System and method for generating a probability distribution of computer performance ratios
A system and method for generating a probability distribution indicating the probability of a range of performance ratios between computer systems. Benchmark and/or other testing results are obtained for both computer systems. For each test, a ratio of one system's performance to the other is calculated. The ratios and/or testing results may be weighted. From the performance ratios, a histogram is produced to indicate the probabilities of achieving the various ratios. Based on the distribution of probabilities, a particular performance ratio can be predicted with a corresponding level of confidence, and used for capacity planning or configuring a computing environment.
1. A method of generating a distribution of performance ratios between multiple computer systems, the method comprising:
in a system that includes at least one microprocessor, application-specific integrated circuit, or programmable logic device:
for each computer system, obtaining results from multiple tests configured to test performance of the computer systems;
for each of the multiple tests, calculating a ratio between the computer systems' test results, wherein calculating the ratio involves dividing a result or a combination of results from a first computer system from the multiple computer systems for a given test by a result or a combination of results from a second computer system from the multiple computer systems for the given test;
weighting one or more of the calculated ratios relative to an expected use of the computer systems by a user;
generating a histogram from the calculated ratios to indicate a distribution of the calculated ratios; and
from the histogram, predicting a probability of an expected level of performance of one of the computer systems compared to another of the computer systems.
2. The method of claim 1 , further comprising:
weighting one or more of the test results.
3. The method of claim 2 , wherein said weighting comprises:
weighting a result of a test relatively closely related to a planned use of the computer systems.
4. The method of claim 1 , wherein the multiple tests include one or more benchmarks.
5. The method of claim 1 , further comprising:
applying a Monte Carlo algorithm to manipulate the distribution of calculated ratios.
6. A computer readable storage medium storing instructions that, when executed by a computer, cause the computer to perform a method of generating a distribution of performance ratios between multiple computer systems, the method comprising:
in a system that includes at least one microprocessor, application-specific integrated circuit, or programmable logic device;
for each computer system, obtaining results from multiple tests configured to test performance of the computer systems;
for each of the multiple tests, calculating a ratio between the computer systems' test results; wherein calculating the ratio involves dividing a result or a combination of results from a first computer system from the multiple computer systems for a given test by a result or a combination of results from a second computer system from the multiple computer systems for the given test;
weighting one or more of the calculated ratios relative to an expected use of the computer systems by a user;
generating a histogram from the calculated ratios to indicate a distribution of the calculated ratios; and
from the histogram, predicting a probability of an expected level of performance of one of the computer systems compared to another of the computer systems.
7. An apparatus for generating a distribution of performance ratios between computer systems, the apparatus comprising:
a first set of results of performance tests executed on a first computer system;
a second set of results of the performance tests executed on a second computer system;
a processor configured to:
calculate, for each of the performance tests, a ratio between the computer systems' set of test results, wherein calculating the ratio involves dividing a result or combination of results from the first computer system for a given test by a result or combination of results from the second computer system for the given test;
weight one or more of the calculated ratios relative to an expected use of the computer systems by a user; and
generate a histogram from the calculated ratios to indicate a distribution of the calculated ratios; and an output device configured to output a probability of achieving an expected level of performance of the second computer system compared to the first computer system.
8. The apparatus of claim 7 , wherein the processor is further configured to weight one or more of the calculated ratios.
9. The apparatus of claim 7 , wherein the processor is further configured to weight one or more of the test results.
10. The apparatus of claim 7 , wherein the processor is further configured to manipulate the distribution of calculated ratios using a Monte Carlo algorithm.
11. The apparatus of claim 7 , wherein the performance tests include one or more benchmarks.