CN109117328A - Memory bandwidth optimization method, device and the storage medium of isomery mixing memory system - Google Patents
Memory bandwidth optimization method, device and the storage medium of isomery mixing memory system Download PDFInfo
- Publication number
- CN109117328A CN109117328A CN201810818661.3A CN201810818661A CN109117328A CN 109117328 A CN109117328 A CN 109117328A CN 201810818661 A CN201810818661 A CN 201810818661A CN 109117328 A CN109117328 A CN 109117328A
- Authority
- CN
- China
- Prior art keywords
- memory bandwidth
- memory
- parameter
- bandwidth
- isomery mixing
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2205—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2273—Test methods
Abstract
The invention discloses memory bandwidth optimization method, device and the storage mediums of a kind of isomery mixing memory system, wherein this method is to extract the parameter for the memory bandwidth for influencing isomery mixing memory system first, then testing time, fopenmp parameter and the Compiler Optimization level parameters of running memory bandwidth are set, the optimum results of the parameter of memory bandwidth, the testing time of memory bandwidth, fopenmp parameter and the corresponding memory bandwidth of Compiler Optimization level parameters are finally calculated.It can be seen that this method can calculate the optimum results of memory bandwidth by the above parameter, enables isomery mixing memory system to play stronger data-handling capacity using such optimum results, improve the speed of data processing.In addition, the memory bandwidth optimization device and storage medium of isomery mixing memory system disclosed by the invention correspond to the above method, effect is same as above.
Description
Technical field
The present invention relates to isomery hybrid system fields, excellent more particularly to a kind of memory bandwidth of isomery mixing memory system
Change method, apparatus and storage medium.
Background technique
With the rapid development of computer technology, data volume is more and more, and the speed issue of big data processing is more prominent.
Traditional DRAM medium faces enormous challenge in terms of handling big data, therefore produce isomery mixing memory system.It is existing
In technology, isomery mixing memory system is usually to be made of DRAM medium and nonvolatile memory, and the system is in addition to including
Outside the characteristic of DRAM medium itself, the non-volatile of nonvolatile memory, low-power consumption, fast relative to disk read-write speed is also had both
The advantages of, therefore, get the attention in recent years.
In isomery mixing memory system, memory bandwidth is a very important parameter, the speed of determination data processing.
It can be seen that how to realize that the optimization of memory bandwidth be those skilled in the art ground urgently to be resolved problem.
Summary of the invention
The object of the present invention is to provide a kind of memory bandwidth optimization method of isomery mixing memory system, device and storages to be situated between
Matter, for realizing the optimization to memory bandwidth, to improve the speed of data processing.
In order to solve the above technical problems, the present invention provides a kind of memory bandwidth optimization method of isomery mixing memory system,
Include:
S10: the parameter for influencing the memory bandwidth of isomery mixing memory system is extracted;
S11: testing time, fopenmp parameter and the Compiler Optimization level parameters of setting running memory bandwidth;
S12: calculate the parameter of the memory bandwidth, the testing time of the memory bandwidth, the fopenmp parameter and
The optimum results of the corresponding memory bandwidth of the Compiler Optimization level parameters.
Preferably, the parameter of the memory bandwidth specifically include cpu frequency under performance mode, hyperthread parameter,
The setting parameter and program line number of passes of array size when memory bandwidth calculates.
Preferably, the setting parameter of array size is obtained especially by such as under type when the memory bandwidth calculates:
cache*core*5/8;
Wherein, cache is the capacity of CPU cache, and core is the nucleus number of CPU.
It preferably, further include exporting the optimum results into journal file.
Preferably, the isomery mixing memory system includes specially DRAM medium and nonvolatile memory.
Preferably, the testing time of the memory bandwidth is specially 5 times or 10 times.
Preferably, step S10-S12 is realized especially by the mode of script.
In order to solve the above technical problems, the present invention also provides a kind of optimizations of the memory bandwidth of isomery mixing memory system to fill
It sets, comprising:
Extraction unit, for extracting the parameter for influencing the memory bandwidth of isomery mixing memory system;
Setting unit, for testing time, fopenmp parameter and the Compiler Optimization rank of running memory bandwidth to be arranged
Parameter;
Computing unit, for calculating the parameter of the memory bandwidth, testing time of the memory bandwidth, described
The optimum results of fopenmp parameter and the corresponding memory bandwidth of the Compiler Optimization level parameters.
In order to solve the above technical problems, the present invention also provides a kind of optimizations of the memory bandwidth of isomery mixing memory system to fill
It sets, including memory, for storing computer program;
Processor realizes the memory of isomery mixing memory system as described above when for executing the computer program
The step of bandwidth optimization method.
In order to solve the above technical problems, the present invention also provides a kind of computer readable storage medium, it is described computer-readable
Computer program is stored on storage medium, the computer program realizes that isomery as described above is mixed when being executed by processor
The step of closing the memory bandwidth optimization method of memory system.
The memory bandwidth optimization method of isomery mixing memory system provided by the present invention is to extract influence isomery to mix first
The parameter of the memory bandwidth of memory system is closed, then testing time, fopenmp parameter and the compiling of running memory bandwidth are set
Device optimizes level parameters, finally calculates the parameter of memory bandwidth, the testing time of memory bandwidth, fopenmp parameter and compiling
Device optimizes the optimum results of the corresponding memory bandwidth of level parameters.It can be seen that this method can be calculated by the above parameter
The optimum results of memory bandwidth enable isomery mixing memory system to play stronger data using such optimum results
Processing capacity improves the speed of data processing.
It is and upper in addition, the memory bandwidth optimization device and storage medium of isomery mixing memory system provided by the present invention
It is corresponding to state method, therefore equally there is above-mentioned beneficial effect.
Detailed description of the invention
In order to illustrate the embodiments of the present invention more clearly, attached drawing needed in the embodiment will be done simply below
It introduces, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ordinary skill people
For member, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of process of the memory bandwidth optimization method of isomery mixing memory system provided in an embodiment of the present invention
Figure;
Fig. 2 is a kind of process of the memory bandwidth optimization method of isomery mixing memory system provided in an embodiment of the present invention
Figure;
Fig. 3 is that a kind of memory bandwidth of isomery mixing memory system provided in an embodiment of the present invention optimizes the structure of device
Figure.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole embodiments.Based on this
Embodiment in invention, those of ordinary skill in the art are without making creative work, obtained every other
Embodiment belongs to the scope of the present invention.
The memory bandwidth optimization method, device and storage that core of the invention is to provide a kind of isomery mixing memory system are situated between
Matter, for realizing the optimization to memory bandwidth, to improve the speed of data processing.
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.
Fig. 1 is a kind of process of the memory bandwidth optimization method of isomery mixing memory system provided in an embodiment of the present invention
Figure.As shown in Figure 1, this method comprises:
S10: the parameter for influencing the memory bandwidth of isomery mixing memory system is extracted.
In specific implementation, isomery mixing memory system includes specially DRAM medium and nonvolatile memory.But
Other than the isomery mixing memory system of above two medium composition, the combination of other media can also be, the present embodiment is not made
It limits.
It should be noted that the parameter for influencing memory bandwidth is more in isomery mixing memory system, although choosing more
Parameter can more reasonably calculate optimal memory bandwidth, still, since parameter is more, then calculating process also can be corresponding
Increase, therefore, in specific implementation, can according to the appropriate Selecting All Parameters of concrete scene and requirement of isomery memory system,
Preferably embodiment, the parameter of memory bandwidth specifically include cpu frequency under performance mode, hyperthread parameter,
The setting parameter and program line number of passes of array size when memory bandwidth calculates.It is understood that above-mentioned several parameters are one
Kind concrete application scene, does not represent and there was only these parameters.
CPU is according to work requirements, and there are many operational modes, for example, performance high performance mode, powersave
Battery saving mode, on-demand mode, super performance mode etc..
Performance high performance mode refers to, can transport at full capacity by maximum basic frequency is set under this modular system
Turn, dominant frequency can be always maintained at maximum value within the set range.It and battery saving mode are on the contrary, always by setting highest frequency fortune
Row;Powersave battery saving mode refers to that system will remain in setting minimum frequency underrun under this mode.Most by setting
Low frequency operation, it is daily there is no use value, unless cooperation setcpu contextual model, uses this shaping modes when closing screen sleep.
Cpu frequency is specifically frequency of the CPU under performance high performance mode in the present embodiment.Hyperthread parameter
Refer to unlatching hyperthread, allow CPU and memory that can reach full working condition simultaneously, maximum plays the corresponding parameter of bandwidth of memory.
The setting parameter of array size when memory bandwidth calculates, array size when memory bandwidth generally also being made to calculate, wherein memory bandwidth
The setting parameter of array size is obtained especially by such as under type when calculating: cache*core*5/8;Wherein, cache CPU
The capacity of cache, core are the nucleus number of CPU.If a server has 2 physical cpus, each physical cpu is 4 core,
That is nucleus number.5 indicate the spring factor for the test peak value setting for reaching memory bandwidth, why to be to come out because obtaining divided by 8
Data be bit, to be converted into Byte type.Finally, program line number of passes may be set according to actual conditions, the present invention does not make
It limits.Preferably embodiment, it is 2 times of core that setting program line number of passes OMP_NUM_THREADS parameter, which comes into force,.
S11: testing time, fopenmp parameter and the Compiler Optimization level parameters of setting running memory bandwidth.
It should be noted that the testing time in the present embodiment may be set according to actual conditions, for example, can be 5 times
Or 10 times, this embodiment is not limited.In view of number of run has a certain impact for optimum results, in specific implementation,
Multiple testing times can be set, other parameters remain unchanged, and by comparing the optimum results of every kind of testing time, choose wherein
The corresponding testing time of best optimum results.
In addition, Compiler Optimization level parameters can be set as needed, for example, Compiler Optimization rank ginseng can be set
Number is 03, i.e. Middle grade.
S12: the parameter of memory bandwidth, the testing time of memory bandwidth, fopenmp parameter and Compiler Optimization grade are calculated
The optimum results of the corresponding memory bandwidth of other parameter.
It is exactly the optimum results that corresponding memory bandwidth is calculated according to the parameter that S10-S11 is obtained in this step, due to
This part content is known to those skilled in the art, so it will not be repeated.
Preferably embodiment, step S10-S12 are realized especially by the mode of script.By way of script,
Artificial tuning cost is saved, and execution efficiency is also higher.
The memory bandwidth optimization method of isomery mixing memory system provided in this embodiment is to extract influence isomery to mix first
The parameter of the memory bandwidth of memory system is closed, then testing time, fopenmp parameter and the compiling of running memory bandwidth are set
Device optimizes level parameters, finally calculates the parameter of memory bandwidth, the testing time of memory bandwidth, fopenmp parameter and compiling
Device optimizes the optimum results of the corresponding memory bandwidth of level parameters.It can be seen that this method can be calculated by the above parameter
The optimum results of memory bandwidth enable isomery mixing memory system to play stronger data using such optimum results
Processing capacity improves the speed of data processing.
Fig. 2 is a kind of process of the memory bandwidth optimization method of isomery mixing memory system provided in an embodiment of the present invention
Figure.As shown in Fig. 2, the present invention also provides another embodiments on the basis of a upper embodiment, in another embodiment,
The above method further include:
S20: optimum results are exported into journal file.
It is only that the optimum results of memory bandwidth have been calculated in a upper embodiment, it will be excellent but there is no restrictions
Change result to export, in the present embodiment, optimum results be exported to journal file, it is to be understood that journal file is for remembering
The record file or file set of recording system action event, operating system have operating system journal file, and Database Systems have number
According to library syslog file, etc..By this step, the content that optimum results are viewed in journal file can be made, side
Just user checks.
In addition, in other embodiments, it can also will include that the journal files of optimum results stores, facilitate subsequent
Check.There are many kinds of the modes of storage, can be locally stored, can also upload unification monitor supervision platform, passes through unification in this way
Monitor supervision platform can obtain the optimum results of the corresponding memory bandwidth of multiple isomery mixing memory systems, realize the mesh of unified monitoring
's.
The present invention also provides a kind of memory bandwidth of isomery mixing memory system corresponding with above method optimization devices
Embodiment.It should be noted that the present invention is described the embodiment of device part from two angles, one is be based on function
The angle of module, another kind are hardware based angles.
Firstly, describing from the angle of functional module, Fig. 3 is a kind of isomery mixing memory system provided in an embodiment of the present invention
Memory bandwidth optimization device structure chart.As shown in figure 3, the device includes:
Extraction unit 10, for extracting the parameter for influencing the memory bandwidth of isomery mixing memory system;
Setting unit 11, for testing time, fopenmp parameter and the Compiler Optimization grade of running memory bandwidth to be arranged
Other parameter;
Computing unit 12, for calculate the parameter of memory bandwidth, the testing time of memory bandwidth, fopenmp parameter and
The optimum results of the corresponding memory bandwidth of Compiler Optimization level parameters.
Since the embodiment of device part is corresponded to each other with the embodiment of method part, the embodiment of device part is asked
Referring to the description of the embodiment of method part, wouldn't repeat here.
The memory bandwidth of isomery mixing memory system provided in this embodiment optimizes device, including extraction unit, setting list
Member and computing unit, first extraction unit extract the parameter for influencing the memory bandwidth of isomery mixing memory system, and then setting is single
Testing time, fopenmp parameter and the Compiler Optimization level parameters of member setting running memory bandwidth, last computing unit meter
It is corresponding interior to calculate the parameter of memory bandwidth, the testing time of memory bandwidth, fopenmp parameter and Compiler Optimization level parameters
Deposit the optimum results of bandwidth.It can be seen that the present apparatus can calculate the optimum results of memory bandwidth by the above parameter, use
Such optimum results enable isomery mixing memory system to play stronger data-handling capacity, improve data processing
Speed.
In addition, described from the angle of hardware configuration, a kind of isomery mixing memory system provided in an embodiment of the present invention it is interior
Bandwidth optimization device is deposited, which includes memory, for storing computer program;
Processor realizes the memory band such as isomery mixing memory system in above-described embodiment when for executing computer program
The step of wide optimization method.
Since the embodiment of device part is corresponded to each other with the embodiment of method part, the embodiment of device part is asked
Referring to the description of the embodiment of method part, wouldn't repeat here.In some embodiments of the invention, processor and memory
It can be connected by bus or other means.
The memory bandwidth of isomery mixing memory system provided in this embodiment optimizes device, including processor and memory,
Memory is stored with computer program, so that processor in the process of implementation, can be realized following method: being to extract to influence first
The parameter of the memory bandwidth of isomery mixing memory system, be then arranged the testing time of running memory bandwidth, fopenmp parameter with
And Compiler Optimization level parameters, finally calculate the parameter of memory bandwidth, the testing time of memory bandwidth, fopenmp parameter with
And the optimum results of the corresponding memory bandwidth of Compiler Optimization level parameters.It can be seen that this method can pass through the above parameter
The optimum results for calculating memory bandwidth enable isomery mixing memory system to play stronger using such optimum results
Data-handling capacity, improve the speed of data processing.
Finally, the present invention also provides a kind of embodiments of computer readable storage medium.Wherein, computer-readable storage medium
It is stored with computer program in matter, is realized when computer program is executed by processor such as above-mentioned isomery mixing as described in the examples
The step of memory bandwidth optimization method of memory system.
Since the embodiment of device part is corresponded to each other with the embodiment of method part, the embodiment of device part is asked
Referring to the description of the embodiment of method part, wouldn't repeat here.
It is understood that if the method in above-described embodiment is realized in the form of SFU software functional unit and as independence
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, of the invention
Technical solution substantially all or part of the part that contributes to existing technology or the technical solution can be in other words
It is expressed in the form of software products, which is stored in a storage medium, and it is each to execute the present invention
The all or part of the steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(Read-OnlyMemory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc.
The various media that can store program code.
Computer storage medium provided in this embodiment is stored with for realizing the memory bandwidth of isomery mixing memory system
The program of optimization method is the parameter for extracting the memory bandwidth for influencing isomery mixing memory system first, then in setting operation
Testing time, fopenmp parameter and the Compiler Optimization level parameters of bandwidth are deposited, the parameter, interior of memory bandwidth is finally calculated
Deposit the testing time of bandwidth, the optimum results of fopenmp parameter and the corresponding memory bandwidth of Compiler Optimization level parameters.By
This is made using such optimum results as it can be seen that this method can calculate the optimum results of memory bandwidth by the above parameter
Isomery mixing memory system can play stronger data-handling capacity, improve the speed of data processing.
Above to memory bandwidth optimization method, device and the storage medium of isomery mixing memory system provided by the present invention
It is described in detail.Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are
With the difference of other embodiments, the same or similar parts in each embodiment may refer to each other.Embodiment is disclosed
Device for, since it is corresponded to the methods disclosed in the examples, so be described relatively simple, related place is referring to method
Part illustrates.It should be pointed out that for those skilled in the art, before not departing from the principle of the invention
It puts, can be with several improvements and modifications are made to the present invention, these improvement and modification also fall into the guarantor of the claims in the present invention
It protects in range.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Claims (10)
1. a kind of memory bandwidth optimization method of isomery mixing memory system characterized by comprising
S10: the parameter for influencing the memory bandwidth of isomery mixing memory system is extracted;
S11: testing time, fopenmp parameter and the Compiler Optimization level parameters of setting running memory bandwidth;
S12: the parameter of the memory bandwidth, the testing time of the memory bandwidth, the fopenmp parameter and described are calculated
The optimum results of the corresponding memory bandwidth of Compiler Optimization level parameters.
2. the memory bandwidth optimization method of isomery mixing memory system according to claim 1, which is characterized in that in described
The parameter for depositing bandwidth specifically includes array ruler when cpu frequency under performance mode, hyperthread parameter, memory bandwidth calculate
Very little setting parameter and program line number of passes.
3. the memory bandwidth optimization method of isomery mixing memory system according to claim 2, which is characterized in that in described
The setting parameter of array size is obtained especially by such as under type when depositing bandwidth calculation: cache*core*5/8;
Wherein, cache is the capacity of CPU cache, and core is the nucleus number of CPU.
4. the memory bandwidth optimization method of isomery mixing memory system according to claim 1, which is characterized in that further include
The optimum results are exported into journal file.
5. the memory bandwidth optimization method of isomery mixing memory system according to claim 1, which is characterized in that described different
Structure mixing memory system includes specially DRAM medium and nonvolatile memory.
6. the memory bandwidth optimization method of isomery mixing memory system according to claim 1, which is characterized in that in described
The testing time for depositing bandwidth is specially 5 times or 10 times.
7. the memory bandwidth optimization method of isomery mixing memory system described in -6 any one according to claim 1, feature
It is, step S10-S12 is realized especially by the mode of script.
8. a kind of memory bandwidth of isomery mixing memory system optimizes device characterized by comprising
Extraction unit, for extracting the parameter for influencing the memory bandwidth of isomery mixing memory system;
Setting unit, for testing time, fopenmp parameter and the Compiler Optimization rank ginseng of running memory bandwidth to be arranged
Number;
Computing unit, for calculating the parameter of the memory bandwidth, the testing time of the memory bandwidth, fopenmp ginseng
The optimum results of the corresponding memory bandwidth of several and described Compiler Optimization level parameters.
9. a kind of memory bandwidth of isomery mixing memory system optimizes device, which is characterized in that including memory, based on storing
Calculation machine program;
Processor realizes isomery mixing memory as described in any one of claim 1 to 7 when for executing the computer program
The step of memory bandwidth optimization method of system.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, the computer program realize isomery mixing memory system as described in any one of claim 1 to 7 when being executed by processor
The step of memory bandwidth optimization method of system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810818661.3A CN109117328A (en) | 2018-07-24 | 2018-07-24 | Memory bandwidth optimization method, device and the storage medium of isomery mixing memory system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810818661.3A CN109117328A (en) | 2018-07-24 | 2018-07-24 | Memory bandwidth optimization method, device and the storage medium of isomery mixing memory system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109117328A true CN109117328A (en) | 2019-01-01 |
Family
ID=64863272
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810818661.3A Pending CN109117328A (en) | 2018-07-24 | 2018-07-24 | Memory bandwidth optimization method, device and the storage medium of isomery mixing memory system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109117328A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022012312A1 (en) * | 2020-07-17 | 2022-01-20 | 华为技术有限公司 | Method and apparatus for monitoring memory bandwidth |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011013867A (en) * | 2009-06-30 | 2011-01-20 | Panasonic Corp | Data processor and performance evaluation analysis system |
CN103605589A (en) * | 2013-11-19 | 2014-02-26 | 浪潮电子信息产业股份有限公司 | Method for optimizing performance test on internal memory of Intel MIC (microphone) card |
CN104268050A (en) * | 2014-10-17 | 2015-01-07 | 浪潮电子信息产业股份有限公司 | Simple method for testing bandwidth of internal memory |
CN104268076A (en) * | 2014-09-23 | 2015-01-07 | 浪潮电子信息产业股份有限公司 | Memory bandwidth automatically testing method applicable to various processor platforms |
CN105117310A (en) * | 2015-07-30 | 2015-12-02 | 浪潮电子信息产业股份有限公司 | Linux system-based memory read-write bandwidth optimization testing method |
CN107168836A (en) * | 2017-05-15 | 2017-09-15 | 郑州云海信息技术有限公司 | A kind of method and device of server memory bandwidth test |
-
2018
- 2018-07-24 CN CN201810818661.3A patent/CN109117328A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011013867A (en) * | 2009-06-30 | 2011-01-20 | Panasonic Corp | Data processor and performance evaluation analysis system |
CN103605589A (en) * | 2013-11-19 | 2014-02-26 | 浪潮电子信息产业股份有限公司 | Method for optimizing performance test on internal memory of Intel MIC (microphone) card |
CN104268076A (en) * | 2014-09-23 | 2015-01-07 | 浪潮电子信息产业股份有限公司 | Memory bandwidth automatically testing method applicable to various processor platforms |
CN104268050A (en) * | 2014-10-17 | 2015-01-07 | 浪潮电子信息产业股份有限公司 | Simple method for testing bandwidth of internal memory |
CN105117310A (en) * | 2015-07-30 | 2015-12-02 | 浪潮电子信息产业股份有限公司 | Linux system-based memory read-write bandwidth optimization testing method |
CN107168836A (en) * | 2017-05-15 | 2017-09-15 | 郑州云海信息技术有限公司 | A kind of method and device of server memory bandwidth test |
Non-Patent Citations (1)
Title |
---|
佚名: "内存测试Stream程序分析(一)--基本参数", 《HTTPS://BLOG.CSDN.NET/MICHAELWUBO/ARTICLE/DETAILS/46907463》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022012312A1 (en) * | 2020-07-17 | 2022-01-20 | 华为技术有限公司 | Method and apparatus for monitoring memory bandwidth |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102663116B (en) | Multi-dimensional OLAP (On Line Analytical Processing) inquiry processing method facing column storage data warehouse | |
Lim et al. | Towards Accurate and Fast Evaluation of {Multi-Stage} Log-structured Designs | |
CN108710613A (en) | Acquisition methods, terminal device and the medium of text similarity | |
IL269344A (en) | Quantifying consistency of a system architecture | |
US20150248462A1 (en) | Dynamically improving streaming query performance based on collected measurement data | |
CN109034244A (en) | Line loss abnormality diagnostic method and device based on electric quantity curve characteristic model | |
CN103177094B (en) | Cleaning method of data of internet of things | |
CN104077328B (en) | The operation diagnostic method and equipment of MapReduce distributed system | |
US10430462B2 (en) | Systems and methods for generating a property graph data model representing a system architecture | |
CN107092627A (en) | The column-shaped storage of record is represented | |
US20180268077A1 (en) | Systems and methods for generating a weighted property graph data model representing a system architecture | |
IL269343A (en) | Quantifying robustness by analyzing a property graph data model | |
WO2020081586A1 (en) | System and method for dependency analysis in a multidimensional database environment | |
Matusevych et al. | Hokusai-sketching streams in real time | |
CN114609994A (en) | Fault diagnosis method and device based on multi-granularity regularization rebalance incremental learning | |
Jensen et al. | Scalable model-based management of correlated dimensional time series in modelardb+ | |
CN109117328A (en) | Memory bandwidth optimization method, device and the storage medium of isomery mixing memory system | |
CN206021244U (en) | A kind of data collecting system under distributed computer cluster | |
CN104731716B (en) | A kind of date storage method | |
CN109684517A (en) | A kind of historical data storage method, reading/writing method, storage device and equipment | |
CN106019369B (en) | Geological data lossless compression algorithm in a kind of improved SEG Y files | |
CN108280224B (en) | Ten thousand grades of dimension data generation methods, device, equipment and storage medium | |
CN103294954A (en) | Compound document malicious code detecting technique and system based on spectral analysis | |
Lin | Retracted: Research on Optimization of Distributed Big Data Real-Time Management Method | |
US11379410B2 (en) | Automated information lifecycle management of indexes |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190101 |
|
RJ01 | Rejection of invention patent application after publication |