CN105068640B - It is a kind of improve high-performance calculation energy consumption than method and system - Google Patents
It is a kind of improve high-performance calculation energy consumption than method and system Download PDFInfo
- Publication number
- CN105068640B CN105068640B CN201510497744.3A CN201510497744A CN105068640B CN 105068640 B CN105068640 B CN 105068640B CN 201510497744 A CN201510497744 A CN 201510497744A CN 105068640 B CN105068640 B CN 105068640B
- Authority
- CN
- China
- Prior art keywords
- precision
- performance
- calculation
- result
- performance calculation
- 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.)
- Active
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 219
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000005265 energy consumption Methods 0.000 title claims abstract description 26
- 235000013399 edible fruits Nutrition 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Landscapes
- Debugging And Monitoring (AREA)
Abstract
This application provides it is a kind of improve high-performance calculation energy consumption than method, including：High performance application is calculated according to full accuracy, obtains high performance application output result；High performance application output result is analyzed and determined, determines the precision of high-performance calculation；The difference of the precision and default high-performance calculation precision of high-performance calculation is judged；When the precision of high-performance calculation and the difference of default high-performance calculation precision be not in default allowable range of error, then repeat the above process, until the difference is in default allowable range of error；The computational accuracy of high-performance calculation processor is adjusted according to the precision of high-performance calculation；Utilize the output result of the accuracy computation high performance application after adjustment.Finally the precision of determining high-performance calculation is less than full accuracy, and control processor is reduced the power consumption of processor, in the case where calculation amount is constant, improved energy consumption ratio with relatively low accuracy computation high performance application.
Description
Technical field
This application involves field of computer technology, more particularly to it is a kind of improve high-performance calculation energy consumption than method and be
System.
Background technology
With the development of technology, people increasingly pay close attention to the high energy consumption that high-performance calculation consumes.
Existing high-performance calculation is generally given tacit consent to be calculated using full accuracy, causes to consume during high-performance calculation
Energy consumption it is larger, increase the expense of energy consumption.
Therefore, how high-performance calculation is effectively carried out, in the case where calculation amount is constant, reduces the energy of high-performance calculation
Consumption, it is the current technical issues that need to address of those skilled in the art to improve energy consumption ratio.
Invention content
Technical problems to be solved in this application be to provide it is a kind of improve high-performance calculation energy consumption than method and system, solution
Acquiescence in the prior art of having determined is calculated using full accuracy, is caused the energy consumption consumed during high-performance calculation larger, is added
The problem of big expense of energy consumption.
Its concrete scheme is as follows：
It is a kind of improve high-performance calculation energy consumption than method, this method includes：
High performance application is calculated according to full accuracy, obtains high performance application output result；
High performance application output result is analyzed and determined, determines the precision of high-performance calculation；
The difference of the precision and default high-performance calculation precision of the high-performance calculation is judged；
When the precision of the high-performance calculation and the difference of default high-performance calculation precision be not in default allowable range of error
When interior, then execution is described calculates high performance application according to full accuracy, obtains the step of high performance application output result
Suddenly, until the difference of the precision of the high-performance calculation and default high-performance calculation precision is in the default allowable range of error
Until；
The computational accuracy of high-performance calculation processor is adjusted according to the precision of the high-performance calculation；
Utilize the output result of high performance application described in the accuracy computation after adjustment.
Above-mentioned method, it is optionally, described to calculate high performance application according to full accuracy, obtain performance application journey
Sequence export as a result, including：
High performance application is calculated according to full accuracy, obtains final calculation result and the centre of high performance application
Result of calculation.
Above-mentioned method, it is optionally, described that high performance application output result is analyzed and determined, determine high-performance
The precision of calculating, including：
The number of significant figures of the final calculation result is analyzed and determined, determines the precision of high-performance calculation；
And/or；
The number of significant figures of the results of intermediate calculations is analyzed and determined, determines the precision of high-performance calculation.
Above-mentioned method, optionally, when the number of significant figures to the final calculation result and the intermediate computations knot
When the number of significant figures of fruit is analyzed and determined, including：
Compare the length of the number of significant figures of the final calculation result and the effective digital of the results of intermediate calculations
The length of digit；
When the length of the number of significant figures of the results of intermediate calculations is less than the effective digital of the final calculation result
During the length of digit, the essence of the high-performance calculation is determined according to the length of the number of significant figures of the results of intermediate calculations
Degree；
When the length of the number of significant figures of the results of intermediate calculations is more than the effective digital of the final calculation result
During the length of digit, the essence of the high-performance calculation is determined according to the length of the number of significant figures of the final calculation result
Degree.
Above-mentioned method, it is optionally, described that high performance application output result is analyzed and determined, determine high-performance
The precision of calculating, including：
Judge whether the high performance application has the definition of result validity；
When there is the high performance application result validity to define, defined, determined according to the result validity
The precision of high-performance calculation.
It is a kind of improve high-performance calculation energy consumption than system, which includes：
For calculating high performance application according to full accuracy, it is defeated to obtain high performance application for first computing unit
Go out result；
It analyzes and determines unit, for being analyzed and determined to high performance application output result, determines high-performance
The precision of calculating, the precision of the high-performance calculation are less than the full accuracy；
First judging unit carries out for the difference of the precision to the high-performance calculation and default high-performance calculation precision
Judge；When the precision of the high-performance calculation and the difference of default high-performance calculation precision be not in default allowable range of error
When, then described the step of calculating high performance application according to full accuracy, obtaining high performance application output result is performed,
Until the precision of the high-performance calculation and the difference of default high-performance calculation precision are in the default allowable range of error
Only；
Adjustment unit, for adjusting the computational accuracy of high-performance calculation processor according to the precision of the high-performance calculation；
Second computing unit, for utilizing the output result of the accuracy computation high performance application after adjusting.
Above-mentioned system, optionally, first computing unit, including：
High performance application is calculated according to full accuracy, obtains final calculation result and the centre of high performance application
Result of calculation.
Above-mentioned system, optionally, the analytical judgment unit, including：
The number of significant figures of the final calculation result is analyzed and determined, determines the precision of high-performance calculation；
And/or；
The number of significant figures of the results of intermediate calculations is analyzed and determined, determines the precision of high-performance calculation.
Above-mentioned system, optionally, in the analytical judgment unit, when to the effective digital of the final calculation result
When the number of significant figures of digit and the results of intermediate calculations is analyzed and determined, including：
Comparing unit, length and the intermediate computations knot for the number of significant figures of the final calculation result
The length of the number of significant figures of fruit；
First determination unit, by work as the results of intermediate calculations number of significant figures length be less than it is described it is final based on
When calculating the length of the number of significant figures of result, according to determining the length of the number of significant figures of the results of intermediate calculations
The precision of high-performance calculation；
Second determination unit, by work as the results of intermediate calculations number of significant figures length be more than it is described it is final based on
When calculating the length of the number of significant figures of result, according to determining the length of the number of significant figures of the final calculation result
The precision of high-performance calculation.
Above-mentioned system, optionally, the analytical judgment unit, including：
Second judgment unit, for judging whether the high performance application has the definition of result validity；
Third determination unit, for when the high performance application have result validity define when, according to the knot
Fruit validity defines, and determines the precision of high-performance calculation.
The application provide a kind of raising high-performance calculation energy consumption than method in, run high performance application for the first time
When, high performance application is calculated according to full accuracy, obtains high performance application output result；Then, to the high property
Energy application program output result is analyzed and determined that determine the precision of high-performance calculation, the precision of the high-performance calculation is less than
The full accuracy；The difference of the precision and default high-performance calculation precision of the high-performance calculation is judged；When described
When the difference of the precision of high-performance calculation and default high-performance calculation precision is not in default allowable range of error, then compute repeatedly
The output of high performance application obtains high-performance calculation precision, until the height as a result, analyzed and determined to output result
Until the precision and the difference of default high-performance calculation precision that performance calculates are in the default allowable range of error；Then, then
In high performance application operational process later, high-performance calculation processor is adjusted according to the precision of the high-performance calculation
Computational accuracy；Utilize the output result of high performance application described in the accuracy computation after adjustment.It is finally determined in the application
The precision of high-performance calculation is less than full accuracy, and control processor is reduced with relatively low accuracy computation high performance application
The power consumption of processor, in the case where calculation amount is constant, improves energy consumption ratio.
Description of the drawings
In order to illustrate more clearly of the technical solution in the embodiment of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present application, for
For those of ordinary skill in the art, without having to pay creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 be the application a kind of raising high-performance calculation energy consumption than embodiment of the method flow chart；
Fig. 2 be the application a kind of raising high-performance calculation energy consumption than system embodiment schematic diagram.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, the technical solution in the embodiment of the present application is carried out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, those of ordinary skill in the art are obtained every other without making creative work
Embodiment shall fall in the protection scope of this application.
With reference to figure 1, show the application it is a kind of improve high-performance calculation energy consumption than embodiment of the method flow chart, can be with
Include the following steps：
Step S101：High performance application is calculated according to full accuracy, obtains high performance application output result.
In the application, high-performance calculation application program brings into operation, and in first operation, the control of processor computational accuracy is single
Member does not do any action, and processor computing unit is calculated according to the full accuracy of acquiescence, after obtaining full accuracy calculating
High performance application exports result.
High performance application output as a result, including：The final calculation result of high performance application and intermediate meter
Calculate the record logs such as result.
And by run for the first time obtain the high performance application output result feed back to high performance application simulation
Analyze predicting unit.
Step S102：High performance application output result is analyzed and determined, determines the essence of high-performance calculation
Degree.
High performance application sunykatuib analysis predicting unit divides the high performance application output result received
Analysis judges, to determine most suitable computational accuracy.
In the application, most suitable computational accuracy can be determined by three kinds of method analyses.
The number of significant figures of the final calculation result can be analyzed and determined, determine the essence of high-performance calculation
Degree；
And/or；
The number of significant figures of the results of intermediate calculations is analyzed and determined, determines the precision of high-performance calculation.
When equal to the number of significant figures of the final calculation result and the number of significant figures of the results of intermediate calculations
When being analyzed and determined, the length of the number of significant figures of the final calculation result and the results of intermediate calculations have
Imitate the length of digit.
When the length of the number of significant figures of the results of intermediate calculations is less than the effective digital of the final calculation result
During the length of digit, the essence of the high-performance calculation is determined according to the length of the number of significant figures of the results of intermediate calculations
Degree.
When the length of the number of significant figures of the results of intermediate calculations is more than the effective digital of the final calculation result
During the length of digit, the essence of the high-performance calculation is determined according to the length of the number of significant figures of the final calculation result
Degree.
When high-performance calculation application program itself is defined with result validity, can be defined according to its validity (logical
It is often number of significant figures), derive the number of significant figures needed during the high performance application operation.
Specially：Judge whether the high performance application has the definition of result validity.
When there is the high performance application result validity to define, defined, determined according to the result validity
The precision of high-performance calculation.
Can also be by artificial setup algorithm precision, i.e., the precision analyzed by the domain expert from point of view of practicability
Empirical value carries out the result precision set of its needs.
Step S103：The difference of the precision and default high-performance calculation precision of the high-performance calculation is judged.
The precision of the high-performance calculation and the high-performance calculation precision pre-set are subjected to difference operation, judge institute
Difference is stated whether in the range of error permission.
Step S104：When the precision of the high-performance calculation and the difference of default high-performance calculation precision be not in default error
When in allowed band, then step S101~step S104 is repeated, until the precision of the high-performance calculation is with presetting high property
Until the difference of energy computational accuracy is in the default allowable range of error.
Step S105：The computational accuracy of high-performance calculation processor is adjusted according to the precision of the high-performance calculation.
Step S106：Utilize the output result of high performance application described in the accuracy computation after adjustment.
After determining high-performance calculation precision, processor computational accuracy control unit is according to the high-performance calculation precision tune
Whole high-performance calculation processor in operational process afterwards, i.e., controls the computational accuracy of application program feasible relatively low
In precision, and transfer to the calculating of processor computing unit progress lower accuracy.
At present, the adjustment of three kinds of integer-bit, IEEE single precisions and IEEE double precisions precision can be carried out.
The application provide a kind of raising high-performance calculation energy consumption than method in, run high performance application for the first time
When, high performance application is calculated according to full accuracy, obtains high performance application output result；Then, to the high property
Energy application program output result is analyzed and determined that determine the precision of high-performance calculation, the precision of the high-performance calculation is less than
The full accuracy；The difference of the precision and default high-performance calculation precision of the high-performance calculation is judged；When described
When the difference of the precision of high-performance calculation and default high-performance calculation precision is not in default allowable range of error, then compute repeatedly
The output of high performance application obtains high-performance calculation precision, until the height as a result, analyzed and determined to output result
Until the precision and the difference of default high-performance calculation precision that performance calculates are in the default allowable range of error；Then, then
In high performance application operational process later, high-performance calculation processor is adjusted according to the precision of the high-performance calculation
Computational accuracy；Utilize the output result of high performance application described in the accuracy computation after adjustment.It is finally determined in the application
The precision of high-performance calculation is less than full accuracy, and control processor is reduced with relatively low accuracy computation high performance application
The power consumption of processor, in the case where calculation amount is constant, improves energy consumption ratio.
It is corresponding with the method that a kind of raising high-performance calculation energy consumption ratio method embodiment of above-mentioned the application is provided, referring to
Fig. 2, present invention also provides a kind of raising high-performance calculation energy consumption than system embodiment, in the present embodiment, which includes：
First computing unit 201 for calculating high performance application according to full accuracy, obtains high performance application
Export result.
In first computing unit, high performance application is calculated according to full accuracy, obtains performance application journey
The final calculation result and results of intermediate calculations of sequence.
It analyzes and determines unit 202, for being analyzed and determined to high performance application output result, determines high property
The precision that can be calculated, the precision of the high-performance calculation are less than the full accuracy.
The analytical judgment unit, including：
The number of significant figures of the final calculation result is analyzed and determined, determines the precision of high-performance calculation；
And/or；
The number of significant figures of the results of intermediate calculations is analyzed and determined, determines the precision of high-performance calculation.
When equal to the number of significant figures of the final calculation result and the number of significant figures of the results of intermediate calculations
When being analyzed and determined, including：
Comparing unit, length and the intermediate computations knot for the number of significant figures of the final calculation result
The length of the number of significant figures of fruit.
First determination unit, by work as the results of intermediate calculations number of significant figures length be less than it is described it is final based on
When calculating the length of the number of significant figures of result, according to determining the length of the number of significant figures of the results of intermediate calculations
The precision of high-performance calculation.
Second determination unit, by work as the results of intermediate calculations number of significant figures length be more than it is described it is final based on
When calculating the length of the number of significant figures of result, according to determining the length of the number of significant figures of the final calculation result
The precision of high-performance calculation.
The analytical judgment unit, including：
Second judgment unit, for judging whether the high performance application has the definition of result validity.
Third determination unit, for when the high performance application have result validity define when, according to the knot
Fruit validity defines, and determines the precision of high-performance calculation.
First judging unit 203, for the precision to the high-performance calculation and the difference of default high-performance calculation precision
Judged；When the precision of the high-performance calculation and the difference of default high-performance calculation precision be not in default allowable range of error
When interior, then execution is described calculates high performance application according to full accuracy, obtains the step of high performance application output result
Suddenly, until the difference of the precision of the high-performance calculation and default high-performance calculation precision is in the default allowable range of error
Until.
Adjustment unit 204, for adjusting the calculating essence of high-performance calculation processor according to the precision of the high-performance calculation
Degree.
Second computing unit 205, for utilizing the output result of the accuracy computation high performance application after adjusting.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation is all difference from other examples, and just to refer each other for identical similar part between each embodiment.
For device class embodiment, since it is basicly similar to embodiment of the method, so description is fairly simple, related part is joined
See the part explanation of embodiment of the method.
Finally, it is to be noted that, herein, 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, term " comprising ", "comprising" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only include 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 also there are other identical elements in the process, method, article or apparatus that includes the element.
For convenience of description, it is divided into various units during description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit is realized can in the same or multiple software and or hardware during application.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can
It is realized by the mode of software plus required general hardware platform.Based on such understanding, the technical solution essence of the application
On the part that the prior art contributes can be embodied in the form of software product in other words, the computer software product
It can be stored in storage medium, such as ROM/RAM, magnetic disc, CD, be used including some instructions so that a computer equipment
(can be personal computer, server either network equipment etc.) performs the certain of each embodiment of the application or embodiment
Method described in part.
A kind of raising high-performance calculation energy consumption ratio method provided herein and system are described in detail above,
The principle and implementation of this application are described for specific case used herein, and the explanation of above example is only used
Understand the present processes and its core concept in help；Meanwhile for those of ordinary skill in the art, according to the application's
Thought, there will be changes in specific embodiments and applications, in conclusion the content of the present specification should not be construed as
Limitation to the application.
Claims (10)
1. it is a kind of improve high-performance calculation energy consumption than method, which is characterized in that this method includes：
High performance application is calculated according to full accuracy, obtains high performance application output result；
High performance application output result is analyzed and determined, determines the precision of high-performance calculation；
The difference of the precision and default high-performance calculation precision of the high-performance calculation is judged；
When the precision of the high-performance calculation and the difference of default high-performance calculation precision be not in default allowable range of error,
Described the step of calculating high performance application according to full accuracy, obtaining high performance application output result is then performed, directly
Until the precision of the high-performance calculation and the difference of default high-performance calculation precision are in the default allowable range of error；
The computational accuracy of high-performance calculation processor is adjusted according to the precision of the high-performance calculation；
Utilize the output result of high performance application described in the accuracy computation after adjustment.
2. according to the method described in claim 1, it is characterized in that, it is described according to full accuracy calculate high performance application,
Obtain high performance application output as a result, including：
High performance application is calculated according to full accuracy, obtains the final calculation result and intermediate computations of high performance application
As a result.
3. according to the method described in claim 2, it is characterized in that, described analyze high performance application output result
Judge, determine the precision of high-performance calculation, including：
The number of significant figures of the final calculation result is analyzed and determined, determines the precision of high-performance calculation；
And/or；
The number of significant figures of the results of intermediate calculations is analyzed and determined, determines the precision of high-performance calculation.
4. according to the method described in claim 3, it is characterized in that, when to the number of significant figures of the final calculation result and
When the number of significant figures of the results of intermediate calculations is analyzed and determined, including：
Compare the length of the number of significant figures of the final calculation result and the number of significant figures of the results of intermediate calculations
Length；
When the length of the number of significant figures of the results of intermediate calculations is less than the number of significant figures of the final calculation result
Length when, the precision of the high-performance calculation is determined according to the length of the number of significant figures of the results of intermediate calculations；
When the length of the number of significant figures of the results of intermediate calculations is more than the number of significant figures of the final calculation result
Length when, the precision of the high-performance calculation is determined according to the length of the number of significant figures of the final calculation result.
5. according to the method described in claim 2, it is characterized in that, described analyze high performance application output result
Judge, determine the precision of high-performance calculation, including：
Judge whether the high performance application has the definition of result validity；
When there is the high performance application result validity to define, defined according to the result validity, determine high property
The precision that can be calculated.
6. it is a kind of improve high-performance calculation energy consumption than system, which is characterized in that the system includes：
First computing unit for calculating high performance application according to full accuracy, obtains high performance application output knot
Fruit；
It analyzes and determines unit, for being analyzed and determined to high performance application output result, determines high-performance calculation
Precision, the precision of the high-performance calculation is less than the full accuracy；
First judging unit, the difference for the precision to the high-performance calculation and default high-performance calculation precision are sentenced
It is disconnected；When the precision of the high-performance calculation and the difference of default high-performance calculation precision be not in default allowable range of error,
Described the step of calculating high performance application according to full accuracy, obtaining high performance application output result is then performed, directly
Until the precision of the high-performance calculation and the difference of default high-performance calculation precision are in the default allowable range of error；
Adjustment unit, for adjusting the computational accuracy of high-performance calculation processor according to the precision of the high-performance calculation；
Second computing unit, for utilizing the output result of the accuracy computation high performance application after adjusting.
7. system according to claim 6, which is characterized in that first computing unit, including：
High performance application is calculated according to full accuracy, obtains the final calculation result and intermediate computations of high performance application
As a result.
8. system according to claim 7, which is characterized in that the analytical judgment unit, including：
The number of significant figures of the final calculation result is analyzed and determined, determines the precision of high-performance calculation；
And/or；
The number of significant figures of the results of intermediate calculations is analyzed and determined, determines the precision of high-performance calculation.
9. system according to claim 8, which is characterized in that in the analytical judgment unit, when to the final meter
When the number of significant figures of calculation result and the number of significant figures of the results of intermediate calculations are analyzed and determined, including：
Comparing unit, length and the results of intermediate calculations for the number of significant figures of the final calculation result
The length of number of significant figures；
First determination unit is less than the final calculating knot for working as the length of the number of significant figures of the results of intermediate calculations
During the length of the number of significant figures of fruit, the high property is determined according to the length of the number of significant figures of the results of intermediate calculations
The precision that can be calculated；
Second determination unit is more than the final calculating knot for working as the length of the number of significant figures of the results of intermediate calculations
During the length of the number of significant figures of fruit, the high property is determined according to the length of the number of significant figures of the final calculation result
The precision that can be calculated.
10. system according to claim 6, which is characterized in that the analytical judgment unit, including：
Second judgment unit, for judging whether the high performance application has the definition of result validity；
Third determination unit, for when there is the high performance application result validity to define, being had according to the result
The definition of effect property determines the precision of high-performance calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510497744.3A CN105068640B (en) | 2015-08-13 | 2015-08-13 | It is a kind of improve high-performance calculation energy consumption than method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510497744.3A CN105068640B (en) | 2015-08-13 | 2015-08-13 | It is a kind of improve high-performance calculation energy consumption than method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105068640A CN105068640A (en) | 2015-11-18 |
| CN105068640B true CN105068640B (en) | 2018-06-26 |
Family
ID=54498026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510497744.3A Active CN105068640B (en) | 2015-08-13 | 2015-08-13 | It is a kind of improve high-performance calculation energy consumption than method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105068640B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101154937A (en) * | 2006-09-28 | 2008-04-02 | 雅马哈株式会社 | Digital filter |
| CN101446804A (en) * | 2007-11-26 | 2009-06-03 | 北京北方微电子基地设备工艺研究中心有限责任公司 | Process control method and device thereof |
| CN104007676A (en) * | 2014-05-08 | 2014-08-27 | 潍柴动力股份有限公司 | Data calibration method and control system |
| CN104156195A (en) * | 2014-08-19 | 2014-11-19 | 中国航天科技集团公司第九研究院第七七一研究所 | System and method for integrating double-precision-extension 80-digit floating point processing unit in processor |
| CN104598197A (en) * | 2015-01-26 | 2015-05-06 | 中国科学院自动化研究所 | Operation method for reciprocal value and/or reciprocal square root of floating-point number and operation device |
-
2015
- 2015-08-13 CN CN201510497744.3A patent/CN105068640B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101154937A (en) * | 2006-09-28 | 2008-04-02 | 雅马哈株式会社 | Digital filter |
| CN101446804A (en) * | 2007-11-26 | 2009-06-03 | 北京北方微电子基地设备工艺研究中心有限责任公司 | Process control method and device thereof |
| CN104007676A (en) * | 2014-05-08 | 2014-08-27 | 潍柴动力股份有限公司 | Data calibration method and control system |
| CN104156195A (en) * | 2014-08-19 | 2014-11-19 | 中国航天科技集团公司第九研究院第七七一研究所 | System and method for integrating double-precision-extension 80-digit floating point processing unit in processor |
| CN104598197A (en) * | 2015-01-26 | 2015-05-06 | 中国科学院自动化研究所 | Operation method for reciprocal value and/or reciprocal square root of floating-point number and operation device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105068640A (en) | 2015-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104502704B (en) | A kind of harmonic contributions computational methods suitable for background harmonic voltage change | |
| Guo et al. | Multi-objective optimization of the proposed multi-reservoir operating policy using improved NSPSO | |
| Jia et al. | Decomposition–coordination model of reservoir group and flood storage basin for real-time flood control operation | |
| CN103617466B (en) | A kind of integrated evaluating method of commodity demand predication model | |
| CN104811344A (en) | Network dynamic service monitoring method and apparatus | |
| CN103457279A (en) | Determination method for partition D-STATCOM integrated optimization configuration scheme of large-scale power grid | |
| Md. Azamathulla | Gene-expression programming to predict friction factor for Southern Italian rivers | |
| CN103489034A (en) | Method and device for predicting and diagnosing online ocean current monitoring data | |
| Seyoum et al. | Investigation into the pressure-driven extension of the EPANET hydraulic simulation model for water distribution systems | |
| CN102737063B (en) | Processing method and processing system for log information | |
| CN102170131A (en) | Limit power calculating method of associated electricity transmission cross-section based on parallel calculating model | |
| Kan et al. | A heterogeneous computing accelerated SCE-UA global optimization method using OpenMP, OpenCL, CUDA, and OpenACC | |
| Kizilöz | Prediction model for the leakage rate in a water distribution system | |
| CN102890732B (en) | Hydrodynamic condition parallel numerical simulation method for channel with various structures | |
| CN103886391B (en) | Traffic prediction method and apparatus | |
| CN105868918A (en) | Similarity index computing method of harmonic current type monitoring sample | |
| CN105068640B (en) | It is a kind of improve high-performance calculation energy consumption than method and system | |
| Rumi et al. | CPU power consumption reduction in android smartphone | |
| Niu et al. | New trust-region algorithm for nonlinear constrained optimization | |
| CN111009927A (en) | Wind power and compressed air energy storage capacity optimization method and system | |
| CN116468116A (en) | Model searching method, device, chip, electronic equipment and computer storage medium | |
| CN105760270B (en) | A kind of method and device of Estimation of energy consumption | |
| Li et al. | A framework for event-based flood scaling analysis by hydrological modeling in data-scarce regions | |
| EP3769279A1 (en) | Method device and system for estimating life of a technical system | |
| Dilini et al. | Effective water management in the mahaweli reservoir system: Analyzing the inflow of the upmost reservoir |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180814 Address after: 200436 Room 411, No. three, JIANGCHANG Road, Jingan District, Shanghai, 411 Patentee after: Shanghai wave Cloud Computing Service Co., Ltd. Address before: 100085 floor 1, C 2-1, No. 2, Shang Di Road, Haidian District, Beijing. Patentee before: Electronic information industry Co.,Ltd of the tide (Beijing) |