Texas Instruments Corporation

Duc Quang Bui

Timothy David Anderson

Joseph R Zbiciak

Naveen Bhoria

Dheera Balasubramanian Samudrala

Joseph Raymond Michael Zbiciak

Peter Richard Dent

Kai Chirca

Soujanya Narnur

Mujibur Rahman

Alan Davis

Rama Venkatasubramanian

Sahithi Krishna

Abhijeet Ashok Chachad

Dheera Balasubramanian

Eric Biscondi

Matthew D Pierson

Daniel Brad Wu

Ramakrishnan Venkatasubramanian

Todd T Hahn

Ashish Rai Shrivastava

Mel Alan Phipps

Jelena Milanovic

Brett L Huber

Reid E Tatge

Tuan Q Dao

Son Hung Tran

Shriram D Moharil

Paul Daniel Gauvreau

Debjit Das Sarma

Ashish Shrivastava

The number of registers required is reduced by overlapping scalar and vector registers. This allows increased compiler flexibility when mixing scalar and vector instructions. Local register read ports are reduced by restricting read access. Dedicated predicate registers reduce requirements for general registers, and allows reduction of critical timing paths by allowing the predicate registers to be placed next to the predicate unit.

Register file structures combining vector and scalar data with global and local accesses

A method to compare first and second source data in a processor in response to a vector maximum with indexing instruction includes specifying first and second source registers containing first and second source data, a destination register storing compared data, and a predicate register. Each of the registers includes a plurality of lanes. The method includes executing the instruction by, for each lane in the first and second source register, comparing a value in the lane of the first source register to a value in the corresponding lane of the second source register to identify a maximum value, storing the maximum value in a corresponding lane of the destination register, asserting a corresponding lane of the predicate register if the maximum value is from the first source register, and de-asserting the corresponding lane of the predicate register if the maximum value is from the second source register.

Vector maximum and minimum with indexing

In an embodiment, a circuit includes a data path including at least a first lane of a first width and a second lane of a second, larger, width; an execution unit to execute a first instruction on data of the first width or less using the first lane, and to execute a second instruction on data greater than the first width and less than or equal to the second width using the second lane; and a control register that stores a value indicating which of the first and second lanes to be used in instruction execution by the execution unit. The circuit is configured to, based on the value stored in the control register, power off the first lane when the execution unit executes the second instruction but not the first instruction, and power off the second lane when the execution unit executes the first instruction but not the second instruction.

System and method to control the number of active vector lanes in a processor

A method for writing data to memory that provides for generation of a predicate to disable a portion of the elements so that only the enabled elements are written to memory. Such a method may be employed to write multi-dimensional data to memory and/or may be used with a streaming address generator.

System and method for predication handling

A Very Long Instruction Word (VLIW) digital signal processor particularly adapted for single instruction multiple data (SIMD) operation on various operand widths and data sizes. A vector compare instruction compares first and second operands and stores compare bits. A companion vector conditional instruction performs conditional operations based upon the state of a corresponding predicate data register bit. A predicate unit performs data processing operations on data in at least one predicate data register including unary operations and binary operations. The predicate unit may also transfer data between a general data register file and the predicate data register file.

Vector SIMD VLIW data path architecture

In an example, a device includes a register file; a set of functional units coupled to the register file; and an instruction decoder coupled to the register file and to the set of functional units. The instruction decoder receives an executable instruction directed to a specific functional unit of the set of functional unit. The executable instruction includes a segment specifying a register of the register file. The instruction decoder also provides the executable instruction to the specific functional unit. The specific functional unit then determines whether to execute the executable instruction based on a value stored in the register of the register file specified by the segment of the executable instruction.

Conditional execution specification of instructions using conditional extension slots in the same execute packet in a VLIW processor

Techniques related to executing a plurality of instructions by a processor comprising receiving a first instruction for execution on an instruction execution pipeline, wherein the instruction execution pipeline is in a first execution mode, and wherein the first instruction is configured to utilize a first memory location, begin execution of the first instruction on the instruction execution pipeline, receiving an execution mode instruction to switch the instruction execution pipeline to a second execution mode, switching the instruction execution pipeline to the second execution mode based on the received execution mode instruction, receiving a second instruction for execution on the instruction execution pipeline, the second instruction configured to utilize the first memory location, determining that the first instruction and the second instruction utilize the first memory location, and stalling execution of the second instruction based on the determining.

Entering protected pipeline mode without annulling pending instructions

In an example, a device includes a memory, a register, a data path including a set of lanes, and a processor that executes a program. The following operations are performed in response to execution of the program: write data to a field of the register, in which the data specifies that at least one lane of the set of lanes is powered on; execute an instruction on the at least one powered on lane; receive an interrupt; based on the interrupt, copy the data from the register to the memory; service the interrupt; and based on completing the service, copy data the data from the memory to the register.

Controlling the number of powered vector lanes via a register field

A system, method, and device are shown that are operable to transform and align a plurality of fields from an input to an output data stream using a multilayer butterfly or inverse butterfly network by selectably switching bit positions of the input data stream. In some examples, a device includes a first circuit configured to selectably switch bit positions of a first subset of the data stream with a second subset of the data stream and a second circuit configured to: selectably switch bit positions of a first subset of the first subset of the data stream with a second subset of the first subset of the data stream, and selectably switch bit positions of a first subset of the second subset of the data stream with a second subset of the second subset of the data stream.

Butterfly network on load data return

Disclosed embodiments relate to look up table operations implemented in a digital data processor. A look up table read instruction recalls data elements of a specified data size from table(s) and stores recalled data elements in successive slots in a destination register. Disclosed embodiments promote data elements to a larger size with selected sign or zero extension. A source operand register stores vector offsets from a table start address. A destination operand stores the results of the look up table read. The look up table instruction implies a base address register and a configuration register. The base address register stores a table base address. The configuration register sets various look up table read operation parameters.

Look up table with data element promotion

A digital data processor includes an instruction memory storing instructions each specifying a data processing operation and at least one data operand field, an instruction decoder coupled to the instruction memory for sequentially recalling instructions from the instruction memory and determining the data processing operation and the at least one data operand, and at least one operational unit coupled to a data register file and to the instruction decoder to perform a data processing operation upon at least one operand corresponding to an instruction decoded by the instruction decoder and storing results of the data processing operation. The at least one operational unit is configured to perform a table write in response to a look up table write instruction by writing at least one data element from a source data register to a specified location in a specified number of at least one table.

Look-up table write

Processors and methods reverse source data in response to a vector reverse instruction. In an implementation, a processor comprises an instruction fetch unit; and a datapath that includes a register file that includes a source register and a destination register; and a set of functional units. The instruction fetch unit receives a vector reverse instruction that specifies a single vector reverse operation to be executed in a single operation. The vector reverse instruction also specifies a first functional unit from among a set of functional units, and based on the vector reverse instruction, the first functional unit receives the first vector from a source register; reverses an order of a set of elements of a first vector stored in the source register to produce a second vector; and causes the second vector to be stored in a destination register.

Vector reverse

In a very long instruction word (VLIW) central processing unit instructions are grouped into execute packets that execute in parallel. A constant may be specified or extended by bits in a constant extension instruction in the same execute packet. If an instruction includes an indication of constant extension, the decoder employs bits of a constant extension instruction to extend the constant of an immediate field. Two or more constant extension slots are permitted in each execute packet, each extending constants for a different predetermined subset of functional unit instructions. In an alternative embodiment, more than one functional unit may have constants extended from the same constant extension instruction employing the same extended bits. A long extended constant may be formed using the extension bits of two constant extension instructions.

Forming constant extensions in the same execute packet in a VLIW processor

Disclosed herein are systems and methods for executing multiple instruction set architectures (ISAs) on a singular processing unit. In an implementation, a processor that includes a first decoder, a second decoder, instruction fetch circuitry, and instruction dispatch circuitry is configured to execute two separate instruction set architectures. In an implementation, the instruction fetch circuitry is configured to fetch instructions from an associated memory. In an implementation the instruction dispatch circuitry is coupled to the instruction fetch circuitry, the first decoder, and the second decoder and is configured to route instructions associated with a first ISA to the first decoder, and route instructions associated with a second ISA to the second decoder.

Multiple instruction set architectures on a processing device

A digital data processor includes an instruction memory storing instructions specifying a data processing operation and a data operand field, an instruction decoder coupled to the instruction memory for recalling instructions from the instruction memory and determining the operation and the data operand, and an operational unit coupled to a data register file and to an instruction decoder to perform a data processing operation upon an operand corresponding to an instruction decoded by the instruction decoder and storing results of the data processing operation. The operational unit is configured to perform a table write in response to a look up table initialization instruction by duplicating at least one data element from a source data register to create duplicated data elements, and writing the duplicated data elements to a specified location in a specified number of at least one table and a corresponding location in at least one other table.

Growing community of inventors

Grand Prairie, TX, United States of America

Duc Quang Bui