WO2007090734A1 - Application software initiated speedup - Google Patents

Application software initiated speedup Download PDF

Info

Publication number
WO2007090734A1
WO2007090734A1 PCT/EP2007/050634 EP2007050634W WO2007090734A1 WO 2007090734 A1 WO2007090734 A1 WO 2007090734A1 EP 2007050634 W EP2007050634 W EP 2007050634W WO 2007090734 A1 WO2007090734 A1 WO 2007090734A1
Authority
WO
WIPO (PCT)
Prior art keywords
processor
instruction
frequency
working frequency
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/EP2007/050634
Other languages
English (en)
French (fr)
Inventor
Håkan WINBOM
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nasdaq Technology AB
Original Assignee
OMX Technology AB
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by OMX Technology AB filed Critical OMX Technology AB
Priority to EP07704070A priority Critical patent/EP1982249A1/en
Priority to JP2008553706A priority patent/JP2009526297A/ja
Priority to AU2007213901A priority patent/AU2007213901B2/en
Publication of WO2007090734A1 publication Critical patent/WO2007090734A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power management, i.e. event-based initiation of a power-saving mode
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234Power saving characterised by the action undertaken
    • G06F1/324Power saving characterised by the action undertaken by lowering clock frequency
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present invention relates generally to management of processor working frequency in computer systems and electronic devices.
  • the systems range from individual computers to distributed computer systems interconnected by one or more networks.
  • This situation may especially occur in financial trading systems (electronic exchanges). These systems receive many quotes/orders from traders and/or brokers, trading in financial instruments, energy contracts and so forth. Examples of when peak periods can occur are during the auction period before opening of an exchange, or when a task is sent that may result in a processor demanding change in an orderbook, or information dissemination, or because something else happened such as a political statement or rumor in the news or any happening that can trigger an increase of quotes/orders sent from traders.
  • Some computer systems are using "variable” (clock) speed in order to preserve energy, reduce heat and related noise.
  • One such technology is Intel's "speed step”.
  • this technology has been applied to battery powered “lap top” computers and office space “desktop” computers for saving battery power and for noise reduction.
  • the operating system and/or the "BIOS” which detects some level of inactivity by the user, and “slows” down the clock by a supervisor state instruction.
  • Supervisor state instructions are instructions only executable in "supervisor state” or some similar mode which is reserved for the operating system.
  • a processor comprising: a frequency generating unit for generation of a variable working frequency, a memory comprising an instruction for changing the working frequency, an interface for receiving a user instruction, wherein the instruction for changing the working frequency is activatable via the interface by the user instruction sent from a user level application.
  • the processor being programmed to: receive a user instruction via the interface from a user level application for changing the working frequency, and based on the user instruction, change the working frequency by using the instruction stored in the memory.
  • the above processor has the advantage that a user level application may directly request a performance increase, such as increasing the work frequency of the processor.
  • an operating system when initiating a hardware operation has to progress through: user mode to OS mode transition, the OS executes the hardware instruction and then transition back to user mode (which may involve a scheduling decision, and possible dispatch of an other process).
  • These steps may be referred to as overhead cost such as cost in time and cost in processor power and so forth.
  • the above described transition process slows down a computer or a computer system. Therefore a processor according to the invention may be able to cut overhead and in this way make use of processor capacity currently not utilized and thereby deliver results faster compared to other processors.
  • a user level application may be the first line of early warning systems for e.g. a change in workload, since it is in the user application where users requests different operations/functionalities to be executed.
  • a user level application may detect the need for speed-up in several different ways, for example when known processor demanding operations/functions are requested.
  • the need for speed-up may be detected by for example an increase of the input queue.
  • the user level application can send a speed-up user instruction to the processor and in this way prepare the processor for an upcoming increase in workload, by increasing the working frequency.
  • the user instruction is triggered and sent in the user application based on a user action.
  • a user action may be any kind of action that a user may perform, either directly via an interface or indirectly based on the user action.
  • a user action can be an action such as: trade action, delete action, amend action, screen update action, direct request of speed up action, this is not an exhaustive list, other actions not mentioned here may also be added in the list.
  • the user instruction may be triggered and sent by a user action belonging to a list, e.g. a "top-ten" list comprising the ten most processor demanding actions.
  • a user action belonging to a list e.g. a "top-ten" list comprising the ten most processor demanding actions.
  • the system checks whether this action belongs to the list and if it does the system sends a speed-up user instruction.
  • This list may be continuously updated and may be based on statistics from the system.
  • the invention may comprise a self learning function that updates the "top-ten" list.
  • the "top-ten" list may comprise an arbitrary number of processor demanding actions and is thus not limited to ten. The length of the list may thus be decided by the context wherein the present invention will be used. Preferably this function would be application software controlled.
  • a user action can also be an action that is automatically executed by a server application.
  • the server application on the server may request a change of the working frequency of the processor such as a speed-up request.
  • a user level application can also be a server application.
  • the server based user level application preferably has a software function that receives data from client computers and thereafter analyses the data in order to see if it comprises processor demanding tasks or instructions, and if it does, the server based user level application may request a speed-up of the working frequency of the processor that will handle the workload.
  • the processor preferably comprises a temperature sensor for measuring a temperature of the processor in order to optimize the working frequency based on the temperature and based on the user instruction. In this way it is possible to control the working frequency so that the processor performs at an optimal speed in relation to the temperature.
  • the processor may further comprise a counter for counting the number of instructions that has been executed in speed-up mode, and when the number of instructions executed in speed-up mode, reaches a predetermined threshold, the speed-up mode is "canceled" or lowered. In this way the temperature problem can be avoided since the threshold would preferably be set to a number that would not overheat the processor. Thus, this may be an alternative and/or complementary to heat sensing.
  • the frequency generating unit may comprise two or more frequency generating devices producing different frequencies in order to generate the variable working frequency.
  • the frequency generating unit preferably comprises a switch for selecting one of the different frequencies in order to generate the variable working frequency.
  • the frequency generating device may be a crystal that vibrates at a regular frequency when an electrical current is applied to it and in this way produces a clock frequency.
  • any other device able to produce a clock frequency that can be used in a processor may be used.
  • the frequency generating unit may comprise a frequency generating device generating a frequency and a divisor for changing the frequency to the variable working frequency.
  • the instruction according to the invention changes the working frequency by changing a divisor factor.
  • the divisor factor may be an integer or a floating point number by which the divisor can be controlled in order to obtain a variable working frequency.
  • the frequency generating unit may comprise a frequency generating device generating a frequency and control means for direct control of the frequency generating device in order to output a variable working frequency.
  • control means could be a device generating a variable pressure to the crystal, or a device generating a temperature change of the crystal, and in this way the frequency of the crystal could be changed.
  • the processor may be implemented in an electronic device such as computers, servers or hand held and portable devices such as mobile phones, palm pilots, cameras or in any other electronic device where it may be necessary to obtain a performance increase during peak periods or for processor demanding instructions.
  • Such an electronic device has the advantage that it may request a performance increase of the underlying hardware in order to execute a processor demanding task. Thus it may deliver a result faster to a user since it is able to at a very early stage identify a processor demanding task that the user has requested.
  • the processor is used in an electronic exchange systems, examples of such systems are OMX systems CLICKTM, SAXESSTM or in clearing systems such as SECURTM.
  • an electronic exchange using a processor according to the invention has the advantage that it may request a performance increase of the underlying hardware if/when it receives a processor demanding request.
  • a processor demanding request may be a delete all order request for a trading firm or any other processor demanding request that may occur in an electronic exchange environment.
  • the above objects are achieved by providing an instruction controlling working frequency in a processor, the instruction is stored in a memory of the processor, and is characterized in that it is activatable by a user level application, for changing the working frequency.
  • the above instruction has the advantage that it provides a solution that directly dramatically cuts overhead such as superfluous steps which causes additional cost such as cost in time and so forth.
  • the instruction makes it possible to, at an early stage, request a hardware performance change. In this way capacity currently not being used can be accessed.
  • the change of the working frequency is a temporary increase of the working frequency in order to handle a future increase in work load.
  • it may also be a decrease of the working frequency.
  • the frequency may be controlled in a way so as to optimize the usage of a processor.
  • the speed of the processor may thus be decided based on a request sent from a user level application.
  • an additional functionality may optimize the usage of the processor even further based on heat generated from the processor.
  • means for measuring the temperature may be necessary to use.
  • the frequency can be decreased for a while and in this way keep the heat at an allowable level but at the same time running the processor at a maximum speed.
  • a user level application for trading comprising program instructions for: based on a user action, requesting a change of a working frequency of a processor in order to change performance of the processor.
  • the above user level application is preferably a trading application such as CLICK TradeTM for trading of commodities and/or financial instruments.
  • a software module installed in the front-end of a computer system such as in a client computer.
  • the user level application may also be any software module in an electronic exchange, such as matching module software or any other server based application.
  • a software module installed in the back-end of a computer system may be any software module in an electronic exchange, such as matching module software or any other server based application.
  • the user level application for trading may select a function comprising a speed-up request and send it together with the task, and in this way ask for a performance increase in order to execute the task faster.
  • a method for increasing performance of a processor based on a prediction of a future change in workload comprising an instruction stored in a memory
  • the method comprising the steps of: - from a user level application, sending a user instruction for changing a working frequency of the processor, and based on the user instruction, changing the working frequency by using the instruction stored in the memory.
  • the above method has the advantage of requesting a performance increase of underlying hardware in order to achieve a faster execution of a processor demanding request.
  • the user level application may be a computer program product loaded on to a computer- readable data carrier or a computer program product downloadable via a network such as the I nternet.
  • the present invention can be used to design system which allows higher absolute peak loads, beyond the current maximum achieved.
  • the invention may also improve cost efficiency by not having to design computer systems quite as large, because the system will be able to handle short term peak loads which are significantly higher than the sustained load capacity. It also allows the computing system to maintain reasonable response times even for costly transactions.
  • Fig. 1 illustrates an overview of the system comprising a CPU, a divisor and a frequency generating unit, wherein the CPU has a memory comprising at least one instruction.
  • Fig.2 illustrates a central computer system comprising the electronic exchange and client computers comprising e.g. trading applications and or clearing applications.
  • Fig.3 illustrates a client computer comprising a user level application and its user interface whereby a user may execute an instruction.
  • Fig. 4 illustrates a first embodiment of a frequency generating unit connected to a processor.
  • Fig.5 illustrates a second embodiment of a frequency generating unit.
  • Fig.6 illustrates an embodiment of the system comprising a temperature sensor.
  • the present invention proposes two new hardware instructions preferably accessible directly by application level software (SW), as opposed to access by BIOS/ Operating system (OS) and device drivers.
  • SW application level software
  • OS Operating system
  • a user mode instruction is an instruction which an application process may execute directly without assistance of the operating system.
  • hardware related instructions are only executable in "supervisor state" or some similar mode which is reserved for the operating system.
  • an application to initiate a hardware operation one usually has to progress through: - User mode to OS mode transition,
  • the OS executes the hardware instruction, and transition back to user mode (which may involve a scheduling decision, and possible dispatch of an other process )
  • the first instruction according to the invention may be Speed_Up(x%), this instruction would preferably request the hardware to speed up as x% of the maximum possible speed-up for as long time as possible.
  • the maximum time would typically be determined by increased temperature of the CPU or surrounding chips, e.g. once a preset maximum temperature is reached, the speed-up is "canceled” or lowered.
  • the maximum time could also be determined by a counter that counts the number of instructions that has been executed in speed-up mode, and when the number of instructions executed in speed-up mode, reaches a predetermined threshold, the speed-up mode is "canceled” or lowered.
  • the second instruction according to the invention would preferably be a reset instruction, for example Speed_Up_release(), as means to allow the application to voluntarily reset to normal mode of execution.
  • the above two instructions are preferably user mode instructions.
  • any Application level process or thread should be allowed to request Speed_up(), normally it should not relinquish control of the CPU by issuing OS and/or I/O call before it calls Speed_Up_Release(). However it could possibly be preempted by the operating system before it is finished, in these cases the speed up state would apply to the OS and/or other thread dispatched on this CPU until a heat limit, time limit or other limit is reached.
  • the objective with the % argument to Speed_Up() is to allow the application to voluntarily request e.g. just 50% of the possible speed up, with the assumption that it may be attained approximately twice as long, and/or that the next request will be able to get a speed up.
  • Order an instruction to make a transaction, i.e. to buy or sell a certain amount of a specific instrument at a given price. Orders are usually received from "investors", i.e. private investors or stock brokers.
  • - Market Maker An entity usually contracted by the operator of the trading system, for example a stock exchange, to maintain both buy and sell prices (and volumes) in the trading system for certain instruments. There may be some restrictions to this, e.g. that buy and sell prices should not differ more than a certain percentage.
  • Deal a match between orders and/or quotes, comprising at least two trades (one buy, one sell) which make up the legs of the deal.
  • Order book a table or a list in a trading system or an exchange, comprising all buy and sell orders as well as all quotes. There is essentially one order book for each tradable object.
  • External events e.g. if the central bank adjusts the interest rate, this is an external event which will cause almost all active traders to re-evaluate their positions in the market. Market makers will most likely delete all their quotes and soon submit new, while "normal" traders may cancel their orders and submit new orders with different prices.
  • a user mode instruction is an instruction which an application process may execute directly without assistance of the operating system.
  • hardware related instructions are only executable in "supervisor state" or some similar mode which is reserved for the operating system.
  • a user mode instruction is an instruction which a user level application may execute directly without assistance of the operating system.
  • Market maker firms using automated quote engines are very sensitive to increased response times; in fact they may treat increased response time as an external event which causes them to issue "wildcard delete” transactions. Indeed if Market Maker firm 1 issues wild card delete, and this causes response times to deteriorate, this may cause other market maker firms to also issue "wildcard delete” transaction, aggravating the issue.
  • Example 2
  • the order books may be filled with large amounts of "retail" orders (each with low volume), suddenly a large participant e.g. a bank decides to buy/sell a huge volume of a particular instrument, thus one deal can generate thousands of trades, this causes a burst of CPU bound work to finish this processing, this is also ideally suited to Speed_Up()/Speed_Up_Reset().
  • FIG. 1 illustrates an overview of an embodiment of the system according to the invention.
  • the system comprises a CPU 2, a memory 3 comprising instructions 16, a frequency generating unit 6 comprising a divisor 4 and a frequency generator 5. Furthermore the figure illustrates a first frequency F1 and a second frequency F2 and a control connection 7 for sending control commands from the CPU to the Divisor so as to change the working frequency F2.
  • An instruction 16 preferably comprises a command and a value.
  • the command may be of the type Speed_Up or Speed_Up_release as described above and the value may be a percentage of the maximum possible speed, also described earlier in this document.
  • Figure 2 illustrates a distributed computer system comprising client computers 8 and a central computer 9.
  • the client computers 8 and the central computer 9 may be interconnected by any kind of network such as the Internet, WAN, LAN, or direct connections such as P2P.
  • wireless communication may be used, for example when the client computer 8 is a hand held electronic device such as a Palmpilot, mobile phone or a portable computer.
  • the figure illustrates a star network but any other type of network may be used, for example ring network or bus network and so forth.
  • the communication may be routed over nodes not shown in figure 2. Secure channels may be necessary to establish between the client computers 8 and the central computer 9.
  • the central computer 9 may be a computer comprising different types of server applications.
  • the central computer 9 comprises an electronic exchange comprising a common database that further comprises market, product, user and transaction information necessary to operate an electronic exchange.
  • the central computer 9 may comprise other subsystems that are necessary for an electronic exchange.
  • Some example of subsystems are an information dissemination system that process and broadcast information about trades and deals, a market place subsystem that manage the exchange's central order book, and so forth.
  • An example of an electronic exchange is the CLICKTM system manufactured by OMX Technology.
  • FIG 3 illustrates a client computer 8 comprising a user interface preferably having two parts, one monitor 10 and one input device 11.
  • the user interface may be a touch screen and in this case the two parts are integrated in one embodiment.
  • the monitor 10 may be any type of device that is able to present information to a user, such as an LCD display, plasma screen and so forth.
  • the input device 11 may be any type of input device such as a keyboard, mouse, joystick or a keyboard specially designed for e.g. trading.
  • the client computer may be any kind of electronic device such as a mobile phone, Palmpilot and so forth that is able to communicate with other electronic devices over a network or by wireless communication.
  • FIG 4 illustrates an embodiment of a frequency generating unit 6 connected to a processor 12.
  • the frequency generating unit 6 comprises a frequency generator 5 and a divisor 4 for changing the frequency generated by the generator 5.
  • the generator 5 generates a first frequency F1 which is changed in to a working frequency F2 that is sent to the processor.
  • FIG. 5 illustrates a second embodiment of a frequency generating unit 6 connected to a processor 12.
  • the generating unit 6 preferably comprises two frequency generators 5 and a Switch device 13.
  • Each frequency generator preferably produce a frequency having a different frequency from the other frequency generator, a first and a second frequency F1 , F2.
  • the switch 13 may switch between the most suitable frequency based on an instruction from a user level application and in this way a third frequency F3 (working frequency) may be sent to the processor 12.
  • the switch 13 is preferably controlled by instructions sent from the processor 12.
  • the number of frequency generators is not limited to two; an arbitrary number of generators may be used.
  • a divisor may also be connected to at least one of the lines which would provide the possibility of changing either the F1 or F2 or F3 or all of them depending on where the devisor(s) is placed in the system.
  • FIG. 6 illustrates a third embodiment of the system according to the invention wherein a temperature sensor 14 is connected to the processor 12 or in the vicinity of the processor such as to the CPU or motherboard.
  • the sensor 14 may be used in order to watch the temperature of the processor 12 so that the temperature stays within allowable limits.
  • the temperature may be controlled by increasing or decreasing the working frequency of the processor 12.
  • the temperature may also be controlled by increasing an air flow if the processor is chilled by air, or by increasing a flow of a liquid if the processor is chilled by a liquid.
  • system may comprise a counter 15 for counting the number of instructions that is executed by the processor 12 as described earlier in the text.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Executing Machine-Instructions (AREA)
  • Power Sources (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
PCT/EP2007/050634 2006-02-07 2007-01-23 Application software initiated speedup Ceased WO2007090734A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP07704070A EP1982249A1 (en) 2006-02-07 2007-01-23 Application software initiated speedup
JP2008553706A JP2009526297A (ja) 2006-02-07 2007-01-23 アプリケーションソフトウェアから開始するスピードアップ
AU2007213901A AU2007213901B2 (en) 2006-02-07 2007-01-23 Application software initiated speedup

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US11/348,551 2006-02-07
US11/348,551 US7634678B2 (en) 2006-02-07 2006-02-07 Application software initiated speedup

Publications (1)

Publication Number Publication Date
WO2007090734A1 true WO2007090734A1 (en) 2007-08-16

Family

ID=37776846

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2007/050634 Ceased WO2007090734A1 (en) 2006-02-07 2007-01-23 Application software initiated speedup

Country Status (7)

Country Link
US (1) US7634678B2 (https=)
EP (1) EP1982249A1 (https=)
JP (1) JP2009526297A (https=)
CN (1) CN101379451A (https=)
AU (1) AU2007213901B2 (https=)
TW (1) TWI417701B (https=)
WO (1) WO2007090734A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009230439A (ja) * 2008-03-21 2009-10-08 Toshiba Tec Corp 情報処理装置及びそのクロック制御方法並びにクロック制御プログラム

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4837456B2 (ja) * 2006-06-28 2011-12-14 パナソニック株式会社 情報処理装置
BRPI0822590A2 (pt) * 2008-04-21 2015-06-23 Adaptive Computing Entpr Inc Sistema de computador para gerenciamento do consumo de energia em um ambiente de computador
US9405348B2 (en) 2008-04-21 2016-08-02 Adaptive Computing Enterprises, Inc System and method for managing energy consumption in a compute environment
US8972702B2 (en) * 2009-11-30 2015-03-03 Intenational Business Machines Corporation Systems and methods for power management in a high performance computing (HPC) cluster
US9052915B2 (en) 2010-09-13 2015-06-09 Hewlett-Packard Development Company, L.P. Booting a machine using thermal credits to adjust operating speed of a component
CN102012764A (zh) * 2010-12-10 2011-04-13 华映视讯(吴江)有限公司 可更新处理器之运算频率的触控系统及其方法
US9069555B2 (en) * 2011-03-21 2015-06-30 Intel Corporation Managing power consumption in a multi-core processor
US8930737B2 (en) 2011-12-13 2015-01-06 Omx Technology Ab Method and devices for controlling operations of a central processing unit
US8782466B2 (en) * 2012-02-03 2014-07-15 Hewlett-Packard Development Company, L.P. Multiple processing elements
TWI470402B (zh) * 2012-04-25 2015-01-21 Academia Sinica 行動裝置cpu工作頻率控制方法
US9823990B2 (en) 2012-09-05 2017-11-21 Nvidia Corporation System and process for accounting for aging effects in a computing device
US9871448B2 (en) 2012-12-31 2018-01-16 Nvidia Corporation Super N-phase switching mode power supply
US10103719B2 (en) * 2013-07-22 2018-10-16 Nvidia Corporation Integrated voltage regulator with in-built process, temperature and aging compensation
US9831198B2 (en) 2013-08-22 2017-11-28 Nvidia Corporation Inductors for integrated voltage regulators
KR102270239B1 (ko) * 2014-08-07 2021-06-28 삼성전자 주식회사 전자장치에서 소프트웨어를 실행하기 위한 방법 및 장치
CN106155733B (zh) * 2015-04-23 2020-07-17 腾讯科技(深圳)有限公司 一种运行应用程序的方法和装置
CN105376401B (zh) * 2015-10-10 2019-09-24 联想(北京)有限公司 信息处理方法、装置及电子设备
CN109961527A (zh) * 2019-04-22 2019-07-02 广州市埃特斯通讯设备有限公司 一种车载单元系统
US11327798B1 (en) * 2019-05-08 2022-05-10 Meta Platforms, Inc. Accelerating an application code portion based on a received configuration
US11392418B2 (en) * 2020-02-21 2022-07-19 International Business Machines Corporation Adaptive pacing setting for workload execution
CN112559058A (zh) * 2020-11-17 2021-03-26 海信视像科技股份有限公司 应用软件加速方法及显示设备
US12572193B2 (en) * 2023-04-06 2026-03-10 Microsoft Technology Licensing, Llc Enhanced electricity limitation enforcement during application runtime

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5630148A (en) * 1994-06-17 1997-05-13 Intel Corporation Dynamic processor performance and power management in a computer system
US6230279B1 (en) * 1997-06-03 2001-05-08 Kabushiki Kaisha Toshiba System and method for dynamically controlling processing speed of a computer in response to user commands
US20020124197A1 (en) * 2000-12-29 2002-09-05 Atkinson Lee W. Method to associate and respond to a requirement for high performance operation of a notebook computer
US20030061523A1 (en) * 2001-09-25 2003-03-27 Stanley Randy P. Method and apparatus to provide a user priority mode
US20030097603A1 (en) * 2001-11-16 2003-05-22 Athas William C. Method and apparatus for increasing the operating frequency of an electronic circuit

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4893271A (en) * 1983-11-07 1990-01-09 Motorola, Inc. Synthesized clock microcomputer with power saving
TW522297B (en) 2000-03-17 2003-03-01 Micro Star Int Co Ltd Automatic over-clock method for CPU
JP3685401B2 (ja) * 2001-12-26 2005-08-17 インターナショナル・ビジネス・マシーンズ・コーポレーション Cpu制御方法、これを用いたコンピュータ装置及びcpu並びにプログラム
EP1338948A1 (en) 2002-02-25 2003-08-27 Hewlett Packard Company, a Delaware Corporation Clock control arrangement for a computing system
US7024672B2 (en) * 2002-06-26 2006-04-04 Microsoft Corporation Process-mode independent driver model
TWI220941B (en) * 2002-12-27 2004-09-11 Inventec Corp Structure and method to adjust the operation frequency of CPU
TWI250396B (en) 2003-04-17 2006-03-01 Winbond Electronics Corp Control circuit of supplied voltage for central processor unit
TW200506577A (en) * 2003-08-14 2005-02-16 Micro Star Int Co Ltd Method and system for dynamically adjusting operating frequency
US7467318B2 (en) 2003-09-29 2008-12-16 Ati Technologies Ulc Adaptive temperature dependent feedback clock control system and method
US7827424B2 (en) * 2004-07-29 2010-11-02 Ati Technologies Ulc Dynamic clock control circuit and method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5630148A (en) * 1994-06-17 1997-05-13 Intel Corporation Dynamic processor performance and power management in a computer system
US6230279B1 (en) * 1997-06-03 2001-05-08 Kabushiki Kaisha Toshiba System and method for dynamically controlling processing speed of a computer in response to user commands
US20020124197A1 (en) * 2000-12-29 2002-09-05 Atkinson Lee W. Method to associate and respond to a requirement for high performance operation of a notebook computer
US20030061523A1 (en) * 2001-09-25 2003-03-27 Stanley Randy P. Method and apparatus to provide a user priority mode
US20030097603A1 (en) * 2001-11-16 2003-05-22 Athas William C. Method and apparatus for increasing the operating frequency of an electronic circuit

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009230439A (ja) * 2008-03-21 2009-10-08 Toshiba Tec Corp 情報処理装置及びそのクロック制御方法並びにクロック制御プログラム

Also Published As

Publication number Publication date
TWI417701B (zh) 2013-12-01
CN101379451A (zh) 2009-03-04
US20070186123A1 (en) 2007-08-09
AU2007213901A1 (en) 2007-08-16
JP2009526297A (ja) 2009-07-16
EP1982249A1 (en) 2008-10-22
US7634678B2 (en) 2009-12-15
AU2007213901B2 (en) 2012-07-05
TW200809459A (en) 2008-02-16

Similar Documents

Publication Publication Date Title
AU2007213901B2 (en) Application software initiated speedup
Nzanywayingoma et al. Efficient resource management techniques in cloud computing environment: a review and discussion
US7925755B2 (en) Peer to peer resource negotiation and coordination to satisfy a service level objective
JP2019194914A (ja) 仮想コンピュータリソースのスケジューリングのためのローリングリソースクレジット
US8335935B2 (en) Power management based on automatic workload detection
TW200305800A (en) Managing system power
JP2008502967A (ja) 計算グリッド内でアプリケーション環境を動的に構築するためのシステムおよび方法
EP3815342B1 (en) Adaptive user-interface assembling and rendering
US20170212581A1 (en) Systems and methods for providing power efficiency via memory latency control
US20200301714A1 (en) Bios setting modification system
US20060161920A1 (en) Method, system, and computer program for managing a queuing system
US8140873B2 (en) User imposed power constraints on web server based on user preferences
WO2022104500A9 (zh) 一种负载控制方法、装置、计算机设备及存储介质
CN108400929B (zh) 数据处理方法、装置、计算设备和介质
JP2026503997A (ja) デジタルサービスに基づくサービスサーバの進入管理方法およびサーバ
Yang Energy-efficient cloud data center with fair service level agreement for green computing
CN103019813A (zh) 获取基于SaaS的交互式程序的交互强度的方法
CN116362731A (zh) 一种业务处理方法、装置、电子设备及计算机可读介质
CN112379970B (zh) 一种负载控制方法、装置、计算机设备及存储介质
HK1129753A (en) Application software initiated speedup
US20230125503A1 (en) Coordinated microservices
US20140310331A1 (en) Monitoring and distributing event processing within a complex event processing environment
Wan et al. Dynamic bidding in spot market for profit maximization in the public cloud
CA3049327C (en) RESOURCE ALLOCATION SYSTEMS AND PROCESSES
US20230275846A1 (en) Systems and methods for resource allocation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application
WWE Wipo information: entry into national phase

Ref document number: 2008553706

Country of ref document: JP

Ref document number: 2007213901

Country of ref document: AU

WWE Wipo information: entry into national phase

Ref document number: 200780004962.2

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2007704070

Country of ref document: EP

WWP Wipo information: published in national office

Ref document number: 2007213901

Country of ref document: AU