Dorian Arnold Computer Science Department University of...
Transcript of Dorian Arnold Computer Science Department University of...
![Page 1: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/1.jpg)
Department of Computer Science
Dorian ArnoldComputer Science Department
University of New Mexico
![Page 2: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/2.jpg)
Scalable Systems Lab
Life Before ICL
![Page 3: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/3.jpg)
Scalable Systems Lab
January 1999 – August, 2001
NetSolve Project
ICL Collaborators:
◦ Henri, Sudesh, Sathish, Jakob, Thara, Michelle, Dieter, Keith S., Tsinghua, Victor, Susan, Shirley, Keith M., Ganapathy, Nathan, David
MY ICL Tenure
![Page 4: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/4.jpg)
Scalable Systems Lab
PhD Student, U. of Wisconsin, ’01 - ’08◦ Scalable, reliable communication infrastructure
◦ Scalable, lightweight tools and applications
Asst. Professor, U. of New Mexico, since ’09◦ Carry-over from dissertation work (naturally)
◦ Autonomous Infrastructure
◦ Virtualization for HPC
◦ Thin Computing
Life After ICL
![Page 5: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/5.jpg)
Scalable Systems Lab
What is HPC?◦ It depends … on who you ask? Computer architect? OS researcher? Applied mathematician? (Dead-end career ) Domain scientist? Distributed systems researcher!
Many domains of expertise◦ One should not need cross-domain expertise to use HPC
resources effectively
The Method behind the Madness
![Page 6: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/6.jpg)
Scalable Systems Lab
My Research Foci
Make HPC systems easier to use without sacrificing performance and reliability
![Page 7: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/7.jpg)
Department of Computer Science
Tree-based Overlay Networks
![Page 8: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/8.jpg)
Scalable Systems Lab8
FEApplicationfront-end
Applicationback-ends BE BE BE BE BE BE BE BE
Data management Large volumes
Data analysisCentralized analysis leads to
computational bottlenecks
Many resources to manage E.g. control channels
Doesn’t Scale!
We need Scalable Tools and Applications
![Page 9: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/9.jpg)
Scalable Systems Lab
Key TBŌN Abstractions
FE
BE BE BE BE BE BE BE BE
CP
CP CP CP CP
CP CP
PacketFilter
FilterState
Filters◦ Executed by processes◦ Persistent state
Channels◦ Reliable◦ Order-preserving
Streams◦ Define sub-groups◦ Distinguish dataflows◦ Specify filter routine
FE
BE BE BE BE BE
CP
CP CP CP
CP CP
![Page 10: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/10.jpg)
Scalable Systems Lab
The Multicast/Reduction Network MRNet is our prototype TBŌN◦ Developed by Arnold, Roth and Miller
Used by many research installations◦ Paradyn (University of Wisconsin)◦ Stack Trace Analysis Tool (LLNL)◦ TauOverMRNet (University of Oregon)◦ TBON-FS (University of Wisconsin)◦ Image Analysis (University of Wisconsin)◦ CEPBA-Tools (Universitat Politècnica de Catalunya)◦ Open|SpeedShop (Krell Institute)◦ TotalView (TotalView Tech.)
Ongoing collaborations: RENCI, Juelich◦ Scalable Tool Communication Infrastructure???????
![Page 11: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/11.jpg)
Department of Computer Science
![Page 12: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/12.jpg)
Scalable Systems Lab
Stack Trace Analysis ToolExtreme Scale Debugging
STAT is a lightweight debugging aid thatuses stack traces to classify processequivalence and profile application.
Thousands of tasks reduce to few classes.
Analyze representatives with full debugger
Temporal analysis determines tasks’relative progress
Goal: Scale up to machine sizes andscale down the information
![Page 13: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/13.jpg)
Scalable Systems Lab13
MPI MPI MPI MPI MPI MPI MPIMPI
Stack Trace Analysis ToolFE
BE BE BE BE BE BE BE BE
CP
CP CP CP CP
CP CP
Application Processes
STAT Front-end
STAT Daemon
MRNetCommunication
ProcessSTAT Filter
![Page 14: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/14.jpg)
Scalable Systems Lab14
STAT Performance on BlueGene/L
0
0.1
0.2
0.3
0.4
0.5
0.6
0K16K
32K48K
64K80K
96K112K
128K144K
160K176K
192K208K
Number of Application Processes
Mer
ge L
aten
cy (s
econ
ds)
1-deep (VN Mode)
2-deep (VN Mode)
3-deep (VN Mode)
zero to 212,992in 0.4!
![Page 15: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/15.jpg)
Department of Computer Science
![Page 16: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/16.jpg)
Scalable Systems Lab
Observations and Recovery ApproachExplicit state replication is expensiveUse inherent information redundancy
Strong data consistency is expensiveUse weak data consistency
Global coordination is expensiveUse localized protocols to satisfy global requirements
Information must be disseminated globallyUse TB• N for efficient, scalable dissemination
![Page 17: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/17.jpg)
Scalable Systems Lab
State Compensation Compensate for lost state using inherently
redundant information from surviving processes◦ Avoid overhead of explicit data replication
State composition◦ Lightweight mechanism for idempotent aggregations
State decomposition◦ For non-idempotent aggregations◦ Requires two coordination phases No overhead in the absence of failures O(log(N)) processes participate in failure recovery
![Page 18: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/18.jpg)
Scalable Systems Lab
State Composition Example
1
7
3
4 1
9
5{1,3,5}{1,3,4} {1,5}
{1,3}
{1,3,4,5} {1,5,8}
4,5 5,8
1,3
{1,8,9}Use orphans states
to compensate for failure
![Page 19: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/19.jpg)
Scalable Systems Lab
State Composition Example
1
7
3
4 1 5{1,3,5}{1,3,4} {1,5}
{1,3}
{1,3,4,5}
4,5
1,3
{1,8,9}
1,8,9
1,51
7
3
4 1
9
5{1,3,5}{1,3,4} {1,5}
{1,3}
{1,3,4,5} {1,5,8}
4,5 5,8
1,3
{1,8,9}
![Page 20: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/20.jpg)
Scalable Systems Lab
State Composition Example
1
7
3
4 1
9
5{1,3,5}{1,3,4} {1,5}
{1,3}
{1,3,4,5} {1,5,8}
4,5 5,8
1,3
{1,8,9}
1
7
3
4 1 5{1,3,5}{1,3,4} {1,5}
{1,3}
{1,3,4,5}
4,5
1,3
{1,8,9}
1,8,9
1,5
![Page 21: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/21.jpg)
Scalable Systems Lab
State Composition Example
7 4 5
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,8}
{1,3,4,5} {1,5,8,9}
9
1,3
{1,5,8,9}
7 4
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,8,9}
{1,3,4,5}
4,5,8,9
{1,5,8,9}
5
4,5,81,3
![Page 22: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/22.jpg)
Scalable Systems Lab
State Composition Example
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,8,9}
{1,3,4,5,7} {1,5,8,9}
1,3
{1,5,8,9}
4,5,8
7
9
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,8,9}
{1,3,4,5,7}
7
4,5,8,9
{1,5,8,9}
1,3
![Page 23: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/23.jpg)
Scalable Systems Lab
State Composition Example
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,7,8,9}
{1,3,4,5,7} {1,5,8,9}
1,3
{1,5,8,9}
4,5,8
79
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,8,7,9}
{1,3,4,5,7}
7
4,5,8,9
{1,5,8,9}
1,3Output stream converges
to that of non-failed execution
![Page 24: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/24.jpg)
Scalable Systems Lab
Robust, Scalable Data Aggregation
0
10
20
30
40
50
60
70
80
90
FIM
S
MAX
AVG
FIM
S
MAX
AVG
FIM
S
MAX
AVG
FIM
S
MAX
AVG
FIM
S
MAX
AVG
FIM
S
MAX
AVG
Fan-out at Failed Process
Rec
over
y La
tenc
y (m
illis
econ
ds)
l(overall) l(new_parent)l(connect) l(compensate)l(cleanup)
7
8
9
10
11
12
13
14
15
0 30 60 90 120 150 180Time (seconds)
Th
rou
gh
pu
t (p
acke
ts/s
eco
nd
)
Failure Recovery Latency
Application Throughput as Failures are Injected
![Page 25: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/25.jpg)
Department of Computer Science
![Page 26: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/26.jpg)
Scalable Systems Lab
Autonomous Middleware
System Knowledge in Application
Sys
tem
Eas
e-of
-use
Application Knowledge in System
Sys
tem
Gen
eral
ity
GoalEfficient, scalable systems from:
Approach: Dynamic, Autonomous OperationSelf-configuring: Automatic TBŌN topology configuration
Self-monitoring: TBŌN health and performance
Self-healing: TBŌN Fault tolerance and failure recovery
Self-optimizing: Dynamic TBŌN reconfiguration to improve performance
Challenges• Reliable service at scale
• Choosing the “best” TBŌN topologies?– Load and system characteristics may vary
over time
• Online improvement of TBŌN performance?– Throughput, latency, resource consumption,
startup costs, …
• Flexible, elegant solution space
Monitoring
Detecting Deciding
Acting
Sensors Effectors
Events
Symptoms Decisions
Actions
System-agnosticApplications
Application-agnosticSystems
![Page 27: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/27.jpg)
27
Problem Statement:Application Efficiency and Scalability
Necessary SystemKnowledge in App.
Sys
tem
ease
-of-
use
Necessary ApplicationKnowledge in System
Sys
tem
Gen
eral
ity
1. How much system-specific knowledgedoes application (developer) need?
2. How much application-specific knowledge does system (developer) need?
3. How far can we get answering “NONE” and “NONE”?
![Page 28: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/28.jpg)
28
The Approach:An Autonomous TB• N Infrastructure
TB• N Autonomy aka the self-* properties:• Self-configuring
– Automatic TB• N topology configuration
• Self-monitoring– TB• N health and performance
• Self-healing– TB• N Fault tolerance and failure recovery
• Self-optimizing– Dynamic TB• N reconfiguration to improve performance
![Page 29: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/29.jpg)
29
Research Challenges
• How can we provide a reliable TB• N service in the presence of failures?
• How do we choose the “best” TB• N topologies?– Application load and system characteristics may vary over time
• How can we dynamically improve TB• N performance?– Throughput, latency, resource consumption, startup costs, …
• Can we design a flexible, elegant solution space?
![Page 30: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/30.jpg)
30
“Performance Failures”
• What is a performance failure?– Generally, a sub-optimal topology, or
– Realizing (much) less than optimal performance• Data aggregation latency and throughput• Resource under-utilization• Imbalanced topologies
– Per application?– Per flow/stream?
![Page 31: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/31.jpg)
31
Per Flow Topologies
• “best” topology depends upon– Participating end-points– Data aggregation operation– Application data rate– …
• “best” is different for different streams!– How can we efficiently enable different topologies for
different flows?
![Page 32: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/32.jpg)
Department of Computer Science
![Page 33: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/33.jpg)
Department of Computer Science
![Page 34: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/34.jpg)
34
TB• N Components for Autonomy
Monitoring
Detecting Deciding
Acting
Sensors EffectorsEvents
SymptomsDiagnosis
Decisions
Actions
Sensors: hw/sw characteristics, runtime events, etc.Monitoring: collecting/correlating events to identify patterns andsymptoms, e.g. threshold checking, etc.Detecting: evaluate symptoms to determine if problems existsand action is necessary, e.g. do we have a bottleneck?
Deciding: determining how best to modify topologyActing: effecting the recommended topology changesKey Challenges:• Decentralization• Low (background) overhead• Rapid execution• Must provide more benefits than drawbacks!
![Page 35: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/35.jpg)
Scalable Systems Lab
Example TBŌN Reductions Simple◦ Min, max, sum, count, average◦ Concatenate
Complex◦ Clock synchronization [Roth, Arnold, Miller ’03]◦ Time-aligned aggregation [Roth, Arnold, Miller ’03]◦ Vision algorithms [Arnold, Pack, Miller ’06]◦ Graph Analysis [Arnold et al. ’07], [Roth, Miller ’05]◦ Equivalence relations
![Page 36: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/36.jpg)
36
Integer Union Example
43
37
51
34
51
11
81
95
{ }{ } { }
{ }
{ } { }
{ }
![Page 37: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/37.jpg)
37
Integer Union Example
4
3
31
5
1
34
5
1
11
8
1
95
{1}{3} {1}
{ }
{ } { }
{1}
![Page 38: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/38.jpg)
38
Integer Union Example
4
17
5
34
5
11
8
95
{1,5}{3,4} {1,5}
{ }
{1,3} {1}
{1,8}
1,3 1
![Page 39: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/39.jpg)
39
Integer Union Example
1
7
3
4 1
9
5{1,3,5}{1,3,4} {1,5}
{1,3}
{1,3,4,5} {1,5,8}
{1,8,9}
4,5 5,8
1,3
![Page 40: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/40.jpg)
40
Integer Union Example
7 4 5
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,8}
{1,3,4,5} {1,5,8,9}
{1,5,8,9}
9
4,5,81,3
![Page 41: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/41.jpg)
41
Integer Union Example
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,8,9}
{1,3,4,5,7} {1,5,8,9}
{1,5,8,9}
7
4,5,81,3
9
![Page 42: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/42.jpg)
Integer Union Example
42
{1,3,4,5}{1,3,4,7} {1,5}
{1,3,4,5,7,8,9}
{1,3,4,5,7} {1,5,8,9}
{1,5,8,9}
7
4,5,81,3
9
![Page 43: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/43.jpg)
MRNet Front-end Interface
43
front_end_main(){Network * net = new Network (topology_file);
Communicator * comm = net->get_BroadcastCommunicator();
Stream * stream =new Stream( comm, IMAX_FILT, WAITFORALL);
stream->send(“%s”, “go”);
stream->recv(“%d”, &result);}
![Page 44: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/44.jpg)
44
MRNet Back-end Interfaceback_end_main(){Stream * stream;Packet *p;char * s;
Network * net = new Network();
net->recv(&tag, &p, &stream);p->unpack( “%s”, &s );
if(s == “go”){stream->send(“%d”, rand_int);
}}
![Page 45: Dorian Arnold Computer Science Department University of ...icl.cs.utk.edu/20/presentations/Dorian_Arnold.pdfScalable Systems Lab PhD Student, U. of Wisconsin, ’01 -’08 Scalable,](https://reader034.fdocuments.net/reader034/viewer/2022042401/5f103ee57e708231d448289e/html5/thumbnails/45.jpg)
45
MRNet Filter Interfaceimax_filter(vector<Packet> packets_in,
vector<Packet> packets_out){for( i=0; i<packets_in.size; i++){result = max( result,
packets[i].get_int());}
Packet p(“%d”, result);
packets_out.pushback(p);}