436 results about "Execution cycle" patented technology

A method is shown for selecting active, or hot, code traces in an executing program for storage in a code cache. A trace is a sequence of dynamic instructions characterized by a start address and a branch history which allows the trace to be dynamically disassembled. Each trace is terminated by execution of a trace terminating condition which is a backward taken branch, an indirect branch, or a branch whose execution causes the branch history for the trace to reach a predetermined limit. As each trace is generated by the executing program, it is loaded into a buffer for processing. When the buffer is full, a counter corresponding to the start address of each trace is incremented. When the count for a start address exceeds a threshold, then the start address is marked as being hot. Each hot trace is then checked to see if the next trace in the buffer shares the same start address, in which case the hot trace is cyclic. If the start address of the next trace is not the same as the hot trace, then the traces in the buffer are checked to see they form a larger cycle of execution. If the traces subsequent to the hot trace are not hot themselves and are followed by a trace having the same start address as the hot trace, then their branch histories are companded with the branch history of the hot trace to form a cyclic trace. The cyclic traces are then disassembled and the instructions executed in the trace are stored in a code cache.

An apparatus, method, and system are described herein for providing programmable control of performance / event counters. An event counter is programmable to track different events, as well as to be checkpointed when speculative code regions are encountered. So when a speculative code region is aborted, the event counter is able to be restored to it pre-speculation value. Moreover, the difference between a cumulative event count of committed and uncommitted execution and the committed execution, represents an event count / contribution for uncommitted execution. From information on the uncommitted execution, hardware / software may be tuned to enhance future execution to avoid wasted execution cycles.

A computing device is described that comprises one or more hardware processors and a memory communicatively coupled to the one or more hardware processors. The memory comprises software that, when executed by the processors, operates as (i) a virtual machine and (ii) a hypervisor. The virtual machine includes a guest kernel that facilitates communications between a guest application being processed within the virtual machine and one or more virtual resources. The hypervisor configures a portion of the guest kernel to intercept a system call from the guest application and redirect information associated with the system call to the hypervisor. The hypervisor enables logic within the guest kernel to analyze information associated with the system call to determine whether the system call is associated with a malicious attack in response to the system call being initiated during a memory page execution cycle. Alternatively, the hypervisor operates to obfuscate interception of the system call in response to the system call being initiated during memory page read cycle.

A method and apparatus for controlling a DRAM refresh rate. In one embodiment, a computer system includes a memory subsystem having a memory controller and one or more DRAM (dynamic random access memory) devices. The memory controller is configured to periodically initiate a refresh cycle to the one or more DRAM devices. The memory controller is also configured to monitor the temperature of the one or more DRAM devices. If the temperature exceeds a preset threshold, the memory controller is configured to increase the rate at which the periodic refresh cycle is performed.

Disclosed is a method and system for performing periodic replication using a write-ordered log. According to one embodiment, a plurality of write operations to a primary data volume are tracked using a write operation log and then data associated with the plurality of write operations is replicated to a secondary data volume by coalescing the plurality of write operations utilizing the write operation log and transferring data associated with the plurality of write operations to the secondary data volume. According to another embodiment the described tracking includes storing metadata associated with the plurality of write operations within the write operation log. In another embodiment, the described coalescing includes identifying a non-overlapping portion of a first write operation and a second write operation of the plurality of write operations utilizing the metadata.

An apparatus and method for fine-grained multithreading in a multipipelined processor core. According to one embodiment, a processor may include instruction fetch logic configured to assign a given one of a plurality of threads to a corresponding one of a plurality of thread groups, where each of the plurality of thread groups may comprise a subset of the plurality of threads, to issue a first instruction from one of the plurality of threads during one execution cycle, and to issue a second instruction from another one of the plurality of threads during a successive execution cycle. The processor may further include a plurality of execution units, each configured to execute instructions issued from a respective thread group.

Hard, real-time, multi-tasking system is monitored by combined hardware and software and logic to detect overrun of any task beyond a declared maximum processor cycle limit for the task. Processor execution cycles utilized by DMA or interrupt processing and not related to the task being executed are not counted. Counter hardware and control logic reduces software overhead for monitoring execution cycle utilization by a task and provides capability not only of overrun detection, but programmed cycle usage alarm, consumed cycle count and overall processor loading or utilization measurements to be made.

A method efficiently dispatches / completes a work element within a multi-node, data processing system that has a global command queue (GCQ) and at least one high latency node. The method comprises: at the high latency processor node, work scheduling logic establishing a local command / work queue (LCQ) in which multiple work items for execution by local processing units can be staged prior to execution; a first local processing unit retrieving via a work request a larger chunk size of work than can be completed in a normal work completion / execution cycle by the local processing unit; storing the larger chunk size of work retrieved in a local command / work queue (LCQ); enabling the first local processing unit to locally schedule and complete portions of the work stored within the LCQ; and transmitting a next work request to the GCQ only when all the work within the LCQ has been dispatched by the local processing units.

Microprocessor that includes a mechanism for detecting soft errors. The processor includes an instruction fetch unit for fetching an instruction and an instruction decoder for decoding the instruction. The mechanism for detecting soft errors includes duplication hardware for duplicating the instruction and comparison hardware. The processor further includes a first execution unit for executing the instruction in a first execution cycle and the duplicated instruction in a second execution cycle. The comparison hardware compares the results of the first execution cycle and the results of the second execution cycle. The comparison hardware can include an exception unit for generating an exception (e.g., raising a fault) when the results are not the same. The processor also includes a commit unit for committing one of the results when the results are the same.

A self testing fault detector having a line side and a load side and a conductive path there between, said apparatus is provided. The self testing fault detector includes a controller, adapted to perform periodic status tests on a protection circuit of the self testing fault detector without interrupting power to the load.

Proposed is a method, implemented in software, for estimating fault state of an apparatus outfitted with sensors. At each execution period the method processes sensor data from the apparatus to obtain a set of parity parameters, which are further used for estimating fault state. The estimation method formulates a convex optimization problem for each fault hypothesis and employs a convex solver to compute fault parameter estimates and fault likelihoods for each fault hypothesis. The highest likelihoods and corresponding parameter estimates are transmitted to a display device or an automated decision and control system. The obtained accurate estimate of fault state can be used to improve safety, performance, or maintenance processes for the apparatus.

In a distributed computing system, an end terminal transmits a job execution request to a job scheduler, which in response determines a resource and a job execution period necessary for executing a job on the resource based on contents of the job indicated in the message. A reservation request message containing the job execution period and the resource identity is sent from the job scheduler to a target resource proxy. The resource proxy determines a scheduled period of the resource based on the job execution period by checking its schedule memory, and transmits a reservation response to the job scheduler. The job scheduler acquires a certificate signed by the user from the end terminal and transmits the acquired certificate to the resource proxy. In response to the certificate of the user, the resource proxy makes a reservation of the identified resource according to the scheduled period.

A method, apparatus and computer system for correcting errors and defects in a storage device. The storage device includes media for storing data. A periodic read scan is performed to test the data. If a repeatable error is found, the data is moved to a new sector from a pool of available sectors. Defects are counted and identified in a defect list for reporting to the host. The storage device is scannable is small segments to minimize impact on performance.

One embodiment of the present disclosure sets forth an effective way to maintain fairness and order in the scheduling of common resource access requests related to replay operations. Specifically, a streaming multiprocessor (SM) includes a total order queue (TOQ) configured to schedule the access requests over one or more execution cycles. Access requests are allowed to make forward progress when needed common resources have been allocated to the request. Where multiple access requests require the same common resource, priority is given to the older access request. Access requests may be placed in a sleep state pending availability of certain common resources. Deadlock may be avoided by allowing an older access request to steal resources from a younger resource request. One advantage of the disclosed technique is that older common resource access requests are not repeatedly blocked from making forward progress by newer access requests.

Apparatus and methods implemented in a processor semiconductor logic chip for providing novel “hint instructions” that uniquely preserve and reuse branch predictions replaced in a branch history table (BHT). A branch prediction is lost in the BHT after its associated instruction is replaced in an instruction cache. The unique “hint instructions” are generated and stored in a unique instruction cache which associates each hint instruction with a line of instructions. The hint instructions contains the latest branch history for all branch instructions executed in an associated line of instructions, and they are stored in the instruction cache during instruction cache hits in the associated line. During an instruction cache miss in an instruction line, the associated hint instruction is stored in a second level cache with a copy of the associated instruction line being replaced in the instruction cache. In the second level cache, the copy of the line is located through the instruction cache directory entry associated with the line being replaced in the instruction cache. Later, the hint instruction can be retrieved into the instruction cache when its associated instruction line is fetched from the second level cache, and then its associated hint instruction is also retrieved and used to restore the latest branch predictions for that instruction line. In the prior art this branch prediction would have been lost. It is estimated that this invention improves program performance for each replaced branch prediction by about 80%, due to increasing the probability of BHT bits correctly predicting the branch paths in the program from about 50% to over 90%. Each incorrect BHT branch prediction may result in the loss of many execution cycles, resulting in additional instruction re-execution overhead when incorrect branch paths are belatedly discovered.

A system, apparatus and method for instruction dispatch on a multi-thread processing device are described herein. The instruction dispatching method includes, in an instruction execution period having a plurality of execution cycles, successively fetching and issuing an instruction for each of a plurality of instruction execution threads according to an allocation of execution cycles of the instruction execution period among the plurality of instruction execution threads. Remaining execution cycles are subsequently used to successively fetch and issue another instruction for each of the plurality of instruction execution threads having at least one remaining allocated execution cycle of the instruction execution period. Other embodiments may be described and claimed.

A system executes services by a “server” for a “client”. A preliminary step establishes a list of available services of the server, set up for the client, in which a processing time is determined releasable by the server for the client per code execution cycle MIF. The system creates on start-up: NT execution tasks for the client, each having a priority of execution level and an allocated average duration of execution, NT being at least 1, the sum of durations of the tasks being at most the releasable processing time; execution rules associating each of the tasks with at least one service of the list; then, during each MIF cycle, the system executes the services on their associated tasks, a task executed by priority and for at most its allocated average time of execution, the non-executed part of a service being executed on its associated task in the next cycle.

A microprocessor with a floating point unit configured to rapidly execute floating point load control word (FLDCW) type instructions in an out of program order context is disclosed. The floating point unit is configured to schedule instructions older than the FLDCW-type instruction before the FLDCW-type instruction is scheduled. The FLDCW-type instruction acts as a barrier to prevent instructions occurring after the FLDCW-type instruction in program order from executing before the FLDCW-type instruction. Indicator bits may be used to simplify instruction scheduling, and copies of the floating point control word may be stored for instruction that have long execution cycles. A method and computer configured to rapidly execute FLDCW-type instructions in an out of program order context are also disclosed.

A system and method for maintaining checkpoints of a keyed data structure using a sequential log are provided. The system and method are built upon the idea of writing all updates to a keyed data structure in a physically sequential location. The system and method make use of a two-stage operation. In a first stage, various values of the same key are combined such that only the latest value in a given checkpoint interval is maintained for writing to persistent storage. In a second stage of the operation, a periodic write operation is performed to actually store the latest values for the key-value pairs to a persistent storage. All such updates to key-value pairs are written to the end of a sequential log. This minimizes the physical storage input / output (I / O) overhead for the write operations. Data structures are provided for identifying the most current entries in the sequential log for each key-value pair.

A processor that includes an in-order execution architecture for executing at least two instructions per cycle (e.g., 2n instructions are processed per cycle, where n is an integer greater than or equal to one) and at least two symmetric execution units. The processor includes an instruction fetch unit for fetching n instructions (where n is an integer greater than or equal to one) and an instruction decoder for decoding the n instruction. The error detection mechanism includes duplication hardware for duplicating the n instructions into a first bundle of n instructions and a second bundle of n instructions. A first execution unit for executing the first bundle of instructions in a first execution cycle, and a second symmetric execution unit for executing the second bundle of instructions in the first execution cycle are provided. The error detection mechanism also includes comparison hardware for comparing the results of the first execution unit and the results of the second execution unit. The comparison hardware can have an exception unit for generating an exception (e.g., raising a fault) when the results are not the same. A commit unit is provided for committing one of the results when the results are the same.

An apparatus includes a processor for executing instructions at runtime and instructions for dynamically compiling the set of instructions executing at runtime. A memory device stores the instructions to be executed and the dynamic compiling instructions. A memory device serves as a trace buffer used to store traces during formation during the dynamic compiling. The dynamic compiling instructions includes a next-executing-cycle (N-E-C) trace selection process for forming traces for the instructions executing at runtime. The N-E-C trace selection process continues through an existing trace-head when forming traces without terminating a recording of a current trace if an existing trace-head is encountered.

A system and method for viewing timing of one or more loops in a graphical program. A graphical program having one or more loops may be created. In one embodiment the one or more loops may include one or more timed loops, i.e., the loops may be configured to execute according to particular execution periods. The graphical program may be executed, and timing analysis data regarding timing of the one or more loops during execution of the graphical program may be stored. A graphical user interface (GUI) for viewing timing of the one or more loops during execution of the graphical program may be displayed. In various embodiments the GUI may display any of various kinds of information regarding timing of the one or more loops, and any kind of visual presentation may be used in displaying the information.

A system and method for using command buffers as timeslices or periods of execution for a long running compute task on a graphics processor. Embodiments of the present invention allow execution of long running compute applications with operating systems that manage and schedule graphics processing unit (GPU) resources and that may have a predetermined execution time limit for each command buffer. The method includes receiving a request from an application and determining a plurality of command buffers required to execute the request. Each of the plurality of command buffers may correspond to some portion of execution time or timeslice. The method further includes sending the plurality of command buffers to an operating system operable for scheduling the plurality of command buffers for execution on a graphics processor. The command buffers from a different request are time multiplexed within the execution of the plurality of command buffers on the graphics processor.

A microprocessor is configured to provide port arbitration in a register file. The microprocessor includes a plurality of functional units configured to collectively operate on a maximum number of operands in a given execution cycle, and a register file providing a number of read ports that is insufficient to provide the maximum number of operands to the plurality of functional units in the given execution cycle. The microprocessor also includes an arbitration logic coupled to allocate the read ports of the register file for use by selected functional units during the given execution cycle.

A system and method for managing the dynamic sharing of processor resources between threads in a multi-threaded processor are disclosed. Out-of-order allocation and deallocation may be employed to efficiently use the various resources of the processor. Each element of an allocate vector may indicate whether a corresponding resource is available for allocation. A search of the allocate vector may be performed to identify resources available for allocation. Upon allocation of a resource, a thread identifier associated with the thread to which the resource is allocated may be associated with the allocate vector entry corresponding to the allocated resource. Multiple instances of a particular resource type may be allocated or deallocated in a single processor execution cycle. Each element of a deallocate vector may indicate whether a corresponding resource is ready for deallocation. Examples of resources that may be dynamically shared between threads are reorder buffers, load buffers and store buffers.

Methods are disclosed that dynamically improve soft real-time task performance in virtualized computing environments under the management of an enhanced hypervisor comprising a credit scheduler. The enhanced hypervisor analyzes the on-going performance of the domains of interest and of the virtualized data-processing system. Based on the performance metrics disclosed herein, some of the governing parameters of the credit scheduler are adjusted. Adjustments are typically performed cyclically, wherein the performance metrics of an execution cycle are analyzed and, if need be, adjustments are applied in a later execution cycle. In alternative embodiments, some of the analysis and tuning functions are in a separate application that resides outside the hypervisor. The performance metrics disclosed herein include: a “total-time” metric; a “timeslice” metric; a number of “latency” metrics; and a “count” metric. In contrast to prior art, the present invention enables on-going monitoring of a virtualized data-processing system accompanied by dynamic adjustments based on objective metrics.