Texas Instruments Corporation

Alexander Tessarolo

Venkatesh Natarajan

Prasanth Viswanathan Pillai

Prohor Chowdhury

Alan Davis

Saya Goud Langadi

Richard Mark Poley

Peter N Ehlig

David Peter Foley

Ajit Deepak Gupte

Mahesh Madhukar Mehendale

Sam Gnana Sabapathy

Karthikeyan Rajan Madathil

Subash Chandar Govindarajan

David A Figoli

G Subash Chandar

Glenn Harland Hopkins

Various embodiments of the present disclosure relate to conditional branch instructions to support software pipelining techniques. In an example embodiment, a system including instruction fetch circuitry, decoder circuitry, and conditional branch circuitry is provided. The instruction fetch circuitry is configured to fetch a conditional branch instruction from memory and provide the instruction to the decoder circuitry. The instruction includes an iteration count and multiple branch destinations. The branch destinations include two or more branch destinations corresponding to conditions against which the conditional branch circuitry evaluates the iteration count. The decoder circuitry is configured to cause the conditional branch circuitry to select a branch destination, of the two or more branch destinations, based on a comparison of the iteration count to each of the conditions and cause the instruction fetch circuitry to fetch an indication of an instruction from a memory location stored at the selected branch destination.

Conditional branch instructions

In an example, a system includes a processor, where the processor includes a plurality of processor registers, and where the processor is configured to execute a first instruction in a first execution context. The processor is also configured to receive a PRESERVE instruction that indicates at least one processor register among the plurality of processor registers. The processor is configured to, responsive to the PRESERVE instruction, preserve parameters in the at least one processor register and clear other processor registers in the plurality of processor registers in the first execution context. The processor is also configured to execute a second instruction in a second execution context.

Securing registers across security zones

A processor with instruction storage configured to store processor instructions, data storage configured to store processor data representing an array, the array including plural data elements, a controller, and an instruction pipeline. The instruction pipeline includes: a load stage circuit configured to load an array element from the data storage, a compare stage circuit configured to compare the array element to a reference value, a store stage circuit configured to store a set of results that includes a result of the comparison of the array element to the reference value, and a loop hit detect stage circuit configured to determine whether any of the set of results is associated with a hit on the reference value.

Reducing overhead in processor array searching

In described examples, an apparatus is arranged to generate a linear term, a quadratic term, and a constant term of a transcendental function with, respectively, a first circuit, a second circuit, and a third circuit in response to least significant bits of an input operand and in response to, respectively, a first, a second, and a third table value that is retrieved in response to, respectively, a first, a second, and a third index generated in response to most significant bits of the input operand. The third circuit is further arranged to generate a mantissa of an output operand in response to a sum of the linear term, the quadratic term, and the constant term.

Transcendental function evaluation

A processor is provided and includes a core that is configured to perform a decode operation on a multi-instruction packet comprising multiple instructions. The decode operation includes receiving the multi-instruction packet that includes first and second instructions. The first instruction includes a primary portion at a fixed first location and a secondary portion. The second instruction includes a primary portion at a fixed second location between the primary portion of the first instruction and the secondary portion of the first instruction. An operational code portion of the primary portion of each of the first and second instructions is accessed and decoded. An instruction packet including the primary and secondary portions of the first instruction is created, and a second instruction packet including the primary portion of the second instruction is created. The first and second instructions packets are dispatched to respective first and second functional units.

Instruction packing scheme for VLIW CPU architecture

A processor (and method) includes a core that performs a floating point division through execution of various instructions. The instructions include a sign, exponent, and mantissa (SEM) separation instruction which causes the core to extract the sign, exponent and mantissa values from numerator and denominator floating point numbers. The instructions also include an unsigned mantissa division instruction which cause the core to iteratively perform a conditional subtraction operation to compute a value indicative of a mantissa of the quotient. The instructions further include a merge instruction that causes the core to generate a quotient floating point number using the extracted sign and exponent from the SEM separation instruction and the value indicative of the mantissa of the quotient.

Architecture and instruction set to support interruptible floating point division

A processor includes a core and a plurality of registers including a first register, a second register, and a third register. The core is configured to perform a division operation that includes execution of a sign extraction instruction in which a sign of at least one of a numerator value and a denominator value is stored, a conditional subtraction instruction which divides the numerator value by the denominator value to generate a quotient value and a remainder value, and a sign assignment instruction which adjusts the sign of at least one of the quotient and remainder values. The conditional subtraction instruction is configured to cause the core to perform multiple iterations of a conditional subtraction in one execution of the conditional subtraction instruction and in one clock cycle. Others methods and apparatus are described as well.

Architecture and instruction set to support integer division

A high resolution capture circuit and integrated circuit chip are disclosed and include first and second capture delay lines and an oscillator delay line. The oscillator delay line includes N timing delay elements sequentially coupled in a ring to generate a first clock signal. The first and second capture delay lines each include M capture delay elements sequentially coupled to pass a received signal in a first direction along a first signal path and to pass a clock signal in a second direction opposite to the first direction along a second signal path. The first capture delay line uses the first clock signal and the second capture delay line uses an inverse of the first clock signal. Each capture delay element forms a flip-flop and provides a one-bit output. All delay elements have essentially identical timing and M is equal to either N or to N/2.

High resolution capture

Processor architectures and associated methods provide interruptible, instruction-based trigonometric function computation based on CORDIC iterations, receiving and outputting floating-point values (e.g., 64-bit). The architectures and methods can provide multiple CORDIC-like iterations in as little as a single CPU processing cycle to provide an overall faster execution of trigonometric operations while having zero additional overhead for service of time-critical interrupts. Post interrupt service, a CORDIC operation can be resumed from where it was interrupted.

Interruptible trigonometric operations

Methods and apparatus to perform serial communications are disclosed. An example serial data transmitter includes: a clock signal generator to generate a digital clock signal; a clock signal controller to enable the clock signal generator; a line break signal generator to, in response to an expiration of a time period, trigger the transmission of a transmission line check frame; a data integrity check generator to generate error detection data corresponding to first data to be transmitted via the transmission port; a signal framer to: generate a first data frame having a preamble, second data, third data, the first data, the error detection data, and fourth data; and generate the transmission line check frame.

Methods and apparatus to perform serial communications

A system includes a memory bank and a control unit. The control unit is configured to perform FFT computations based on Merged radix-2 butterfly calculations by performing FFT computations over N input items, and to access the memory bank for (&#xbd;&#xd7;logN)&#xd7;(10&#xd7;logN) times.

Approach for significant improvement of FFT performance in microcontrollers

A decoding system suitable for Viterbi decoding includes a decoder that includes a state metrics array, a butterfly unit, and a constraint length multiplexer. The state metrics array includes registers in which each register is arranged to store a state metric for processing. The butterfly unit includes an array of butterfly elements where each butterfly element is arranged to generate intermediate state metrics in parallel with other butterfly elements in the butterfly unit. The constraint length multiplexer unit is arranged to generate new state metrics in response to the intermediate state metrics and a Viterbi constraint length value stored in a constraint length register. Transition bits can also be generated in response to the constraint length.

Growing community of inventors

Lindfield, Australia

Alexander Tessarolo