Intel Corporation

Vxtel, Inc.

Ruban Kanapathipillai

Kumar Ganapathy

Kenneth Malich

Executing digital signal processing (DSP) instructions in a digital signal processor integrated circuit comprising receiving a DSP instruction in digital signal processor integrated circuit to process one or more complex number operands; fetching a first operand with a first data type, the first operand having real and imaginary values with a complex data type; fetching a second operand with a second data type; prior to executing a DSP operation, determining a permutation of the first operand, the second operand, or both the first operand and the second operand, and permuting instances of the first operand, the second operand, or both the first operand and the second operand to execute the DSP operation; and executing the DSP operation in the digital signal processor integrated circuit using the first operand and the second operand to obtain a result, the result having real and imaginary values with a complex data type.

DSP operations with permutation of vector complex data type operands

Methods of performing dyadic digital signal processing (DSP) instructions. In one embodiment of the invention, the method includes fetching a dyadic DSP instruction having a main operation and a sub operation; predecoding the dyadic DSP instruction to generate predecoded instruction signals; and decoding the predecoded instruction signals to generate select signals to selectively couple data from a first plurality of buses coupled to inputs of multiplexers of a first plurality of DSP functional blocks to execute the main operation of the dyadic DSP instruction in one processor cycle and to selectively couple data from a second plurality of buses coupled to inputs of multiplexers of a second plurality of DSP functional blocks to execute the sub operation of the dyadic DSP instruction in the one processor cycle.

Dyadic DSP instruction predecode signal selective multiplexing data from input buses to first and second plurality of functional blocks to execute main and sub operations

An instruction set architecture (ISA) for application specific signal processor (ASSP) is tailored to digital signal processing applications. The ISA implemented with the ASSP, is adapted to DSP algorithmic structures. The ISA of the present invention includes flexible data typing, permutation, and type matching of operands. The flexible data typing, permutation and type matching of operands provides programming flexibility to support different filtering and DSP algorithms having different types of filter coefficients or data samples. A data typer and aligner within each signal processing unit within the ASSP supports flexible data typing, permutation and type matching of operands of the instruction set architecture.

DSP data type matching for operation using multiple functional units

An application specific signal processor (ASSP) performs vectorized and nonvectorized operations. Nonvectorized operations may be performed using a saturated multiplication and accumulation operation. The ASSP includes a serial interface, a buffer memory, a core processor for performing digital signal processing which includes a reduced instruction set computer (RISC) processor and four signal processing units. The four signal processing units execute the digital signal processing algorithms in parallel including the execution of the saturated multiplication and accumulation operation. The ASSP is utilized in telecommunication interface devices such as a gateway. The ASSP is well suited to handling voice and data compression/decompression in telecommunication systems where a packetized network is used to transceive packetized data and voice.

Methods and apparatuses for signal processing

Disclosed is a method and apparatus for a unified RISC/DSP pipeline controller to control the execution of both reduced instruction set computer (RISC) control instructions and digital signal processing (DSP) instructions for a signal processor. The unified RISC/DSP pipeline controller is coupled to a program memory, a RISC control unit, and at least one signal processing unit. The program memory stores both DSP and RISC control instructions and the RISC control-unit controls the flow of operands and results between the signal processing unit and a data memory that stores data. The signal processing unit executes the DSP instruction. The unified RISC/DSP pipeline controller generates DSP control signals to control the execution of the DSP instruction by the signal processing unit and RISC control signals to control the execution of the RISC control instruction by the RISC control unit.

Method and apparatus for a unified RISC/DSP pipeline controller for both reduced instruction set computer (RISC) control instructions and digital signal processing (DSP) instructions

An instruction set architecture (ISA) to convert voice and data samples into packets for transmission over a network and to convert packets received from the network into voice and data samples. In one embodiment, the ISA includes a digital signal processing (DSP) instruction set architecture for a plurality of signal processing units and a control instruction set architecture to control the execution of DSP instructions by the plurality of signal processing units. In another embodiment, the ISA includes a plurality of DSP instructions including a 20-bit DSP instruction and a 40-bit DSP instruction and a plurality of control instructions to control execution of the plurality of DSP instructions including a 20-bit control instruction and a 40-bit control instruction. The DSP instructions may be dyadic DSP instructions including a main DSP operation and a sub DSP operation.

Dyadic instruction processing instruction set architecture with 20-bit and 40-bit DSP and control instructions

A loop buffer for storing and holding instructions executed within loops for digital signal processing. Control logic detects the beginning and ending of a loop to signal the loop buffer control logic to start instruction execution in a cyclical fashion using the instructions stored within the loop buffer. After completion of the required number of loops, the instructions in the loop buffer are overwritten with new instructions until the next loop is to be processed. The loop buffer conserves power by avoiding the fetching of instructions unnecessarily from memory.

Method and apparatus for loop buffering digital signal processing instructions

Disclosed is a method, apparatus, and an instruction set architecture (ISA) for an application specific signal processor (ASSP) tailored to digital signal processing (DSP) applications. A single DSP instruction includes a pair of sub-instructions: a primary DSP sub-instruction and a shadow DSP sub-instruction. Both the primary and the shadow DSP sub-instructions are dyadic DSP instructions performing two operations in one instruction cycle. Each signal processing unit of the ASSP includes a primary stage to execute a primary DSP sub-instruction based upon current data and a shadow stage to simultaneously execute a shadow DSP sub-instruction based upon delayed data stored locally within registers of the signal processing units. The present invention efficiently executes DSP instructions by simultaneously executing primary DSP sub-instructions (based upon current data) and shadow DSP sub-instructions (based upon delayed locally stored data) with a single DSP instruction.

Method and apparatus for instruction set architecture to perform primary and shadow digital signal processing sub-instructions simultaneously

A dyadic digital signal processing (DSP) instruction processor including a first DSP functional block to execute a main operation of a dyadic DSP instruction and a second DSP functional block to execute a sub operation of the dyadic DSP instruction with data paths of each selectively configured to execute the main operation and the sub operation of the dyadic DSP instruction. A voice and data communication system has a first gateway and a second gateway coupled to a packetized network, each gateway having a network interface including the dyadic DSP instruction processor. An application specific signal processor with a signal processor having a first DSP functional block to execute a main operation of a dyadic DSP instruction and a second DSP functional block to execute a sub operation with multiplexers coupled to the first DSP functional block and the second DSP functional block to selectively configure data paths thereto.

Dyadic DSP instruction processor with main and sub-operation functional blocks selected from each set of multiplier and adder

An instruction set architecture (ISA) for application specific signal processor (ASSP) is tailored to digital signal processing applications. The instruction set architecture implemented with the ASSP, is adapted to DSP algorithmic structures. The instruction word of the ISA is typically 20 bits but can be expanded to 40-bits to control two instructions to be executed in series or parallel. All DSP instructions of the ISA are dyadic DSP instructions performing two operations with one instruction in one cycle. The DSP instructions or operations in the preferred embodiment include a multiply instruction (MULT), an addition instruction (ADD), a minimize/maximize instruction (MIN/MAX) also referred to as an extrema instruction, and a no operation instruction (NOP) each having an associated operation code (&ldquo;opcode&rdquo;). The present invention efficiently executes DSP instructions by means of the instruction set architecture and the hardware architecture of the application specific signal processor.

Dyadic DSP instructions for digital signal processors

A signal processor with an instruction set architecture (ISA) for flexible data typing, permutation, and type matching of operands. The signal processor includes a data typer and aligner to support flexible data typing, permutation and type matching of operands of the instruction set architecture. The data typer and aligner is selectively configued to align and select one of more sets of data bits from one or more data buses as operands for functional blocks of the signal processor in response to fields of an instruction.

Processors with data typer and aligner selectively coupling data bits of data buses to adder and multiplier functional blocks to execute instructions with flexible data types

Dyadic operations instruction processor with configurable functional blocks

Disclosed is a method, apparatus, and an instruction set architecture (ISA) for an application specific signal processor (ASSP) tailored to digital signal processing (DSP) applications. The instruction set architecture implemented with the ASSP, is adapted to DSP algorithmic structures. In one embodiment, a single DSP instruction includes a pair of sub-instructions: a primary DSP sub-instruction and a shadow DSP sub-instruction. Both the primary and the shadow DSP sub-instructions are dyadic DSP instructions performing two operations in one instruction cycle. The DSP operations, in one embodiment, include a multiply instruction (MULT), an addition instruction (ADD), a minimize/maximize instruction (MIN/MAX), and a no operation instruction (NOP). Each signal processing unit includes a primary stage to execute a primary DSP sub-instruction based upon current data and a shadow stage to simultaneously execute a shadow DSP sub-instruction based upon delayed data stored locally within registers of the signal processing units. Control logic is utilized to control shadow selectors of each signal processing unit to select delayed data (specified by the shadow DSP sub-instruction) for use by the shadows stages of the signal processing units. In this way, the present invention efficiently executes DSP instructions by simultaneously executing primary DSP sub-instructions (based upon current data) and shadow DSP sub-instructions (based upon delayed locally stored data) with a single DSP instruction thereby performing four operations per single instruction cycle.

Growing community of inventors

Fremont, CA, United States of America

Ruban Kanapathipillai