CN102831019B - The dynamic estimation in the life-span of semiconductor devices - Google Patents

Abstract

In one embodiment, the present invention includes a kind of method, described method is for obtaining the dynamic duty parameter information of the semiconductor devices of such as processor, the entirety of described device or the dynamic service condition of one or more part is determined based on dynamic duty parameter information, and based on the residual life of device described in dynamic service condition dynamic estimation.Described device can be controlled according to desired mode according to estimation residual life.Also describe other embodiments, and require to protect it.

Description

The dynamic estimation in the life-span of semiconductor devices

The application is divisional application, its original application is International Patent Application PCT/ES2005/070188 that on May 22nd, 2008 enters National Phase in China, international filing date is on Dec 30th, 2005, the China national application number of this original application is 200580052138.5, and denomination of invention is " dynamic estimation in the life-span of semiconductor devices ".

Technical field

Embodiments of the invention relate to semiconductor devices, more specifically, relate to the expected life determining this device.

Background technology

The measurement in the life-span (that is, its time between failures) of semiconductor devices relates to the current and following technique, because transistor and other structures will become less, degenerates faster.The method in the life-span of this device of existing prediction is static method, its in temperature, voltage and frequency for supposing rigid condition whole device lifetime.But its dynamic perfromance may differ greatly with supposed rigid condition.In addition, each resource in integrated circuit (IC) works all under different conditions, thus will produce the different life-spans for different resources.

Device lifetime, a generation generation shortened.In addition, the life-span depends on the real work parameter of such as different operating voltage and temperature and convergent-divergent (scaling) trend of different technologies.This life-span shortened gradually is derived from some source of degradation: electromigration, stress migration, time correlation dielectric breakdown (TDDB), negative bias thermal instability (NBTI) and thermal cycle.Suppose that the failure rate caused by these factors is evenly distributed on five sources.Usually this failure rate is called down-time ratio (failuresintime, FIT), that is, 10 ⁹estimated faults amount in hour.The acquisition of FIT value can be adopted as the mean free error time (MTTF) of 1/FIT, and this is estimating of usual employing in the industry.For any technology, all can obtain MTTF by supposing steady-state operation under rigid condition (such as, temperature, voltage, frequency and utilization factor).

But temperature, voltage, frequency and utilization factor all can change along with circuit lifetime, thus homeostatic mechanism cannot life-span of Accurate Prediction device.Therefore, be necessary to improve lifetime measurement.

Accompanying drawing explanation

Fig. 1 is the block scheme of processor according to an embodiment of the invention;

Fig. 2 is the block scheme of processor according to another embodiment of the present invention;

Fig. 3 is the process flow diagram of method according to an embodiment of the invention;

Fig. 4 is the process flow diagram controlling resource according to one embodiment of present invention;

Fig. 5 is the block scheme of multicomputer system according to an embodiment of the invention.

Embodiment

In various embodiments, the dynamic estimation to the such as residual life of the semiconductor devices of processor, Memory Controller and other functional units can be performed.Can on the basis of each device (such as, integrated circuit (IC)) or on more fine-grained basis enterprising Mobile state life estimate.Such as, for the treatment of in the embodiment of device, in multi-core processor, life estimate can be carried out on the basis of each kernel.In addition, in other embodiments, life estimate can be carried out on the basis of each piece, such as, life estimate be carried out on the basis of each functional unit, cache structure, register file or other blocks.

Life estimate both can consider the working time of device, considered that again device is in the time of idle condition.In this way, the accurate estimation of residual life can be determined.As will be further discussed like that, can perform the service condition of device or the judgement of so-called mileage (mileage) according to periodic intervals, thus make life estimate can reflect the dynamic operating condition of device exactly.In addition, at each interval, determined mileage and the estimation of the static state of device lifetime can be compared.In this way, estimated residual life can be judged regularly.Utilize the residual life of this estimation, the mode in its life-span can be extended according to (such as), or according to the mode improving or continue its performance by control device when considering residue device capabilities, device is controlled.

With reference now to Fig. 1, it illustrates the block scheme of processor according to an embodiment of the invention.As shown in Figure 1, processor 10 can be the dual core processor with the first kernel (i.e. core A) 20 and the second kernel (that is, kernel B) 30.Although show dual core in the embodiment in figure 1, should be appreciated that scope of the present invention not by such restriction, in other embodiments, single kernel or multi-core processor also can utilize embodiments of the invention.

Still with reference to figure 1, the first shown kernel 20 comprises various pieces, and described piece comprises one or more performance element 22, one or more register file 24 and one or more high-speed cache 26.Certainly, the kernel framework of specifying can comprise extra block, such as, and storer class formation (register file, high-speed cache, queue etc.) and other combinational circuits (performance element, decode logic etc.).In various embodiments, performance element 22 can be taked various forms and can such as comprise one or more scalar processing unit, such as, and integer unit and floating point unit.In addition, one or more single instruction multiple data (SIMD) unit can exist together with other functional units such as such as scalar/vectors.In addition, the first kernel 20 comprises can be such as the controller 28 of microcontroller.Controller 28 may be used for performing dynamic life time evaluation method according to an embodiment of the invention.In addition, in certain embodiments, controller 28 at least can also control the operation of performance element 22 based on determined estimation residual life, will be further discussed hereinafter to it.

First kernel 20 also comprises multiple sensors of the running parameter measuring kernel.In the embodiment shown in fig. 1, each block comprises its oneself sensor.Correspondingly, sensor 21 is associated with performance element 22, and sensor 23 is associated with register file 24, and sensor 25 is associated with high-speed cache 26.Although show these related sensors, should be appreciated that can there is more or less sensor in various embodiments.In addition, described sensor can have identical or different types.Such as, in one embodiment, each in these sensors can be such as based on the temperature sensor of the sensor of diode.In other embodiments, other working parameter sensor can also be there are, such as, current sensor, voltage sensor etc.

In addition, as shown in Figure 1, controller 28 comprises storer 27, and such as, it can be the nonvolatile memory for the determined life estimate information of dynamic memory.In addition, in certain embodiments, storer 27 can comprise the microcode for performing dynamic life time measuring method according to an embodiment of the invention.In such embodiments, if controller 28 does not comprise the independent logic for calculating mileage, then controller 28 can control the one or more operation in performance element 22, to perform microcode.

Processor 10 can also comprise the cache memory 40 being coupled to two kernels.And cache memory 40 can be coupled to Memory Controller hub (MCH) 50, the control between other parts of the memory hierarchy of the system storage that described Memory Controller hub provides cache memory 40 and such as processor 10 to be coupled with it with communicate.Although do not illustrate for the ease of illustrating in FIG, should be appreciated that the second kernel 30 can comprise the structure similar with the structure shown in the first kernel 20.

Certainly, other embodiments are also possible.Such as, replace the nonshared control unit in each kernel, can, at processor memory at single controller, to receive the operating parameter information from multiple kernel, and determine to estimate residual life based on described information.In addition, in certain embodiments, controller 28 can comprise its oneself processing power, thus determines to estimate residual life according to the information received from each sensor.But, as an alternative, in other embodiments, controller 28 can control the streamline (pipeline) of its its relevant kernel, thus remove unsettled operation, and be provided for the code that performs in the resource of kernel, to realize the kinetic measurement to estimation residual life.Although be illustrated under many kernel environment, embodiments of the invention can be applied to the device that its temperature any, voltage and frequency come under observation here.

With reference now to Fig. 2, it illustrates the block scheme of processor according to another embodiment of the present invention.As shown in Figure 2, processor 100 can be again multi-core processor, more specifically, can make dual core processor.But, in this embodiment, there is nonshared control unit 160 with the determination of process for the estimation residual life of the resource in processor 100.

As shown in Figure 2, processor 100 comprises the first kernel (that is, core A) 120 and the second kernel (that is, kernel B) 130.In addition, similar to the above description carried out for Fig. 1, processor 100 comprises the cache memory 140 being coupled to kernel, and described cache memory 140 is coupled to again the front side bus (FSB) of the system residing for (such as) processor 100 via MCH150.In other embodiments, via one or more point-to-point interconnection, processor 100 can be coupled to the miscellaneous part of such as storer, chipset etc.

First kernel 120 comprises one or more performance element 122, one or more register file 124 and one or more high-speed cache 126.Although show the block that these are concrete in the embodiment of fig. 2, be to be understood that there is block that is more or that arrange differently in other embodiments.In addition, the first kernel 120 comprises sensor 128, and it can be the single-sensor of the running parameter for measuring the first kernel 120.Such as, sensor 128 can be the temperature sensor of the temperature for measuring kernel.Certainly, in other embodiments, other sensors can be there are in the first kernel 120, comprise the sensor being positioned at each functional block or being closely related with it.Second kernel 130 can comprise similar parts.

Thus, in the embodiment of fig. 2, so controller 160 can receive sensor 128 and be positioned at the operating parameter information of the second kernel 130 or associated one or more similar sensor.Based on this information, controller 160 can be determined to estimate residual life for each kernel.Independently can also determine to combine, to provide the information relevant to the entirety of processor 100 by such.Controller 160 can also comprise storer 165, and it can be for storing and mileage and the nonvolatile memory estimating the up-to-date information that residual life is relevant.Or, such information can be stored in the another location of system, such as, be stored in another nonvolatile memory.

Note, although Fig. 1 and Fig. 2 shows the concrete configuration of controller and related sensor, should be appreciated that in various embodiments, the position of controller and the position of sensor have nothing to do.Therefore, in certain embodiments, controller on single kernel upper sensor and relevant kernel may be there is.Or multiple kernel upper sensor can be associated with kernel outer controller.Various embodiment of the present invention take into account this configuration of these and other of controller and sensor.

With reference now to Fig. 3, it illustrates the process flow diagram of method according to an embodiment of the invention.As shown in Figure 3, such as, the controller implementation method 200 of such as microcontroller can be passed through, to implement residual life estimation.Or, the instruction implementation method 200 that can be performed by the processor such as carrying out life estimate to it by general processor.

Method 200 can from the running parameter obtaining device (block 210).Such as, with regard to the embodiment of the semiconductor devices for such as processor, one or more running parameter can be obtained.Such as, these running parameters can comprise actual temperature, voltage and frequency of operation, although such as other running parameters of humidity, air pressure, salinity, strong-electromagnetic field, radiation, acceleration are also possible.In certain embodiments, the Given information that can process based on processor, instead of obtain voltage and frequency based on the sensor for these parameters.Correspondingly, in certain embodiments, only serviceability temperature sensor provides corresponding operating parameter information.Next, can based on the mileage (block 220) of running parameter for the time interval calculating device of specifying.That is, the actual mileage based on the actual use of device or loss can be calculated.The measurement of this loss of different modes can be performed.In addition, the time interval of carrying out this calculating can change.In some implementations, the time interval can be longer relative to the machine cycle, but shorter with regard to real-time parameter.Such as, the time interval can change at about 1.0 milliseconds (ms) with between 1 minute, although scope of the present invention is not limited thereto.In so short real-time amount, unlikely there is significant temperature, voltage or frequency change.

Utilize the mileage calculated, estimation residual life (block 230) can be determined based on current estimation residual life and the mileage calculated.That is, the current estimated life of existing system and the mileage that an in the end time interval occurs can be compared.Current estimated life can deduct all calculating mileages corresponding to the stable state estimated life (such as, entire life) of device and determine (such as, total kilometrage).Therefore, current mileage can be deducted from current estimated life, to obtain new estimation residual life.Then, can report and preserve this information (block 240).Such as, described information can be stored in the nonvolatile memory of processor itself, or can be stored in another nonvolatile memory of system.

Still with reference to figure 3, next can determine whether the time interval passes by (diamond block 250).If no, so diamond block returns himself.Otherwise if the time interval passes by, so control to be back to discussed above piece 210.In this way, the periodic measurement of actual mileage can be implemented, and can upgrade continuously and reporting residual estimated life to use in controlling mechanism, as hereafter will discussed further.Certainly, the mode of other estimation residual life can also be taked.

Can control system based on residue estimated life, thus correspondingly adjust its characteristic, running parameter or task management.Such as, if determine that the estimated life of one or more kernels of processor is close to terminating, then can make such processor lose efficacy, or can make its frequency of interior nuclear alteration and/or voltage.In other embodiments, system can be selected to such processor transmission work, thus thoroughly exhausts its resource before its life termination.Or task can be guided away from such processor.Therefore, the different modes of this control may be adopted in various embodiments.

With reference now to Fig. 4, it illustrates the process flow diagram controlling resource according to embodiments of the invention.As shown in Figure 4, method 300 can from the estimated life information received for one or more processor resource (block 310).Such as, scheduler program (such as, being associated with operating system (OS) or processor scheduling program) can receive the estimated life information according to the method 200 above described with reference to figure 3.

Can determine whether one or more estimated life (such as, different processor resource) is in (diamond block 320) under predetermined threshold based on this estimated life information.Threshold value can be arranged on different levels, its scope is very wide in various embodiments.If life value is not less than threshold value, then control to be back to block 310, at this, described method waits for the reception next time of estimated life information.

Otherwise if if at diamond block 320 place, at least one determining in life estimate is in below threshold value, then control to proceed to block 330.At this moment, the resource (block 330) be associated with the estimated life decreased can correspondingly be controlled.Such as, as mentioned above, such processor resource can be made to lose efficacy, such as, whole processor or its kernel or block, or in the voltage that described processor resource can be made to be operated in reduction and/or frequency, there are other controlling mechanisms in addition.Although adopt this embodiment in the embodiment of Fig. 4 to be illustrated, be to be understood that scope of the present invention is not limited thereto.

In order to determine the residual life of block, in various embodiments can in conjunction with Static and dynamic information.In certain embodiments, static information can correspond to stable state MTTF, by determining that described stable state MTTF obtains the expected life of block.In one embodiment, steady-state model may be used for based on static temperature (T _base) and voltage (V _base) parameter determination specified life (MTTF _steady), wherein by degree Celsius or degree Kelvin in units of measuring tempeature.More specifically, in this embodiment, the MTTF of whole semiconductor devices can be determined as follows _steady:

${\mathrm{MTTF}}_{\mathrm{steady}}=\frac{1}{{\mathrm{\λ}}_{\mathrm{total}}}=\frac{1}{{\mathrm{\Σ}}_{i=1}^j{\mathrm{\Σ}}_{l=1}^k{\mathrm{\λ}}_{i1}}$ [equation 1]

Wherein λ _totalcorresponding to the total failare rate of semiconductor devices (such as processor), λ _ilit is the failure rate of i-th structure caused by l fault mechanism.Correspondingly, can by the single failure rate of all parts of processor be added the total failare rate determining processor.Therefore, can think that total failare rate is the failure rate sum model combining the impact relating to the different structure of (across) processor or the different faults mechanism of block.Although in various embodiments, can estimate on the basis of each block and use these total failare rates, also can measure the estimated life with the more fine-grained structure in analysis processor or other semiconductor devices.In addition, should be appreciated that in various embodiments, the different models of explaining different faults mechanism can be realized in the process determining the failure rate relating to different structure.

Then, the actual mileage of a series of equation computing block can be adopted.The actual mileage of this part or service condition not only but also for based on the static information determining stable state expected life, thus can explain dynamic differential based on the block service condition of reality based on multidate information.Although the mileage calculation of different modes can be performed, in certain embodiments, multiple equation can be adopted to calculate mileage based on the varying environment parameter observed for the block that will analyze.

First, mileage when opening time mileage equation measuring element (such as, the physical block of processor) can be adopted in running order.Specifically, in certain embodiments, equation 2 can be adopted:

MileageOn=∑ (Δ tKTon ^(Tnow-Tbase)kVon ^(Vnow-Vbase)kFon ^{(Fnow- fmax_this_V)/Fmax_this_V}) [equation 2]

With regard to equation 2, Δ t is the time interval between two observations (that is, last observation and current observation).KTon, KVon and KFon are in the cycle of opening, the technology dependent constant with temperature, voltage and frequency dependence for device.For various technique (such as, 65nm, 45nm and 32nm), these constraint conditions always may be greater than 1, and this means that temperature, voltage or frequency are higher, mileage is larger.

Table 1 shows in the value according to the constant adopted in the mileage calculation of an embodiment.Other realize in, other constant values can be adopted, as based on known technological parameter and/or empirical model determined.

table 1

Current variable Tnow, Vnow and Fnow correspond respectively to temperature, voltage and the frequency observed in this period of time.Value V _baseand T _basecorrespond respectively to the steady state measurement of temperature and voltage.Finally, F _{max_this_V}correspond to the highest frequency possible when the specified power supply operating at voltages residing for devices function.Note, the current mileage value determined in equation 2 is added with all previously such values, thus obtain the net cycle time mileage of device.

Secondly, the mileage at those intervals when free time mileage equation measuring element (such as, the physical block of processor) can be adopted to be in idle condition.In such interval, only have stress to move and the degeneration that causes of thermal cycle, but device such as can not because of electromigration, TDDB and NBTI and degenerating.Several sources of trouble may be evenly distributed on owing to degenerating, and in fact only have some to make it degenerate when device is in idle condition in the middle of them, therefore can the adoption rate factor.Specifically, for equation 3, the scale factor of 2/5 below can be adopted as:

MileageOff=∑ (Δ t2/5KToff ^(Tnow-Tbase)) [equation 3]

Wherein KToff(is similar to KTon) be in the cycle of idle condition, the technology dependent constant with temperature correlation for device.Δ t, Tnow are identical with in equation 2 with Tbase.Note, the current mileage value determined in equation 3 is added with all previously such values, thus total free time mileage of acquisition device.

The total kilometrage of calculating device can be carried out based on equation 2 and equation 3 sum.

Mileage=MileageOn+MileageOff [equation 4]

Finally, in this embodiment, can determine to estimate residual life by the mileage value determined in steady-state value and equation 4 is compared.

MTTF _remaining=MTTF _steady– Mileage [equation 5]

Correspondingly, the mileage determined in equation 4 illustrates considers actual temperature (T _now) and voltage (V _now) actual degeneration.Such as, in temperature more than T _basework when 10 degree and the degree of degeneration that block causes was equivalent at T in 1 hour _basethe degree of degeneration (mileages of 1.5 hours) that lower work causes for 1.5 hours.On the other hand, (such as, T is compared in lower temperature _baselow 10 degree) under work the degree of degeneration that described piece is caused be equivalent at T _basethe degree of degeneration that lower work causes for 0.5 hour.Therefore, estimate that residual life can determine (such as, determining in device manufacturing) with the static state of estimated life and based on based on the consumption of actual dynamic duty parameter or the dynamic estimation of mileage.Although adopt this to be illustrated relative to the embodiment of equation 1-5, be to be understood that scope of the present invention is not limited thereto.Such as, in other embodiments, not that summation is determined to the mileage at each interval, but can carry out independent mileage determine and by its from estimation remaining lifetime value cut, described estimation remaining lifetime value self is based on the initial estimated life of device, and the actual consumption at each interval by this interval upgrades it.Certainly, other embodiments are also possible.

In order to implement to calculate according to an embodiment of the invention, the dynamic mileage of one or more device can be recorded.Generally speaking, the data volume storing mileage can be relatively little.Such as, under many kernel environment, in order to grasp the mileage situation of each kernel, can only use several byte to each kernel.Can by this information record in the nonvolatile memory, thus each mileage consumption of determining for semiconductor devices can be added up.These add up and store can be in various granular level.Such as, have in the embodiment that independently mileage determines at different processor resources, each such mileage determines to have corresponding position in memory.Such as, or in the embodiment of method adopting more coarseness, when based on each kernel, each kernel can have its private memory.In addition, in certain embodiments, estimation residual life can also be stored, and use (that is, at ongoing interval (ongoinginterval) place) in the further estimation of residual life afterwards.In this information can being kept in basic input/output (BIOS) or being kept at little nonvolatile memory that user can not access.Note, in various embodiments, can periodically (such as, per a few minutes) mileage is backuped to this storer, with conserve energy.Because embodiments of the invention only perform little calculating within each time interval, therefore mileage is upgraded not expensive.Thus, the data from one or more environmental sensor can be read very continually, and upgrade mileage (such as, every 1 millisecond, per minute or similar interval).

In various embodiments, can calculate according to various mode, the impact of all mode opposite sum energy ezpenditure is all very little.Such as, under many kernel environment, there is following possible option.In one embodiment, can be provided in the microcontroller shared between all kernels, to calculate the mileage of each kernel or its part, described microcontroller is such as the controller 160 of Fig. 2.This microcontroller can comprise one or more logical block, to carry out desired calculating.When unlatching comprises the system of such processor, microcontroller can load mileage information from nonvolatile memory, and just obtains data from the sensor of each kernel every Δ t, thus upgrades its mileage and again stored by described mileage.

Be not have overall microcontroller, each kernel but can have oneself microcontroller, described microcontroller has oneself the logic for calculating mileage.Or each kernel can have oneself microcontroller, described microcontroller stops taking out instruction from kernel, wait for that streamline becomes empty, inject the instruction calculated needed for mileage, result is kept in the register of himself, finally recover the program performing current operation.

Therefore, prediction device utilizes embodiments of the invention, the Accurate Prediction of device lifetime can be realized, thus made device itself or any software failure/migration on it before will be damaged.The mileage measuring kernel under many kernel environment can realize the guiding strategy for task.Such as, according to desired embodiment, task can be directed to the minimum or maximum kernel of use.In addition, measure mileage can allow to be used in device loss high when reduce the mechanism of device performance, to extend device lifetime.Such as, when mileage is determined to reach predetermined threshold, the reduction of device performance can be implemented.Such as, such performance can be implemented by reduction operating voltage and/or frequency to reduce.

Adopt embodiments of the invention can make other processor features effectively/lost efficacy.Such as, in some implementations, processor can comprise various steering logic, thus based on service condition make some function or block effectively/lost efficacy.In addition, mileage can be utilized to determine to realize different pricing strategies.In such embodiment, can make processor or other semiconductor devices that predetermined mileage is housed.Such as, so predetermined mileage can be stored in the nonvolatile memory of described processor or other semiconductor devices.In addition, in certain embodiments, predetermined mileage can be set to the value lower than actually determined static life.In this way, can for arranging lower predetermined age with the device sold lower than the price point of the similar device with higher predetermined age value.In this way, the processor with identical function can be sold with different price point according to the preset life-span of device.In operation, the kinetic measurement of mileage and this predetermined mileage can be compared, to determine when to reach end-of-life condition.When reaching such condition, embodiments of the invention can make processor or other semiconductor device failure.

Such as, in some embodiments, when calculated mileage corresponds to the predetermined fare register of processor, the programmable fuse logic (fuselogic) in processor can be made effective.Correspondingly, described fuse logic can make processor lose efficacy by any one in various mode.In this way, the max mileage (such as, mileage budget is higher, and price is higher) that can allow according to the price fixing of device.In other embodiments, can provide for user the chance such as being obtained extra mileage by additional payment.

In other embodiments, replace fuse logic, predetermined fare register makes processor or its partial failure when residual life meets control register or other such controlling functions parts can be set to (such as).By the loss situation utilizing mileage to grasp device, more reliable processor can be provided, because can it be made to lose efficacy before with old device failure in some implementations.

Embodiment can be realized by various system type.With reference now to Fig. 5, it illustrates the block scheme of multicomputer system according to an embodiment of the invention.As shown in Figure 5, multicomputer system is point-to-point interconnection system, and it comprises the first processor 470 and the second processor 480 that are coupled via point-to-point interconnection 450.As shown in Figure 5, each in processor 470 and 480 can be the multi-core processor comprising the first and second processor cores (that is, processor cores 474a and 474b and processor cores 484a and 484b).Each in processor 470 and 480 can also comprise controller 475 and 485 respectively, determines according to the dynamic estimation life-span of embodiment to perform.In some embodiments, these controllers can comprise the storer for predetermined mileage and dynamic mileage.First processor 470 also comprises Memory Controller hub (MCH) 472 and point-to-point (P-P) interface 476 and 478.Similarly, the second processor 480 comprises MCH482 and P-P interface 486 and 488.As shown in Figure 5, processor is coupled to respective memory by MCH472 and 482, i.e. storer 432 and storer 434, and it can be the part that this locality is connected to the primary memory of respective processor.

In certain embodiments, the operating system (OS) of multicomputer system can one or more in first processor 470 and the second processor 480 be run.Described OS can comprise the program scheduler on scheduling different processor and kernel thereof.In some embodiments, controller 475 and 485 can provide estimation residual life information to OS scheduler program.Then, utilize this information, described scheduler program to/from one or the other in first processor 470 or the second processor 480 or its kernel steering routine, or can guide the process from it.In addition, scheduler program can based on other controlling functions of estimation residual life information realization.

Via P-P interface 452 and 454, first processor 470 and the second processor 480 can be coupled to chipset 490 respectively.As shown in Figure 5, chipset 490 comprises P-P interface 494 and 498.In addition, chipset 490 comprises the interface 492 for making chipset 490 be coupled with high performance graphics engine 438.In one embodiment, can adopt advanced graphics port (AGP) bus 439 that graphics engine 438 is coupled to chipset 490.AGP bus 439 can follow the accelerated graphics port interface specification of 2.0 revised editions that on May 4th, 1998 is announced by the Intel company in Santa Clara city.Or point-to-point interconnection 439 can be coupled these parts.

Chipset 490 can be coupled to the first bus 416 via interface 496 again.In one embodiment, first bus 416 can be the PCI local bus specification (manufacture version) of 2.1 revised editions as born the date of June nineteen ninety-five Peripheral Component Interconnect (PCI) bus that defines, or can be the bus of such as PCIExpress bus or other third generation I/O (I/O) interconnect bus, although scope of the present invention is not limited thereto.

As shown in Figure 5, various I/O device 414 can be coupled to the first bus 416 together with bus bridge 418, the first bus 416 is coupled to the second bus 420 by described bus bridge 418.In one embodiment, the second bus 420 can be low pin number (LPC) bus.In one embodiment, various device can be coupled to the second bus 420, described device such as comprises keyboard/mouse 422, communicator 426 and can comprise the data storage cell 428 of code 430.The lifetime data 432 of the accumulative mileage value of the various resources corresponding to system can also be comprised for the data storage cell 428 of nonvolatile memory.In addition, audio frequency I/O424 can be coupled to the second bus 420.

Can codes implement embodiment be passed through, and can store on the storage medium of instruction by stored thereon for described embodiment, described instruction can be adopted to System Programming to perform described instruction.Storage medium can include but not limited to the dish of any type, and it comprises floppy disk, CD, compact disc read-only memory (CD-ROM), CD-RW (CD-RW) and magneto-optic disk; Semiconductor devices, such as, random-access memory (ram), Erasable Programmable Read Only Memory EPROM (EPROM), flash memory, the Electrically Erasable Read Only Memory (EEPROM) of ROM (read-only memory) (ROM), such as dynamic RAM (DRAM) and static RAM (SRAM); Magnetic or optical card; Or any other is suitable for the medium of store electrons instruction.

Although describe the present invention relative to the embodiment of limited quantity, those skilled in the art will be appreciated that and can make many modifications and variations by it.Be intended to make appending claims contain all this modifications and variations dropped in practicalness of the present invention and scope.

Claims (8)

1., for estimating the method in the life-span of at least one resource, comprising:

Based on the obtained multidate information about at least one resource described, the actual mileage of at least one resource described is determined according to periodic intervals, if it is in running order in described periodic intervals to comprise at least one resource described, then calculate according to first and determine described actual mileage, if and at least one resource described is in off working state in described periodic intervals, then calculates according to second and determine described actual mileage;

The dynamic life time of at least one resource described is estimated based on the actual mileage of at least one resource described and static prediction life-span; And

Described actual mileage is kept in the nonvolatile memory of semiconductor devices.

2. method according to claim 1, also comprises the described actual mileage determining described periodic intervals, and by itself and the actual mileage of preserving, thus upgrade the actual mileage preserved.

3. a semiconductor equipment, comprising:

A kind of processor, comprising:

For performing at least one resource of instruction;

At least one environmental sensor; And

Be coupled to the logic of at least one environmental sensor described, it is for based on the obtained multidate information about at least one resource described, the actual mileage of at least one resource described is determined according to periodic intervals, the dynamic life time of at least one resource described is estimated based on the actual mileage of at least one resource described and static prediction life-span, and described actual mileage is kept in the nonvolatile memory of described semiconductor equipment, wherein, if at least one resource described is in running order in described periodic intervals, then described actual mileage calculates according to first and determines, if and at least one resource described is in off working state in described periodic intervals, then described actual mileage calculates according to second and determines,

Controller, it controls described processor based on estimated dynamic life time.

4. semiconductor equipment according to claim 3, wherein said logic, for determining the described actual mileage of described periodic intervals, and by itself and the actual mileage of preserving, thus upgrades the actual mileage preserved.

5. a semiconductor system, comprising:

Perform the first processor of instruction, described first processor comprises:

At least one performs the resource of instruction; And

At least one thermal surveillance device;

Be coupled to the first controller of at least one thermal surveillance device described, it is for determining the actual mileage of at least one resource described based on the multidate information obtained from least one thermal surveillance device described;

Be coupled to the second processor of the first processor of described execution instruction;

Be coupled to the second controller of described first processor and the second processor, it for receiving the described actual mileage from described first controller, and at least controls the service condition of described first processor based on described actual mileage; And

Be coupled to the dynamic RAM (DRAM) of described first processor and described second processor.

6. semiconductor system according to claim 5, wherein said first controller is used for determining described actual mileage according to periodic intervals, and is kept in the nonvolatile memory of described semiconductor system by described actual mileage.

7. semiconductor system according to claim 6, wherein said first controller, for determining the described actual mileage of described periodic intervals, and by itself and the actual mileage of preserving, thus upgrades the actual mileage preserved.

8. semiconductor system according to claim 6, if it is in running order in described periodic intervals that wherein said first controller is used at least one resource described, then calculate according to first and determine described actual mileage, if at least one resource described is in off working state in described periodic intervals, then calculates according to second and determine described actual mileage.