Abstract: A memory storage structure includes a memory storage device, and a first meta-structure having a first size and operating at a first speed. The first speed is faster than a second speed for storing meta-information based on information stored in a memory. A second meta-structure is hierarchically associated with the first meta-structure. The second meta-structure has a second size larger than the first size and operates at the second speed such that faster and more accurate prefetching is provided by coaction of the first and second meta-structures. A method is provided to assemble the meta-information in the first meta-structure and copy this information to the second meta-structure, and prefetching the stored information from the second meta-structure to the first meta-structure ahead of its use.

Abstract: A method and an apparatus for enabling a prefetch engine to detect and support hardware prefetching with different streams in received accesses. Multiple (simple) history tables are provided within (or associated with) the prefetch engine. Each of the multiple tables is utilized to detect different access patterns. The tables are indexed by different parts of the address and are accessed in a preset order to reduce the interference between different patterns. When an address does not fit the patterns of a first table, the address is passed to the next table to be checked for a match of different patterns. In this manner, different patterns may be detected at different tables within a single prefetch engine.

Abstract: The information processing device of the present invention stores the branch history information of a fetched instruction. When branch prediction fails, BHR information used for the branch prediction is restored using this stored branch history information. Thus, even when branch prediction fails, BHR information can be accurately restored. Accordingly, prediction accuracy can be improved.

Abstract: An estimator suitable for hot-path detection conducted while managing the history of the executed instructions is provided.

Abstract: A method for branch prediction, the method comprising, receiving a load instruction including a first data location in a first memory area, retrieving data including a branch address and a target address from the first data location data location, and saving the data in a branch prediction memory.

Abstract: Associated with an instruction in a program is a computation history. The computation history represents all objects that affect the result of the instruction, such objects including (but not limited to) registers, memory locations, static values, and instruction program counters. The computation history may be used to make a prediction about a property of the instruction.

Abstract: A system is disclosed for providing branch misprediction prediction in a microprocessor. The system includes a mispredicted branch table that includes address, distance, and true/not true fields, and an index to the mispredicted branch table that is formed responsive to 1) a current mispredicted branch, 2) a global history, 3) a global misprediction history, and 4) a branch misprediction distance.

Abstract: Provided is a means for accessing multiple entries from a branch history table (BHT) in a single clock cycle, in the context of pipelined instruction processing. In a first clock cycle, a plurality of conditional branch instructions is fetched. A value is accessed from a global history record (GHR) of conditional branch resolutions and predictions for a fetched conditional branch instruction. An associated instruction address is hashed with a left-shifted GHR value. The result is used to access a word in an indexed BHT stored in a single-port random access memory (RAM). The word comprises a branch direction count for the plurality of fetched conditional branch instructions. In a second clock cycle a conditional branch instruction is executed at an execute stage and the BHT is written with an updated branch direction count in response to a resolution of the executed conditional branch instruction.

Abstract: The present invention relates to an information processing apparatus predicting a branch destination of a branch instruction using a branch history register to realize effective replacement by enabling an unnecessary entry to be selected as an entry, which is an object of replacement, without using new resources in a full-associative memory device. The invention includes a selector for selecting one entry from all entries of a past branch history memory section if all entries of the past branch history memory section are in use when a branch history about a new branch instruction is registered into the past branch history memory section and a replacing section for registering the branch history about the new branch instruction into one entry selected by said selector, wherein the selector has a first selecting function of selecting one entry based on the branch history held by the past branch history memory section.

Abstract: Methods, apparatus, and products for branch prediction in a computer processor are disclosed that include: recording for a sequence of occurrences of a branch, in an algorithm in which the branch occurs more than once, each result of the branch, including maintaining a pointer to a location of a most recently recorded result; resetting the pointer to a location of the first recorded result upon completion of the algorithm; and predicting subsequent results of the branch, in subsequent occurrences of the branch, in dependence upon the recorded results.

Abstract: Concurrently branch predicting for multiple branch-type instructions demands of high performance environments. Concurrently branch predicting for multiple branch-type instructions provides the instruction flow for a high bandwidth pipeline utilized in advanced performance environments. Branch predictions are concurrently generated for multiple branch-type instructions. The concurrently generated branch predictions are then supplied for further processing of the corresponding branch-type instructions.

Abstract: A system and method for performing search area confined branch prediction in a processor are provided. The system includes a branch target buffer (BTB) to hold branch information for branch prediction, where the branch information includes a branch address. The system also includes search logic for searching the BTB to locate a branch address. The system additionally includes throttle logic to stop searching the BTB in response to reaching a predefined search limit.

Abstract: A method, system and computer product for purging pattern history tables as a function of global accuracy in a state machine-based filter gshare branch predictor. An exemplary embodiment includes a method including storing a plurality of encountered branch instructions in the branch history table, indexing the branch history table by a branch instruction address, modifying an entry of the branch history table, indexing the pattern history table, selecting at least one of a branch history entry and a pattern history table entry as a prediction for the branch instruction, wherein the pattern history table entry is selected as the prediction for the branch instruction in response to the branch history entry being in a state specifying to use the pattern history table entry, comparing a pattern history table accuracy to an accuracy threshold, and in response to the pattern history table accuracy falling below the accuracy threshold, purging the PHT.

Abstract: A data processor that addresses instructions as groups of commands which may contain more than one branch command, such as VLIW instructions that contain several commands for parallel execution. The processor selects an expected taken branch command from the branch commands in a group. The processor also selects a tentative target for the expected taken branch command and tentatively redirects control flow to a further group of commands identified by the tentative target. The processor contains an associative target memory for storing targets of previously executed branch commands. Targets are retrieved with an associative address that identifies a command in the group, the tentative target being selected on the basis of a match between the associative address associated with the tentative target and an indication of the expected taken command.

Abstract: System and method for reducing branch prediction latency using a branch target buffer with most recently used column prediction. An exemplary embodiment includes a method for reducing branch prediction latency, the method including reading most-recently-used information from a most-recently-used table associated with the branch target buffer where each most-recently-used entry corresponds to one or more branch target buffer rows and specifies the ordering from least-recently-used to most-recently-used of the associated branch target buffer columns, selecting a row from the branch target buffer and simultaneously selecting the associated entry from the most-recently-used table and speculating that there is a prediction in the most recently used column of the plurality of columns from the selected row from the branch target buffer while determining whether there is a prediction and which column contains the prediction.

Abstract: A system for using complex branch execution hardware and a hardware based Multiplex (MUX) to multiplex a fetch address of a future branch and a branch fetch address to one index hash value used to index a branch target prediction table for execution by a processor core, to reduce branch mis-prediction by preloading.

Abstract: In at least one embodiment, a processor includes at least one execution unit that executes instructions and instruction sequencing logic, coupled to the at least one execution unit, that fetches instructions from a memory system for execution by the at least one execution unit. The instruction sequencing logic including a branch target address cache (BTAC) including a plurality of entries for storing branch target address predictions. The BTAC includes index logic that selects an entry to access utilizing a BTAC index based upon at least a set of higher order bits of an instruction address and a set of lower order bits of the instruction address.

Abstract: A global history vector (GHV) mechanism maintains a folded GHV with higher order entries an an unfolded GHV with lower order entries. When a new entry arrives at the GHV, the GHV mechanism performs an XOR of the oldest unfolded entry in the unfolded GHV with the new entry. The XOR result is then shifted into the folded GHV as the newest folded entry. The oldest folded entry is discarded during the shift in of the newest folded entry. The GHV mechanism thus provides a resulting folded GHV that is current and can be utilized for XORing with an IFAR by performing an XOR operation. Only a single XOR logic is required to perform a single bit XOR operation between the oldest entry and the youngest entry, resulting in reducing the cycle time required to complete the folding operation on a GHV.

Abstract: A system and method are provided for updating a global history prediction record in a microprocessor system using pipelined instruction processing. The method accepts a microprocessor instruction of consecutive operations, including a conditional branch operation with an associated branch address, at a first stage in a pipelined microprocessor execution process. A global history record (GHR) of conditional branch resolutions and predictions is accessed and hashed with the branch address, creating a first hash result. The first hash result is used to access an indexed branch history table (BHT) of branch direction counts and the BHT is used to make a branch prediction. If the branch prediction being “taken”, the current GHR value is left-shifted and hashed with the branch address, creating a second hash result which is used in creating an updated GHR.

Abstract: Systems, methods and apparatuses for the generation of a global history are disclosed. Embodiments of the present invention may provide logic operable to generate a global history and a global history register operable to store a global history. More specifically, in one embodiment the global history logic comprises a set of multiplexers, each set corresponding to one of a set of instructions fetched in a cycle of a microprocessor, the number of multiplexers in each set equal to the number of bits of global history and each multiplexer within a set having a select signal corresponding to the same instruction to which that set of multiplexers corresponds.

Abstract: Systems and methods are provided to detect instances where dynamic predication of indirect jumps (DIP) is considered to be ineffective utilizing data collected on the recent effectiveness of dynamic predication on recently executed indirect jump instructions. Illustratively, a computing environment comprises a DIP monitoring engine cooperating with a DIP monitoring table that aggregates and processes data representative of the effectiveness of DIP on recently executed jump instructions. Illustratively, the exemplary DIP monitoring engine collects and processes historical data on DIP instances, where, illustratively, a monitored instance can be categorized according to one or more selected classifications. A comparison can be performed for currently monitored indirect jump instructions using the collected historical data (and classifications) to determine whether DIP should be invoked by the computing environment or whether to invoke other indirect jump prediction paradigms.

Abstract: A system and method for efficient improvement of branch prediction in a microprocessor with negligible impact on die-area, power consumption, and clock cycle period. It is determined if a program counter (PC) register contains a polymorphic indirect unconditional branch (PIUB) instruction. One determination may be searching a table with a portion or all of a PC of past PIUB instructions. If a hit occurs in this table, the global shift register (GSR) is updated by shifting a portion of the branch target address into the GSR, rather than updating the GSR with a taken/not-taken prediction bit. The stored value in the GSR is input into a hashing function along with the PC in order to index prediction tables such as a pattern history table (PHT), a branch target buffer (BTB), an indirect target array, or other. The updated value due to the PIUB instruction improves the accuracy of the prediction tables.

Abstract: The invention provides a method and apparatus for branch prediction in a processor. A fetch-block branch target buffer is used in an early stage of pipeline processing before the instruction is decoded, which stores information about a control transfer instruction for a “block” of instruction memory. The block of instruction memory is represented by a block entry in the fetch-block branch target buffer. The block entry represents one recorded control-transfer instruction (such as a branch instruction) and a set of sequentially preceding instructions, up to a fixed maximum length N. Indexing into the fetch-block branch target buffer yields an answer whether the block entry represents memory that contains a previously executed a control-transfer instruction, a length value representing the amount of memory that contains the instructions represented by the block, and an indicator for the type of control-transfer instruction that terminates the block, its target and outcome.

Abstract: A frequency-based prediction of indirect jumps executing in a computing environment is provided. Illustratively, a computing environment comprises a prediction engine that processes data representative of indirect jumps performed by the exemplary computing environment according to a selected frequency-based prediction paradigm. Operatively, the exemplary prediction engine can keep track of targets, in a table, taken for each indirect jump and program context (e.g., branch history and/or path information) of an exemplary computing program. Further, the prediction engine can also store a frequency counter associated with each target in the exemplary table. Illustratively, the frequency counter can record the number of times a target was taken in the recent past executions of an observed one or more indirect jump. The prediction engine can supply the target address of an indirect jump based on the values of the frequency counters of each stored target address.

Abstract: A system and method are provided for updating a speculative global history prediction record in a microprocessor system using pipelined instruction processing. The method accepts microprocessor instructions with consecutive operations, including a conditional branch operation with an associated first branch address. A speculative global history record (SGHR) of conditional branch resolutions and predictions is accessed and hashed with the first branch address, creating a first hash result. The first hash result is used to index a branch history table (BHT) of previous first branch resolutions. As a result, a first branch prediction is made, and the SGHR is updated with the first branch prediction. A non-speculative global history record (NSGHR) of branch resolutions is updated with the resolution of the first branch operation, and if the first branch prediction is incorrect, the SGHR is corrected using the NSGHR.

Abstract: In one embodiment, the present invention includes a method for determining if an entry corresponding to a prediction address is present in a first predictor, and overriding a prediction output from a second predictor corresponding to the prediction address if the entry is present in the first predictor. Other embodiments are described and claimed.

Abstract: A polymorphic branch predictor and method includes a plurality of branch prediction methods. The methods are selectively enabled to perform branch prediction. A selection mechanism is configured to select one or more of the branch prediction methods in accordance with a dynamic setting to optimize performance of the branch predictor during operation in accordance with a current task.

Abstract: Methods, systems and computer program products for concomitant pair per-fetching. Exemplary embodiments include a method for concomitant pair prefetching, the method including detecting a stride pattern, detecting an indirect access pattern to define an access window, prefetching candidates within the defined access window, wherein the prefetching comprises obtaining prefetch addresses from a history table, updating a miss stream window, selecting a candidate of a concomitant pair from the miss stream window, producing an index from the candidate pair, accessing an aging filter, updating the history table and selecting another concomitant pair candidate from the miss stream window.

Abstract: Methods and apparatus are provided for enhanced instruction handling in processing environments. If branch misprediction occurs during instruction processing, a branch history table may be updated based upon the number of instructions to be fetched. The branch history table may be updated in accordance with a first mode if at least two instructions are available, and may be updated in accordance with a second mode if less than two instructions are available. A compiler can assist the processing by aligning instructions for processing. The instructions can be aligned across multiple instruction fetch groups so that instructions are available for fetching and the branch history table is updated prior to performing a branching operation.

Abstract: A two level branch history table (TLBHT) is substantially improved by providing a mechanism to prefetch entries from the very large second level branch history table (L2 BHT) into the active (very fast) first level branch history table (L1 BHT) before the processor uses them in the branch prediction process and at the same time prefetch cache misses into the instruction cache. The mechanism prefetches entries from the very large L2 BHT into the very fast L1 BHT before the processor uses them in the branch prediction process. A TLBHT is successful because it can prefetch branch entries into the L1 BHT sufficiently ahead of the time the entry is needed. This feature of the TLBHT is also used to prefetch instructions into the cache ahead of their use. In fact, the timeliness of the prefetches produced by the TLBHT can be used to remove most of the cycle time penalty incurred by cache misses.

Abstract: Methods and related computer program products, systems, and devices for using a NAND flash as a program ROM are disclosed.

Abstract: A branch prediction device capable of preventing degradation of branch prediction accuracy and a delay in processing speed is provided. The branch prediction device includes a branch prediction information accumulation processing section which stores branch prediction groups in which a plurality of pieces of branch prediction information are grouped, and performs accumulation-processing of the branch prediction information. The branch prediction device further includes a pipeline access control section which performs processing, upon request, by pipeline processing, including first selection control processing for selection-controlling at least one branch prediction group from the branch prediction groups, and second selection control processing for selection-controlling one or a plurality of pieces of branch prediction information from the branch prediction group, and controls an access to the branch prediction information accumulation processing section.

Abstract: Embodiments of the invention provide a method of storing branch prediction information. In one embodiment, the method includes receiving a branch instruction and storing local branch prediction information for the branch instruction including a local predictability value for the local branch prediction information. The method further includes storing global branch prediction information for the branch instruction only if the local predictability value is below a threshold value of predictability.

Abstract: A data processing system includes at least first and second coherency domains each containing at least one processing unit, an interconnect fabric coupling the first and second coherency domains, and a cache memory within the first coherency domain. The cache memory comprises a data array, a cache directory of contents of the data array, and a cache controller including a prefetch predictor. The prefetch predictor determines a predicted scope of broadcast on the interconnect fabric for a first prefetch operation having a first target address based upon a scope of a previous second prefetch operation having a different second target address. The cache controller issues the first prefetch operation on the interconnect fabric with the predicted scope.

Abstract: One embodiment of the present invention provides a system that predicts a jump target for a jump instruction. During operation, the system starts fetching the jump instruction while executing a process. Next, the system uses a program counter for the process and uses state information that is specific to the process to look up the jump target for the jump instruction. Finally, the system uses the jump target returned by the lookup as a predicted jump target for the jump instruction.

Abstract: One aspect of the embodiments utilizes a branch instruction predicting unit includes a history memory to store a branch address as history information, a selecting unit to select a storing place with reference to selection information for selecting either one of storing places when the branch address of the branch instruction is stored as the history information, In the case that there are a plurality of branch addresses to be stored at a storing place, when a first branch address is stored at a storing place, a second branch address is stored at a storing place in accordance with selection information updated by the updating unit.

Abstract: A system and method for optimizing the branch logic of a processor to improve handling of hard to predict indirect branches are provided. The system and method leverage the observation that there will generally be only one move to the count register (mtctr) instruction that will be executed while a branch on count register (bcctr) instruction has been fetched and not executed. With the mechanisms of the illustrative embodiments, fetch logic detects that it has encountered a bcctr instruction that is hard to predict and, in response to this detection, blocks the target fetch from entering the instruction buffer of the processor. At this point, the fetch logic has fetched all the instructions up to and including the bcctr instruction but no target instructions. When the next mtctr instruction is executed, the branch logic of the processor grabs the data and starts fetching using that target address.

Abstract: A branch prediction control device, in an information processing unit which performs a pipeline process, generates a branch prediction address used for verification of an instruction being speculatively executed. The branch prediction control device includes a first return address storage unit storing the prediction return address, a second return address storage unit storing a return address to be generated depending on an execution result of the call instruction, and a branch prediction address storage unit sending a stored prediction return address as a branch prediction address and storing the sent branch prediction address. When the branch prediction address differs from a return address, which is generated after executing a branch instruction or a return instruction, contents stored in the second return address storage unit are copied to the first return address storage unit.

Abstract: In one embodiment, a processor comprises a branch prediction array, an index generator coupled to the branch prediction array, and a control unit coupled to the index generator. The branch prediction array is configured to store a plurality of branch predictions for conditional branches. The index generator is configured to generate an index to the branch prediction array responsive to at least a portion of a fetch address corresponding to a fetch request that is at a first pipeline stage of the processor and further responsive to a branch history. The control unit is configured to update the branch history responsive to a first fetch request at the first pipeline stage and to defer the update for a second fetch request to a second pipeline stage subsequent to the first pipeline stage.

Abstract: A method of tentative tracing execution events in a multiprocessor system. Each processor stores tentative events in a corresponding buffer. The processor sets pointers in an array to a head and tail of a thread. When a condition triggers a tentative thread to be committed, the processor marks the first event as committed and sets the pointers to a null value. When a condition triggers the thread to be discarded, the processor marks the first event as discarded and sets the pointers to a null value. The processor makes the buffer available to a consumer process, which extracts the first event. If the first event is marked as committed, the consumer process follows a link to a second event of the thread and marks the second event as committed. If the first event is marked as discarded, the second event is marked as discarded and the first event is skipped.

Abstract: A method and apparatus for updating global branch history information are disclosed. A dynamic branch predictor within a data processing system includes a global branch history (GBH) buffer and a branch history table. The GBH buffer contains GBH information of a group of the most recent branch instructions. The branch history table includes multiple entries, each entry is associated with one or more branch instructions. The GBH information from the GBH buffer can be used to index into the branch history table to obtain a branch prediction signal. In response to a fetch group of instructions, a fixed number of GBH bits is shifted into the GBH buffer. The number of GBH bits is the same regardless of the number of branch instructions within the fetch group of instructions. In addition, there is a unique bit pattern associated with the case of no taken branch in the fetch group, regardless of the number of not-taken branches of even if there are any branches in the fetch group.

Abstract: A processor core and method of executing instructions, both of which utilizes schedules, are presented. Each of the schedules includes a sequence of instructions, an address of a first of the instructions in the schedule, an order vector of an original order of the instructions in the schedule, a rename map of registers for each register in the schedule, and a list of register names used in the schedule. The schedule exploits instruction-level parallelism in executing out-of-order instructions. The processor core includes a schedule cache that is configured to store schedules, a shared cache configured to store both I-side and D-side cache data, and an execution resource for requesting a schedule to be executed from the schedule cache. The processor core further includes a scheduler disposed between the schedule cache and the cache.

Abstract: Methods for storing branch information in an address table of a processor are disclosed. A processor of the disclosed embodiments may generally include an instruction fetch unit connected to an instruction cache, a branch execution unit, and an address table being connected to the instruction fetch unit and the branch execution unit. The address table may generally be adapted to store a plurality of entries with each entry of the address table being adapted to store a base address and a base instruction tag. In a further embodiment, the branch execution unit may be adapted to determine the address of a branch instruction having an instruction tag based on the base address and the base instruction tag of an entry of the address table associated with the instruction tag. In some embodiments, the address table may further be adapted to store branch information.

Abstract: A method of representing instruction execution path history is provided. The method in one aspect may include gathering information associated with a current instruction, the information including at least a target address. Previously computed bits representing execution path history is modified and hashed based on the target address, to compute current execution path history.

Abstract: A branch prediction mechanism includes a history value register storing a history value which is used to address into a history buffer from which a plurality of prediction values are read and stored into a prediction value store. The one or more prediction values to be used with a potential branch instruction are selected from the prediction values store using a multiplexer switched by a branch predicting portion of a fetch address. The history buffer is only read when the history value changes whereas the prediction values store is read each time a potential branch instruction is identified requiting a prediction value to be associated with it. The reduced duty cycle of the history buffer saves power.

Abstract: A method, system, and computer program product are provided, for maintaining a path history register of register indirect branches. A set of bits is generated based on a set of target address bits using a hit selection and/or a hash function operation, and the generated set of bits is inserted into a path history register by shifting bits in the path history register and/or applying a hash operation, information corresponding to prior history is removed from the path history register, using a shift out operation and/or a hash operation. The path, history register is used to maintain a recent target, table and generate register-indirect branch target address predictions based on path history correlation between register-indirect branches captured by the path history register.

Abstract: A method and processor for reducing the fetch time of target instructions of a predicted taken branch instruction. Each entry in a buffer, referred to herein as a “branch target buffer”, may store an address of a branch instruction predicted taken and the instructions beginning at the target address of the branch instruction predicted taken. When an instruction is fetched from the instruction cache, a particular entry in the branch target buffer is indexed using particular bits of the fetched instruction. The address of the branch instruction in the indexed entry is compared with the address of the instruction fetched from the instruction cache. If there is a match, then the instructions beginning at the target address of that branch instruction are dispatched directly behind the branch instruction. In this manner, the fetch time of target instructions of a predicted taken branch instruction is reduced.

Abstract: A system, method and device for storing branch predictions in a queue that may be connected to a branch prediction unit, and for delivering the stored predictions to an instruction fetch unit. A look up may be made of for example two sequential lines, and for example a segmented cache of a branch prediction unit may generate predictions of an address having an even numbered index by referring to for example a first side of the cache, and an address with an odd numbered index by referring to for example a second side of the cache. Branch predictions for two sequential lines may be generated during for example a prediction period such as two clock cycles. In some embodiments, a next instruction pointer of a branch prediction unit may be independent or decoupled from of a next instruction pointer of an instruction fetch unit.

Abstract: A branch prediction mechanism includes a branch prediction memory and an extended pattern cache. The extended pattern cache detects predetermined repeating patterns of branch outcomes and stores a plurality of compressed representations of these such that when they recur their termination can be predicted. This enables program loops which are longer in length than can be represented within a reasonably sized branch prediction memory to nevertheless be detected and have their loop ends predicted.

Abstract: A multi-mode predictor for a processor having a plurality of prediction modes is disclosed. The prediction modes are used to predict non-binary values. The predictor is a multi-mode predictor comprising a per-IP (“PIP”) table and a next value table. The PIP table includes a plurality of PIP information fields and the next value table includes a plurality of fields. The multi-mode predictor also includes a plurality of prediction modes. The processor includes a set of instructions that index the PIP table to provide a valid signal. The processor also includes a set of predicted values for the set of instructions. The set of predicted values is stored in the PIP table and the next value table. According to the valid signal a hit/miss condition in the next value table, a predicted value is selected from the PIP table or the next value table.