DownloadNote - The PPT/PDF document "Drinking from Both" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Presentations text content in Drinking from Both
Slide1
Drinking from Both Glasses:Combining Pessimistic andOptimistic Tracking of Cross-Thread Dependences
GoalOptimistic tracking for most non-conflicting accessesPessimistic tracking for most conflicting accesses
31
Slide32
Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
32
Slide33
Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
33
Hybrid State Model
Adaptive Policy
Slide34
Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
34
Hybrid State Model
Adaptive Policy
Challenging!
Slide35
Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
35
Hybrid State Model
Deferred Unlocking
Adaptive Policy
Slide36
Pessimistic-Optimistic Mismatch
36
safe point
read check
…
change state
wr
o.f
write check
rd o.f
Pessimistic Tracking
Optimistic Tracking
…
Lock
o.state
rd
/wr o.f
Unlock o.state
…
Slide37
Pessimistic-Optimistic Mismatch (#1)
37
safe point
read check
…
change state
wr
o.f
write check
rd o.f
…
Lock
o.state
rd/wr o.f
Unlock o.state
…
Pessimistic Tracking
Optimistic Tracking
No unlock!
Slide38
Pessimistic-Optimistic Mismatch (#1)
38
safe point
read check
…
change state
wr
o.f
write check
rd o.f
…
Lock
o.state
rd/wr o.f
Unlock o.state
…
Pessimistic Tracking
Optimistic Tracking
No unlock!
Conditional unlock?
Slide39
Pessimistic-Optimistic Mismatch (#2)
39
safe point
read check
…
change state
wr
o.f
write check
rd o.f
Pessimistic Tracking
Optimistic Tracking
…
Lock
o.state
rd
/
wr
o.f
Unlock o.state
…
Atomic
Atomic
Slide40
Pessimistic-Optimistic Mismatch (#2)
40
safe point
read check
…
change state
wr
o.f
write check
rd o.f
Pessimistic Tracking
Optimistic Tracking
…
Lock
o.state
rd
/
wr
o.f
Unlock o.state
…
Atomic
Atomic
Atomicity granularity may
affect specific analysis
Slide41
Pessimistic-Optimistic Mismatch (#2)
41
safe point
read check
…
change state
wr
o.f
write check
rd o.f
Pessimistic Tracking
Optimistic Tracking
…
Lock
o.state
rd
/
wr
o.f
Unlock o.state
…
Atomic
Atomic
Conditional unlock
Atomicity granularity may
affect specific analysis
Slide42
Key Insights
Coarsening atomicity granularity for pessimistic tracking
42
Slide43
Key Insights
Coarsening atomicity granularity for pessimistic trackingProgram synchronization may hint at cross-thread dependences
43
Slide44
Addressing Pessimistic-Optimistic Mismatch
Defer unlocking of pessimistic stateTill program synchronization release operation (PSRO)
44
Slide45
Addressing Pessimistic-Optimistic Mismatch
Defer unlocking of pessimistic stateTill program synchronization release operation (PSRO)Reader-writer locking
45
Slide46
Addressing Pessimistic-Optimistic Mismatch
Defer unlocking of pessimistic stateTill program synchronization release operation (PSRO)Reader-writer lockingFall back to coordination on contention when locking a state
46
Slide47
Deferred Unlocking Example 1
synchronized (m) { …}
47
Unlock all states
Lock
o.state
wr o.f
synchronized (m) { …
Lock
o.state
rd
o.f
Slide48
Deferred Unlocking Example 2
synchronized (m) { … …}
48
Unlock all states
Lock
o.state
wr o.f
Lock o.state
rd o.f
safe point
Slide49
Deferred Unlocking Example 2
synchronized (m) { …}
49
Unlock all states
Lock
o.state
wr o.f
Lock o.state
rd o.f
safe point
Contention => object-level data race
Slide50
Hybrid State Model
50
Slide51
Hybrid State Model
51
Slide52
Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
52
Hybrid State Model
Deferred Unlocking
Adaptive Policy
Slide53
Adaptive Policy
Decide when to transition between pessimistic and optimistic states
53
Slide54
Adaptive Policy
Decide when to transition between pessimistic and optimistic statesCost—benefit model
54
Slide55
Adaptive Policy
Decide when to transition between pessimistic and optimistic statesCost—benefit modelBoil down to counting state transitions
55
Slide56
Adaptive Policy
Decide when to transition between pessimistic and optimistic statesCost—benefit modelBoil down to counting state transitionsOnline profilingPer-objectSimple yet effective
56
Slide57
Application of Hybrid Tracking
Two dynamic analysesHybrid dependence recorder and replayer (detect)Hybrid region serializability (RS) enforcer (control)
57
Slide58
Application of Hybrid Tracking
Two dynamic analysesHybrid dependence recorder and replayer (detect)Hybrid region serializability (RS) enforcer (control)Deferred unlocking helps overcome key challenges!
58
Slide59
Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
59
Slide60
Implementation
Jikes RVM 3.1.3
60
Slide61
Implementation
Jikes RVM 3.1.3Pessimistic tracking, optimistic tracking[Octet, Bond et al. OOPSLA’13]Optimistic recorder and replayer[Replay, Bond et al. PPPJ’15]Optimistic RS enforcer[EnfoRSer, Sengupta et al, ASPLOS’15]
61
Slide62
Implementation
Jikes RVM 3.1.3Pessimistic tracking, optimistic tracking[Octet, Bond et al. OOPSLA’13]Optimistic recorder and replayer[Replay, Bond et al. PPPJ’15]Optimistic RS enforcer[EnfoRSer, Sengupta et al, ASPLOS’15]Hybrid tracking, hybrid recorder and replayer, hybrid RS enforcerpublicly available
62
Slide63
Performance of Tracking
63
22%
Slide64
Performance of Tracking
64
Slide65
Performance of Tracking
65
Most programs are low-conflict
22%
Slide66
Performance of
Recorders and RS enforcers
66
Recorders
RS enforcers
Slide67
Additional Materials
67
Slide68
Related work
Analyses that use pessimistic tracking[FastTrack, Flanagan & Freund, PLDI’09][Velodrome, Flanagan et al., PLDI’08][Chimera, Lee et al., PLDI’12][Lightweight Transactions, Harris & Fraser, OOPSLA’03][DMP, Devietti et al., ASPLOS’09]Analyses that use optimistic tracking[Shasta, Scales et al. ASPLOS’96][Object Race Detection, von Praun & Gross, OOPSLA’01][DoubleChecker, Biswas et al. PLDI’14][LarkTM, Zhang et al, PPoPP’15]Adaptive Mechanisms[Adaptive Locks, Usui et al. PACT’09][Strong Atomicity TM, Abadi et al. PPoPP’09][Adaptive Lock Elision, Dice et al, SPAA’14][Concurrency Control, Ziv et al, PLDI’15]
68
Slide69
Contributions
Hybrid tracking combines pessimistic tracking and optimistic tracking effectively and efficientlyHybrid tracking achieves better overall performanceNever significantly degrades performanceSometimes improves performance substantiallySuitable for workload of diverse communication patterns
69
Slide70
Differences From Locking in Programs
Locking in ProgramTracking DependencesVisible to program?YesNoScopeCode segmentAround each memory accessFrequencyRareCommon
70
Slide71
Adaptive Policy
Decide when to transition between pessimistic and optimistic statesCost—Benefit model
71
Slide72
Online Profiling
Counting conflicting/non-conflicting state transitions for each objectCoarse profiling for optimistic objectDetailed profiling for pessimistic objectPer-object vs aggregate profilingPer-object is effective for programs we evaluated
Download this presentation
DownloadNote - The PPT/PDF document "Drinking from Both" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Presentations text content in Drinking from Both
Drinking from Both Glasses:Combining Pessimistic andOptimistic Tracking of Cross-Thread Dependences
Man CaoMinjia ZhangAritra SenguptaMichael D. Bond
1
PPoPP
2016
Slide2Dynamic Analyses for Parallel Programs
Error detectionData Race DetectorAtomicity Violation DetectorProgramming modelTransactional MemoryEnforcement of Strong Memory ModelDebuggingRecord & ReplayDeterministic Execution
2
Slide3Dynamic Analyses for Parallel Programs
Error detectionData Race DetectorAtomicity Violation DetectorProgramming modelTransactional MemoryEnforcement of Strong Memory ModelDebuggingRecord & ReplayDeterministic Execution
3
Bad performance!
Slide4Dynamic Analyses for Parallel Programs
Error detectionData Race DetectorAtomicity Violation DetectorProgramming modelTransactional MemoryEnforcement of Strong Memory ModelDebuggingRecord & ReplayDeterministic Execution
4
Bad performance!
Difficulties?
Slide5Cross-thread dependences
5
o.f
= …
… = o.f
T1
T2
Slide6Cross-thread dependences
Tracking cross-thread dependences
6
o.f
= …
… = o.f
T1
T2
Slide7Cross-thread dependences
Tracking cross-thread dependencesDetectingControlling
7
o.f
= …
… = o.f
T1
T2
Slide8Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
8
Slide9Pessimistic Tracking
9
Per-object metadata:
o.state
last writer/reader
thread
Slide10Pessimistic Tracking
10
rd/wr o.f
Per-object metadata:
o.state
last writer/reader
thread
At each object access:
Slide11Pessimistic Tracking
11
Check o.state
rd/wr o.f
Analysis-specific work
Update
o.state
Per-object metadata:
o.state
last writer/reader
thread
At each object access:
Slide12Pessimistic Tracking
12
Check o.state
rd/wr o.f
Analysis-specific work
Update
o.state
Atomic
Per-object metadata:
o.state
last writer/reader
thread
At each object access:
Slide13Pessimistic Tracking
13
Check o.state
rd/wr o.f
Analysis-specific work
Update
o.state
Lock o.state
Unlock o.state
Per-object metadata:
o.state
last writer/reader
thread
At each object access:
Slide14Pessimistic Tracking
14
Check o.state
rd/wr o.f
Analysis-specific work
Update
o.state
Lock o.state
Unlock o.state
NOT program locks
Per-object metadata:
o.state
last writer/reader
thread
At each object access:
Slide15Pessimistic Tracking
15
…
Lock o.state
wr o.f
Unlock o.state
…
Lock
o.state
rd o.f
Unlock o.state
Slide16Pessimistic Tracking
16
…
Lock o.state
wr o.f
Unlock o.state
…
Lock
o.state
rd o.f
Unlock o.state
Synchronization and write metadata
Slide17Performance of Pessimistic Tracking Alone
17
340%
Slide18Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
18
Slide19Optimistic Tracking
19
Biased reader-writer lock for o.state
Slide20Optimistic Tracking
20
Biased reader-writer lock for o.stateAvoid synchronization for non-conflicting accesses
Slide21Optimistic Tracking
21
Biased reader-writer lock for o.stateAvoid synchronization for non-conflicting accessesHeavyweight coordination for conflicting accesses
Slide22Optimistic Tracking
22
T1
T2
wr o.f
write check
o.state
: WrExT1
Slide23Optimistic Tracking
23
T1
T2
wr o.f
write check
o.state
: WrExT1
o.state
: WrExT1
read check
Slide24Optimistic Tracking
24
T1
T2
read check
Analysis-specific work
wr
o.f
write check
o.state
: WrExT1
o.state: WrExT1
Request
Slide25Optimistic Tracking
25
T1
T2
safe point
read check
Analysis-specific work
change state
wr o.f
write check
rd
o.f
o.state
: WrExT1
o.state ← RdExT2
o.state: WrExT1
Request
Response
Slide26Performance of Optimistic Tracking Alone
26
Slide27Performance of Optimistic Tracking Alone
27
Slide28Cost of Different Tracking
PessimisticOptimisticSame stateCoordination150479200
28
In CPU cycles
Averaged across all programs
Slide2929
Optimistic
tracking
performs best if there are
few conflicting
accesses.
Slide3030
Pessimistic
tracking
is
cheaper
for
conflicting
accesses.
Slide31Drink from both glasses?
GoalOptimistic tracking for most non-conflicting accessesPessimistic tracking for most conflicting accesses
31
Slide32Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
32
Slide33Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
33
Hybrid State Model
Adaptive Policy
Slide34Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
34
Hybrid State Model
Adaptive Policy
Challenging!
Slide35Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
35
Hybrid State Model
Deferred Unlocking
Adaptive Policy
Slide36Pessimistic-Optimistic Mismatch
36
safe point
read check
…
change state
wr
o.f
write check
rd o.f
Pessimistic Tracking
Optimistic Tracking
…
Lock
o.state
rd
/wr o.f
Unlock o.state
…
Slide37Pessimistic-Optimistic Mismatch (#1)
37
safe point
read check
…
change state
wr
o.f
write check
rd o.f
…
Lock
o.state
rd/wr o.f
Unlock o.state
…
Pessimistic Tracking
Optimistic Tracking
No unlock!
Slide38Pessimistic-Optimistic Mismatch (#1)
38
safe point
read check
…
change state
wr
o.f
write check
rd o.f
…
Lock
o.state
rd/wr o.f
Unlock o.state
…
Pessimistic Tracking
Optimistic Tracking
No unlock!
Conditional unlock?
Slide39Pessimistic-Optimistic Mismatch (#2)
39
safe point
read check
…
change state
wr
o.f
write check
rd o.f
Pessimistic Tracking
Optimistic Tracking
…
Lock
o.state
rd
/
wr
o.f
Unlock o.state
…
Atomic
Atomic
Slide40Pessimistic-Optimistic Mismatch (#2)
40
safe point
read check
…
change state
wr
o.f
write check
rd o.f
Pessimistic Tracking
Optimistic Tracking
…
Lock
o.state
rd
/
wr
o.f
Unlock o.state
…
Atomic
Atomic
Atomicity granularity may
affect specific analysis
Slide41Pessimistic-Optimistic Mismatch (#2)
41
safe point
read check
…
change state
wr
o.f
write check
rd o.f
Pessimistic Tracking
Optimistic Tracking
…
Lock
o.state
rd
/
wr
o.f
Unlock o.state
…
Atomic
Atomic
Conditional unlock
Atomicity granularity may
affect specific analysis
Slide42Key Insights
Coarsening atomicity granularity for pessimistic tracking
42
Slide43Key Insights
Coarsening atomicity granularity for pessimistic trackingProgram synchronization may hint at cross-thread dependences
43
Slide44Addressing Pessimistic-Optimistic Mismatch
Defer unlocking of pessimistic stateTill program synchronization release operation (PSRO)
44
Slide45Addressing Pessimistic-Optimistic Mismatch
Defer unlocking of pessimistic stateTill program synchronization release operation (PSRO)Reader-writer locking
45
Slide46Addressing Pessimistic-Optimistic Mismatch
Defer unlocking of pessimistic stateTill program synchronization release operation (PSRO)Reader-writer lockingFall back to coordination on contention when locking a state
46
Slide47Deferred Unlocking Example 1
synchronized (m) { …}
47
Unlock all states
Lock
o.state
wr o.f
synchronized (m) { …
Lock
o.state
rd
o.f
Slide48Deferred Unlocking Example 2
synchronized (m) { … …}
48
Unlock all states
Lock
o.state
wr o.f
Lock o.state
rd o.f
safe point
Slide49Deferred Unlocking Example 2
synchronized (m) { …}
49
Unlock all states
Lock
o.state
wr o.f
Lock o.state
rd o.f
safe point
Contention => object-level data race
Slide50Hybrid State Model
50
Slide51Hybrid State Model
51
Slide52Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
52
Hybrid State Model
Deferred Unlocking
Adaptive Policy
Slide53Adaptive Policy
Decide when to transition between pessimistic and optimistic states
53
Slide54Adaptive Policy
Decide when to transition between pessimistic and optimistic statesCost—benefit model
54
Slide55Adaptive Policy
Decide when to transition between pessimistic and optimistic statesCost—benefit modelBoil down to counting state transitions
55
Slide56Adaptive Policy
Decide when to transition between pessimistic and optimistic statesCost—benefit modelBoil down to counting state transitionsOnline profilingPer-objectSimple yet effective
56
Slide57Application of Hybrid Tracking
Two dynamic analysesHybrid dependence recorder and replayer (detect)Hybrid region serializability (RS) enforcer (control)
57
Slide58Application of Hybrid Tracking
Two dynamic analysesHybrid dependence recorder and replayer (detect)Hybrid region serializability (RS) enforcer (control)Deferred unlocking helps overcome key challenges!
58
Slide59Outline
Dynamic Analyses and Cross-thread DependencesPessimistic TrackingOptimistic TrackingOur approachHybrid TrackingEvaluation
59
Slide60Implementation
Jikes RVM 3.1.3
60
Slide61Implementation
Jikes RVM 3.1.3Pessimistic tracking, optimistic tracking[Octet, Bond et al. OOPSLA’13]Optimistic recorder and replayer[Replay, Bond et al. PPPJ’15]Optimistic RS enforcer[EnfoRSer, Sengupta et al, ASPLOS’15]
61
Slide62Implementation
Jikes RVM 3.1.3Pessimistic tracking, optimistic tracking[Octet, Bond et al. OOPSLA’13]Optimistic recorder and replayer[Replay, Bond et al. PPPJ’15]Optimistic RS enforcer[EnfoRSer, Sengupta et al, ASPLOS’15]Hybrid tracking, hybrid recorder and replayer, hybrid RS enforcerpublicly available
62
Slide63Performance of Tracking
63
22%
Slide64Performance of Tracking
64
Slide65Performance of Tracking
65
Most programs are low-conflict
22%
Slide66Performance of
Recorders and RS enforcers
66
Recorders
RS enforcers
Slide67Additional Materials
67
Slide68Related work
Analyses that use pessimistic tracking[FastTrack, Flanagan & Freund, PLDI’09][Velodrome, Flanagan et al., PLDI’08][Chimera, Lee et al., PLDI’12][Lightweight Transactions, Harris & Fraser, OOPSLA’03][DMP, Devietti et al., ASPLOS’09]Analyses that use optimistic tracking[Shasta, Scales et al. ASPLOS’96][Object Race Detection, von Praun & Gross, OOPSLA’01][DoubleChecker, Biswas et al. PLDI’14][LarkTM, Zhang et al, PPoPP’15]Adaptive Mechanisms[Adaptive Locks, Usui et al. PACT’09][Strong Atomicity TM, Abadi et al. PPoPP’09][Adaptive Lock Elision, Dice et al, SPAA’14][Concurrency Control, Ziv et al, PLDI’15]
68
Slide69Contributions
Hybrid tracking combines pessimistic tracking and optimistic tracking effectively and efficientlyHybrid tracking achieves better overall performanceNever significantly degrades performanceSometimes improves performance substantiallySuitable for workload of diverse communication patterns
69
Slide70Differences From Locking in Programs
Locking in ProgramTracking DependencesVisible to program?YesNoScopeCode segmentAround each memory accessFrequencyRareCommon
70
Slide71Adaptive Policy
Decide when to transition between pessimistic and optimistic statesCost—Benefit model
71
Slide72Online Profiling
Counting conflicting/non-conflicting state transitions for each objectCoarse profiling for optimistic objectDetailed profiling for pessimistic objectPer-object vs aggregate profilingPer-object is effective for programs we evaluated
72
Slide73Evaluation
Parallel programsDaCapo Benchmarks 2006 & 2009SPEC JBB 2000 & 2005Platform32 cores (Intel Xeon E5 4620)
73
Slide74Performance of Recorders
74
Slide75Performance of RS enforcers
75