Index

A

accessible documentation, 1

addpath command, 1

address spaces, text and data regions, 1

aggressive backtracking, 1

aliased functions, 1

alternate entry points in Fortran functions, 1

alternate source context, 1

analyzer command

font size (-f) option, 1

help (-h) option, 1

JVM options (-J) option, 1

JVM path (-j) option, 1

verbose (-v) option, 1

version (-V) option, 1

Analyzer, See Performance Analyzer

annotated disassembly code, See disassembly code, annotated

annotated source code, See source code, annotated

API, Collector, 1

appending path to files, 1

arc, call graph, 1, 2

archiving load objects in experiments, 1, 2

asynchronous I/O library, interaction with data collection, 1

attaching the Collector to a running process, 1

attributed metrics

defined, 1

effect of recursion on, 1

illustrated, 1

use of, 1

B

body functions, compiler-generated

defined, 1

displayed by the Performance Analyzer, 1, 2

names, 1, 2

propagation of inclusive metrics, 1

branch target, 1

C

C compiler option, xhwcprof, 1

call stack, 1

default alignment and depth in the Timeline tab, 1

defined, 1

effect of tail-call optimization on, 1

in the Event tab, 1

in Timeline tab, 1

incomplete unwind, 1

mapping addresses to program structure, 1

unwinding, 1

callers-callees metrics

attributed, 1, 2

displaying list of in er_print utility, 1

printing for a single function in er_print utility, 1

printing in er_print utility, 1

selecting in er_print utility, 1

sort order in er_print utility, 1

Callers-Callees tab, 1, 2

clock-based profiling

accuracy of metrics, 1

collecting data in dbx, 1

collecting data with the collect command, 1

comparison with gethrtime and gethrvtime, 1

data in profile packet, 1

default metrics, 1

defined, 1

distortion due to overheads, 1

interval, See profiling interval

metrics, 1, 2

cloned functions, 1, 2

collect command

archiving (-A) option, 1

clock-based profiling (-p) option, 1

collecting data with, 1

data collection options, 1, 2

data limit (-L) option, 1

dry run (-n) option, 1

experiment control options, 1

experiment directory (-d) option, 1

experiment group (-g) option, 1

experiment name (-o) option, 1

follow descendant processes (-F) option, 1

hardware counter overflow profiling (-h) option, 1

heap tracing (-H) option, 1

Java version (-j) option, 1

listing the options of, 1

miscellaneous options, 1

MPI tracing (-m) option, 1

output options, 1

pause and resume data recording (-y) option, 1

periodic sampling (-S) option, 1

readme display (-R) option, 1

record sample point (-l) option, 1

stop target after exec (-x) option, 1

synchronization wait tracing (-s) option, 1

syntax, 1

verbose (-v) option, 1

version (-V) option, 1

with ppgsz command, 1

Collect Experiment

Preview command, 1

Collector

API, 1, 2, 3

attaching to a running process, 1

defined, 1, 2

disabling in dbx, 1

enabling in dbx, 1

running in dbx, 1

running with the collect command, 1

collectorAPI.h, 1

common subexpression elimination, 1

compiler commentary, 1

classes defined, 1

cloned functions, 1

common subexpression elimination, 1

description of, 1

filtering in er_src utility, 1

filtering types displayed, 1

inlined functions, 1

loop optimizations, 1

parallelizaton, 1

selecting for annotated disassembly listing in er_print utility, 1

selecting for annotated source listing in er_print utility, 1

compiler optimization

inlining, 1

parallelization, 1

compiler-generated body functions

defined, 1

displayed by the Performance Analyzer, 1, 2

names, 1, 2

propagation of inclusive metrics, 1

compilers, accessing, 1

compiling

affects of optimization on program analysis, 1

debug symbol information format, 1

effect of static linking on data collection, 1

for gprof, 1

for Lines analyses, 1

for prof, 1

for tcov, 1

for tcov Enhanced, 1

Java programming language, 1

linking for data collection, 1

source code for annotated Source and Disassembly, 1

static linking of libraries, 1

copying an experiment, 1

correlation, effect on metrics, 1

CPU filtering, 1

CPUs

listing selected, in er_print utility, 1

selecting in er_print utility, 1

D

data collection

controlling from your program, 1

disabling from your program, 1

disabling in dbx, 1

dynamic memory allocation effects, 1

enabling in dbx, 1

from MPI programs, 1

linking for, 1

MPI program, using dbx, 1

MPI program, 1, 2

pausing for collect command, 1

pausing from your program, 1

pausing in dbx, 1

preparing your program for, 1

program control of, 1

rate of, 1

resuming for collect command, 1

resuming from your program, 1

resuming in dbx, 1

segmentation faults, 1

using dbx, 1

using the collect command, 1

data objects

<Scalar> descriptors, 1

<Total> descriptor, 1

defined, 1

in hardware counter overflow experiments, 1

layout, 1

scope, 1

set the sort metric for, 1

Data Space Display, 1

Data Space Display mode, 1

data types, 1

clock-based profiling, 1

default, in the Timeline tab, 1

hardware counter overflow profiling, 1

heap tracing, 1

MPI tracing, 1

synchronization wait tracing, 1

data_objects command, 1

data_olayout command, 1

data_osingle command, 1

data_osort command, 1

DataLayout tab, 1

datamode on command, 1

datamode setting, 1

DataObjects tab, 1

dbx

collecting data under MPI, 1

running the Collector in, 1

dbx collector subcommands

archive, 1

dbxsample, 1

disable, 1

enable, 1

enable_once (obsolete), 1

hwprofile, 1

limit, 1

pause, 1

profile, 1

quit (obsolete), 1

resume, 1

sample, 1

sample record, 1

show, 1

status, 1

store, 1

store filename (obsolete), 1

synctrace, 1

default metrics, 1

defaults, setting in a defaults file, 1

descendant experiments, 1

descendant processes

collecting data for all followed, 1

collecting data for selected, 1

experiment location, 1

experiment names, 1

followed by Collector, 1

limitations on data collection for, 1

directives, parallelization, 1, 2

disassembly code, annotated

branch target, 1

cloned functions, 1

description, 1

for cloned functions, 1, 2

hardware counter metric attribution, 1

HotSpot-compiled instructions, 1

inclusive metrics, 1

instruction issue dependencies, 1

interpreting, 1

Java native methods, 1

location of executable, 1

metric formats, 1

printing in er_print utility, 1

setting preferences in er_print utility, 1

setting the highlighting threshold in er_print utility, 1

viewing with er_src utility, 1

Disassembly tab, 1

disk space, estimating for experiments, 1

documentation index, 1

documentation, accessing, 1 - 2

DTrace driver

described, 1

setting up access to, 1

dynamically compiled functions

Collector API for, 1

definition, 1, 2

E

entry points, alternate, in Fortran functions, 1

environment variables

JAVA_PATH, 1

JDK_HOME, 1

LD_LIBRARY_PATH, 1

LD_PRELOAD, 1

PATH, 1

SUN_PROFDATA, 1

SUN_PROFDATA_DIR, 1

TCOVDIR, 1, 2

.er.rc file, 1, 2, 3, 4

er_archive utility, 1

er_cp utility, 1

er_export utility, 1

er_kernel utility, 1

er_mv utility, 1

er_print commands

addpath, 1

allocs, 1

callers-callees, 1

cmetric_list, 1

cmetrics, 1

cpu_list, 1

cpu_select, 1

csingle, 1

csort, 1

data_objects, 1

data_olayout, 1

data_osingle, 1

data_osort, 1

dcc, 1

disasm, 1

dmetrics, 1

dsort, 1

exp_list, 1

fsingle, 1

fsummary, 1

functions, 1

header, 1

help, 1

javamode, 1

leaks, 1

limit, 1

lines, 1

lsummary, 1

lwp_list, 1

lwp_select, 1

mapfile, 1

metric_list, 1

metrics, 1

name, 1

object_list, 1

object_select, 1

objects, 1

outfile, 1

overview, 1

pcs, 1

psummary, 1

quit, 1

sample_list, 1

sample_select, 1

scc, 1

script, 1

setpath, 1

sort, 1

source, 1

src, 1

statistics, 1

sthresh, 1, 2

thread_list, 1

thread_select, 1

tldata, 1

tlmode, 1

Version, 1

version, 1

er_print utility

command-line options, 1

commands, See er_print commands

metric keywords, 1

metric lists, 1

purpose, 1

syntax, 1

er_rm utility, 1

er_src utility, 1

errors reported by tcov, 1

event marker, 1

Event tab, 1, 2

events

default display type in the Timeline tab, 1

displayed in Timeline tab, 1

exclusive metrics

defined, 1

for PLT instructions, 1

how computed, 1

illustrated, 1

use of, 1

execution statistics

comparison of times with the <Total> function, 1

printing in er_print utility, 1

experiment directory

default, 1

specifying in dbx, 1

specifying with collect command, 1

experiment filtering, 1

experiment groups

adding, 1

creating, 1

default name, 1

defined, 1

multiple, 1

name restrictions, 1

preview, 1

removing, 1

specifying name in dbx, 1

specifying name with collect command, 1

experiment names

default, 1

MPI default, 1, 2

MPI, using MPI_comm_rank and a script, 1

restrictions, 1

specifying in dbx, 1

experiments

adding, 1

appending current path, 1

archiving load objects in, 1, 2

copying, 1

data aggregation, 1

default name, 1

defined, 1

descendant, 1

groups, 1

header information in er_print utility, 1

limiting the size of, 1, 2

listing in er_print utility, 1

location, 1

moving, 1, 2

moving MPI, 1

MPI storage issues, 1

multiple, 1

naming, 1

opening, 1

preview, 1

removing, 1

setting mode for Java, 1

setting path to find files, 1

storage requirements, estimating, 1

terminating from your program, 1

where stored, 1, 2

Experiments tab, 1

explicit multithreading, 1

F

fast traps, 1

filter CPU, 1

Filter Data dialog box, 1

filter experiment, 1

filter LWPs, 1

filter sample, 1

filter threads, 1

Find tool, 1

Fortran

alternate entry points, 1

Collector API, 1

subroutines, 1

frames, stack, See stack frames

function calls

between shared objects, 1

imputed, in OpenMP programs, 1

in single-threaded programs, 1

recursive, metric assignment to, 1

function list

compiler-generated body function, 1

printing in er_print utility, 1

sort order, specifying in er_print utility, 1

function names, C++, choosing long or short form in er_print utility, 1

function PCs, aggregation, 1, 2, 3

function reordering, 1

function-list metrics

displaying list of in er_print utility, 1

selecting default in .er.rc file, 1

selecting in er_print utility, 1

setting default sort order in .er.rc file, 1

functions

@plt, 1

address within a load object, 1

aliased, 1

alternate entry points (Fortran), 1

body, compiler-generated, See body functions, compiler-generated

cloned, 1, 2

Collector API, 1, 2

definition of, 1

dynamically compiled, 1, 2, 3

global, 1

inlined, 1

MPI, 1, 2

non-unique, names of, 1

outline, 1, 2

static, in stripped shared libraries, 1, 2

static, with duplicate names, 1

system library, interposition by Collector, 1

<Total>, 1

<Unknown>, 1

variation in addresses of, 1

wrapper, 1

Functions tab, 1, 2

G

gprof

limitations, 1

output from, interpreting, 1

summary, 1

using, 1

H

hardware counter attribute options, 1

hardware counter library, libcpc.so, 1

hardware counter list

description of fields, 1

obtaining with collect command, 1

obtaining with dbx collector command, 1

raw counters, 1

well-known counters, 1

hardware counter metrics, displayed in DataObjects tab, 1

hardware counter overflow profiling

collecting data with collect command, 1

collecting data with dbx, 1

data in profile packet, 1

default metrics, 1

defined, 1

hardware counter overflow value

consequences of too small or too large, 1

defined, 1

experiment size, effect on, 1

setting in dbx, 1

setting with collect, 1

hardware counters

choosing with collect command, 1

choosing with dbx collector command, 1

counter names, 1

data objects and metrics, 1

list described, 1

obtaining a list of, 1, 2

overflow value, 1

heap tracing

collecting data in dbx, 1

collecting data with collect command, 1

default metrics, 1

metrics, 1

preloading the Collector library, 1

high metric values

in annotated disassembly code, 1

in annotated source code, 1

I

inclusive metrics

defined, 1

effect of recursion on, 1

for outlined functions, 1

for PLT instructions, 1

for slave threads, 1

how computed, 1

illustrated, 1

use of, 1

index lines, 1

in Disassembly tab, 1, 2

in er_print utility, 1, 2

in Source tab, 1, 2, 3

index lines, special

compiler-generated body functions, 1

HotSpot-compiled instructions, 1

instructions without line numbers, 1

Java native methods, 1

outline functions, 1

inlined functions, 1

input file

terminating in er_print utility, 1

to er_print utility, 1

instruction issue

delay, 1

grouping, effect on annotated disassembly, 1

intermediate files, use for annotated source listings, 1

interposition by Collector on system library functions, 1

interval, profiling, See profiling interval

interval, sampling, See sampling interval

J

Java

dynamically compiled methods, 1, 2

memory allocations, 1

monitors, 1

profiling limitations, 1

setting er_print display output for, 1

Java Virtual Machine path, analyzer command option, 1

JAVA_PATH environment variable, 1

javamode command, 1

javamode setting, 1

JDK_HOME environment variable, 1

--jdkhome analyzer command option, 1

JVM versions, 1

K

kernel clock profiling, 1

kernel experiment

field label meanings, 1

types of data, 1

kernel profile, analyzing, 1

kernel profiling

profiling a specific process or kernel thread, 1

profiling the kernel and load together, 1

profiling under load, 1

setting up your system for, 1

keywords, metric, 1, 2

L

LD_LIBRARY_PATH environment variable, 1

LD_PRELOAD environment variable, 1

leaf PC, 1, 2

Leak tab, 1

LeakList tab, 1

leaks, memory, definition, 1

Legend tab, 1, 2

libaio.so, interaction with data collection, 1

libcollector.h, 1

as part of C and C++ interface to collector, 1

as part of Java programming language interface to collector, 1

libcollector.so shared library

preloading, 1

using in your program, 1

libcpc.so, use of, 1

libfcollector.h, 1

libraries

collectorAPI.h, 1

interposition on, 1

libaio.so, 1

libcollector.so, 1, 2

libcpc.so, 1, 2

libthread.so, 1, 2, 3, 4

MPI, 1, 2

static linking, 1

stripped shared, and static functions, 1, 2

system, 1

limitations

descendant process data collection, 1

experiment group names, 1

experiment name, 1

Java profiling, 1

profiling interval value, 1

tcov, 1

limiting output in er_print utility, 1

limiting the experiment size, 1, 2

Lines tab, 1, 2

load objects

addresses of functions, 1

contents of, 1

defined, 1

listing selected, in er_print utility, 1

printing list in er_print utility, 1

selecting in er_print utility, 1

symbol tables, 1

writing layouts of, 1

lock file management

tcov, 1

tcov Enhanced, 1

loop optimizations, 1

LWPs

creation by threads library, 1

filtering, 1

listing selected, in er_print utility, 1

selecting in er_print utility, 1

M

man pages, accessing, 1

MANPATH environment variable, setting, 1

mapfile

generating, 1

generating with er_print utility, 1

memory allocations, 1

and leaks, 1

effects on data collection, 1

memory leaks, definition, 1

methods, See functions

metrics

attributed, 1

attributed, See attributed metrics

clock-based profiling, 1, 2

default, 1

defined, 1

effect of correlation, 1

exclusive, See exclusive metrics

function-list, See function-list metrics

hardware counter, attributing to instructions, 1

heap tracing, 1

inclusive and exclusive, 1, 2

inclusive, See inclusive metrics

interpreting for instructions, 1

interpreting for source lines, 1

memory allocation, 1

MPI tracing, 1

synchronization wait tracing, 1

threshold, 1

threshold, setting, 1

time precision, 1

timing, 1

microstates, 1

contribution to metrics, 1

switching, 1

microtasking library routines, 1

moving an experiment, 1, 2

MPI experiments

default name, 1

moving, 1

storage issues, 1

MPI programs

attaching to, 1

collecting data from, 1

collecting data with collect command, 1

collecting data with dbx, 1

experiment names, 1, 2, 3

experiment storage issues, 1

MPI tracing

collecting data in dbx, 1

collecting data with collect command, 1

data in profile packet, 1

functions traced, 1

interpretation of metrics, 1

metrics, 1

preloading the Collector library, 1

multithreaded applications

attaching the Collector to, 1

execution sequence, 1

multithreading

explicit, 1

parallelization directives, 1

N

naming an experiment, 1

networked disks, 1

nfs, 1

non-unique function names, 1

O

OpenMP parallelization, 1, 2

optimizations

common subexpression elimination, 1

program analysis affect of, 1

tail-call, 1

options, command-line, er_print utility, 1

outline functions, 1, 2

output file, in er_print utility, 1

overflow value, hardware counter, See hardware counter overflow value

overview data, printing in er_print utility, 1

P

parallel execution

call sequence, 1

directives, 1, 2

PATH environment variable, 1

setting, 1

path to files, 1

pausing data collection

for collect command, 1

from your program, 1

in dbx, 1

PCs

defined, 1

from PLT, 1

ordered list in er_print utility, 1

PCs tab, 1, 2

Performance Analyzer

Callers-Callees tab, 1, 2

command-line options, 1

DataLayout tab, 1

DataObjects tab, 1

defaults, 1

defined, 1

definition, 1

Disassembly tab, 1

Event tab, 1, 2

Experiments tab, 1

File menu, 1

Filter Data dialog box, 1

Find tool, 1

Functions tab, 1, 2

Help menu, 1

Leak tab, 1

LeakList tab, 1

Legend tab, 1, 2

Lines tab, 1, 2

PCs tab, 1, 2

recording an experiment, 1

Show/Hide Functions, 1

Source tab, 1

starting, 1

Statistics tab, 1

Summary tab, 1, 2

Timeline menu, 1

Timeline tab, 1, 2

View menu, 1

performance data, conversion into metrics, 1

performance metrics, See metrics

PLT (Program Linkage Table), 1

@plt function, 1

ppgsz command, 1

preloading libcollector.so, 1

printing the current path, 1

process address-space text and data regions, 1

prof

limitations, 1

output from, 1

summary, 1

using, 1

profile bucket, 1, 2, 3

profile packet

clock-based data, 1

hardware counter overflow data, 1

MPI tracing data, 1

size of, 1

synchronization wait tracing data, 1

profiled shared libraries, creating

for tcov, 1

for tcov Enhanced, 1

profiling interval

defined, 1

experiment size, effect on, 1

limitations on value, 1

setting with dbx collector command, 1

setting with the collect command, 1, 2

profiling, 1, 2

program counter (PC), 1, 2

program execution

call stacks described, 1

explicit multithreading, 1

OpenMP parallel, 1

shared objects and function calls, 1

signal handling, 1

single-threaded, 1

tail-call optimization, 1

traps, 1

Program Linkage Table (PLT), 1

program structure, mapping call stack addresses to, 1

R

raw hardware counters, 1, 2

recursive function calls

apparent, in OpenMP programs, 1

metric assignment to, 1

removing an experiment or experiment group, 1

restrictions, See limitations

resuming data collection

for collect command, 1

from your program, 1

in dbx, 1

S

sample filtering, 1

sample points, displayed in Timeline tab, 1

samples

circumstances of recording, 1

defined, 1

information contained in packet, 1

interval, See sampling interval

listing selected, in er_print utility, 1

manual recording in dbx, 1

manual recording with collect, 1

periodic recording in dbx, 1

periodic recording with collect command, 1

recording from your program, 1

recording when dbx stops a process, 1

selecting in er_print utility, 1

Sampling Collector, See Collector

sampling interval

defined, 1

setting in dbx, 1

setting with the collect command, 1

<Scalar> data object descriptor, 1

segmentation faults during data collection, 1

Set Data Presentation dialog box, Data Space Display, 1

setpath command, 1

setuid, use of, 1

shared objects, function calls between, 1

shell prompts, 1

Show/Hide Functions dialog box, 1

signal handlers

installed by Collector, 1, 2

user program, 1

signals

calls to handlers, 1

profiling, 1

profiling, 1, 2

use for manual sampling with collect command, 1

use for pause and resume with collect command, 1

single-threaded program execution, 1

sort order

callers-callees metrics, in er_print utility, 1

function list, specifying in er_print utility, 1

source code, annotated

cloned functions, 1

compiler commentary, 1

compiler-generated body functions, 1

description, 1, 2

discerning annotations from source, 1

for cloned functions, 1

from tcov, 1

index lines, 1

instructions without line numbers, 1

interpreting, 1

location of source files, 1

metric formats, 1

outline functions, 1

printing in er_print utility, 1

setting compiler commentary classes in er_print utility, 1

setting the highlighting threshold in er_print utility, 1

use of intermediate files, 1

viewing in Performance Analyzer, 1

viewing with er_src utility, 1

source code, compiler commentary, 1

source lines, ordered list in er_print utility, 1

Source tab, 1

stack frames

defined, 1

from trap handler, 1

reuse of in tail-call optimization, 1

static functions

duplicate names, 1

in stripped shared libraries, 1, 2

static linking, effect on data collection, 1

Statistics tab, 1

storage requirements, estimating for experiments, 1

subroutines, See functions

summary metrics

for a single function, printing in er_print utility, 1

for all functions, printing in er_print utility, 1

Summary tab, 1, 2

SUN_PROFDATA environment variable, 1

SUN_PROFDATA_DIR environment variable, 1

symbol tables, load-object, 1

synchronization delay events

data in profile packet, 1

defined, 1

metric defined, 1

synchronization delay tracing

default metrics, 1

synchronization wait time

defined, 1, 2

metric, 1, 2

with unbound threads, 1

synchronization wait tracing

collecting data in dbx, 1

collecting data with collect command, 1

data in profile packet, 1

defined, 1

metrics, 1

preloading the Collector library, 1

threshold, See threshold, synchronization wait tracing

wait time, 1, 2

syntax

er_archive utility, 1

er_export utility, 1

er_print utility, 1

er_src utility, 1

T

tail-call optimization, 1

tcov

annotated source code, 1

compiling a program for, 1

errors reported by, 1

limitations, 1

lock file management, 1

output, interpreting, 1

profiled shared libraries, creating, 1

summary, 1

using, 1

tcov Enhanced

advantages of, 1

compiling a program for, 1

lock file management, 1

profile bucket, 1, 2

profiled shared libraries, creating, 1

using, 1

TCOVDIR environment variable, 1, 2

thread filtering, 1

threads

bound and unbound, 1, 2

creation of, 1

library, 1, 2, 3, 4

listing selected, in er_print utility, 1

main, 1

scheduling of, 1, 2

selecting in er_print utility, 1

system, 1, 2

wait mode, 1

worker, 1, 2

threshold, highlighting

in annotated disassembly code, er_print utility, 1

in annotated source code, er_print utility, 1

threshold, synchronization wait tracing

calibration, 1

defined, 1

effect on collection overhead, 1

setting with dbx collector, 1

setting with the collect command, 1, 2

time metrics, precision, 1

Timeline menu, 1

Timeline tab, 1, 2

TLB (translation lookaside buffer) misses, 1, 2

<Total> data object descriptor, 1

<Total> function

comparing times with execution statistics, 1

described, 1

traps, 1

typographic conventions, 1

U

<Unknown> function

callers and callees, 1

mapping of PC to, 1

unwinding the call stack, 1

V

version information

for collect command, 1

for er_cp utility, 1

for er_mv utility, 1

for er_print utility, 1

for er_rm utility, 1

for er_src utility, 1

W

wait time, See synchronization wait time

well-known hardware counters, 1

wrapper functions, 1

X

-xdebugformat, setting debug symbol information format, 1

xhwcprof C compiler option, 1