The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors:
Abstract: "In a shared memory multiprocessor with caches, executing tasks develop 'affinity' to processors by filling their caches with data and instructions during their computation. A policy that schedules processors without considering this affinity may waste processing power by ca...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Seattle, Wash.
1991
|
| Series: | University of Washington <Seattle, Wash.> / Department of Computer Science: Technical report
91,3,3 |
| Subjects: | |
| Summary: | Abstract: "In a shared memory multiprocessor with caches, executing tasks develop 'affinity' to processors by filling their caches with data and instructions during their computation. A policy that schedules processors without considering this affinity may waste processing power by causing excessive amounts of cache refilling. Our work focuses on quantifying the effect of processor reallocation on the performance of parallel applications multiprogrammed on a shared memory multiprocessor, and on evaluating how the magnitude of this cost affects the appropriate choice of processor allocation policy. We first identify the components of application response time, including processor reallocation costs Next, we measure the impact of processor reallocation on the cache behavior of each of several parallel applications executing on a Sequent Symmetry multiprocessor. We also measure the performance of these applications under a number of alternative processor allocation policies. These experiments lead us to conclude that on current machines processor affinity has only a very weak influence on the choice of scheduling discipline, and that the benefits of frequent processor reallocation outweigh the penalties imposed by such reallocation. Finally, we use this experimental data to parameterize a simple analytic model, allowing us to evaluate the effect of processor affinity on future machines, those containing faster processors and larger caches. |
| Physical Description: | 18 S. |
Staff View
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV008992809 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 940206s1991 |||| 00||| eng d | ||
| 035 | |a (OCoLC)27050656 | ||
| 035 | |a (DE-599)BVBBV008992809 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-29T | ||
| 100 | 1 | |a Vaswani, Raj |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors |c Raj Vaswani and John Zahorjan |
| 264 | 1 | |a Seattle, Wash. |c 1991 | |
| 300 | |a 18 S. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a University of Washington <Seattle, Wash.> / Department of Computer Science: Technical report |v 91,3,3 | |
| 520 | 3 | |a Abstract: "In a shared memory multiprocessor with caches, executing tasks develop 'affinity' to processors by filling their caches with data and instructions during their computation. A policy that schedules processors without considering this affinity may waste processing power by causing excessive amounts of cache refilling. Our work focuses on quantifying the effect of processor reallocation on the performance of parallel applications multiprogrammed on a shared memory multiprocessor, and on evaluating how the magnitude of this cost affects the appropriate choice of processor allocation policy. We first identify the components of application response time, including processor reallocation costs | |
| 520 | 3 | |a Next, we measure the impact of processor reallocation on the cache behavior of each of several parallel applications executing on a Sequent Symmetry multiprocessor. We also measure the performance of these applications under a number of alternative processor allocation policies. These experiments lead us to conclude that on current machines processor affinity has only a very weak influence on the choice of scheduling discipline, and that the benefits of frequent processor reallocation outweigh the penalties imposed by such reallocation. Finally, we use this experimental data to parameterize a simple analytic model, allowing us to evaluate the effect of processor affinity on future machines, those containing faster processors and larger caches. | |
| 650 | 4 | |a Cache memory | |
| 650 | 4 | |a Multiprocessors | |
| 700 | 1 | |a Zahorjan, John |e Verfasser |4 aut | |
| 810 | 2 | |a Department of Computer Science: Technical report |t University of Washington <Seattle, Wash.> |v 91,3,3 |w (DE-604)BV008930431 |9 91,3,3 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-005941727 | ||
Record in the Search Index
| _version_ | 1804123335330627584 |
|---|---|
| any_adam_object | |
| author | Vaswani, Raj Zahorjan, John |
| author_facet | Vaswani, Raj Zahorjan, John |
| author_role | aut aut |
| author_sort | Vaswani, Raj |
| author_variant | r v rv j z jz |
| building | Verbundindex |
| bvnumber | BV008992809 |
| ctrlnum | (OCoLC)27050656 (DE-599)BVBBV008992809 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02587nam a2200325 cb4500</leader><controlfield tag="001">BV008992809</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">940206s1991 |||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)27050656</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV008992809</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-29T</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Vaswani, Raj</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors</subfield><subfield code="c">Raj Vaswani and John Zahorjan</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Seattle, Wash.</subfield><subfield code="c">1991</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">18 S.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">University of Washington <Seattle, Wash.> / Department of Computer Science: Technical report</subfield><subfield code="v">91,3,3</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "In a shared memory multiprocessor with caches, executing tasks develop 'affinity' to processors by filling their caches with data and instructions during their computation. A policy that schedules processors without considering this affinity may waste processing power by causing excessive amounts of cache refilling. Our work focuses on quantifying the effect of processor reallocation on the performance of parallel applications multiprogrammed on a shared memory multiprocessor, and on evaluating how the magnitude of this cost affects the appropriate choice of processor allocation policy. We first identify the components of application response time, including processor reallocation costs</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Next, we measure the impact of processor reallocation on the cache behavior of each of several parallel applications executing on a Sequent Symmetry multiprocessor. We also measure the performance of these applications under a number of alternative processor allocation policies. These experiments lead us to conclude that on current machines processor affinity has only a very weak influence on the choice of scheduling discipline, and that the benefits of frequent processor reallocation outweigh the penalties imposed by such reallocation. Finally, we use this experimental data to parameterize a simple analytic model, allowing us to evaluate the effect of processor affinity on future machines, those containing faster processors and larger caches.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cache memory</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multiprocessors</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zahorjan, John</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Department of Computer Science: Technical report</subfield><subfield code="t">University of Washington <Seattle, Wash.></subfield><subfield code="v">91,3,3</subfield><subfield code="w">(DE-604)BV008930431</subfield><subfield code="9">91,3,3</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-005941727</subfield></datafield></record></collection> |
| id | DE-604.BV008992809 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T17:28:08Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-005941727 |
| oclc_num | 27050656 |
| open_access_boolean | |
| owner | DE-29T |
| owner_facet | DE-29T |
| physical | 18 S. |
| publishDate | 1991 |
| publishDateSearch | 1991 |
| publishDateSort | 1991 |
| record_format | marc |
| series2 | University of Washington <Seattle, Wash.> / Department of Computer Science: Technical report |
| spelling | Vaswani, Raj Verfasser aut The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors Raj Vaswani and John Zahorjan Seattle, Wash. 1991 18 S. txt rdacontent n rdamedia nc rdacarrier University of Washington <Seattle, Wash.> / Department of Computer Science: Technical report 91,3,3 Abstract: "In a shared memory multiprocessor with caches, executing tasks develop 'affinity' to processors by filling their caches with data and instructions during their computation. A policy that schedules processors without considering this affinity may waste processing power by causing excessive amounts of cache refilling. Our work focuses on quantifying the effect of processor reallocation on the performance of parallel applications multiprogrammed on a shared memory multiprocessor, and on evaluating how the magnitude of this cost affects the appropriate choice of processor allocation policy. We first identify the components of application response time, including processor reallocation costs Next, we measure the impact of processor reallocation on the cache behavior of each of several parallel applications executing on a Sequent Symmetry multiprocessor. We also measure the performance of these applications under a number of alternative processor allocation policies. These experiments lead us to conclude that on current machines processor affinity has only a very weak influence on the choice of scheduling discipline, and that the benefits of frequent processor reallocation outweigh the penalties imposed by such reallocation. Finally, we use this experimental data to parameterize a simple analytic model, allowing us to evaluate the effect of processor affinity on future machines, those containing faster processors and larger caches. Cache memory Multiprocessors Zahorjan, John Verfasser aut Department of Computer Science: Technical report University of Washington <Seattle, Wash.> 91,3,3 (DE-604)BV008930431 91,3,3 |
| spellingShingle | Vaswani, Raj Zahorjan, John The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors Cache memory Multiprocessors |
| title | The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors |
| title_auth | The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors |
| title_exact_search | The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors |
| title_full | The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors Raj Vaswani and John Zahorjan |
| title_fullStr | The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors Raj Vaswani and John Zahorjan |
| title_full_unstemmed | The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors Raj Vaswani and John Zahorjan |
| title_short | The implications of cache affinity on processor scheduling for multiprogrammed, shared memory multiprocessors |
| title_sort | the implications of cache affinity on processor scheduling for multiprogrammed shared memory multiprocessors |
| topic | Cache memory Multiprocessors |
| topic_facet | Cache memory Multiprocessors |
| volume_link | (DE-604)BV008930431 |
| work_keys_str_mv | AT vaswaniraj theimplicationsofcacheaffinityonprocessorschedulingformultiprogrammedsharedmemorymultiprocessors AT zahorjanjohn theimplicationsofcacheaffinityonprocessorschedulingformultiprogrammedsharedmemorymultiprocessors |