Systems and methods for stalling a host processor. In some embodiments, the host processor may be caused to initiate one or more selected transactions, wherein the one or more selected transactions comprise a bus transaction. The host processor may be prevented from completing the one or more selected transactions, to thereby stall the host processor.

A processor includes a scalar processor core and a vector coprocessor core coupled to the scalar processor core. The scalar processor core is configured to retrieve an instruction stream from program storage, and pass vector instructions in the instruction stream to the vector coprocessor core. The vector coprocessor core includes a register file, a plurality of execution units, and a table lookup unit. The register file includes a plurality of registers. The execution units are arranged in parallel to process a plurality of data values. The execution units are coupled to the register file. The table lookup unit is coupled to the register file in parallel with the execution units. The table lookup unit is configured to retrieve table values from one or more lookup tables stored in memory by executing table lookup vector instructions in a table lookup loop.

One embodiment provides for a graphics processing unit to accelerate machine-learning operations, the graphics processing unit comprising a multiprocessor having a single instruction, multiple thread (SIMT) architecture, the multiprocessor to execute at least one single instruction; and a first compute unit included within the multiprocessor, the at least one single instruction to cause the first compute unit to perform a two-dimensional matrix multiply and accumulate operation, wherein to perform the two-dimensional matrix multiply and accumulate operation includes to compute an intermediate product of 16-bit operands and to compute a 32-bit sum based on the intermediate product.

An embodiment of the invention is a processor including execution circuitry to, in response to a decoded instruction, convert a half-precision floating-point value to a single-precision floating-point value and store the single-precision floating-point value in each of the plurality of element locations of a destination register. The processor also includes a decoder and the destination register. The decoder is to decode an instruction to generate the decoded instruction.

In a processor device according to the present invention, a memory access unit reads data to be processed from an external memory and writes the data to a first register group that a plurality of processors does not access among a plurality of register groups. A control unit sequentially makes each of the plurality of processors implement a same instruction, in parallel with changing an address of a register group that stores the data to be processed. A scheduler, based on specified scenario information, specifies an instruction to be implemented and a register group to be accessed for the plurality of processors, and specifies a register group to be written to among the plurality of register groups and data to be processed that is to be written for the memory access unit.

A technique for computationally-efficient privacy-preserving homomorphic inferencing against a decision tree. Inferencing is carried out by a server against encrypted data points provided by a client. Fully homomorphic computation is enabled with respect to the decision tree by intelligently configuring the tree and the real number-valued features that are applied to the tree. To that end, and to the extent the decision tree is unbalanced, the server first balances the tree. A cryptographic packing scheme is then applied to the balanced decision tree and, in particular, to one or more entries in at least one of: an encrypted feature set, and a threshold data set, that are to be used during the decision tree evaluation process. Upon receipt of an encrypted data point, homomorphic inferencing on the configured decision tree is performed using a highly-accurate approximation comparator, which implements a “soft” membership recursive computation on real numbers, all in an oblivious manner.

A method to classify source data in a processor in response to a vector floating-point classification instruction includes specifying, in respective fields of the vector floating-point classification instruction, a source register containing the source data and a destination register to store classification indications for the source data. The source register includes a plurality of lanes that each contains a floating-point value and the destination register includes a plurality of lanes corresponding to the lanes of the source register. The method further includes executing the vector floating-point classification instruction by, for each lane in the source register, classifying the floating-point value in the lane to identify a type of the floating-point value, and storing a value indicative of the identified type in the corresponding lane of the destination register.

A processing element is implemented in a stage of a pipeline and configured to execute an instruction. A first array of multiplexers is to provide information associated with the instruction to the processing element in response to the instruction being in a first set of instructions. A second array of multiplexers is to provide information associated with the instruction to the first processing element in response to the instruction being in a second set of instructions. A control unit is to gate at least one of power or a clock signal provided to the first array of multiplexers in response to the instruction being in the second set.

Systems, methods, and apparatuses relating sparsity based FMA. In some examples, an instance of a single FMA instruction has one or more fields for an opcode, one or more fields to identify a source/destination matrix operand, one or more fields to identify a first plurality of source matrix operands, one or more fields to identify a second plurality of matrix operands, wherein the opcode is to indicate that execution circuitry is to select a proper subset of data elements from the first plurality of source matrix operands based on sparsity controls from a first matrix operand of the second plurality of matrix operands and perform a FMA.

A processor includes a register file and control logic that detects multiple different sets of sequential zero bits of a register in the register file, wherein each of the multiple different sets has a bit length that corresponds to a partial instruction width and operates at a first partial instruction width or a second partial instruction width with the register file depending on number of sets of zero bits detected in the register. In certain examples, the control logic causes operating at first instruction width that avoids merging of a first bit length of data in the register and operating at the second instruction width that avoids merging of a second bit length of data in the register. In some examples, a register rename map table incudes multiple zero bits that identify the detected multiple different sets of bits of sequential zeros.