[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN105607726A - Method and device for lowering internal storage power consumption of high-performance computing cluster - Google Patents

Method and device for lowering internal storage power consumption of high-performance computing cluster Download PDF

Info

Publication number
CN105607726A
CN105607726A CN201510983353.2A CN201510983353A CN105607726A CN 105607726 A CN105607726 A CN 105607726A CN 201510983353 A CN201510983353 A CN 201510983353A CN 105607726 A CN105607726 A CN 105607726A
Authority
CN
China
Prior art keywords
internal memory
hpcc
fault
tolerant
power consumption
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.)
Granted
Application number
CN201510983353.2A
Other languages
Chinese (zh)
Other versions
CN105607726B (en
Inventor
王渭巍
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.)
Inspur Beijing Electronic Information Industry Co Ltd
Original Assignee
Inspur Beijing Electronic Information Industry Co Ltd
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 Inspur Beijing Electronic Information Industry Co Ltd filed Critical Inspur Beijing Electronic Information Industry Co Ltd
Priority to CN201510983353.2A priority Critical patent/CN105607726B/en
Publication of CN105607726A publication Critical patent/CN105607726A/en
Application granted granted Critical
Publication of CN105607726B publication Critical patent/CN105607726B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/325—Power saving in peripheral device
    • G06F1/3275—Power saving in memory, e.g. RAM, cache
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/14—Error detection or correction of the data by redundancy in operation
    • G06F11/1402—Saving, restoring, recovering or retrying
    • G06F11/1474—Saving, restoring, recovering or retrying in transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3452—Performance evaluation by statistical analysis
    • Y—GENERAL 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computer Hardware Design (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Power Sources (AREA)
  • Techniques For Improving Reliability Of Storages (AREA)

Abstract

The invention discloses a method and device for lowering the internal storage power consumption of a high-performance computing cluster. The method includes the steps of monitoring the running situation of the high-performance computing cluster in real time, analyzing the type of operation which is being run by the high-performance computing cluster, determining the internal storage fault tolerance mechanism of the operation which is being run by the high-performance computing cluster, obtaining the fault tolerance grade of the internal storage fault tolerance mechanism, and distributing the internal storage power consumption of the high-performance computing cluster according to the fault tolerance grade. By means of the method, the internal storage power consumption is lowered, and the energy consumption ratio is increased on the premise of ensuring that the performance of the cluster is kept unchanged.

Description

A kind of method and device that reduces HPCC power consumption of internal memory
Technical field
The present invention relates to High Performance Computing field, particularly relate to a kind of high-performance meter that reducesCalculate method and the device of cluster power consumption of internal memory.
Background technology
At present, along with the scale of HPCC constantly increases, power consumption increases day by day, fortuneEnergy consumption cost between the departure date, has even exceeded the construction cost of cluster, therefore a lot of manufacturersAll in the more efficient heat dissipation technology of research and development. But the heat dissipation technology that adopt the present age is as without revolutionary skillArt innovation does not almost improve leeway, and cost is also higher simultaneously.
Meanwhile, it is fault-tolerant that the internal memory acquiescence that most HPCCs adopt has been opened ECCMechanism, such as the data bit of 64 just need the fault-tolerant check bit of 8, therefore internal memory is fault-tolerantMechanism has improved power consumption of internal memory, and some high-performance calculation application program is without fault-tolerant, or onlyOnly need simple fault-tolerantly can meet user's requirement, so just caused the waste of power consumption.
Summary of the invention
The object of this invention is to provide a kind of method that reduces HPCC power consumption of internal memoryAnd device, to realize reduction power consumption of internal memory, keeping improving energy under the constant prerequisite of cluster performanceLoss-rate.
For solving the problems of the technologies described above, the invention provides a kind of HPCC internal memory that reducesThe method of power consumption, the method comprises:
The operation conditions of Real-Time Monitoring HPCC;
The homework type that HPCC is being moved is analyzed, and determines high-performance meterThe internal memory fault tolerant mechanism of the operation that calculation cluster is moving;
Obtain the fault-tolerant rank of described internal memory fault tolerant mechanism, the described fault-tolerant rank of foundation is to high-performanceThe power consumption of internal memory that calculates cluster distributes.
Preferably, described internal memory fault tolerant mechanism comprises: without fault tolerant mechanism, even-odd check mechanismOr ECC verification scheme.
Preferably, before the operation conditions of described Real-Time Monitoring HPCC, also comprise:
After high-performance calculation application program brings into operation, obtain the current of HPCCThe submission script of operation, and set keyword in submission script, utilize keyword to set high propertyCan calculate the internal memory fault tolerant mechanism of the current operation of cluster.
Preferably, described in obtain the fault-tolerant rank of described internal memory fault tolerant mechanism, according to described fault-tolerantRank is distributed the power consumption of internal memory of HPCC, comprising:
Receive the submission script of the current operation of HPCC;
By keyword search and analysis, obtain the internal memory of the current operation of HPCCFault tolerant mechanism;
Determine the fault-tolerant rank of described internal memory fault tolerant mechanism according to described internal memory fault tolerant mechanism, foundationDescribed fault-tolerant rank is distributed the power consumption of internal memory of HPCC.
The present invention also provides a kind of device that reduces HPCC power consumption of internal memory, this deviceComprise:
Monitoring modular, for the operation conditions of Real-Time Monitoring HPCC;
Analysis module, divides for the homework type that HPCC is being movedAnalyse, determine the internal memory fault tolerant mechanism of the operation that HPCC moving;
Distribution module, for obtaining the fault-tolerant rank of described internal memory fault tolerant mechanism, according to described appearanceWrong rank is distributed the power consumption of internal memory of HPCC.
Preferably, described internal memory fault tolerant mechanism comprises: without fault tolerant mechanism, even-odd check mechanismOr ECC verification scheme.
Preferably, described device also comprises:
Setting module, after bringing into operation in high-performance calculation application program, obtains high-performanceCalculate the submission script of the current operation of cluster, and set keyword in submission script, utilizeThe internal memory fault tolerant mechanism of the current operation of HPCC set in keyword.
Preferably, described distribution module comprises:
Receiving element, for receiving the submission script of current operation of HPCC;
Search unit, for by keyword search and analysis, obtains HPCCThe internal memory fault tolerant mechanism of current operation;
Allocation units, for determining described internal memory fault tolerant mechanism according to described internal memory fault tolerant mechanismFault-tolerant rank, distributes the power consumption of internal memory of HPCC according to described fault-tolerant rank.
A kind of method and dress that reduces HPCC power consumption of internal memory provided by the present inventionPut the operation conditions of Real-Time Monitoring HPCC; HPCC is transportedThe homework type of row is analyzed, and determines the internal memory of the operation that HPCC movingFault tolerant mechanism; Obtain the fault-tolerant rank of described internal memory fault tolerant mechanism, according to described fault-tolerant rank pairThe power consumption of internal memory of HPCC distributes. Visible, by HPCCOperation is monitored in real time, is analyzed, determine at present operation of HPCC homework type inDeposit fault tolerant mechanism, and come HPCC according to the fault-tolerant rank of internal memory fault tolerant mechanismPower consumption of internal memory distributes, thereby adjusts power consumption of internal memory according to fault-tolerant rank, reduces internal memory meritConsumption, is keeping raising energy loss-rate under the constant prerequisite of cluster performance.
Brief description of the drawings
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, belowTo the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described, aobvious andEasily insight, the accompanying drawing in the following describes is only embodiments of the invention, common for this areaTechnical staff, is not paying under the prerequisite of creative work, can also be attached according to what provideFigure obtains other accompanying drawing.
Fig. 1 is a kind of method that reduces HPCC power consumption of internal memory provided by the present inventionFlow chart;
Fig. 2 is a kind of device that reduces HPCC power consumption of internal memory provided by the present inventionStructural representation.
Detailed description of the invention
Core of the present invention is to provide a kind of method that reduces HPCC power consumption of internal memoryAnd device, to realize reduction power consumption of internal memory, keeping improving energy under the constant prerequisite of cluster performanceLoss-rate.
In order to make those skilled in the art person understand better the present invention program, below in conjunction with thisAccompanying drawing in inventive embodiments, carries out clear, complete to the technical scheme in the embodiment of the present inventionGround is described, and obviously, described embodiment is only the present invention's part embodiment, instead ofWhole embodiment. Based on the embodiment in the present invention, those of ordinary skill in the art are not havingMake the every other embodiment obtaining under creative work prerequisite, all belong to the present invention's protectionScope.
Please refer to Fig. 1, Fig. 1 is a kind of HPCC that reduces of side provided by the present inventionThe flow chart of the method for power consumption of internal memory, the method comprises:
S11: the operation conditions of Real-Time Monitoring HPCC;
S12: the homework type that HPCC is being moved is analyzed, determines highThe internal memory fault tolerant mechanism of the operation that performance calculating cluster is moving;
S13: obtain the fault-tolerant rank of internal memory fault tolerant mechanism, the fault-tolerant rank of foundation is to high-performance meterThe power consumption of internal memory of calculating cluster distributes.
Wherein, internal memory fault tolerant mechanism comprises: without fault tolerant mechanism, even-odd check mechanism or ECCVerification scheme.
A kind of method that reduces HPCC power consumption of internal memory provided by the present invention, in real timeThe operation conditions of monitoring HPCC; The operation that HPCC is being movedType is analyzed, and determines the internal memory fault tolerant mechanism of the operation that HPCC moving;Obtain the fault-tolerant rank of internal memory fault tolerant mechanism, the fault-tolerant rank of foundation is in HPCCDepositing power consumption distributes.
Visible, the method by HPCC operation monitor in real time, analyze, determineHPCC is the internal memory fault tolerant mechanism of the homework type of operation at present, and holds according to internal memoryThe fault-tolerant rank of wrong mechanism is distributed the power consumption of internal memory of HPCC, thereby complies withAdjust power consumption of internal memory according to fault-tolerant rank, reduce power consumption of internal memory, keeping, cluster performance is constantUnder prerequisite, improving can loss-rate.
Preferably, before the operation conditions of Real-Time Monitoring HPCC, at high-performance meterAfter calculation application program brings into operation, obtain the submission script of the current operation of HPCC,And set keyword in submission script, utilize keyword to set the current of HPCCThe internal memory fault tolerant mechanism of operation.
Based on step S13, this step preferably adopts following steps to realize:
S1: the submission script that receives the current operation of HPCC;
S2: by keyword search and analysis, obtain the current operation of HPCCInternal memory fault tolerant mechanism;
S3: determine the fault-tolerant rank of internal memory fault tolerant mechanism according to internal memory fault tolerant mechanism, according to fault-tolerantRank is distributed the power consumption of internal memory of HPCC.
Please refer to Fig. 2, Fig. 2 is a kind of HPCC internal memory that reduces provided by the present inventionThe structural representation of the device of power consumption, this device comprises:
Monitoring modular 101, for the operation conditions of Real-Time Monitoring HPCC;
Analysis module 102, carries out for the homework type that HPCC is being movedAnalyze, determine the internal memory fault tolerant mechanism of the operation that HPCC moving;
Distribution module 103, for obtaining the fault-tolerant rank of internal memory fault tolerant mechanism, according to tolerant levelThe other power consumption of internal memory to HPCC distributes.
Wherein, internal memory fault tolerant mechanism comprises: without fault tolerant mechanism, even-odd check mechanism or ECCVerification scheme.
Preferably, described device also comprises:
Setting module, after bringing into operation in high-performance calculation application program, obtains high-performanceCalculate the submission script of the current operation of cluster, and set keyword in submission script, utilizeThe internal memory fault tolerant mechanism of the current operation of HPCC set in keyword.
Wherein, distribution module comprises:
Receiving element, for receiving the submission script of current operation of HPCC;
Search unit, for by keyword search and analysis, obtains HPCCThe internal memory fault tolerant mechanism of current operation;
Allocation units, for determining the tolerant level of internal memory fault tolerant mechanism according to internal memory fault tolerant mechanismNot, according to fault-tolerant rank, the power consumption of internal memory of HPCC is distributed.
A kind of device that reduces HPCC power consumption of internal memory provided by the present invention, monitoringThe operation conditions of module Real-Time Monitoring HPCC; Analysis module is to high-performance calculation collectionThe homework type that group is moving is analyzed, and determines the work that HPCC is movingThe internal memory fault tolerant mechanism of industry; Distribution module is obtained the fault-tolerant rank of internal memory fault tolerant mechanism, according to holdingWrong rank is distributed the power consumption of internal memory of HPCC.
Visible, this device by HPCC operation monitor in real time, analyze, determineHPCC is the internal memory fault tolerant mechanism of the homework type of operation at present, and holds according to internal memoryThe fault-tolerant rank of wrong mechanism is distributed the power consumption of internal memory of HPCC, thereby complies withAdjust power consumption of internal memory according to fault-tolerant rank, reduce power consumption of internal memory, keeping, cluster performance is constantUnder prerequisite, improving can loss-rate.
Concrete, monitor in real time, analyze, in advance by HPCC job scheduling systemAltimetry performance calculates the at present homework type of operation of cluster, and according to homework type switch internal memoryFault tolerant mechanism, thus power consumption of internal memory reduced, keeping improving energy under the constant prerequisite of cluster performanceLoss-rate.
Described analysis module is HPCC internal memory fault tolerant mechanism switch element; Described pointJoining module is HPCC job scheduling system homework type analytic unit.
HPCC job scheduling system homework type analytic unit, submits to by operationScript keyword is set, and judges whether this operation needs internal memory fault-tolerant, and has three kinds of judged results:Without fault-tolerant; Adopt even-odd check; Adopt ECC verification.
HPCC internal memory fault tolerant mechanism switch element, can also be according to high-performance calculationCluster job scheduling system homework type analytic unit, changes the fault tolerant mechanism of internal memory in real time.
By HPCC job scheduling system monitor in real time, prediction high-performanceCalculate the cluster homework type of operation at present, and according to the fault tolerant mechanism of homework type switch internal memory,Thereby reduction power consumption of internal memory, is keeping raising energy loss-rate under the constant prerequisite of cluster performance.
Detailed, first high-performance calculation application program brings into operation, and HPCC is doneIndustry generally submits to script to be submitted to job scheduling system by operation, and is divided by job scheduling systemJoin computational resource. Submit in script and set keyword in operation, the internal memory of setting this operation holdsWrong mechanism, is divided three classes: without fault-tolerant; Adopt even-odd check; Adopt ECC verification.
Job scheduling system homework type analytic unit receives after job script, passes through keywordSearch for and analyze, set the fault-tolerant rank of this operation, then to cluster internal memory fault tolerant mechanism switchUnit sends instruction. Cluster internal memory fault tolerant mechanism switch element receives after instruction, to being assigned toServer memory send setting instruction, its internal memory fault tolerant mechanism is set.
Cluster internal memory fault tolerant mechanism switch element can adopt cluster job scheduling system to serverThe form that BMC controls realizes, and the ECC switch of internal memory can be controlled by BMC at present.
The operation result of high performance application generally has accuracy standard, finishes at job runAfter, can judge that the different set of fault tolerant mechanism is on the correctness impact of result by precision checking.If Accuracy is large or result is incorrect, can set the fault tolerant mechanism of the type operationFor by force, i.e. ECC. If precision does not affect, can set and adopt weak fault tolerant mechanism (strangeEven bit check) or without fault-tolerant.
To sum up, a kind of method that reduces HPCC power consumption of internal memory provided by the present inventionAnd device, the operation conditions of Real-Time Monitoring HPCC; To HPCC justHomework type in operation is analyzed, and determines operation that HPCC movingInternal memory fault tolerant mechanism; Obtain the fault-tolerant rank of internal memory fault tolerant mechanism, the fault-tolerant rank of foundation is to high propertyThe power consumption of internal memory that can calculate cluster distributes. Visible, by HPCC operationMonitoring in real time, analysis, determine that the internal memory of the homework type of the current operation of HPCC holdsWrong mechanism, and carry out the internal memory to HPCC according to the fault-tolerant rank of internal memory fault tolerant mechanismPower consumption is distributed, thereby adjusts power consumption of internal memory according to fault-tolerant rank, reduces power consumption of internal memory,Keeping, under the constant prerequisite of cluster performance, raising can loss-rate.
Above to a kind of side that reduces HPCC power consumption of internal memory provided by the present inventionMethod and device are described in detail. Applied specific case herein to principle of the present invention andEmbodiment is set forth, and the explanation of above embodiment is just of the present invention for helping to understandMethod and core concept thereof. It should be pointed out that for those skilled in the art,Under the premise without departing from the principles of the invention, can also carry out some improvement and modification to the present invention,These improvement and modification also fall in the protection domain of the claims in the present invention.

Claims (8)

1. a method that reduces HPCC power consumption of internal memory, is characterized in that, bagDraw together:
The operation conditions of Real-Time Monitoring HPCC;
The homework type that HPCC is being moved is analyzed, and determines high-performance meterThe internal memory fault tolerant mechanism of the operation that calculation cluster is moving;
Obtain the fault-tolerant rank of described internal memory fault tolerant mechanism, the described fault-tolerant rank of foundation is to high-performanceThe power consumption of internal memory that calculates cluster distributes.
2. the method for claim 1, is characterized in that, described internal memory fault tolerant mechanismComprise: without fault tolerant mechanism, even-odd check mechanism or ECC verification scheme.
3. the method for claim 1, is characterized in that, the high property of described Real-Time MonitoringBefore calculating the operation conditions of cluster, also comprise:
After high-performance calculation application program brings into operation, obtain the current of HPCCThe submission script of operation, and set keyword in submission script, utilize keyword to set high propertyCan calculate the internal memory fault tolerant mechanism of the current operation of cluster.
4. method as claimed in claim 3, is characterized in that, described in obtain described internal memoryThe fault-tolerant rank of fault tolerant mechanism, the internal memory merit according to described fault-tolerant rank to HPCCConsumption is distributed, and comprising:
Receive the submission script of the current operation of HPCC;
By keyword search and analysis, obtain the internal memory of the current operation of HPCCFault tolerant mechanism;
Determine the fault-tolerant rank of described internal memory fault tolerant mechanism according to described internal memory fault tolerant mechanism, foundationDescribed fault-tolerant rank is distributed the power consumption of internal memory of HPCC.
5. a device that reduces HPCC power consumption of internal memory, is characterized in that, bagDraw together:
Monitoring modular, for the operation conditions of Real-Time Monitoring HPCC;
Analysis module, divides for the homework type that HPCC is being movedAnalyse, determine the internal memory fault tolerant mechanism of the operation that HPCC moving;
Distribution module, for obtaining the fault-tolerant rank of described internal memory fault tolerant mechanism, according to described appearanceWrong rank is distributed the power consumption of internal memory of HPCC.
6. device as claimed in claim 5, is characterized in that, described internal memory fault tolerant mechanismComprise: without fault tolerant mechanism, even-odd check mechanism or ECC verification scheme.
7. device as claimed in claim 5, is characterized in that, described device also comprises:
Setting module, after bringing into operation in high-performance calculation application program, obtains high-performanceCalculate the submission script of the current operation of cluster, and set keyword in submission script, utilizeThe internal memory fault tolerant mechanism of the current operation of HPCC set in keyword.
8. device as claimed in claim 7, is characterized in that, described distribution module comprises:
Receiving element, for receiving the submission script of current operation of HPCC;
Search unit, for by keyword search and analysis, obtains HPCCThe internal memory fault tolerant mechanism of current operation;
Allocation units, for determining described internal memory fault tolerant mechanism according to described internal memory fault tolerant mechanismFault-tolerant rank, distributes the power consumption of internal memory of HPCC according to described fault-tolerant rank.
CN201510983353.2A 2015-12-24 2015-12-24 A kind of method and device reducing High Performance Computing Cluster power consumption of internal memory Active CN105607726B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510983353.2A CN105607726B (en) 2015-12-24 2015-12-24 A kind of method and device reducing High Performance Computing Cluster power consumption of internal memory

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510983353.2A CN105607726B (en) 2015-12-24 2015-12-24 A kind of method and device reducing High Performance Computing Cluster power consumption of internal memory

Publications (2)

Publication Number Publication Date
CN105607726A true CN105607726A (en) 2016-05-25
CN105607726B CN105607726B (en) 2018-11-23

Family

ID=55987714

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510983353.2A Active CN105607726B (en) 2015-12-24 2015-12-24 A kind of method and device reducing High Performance Computing Cluster power consumption of internal memory

Country Status (1)

Country Link
CN (1) CN105607726B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023077762A1 (en) * 2021-11-03 2023-05-11 华为技术有限公司 Allocation method and apparatus for data storage space
CN116755982A (en) * 2023-05-15 2023-09-15 合芯科技(苏州)有限公司 A server energy consumption ratio calculation method and system
CN118820021A (en) * 2024-08-02 2024-10-22 开元云(北京)科技有限公司 A memory power consumption monitoring system for high performance computing clusters

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007103590A2 (en) * 2006-02-21 2007-09-13 Freescale Semiconductor Inc. Error correction device and method thereof
US20080201626A1 (en) * 2007-02-20 2008-08-21 Qimonda North America Corp. Power savings for memory with error correction mode
CN101980339A (en) * 2010-11-04 2011-02-23 浙江大学 An Error Correction Coding Method for DRAM Cache
US20120144264A1 (en) * 2010-12-06 2012-06-07 Bains Kuljit S Memory Device On the Fly CRC Mode

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007103590A2 (en) * 2006-02-21 2007-09-13 Freescale Semiconductor Inc. Error correction device and method thereof
US20080201626A1 (en) * 2007-02-20 2008-08-21 Qimonda North America Corp. Power savings for memory with error correction mode
CN101980339A (en) * 2010-11-04 2011-02-23 浙江大学 An Error Correction Coding Method for DRAM Cache
US20120144264A1 (en) * 2010-12-06 2012-06-07 Bains Kuljit S Memory Device On the Fly CRC Mode

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023077762A1 (en) * 2021-11-03 2023-05-11 华为技术有限公司 Allocation method and apparatus for data storage space
CN116755982A (en) * 2023-05-15 2023-09-15 合芯科技(苏州)有限公司 A server energy consumption ratio calculation method and system
CN118820021A (en) * 2024-08-02 2024-10-22 开元云(北京)科技有限公司 A memory power consumption monitoring system for high performance computing clusters

Also Published As

Publication number Publication date
CN105607726B (en) 2018-11-23

Similar Documents

Publication Publication Date Title
Kansal et al. Virtual machine power metering and provisioning
US9696786B2 (en) System and method for optimizing energy consumption by processors
CN108733540B (en) Method and system for testing computational power and power consumption of mining machine
US20130139152A1 (en) Cloud provisioning accelerator
Nguyen et al. Availability modeling and analysis of a data center for disaster tolerance
US11700210B2 (en) Enhanced selection of cloud architecture profiles
CN102789529B (en) Fault prediction method, device, system and equipment
Benedict Energy-aware performance analysis methodologies for HPC architectures—An exploratory study
CN102959510A (en) Method and system for computer power and resource consumption modeling
CN104156296A (en) System and method for intelligently monitoring large-scale data center cluster computing nodes
US10423201B2 (en) Method and apparatus for demand estimation for energy management of client systems
CN105607726A (en) Method and device for lowering internal storage power consumption of high-performance computing cluster
CN103744772A (en) Method and system for detecting task running performance
CN104615945A (en) Code cracking method and system based on multiple GPU cracking devices
CN115269108A (en) Data processing method, device and equipment
CN105354127A (en) Cloud management platform based monitoring method
CN103957229B (en) Active update method, device and the server of physical machine in IaaS cloud system
Rosà et al. Demystifying casualties of evictions in big data priority scheduling
EP3826233B1 (en) Enhanced selection of cloud architecture profiles
CN115757075A (en) Task abnormity detection method and device, computer equipment and storage medium
Pavlenko et al. Vertically Autoscaling Monolithic Applications with CaaSPER: Scalable C ontainer-a s-a-S ervice P erformance E nhanced R esizing Algorithm for the Cloud
CN115471215B (en) Business process processing method and device
CN105573885A (en) Method and device for monitoring and counting bottom hardware behaviours
CN106155782A (en) Virtual machine migration method and device
CN112579046B (en) User story analysis method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant