Title: Performance%20Analysis%20Tools
1Performance Analysis Tools
- Nadya Williams
- Spring, 2000
- UCSD
2Outline
- Background
- Performance measurement
- SvPablo
- Autopilot
- Paradyn
- XPVM
3Background
- Goal - high performance computing for
applications that are distributed - by design, e.g. collaborative environments,
distributed data analysis, computer-enhanced
instruments - by implementation, e.g. metacomputing,
high-throughput computing - Goal - to achieve maintain performance
guarantees in heterogeneous, dynamic environments
4Background
- Performance-robust grid applications need to
- Identify resources required to meet application
performance requirements - Select from problem specification, algorithm
code variants - Establish hierarchical performance contracts
- Select and manage adaptation strategies when
performance contracts are violated
5Computational grids
MPP
Real-time Data Analysis
Network
Viz Engine
Network
Visualization and Steering
Network
- Shared resources
- computation, network, and data archives
6Complexity
- Emerging applications are dynamic
- time varying resource demands
- time varying resource availability
- heterogeneous execution environments
- geographically distributed
- Display and analysis hierarchy
- code, thread, process, processor
- system and local area network
- national/international network
7Grid performance challenges
- Wide area infrastructure
- Many resource models
- Behavioral variability
- complex applications, diverse systems and
networks - irreproducible behavior
- Heterogeneous applications
- multilingual and multimodel
- real-time constraints and shared resources
- Prediction scheduling
8Outline
- Background
- Performance measurement
- SvPablo
- Autopilot
- Paradyn
- XPVM
9Performance analysis
- The ability to
- capture
- analyze
- present
- optimize
- Multiple analysis levels
- hardware
- system software
- runtime systems
- libraries
- applications
Good tools must accommodate all
10Real-time Multilevel Analysis
- Multilevel Drilldown
- multiple sites
- multiple metrics
- real-time display
- Problems
- uncertainty and perturbation
- confusion of cause and effect
11Guidelines
- Design for locality
- regardless of programming model
- threads, MPI, data parallel -- its the same
- Recognize historical models
- large codes develop over time
- assumptions change
- Think about more than FLOPS
- I/O, memory, networking, user interfaces
12Initial steps
- Develop infrastructure for structural and
performance information - Provide instrumentation of end-user applications
communication libraries - Study performance characteristics of real grid
applications
13Peak and Sustained Performance
- Peak performance
- perfect conditions
- Actual performance
- considerably less
- Environment dictates performance
- locality really matters
- we must design for performance stability
- more of less may be better than less of more
14Instrumentation approaches
- At least four major techniques
- profiling
- counting
- interval timing
- event tracing
- Each strikes a different balance
- detail and insight
- measurement perturbation
- Understand overheads and benefits
15Measurement developments
- Hardware counters
- once rare (Cray), now common (Sun, IBM, Intel,
Compaq) - metrics
- operation types
- memory stalls
- Object code patching
- run-time instrumentation
- Compiler integration
- inverse compiler transformations
- high-level language analysis
16Correlating semantic levels
- Performance measurements
- capture behavior of executing software
- reflect output of multi-level transformations
- Performance tools
- must relate data to user semantic model
- cache miss ratios cannot help a MATLAB user
- message counts cannot help an HPF user
- should suggest possible performance remedies
17Analysis developments
- Visualization techniques
- traces and statistics
- Search and destroy
- AI suggestions and consultants
- critical paths and zeroing
- Data reduction and processing
- statistical clustering/projection pursuit
- neural net, and time series classification
- Real-time control
- sensor/actuator models
18Performance tool checkpoint
- An incomplete view
- representative techniques and tools
- Major evolution
- from architectural views/post-mortem analysis
- to deeper correlation and derived metrics
- Key open problems
- adaptivity
- scale
- semantic correlation
19Representative vendor tools
- IBM VT
- ParaGraph trace display and statistical metrics
- Silicon Graphics Speedshop
- R10000, R12000 hardware counter tools
- Pallas Vampir
- event tracing and display tools
- Cray ATExpert (autotasking)
- basic AI suggestions for tuning
- Intel SPV
- ParaGraph and hardware counter displays
- TMC/SUN Prism
- data parallel and message passing analysis
20Representative research tools
- Illinois SvPablo
- performance data metaformat
- Globus integration (sensor/actuator control)
- Illinois Autopilot
- performance steering
- Wisconsin Paradyn
- runtime code patching
- performance consultant
- Oak Ridge National Lab XPVM
- X Windows based, graphical console and monitor
for PVM
21Outline
- Background
- Performance measurement
- SvPablo
- Autopilot
- Paradyn
22SvPablo Graphical source code browser for
performance tuning and visualization
- Department of Computer Science
- University of Illinois at
- Urbana-Champaign
23SvPablo Outline
- Background
- SvPablo overview
- SvPablo model
- Automatic/Interactive instrumentation of programs
- The Pablo Self-Defining Data Format
24SvPablo Background
- Motivations
- emerging high-level languages (HPF and HPC)
- aggressive code transformations for parallelism
- large semantic gap between user and code
- Goals
- relate dynamic performance data to source
- hide semantic gap
- generate instrumented executable/simulated code
- support performance scalability predictions
25Background
- Tools should provide the performance data and
suggestions for performance improvements at the
level of an abstract, high-level program - Tools should integrate dynamic performance data
with information recorded by the compiler that
describes the mapping from the high-level source
to the resulting low-level explicitly parallel
code
26SvPablo overview
- A graphical user interface tool for
- source code instrumentation
- browsing runtime performance data
- Two major components
- performance instrumentation libraries
- performance analysis and presentation
- Provides
- performance data capture
- analysis
- presentation
27SvPablo overview
- Instrumentation
- automatic
- HPF (from PGI)
- interactive
- ANSI C
- Fortran 77
- Fortran 90
- Data capture
- dynamic software statistics (no traces)
- SGI R10000 counter values
28SvPablo overview
- Source code instrumentation
- HPF PGI runtime system invokes instrumentation
- each procedure call
- each HPF source line
- C and Fortran programs interactively
instrumented - outer loops
- function calls
- Instrumentation maintains statistical summary
- Summaries correlated across processors
- Correlated summary input to browser
29SvPablo overview
- Architectures
- any system with the PGI HPF compile
- any system with F77 or F90
- C applications supported on
- single processor Unix workstations
- network of Unix workstations using MPI
- Intel Paragon
- Meiko CS2
- GUI supports
- Sun (Solaris)
- SGI (IRIX)
30Statistics metrics
- For procedures
- count
- exclusive / inclusive duration
- send / receive message duration (HPF only)
- For lines
- count
- duration
- exclusive duration
- message send and message receive (HPF only)
- duration
- count
- size
- event counters (SGI)
- Mean, STD, Min, Max
31SvPablo model
Application
. . .
Performance contexts
Source files
. . .
Performance data
Performance data
32New project dialog box
33HPF performance analysis data flow
HPF source code
SvPablo data capture library
instrumented object code
performance file
SvPabloCombine
Linker
Graphical performance browser
Parallel Architecture
instrumented executable
34HPF instrumentation
- pghpf -c -Mproflines source1.F
- pghpf -c -Mproflines source2.F
- pghpf -Mstats -o prog source1.o source2.o
- /usr/local/SvPablo/lib/pghpf2SDDF.o
- prog -pghpf -np 8
- SvPabloCombine HPF_SDDF
35Performance visualization
Metrics count exclusive duration
36Performance metric selection dialog
37C / F77/ F90 data flow
instrumented source code
create or edit project
SvPablo data capture library
compiler
per-process performance files
Instrument C or Fortran files
instrumented object code
SvPabloCombine
visualize performance file
Linker
Parallel Architecture
performance file
instrumented executable
SvPablo
38Interactive instrumentation
Instrumentable Constructs (function calls and
outer loops)
39Generating an instrumented executable program
- mpicc -c file1.Context1.inst.c
- mpicc -c file2.Context1.inst.c
- mpicc -c Context1/InstrumentationInit.c
- mpicc -o instFile InstrumentationInit.o
- file1.Context1.inst.o
- file2.Context1.inst.o
- svPabloLib.a
40SDDF a medium of exchange
- Self-Defining Data Format
- data meta-format language for performance data
description - specifies both data record structures and data
record instances - separates data structure and semantics
- allows the definition of records containing
scalars and arrays - supported by the Pablo SDDF library
41SDDF files classes of records
- Command conveys action to be taken
- Stream Attribute gives information pertinent to
the entire file - Record Descriptor declares record structure
- Record Data encapsulates data values
42Record descriptors
- Describe record layout
- Each Record Descriptor contains
- A unique tag and record name
- An optional Record Attribute
- Field Descriptors, each one containing
- an optional Field Attribute
- field type specifier
- field name
- optional field dimension
43SDDF record descriptor data
tag
- 300
- // "description" "PGI Line-Based Profile Record"
- "PGI Line Profile"
- int "Line Number"
- int "Processor Number
- int "Procedure ID"
- int "Count"
- double "Inclusive Seconds"
- double "Exclusive Seconds"
- int "Send Data Count"
- int "Send Data Byte"
- double "Send Data Seconds"
- int "Receive Data Count"
- int "Receive Data Byte"
- double "Receive Data Seconds"
-
- "PGI Line Profile" 359, 27,9, 4, 399384,
31.071, 31.071, 0, 0, 0, 0, 0, 0
record name
field descriptors
44SvPablo language transparency
- Meta-format for performance data
- language defined by line and byte offsets
- metrics defined by mapping to offsets
- SDDF records
- performance mapping information
- performance measurements
- Result
- language independent performance browser
- mechanism for scalability model integration
45SvPablo conclusions
- Versatility yes
- analysis GUI is quite versatile, provides the
ability to define new modules, but steep learning
curve - theoretically, any type of view could be
constructed from the toolkit provided - Portability not quite
- Intended for wide range of parallel platforms and
programming languages, reality is different
(SUN, SGI) - Scalability - some
- Pablo trace library monitors and dynamically
alters the volume, frequency, and types of event
data recorded - not clear how automatically or by user at low
level? - need to integrate predictions
46Outline
- Background
- Performance measurement
- SvPablo
- Autopilot
- Paradyn
- XPVM
47Autopilot - a performance steering
toolkitProvides flexible infrastructure for
real-time adaptive control of parallel and
distributed computing resources
- Department of Computer Science
- University of Illinois at
- Urbana-Champaign
48Autopilot outline
- Background
- Autopilot overview
- Autopilot components
- Conclusions
49Autopilot background
- HPC from single parallel systems to distributed
collections of heterogeneous sequential and
parallel systems. - emerging applications are irregular
- have complex, data dependent execution behavior
- dynamic, with time varying resource demands
- failure to recognize that resource allocation and
management must evolve with applications - Consequence small changes in application
structure - can lead to large changes in observed
performance.
50Autopilot background
- interactions between application and system
resources change - across applications
- during a single application's execution
- Autopilot approach create adaptable
- runtime libraries
- resource management policies
51Autopilot overview
- After the integration of
- dynamic performance instrumentation
- on-the-fly performance data reduction
- configurable, malleable resource management
algorithms - real-time adaptive control mechanism
- Have adaptive resource management infrastructure
- Given
- application request patterns
- observed system performance
- Automatically choose configure resource
management algorithms - increase portability
- increase achieved performance
52Autopilot components
- Autopilot - implements the core features of the
Autopilot system. - Fuzzy Library - needed to build the classes
supporting the fuzzy logic decision procedure
infrastructure - Autodriver - provides a graphical user interface
(written in Java) - Performance Monitor - provides tools to retrieve
and record various system performance statistics
on a set of machines.
531 Autopilot component
- libAutopilot.a creation, registration, and use
- sensors
- actuators (enable and configure resource
management policies) - decision procedures
- AutopilotManager - a utility program which
displays the sensors and actuators currently
registered with the Autopilot Manager
542 Fuzzy library component
- Fuzzy Rules to C translator
- related classes used by the Autopilot fuzzy logic
decision procedure infrastructure.
553 Autodriver component
- Autopilot Adapter program
- provides a Java interface to Autopilot
- (must run on UNIX)
- JAVA GUI
- talks to Autopilot through the Adapter
- allows a user to monitor and interact with live
sensors and actuators. - (runs on any platform that supports Java)
564 Performance monitor component
- two kinds of processes
- Collectors
- run on the machines to be monitored
- capture quantitative application and system
performance data - Recorders
- compute performance metrics.
- record or output it.
- communicate via Autopilot component
57Closed loop adaptive control
Illinois Autopilot Toolkit (Reed et al)
Globus integration
Real-time measurement
58Autopilot conclusions
- Goal is creation of an infrastructure for
building resilient, distributed and parallel
applications. - allow the creation of software that can change
its behavior and optimize its performance in
response to real-time data - on software dynamics
- performance.
- order of magnitude performance improvements
59Outline
- Background
- Performance measurement
- SvPablo
- Autopilot
- Paradyn
60Paradynperformance measurement tool for
parallel and distributed programs
- Computer Science,
- University of Wisconsin
61Paradyn outline
- Motivations
- Approach
- Performance Consultant
- Conclusions
62Paradyn motivations
- provide a performance measurement tool that
scales to long-running programs on large parallel
and distributed systems - automate much of the search for performance
bottlenecks - avoid the space and time overhead typically
associated with trace-based tools. - go beyond post-mortem analysis
63Paradyn approach
- Dynamic instrumentation
- based on dynamically controlling what performance
data is to be collected. - allows data collection instructions to be
inserted into an application program during
runtime. - Paradyn
- dynamically instruments the application
- automatically controls the instrumentation in
search of performance problems
64Paradyn model
- the Paradyn front-end and user interface
- display performance visualizations
- use the Performance Consultant to find
bottlenecks - start and stop the application
- monitor the status of the application
- the Paradyn daemons
- monitor and instrument the application processes.
65Performance consultant module
- automatically directs the placement of
instrumentation - has a knowledge base of performance bottlenecks
and program structure - can associate bottlenecks with specific causes
and with specific parts of a program.
66Paradyn runtime
- Concepts for performance data analysis/presentatio
n - metric-focus grid cross-product of two vectors
- list of performance metrics (CPU time, blocking
time) - list of program components (procedures,
processors, disks) - elements of the matrix can be single-valued
(e.g., current - value, average, min, or max) or time-histograms
- time-histogram fixed-size data structure
recording behavior of a metric as it varies over
time - Performance data granularity
- global phase
- local phase
67Performance consultant
Wisconsin Paradyn Toolkit (Miller et al)
unknown
true
false
68Performance consultant
Wisconsin Paradyn Toolkit (Miller et al)
69Outline
- Background
- Performance measurement
- SvPablo
- Autopilot
- Paradyn
- XPVM
70XPVMGraphical console and monitor for PVM
- developed at the Oak Ridge National Lab
- Provides a graphical user interface to the PVM
console commands - Provides several animated views to monitor the
execution of PVM programs
71XPVM overview
- Xpvm generates trace records during PVM program
execution. The resulting trace file is used to
"playback" a program's execution. - The xpvm views provide information about the
interactions among tasks in a parallel PVM
program, to assist in debugging and performance
tuning. - Xpvm writes a Pablo self-defining trace file
72XPVM menus
- Host menu permits to configure a parallel
virtual machine by adding/removing hosts - Tasks menu enables to spawn, signal, or kill PVM
processes, can monitor selected PVM system tasks,
such as the group server process
73XPVM menus
- Reset menu resets parallel virtual machine, xpvm
views, or trace file - Help menu provides help features
- Views permits selection of any of the five xpvm
displays for monitoring program execution
74XPVM menus
- Trace file play back controls - play, step
forward, stop or reset the execution trace file - Trace file selection window - displays the name
of the current trace file
75XPVM views (5)
- Network
- Displays high-level activity on each node in the
virtual machine - Each host is represented by an icon image showing
host name and architecture - Icons are color illuminated to indicate status
- Active - at least one task on that host is doing
useful work - System - no tasks are doing user work and at
least one task is busy executing PVM system
routines - No tasks
76Network
77Space time
- Shows status of all tasks as they execute across
all hosts - Computing - executing useful user computations
- Overhead - executing PVM system routines for
communication, task control, etc. - Waiting - waiting for messages from other tasks
- Message - indicates communications between tasks
78Space time
79Utilization
- Summarizes the Space-Time view at each instant by
showing the aggregate number of tasks computing,
in overhead or waiting for a message. - Shares same horizontal time scale as the
Space-Time view - Zooming-in
- Zooming-out
80Utilization
81Call trace
- Displays each tasks' most recent PVM call
- Changes as program executes
- Useful for debugging
- Clicking on a task in the scrolling task list
will display that task's full name and TID
82Call trace
83Task output
- Provides a view of output (stdout) generated by
tasks in a scrolling window - Can be saved to a file at any point
84Concluding remarks
- System complexity is rising fast
- computational grids
- multidisciplinary applications
- performance tools
- There are many open problems
- adaptive optimization
- performance prediction
- compiler/tool integration
- performance quality of service (QoS)
85Concluding remarks
- the software problems are large cannot be solve
in isolation - open source collaboration
- vendors, laboratories, and academics
- technology assessment