A streaming engine employed in a digital data processor specifies a fixed read only data stream defined by plural nested loops. An address generator produces addresses of data elements. A steam head register stores data elements next to be supplied to functional units for use as operands. Stream metadata is stored in response to a stream store instruction. Stored stream metadata is restored to the stream engine in response to a stream restore instruction. An interrupt changes an open stream to a frozen state discarding stored stream data. A return from interrupt changes a frozen stream to an active state.

Embodiments detailed herein relate to arithmetic operations of float-point values. An exemplary processor includes decoding circuitry to decode an instruction, where the instruction specifies locations of a plurality of operands, values of which being in a floating-point format. The exemplary processor further includes execution circuitry to execute the decoded instruction, where the execution includes to: convert the values for each operand, each value being converted into a plurality of lower precision values, where an exponent is to be stored for each operand; perform arithmetic operations among lower precision values converted from values for the plurality of the operands; and generate a floating-point value by converting a resulting value from the arithmetic operations into the floating-point format and store the floating-point value.

A processor includes a front-end with an instruction set that operates at a first bit width and a floating point unit coupled to receive the instruction set in the processor that operates at the first bit width. The floating point unit operates at a second bit width and, based upon a bit width assessment of the instruction set provided to the floating point unit, the floating point unit employs a shadow-latch configured floating point register file to perform bit width reconfiguration. The shadow-latch configured floating point register file includes a plurality of regular latches and a plurality of shadow latches for storing data that is to be either read from or written to the shadow latches. The bit width reconfiguration enables the floating point unit that operates at the second bit width to operate on the instruction set received at the first bit width.

An apparatus to facilitate large integer multiplication enhancements 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 multiplication operation, wherein the multiplication operation is part of a chain of multiplication operations for a large integer multiplication; and issue a multiply and add (MAD) instruction for the multiplication operation utilizing at least one of a double precision multiplier or a 48 bit output, wherein the MAD instruction to generate an output in a single clock cycle of the processor.

Data structure and microcontroller architecture performing binary multiply-accumulate operations using multiple partial copies of weights. Destination-register location, source-register location, and weight-register location are received. Using the weight-register location, a sub-set of the weight bits is copied a select number of times based on a filter index value that is received. Each copy of the sub-set of weights is executed in parallel. Using the source-register location, a sub-set of the input bits is selected based on the size of the sub-set of weights, wherein the sub-set of input bits is shifted one bit from a previous sub-set of input bits. XOR operation is performed on each corresponding bit in the copy of the sub-set of weights with each corresponding bit in the selected sub-set of input bits. In a corresponding destination sub-location, output of each XOR operation is aggregated with each other and with current value of the corresponding destination sub-location.

A first processor processes an instruction configured to perform a plurality of functions. The plurality of functions includes one or more functions to operate on one or more tensors. A determination is made of a function of the plurality of functions to be performed. The first processor provides to a second processor information related to the function. The second processor is to perform the function. The first processor and the second processor share memory providing memory coherence.

The present disclosure relates to a processing device including a memory configured to store data to be computed; a computational circuit configured to compute the data to be computed, which includes performing acceleration computations on the data to be computed by using an adder circuit and a multiplier circuit; and a control circuit configured to control the memory and the computational circuit, which includes performing acceleration computations according to the data to be computed. The present disclosure may have high flexibility, good configurability, fast computational speed, low power consumption, and other features.

Data employed in computations is processed so that during computations more of the data can be fit into or maintained in a smaller but higher speed memory than an original source of the data. More specifically, a sensitivity value is determined for various items of the data which reflect the number of bits in the data items that are not garbage bits, and only information in the data items that are indicated by the sensitivity value to not be garbage bits are necessarily effectively retained. At least the information that is not garbage bits and the corresponding associated sensitivity are packed together. The results of computations that are performed using the data items as at least one of the operands for the computation are associated with a sensitivity that is derived from the individual sensitivities of the operands used in the computation.

A method, computer readable medium, and processor are disclosed for performing matrix multiply and accumulate (MMA) operations. The processor includes a datapath configured to execute the MMA operation to generate a plurality of elements of a result matrix at an output of the datapath. Each element of the result matrix is generated by calculating at least one dot product of corresponding pairs of vectors associated with matrix operands specified in an instruction for the MMA operation. A dot product operation includes the steps of: generating a plurality of partial products by multiplying each element of a first vector with a corresponding element of a second vector; aligning the plurality of partial products based on the exponents associated with each element of the first vector and each element of the second vector; and accumulating the plurality of aligned partial products into a result queue utilizing at least one adder.

According to one implementation of the present disclosure, a method includes performing a spatial alignment of at least one of first or second data tiers of a circuit; and performing a computation based on the spatial alignment of the at least one of the first and second data tiers. According to another implementation of the present disclosure, a circuit includes: a compute circuitry; and at least first and second data tiers of two or more data tiers positioned at least partially overlapping one another. In an example, each of the at least first and second data tiers is coupled to the compute circuitry. In certain implementations, the positioning of the first and second data tiers at least partially overlapping one another corresponds to a spatial alignment.