Abstract: Various embodiments are provided for using a reduced precision based programmable and single instruction multiple data (SIMD) dataflow architecture in a computing environment. One or more instructions between a plurality of execution units (EUs) operating in parallel within each one of a plurality of execution elements (EEs).

Abstract: Embodiments for implementing a fused multiply-multiply-accumulate (“FMMA”) unit by one or more processors in a computing system. Mantissas for two products, an exponent difference of the two products serving as an alignment shift amount for a product of the two products having a smallest exponent, and an alignment shift amount for an addend relative to an alternative product of the two product having a larger exponent may be determined in parallel. The addend may be aligned relative to the alternative product having the larger exponent. The product having the smallest exponent may be aligned relative to the alternative product having the larger exponent according to the alignment shift amount.

Abstract: Various embodiments are provided for facilitating data processing by one or more processors in a computing system. An instruction to be executed may be obtained. The instruction is a single instruction multiple data (SIMD) reduction operation of an operand vector with a plurality of vector elements. The SIMD reduction operation may be executed to produce a result vector with a plurality of alternative vector elements. One or more reduction functions may be performed on each of a pair of vector elements from the plurality of vector elements of the operand vector and a result of the one or more reduction functions may be placed in a corresponding vector element of the result vector.

Abstract: Embodiments for implementing a communicating memory between a plurality of computing components are provided. In one embodiment, an apparatus comprises a plurality of memory components residing on a processing chip, the plurality of memory components interconnected between a plurality of processing elements of at least one processing core of the processing chip and at least one external memory component external to the processing chip. The apparatus further comprises a plurality of load agents and a plurality of store agents on the processing chip, each interfacing with the plurality of memory components. Each of the plurality of load agents and the plurality of store agents execute an independent program specifying a destination of data transacted between the plurality of memory components, the at least one external memory component, and the plurality of processing elements.

Abstract: Various embodiments are provided reusing an operand in an instruction set architecture (ISA) by one or more processors in a computing system. An instruction may specify that an operand register for a selected operand retain operand data used by a previous instruction. The operand data in the operand register may be reused by the instruction.

Abstract: Techniques facilitating binary floating-point multiply and scale operation for compute-intensive numerical applications and apparatuses are provided. An embodiment relates to a system that can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a receiver component that receives an instruction to perform a multiply and scale operation of the first floating point operand value, the second floating point operand value, and the integer operand value, wherein the multiplication component obtains the floating-point product in response to the instruction to perform the multiply and scale operation. The multiplication can be performed as a single instruction.

Abstract: Various embodiments are provided for implementing instruction initialization in a dataflow architecture in a computing environment. A data packet may be transmitted from a selected node to one or more of a plurality of nodes using one or more existing data paths in an initialization network. A determination operation is performed to determine whether one or more of a plurality of nodes is a target node intended for the data packet. Those of the plurality of nodes determined to be a target node initialize one or more components of the target node using the data packet. The data packet may be forwarded by each of the one or more of a plurality of nodes to a subsequent node in the initialization network.

Abstract: Embodiments for implementing a communicating memory between a plurality of computing components are provided. In one embodiment, an apparatus comprises a plurality of memory components residing on a processing chip, the plurality of memory components interconnected between a plurality of processing elements of at least one processing core of the processing chip and at least one external memory component external to the processing chip. The apparatus further comprises a plurality of load agents and a plurality of store agents on the processing chip, each interfacing with the plurality of memory components. Each of the plurality of load agents and the plurality of store agents execute an independent program specifying a destination of data transacted between the plurality of memory components, the at least one external memory component, and the plurality of processing elements.

Abstract: Techniques for operating on and calculating binary floating-point numbers using an enhanced floating-point number format are presented. The enhanced format can comprise a single sign bit, six bits for the exponent, and nine bits for the fraction. Using six bits for the exponent can provide an enhanced exponent range that facilitates desirably fast convergence of computing-intensive algorithms and low error rates for computing-intensive applications. The enhanced format can employ a specified definition for the lowest binade that enables the lowest binade to be used for zero and normal numbers; and a specified definition for the highest binade that enables it to be structured to have one data point used for a merged Not-a-Number (NaN)/infinity symbol and remaining data points used for finite numbers. The signs of zero and merged NaN/infinity can be “don't care” terms. The enhanced format employs only one rounding mode, which is for rounding toward nearest up.

Abstract: Techniques for operating on and calculating binary floating-point numbers using an enhanced floating-point number format are presented. The enhanced format can comprise a single sign bit, six bits for the exponent, and nine bits for the fraction. Using six bits for the exponent can provide an enhanced exponent range that facilitates desirably fast convergence of computing-intensive algorithms and low error rates for computing-intensive applications. The enhanced format can employ a specified definition for the lowest binade that enables the lowest binade to be used for zero and normal numbers; and a specified definition for the highest binade that enables it to be structured to have one data point used for a merged Not-a-Number (NaN)/infinity symbol and remaining data points used for finite numbers. The signs of zero and merged NaN/infinity can be “don't care” terms. The enhanced format employs only one rounding mode, which is for rounding toward nearest up.

Abstract: A convolutional lowering component (CoLor component) between processor and memory units (or within a memory hierarchy) maps location in a lowered matrix to an equivalent location in a non-lowered matrix and provides auto zero padding in computational heavy convolutional layers. An identification component identifies processing components that execute computations in deep neural networks (DNNs) in which convolutions are realized as general matrix to matrix multiplications (GEMM) operations, and identifies a subset of the processing components that store deep neural network (DNN) features in a non-lowered form component that determines output for successively larger neural networks of a set. An address translation component translates address requests, generated by the subset of processing components to a memory subsystem, from a lowered index form to a non-lowered index form.

Abstract: Techniques for operating on and calculating binary floating-point numbers using an enhanced floating-point number format are presented. The enhanced format can comprise a single sign bit, six bits for the exponent, and nine bits for the fraction. Using six bits for the exponent can provide an enhanced exponent range that facilitates desirably fast convergence of computing-intensive algorithms and low error rates for computing-intensive applications. The enhanced format can employ a specified definition for the lowest binade that enables the lowest binade to be used for zero and normal numbers; and a specified definition for the highest binade that enables it to be structured to have one data point used for a merged Not-a-Number (NaN)/infinity symbol and remaining data points used for finite numbers. The signs of zero and merged NaN/infinity can be “don't care” terms. The enhanced format employs only one rounding mode, which is for rounding toward nearest up.

Abstract: A convolutional lowering component (CoLor component) between processor and memory units (or within a memory hierarchy) maps location in a lowered matrix to an equivalent location in a non-lowered matrix and provides auto zero padding in computational heavy convolutional layers. An identification component identifies processing components that execute computations in deep neural networks (DNNs) in which convolutions are realized as general matrix to matrix multiplications (GEMM) operations, and identifies a subset of the processing components that store deep neural network (DNN) features in a non-lowered form component that determines output for successively larger neural networks of a set. An address translation component translates address requests, generated by the subset of processing components to a memory subsystem, from a lowered index form to a non-lowered index form.

Abstract: Aspects of the invention include receiving, by a processor, a plurality of instructions at an instruction pipeline. The processor can further determine an operand bit field size for each of the received plurality of instructions. The processor can further compare the operand bit field size of at least a subset of the received instructions to a predetermined threshold. The processor can further fuse at least two of the received instructions that have an operand bit field size that meets the predetermined threshold. The processor can further perform an execution stage within the instruction pipeline to execute the received instructions, including the fused instructions.

Abstract: The present invention relates to a method and circuit for performing multiply-operations in an arithmetic unit of a computer processor. In a multiplier thereof, zero detection of the resulting product bit string (22) is needed for a proper setting of condition code and overflow status information. Zero detection according to prior art decreases the calculation speed in the multiplier. In order to provide a method and respective electronic circuit, wherein the zero detection is earlier completed, it is proposed to use a leading zero anticipation (LZA) hardware—i.e., an LZA circuit (40), which exists usually anyway in floating point processor adders for calculating the number of leading zeros for operand normalization purposes—for performing a zero detection of the product by aid of the partial results (16, 17) emerging at the output of the Wallace tree of the multiplier.

Abstract: A system for performing floating point arithmetic operations including an input register adapted for receiving an operand. The system also includes computer instructions for performing single precision incrementing of the operand in response to determining that the operand is single precision, that the operand requires the incrementing based on the results of a previous operation and that the previous operation did not perform the incrementing. The operand was created in the previous operation. The system further includes instructions for performing double precision incrementing of the operand in response to determining that the operand is double precision, that the operand requires the incrementing based on the results of the previous operation and that the previous operation did not perform the incrementing.

Abstract: A method for converting from binary to decimal. The method includes receiving a binary coded decimal (BCD) number made up of one or more sets of three digits. A running sum and a running carry are set to zero. The following steps are performed for each set of three digits in the BCD number in order from the set of three digits containing the three most significant digits of the BCD number to the set of three digits containing the three least significant digits of the BCD number. The steps include: creating six partial products based on the set of three digits, the running sum and the running carry; combining the six partial products into two partial products; and storing the two partial products in the running sum and the running carry. After the loop has been performed for each set of three digits in the BCD number, the running sum and the running carry are combined into a final binary result.

Abstract: A system for performing floating point arithmetic operations including an input register adapted for receiving an operand. The system also includes a mechanism for performing a shift or masking operation in response to determining that the operand is in an un-normalized format. The system also includes instructions for performing single precision incrementing of the operand in response to determining that the operand is single precision, that the operand requires the incrementing based on the results of a previous operation and that the previous operation did not perform the incrementing. The operand was created in the previous operation. The system further includes instructions for performing double precision incrementing of the operand in response to determining that the operand is double precision, that the operand requires the incrementing based on the results of the previous operation and that the previous operation did not perform the incrementing.

Abstract: A method for converting from binary to decimal. The method includes receiving a binary number, the binary number including one or more sets of bits. An accumulated sum is set to zero. The accumulated sum is in a binary coded decimal (BCD) format. The following loop is repeated for each set of bits in the binary number in order from the set of bits containing the most significant bit of the binary number to the set of bits containing the least significant bit of the binary number: the accumulated sum is converted into a 5,1 code format resulting in an interim sum. The loop also includes repeating for each next bit in the set in order from the most significant bit to the least significant bit in the set: doubling the interim sum; and replacing the least significant bit of the interim sum with the next bit. The last step in the loop includes converting the interim sum into the BCD format and storing the results of the converting in the accumulated sum.