CN106708682A - Method for improving SPEC-CPU-speed test performance of server - Google Patents
Method for improving SPEC-CPU-speed test performance of server Download PDFInfo
- Publication number
- CN106708682A CN106708682A CN201710042832.3A CN201710042832A CN106708682A CN 106708682 A CN106708682 A CN 106708682A CN 201710042832 A CN201710042832 A CN 201710042832A CN 106708682 A CN106708682 A CN 106708682A
- Authority
- CN
- China
- Prior art keywords
- cpu
- core
- server
- test results
- speed test
- 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
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- G06F11/2236—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 to test CPU or processors
- G06F11/2242—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 to test CPU or processors in multi-processor systems, e.g. one processor becoming the test master
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention provides a method for improving the SPEC-CPU-speed test performance of a server. A plurality of CPUs and a plurality of core processors are arranged in the server; the method includes the following steps that S1, the first CPU obtains the core-number adjustment range; S2, the first CPU limits the number of started cores in the core-number adjustment range to constrainedly increase the operating frequency of a single core; S3, under the selected core number, the operating environment of an SPEC CPU is established, and a configuration operating file name is speed; S4, the SPEC CPU operates for testing, and the test performance is obtained. The method is easy to achieve, the test result of the corresponding performance of the server is obviously improved, the performance can be improved only by adjusting of a BIOS without any adjustment of a hardware system or any adjustment of a software system, and compared with other modes, the limiting condition is small.
Description
Technical field
The invention belongs to Servers standard testing field, and in particular to one kind lifting server S PEC CPU speed are surveyed
The method for trying achievement.
Background technology
SPEC is standard performance assessment company(Standard Performance Evaluation Corporation)'s
Referred to as.SPEC by computer vendors, system integrator, university, research institution, consulting Deng Duo companies constitute it is non-profit-making
Tissue, the target of this tissue is to set up, safeguard a set of standard for assessing computer system.
The arithmetical operation of the traditional calculations performance testing tools such as SPEC cpu tests same Linpack, Super Pi circulation
Different to carry out benchmark test, SPEC cpu tests have used the application program of real world.SPEC cpu tests include 12
Item integer arithmetic and 17 floating-point operations, are divided into rate tests and test two, wherein rate test principal measure systems with speed
How concurrent calculation process performance, the single task process performance of speed principal measure systems.
As can be seen here, it is not high for the multiple threads Capability Requirement of system CPU in speed tests, otherwise but to ginseng
There is larger requirement with the single cpu core capabilities of test.Current two-way and two-way above server configure plural 6 core and
Above processor, due to the design and application characteristic of modern CPU, multi-core CPU is often reached with sacrificing the performance of single core
To the lifting of overall multiple threads ability.
The content of the invention
This practicality invention purpose be, for the design and application characteristic of above-mentioned modern CPU, multi-core CPU often with
Sacrifice the performance of single core to reach the Upgrade Problem of overall multiple threads ability, there is provided a kind of lifting server of design
The method of SPEC CPU speed test results, to solve above-mentioned technical problem.
To achieve the above object, the present invention provides following technical scheme:
A kind of method for lifting server S PEC CPU speed test results, is provided with multiple CPU, Duo Gehe in the server
The heart, using following steps:
S1. a CPU obtains core number adjusting range;
S2. a CPU limits the core amounts of unlatching in core number adjusting range, to force the operation for improving single core frequently
Rate;
S3. under selected core number, the running environment of SPEC CPU, configuration operation filename selection speed are built;
S4. operation SPEC CPU are tested, and obtain speed test results.
Further, a CPU includes the first core, and a CPU obtains the specific step of core number adjusting range in step 1
It is rapid as follows:
S11. a CPU detection service devices core number is M;
S12. a CPU controls M core fully open, and a CPU detects that the running frequency of single core is F;
S13. any one of CPU closings in addition to the first core enlivens core so that the core number of opening is M ', note
When record opens core number for M ', single core running frequency is F ';
S14. a CPU compares F and F ';
As F=F ', step S13 is returned to;
Work as F<During F ', core number M2=M ' is recorded;
S15. any one of CPU closings in addition to the first core enlivens core so that opening core number is M ' ', note
When record opens core number for M ' ', single core running frequency is F ' ';
S16. a CPU compares F ' and F ' ';
As F '<During F ' ', F '=F ' ', M '=M ' ' are made, return to step S15;
As F '=F ' ', core number M1=M ' is recorded;
The adjusting range that first CPU obtains core number is M1-M2.
Further, the opening and closing limitation of core is carried out under BOIS in step 1 or step 2.
Further, the software version using SPEC CPU2006 in the running environment of SPEC CPU is built in the step 3
This, SPEC CPU are run in step 4 carries out software version of the test using SPEC CPU2006.
Further, base value and peak value of the speed test results including overall scores are obtained in the step 4, and
Base values and peak values that speed test results are respectively itemized.
Further, each subitem achievement includes 400.perlbench, 401.bzip2,403.gcc, 429.mcf,
445.gobmk, 456.hmmer, 458.sjeng, 462.libquantum, 464. h264ref, 471.omnetpp,
The base values and peak values of 473.astar and 483.xalancbmk.
Further, the test result for being obtained in the step 4 is by the execution time normalization of tested computer, that is, to use
One reference processor performs execution time of the time divided by tested computer, and test result value is bigger, represent that performance is faster.
Further, test will be carried out three times in the step 4, take median.
Further, at least two CPU, at least six cores are provided with the server.
Further, the server product is applied to the server product that all BIOS support core cpu control.
The beneficial effects of the present invention are:The present invention supports the server product of core cpu control suitable for all BIOS,
As long as there is the control to enabling CPU core calculation in BIOS, it is possible to using this invention lifting corresponding test result;This
The content of the invention is easily achieved, obvious to the lifting of server respective performances test result, without doing any to hardware and software systems
Adjustment, only by the adjustment to BIOS it is achieved that restrictive condition is less compared with other modes.
Additionally, design principle reliability of the present invention, simple structure, with application prospect widely.
As can be seen here, compared with prior art, with prominent substantive distinguishing features and significant progress, it is implemented the present invention
Beneficial effect be also obvious.
Brief description of the drawings
Fig. 1 is the flow chart that the CPU of step 1 of the present invention oneth obtains core number adjusting range;
Fig. 2 is using the speed tests subitem and overall scores before the present invention;
Fig. 3 is using the speed tests subitem and overall scores after the present invention.
Specific embodiment:
To enable that the purpose of the present invention, feature, advantage are more obvious and understandable, below in conjunction with this specific embodiment
Accompanying drawing, the technical scheme in the present invention is clearly and completely described.
The present invention provides a kind of method for lifting server S PEC CPU speed test results, is set in the server
There are at least two CPU, at least six cores, using following steps:
S1. a CPU obtains core number adjusting range;What the adjustment of core number was carried out under BOIS;
As shown in figure 1 and table 1, comprise the following steps that:
S11. a CPU detection service devices core number is that M is 22;
S12. a CPU controls M for 22 cores are fully open, and a CPU detects the running frequency of single core for F is
2800MHz;Core is fully open to be carried out under BOIS;
S13. a CPU closes any one in addition to the first core and enlivens core so that the core number of opening is for M '
21, when record opening core number M ' is 21, single core running frequency is that F ' is 2800MHz;It is under BOIS to close core
Carry out;
S14. a CPU compares F and F ';
Because 2800MHz=2800MHz, S13 detections are continued back at,
Obtain core number for 20 when, single core running frequency be 2800MHz,
The like, when core number is for difference 19,18,17,16,15,14,13,12,11,10,9, single core running frequency point
All it is not 2800MHz,
Any one of repeat step S13, a CPU closing in addition to the first core enlivens core so that the core number of opening
Mesh is that M ' is 8, and when record opening core number M ' is 8, single core running frequency is that F ' is 2900MHz;
2800MHz<2900 MHz, record core number M2=8;
S15. any one of CPU closings in addition to the first core enlivens core so that it is that M ' ' is 7 to open core number,
When record opening core number M ' ' is 7, single core running frequency is that F ' ' is 3000MHz;Closing core is entered under BOIS
Capable;
S16. a CPU compares F ' and F ' ';
Because 2900MHz<3000MHz, makes F '=3000 MHz, and M '=7 continue back at S15 detections,
Obtain core number for 6 when, single core running frequency be 3100MHz, M '=6,
The like, obtain core number for 5 when, single core running frequency be 3200MHz, M '=5,
Core number be 4 when, single core running frequency be 3300MHz, M '=4,
Core number be 3 when, single core running frequency be 3400MHz, M '=3,
Core number be 2 when, single core running frequency be 3600MHz, M '=2,
Any one of repeat step S15, a CPU closing in addition to the first core enlivens core so that open core number
For M ' ' is 1, when record opening core number M ' ' is 1, single core running frequency is that F ' ' is 3600MHz;
Because 3600MHz=3600MHz, core number M1=M '=2 are recorded;
The adjusting range that first CPU obtains core number is 2-8.
Table 1
The data of table 1 are that by taking Intel model Cs PU as an example, sampling after tested is learnt, single in the state of open whole core cpu
The highest frequency that individual core can reach is 2.8GHz, and single core can reach most in the case of about 2/3 core of disabling
High-frequency is 3.0GHz, and highest frequency may be up to 3.6GHz during final only open 2 cores.
S2. a CPU limits the core amounts opened in core number adjusting range 2-8, to force to improve single core
Running frequency;Selected core number of opening is 2;
S3. under selected core number, the running environment of SPEC CPU, configuration operation filename selection speed are built;Build
Using the software version of SPEC CPU2006 in the running environment of SPEC CPU;
S4. operation SPEC CPU2006 are tested, and speed test results are obtained, using speed test results before and after the present invention
As shown in Fig. 2 and Fig. 3 and Biao 2;
Table 2
It can be seen that each item-dividing test achievement is improved, overall scores of the reflection to test(By taking Peak achievements as an example), using this
Total test result has 2.5% lifting after item method(Note:Illustrated according to SPEC officials, it is identical hard in SPEC cpu tests
The lower test result of part configuration is considered for great performance boost more than 1.75%).
Speed test results include the base values and peak values of overall scores, and the base that speed test results are respectively itemized
Value and peak values;
Each subitem achievement includes 400.perlbench, 401.bzip2,403.gcc, 429.mcf, 445.gobmk,
456.hmmer, 458.sjeng, 462.libquantum, 464. h264ref, 471.omnetpp, 473.astar and
The base values and peak values of 483.xalancbmk;
Test result is by the execution time normalization of tested computer, i.e., with an execution time for reference processor divided by quilt
The execution time of computer is surveyed, test result value is bigger, represent that performance is faster;
Test will be carried out three times, take median.
Server product of the invention is applied to the server product that all BIOS support core cpu control.
BIOS is the initialism of English " Basic Input Output System ", and literally rear Chinese is exactly "
Basic input output system ".In fact, it is one group of program being cured in computer on mainboard on a rom chip, and it is preserved
Self-check program and system self-triggered program after program, the start of the most important basic input and output of computer, it can be from CMOS
The specifying information that middle read-write system is set.Its major function be for computer provide the bottom, most direct hardware setting and
Control.
The integer arithmetic of SPEC CPU 2006 contains 400.perlbench PERL programming languages, 401.bzip2 pressures
Contracting, 403.gcc C compilers, 429.mcf Combinatorial Optimizations, 445.gobmk artificial intelligence(Go), 456.hmmer gene sequences
Row search, 458.sjeng artificial intelligence(Chess), 462.libquantum physics(Quantum calculation)、464.h264ref
Video compress, 471.omnetpp discrete events simulations, 473.astar pathfindings algorithm, 483.xalancbmk XML treatment are altogether
12.
SPEC CPU 2006 be SPEC tissue release a set of cpu subsystem assessment software, it include CINT2006 and
The sub-projects of CFP2006 two, are respectively used to measure integer performance and floating-point performance, and single project divides multithreading and single thread to survey again
Examination, the result of test includes base benchmark results and peak peak results, and the requirement of " Base " rule must be in compiling external member
In whole test events when optimized using general setting(Simple tuning), and " Peak " allows compiling each
The indivedual optimizations tested specifically designed for this are used during benchmark, that is to say, that Peak results leave for the manufacturer of testing results/
The more tuning leeway of evaluator are obtaining more preferable achievement.
Above-described embodiment is illustrative and not restrictive, and above-described embodiment is only to aid in understanding the present invention, therefore this
Invention is not limited to the embodiment described in specific embodiment, every by those skilled in the art's technology according to the present invention scheme
The other specific embodiments for drawing, also belong to the scope of protection of the invention.
Claims (10)
1. a kind of method for lifting server S PEC CPU speed test results, is provided with multiple CPU in the server, multiple
Core, it is characterised in that use following steps:
S1. a CPU obtains core number adjusting range;
S2. a CPU limits the core amounts of unlatching in core number adjusting range, to force the operation for improving single core frequently
Rate;
S3. under selected core number, the running environment of SPEC CPU, configuration operation filename selection speed are built;
S4. operation SPEC CPU are tested, and obtain speed test results.
2. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 1, it is characterised in that
First CPU includes the first core, and a CPU obtains comprising the following steps that for core number adjusting range in step 1:
S11. a CPU detection service devices core number is M;
S12. a CPU controls M core fully open, and a CPU detects that the running frequency of single core is F;
S13. any one of CPU closings in addition to the first core enlivens core so that the core number of opening is M ', note
When record opens core number for M ', single core running frequency is F ';
S14. a CPU compares F and F ';
As F=F ', step S13 is returned to;
Work as F<During F ', core number M2=M ' is recorded;
S15. any one of CPU closings in addition to the first core enlivens core so that opening core number is M ' ', note
When record opens core number for M ' ', single core running frequency is F ' ';
S16. a CPU compares F ' and F ' ';
As F '<During F ' ', F '=F ' ', M '=M ' ' are made, return to step S15;
As F '=F ' ', core number M1=M ' is recorded;
The adjusting range that first CPU obtains core number is M1-M2.
3. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 1, it is characterised in that
The opening and closing limitation of core is carried out under BOIS in step 1 or step 2.
4. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 1, it is characterised in that
The software version using SPEC CPU2006 in the running environment of SPEC CPU is built in the step 3, SPEC is run in step 4
CPU carries out software version of the test using SPEC CPU2006.
5. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 1, it is characterised in that
Base value and peak value of the speed test results including overall scores, and each point of speed test results are obtained in the step 4
The base values and peak values of item.
6. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 5, it is characterised in that
Each subitem achievement includes 400.perlbench, 401.bzip2,403.gcc, 429.mcf, 445.gobmk, 456.hmmer,
458.sjeng, 462.libquantum, 464. h264ref, 471.omnetpp, 473.astar and 483.xalancbmk's
Base values and peak values.
7. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 1, it is characterised in that
The test result obtained in the step 4 is by the execution time normalization of tested computer, i.e., with reference processor
The execution time, test result value was bigger divided by the execution time of tested computer, represented that performance is faster.
8. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 1, it is characterised in that
Test will be carried out three times in the step 4, take median.
9. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 1, it is characterised in that
At least two CPU, at least six cores are provided with the server.
10. a kind of method for lifting server S PEC CPU speed test results as claimed in claim 1, its feature exists
In the server product is applied to the server product that all BIOS support core cpu control.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710042832.3A CN106708682B (en) | 2017-01-20 | 2017-01-20 | Method for improving SPEC CPU speed test result of server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710042832.3A CN106708682B (en) | 2017-01-20 | 2017-01-20 | Method for improving SPEC CPU speed test result of server |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106708682A true CN106708682A (en) | 2017-05-24 |
CN106708682B CN106708682B (en) | 2020-10-23 |
Family
ID=58908836
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710042832.3A Active CN106708682B (en) | 2017-01-20 | 2017-01-20 | Method for improving SPEC CPU speed test result of server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106708682B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106951349A (en) * | 2017-03-16 | 2017-07-14 | 郑州云海信息技术有限公司 | A kind of method and apparatus for carrying out cpu test to domestic server using SPEC CPU |
CN107741868A (en) * | 2017-10-19 | 2018-02-27 | 郑州云海信息技术有限公司 | The method to set up and device of a kind of basic input-output system BIOS |
CN108845906A (en) * | 2018-07-19 | 2018-11-20 | 郑州云海信息技术有限公司 | A kind of method and device promoting SPEC cpu test result |
CN109101409A (en) * | 2018-07-24 | 2018-12-28 | 郑州云海信息技术有限公司 | A method of promoting SPEC CPU2006 execution efficiency |
CN111221696A (en) * | 2019-12-31 | 2020-06-02 | 苏州浪潮智能科技有限公司 | SPEC Power test method and device |
CN111450514A (en) * | 2020-03-26 | 2020-07-28 | 上海交通大学 | Quantum weiqi system and method |
CN112231156A (en) * | 2020-09-25 | 2021-01-15 | 苏州浪潮智能科技有限公司 | SPEC CPU2017 test result estimation method, system, device and medium |
CN113448789A (en) * | 2021-06-30 | 2021-09-28 | 东莞市小精灵教育软件有限公司 | Test method and device and electronic equipment |
CN116302728A (en) * | 2022-11-04 | 2023-06-23 | 中国标准化研究院 | Server energy efficiency test system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110296266A1 (en) * | 2010-05-27 | 2011-12-01 | International Business Machines Corporation | Self-Adjusting Critical Path Timing of Multi-Core VLSI Chip |
US20140044157A1 (en) * | 2011-02-14 | 2014-02-13 | The Regents Of The University Of California | Multi-band interconnect for inter-chip and intra-chip communications |
CN104216679A (en) * | 2013-08-28 | 2014-12-17 | 威盛电子股份有限公司 | Microprocessor and execution method thereof |
CN104820627A (en) * | 2015-05-05 | 2015-08-05 | 浪潮电子信息产业股份有限公司 | Method for automatically testing CPU computing performance |
CN105468522A (en) * | 2015-11-20 | 2016-04-06 | 浪潮电子信息产业股份有限公司 | Software pressure testing method based on Linux system CPU load control |
CN106033374A (en) * | 2015-03-13 | 2016-10-19 | 西安酷派软件科技有限公司 | Method and device for distributing multi-core central processing unit in multisystem, and terminal |
CN106155866A (en) * | 2016-08-01 | 2016-11-23 | 浪潮电子信息产业股份有限公司 | A kind of method and device of monitoring CPU core frequency |
CN106168846A (en) * | 2015-05-20 | 2016-11-30 | 联发科技股份有限公司 | Calculating system and the method controlling multi-core processor operation in calculating system |
-
2017
- 2017-01-20 CN CN201710042832.3A patent/CN106708682B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110296266A1 (en) * | 2010-05-27 | 2011-12-01 | International Business Machines Corporation | Self-Adjusting Critical Path Timing of Multi-Core VLSI Chip |
US20140044157A1 (en) * | 2011-02-14 | 2014-02-13 | The Regents Of The University Of California | Multi-band interconnect for inter-chip and intra-chip communications |
CN104216679A (en) * | 2013-08-28 | 2014-12-17 | 威盛电子股份有限公司 | Microprocessor and execution method thereof |
CN106033374A (en) * | 2015-03-13 | 2016-10-19 | 西安酷派软件科技有限公司 | Method and device for distributing multi-core central processing unit in multisystem, and terminal |
CN104820627A (en) * | 2015-05-05 | 2015-08-05 | 浪潮电子信息产业股份有限公司 | Method for automatically testing CPU computing performance |
CN106168846A (en) * | 2015-05-20 | 2016-11-30 | 联发科技股份有限公司 | Calculating system and the method controlling multi-core processor operation in calculating system |
CN105468522A (en) * | 2015-11-20 | 2016-04-06 | 浪潮电子信息产业股份有限公司 | Software pressure testing method based on Linux system CPU load control |
CN106155866A (en) * | 2016-08-01 | 2016-11-23 | 浪潮电子信息产业股份有限公司 | A kind of method and device of monitoring CPU core frequency |
Non-Patent Citations (1)
Title |
---|
SERGIO ALDEA · DIEGO R. LLANOS · ARTURO GONZÁLEZ-ESCRIBANO: "Using SPEC CPU2006 to evaluate the sequential and parallel code", 《THE JOURNAL OF SUPERCOMPUTING》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106951349A (en) * | 2017-03-16 | 2017-07-14 | 郑州云海信息技术有限公司 | A kind of method and apparatus for carrying out cpu test to domestic server using SPEC CPU |
CN107741868A (en) * | 2017-10-19 | 2018-02-27 | 郑州云海信息技术有限公司 | The method to set up and device of a kind of basic input-output system BIOS |
CN107741868B (en) * | 2017-10-19 | 2021-02-05 | 苏州浪潮智能科技有限公司 | Setting method and device for Basic Input Output System (BIOS) |
CN108845906A (en) * | 2018-07-19 | 2018-11-20 | 郑州云海信息技术有限公司 | A kind of method and device promoting SPEC cpu test result |
CN109101409A (en) * | 2018-07-24 | 2018-12-28 | 郑州云海信息技术有限公司 | A method of promoting SPEC CPU2006 execution efficiency |
CN111221696A (en) * | 2019-12-31 | 2020-06-02 | 苏州浪潮智能科技有限公司 | SPEC Power test method and device |
CN111450514A (en) * | 2020-03-26 | 2020-07-28 | 上海交通大学 | Quantum weiqi system and method |
CN111450514B (en) * | 2020-03-26 | 2023-05-02 | 上海交大知识产权管理有限公司 | Quantum go system and method |
CN112231156A (en) * | 2020-09-25 | 2021-01-15 | 苏州浪潮智能科技有限公司 | SPEC CPU2017 test result estimation method, system, device and medium |
CN112231156B (en) * | 2020-09-25 | 2022-07-08 | 苏州浪潮智能科技有限公司 | SPEC CPU2017 test result estimation method, system, device and medium |
CN113448789A (en) * | 2021-06-30 | 2021-09-28 | 东莞市小精灵教育软件有限公司 | Test method and device and electronic equipment |
CN116302728A (en) * | 2022-11-04 | 2023-06-23 | 中国标准化研究院 | Server energy efficiency test system |
Also Published As
Publication number | Publication date |
---|---|
CN106708682B (en) | 2020-10-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106708682A (en) | Method for improving SPEC-CPU-speed test performance of server | |
Singh et al. | Napel: Near-memory computing application performance prediction via ensemble learning | |
Limaye et al. | A workload characterization of the SPEC CPU2017 benchmark suite | |
Bienia et al. | Parsec vs. splash-2: A quantitative comparison of two multithreaded benchmark suites on chip-multiprocessors | |
Ding et al. | Autotuning algorithmic choice for input sensitivity | |
Purini et al. | Finding good optimization sequences covering program space | |
Chen et al. | Statistical GPU power analysis using tree-based methods | |
Gao et al. | Data motifs: A lens towards fully understanding big data and ai workloads | |
Azmandian et al. | Workload characterization at the virtualization layer | |
Domke et al. | Double-precision fpus in high-performance computing: an embarrassment of riches? | |
Wang et al. | GPGPU power estimation with core and memory frequency scaling | |
Hassan et al. | A reusable characterization of the memory system behavior of spec2017 and spec2006 | |
de Oliveira Castro et al. | Fine-grained benchmark subsetting for system selection | |
Akgun et al. | Improving storage systems using machine learning | |
Velasco-Montero et al. | On the correlation of CNN performance and hardware metrics for visual inference on a low-cost CPU-based platform | |
Gupta et al. | Survey of breast cancer detection using machine learning techniques in big data | |
Alcorta et al. | Lightweight ml-based runtime prefetcher selection on many-core platforms | |
Tang et al. | Sctuner: An autotuner addressing dynamic i/o needs on supercomputer i/o subsystems | |
Gao et al. | A dwarf-based scalable big data benchmarking methodology | |
Rodrigues et al. | Energy predictive models for convolutional neural networks on mobile platforms | |
Akgun et al. | Kml: Using machine learning to improve storage systems | |
Künas et al. | Offloading the training of an i/o access pattern detector to the cloud | |
Stanic et al. | VALib and SimpleVector: Tools for rapid initial research on vector architectures | |
Lella et al. | DBJoules: An Energy Measurement Tool for Database Management Systems | |
Xu et al. | Methodology for the analysis of dynamic application parallelism and its application to reconfigurable computing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200916 Address after: 215100 No. 1 Guanpu Road, Guoxiang Street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province Applicant after: SUZHOU LANGCHAO INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 450000 Henan province Zheng Dong New District of Zhengzhou City Xinyi Road No. 278 16 floor room 1601 Applicant before: ZHENGZHOU YUNHAI INFORMATION TECHNOLOGY Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |