Revisiting the effects of the Spectre and Meltdown patches using the top-down microarchitectural method and purchasing power parity theory
Software patches are made available to fix security vulnerabilities, enhance performance, and usability. Previous works focused on measuring the performance effect of patches on benchmark runtimes. In this study, we used the Top-Down microarchitecture analysis method to understand how pipeline bottl...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2021-10-01
|
| Series: | BenchCouncil Transactions on Benchmarks, Standards and Evaluations |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772485921000119 |
| _version_ | 1811292634703986688 |
|---|---|
| author | Yectli A. Huerta David J. Lilja |
| author_facet | Yectli A. Huerta David J. Lilja |
| author_sort | Yectli A. Huerta |
| collection | DOAJ |
| description | Software patches are made available to fix security vulnerabilities, enhance performance, and usability. Previous works focused on measuring the performance effect of patches on benchmark runtimes. In this study, we used the Top-Down microarchitecture analysis method to understand how pipeline bottlenecks were affected by the application of the Spectre and Meltdown security patches. Bottleneck analysis makes it possible to better understand how different hardware resources are being utilized, highlighting portions of the pipeline where possible improvements could be achieved. We complement the Top-Down analysis technique with the use a normalization technique from the field of economics, purchasing power parity (PPP), to better understand the relative difference between patched and unpatched runs. In this study, we showed that security patches had an effect that was reflected on the corresponding Top-Down metrics. We showed that recent compilers are not as negatively affected as previously reported. Out of the 14 benchmarks that make up the SPEC OMP2012 suite, three had noticeable slowdowns when the patches were applied. We also found that Top-Down metrics had large relative differences when the security patches were applied, differences that standard techniques based in absolute, non-normalized, metrics failed to highlight. |
| first_indexed | 2024-04-13T04:48:19Z |
| format | Article |
| id | doaj.art-e7d65d754f5c41b2916afb9e06077423 |
| institution | Directory Open Access Journal |
| issn | 2772-4859 |
| language | English |
| last_indexed | 2024-04-13T04:48:19Z |
| publishDate | 2021-10-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | BenchCouncil Transactions on Benchmarks, Standards and Evaluations |
| spelling | doaj.art-e7d65d754f5c41b2916afb9e060774232022-12-22T03:01:47ZengKeAi Communications Co. Ltd.BenchCouncil Transactions on Benchmarks, Standards and Evaluations2772-48592021-10-0111100011Revisiting the effects of the Spectre and Meltdown patches using the top-down microarchitectural method and purchasing power parity theoryYectli A. Huerta0David J. Lilja1Scientific Computation; Minnesota Supercomputing Institute; University of Minnesota, USA; Corresponding author at: Scientific Computation .Scientific Computation; Electrical and Computer Engineering Department; University of Minnesota, USASoftware patches are made available to fix security vulnerabilities, enhance performance, and usability. Previous works focused on measuring the performance effect of patches on benchmark runtimes. In this study, we used the Top-Down microarchitecture analysis method to understand how pipeline bottlenecks were affected by the application of the Spectre and Meltdown security patches. Bottleneck analysis makes it possible to better understand how different hardware resources are being utilized, highlighting portions of the pipeline where possible improvements could be achieved. We complement the Top-Down analysis technique with the use a normalization technique from the field of economics, purchasing power parity (PPP), to better understand the relative difference between patched and unpatched runs. In this study, we showed that security patches had an effect that was reflected on the corresponding Top-Down metrics. We showed that recent compilers are not as negatively affected as previously reported. Out of the 14 benchmarks that make up the SPEC OMP2012 suite, three had noticeable slowdowns when the patches were applied. We also found that Top-Down metrics had large relative differences when the security patches were applied, differences that standard techniques based in absolute, non-normalized, metrics failed to highlight.http://www.sciencedirect.com/science/article/pii/S2772485921000119Bottleneck analysisSystem characterizationPerformance measurement |
| spellingShingle | Yectli A. Huerta David J. Lilja Revisiting the effects of the Spectre and Meltdown patches using the top-down microarchitectural method and purchasing power parity theory BenchCouncil Transactions on Benchmarks, Standards and Evaluations Bottleneck analysis System characterization Performance measurement |
| title | Revisiting the effects of the Spectre and Meltdown patches using the top-down microarchitectural method and purchasing power parity theory |
| title_full | Revisiting the effects of the Spectre and Meltdown patches using the top-down microarchitectural method and purchasing power parity theory |
| title_fullStr | Revisiting the effects of the Spectre and Meltdown patches using the top-down microarchitectural method and purchasing power parity theory |
| title_full_unstemmed | Revisiting the effects of the Spectre and Meltdown patches using the top-down microarchitectural method and purchasing power parity theory |
| title_short | Revisiting the effects of the Spectre and Meltdown patches using the top-down microarchitectural method and purchasing power parity theory |
| title_sort | revisiting the effects of the spectre and meltdown patches using the top down microarchitectural method and purchasing power parity theory |
| topic | Bottleneck analysis System characterization Performance measurement |
| url | http://www.sciencedirect.com/science/article/pii/S2772485921000119 |
| work_keys_str_mv | AT yectliahuerta revisitingtheeffectsofthespectreandmeltdownpatchesusingthetopdownmicroarchitecturalmethodandpurchasingpowerparitytheory AT davidjlilja revisitingtheeffectsofthespectreandmeltdownpatchesusingthetopdownmicroarchitecturalmethodandpurchasingpowerparitytheory |