Abstract: A method and apparatus for a checker instruction in a redundant multithreading environment is described. In one embodiment, when RMT requires, a processor may issue a checker instruction in both a leading thread and a trailing thread. The checker instruction may travel down individual pipelines for each thread independently until it reaches a buffer at the end of each pipeline. Then, prior to committing the checker instruction, the checker instruction looks for its counterpart and does a comparison of the instructions. If the checker instructions match, the checker instructions commit and retires otherwise an error is declared.

Abstract: A processor is provided which has a modular organization including at least one local store operable to store data and instructions for execution, at least one functional unit operable to execute instructions on data provided from the local store, and at least one issue logic unit operable to convert instructions provided from the local store into operations of the functional unit for executing the instructions. The at least one issue logic unit may be operable to decode a unitary instruction provided from the local store to simultaneously operate all of the functional units according to the unitary instruction. Each issue logic unit may be operable to decode multiple instructions to separately operate first and second subsets of the plurality of functional units according to respective ones of the multiple instructions.

Abstract: A method, apparatus and computer program product are provided for implementing a level bias function for branch prediction control for generating test simulation vectors. User selected options are received for a set of constraints for generating test simulation vectors for branch conditional instructions. Current resource values for predicting a branch for a branch conditional instruction are read. A branch operand field is generated to include a set of valid values using the current resource values and based upon said user selected constraints. The branch operand field defines conditions under which a branch is taken.

Abstract: A field programmable gate array includes a virtual bus interface that receives a control word from a host processor over a standard I/O bus. A configurable very long instruction word (VLIW) controller receives the control word via virtual bus interface signals mapped from the virtual bus interface. A reconfigurable communication and control fabric controls the data paths and programming modes of single instruction-multiple data (SIMD) processing element cells. The configurable VLIW controller has an interface with the reconfigurable communication and control fabric. SIMD processing element cells are controlled by the configurable VLIW controller through the reconfigurable communication and control fabric via the interface.

Abstract: A method, apparatus, and computer instructions for autonomically counting selected branch instructions executed in a processor to improve branch predictions. Counters are provided to count branch instructions that are executed in a processor to collect branch statistics. A set of branch statistics fields is allocated to associate with a branch instruction. When a program is executed, the stored statistics allows the program to look at the branch statistics in the counter to perform branch prediction. Hence, a user may use branch statistics values from the hardware counter to perform analysis on application code.

Abstract: One embodiment of the present invention provides a system that facilitates deferring execution of instructions with unresolved data dependencies as they are issued for execution in program order. During a normal execution mode, the system issues instructions for execution in program order. Upon encountering an unresolved data dependency during execution of an instruction, the system generates a checkpoint that can subsequently be used to return execution of the program to the point of the instruction. Next, the system executes the instruction and subsequent instructions in an execute-ahead mode, wherein instructions that cannot be executed because of an unresolved data dependency are deferred, and wherein other non-deferred instructions are executed in program order. Upon encountering a store during the execute-ahead mode, the system determines if the store buffer is full. If so, the system prefetches a cache line for the store, and defers execution of the store.

Abstract: A loop detector with an array to store a counter of loop iterations, where the number of entries in the array may be, for example, smaller than the number of entries in the loop detector. Entries in the array may, for example, be associated with more than one entry in the loop detector. The array may store, for example, a counter of speculative iterations of a loop or, for example, a number of actual iterations of a loop.

Abstract: An array-type computer processor stops, with a plurality of computer programs held, a state control unit and a data-path unit, upon input of event data for task switching. The array-type computer processor obtains the operation state of the state control unit and the processed data of the data-path unit when stopped, and temporarily holds them for each of a plurality of the computer programs. Upon completion of this, the array-type computer processor reads the operation state and processed data of any other computer program and sets them in the state control unit and data-path unit. Upon completion of this, the array-type computer processor outputs to the state control unit the event data for starting the operation. The state control unit then starts to sequentially transfer the operation state, thereby making it possible to perform the process operations according to a plurality of computer programs in a time-sharing manner.

Abstract: A method and apparatus for nested control flow includes a processor having at least one context bit. The processor includes a plurality of arithmetic logic units for performing single instruction multiple data (SIMD) operations. The method and apparatus further includes a first memory device storing a plurality of instructions wherein each of the plurality of instructions includes a plurality of extra bits. The processor is operative to execute the instructions based on the extra bits and in conjunction with a context bit. The method and apparatus further includes a second memory device, such as a general purpose register operably coupled to the processor, the second memory device receiving an incrementing counter instruction upon the execution of one of the plurality of instructions. As such, the method and apparatus allows for nested control flow through a single context bit in conjunction with instructions having a plurality of extra bits.

Abstract: At an MA stage, data, such as a header address of an interrupt processing routine, is loaded via a data bus and immediately supplied to a program counter via multiplexers without the intervention of an instruction decode stage in accordance with a setting address outputted from an EXE/MA buffer to an address bus. Thus, at the next processing timing at which the header address of the interrupt processing routine is loaded, the loaded header address is set in the program counter and fetching of a header instruction of the interrupt processing routine so that the interrupt processing routine can be immediately started.

Abstract: A method, completion table and processor for tracking a larger number of outstanding instructions. The completion table may include a plurality of entries where each entry tracks a consecutive number of outstanding instructions. Each entry may be configured to store an instruction address and an identification of a first of the consecutive number of outstanding instructions. By being able to track a consecutive number of outstanding instructions, such as the length of a cache line, in each entry in the completion table by only storing the instruction address and identification of the first of the consecutive number of outstanding instruction in that entry, the completion table may be able to track a larger number of outstanding instruction without increasing its size.

Abstract: According to some embodiments, a processing element includes (i) a next neighbor register to receive information directly from a previous processing element in a series of processing elements, and (ii) a previous neighbor register to receive information directly from a next processing element in the series.

Abstract: Execution of a single stand-alone instruction manipulates two n bit strings of data to pack data or align the data. Decoding of the single instruction identifies two registers of n bits each and a shift value, preferably as parameters of the instruction. A first and a second subset of data of less than n bits are selected, by logical shifting, from the two registers, respectively, based solely upon the shift value. Then, the subsets are concatenated, preferably by a logical OR, to obtain an output of n bits. The output may be aligned data or packed data, particularly useful for performing a single operation on multiple sets of the data through parallel processing with a SIMD processor.

Abstract: A hardware looping mechanism and method is described herein for handling any number and/or type of discontinuity instruction that may arise when executing program instructions within a scalar or superscalar processor. For example, the hardware looping mechanism may provide zero-overhead looping for branch instructions, in addition to single loop constructs and multiple loop constructs (which may or may not be nested). Zero-overhead looping may also be provided in special cases, e.g., when servicing an interrupt or executing a branch-out-of-loop instruction. In addition to reducing the number of instructions required to execute a program, as well as the overall time and power consumed during program execution, the hardware looping mechanism described herein may be integrated within any processor architecture without modifying existing program code.

Abstract: A processor including a register file and method for computing flush masks in a multi-threaded processing system provides fast and low-logic-overhead computation of a flush result in response to multiple flush request sources. A flush mask register file is implemented by multiple cells in an array where cells are absent from the diagonal where the column index is equal to the row index. Each cell has a vertical write enable and a horizontal write enable. When a row is written to validate that row's tag value, the column having an index equal to the row selector is automatically reset (excepting the absent cell mentioned above) . On a read of a row, a wired-AND circuit provided at each column provides a bit field corresponding to other rows that have been written since a last reset of the row, which is a flush mask indicating newer tags and the selected tag.

Abstract: Methods and apparatus are provided for branch prediction in a digital processor. A method includes providing a branch target buffer having a tag array and a data array, wherein each entry in the tag array provides an index to a corresponding entry in the data array, storing in a selected entry in the tag array information representative of a branch target of a current branch instruction, storing in a corresponding entry in the data array information representative of a branch target of a next branch instruction, and providing the information representative of the branch target of the next branch instruction in response to a match to an entry in the tag array. The information representative of the branch target of the next branch instruction may include a taken branch target address of the next branch instruction and an offset value. The offset value may represent an address of a next sequential instruction following the next branch instruction.

Abstract: According to some embodiments, a dynamic region in a register file may be described for an operand. The described region may, for example, store multiple data elements, each data element being associated with an execution channel of an execution engine. Information may then be stored into and/or retrieved from the register file in accordance with the described region.

Abstract: Methods and systems that allow recovery of the program counter or instruction pointer for a target (non-native) instruction that is translated into a host (native) instruction, and that allow recovery of other information about the translator or the target system state, are described. The program counter or instruction pointer can be recovered, for example, after an exception has been processed or incident to a rollback operation.

Abstract: A system for executing instructions is presented. In some embodiments, among others, the system comprises functional units, local multiplexers, local register files, and a global register file, which are communicatively coupled to each other and arranged to accommodate shortened instruction words in multiple-issue processors. These components are arranged to permit greater access to registers by instructions, thereby permitting reduction of the word length, as compared to conventional very long instruction word (VLIW) processors.

Abstract: Method and apparatus for non-lock-step operation between a processor and a controller is described. An instruction is provided from the processor to the controller. A busy signal is provided from the controller to the processor to indicate that the controller is not ready to execute the instruction. Initiation of execution of the instruction by the controller is done while continuing to indicate to the processor that the controller is not ready to execute the instruction.