coarse grained transactions
play

Coarse-Grained Transactions Eric Koskinen University of Cambridge - PowerPoint PPT Presentation

Mar 16, 2024 •49 likes •979 views

Coarse-Grained Transactions Eric Koskinen University of Cambridge 20 January 2010 Joint work with Matthew Parkinson, Maurice Herlihy Wednesday, 20 January 2010 Abstract Data Types global SkipList set; atomic { atomic { set.Add(3); if

  1. Coarse-Grained Transactions Eric Koskinen University of Cambridge 20 January 2010 Joint work with Matthew Parkinson, Maurice Herlihy Wednesday, 20 January 2010

  2. Abstract Data Types global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } Wednesday, 20 January 2010

  3. Abstract Data Types ADT Operations global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } Wednesday, 20 January 2010

  4. Abstract Data Types ADT Operations global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } T1 (Add3) (Rm5) T2 (Has6) (Rm7) Wednesday, 20 January 2010

  5. Abstract Data Types ADT Operations global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) Wednesday, 20 January 2010

  6. Abstract Data Types ADT Operations global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } Abort! T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) Wednesday, 20 January 2010

  7. Abstract Data Types ADT Operations global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } Abort! T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  8. Abstract Data Types ADT Operations global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } Abort! T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Abort! Wednesday, 20 January 2010

  9. Abstract Data Types • Low-level synchronization (r/w conflicts) impairs performance • So how can operations be synchronized? Wednesday, 20 January 2010

  10. what if skiplist is linearizable? Wednesday, 20 January 2010

  11. Abstract Data Types global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  12. Abstract Data Types global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  13. Abstract Data Types global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  14. Abstract Data Types global SkipList set; atomic { atomic { set.Add(3); if set.Has(6) then set.Rm(5) set.Rm(7) } } T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Equiv. Serial History T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  15. Abstract Data Types • Abstract data types ... Wednesday, 20 January 2010

  16. Abstract Data Types • Abstract data types ... • ... require abstract synchronization: Wednesday, 20 January 2010

  17. Abstract Data Types • Abstract data types ... • ... require abstract synchronization: • ... based on method “movement” Wednesday, 20 January 2010

  18. Abstract Data Types • Abstract data types ... • ... require abstract synchronization: • ... based on method “movement” • Left Movers, Right Movers, Both Movers Wednesday, 20 January 2010

  19. Abstract Data Types set.Rm(5) set.Rm(7) set.Rm(5) set.Has(6) T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  20. Abstract Data Types set.Rm(5) set.Rm(7) ⊳ set.Rm(5) set.Has(6) T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  21. Abstract Data Types set.Rm(5) set.Rm(7) ⊲ set.Rm(5) set.Has(6) T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  22. Abstract Data Types set.Rm(5) set.Rm(7) ⊲ ⊳ set.Rm(5) set.Has(6) T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  23. Abstract Data Types set.Rm(5) set.Rm(7) ⊲ ⊳ set.Rm(5) set.Has(6) ⊲ ⊳ T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  24. Abstract Data Types set.Rm(5) set.Rm(7) ⊲ ⊳ set.Rm(5) set.Has(6) ⊲ ⊳ set.*(x) set.*(y) ⊲ ⊳ T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  25. Abstract Data Types set.Rm(5) set.Rm(7) ⊲ ⊳ set.Rm(5) set.Has(6) ⊲ ⊳ if x ≠ y set.*(x) set.*(y) ⊲ ⊳ T1 (Add3) (Rm5) (cmt) T2 (Has6) (Rm7) (cmt) Wednesday, 20 January 2010

  26. Left-movers o.m ⊳ p.n iff Wednesday, 20 January 2010

  27. Left-movers o.m ⊳ p.n iff { σ ′′ | ∃ σ ′ .σ → σ ′ ∧ σ ′ p.n o.m − − − − → σ ′′ } ⊆ ∀ σ { σ ′′′ | ∃ σ ′ .σ → σ ′ ∧ σ ′ p.n o.m − − − − → σ ′′′ } Wednesday, 20 January 2010

  28. Left-movers o.m ⊳ p.n iff { σ ′′ | ∃ σ ′ .σ → σ ′ ∧ σ ′ p.n o.m − − − − → σ ′′ } ⊆ ∀ σ { σ ′′′ | ∃ σ ′ .σ → σ ′ ∧ σ ′ p.n o.m − − − − → σ ′′′ } Similar for Right-movers Wednesday, 20 January 2010

  29. Left-movers dec() inc() dec() 1 0 1 0 time Wednesday, 20 January 2010

  30. Left-movers inc() dec() dec() 1 0 1 11 0 2 1 0 time What Theory? Sept 2009 10 Wednesday, 20 January 2010

  31. Left-movers Valid sequence of calls (same return values) inc() dec() dec() 1 0 1 11 0 2 1 0 time What Theory? Sept 2009 11 Wednesday, 20 January 2010

  32. Left-movers inc() dec() dec() 1 0 1 11 0 2 1 0 time Same final state What Theory? Sept 2009 12 Wednesday, 20 January 2010

  33. Left-movers inc() dec() dec() 1 0 1 11 0 2 1 0 time Same final state inc() dec() What Theory? Sept 2009 12 Wednesday, 20 January 2010

  34. Left-movers inc() dec() dec() 1 0 1 11 0 2 1 0 time Same final state inc() dec() ⊳ What Theory? Sept 2009 12 Wednesday, 20 January 2010

  35. Left-movers dec() inc() dec() 1 0 1 0 time What Theory? Sept 2009 13 Wednesday, 20 January 2010

  36. Left-movers dec() inc() dec() -1 1 0 1 0 time What Theory? Sept 2009 14 Wednesday, 20 January 2010

  37. Left-movers dec() inc() dec() -1 1 0 1 0 time dec() is NOT a left mover w.r.t inc() What Theory? Sept 2009 14 Wednesday, 20 January 2010

  38. Right-movers time If and are adjacent, Ok to move later Wednesday, 20 January 2010

  39. Right-movers Both-movers time time If and are adjacent, If and are adjacent, Ok to move later Ok to swap Wednesday, 20 January 2010

  40. Syntax ::= c ; s | beg t ; s | skip s ::= c ; t | x := o.m ( a ); t | end t Wednesday, 20 January 2010

  41. Atomic Semantics C a = T, σ where T : list s Wednesday, 20 January 2010

  42. Atomic Semantics C a = T, σ where T : list s → A s ′ , σ ′ s, σ − → A T 1 :: s ′ :: T 2 , σ ′ T 1 :: s :: T 2 , σ − Wednesday, 20 January 2010

  43. Atomic Semantics C a = T, σ where T : list s → A s ′ , σ ′ s, σ − → A T 1 :: s ′ :: T 2 , σ ′ T 1 :: s :: T 2 , σ − Statements σ ′ ∈ � c � σ → A s, σ ′ c ; s, σ − t, σ ⇓ A σ ′ → A s, σ ′ beg t ; s, σ − Wednesday, 20 January 2010

  44. Atomic Semantics C a = T, σ where T : list s → A s ′ , σ ′ s, σ − → A T 1 :: s ′ :: T 2 , σ ′ T 1 :: s :: T 2 , σ − Statements Transactions σ ′′ ∈ � o.m ( a ) � σ t, σ ′′ ⇓ A σ ′ σ ′ ∈ � c � σ → A s, σ ′ o.m ( a ); t, σ ⇓ A σ ′ c ; s, σ − t, σ ⇓ A σ ′ end , σ ⇓ A σ → A s, σ ′ beg t ; s, σ − Wednesday, 20 January 2010

  45. Theorem. The atomic semantics Atomic Semantics produce serial histories. C a = T, σ where T : list s → A s ′ , σ ′ s, σ − → A T 1 :: s ′ :: T 2 , σ ′ T 1 :: s :: T 2 , σ − Statements Transactions σ ′′ ∈ � o.m ( a ) � σ t, σ ′′ ⇓ A σ ′ σ ′ ∈ � c � σ → A s, σ ′ o.m ( a ); t, σ ⇓ A σ ′ c ; s, σ − t, σ ⇓ A σ ′ end , σ ⇓ A σ → A s, σ ′ beg t ; s, σ − Wednesday, 20 January 2010

  46. Implementation Strategies Wednesday, 20 January 2010

  47. Implementation Strategies Pessimistic Optimistic undos undos undos T 1 T 2 T 3 T 1 T 2 T 3 add(2) rm(4) add(4) redos redos redos merge merge Boosting, Open Nested Txns, Lock Inf. RW STM, Intel, TL2, Burkhardt Wednesday, 20 January 2010

  48. Implementation Strategies Pessimistic Optimistic undos undos undos T 1 T 2 T 3 T 1 T 2 T 3 add(2) rm(4) add(4) Abort! redos redos redos merge merge Boosting, Open Nested Txns, Lock Inf. RW STM, Intel, TL2, Burkhardt Wednesday, 20 January 2010

  49. Implementation Strategies Pessimistic Optimistic C opt = T, σ sh , ℓ sh C p = T, σ T i : N ⊥ × s × list M T i : N ⊥ × s × σ × σ × ℓ τ Wednesday, 20 January 2010

  50. Implementation Strategies Pessimistic Optimistic C opt = T, σ sh , ℓ sh C p = T, σ T i : N ⊥ × s × list M T i : N ⊥ × s × σ × σ × ℓ τ transaction identifier code oustanding ops Wednesday, 20 January 2010

  51. Implementation Strategies Pessimistic Optimistic C opt = T, σ sh , ℓ sh C p = T, σ T i : N ⊥ × s × list M T i : N ⊥ × s × σ × σ × ℓ τ transaction identifier thread-local state previous state code replay log oustanding ops Wednesday, 20 January 2010

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Application of the Lattice Boltzmann method with moving boundaries in a coarse-grained suspension

Application of the Lattice Boltzmann method with moving boundaries in a coarse-grained suspension

Basics Moving particles Coarse-grained blood model Application of the Lattice Boltzmann method with moving boundaries in a coarse-grained suspension model for hemodynamics Florian Janoschek Jens Harting Department of Applied Physics,

725 views • 27 slides
MOLECULAR DYNAMICS STUDY OF LIPOSOMES WITH A NEW COARSE-GRAINED MOLECULAR MODEL Wataru SHINODA

MOLECULAR DYNAMICS STUDY OF LIPOSOMES WITH A NEW COARSE-GRAINED MOLECULAR MODEL Wataru SHINODA

MOLECULAR DYNAMICS STUDY OF LIPOSOMES WITH A NEW COARSE-GRAINED MOLECULAR MODEL Wataru SHINODA AIST 2010/08/26 MULTI-SCALE MODELING phenomenological modeling molecular modeling CONTENTS 1. COARSE-GRAINED MOLECULAR MODELING II. VESICLES

482 views • 21 slides
Predictability of Coarse-Grained Models of Atomistic Systems in the Presence of Uncertainty J.

Predictability of Coarse-Grained Models of Atomistic Systems in the Presence of Uncertainty J.

Predictability of Coarse-Grained Models of Atomistic Systems in the Presence of Uncertainty J. Tinsley Oden Institute for Computational Engineering and Sciences The University of Texas at Austin Belytschko Lecture Theoretical and Applied

1.29k views • 109 slides
A Practical Approach to Exploiting Coarse-Grained Pipeline Parallelism in C Programs William

A Practical Approach to Exploiting Coarse-Grained Pipeline Parallelism in C Programs William

A Practical Approach to Exploiting Coarse-Grained Pipeline Parallelism in C Programs William Thies, Vikram Chandrasekhar, Saman Amarasinghe Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology MICRO 40

603 views • 39 slides
Studying Protein Structure through Hydrogen Exchange and Coarse- grained Conformational Sampling

Studying Protein Structure through Hydrogen Exchange and Coarse- grained Conformational Sampling

Studying Protein Structure through Hydrogen Exchange and Coarse- grained Conformational Sampling Didier Devaurs Univ. Grenoble Alpes / Inria D. Antunes, J. Abella, M. Moll, L. Kavraki Rice University M. Papanastasiou, D. Ricklin, J. Lambris

483 views • 24 slides
Junfeng Fan ESAT/COSIC ECC implementation methods Multi-core systems Coarse-Grained

Junfeng Fan ESAT/COSIC ECC implementation methods Multi-core systems Coarse-Grained

Junfeng Fan ESAT/COSIC ECC implementation methods Multi-core systems Coarse-Grained Parallelism (CGP) Fine-Grained Parallelism (FGP) Fine-Grained Parallelism (FGP) Two Dimensional Parallelism (TDP) Results Conclusions Q

467 views • 20 slides
Coarse-grained models for PDEs with random coefficients C. Grigo and P.-S. Koutsourelakis

Coarse-grained models for PDEs with random coefficients C. Grigo and P.-S. Koutsourelakis

Coarse-grained models for PDEs with random coefficients C. Grigo and P.-S. Koutsourelakis Continuum Mechanics Group Department of Mechanical Engineering Technical University of Munich SIAM CSE Atlanta 1 Mar 2017 SIAM CSE 17 Mar 1 st ,

1.03k views • 66 slides
Refinements in Data Manipulation Method for Coarse Grained Reconfigurable Architectures Takuya

Refinements in Data Manipulation Method for Coarse Grained Reconfigurable Architectures Takuya

Refinements in Data Manipulation Method for Coarse Grained Reconfigurable Architectures Takuya Kojima and Hideharu Amano Keio University, Japan 14th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC 2019)

501 views • 28 slides
Exploiting Coarse-Grained Task, Data, and Pipeline Parallelism in Stream Programs Michael

Exploiting Coarse-Grained Task, Data, and Pipeline Parallelism in Stream Programs Michael

Exploiting Coarse-Grained Task, Data, and Pipeline Parallelism in Stream Programs Michael Gordon, William Thies, and Saman Amarasinghe Massachusetts Institute of Technology ASPLOS October 2006 San Jose, CA http://cag.csail.mit.edu/streamit

420 views • 39 slides
Coarse-Grained Parallelism Variable Privatization, Loop Alignment, Loop Fusion, Loop

Coarse-Grained Parallelism Variable Privatization, Loop Alignment, Loop Fusion, Loop

Coarse-Grained Parallelism Variable Privatization, Loop Alignment, Loop Fusion, Loop interchange and skewing, Loop Strip-mining cs6363 1 Introduction Our previous loop transformations target vector and superscalar architectures Now

538 views • 32 slides
T ANGRAM : Optimized Coarse-Grained Dataflow for Scalable NN Accelerators Mingyu Gao, Xuan Yang,

T ANGRAM : Optimized Coarse-Grained Dataflow for Scalable NN Accelerators Mingyu Gao, Xuan Yang,

T ANGRAM : Optimized Coarse-Grained Dataflow for Scalable NN Accelerators Mingyu Gao, Xuan Yang, Jing Pu, Mark Horowitz, Christos Kozyrakis Stanford University Tsinghua University Google ASPLOS April 2019 Neural Networks (NNs) q

577 views • 19 slides
Development of coarse-grained models for nucleic acids (and aromatic systems) Samuela Pasquali

Development of coarse-grained models for nucleic acids (and aromatic systems) Samuela Pasquali

Development of coarse-grained models for nucleic acids (and aromatic systems) Samuela Pasquali & Elisa Frezza Laboratoire de Cristallographie et RMN Biologiques Facult de Pharmacie, Universit Paris Descartes Nucleic acids complex

486 views • 22 slides
Systematic Coarse-Grained Models for Molecular Systems Using Entropy Vagelis Harmandaris 1,2 *,

Systematic Coarse-Grained Models for Molecular Systems Using Entropy Vagelis Harmandaris 1,2 *,

Systematic Coarse-Grained Models for Molecular Systems Using Entropy Vagelis Harmandaris 1,2 *, Evangelia Kalligiannaki 2 *, and Markos Katsoulakis 3 1 Department of Mathematics and Applied Mathematics, University of Crete; 2 Institute of Applied

323 views • 28 slides
Mechanized Verification of Fine-grained Concurrent Programs Ilya Sergey Aleks Nanevski

Mechanized Verification of Fine-grained Concurrent Programs Ilya Sergey Aleks Nanevski

Mechanized Verification of Fine-grained Concurrent Programs Ilya Sergey Aleks Nanevski Anindya Banerjee PLDI 2015 Terminology Coarse-grained Concurrency synchronisation between threads via locks ; Fine-grained

973 views • 72 slides
Coarse-grained Force Field Development of Room Temperature Ionic Liquids Presenter: Alireza

Coarse-grained Force Field Development of Room Temperature Ionic Liquids Presenter: Alireza

Coarse-grained Force Field Development of Room Temperature Ionic Liquids Presenter: Alireza Moradzadeh, PI: Narayana R. Aluru University of Illinois at Urbana-Champaign Introduction and Background Room Temperature Ionic Liquid (RTIL) are a

155 views • 14 slides
Allocator Basics Pages too coarse-grained for allocating individual objects. Instead:

Allocator Basics Pages too coarse-grained for allocating individual objects. Instead:

Allocator Basics Pages too coarse-grained for allocating individual objects. Instead: flexible-sized, word-aligned blocks. Dynamic Memory Allocation in the Heap Free word (malloc and free) Allocated word Allocated block Free block (4 words)

96 views • 6 slides
a = b c . . . C ONTENT G ENERAL R ECURSION Intro & motivation, getting started with

a = b c . . . C ONTENT G ENERAL R ECURSION Intro & motivation, getting started with

L AST W EEK Constructive Logic & Curry-Howard-Isomorphism The Coq System NICTA Advanced Course The HOL4 system Before that: datatypes, recursion, induction Theorem Proving Slide 1 Slide 3 Principles, Techniques, Applications

898 views • 7 slides
LArTPC Testbeam: CAPTAIN and LArIAT Jason St. John, University of Cincinnati On behalf of the

LArTPC Testbeam: CAPTAIN and LArIAT Jason St. John, University of Cincinnati On behalf of the

LArTPC Testbeam: CAPTAIN and LArIAT Jason St. John, University of Cincinnati On behalf of the LArIAT Collaboration and for the CAPTAIN Collaboration NuFact 2015, Rio de Janeiro Outline miniCAPTAIN (neutrons) & LArIAT (charged species) -

677 views • 49 slides
Population pressures Outline Basic data 1. Malthusian theories 2. Demographic transitions 3.

Population pressures Outline Basic data 1. Malthusian theories 2. Demographic transitions 3.

Lecture notes on population and fertility Rajeev Dehejia Population pressures Outline Basic data 1. Malthusian theories 2. Demographic transitions 3. Demographic gifts and burdens 4. 11:09 am, Monday 10 April 2017 Population: %

789 views • 68 slides
Nesting Transactions: Why and What do we need? J. Eliot B. Moss University of Massachusetts

Nesting Transactions: Why and What do we need? J. Eliot B. Moss University of Massachusetts

Nesting Transactions: Why and What do we need? J. Eliot B. Moss University of Massachusetts moss@cs.umass.edu Reporting joint work with Tony Hosking (Purdue) U NIVERSITY OF M ASSACHUSETTS , A MHERST Department of Computer Science 1 U

640 views • 46 slides
20 years of isogeny-based cryptography Luca De Feo feat. Jean Kieffer, Benjamin Smith

20 years of isogeny-based cryptography Luca De Feo feat. Jean Kieffer, Benjamin Smith

20 years of isogeny-based cryptography Luca De Feo feat. Jean Kieffer, Benjamin Smith Universit Paris Saclay, UVSQ & Inria November 14, 2017, Elliptic Curve Cryptography, Nijmegen Slides online at http://defeo.lu/docet/ Overview

1.07k views • 84 slides
Vulnerability Analysis (IV): Program Verifjcation Slide credit: Vijay Dawn Song DSilva

Vulnerability Analysis (IV): Program Verifjcation Slide credit: Vijay Dawn Song DSilva

Computer Security Course. Dawn Computer Security Course. Dawn Song Song Vulnerability Analysis (IV): Program Verifjcation Slide credit: Vijay Dawn Song DSilva Program Verifjcation Dawn Song Program Verifjcation How to prove a

768 views • 60 slides
BOMB: OUR ROLE AS EDUCATORS Ken Shain November 16, 2019 PRESENTOR Ken enneth eth S. Sha hain

BOMB: OUR ROLE AS EDUCATORS Ken Shain November 16, 2019 PRESENTOR Ken enneth eth S. Sha hain

DEFUSING THE RACE BOMB: OUR ROLE AS EDUCATORS Ken Shain November 16, 2019 PRESENTOR Ken enneth eth S. Sha hain Teacher & PD Facilitator, Minneapolis School District Teacher of the Year Nominee, 2017 MFT Local 59, Executive

946 views • 58 slides
The Memory-Tightness of Authenticated Encryption Stefano Tessaro Ashrujit Ghoshal Joseph Jaeger

The Memory-Tightness of Authenticated Encryption Stefano Tessaro Ashrujit Ghoshal Joseph Jaeger

The Memory-Tightness of Authenticated Encryption Stefano Tessaro Ashrujit Ghoshal Joseph Jaeger University of Washington CRYPTO 2020 Concrete security theorems: resources 1 0 resources Traditionally: time

402 views • 29 slides

More recommend