. The VRM includes a plurality of conductors intercoupling the first voltage rail circuit board, the first capacitor circuit board, the second voltage rail circuit board, and the second capacitor circuit board.

Abstract: An integrated circuit with specialized processing blocks is provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted without terminating execution of the neural network.

Abstract: An integrated circuit with specialized processing blocks is provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted without terminating execution of the neural network.

Abstract: An integrated circuit with specialized processing blocks are provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted without terminating execution of the neural network.

Abstract: An integrated circuit with specialized processing blocks is provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: An integrated circuit with specialized processing blocks is provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted without terminating execution of the neural network.