IRIX Base Documentation 1998 November/IRIX 6.5.2 Base Documentation November 1998.img/usr/share/catman/u_man/cat1/speedshop.z/speedshop

Text File | 1998-10-30 | 40KB | 661 lines

SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



NNNNAAAAMMMMEEEE
     SpeedShop, speedshop - an integrated package of performance tools

DDDDEEEESSSSCCCCRRRRIIIIPPPPTTTTIIIIOOOONNNN
     SpeedShop is the generic name for an integrated package of performance
     tools to run performance experiments on executables, and to examine the
     results of those experiments.  It also supports starting a process, in
     such a way as to permit a debugger to attach to it, and it supports
     running Purify on executables.

     For Purify and for some experiments instrumentation is necessary; if so,
     it will be performed automatically, and the resulting instrumented
     executable run to generate the data.

SSSSUUUUPPPPPPPPOOOORRRRTTTTEEEEDDDD EEEEXXXXEEEECCCCUUUUTTTTAAAABBBBLLLLEEEESSSS
     SpeedShop works under IRIX 6.2, or later, and supports executables
     compiled with the IRIX 6.2 compilers (o32, n32 and 64), or with the
     MIPSPro 7.x compilers (n32 and 64).  SpeedShop supports C, C++, FORTRAN,
     ADA, and asm programs.  Programs must be built using shared libraries
     (DSOs); nonshared or stripped executables are not supported.

RRRREEEECCCCOOOORRRRDDDDIIIINNNNGGGG EEEEXXXXPPPPEEEERRRRIIIIMMMMEEEENNNNTTTTSSSS
     Experiments are recorded using the ssrun(1) command, as follows:
          ssssssssrrrruuuunnnn ----<_e_x_p_t_y_p_e> <_a._o_u_t-_n_a_m_e> <_a._o_u_t _a_r_g_u_m_e_n_t_s>
     where <_e_x_p_t_y_p_e> is one of the named experiments listed below.

     The result of an experiment is one or more files that are named by the
     following convention:
                    <_a._o_u_t-_n_a_m_e>.<_e_x_p_t_y_p_e>.<_c_o_d_e><_p_i_d>
     where <code> is:
     'm' for the master process created by _s_s_r_u_n;
     'p' for a process created by a call to _s_p_r_o_c();
     'f' for a process created by a call to _f_o_r_k();
     'e' for a process created by a call to _e_x_e_c();
     's' for a process created by a call to _s_y_s_t_e_m(); and
     'fe' for the _e_x_e_c'd process created by calls to _f_o_r_k() and _e_x_e_c()
     with environment variable _SPEEDSHOP_TRACE_FORK_TO_EXEC being set to False.

     To start the target process running, and leave it in a state to attach
     a debugger, add the ----hhhhaaaannnngggg flag:
          ssssssssrrrruuuunnnn ----hhhhaaaannnngggg ----<_e_x_p_t_y_p_e> <_a._o_u_t-_n_a_m_e> <_a._o_u_t _a_r_g_u_m_e_n_t_s>

     To get more detailed information about the run, add the ----vvvv
     flag:
          ssssssssrrrruuuunnnn ----vvvv ----<_e_x_p_t_y_p_e> <_a._o_u_t-_n_a_m_e> <_a._o_u_t _a_r_g_u_m_e_n_t_s>
               -or-
          ssssssssrrrruuuunnnn ----vvvv ----hhhhaaaannnngggg ----<_e_x_p_t_y_p_e> <_a._o_u_t-_n_a_m_e> <_a._o_u_t _a_r_g_u_m_e_n_t_s>

     To run Purify on an executable, use:
          ssssssssrrrruuuunnnn ----ppppuuuurrrriiiiffffyyyy <_a._o_u_t-_n_a_m_e> <_a._o_u_t _a_r_g_u_m_e_n_t_s>

     Purify and performance experiments are mutually exclusive.



                                                                        PPPPaaaaggggeeee 1111






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



     ssssssssrrrruuuunnnn may take additional arguments; see its man page for further
     information.

EEEEXXXXPPPPEEEERRRRIIIIMMMMEEEENNNNTTTT TTTTYYYYPPPPEEEESSSS
     The following experiment types, specified by <_e_x_p_t_y_p_e> above, are
     supported in the current release:

     uuuusssseeeerrrrttttiiiimmmmeeee aaaannnndddd ttttoooottttaaaallllttttiiiimmmmeeee
          uses statistical callstack profiling, based on process virtual time
          (including time spent when the system is running on behalf of the
          process) for usertime and wall clock time for totaltime, with a time
          sample interval of 30 milliseconds.
          NNNNooootttteeee:::: o32 executables must explicitly link with -_l_e_x_c for these
          experiments to work; program execution may show significant slowdown
          compared to the original executable; the stack unwind code sometimes
          fails to completely unwind the stack; consequently, caller
          attribution can not be done beyond the point of failure.

     [[[[ffff]]]]ppppccccssssaaaammmmpppp[[[[xxxx]]]]
          uses statistical PC sampling, using 16-bit bins, based on user and
          system time, with a sample interval of 10 milliseconds.  If the
          optional ffff prefix is specified, a sample interval of 1 millisecond
          will be used.  If the optional xxxx suffix is specified, a 32-bit bin
          size will be used.

     iiiiddddeeeeaaaallll
          uses basic-block counting, done by instrumenting the executable.

     ffffppppeeee  does tracing of all floating-point exceptions.

     iiiioooo   does tracing of various I/O system calls.

     On machines with hardware performance counters, (R10000 machines), the
     following additional types are supported:

     [[[[ffff]]]]ggggiiii____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the graduated-
          instruction counter, at an overflow interval of 32771.  If the
          optional ffff prefix is used, the overflow interval will be 6553.

     [[[[ffff]]]]ccccyyyy____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the cycle
          counter, at an overflow interval of 16411.  If the optional ffff prefix
          is used, the overflow interval will be 3779.

     [[[[ffff]]]]iiiicccc____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the primary
          instruction-cache miss counter, at an overflow interval of 2053.  If
          the optional ffff prefix is used, the overflow interval will be 419.






                                                                        PPPPaaaaggggeeee 2222






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



     [[[[ffff]]]]iiiisssscccc____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the secondary
          instruction-cache miss counter, at an overflow interval of 131.  If
          the optional ffff prefix is used, the overflow interval will be 29.

     [[[[ffff]]]]ddddcccc____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the primary
          data-cache miss counter, at an overflow interval of 2053.  If the
          optional ffff prefix is used, the overflow interval will be 419.

     [[[[ffff]]]]ddddsssscccc____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the secondary
          data-cache miss counter, at an overflow interval of 131.  If the
          optional ffff prefix is used, the overflow interval will be 29.

     [[[[ffff]]]]ttttllllbbbb____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the TLB miss
          counter, at an overflow interval of 257.  If the optional ffff prefix
          is used, the overflow interval will be 53.

     [[[[ffff]]]]ggggffffpppp____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the graduated
          floating-point instruction counter, at an overflow interval of
          32771.  If the optional ffff prefix is used, the overflow interval will
          be 6553.

     [[[[ffff]]]]ffffsssscccc____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the failed store
          conditionals counter, at an overflow interval of 2003.  If the
          optional ffff prefix is used, the overflow interval will be 401.

     pppprrrrooooffff____hhhhwwwwcccc
          uses statistical PC sampling, based on overflows of the counter
          specified by the environment variable _SPEEDSHOP_HWC_COUNTER_NUMBER,
          at an interval given by the environment variable
          _SPEEDSHOP_HWC_COUNTER_OVERFLOW.  Note that these environment
          variables can not be used to override the counter number or interval
          for the other defined experiments.  They are examined only when the
          pppprrrrooooffff____hhhhwwwwcccc experiment is specified.  The default counter is the
          primary instruction-cache miss counter and the default overflow
          interval is 2053.

     ggggiiii____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the graduated-instruction counter, at an
          overflow interval of 1000003.

     ccccyyyy____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the cycle counter, at an overflow interval of
          10000019.




                                                                        PPPPaaaaggggeeee 3333






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



     iiiicccc____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the primary instruction-cache-miss counter, at
          an overflow interval of 8009.

     iiiisssscccc____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the secondary instruction-cache-miss counter,
          at an overflow interval of 2003.

     ddddcccc____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the primary data-cache-miss counter, at an
          overflow interval of 8009.

     ddddsssscccc____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the secondary data-cache-miss counter, at an
          overflow interval of 2003.

     ttttllllbbbb____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the TLB miss counter, at an overflow interval
          of 2521.

     ggggffffpppp____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the graduated floating-point instruction
          counter, at an overflow interval of 10007.

     ffffsssscccc____hhhhwwwwccccttttiiiimmmmeeee
          profiles the cycle counter using statistical call-stack sampling,
          based on overflows of the failed store conditionals counter, at an
          overflow interval of 5003.

     pppprrrrooooffff____hhhhwwwwccccttttiiiimmmmeeee
          profiles the counter specified by the environment variable
          _SPEEDSHOP_HWC_COUNTER_PROF_NUMBER using statistical call-stack
          sampling, based on overflows of the counter specified by the
          environment variable _SPEEDSHOP_HWC_COUNTER_NUMBER, at an interval
          given by the environment variable _SPEEDSHOP_HWC_COUNTER_OVERFLOW.
          Note that these environment variables can not be used to override
          the counter numbers or interval for the other defined experiments.
          They are examined only when the pppprrrrooooffff____hhhhwwwwccccttttiiiimmmmeeee experiment is
          specified.  The default overflow and profling counter is the cycle
          counter and the default overflow interval is 10000019.

     One additional experiment type may be recorded, but no report generation
     for it is yet supported.  It is:






                                                                        PPPPaaaaggggeeee 4444






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



     hhhheeeeaaaapppp does tracing of all _m_a_l_l_o_c and _f_r_e_e, _e_t_c. calls, and also supports
          various options for debugging heap usage.

     Custom experiments will be supported in future releases.

RRRREEEEPPPPOOOORRRRTTTT GGGGEEEENNNNEEEERRRRAAAATTTTIIIIOOOONNNN
     Report generation is done through the prof(1) command:
          pppprrrrooooffff <_o_u_t_p_u_t _f_i_l_e> . . . <_o_u_t_p_u_t _f_i_l_e>
     It will add the data from all of the output files, and produce a listing
     which depends on the particular experiment type.  For all experiments, it
     will produce a list of functions, annotated with the appropriate metric.

     For [[[[ffff]]]]ppppccccssssaaaammmmpppp[[[[xxxx]]]], and the various ****____hhhhwwwwcccc experiments, the function list is
     annotated with the exclusive metric;  for the PC sampling experiments,
     the metric is exclusive time, for the various hardware counter profiling
     experiments the metric is exclusive counts.

     For iiiiddddeeeeaaaallll experiments, the function list is annotated with a cycle count
     and percentage, a cumulative percentage for that function and all others
     above it in the list, an estimated of idealized time, an instruction
     execution count, and a call count.  If the ----bbbb[[[[uuuutttttttteeeerrrrffffllllyyyy]]]] flag is added, a
     list of callers and callees of each function is also produced.

     For uuuusssseeeerrrrttttiiiimmmmeeee and ttttoooottttaaaallllttttiiiimmmmeeee and the various ****____hhhhwwwwccccttttiiiimmmmeeee experiments, the
     function list is annotated with percentage of time or counts for the
     function, the time in that function, and the time or counts in that
     function and its descendants, and a count of the number of callstacks
     containing that function.  If the ----bbbb[[[[uuuutttttttteeeerrrrffffllllyyyy]]]] flag is added, a list of
     callers and callees of each function is also produced.

     For ffffppppeeee experiments, the function list is annotated with the percentage
     of FPEs in that function, and counts for the function and its
     descendants.  If the ----bbbb[[[[uuuutttttttteeeerrrrffffllllyyyy]]]] flag is added, a list of callers and
     callees of each function is also produced.

     For iiiioooo experiments, the function list is annotated with the percentage of
     IO calls in that function, and counts for the function and its
     descendants.  If the ----bbbb[[[[uuuutttttttteeeerrrrffffllllyyyy]]]] flag is added, a list of callers and
     callees of each function is also produced.

     There are many additional options to _p_r_o_f; see the prof(1) man page for
     further details.

CCCCAAAALLLLIIIIPPPPEEEERRRR SSSSAAAAMMMMPPPPLLLLEEEESSSS
     In the current releases, caliper samples may be recorded, and the
     -calipers option to prof, will allow you to see the data for any
     caliper-setting.

     Caliper samples are supported in three different ways.  First, the user
     can explicitly link with the SpeedShop runtime, and call its API routine
     to record a caliper sample; second, the user can define a signal to be
     used to record a caliper sample, by specifying the environment variable



                                                                        PPPPaaaaggggeeee 5555






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



     _SPEEDSHOP_CALIPER_POINT_SIG and send the target the specified signal;
     third, a caliper-sample trap may be set in either _d_b_x, or the WorkShop
     debugger.  In the current debuggers, this is done by planting an stop
     trap (breakpoint), and, when the process stops, evaluating the
     expression:
               ssrt_caliper_point(0, 0)
     the evaluation of the expression always returns zero, but a side effect
     of the evaluation is the recording of the appropriate data.  After
     evaluation, process execution may be resumed.  See the ssapi(3) man page
     for further details.

UUUUSSSSEEEERRRR EEEENNNNVVVVIIIIRRRROOOONNNNMMMMEEEENNNNTTTT VVVVAAAARRRRIIIIAAAABBBBLLLLEEEE CCCCOOOONNNNTTTTRRRROOOOLLLLSSSS
     Various environment variables are normally used to control the operation
     of SpeedShop.  They are:

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____VVVVEEEERRRRBBBBOOOOSSSSEEEE
          causes a log of each program's operation to be written to stderr.
          If it is set to an empty string, only major events are logged; if it
          is set to a non-empty string, more detailed events are logged.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____SSSSIIIILLLLEEEENNNNTTTT
          if set, suppresses all output, other than fatal error messages from
          SpeedShop.  If both _SPEEDSHOP_VERBOSE and _SPEEDSHOP_SILENT are
          set, _SPEEDSHOP_SILENT wins.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____CCCCAAAALLLLIIIIPPPPEEEERRRR____PPPPOOOOIIIINNNNTTTT____SSSSIIIIGGGG <<<<ssssiiiiggggnnnnaaaallll----nnnnuuuummmmbbbbeeeerrrr>>>>
          if specified, gives a signal number to be used for recording a
          caliper-point in the experiment.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____PPPPOOOOLLLLLLLLPPPPOOOOIIIINNNNTTTT____CCCCAAAALLLLIIIIPPPPEEEERRRR____PPPPOOOOIIIINNNNTTTT <<<<ttttiiiimmmmeeeerrrr____ttttyyyyppppeeee>>>>,,,,<<<<ttttiiiimmmmeeeerrrr____iiiinnnntttteeeerrrrvvvvaaaallll>>>>
          if specified, defines the timer type and the timer interval (in
          secs) for pollpoint caliper points.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____OOOOUUUUTTTTPPPPUUUUTTTT____DDDDIIIIRRRREEEECCCCTTTTOOOORRRRYYYY
          if specified, the output data files and the instrumented binaries
          will be put in the named directory.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____OOOOUUUUTTTTPPPPUUUUTTTT____FFFFDDDD
          if specified, gives the number of the file descriptor to be used for
          writing the output file.  NNNNooootttteeee:::: this option is not supported in the
          current release.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____RRRREEEEUUUUSSSSEEEE____FFFFIIIILLLLEEEE____DDDDEEEESSSSCCCCRRRRIIIIPPPPTTTTOOOORRRRSSSS
          if set, opens and closes the file descriptors for the output files
          every time performance data is to be written. If the target program
          is using chdir(), then the _SPEEDSHOP_OUTPUT_DIRECTORY environment
          variable should also be set to the full pathname of the directory
          where the output files are to be put.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____OOOOUUUUTTTTPPPPUUUUTTTT____FFFFIIIILLLLEEEENNNNAAAAMMMMEEEE
          if specified, the given name will be used for the output file;  if
          _SPEEDSHOP_OUTPUT_DIRECTORY is also specified, it will be prepended



                                                                        PPPPaaaaggggeeee 6666






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



          to the name.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____HHHHWWWWCCCC____CCCCOOOOUUUUNNNNTTTTEEEERRRR____NNNNUUUUMMMMBBBBEEEERRRR
          specifies the overflow counter to be used for pppprrrrooooffff____hhhhwwwwcccc or
          pppprrrrooooffff____hhhhwwwwccccttttiiiimmmmeeee experiments.  Counters are numbered between 0 and 31,
          and are described in the MIPS R10000 Microprocessor User's Manual,
          Chapter 14.  Counter 0 counters are numbered 0-15, and counter 1
          counters are numbers 16-31.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____HHHHWWWWCCCC____CCCCOOOOUUUUNNNNTTTTEEEERRRR____OOOOVVVVEEEERRRRFFFFLLLLOOOOWWWW
          specifies the overflow value for the counter to be used in pppprrrrooooffff____hhhhwwwwcccc
          or pppprrrrooooffff____hhhhwwwwccccttttiiiimmmmeeee experiments.  The value chosen may be any number
          greater than 0.  Some choices may produce data that is not
          statistically random, but rather reflects a correlation between the
          overflow interval and a cyclic behavior in the application.  Users
          may want to do two or more runs with different overflow values.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____HHHHWWWWCCCC____CCCCOOOOUUUUNNNNTTTTEEEERRRR____PPPPRRRROOOOFFFF____NNNNUUUUMMMMBBBBEEEERRRR
          specifies the profiling counter to be used for pppprrrrooooffff____hhhhwwwwccccttttiiiimmmmeeee
          experiments.  Counters are numbered between 0 and 31, and are
          described in the MIPS R10000 Microprocessor User's Manual, Chapter
          14.  Counter 0 counters are numbered 0-15, and counter 1 counters
          are numbers 16-31.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____HHHHWWWWCCCC____CCCCOOOOUUUUNNNNTTTTEEEERRRR____SSSSIIIIGGGGNNNNAAAALLLL____NNNNUUUUMMMMBBBBEEEERRRR
          specifies the profiling signal to be used for pppprrrrooooffff____hhhhwwwwccccttttiiiimmmmeeee
          experiments.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____OOOOUUUUTTTTPPPPUUUUTTTT____NNNNOOOOCCCCOOOOMMMMPPPPRRRREEEESSSSSSSS
          if set, disables the compression of performance data.

     Other variables will be documented in the future releases.

PPPPRRRROOOOCCCCEEEESSSSSSSS TTTTRRRRAAAACCCCKKKKIIIINNNNGGGG EEEENNNNVVVVIIIIRRRROOOONNNNMMMMEEEENNNNTTTT VVVVAAAARRRRIIIIAAAABBBBLLLLEEEE CCCCOOOONNNNTTTTRRRROOOOLLLLSSSS
     Various environment variables may be used for controlling the treatment
     of processes spawned from the original target.  They are:

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____TTTTRRRRAAAACCCCEEEE____FFFFOOOORRRRKKKK {{{{TTTTrrrruuuueeee||||FFFFaaaallllsssseeee}}}}
          if True, specifies that processes spawned by calls to _f_o_r_k() will be
          monitored, if they do not call _e_x_e_c().  If they do call _e_x_e_c(), and
          _SPEEDSHOP_TRACE_FORK_TO_EXEC is not set to True, the data covering
          the time between the _f_o_r_k() and the _e_x_e_c() will be discarded.  It is
          True by default.  NNNNooootttteeee:::: in the current release, data will be
          recorded independent of whether the process calls _e_x_e_c() or not.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____TTTTRRRRAAAACCCCEEEE____FFFFOOOORRRRKKKK____TTTTOOOO____EEEEXXXXEEEECCCC {{{{TTTTrrrruuuueeee||||FFFFaaaallllsssseeee}}}}
          if True, specifies that process spawned by calls to _f_o_r_k() will be
          monitored, even if they also call _e_x_e_c().  It is False by default.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____TTTTRRRRAAAACCCCEEEE____EEEEXXXXEEEECCCC {{{{TTTTrrrruuuueeee||||FFFFaaaallllsssseeee}}}}
          if True, specifies that process spawned by calls to any of the
          various flavors of _e_x_e_c() will be monitored.  It is True by default.



                                                                        PPPPaaaaggggeeee 7777






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____TTTTRRRRAAAACCCCEEEE____SSSSPPPPRRRROOOOCCCC {{{{TTTTrrrruuuueeee||||FFFFaaaallllsssseeee}}}}
          if True, specifies that process spawned by calls to _s_p_r_o_c() will be
          monitored.  It is True by default.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____TTTTRRRRAAAACCCCEEEE____SSSSYYYYSSSSTTTTEEEEMMMM {{{{TTTTrrrruuuueeee||||FFFFaaaallllsssseeee}}}}
          if True, specifies that process spawned by calls to _s_y_s_t_e_m() will be
          monitored.  It is False by default.

EEEEXXXXPPPPEEEERRRRTTTT----MMMMOOOODDDDEEEE EEEENNNNVVVVIIIIRRRROOOONNNNMMMMEEEENNNNTTTT VVVVAAAARRRRIIIIAAAABBBBLLLLEEEE CCCCOOOONNNNTTTTRRRROOOOLLLLSSSS
     Various additional environment variables may be used for debugging and
     finer control of the operation of SpeedShop.  They are:

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____SSSSAAAAMMMMPPPPLLLLIIIINNNNGGGG____MMMMOOOODDDDEEEE
          for PC-sampling and hardware-counter profiling, if set to 1, will
          generate data for the base executable only.  If it is not set, or
          set to anything other than 1, data is generated for the executable
          and all DSOs it uses.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____IIIINNNNIIIITTTT____DDDDEEEEFFFFEEEERRRRRRRREEEEDDDD____SSSSIIIIGGGG <<<<ssssiiiiggggnnnnaaaallll----nnnnuuuummmmbbbbeeeerrrr>>>>
          If specified, initialization of the experiment will not be performed
          when the target process starts, but rather will be delayed until the
          specified signal is sent to the process.   A handler for the given
          signal will be installed when the process starts, and it is the
          users responsibility to ensure that it is not overridden by the
          target code.  If the process terminates before the signal is
          received, no data will be recorded.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____SSSSHHHHUUUUTTTTDDDDOOOOWWWWNNNN____SSSSIIIIGGGG <<<<ssssiiiiggggnnnnaaaallll----nnnnuuuummmmbbbbeeeerrrr>>>>
          If specified, termination of the experiment will not be performed
          when the target process exits, but rather will happen when the
          specified signal is sent to the process.   A handler for the given
          signal will be installed when the process starts, and it is the
          users responsibility to ensure that it is not overridden by the
          target code.  If the process terminates before the signal is
          received, data is recorded normally.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____EEEEXXXXPPPPEEEERRRRIIIIMMMMEEEENNNNTTTT____TTTTYYYYPPPPEEEE
          passes the name of the experiment to the runtime.  It is normally
          set by ssrun(1), but may be overwritten.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____MMMMAAAARRRRCCCCHHHHIIIINNNNGGGG____OOOORRRRDDDDEEEERRRRSSSS
          passes the marching orders of the experiment to the runtime.  It is
          normally set by ssrun(1) from the experiment type, but may be
          overwritten.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____SSSSBBBBRRRRKKKK____BBBBUUUUFFFFFFFFEEEERRRR____LLLLEEEENNNNGGGGTTTTHHHH
          defines the segment grow size for the internal _m_a_l_l_o_c arena used.
          This arena is completely separate from the user's arena, and it
          usually grows in default segments of size 0x100000.






                                                                        PPPPaaaaggggeeee 8888






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____SSSSBBBBRRRRKKKK____BBBBUUUUFFFFFFFFEEEERRRR____AAAADDDDDDDDRRRR
          defines the preferred starting address to be used for the internal
          _m_a_l_l_o_c arena. This option has to used with extreme care since it
          might result in memory regions overlap.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____FFFFIIIILLLLEEEE____BBBBUUUUFFFFFFFFEEEERRRR____LLLLEEEENNNNGGGGTTTTHHHH
          defines the size of the buffer used for writing the experiment
          files.  The default length is 64KB.  The buffer is only used for
          writing many small records to the file (as in tracing experiments);
          large records are written directly, to avoid the buffering overhead.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____DDDDEEEEBBBBUUUUGGGG____NNNNOOOO____SSSSIIIIGGGG____TTTTRRRRAAAAPPPPSSSS
          if set, disables the normal setting of signal handlers for all fatal
          and exit signals.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____DDDDEEEEBBBBUUUUGGGG____NNNNOOOO____SSSSTTTTAAAACCCCKKKK____UUUUNNNNWWWWIIIINNNNDDDD
          if set, suppresses the stack unwind as done in uuuusssseeeerrrrttttiiiimmmmeeee, ttttoooottttaaaallllttttiiiimmmmeeee,
          or other callstack-based experiments.  The option is used as a
          workaround for various unwind bugs in _l_i_b_e_x_c.

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____RRRRLLLLDDDD
          defines the full pathname to rld to be used and enables rld
          profiling (for pcsamp and hwc experiments only).

     ____SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP____IIIINNNNSSSSTTTTRRRR____AAAARRRRGGGGSSSS
          defines additional instrumentation arguments.

IIIINNNNSSSSTTTTRRRRUUUUMMMMEEEENNNNTTTTAAAATTTTIIIIOOOONNNN
     Instrumentation is done with the pixie(1) command, invoked automatically
     by ssrun(1), and, if necessary for DSOs that are opened during a run, by
     the runtime library.  Users normally would not invoke pixie(1) directly.

     In the current release, instrumented executables and DSOs appear in the
     current working directory.  In a future release, the DSOs will be cached.

SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP AAAAPPPPIIII RRRROOOOUUUUTTTTIIIINNNNEEEESSSS
     The SpeedShop API routines are defined in the include file
     "SpeedShop/api.h", installed in /_u_s_r/_i_n_c_l_u_d_e.  It defines three entry
     points, described int the SpeedShop API man page, ssapi(3).

SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP CCCCUUUUSSSSTTTTOOOOMMMM DDDDAAAATTTTAAAA CCCCAAAAPPPPTTTTUUUURRRREEEE RRRROOOOUUUUTTTTIIIINNNNEEEESSSS
     The SpeedShop facility for users to add custom data capture routines is
     not available in the current release.

MMMMIIIISSSSCCCCEEEELLLLLLLLAAAANNNNEEEEOOOOUUUUSSSS UUUUTTTTIIIILLLLIIIITTTTYYYY PPPPRRRROOOOGGGGRRRRAAAAMMMMSSSS
     Several utility routines are provided, in addition to the main
     functionality in SpeedShop.  They are:

     ssssssssccccoooorrrrdddd
          and ssssssssoooorrrrddddeeeerrrr are used to generate cord feedback files from recorded
          data.  sssssssswwwwsssseeeexxxxttttrrrr is a script to produce the working-set files used
          for cord computations.  See their respective man pages for more



                                                                        PPPPaaaaggggeeee 9999






SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))                                                      SSSSPPPPEEEEEEEEDDDDSSSSHHHHOOOOPPPP((((1111))))



          information.

     ssssssssuuuussssaaaaggggeeee
          is a variant of time(1) that prints more information about the
          resource usage of a program.  See ssusage(1) for more information.

     ssssssssdddduuuummmmpppp
          is a program which produces a formatted dump of a SpeedShop
          experiment.

     ssssqqqquuuueeeeeeeezzzzeeee
          is a program which allocates and locks down memory, making the
          system behave as if it had less physical memory that it really does.
          See squeeze(1) for more information.

     tttthhhhrrrraaaasssshhhh
          is a program that allocates memory, and then touches all of the
          pages, in order to force other pages out of the system's physical
          memory.  See thrash(1) for more information.

     ffffbbbbdddduuuummmmpppp
          is a program that dumps out the contents of the compiler feedback
          files produced by the ----ffffeeeeeeeeddddbbbbaaaacccckkkk option to prof(1).  See fpdump(1)
          and prof(1) for more information.

CCCCAAAAVVVVEEEEAAAATTTTSSSS
     Depending on the revision of the R10000 CPUs there is a difference in the
     interpretation of counter number 14 (``Virtual coherency condition'' for
     parts before revision 3.1 or ``ALU/FPU completion cycles'' for parts at
     revision 3.1 or later).  There are also some subtle differences in the
     semantics of some of the counters.

     In systems with a homogeneous deployment of CPUs at the same revision,
     speedshop will adjust the reported information accordingly.

     For systems with a mixed deployment of CPU revisions including some
     before 3.1 and some at or after 3.1, the interpretation of counter 14 is
     undefined, and there may be some slight inaccuracies due to aggregation
     of counters with different semantics across all CPUs.

     Identification of the revisions for all CPUs can be made using the -v
     option to hinv(1).

SSSSEEEEEEEE AAAALLLLSSSSOOOO
     ssrun(1), ssdump(1), prof(1), pixie(1), fbdump(1), ssusage(1),
     squeeze(1), thrash(1), malloc_ss(3), fpe_ss(3), io_ss(3), ssapi(3),
     perfex(1), r10k_counters(5), sscord(1), ssorder(1), sswsextr(1)








                                                                       PPPPaaaaggggeeee 11110000