-----------------------------------------------------------------------------------
Fujitsu PRIMEPOWER flags/tunables description (Jun.30 2003)
(Each section is sorted in case insensitive, alphabetical order)
Table of Contents
[1] Fujitsu Parallelnavi 1.0.2 compiler flag description
[2] Fujitsu Parallelnavi 2.1 compiler flag description
[3] Sun C, C++ and Fortran Sun ONE Studio 8 flag description
[4] Environment Variables
[5] Kernel Parameters (/etc/system)
[6] Configuration file for large page manager (/etc/opt/FJSVpnrm/lpg.conf)
[7] Commands for feedback control
-----------------------------------------------------------------------------------
[1] Fujitsu Parallelnavi 1.0.2 compiler flag description (Jun.30 2003)
Compiler options Remark
-----------------------------------------------------------------------------------
-dy/-dn
Specifies dynamic(-dy) or static(-dn) linkage of
libraries. -dy is the default unless -Kfast_GP=n (n>=3) is
specified and -Klargepage is not specified, in that case
-dn is the default.
-Kbcopy Convert memory copy loop to memmove or memcpy function.
-Kcfunc This uses high speed mathematical functions and library
functions (malloc,calloc,realloc,free) prepared by this
compilation system.
-Kfast_GP[={0|1|2|3|4|5}]
This performs optimization for SPARC64 GP series.
0: This performs optimization suitable for SPARC64 GP.
1: This generates multiply and add instruction in
addition to -Kfast_GP=0. (default)
2: This performs reordering of expression evaluation in
addition to -Kfast_GP=1.
3: (C and C++ compiler)
This generates crossfile optimization, and
inter-procedural optimization in addition to -Kfast_GP=2.
(Fortran compiler)
This performs loop restructuring optimization in addition
to -Kfast_GP=2.
4: (C and C++ compiler only)
This generates advanced branch optimization in
addition to -Kfast_GP=3.
5: (C and C++ compiler only)
This generates global instruction scheduling
optimization suit for scientific application in
addition to -Kfast_GP=3.
-KGREG The global registers g2 through g7 are subject to register
allocation in the compile stage.
-Klargepage Specifies to generate executable program which utilizes
Parallelnavi largepage facility.
This option expands the page size of virtual memory
from original 8KB to 4MB.
-Knounroll Prevents loop unrolling optimizations.
-Kpg Generates instructions to produce a profile file for
subsequent optimization (global instruction scheduling
etc.).
-Kpopt This option specifies the optimization data pointed to by
pointers using a limited interpretation that the areas
referred by pointers are only referred by pointers.
-Kpu[=file] This performs optimization (global instruction scheduling,
etc.) using program runtime profile information obtained
by specifying -Kpg option.
-Kprefetch[={1|2|3|4}] Generate prefetch instruction correspond to each
prefetch level.
1: Basic level prefetch for array elements only
inner-most loop.
2: In addition to the -Kprefetch=1, generates the
prefetch instruction for array elements within the
loop pre-header which access the first iteration in
the loop.
3: In addition to the -Kprefetch=2, when the stride of
access for array elements are larger than cache line
size, compiler generates prefetch instruction for
each cache line size access.
4: Maximum level for generating prefetch instruction.
In addition to -Kprefetch=3, compiler generates the
prefetch instruction for array elements which access
in the outer loop.
-Kstaticclump When this option is specified, all variables in the
source file which are declared as static or global
(except large arrays) are compiled together
(renamed to avoid conflicts if necessary) into one
big structure and can therefore be addressed
with the base address of the structure and an index
from this base address.
-Kuse_rodata This option specifies whether string constant, floating
point constant and initialization value of aggregate type
local storage variable are allocated to read-only data
section.
-Kxi=N Inline expansion, instead of function calls, is performed.
Expanded function is selected by result of profiler. N is
the percentage that means increased object size.
-O[level] Specifies the optimization level.
0: No optimization.
1: Basic optimization.
2: Loop unrolling in addition to -O1.
3: Global instruction scheduling and restructuring of
nested loop in addition to -O2.
4: Enhanced optimization of loop restructuring
rather than -O3.
-----------------------------------------------------------------------------------
[2] Fujitsu Parallelnavi 2.1 compiler flag description (Jun.30 2003)
Compiler options Remark
-----------------------------------------------------------------------------------
-Am Required if a source file contains modules which will
be referenced by USE statements in other source files
or if a source file contains USE statements that reference
modules in another source file.
-dy/-dn Specifies dynamic(-dy) or static(-dn) linkage of
libraries. -dy is the default unless -Kfast_GP=n (n>=3)
is specified and -Klargepage is not specified, in that
case -dn is the default.
-f omitmsg Set the level of diagnostic messages output and inhibit
specific messages.
omitmsg is one of i, w, or s, and/or a list of msgnum.
i: All messages are output, this is the default.
w: i level messages are not output.
s: i and w level messages are not output.
msgnum: Message number msgnum is inhibited. msgnum must
be an i or w level message.
-Fixed Specifies that Fortran source programs are written in
fixed source form.
-fs Do not print any warnings or diagnostic messages other
than fatal errors.
-Kalignc[=N] Adjust entry of global data alignment at n-byte boundary.
N can be specified from 1 to 32768.
-Kalignl[=N] Adjust entry of local data alignment at n-byte boundary.
N can be specified from 1 to 32768.
-Karraypad_const[=N] Insert padding elements after each row of an array whose
size is declared with constants for efficient use of cache.
-Kauto Local variables (without an initial value or the SAVE
attribute) are allocated on the runtime stack. Their
values are lost when the procedure ends.
-Kcfunc This uses high speed mathematical functions and library
functions (malloc,calloc,realloc,free) prepared by this
compilation system.
-Kcommonpad[=N] Insert padding elements in common blocks for efficient
use of cache. N can be specified from 4 to 4096.
-Kcrossfile This option specifies crossfile optimization.
If program consists of several files, the compiler refers
these files at one time, and analyzes data dependency and
control relation across these files.
-Kfast_GP2[={0|1|2}] This performs optimization for SPARC64 GP2 series.
0: This performs optimization suitable for SPARC64 GP2.
1: This generates multiply and add instruction in
addition to -Kfast_GP2=0. (default)
2: This performs reordering of expression evaluation in
addition to -Kfast_GP2=1.
-KFMADD This option specifies use of the combined multiply-
add/subtract floating-point instructions.
-Kfrecipro This option specifies to convert a floating point
division into multiplication by the reciprocal.
-Kfuse Fuses neighboring loops.
-KGREG_SYSTEM The global registers g5 through g7 are subject to register
allocation in the compile stage.
-Kgs Performs global instruction scheduling.
-Kilfunc This option replaces several and double precision
mathematical functions,sin,cos,log10,log and exp with
compiler builtin functions.
-Klargepage Specifies to generate executable program which utilizes
Parallelnavi largepage facility.
-KNOFMADD This option suppresses use of the combined multiply-
add/subtract floating-point instructions.
-Knoprefetch Suppresses use the prefetch instruction.
-Knounroll Prevents loop unrolling optimizations.
-Knovfunc Suppresses to change the intrinsic function
(including power operation) to a multi-operation function.
-Kpreex This option specifies the optimization by moving the
evaluation of invariant expressions beyond branch.
-Kpopt This option specifies the optimization data pointed to by
pointers using a limited interpretation that the areas
referred by pointers are only referred by pointers.
-Kpg Generates instructions to produce a profile file for
subsequent optimization (global instruction scheduling
etc.).
-Kprefetch[={1|2|3|4}] Generate prefetch instruction correspond to each prefetch
level.
1: Basic level prefetch for array elements only
inner-most loop.
2: In addition to the -Kprefetch=1, generates the
prefetch instruction for array elements within the
loop pre-header which access the first iteration in
the loop.
3: In addition to the -Kprefetch=2, when the stride of
access for array elements are larger than cache line
size, compiler generates prefetch instruction for
each cache line size access.
4: Maximum level for generating prefetch instruction.
In addition to -Kprefetch=3, compiler generates the
prefetch instruction for array elements which access
in the outer loop.
-Kprefetch_cache_level=[1/2/3]
LEVEL-1: Generate prefetch instructions in order
for the data to reside in the primary cache.
LEVEL-2: Generate prefetch instructions in order
for the data to reside only in the secondary cache.
LEVEL-3: Generate both LEVEL-1 and -2 prefetch
instructions.
-Kprefetch_infer For data prefetch control, in cases where
the stride of array accesses is not clear from
static analysis of the source files,
the compiler is told to use its internal
heuristics for the addresses that have been
determined by the compiler as prefetch
addresses.
-Kprefetch_iteration=N Generate the prefetch instruction of the data which is
referred after N iterations.
-Kprefetch_line=N Generate the prefetch instruction to get the data located
N times bytes in a line of the primary data cache ahead of
the address a neighboring load or store instruction points.
-Kprefetch_line_L2=N Same to -Kprefetch_line=N, except the data reside only
in the secondary cache.
-Kpreload Moves load instructions across branches.
-Kpreschedule_length[=N]
When -O5 is used, the instruction scheduler
works twice, before and after the register allocation,
which are named pre-pass and post-pass
scheduling respectively. -Kpreschedule_length[=N]
can control how aggressively pre-pass scheduling works.
The unit is the upper limit of the distance an
instruction can move from its original place.
-Kpu[=file] This performs optimization (global instruction scheduling,
etc.) using program runtime profile information obtained
by specifying -Kpg option.
-Kunroll[=N] Performs loop unrolling. N means upper limit of unrolling
expansion number, whose value should be from 2 to 9999.
-O[level] Specifies the optimization level.
0: No optimization.
1: Basic optimization.
2: Loop unrolling in addition to -O1.
3: Global instruction scheduling and restructuring of
nested loop in addition to -O2.
4: Enhanced optimization of loop restructuring rather
than -O3.
5: Creates an object program by applying further
optimizations of register allocation in addition
to -O4.
-SSL2 The whole set of routines from SSL II, SSL II Thread-
Parallel Capabilities and BLAS/LAPACK becomes part of
link-edit libraries.
-x- Inline expansion, instead of function calls, is performed
for all functions defined in the C source code.
-x stm_no Applying optimization for inline expansion of user-defined
external procedure having fewer than specified number of
execution statements in the stm_no arguments.
-x dir=directory_name Performs inline expansion of procedures defined in the files
under the directory specified and in the file currently
being compiled.
-----------------------------------------------------------------------------------
[3] Sun C, C++ and Fortran Sun ONE Studio 8 flag description (Jun.30 2003)
Compiler options Remark
-----------------------------------------------------------------------------------
-array_pad_rows,<n> Enable padding of arrays by n.
(Fortran)
cc Invoke the Sun ONE Studio 8 Compiler C
(C compiler)
CC Invoke the Sun ONE Studio 8 Compiler C++
(C++ compiler)
-crit Enable optimization of critical control paths
(optimizer)
-dalign Assume data is naturally aligned.
(C, C++, Fortran)
-Dalloca=__builtin_alloca
(Portability flag) Portability switch, used for 176.gcc:
allow use of compiler's internal builtin alloca.
-depend Synonym for -xdepend.
(Fortran)
-DHOST_WORDS_BIG_ENDIAN Portability switch, used for 176.gcc:
(Portability flag) controls how bytes are numbered within a word.
-D__MATHERR_ERRNO_DONTCARE
(C) Allows the compiler to assume that your code
does not rely on setting of the errno variable.
-DSPEC_CPU2000_SOLARIS Portability switch, used for 253.perlbmk:
(Portability flag) selects header files and code paths compatible
with Solaris.
-DSUN Portability switch, used for 186.crafty:
(Portability flag) selects header files and code paths
compatible with Solaris.
-DSYS_HAS_CALLOC_PROTO Portability switch, used for 254.gap:
(Portability flag) allows use of the designated prototype.
-DSYS_HAS_IOCTL_PROTO Portability switch, used for 254.gap:
(Portability flag) allows use of the designated prototype.
-DSYS_HAS_SIGNAL_PROTO Portability switch, used for 254.gap:
(Portability flag) allows use of the designated prototype.
-DSYS_HAS_TIME_PROTO Portability switch, used for 254.gap:
(Portability flag) allows use of the designated prototype.
-DSYS_IS_USG Portability switch, used for 254.gap:
(Portability flag) selects code compatible with USG-based systems.
-e Portability switch, used for 178.galgel:
(Portability, Fortran) allows source lines to be up to 132 characters long.
f90 Invoke the Sun ONE Studio 8 Compiler Fortran 90
(Fortran compiler)
-fast A convenience option, this switch selects the
(C) following switches that are defined elsewhere
in this page:
-D__MATHERR_ERRNO_DONTCARE
-dalign
-fns
-fsimple=2
-fsingle
-ftrap=%none
-xalias_level=basic
-xbuiltin=%all
-xdepend
-xlibmil
-xO5
-xprefetch=auto,explicit
-xtarget=native
-fast A convenience option, this switch selects the
(C++) following switches that are defined elsewhere
in this page:
-dalign
-fns
-fsimple=2
-ftrap=%none
-xbuiltin=%all
-xlibmil
-xlibmopt
-xO5
-xtarget=native
-fast A convenience option, this switch selects the
(Fortran) following switches that are defined elsewhere
in this page:
-dalign
-depend
-fns
-fsimple=2
-ftrap=common
-xlibmil
-xlibmopt
-xO5
-xpad=local
-xprefetch=auto,explicit
-xtarget=native
-xvector=yes
-fixed Portability switch, used for 178.galgel:
(Portability, Fortran) assume fixed-format source input.
-fns Selects faster (but nonstandard) handling of
(C, C++, Fortran) floating point arithmetic exceptions and
gradual underflow.
-fsimple=<n> Controls simplifying assumptions for
(C, C++, Fortran) floating point arithmetic:
-fsimple=0 Permits no simplifying assumptions.
Preserves strict IEEE 754 conformance.
-fsimple=1 Allows the optimizer to assume:
The IEEE 754 default rounding/trapping
modes do not change after process initialization.
Computations producing no visible result other
than potential floating-point exceptions may
be deleted. Computations with Infinity or NaNs
as operands need not propagate NaNs to their
results. For example, x*0 may be replaced by 0.
Computations do not depend on sign of zero.
-fsimple=2 Permits more aggressive floating point
optimizations that may cause programs to
produce different numeric results due to
changes in rounding. Even with -fsimple=2,
the optimizer still is not permitted to
introduce a floating point exception in a
program that otherwise produces none.
-fsingle Evaluate float expressions as single precision.
(C)
-ftrap=common Sets the IEEE 754 trapping mode to common exceptions
(C, C++, Fortran) (invalid, division by zero, and overflow).
-ftrap=%none Turns off all IEEE 754 trapping modes.
(C, C++, Fortran)
-library=iostream Portability switch, used for 252.eon:
(Portability, C++) allow use of the classic iostream library.
-ll2amm Include a library containing chip specific
(linker) memory routines.
-lm Include the math library.
(linker)
-lmopt Include the optimized math library. This option
(linker) usually generates faster code, but may produce
slightly different results. Usually these results
will differ only in the last bit.
-lprism32 (linker) Library to enable Intimate Shared Memory (ISM)
(linker) (4MB page) usage.
-noex Do not allow C++ exceptions. A throw specification
(C++) on a function is accepted but ignored; the compiler
does not generate exception code.
-O A synomym for -xO3.
(Fortran)
-Qoption <phase> <flags>
Pass flags along to compiler phase:
f90comp Fortran first pass
iropt Global optimizer
cg Code Genetator
-Qoption cg <flags> See -Wc,<flags> below. (The code generator
(code generator) phase is addressed via -Qoption cg in
Fortran and C++; and via -Wc in C.)
-Qoption cg -Qeps:enabled=1
(code generator) See -Wc,-Qeps:enabled=1
-Qoption cg -Qeps:ws=<n>
(code generator) See -Wc,-Qeps:ws=<n>
-Qoption cg -Qgsched-T<n>
(code generator) See -Wc,-Qgsched-T<n>
-Qoption cg -Qgsched-trace_late=1
(code generator) See -Wc,-Qgsched-trace_late=1
-Qoption iropt <flags> See -W2,<flags> below. (The optimizer can
(optimizer) be addressed either via Qoption iropt in
Fortran and C++; or via -W2 in C.)
-Qoption iropt -Addint:sf=<n>
(optimizer) When considering whether to interchange loops, set memory
store operation weight to n. A higher value of n indicates
a greater performance cost for stores.
-Qoption iropt -Ainline[:cp=<n>][:cs=<n>][:inc=<n>][:irs=<n>][:mi][:recursion=1]
(optimizer) See -W2,[:cp=<n>][:cs=<n>][:inc=<n>][:irs=<n>][:mi][:recursion=1]
-Qoption iropt -Apf:pdl=1
(optimizer) Do prefetching for one-level indirect memory references.
-Qoption iropt -Atile:skewp[:b<n>]
(optimizer) Perform loop tiling which is enabled by loop skewing.
Loop skewing is a transformation that transforms a
non-fully interchangeable loop nest to a fully
interchangeable loop nest. The optional b<n> sets the
tiling block size to n.
-Qoption iropt -Aujam:inner=g
(optimizer) Increase the probability that small-trip-count inner
loops will be fully unrolled.
-Qoption iropt -Mt<n> See -W2,-Mt<n>
RM_SOURCES = lapak.f90 This option allows building the benchmark 178.galgel
(SPEC tools) without its copy of the lapak sources; instead,
the lapak entry points in the sunperf library are used.
rm -rf ./feedback.profile ./SunWS_cache
(Unix) Remove any profile feedback information from previous runs.
-stackvar Allocate routine local variables on the stack.
(Fortran)
submit=echo 'pbind -b...' > dobmk; sh dobmk
(SPEC tools, Unix) When running multiple copies of benchmarks, the SPEC
config file feature submit is sometimes used to
cause individual jobs to be bound to specific processors:
submit= causes the SPEC tools to use this line when
submitting jobs.
echo ...> dobmk causes the generated commands to be written to a
file, namely dobmk.
pbind -b causes this copy's processes to be bound to the CPU
specified by the expression that follows it. See the
config file used in the submission for the exact
syntax, which tends to be cumbersome because of the
need to carefully quote parts of the expression.
When all expressions are evaluated, each CPU ends up
with exactly one copy of each benchmark. The pbind
expression may include:
$SPECUSERNUM: the SPEC tools-assigned number for
this copy of the benchmark.
psrinfo: find out what processors are available
grep off-line: search the psrinfo output for
information regarding off-line cpus
awk...print \$1: Pick out the line corresponding to
this copy of the benchmark and use
the CPU number mentioned at the
start of this line.
sh dobmk actually runs the benchmark.
-W<phase>,<flags> Pass flags along to compiler phase (2=optimizer,
c=code genetator).
-W2,-Abcopy Increase the probability that the compiler will
(optimizer) perform memcpy/memset transformations.
-W2,-Abopt Enable aggressive optimizations of all branches.
(optimizer)
-W2,-Aheap Allows the compiler to recognize malloc-like
(optimizer) memory allocation functions.
-W2,-Ainline[:cp=<n>][:cs=<n>][:inc=<n>][:irs=<n>][:mi][:recursion=1]
(optimizer) Control the optimizer's loop inliner:
cp=<n> The minimum call site frequency counter in order to
consider a routine for inlining.
cs=<n> Set inline callee size limit to n. The unit roughly
corresponds to the number of instructions.
inc=<n> The inliner is allowed to increase the size of the
program by up to n%.
irs=<n> Allow routines to increase by up to n. The unit
roughly corresponds to the number of instructions.
mi Perform maximum inlining (without considering code
size increase).
recursion=1 Allow routines that are called recursively to still
be eligible for inlining.
-W2,-crit Enable optimization of critical control paths.
(optimizer)
-W2,-Amemopt:arrayloc Reconstruct array subscripts during memory
(optimizer) allocation merging and data layout program
transformation.
-W2,-Apf:llist=<n>:noinnerllist
(optimizer) Do speculative prefetching for link-list data structures:
llist=<n> perform prefetching n iterations ahead
noinnerllist do not attempt for innermost loops.
-W2,-Ashort_ldst Convert multiple short memory operations into
(optimizer) single long memory operations.
-W2,-Aunroll Enables outer-loop unrolling.
(optimizer)
-W2,-Mr<n> Maximum code increase due to inlining is limited
(optimizer) to n triples.
-W2,-Ms<n> Maximum level of recursive inlining.
(optimizer)
-W2,-Mt<n> The maximum size of a routine body eligible for
(optimizer) inlining is limited to n triples.
-W2,-reroll=1 Turns on loop rerolling.
(optimizer)
-W2,-whole Do whole program optimizations.
(optimizer)
-Wc,-Qdepgraph-early_cross_call=1
(code generator) There are several scheduling passes in the compiler.
This option allows early passes to move instructions
across call instructions.
-Wc,-Qeps:do_spec_load=1
(code generator) Allow generating speculative load during EPS.
-Wc,-Qeps:enabled=1 Use enhanced pipeline scheduling(EPS)
(code generator) and selective scheduling algorithms for
instruction scheduling.
-Wc,-Qeps:rp_filtering_margin=100
(code generator) Turn off register pressure heuristics in EPS.
-Wc,-Qeps:ws=<n> Set the EPS window size, that is, the number
(code generator) of instructions it will consider across all
paths when trying to find independent
instructions to schedule a parallel group.
Larger values may result in better run time,
at the cost of increased compile time.
-Wc,-Qgsched-T<n> Sets the aggressiveness of the trace
(code generator) formation, where n is 4, 5, or 6.
The higher the value of n, the lower
the branch probability needed to include
a basic block in a trace.
-Wc,-Qgsched-trace_late=1
(code generator) Turns on the late trace scheduler.
-Wc,-Qicache-chbab=1 Turn on optimization to reduce branch
(code generator) after branch penalty: nops will be inserted
to prevent one branch from occupying
the delay slot of another branch.
-Wc,-Qipa:valueprediction
(code generator) Use profile feedback data to predict values and attempt
to generate faster code along these control paths,
even at the expense of possibly slower code along paths
leading to different values. Correct code is generated
for all paths.
-Wc,-Qiselect-funcalign=<n>
(code generator) Do function entry alignment at n-byte boundaries.
-Wc,-Qiselect-sw_pf_tbl_th=<n>
(code generator) Peels the most frequent test branches/cases off a switch
until the branch probability reaches less than 1/n.
This is effective only when profile feedback is used.
-Wc,-Qlp=<n>[-av=<n>][-t=<n>][-fa=<n>][-fl=<n>]
(code generator) Control irregular loop prefetching:
lp=<n> Turns the module on (1) or off (0)
(default is on for F90; off for C/C++)
-av=<n> Sets the prefetch look ahead distance, in bytes.
Default is 256.
-t=<n> Sets the number of attempts at prefetching. If not
specified, t=2 if -xprefetch_level=3 has been set;
otherwise, defaults to t=1.
-fa=<n> 1=Force user settings to override internally computed values.
-fl=<n> 1=Force the optimization to be turned on for all languages.
-Wc,-Qms_pipe+intdivusefp
(code generator) In pipelined loops, use floating point divide
instructions for signed integer division.
-Wc,-Qms_pipe+prefolim=<n>
(code generator) Set number of outstanding prefetches
in pipelined loops to <n>
-Wc,-Qms_pipe+unoovf Assert (to the pipeliner) that unsigned
(code generator) int computations will not overflow.
-Wc,-Qms_pipe-prefst Turn off prefetching for stores in the pipeliner.
(code generator)
-Wc,-Qms_pipe-pref Turn off prefetching within modulo scheduling.
(code generator)
-Wc,-Qpeep-Sh0 Reduce the probability that the compiler will hoist sethi
(code generator) instructions out of loops.
-xalias_level=[basic|std|strong]
(C) Allows the compiler to perform type-based alias analysis
at the specified alias level:
basic Assume that memory references that involve
different C basic types do not alias each other.
std Assume aliasing rules described in the ISO 1999 C
standard.
strong In addition to the restrictions at the std level,
assume that pointers of type char * are used only
to access an object of type char; and assume that
there are no interior pointers.
-xalias_level=compatible
(C++) Allows the compiler to assume that
layout-incompatible types are not aliased.
-xarch=<a> Limit the set of instructions the compiler may use
(C, C++, Fortran) to generic, generic64, native, native64, v7, v8a,
v8, v8plus, v8plusa, v8plusb, v9, v9a, v9b.
Typical settings include:
UltraSPARC-II, 32-bit mode: v8plusa
UltraSPARC-II, 64-bit mode: v9a
UltraSPARC-III, 32-bit mode: v8plusb
UltraSPARC-III, 64-bit mode: v9b
For more information, see the Fortran User's Guide
at docs.sun.com
-xbuiltin=%all Substitute intrinsic functions or inline system
(C, C++) functions where profitable for performance.
-xchip=<c> Specifies the target processor for use by the
(C, C++, Fortran) optimizer. c must be one of: generic, generic64,
native, native64, old, super, super2, micro, micro2,
hyper, hyper2, powerup, ultra, ultra2, ultra2i,
ultra3, ultra3cu, 386, 486, pentium, pentium_pro,
603, 604.
-xcache=<c> Defines the cache properties for use by the
(C, C++, Fortran) optimizer. c must be one of the following:
native (set parameters for the host environment)
* s1/l1/a1
* s1/l1/a1:s2/l2/a2
* s1/l1/a1:s2/l2/a2:s3/l3/a3
The si/li/ai are defined as follows:
si The size of the data cache
at level i, in kilobytes.
li The line size of the data cache
at level i, in bytes.
ai The associativety of the data cache
at level i.
-xdepend Analyze loops for inter-iteration data dependencies,
(C, Fortran) and do loop restructuring.
-xinline= Turn off inlining.
(C, C++, Fortran)
-xipo[=2] Perform optimizations across all object files in the
(C, C++, Fortran) link step:
0=off
1=on
2=performs whole-program detection and analysis
-xlibmil Use inline expansion for math library, libm.
(C, C++, Fortran)
-xlibmopt Select the optimized math library.
(C++, Fortran)
-xlic_lib=sunperf Link with Sun supplied licensed sunperf library.
(C, C++, Fortran)
-xlinkopt Perform link-time optimizations, such as branch
(C, C++, Fortran) optimization and cache coloring.
-xO<n> Specify optimization level n:
(C, C++, Fortran)
-xO1 Does only basic local optimizations (peephole).
-xO2 Do basic local and global optimizations, such as
induction variable elimination, common
subexpression elimination, constant propogation,
register allocation, and basic block merging.
-xO3 Add global optimizations at the function level,
loop unrolling, and software pipelining.
-xO4 Adds automatic inlining of functions in the
same file.
-xO5 Uses optmization algorithms that may take
significantly more compilation time or that
do not have as high a probability of improving
execution time, such as speculative code motion.
-xpad=common[:<n>] If multiple same-sized arrays are placed in common,
(Fortran) insert padding between them for better use of cache.
n specifies the amount of padding to apply, in units
that are the same size as the array elements. If no
parameter is specified then the compiler selects one
automatically.
-xpad=local Pad local variables, for better use of cache.
(Fortran)
-xprefetch=auto,explicit
(C, C++, Fortran) Allow generation of prefetch instructions. -xprefetch and
-xprefetch=yes is a synonym for -xprefetch=auto,explicit.
-xprefetch=latx:<n> Adjust the compiler's assumptions about prefetch latency
(C, C++, Fortran) by the specified factor. Typically values in the range of
0.5 to 2.0 will be useful. A lower number might indicate
that data will usually be cache resident; a higher number
might indicate a relatively larger gap between the
processor speed and the memory speed (compared to the
assumptions built into the compiler).
-xprefetch=no%auto Turn off prefetch instruction generation.
(C, C++, Fortran)
-xprefetch_level=<n> Control the level of searching that the compiler does
(C, C++, Fortran) for prefetch opportunities by setting n to 1, 2, or 3,
where higher numbers mean to do more searching.
The default is 2.
-xprofile=collect:./feedback
(C, C++, Fortran) Collect profile data for feedback-directed optimization,
and store it in a sub directory of the current directory,
named ./feedback.
-xprofile=use:./feedback
(C, C++, Fortran) Use data collected for profile feedback. Look for it in
a subdirectory of the current directory, named ./feedback.
-xregs=syst Allows use of the system reserved registers %g6 and
(C, C++, Fortran) %g7, and %g5 if not already allowed by -xarch value.
-xrestrict Treat pointer-valued function parameters as
(C) restricted pointers.
-xsafe=mem Enables the use of non-faulting loads when used in
(C, C++, Fortran) conjunction with -xarch=v8plus. Assumes that no memory
based traps will occur.
-xsfpconst Represents unsuffixed floating-point constants
(C, C++, Fortran) as single precision.
-xtarget=[system_name] Selects options appropriate for the system where
(C, C++, Fortran) the compile is taking place, including architecture,
chip, and cache sizes. (These can also be controlled
separately, via -xarch, -xchip, and -xcache, respectively.)
-xunroll=n Specifies whether or not the compiler optimizes
(C, C++, Fortran) (unrolls) loops. n is a positive integer. When n is
1, it is a command and the compiler unrolls no loops.
When n is greater than 1, -xunroll=n merely suggests
to the compiler that it unroll loops n times.
-xvector Allow the compiler to transform math library calls within
(C, Fortran) loops into calls to the vector math library.
-----------------------------------------------------------------------------------
[4] Environment Variables
Flag Remark
-----------------------------------------------------------------------------------
LD_LIBRARY_PATH=<p> Specify the locations to resolve dynamic link dependencies.
PRISM_HEAP=<n> Set the heap size limit for large pages.
PRISM_MODE=2 Large page mode: Attempt to put text, data and heap
all into large pages.
ulimit -s unlimited Allow stack size to grow without limit.
-----------------------------------------------------------------------------------
[5] Kernel Parameters (/etc/system)
System Tunable Remark
-----------------------------------------------------------------------------------
autoup The frequency of file system sync operations.
consistent_coloring Controls the page coloring policy. It can be set to
one of the following:
0 (default) dynamic (uses various vaddr bits)
1 static (virtual=paddr)
shmsys:shminfo_shmmax Maximum size of system V shared memory segment that
can be created.
shmsys:shminfo_shmmin Minimum size of system V shared memory segment that
can be created.
shmsys:shminfo_shmmni System wide limit on number of shared memory
segments that can be created.
shmsys:shminfo_shmseg Limit on the number of shared memory segments that
any one process can create.
tune_t_fsflushr The number of seconds between fsflush invocations for
checking dirty memory.
-----------------------------------------------------------------------------------
[6] Configuration file for large page manager (/etc/opt/FJSVpnrm/lpg.conf)
Tunable Remark
-----------------------------------------------------------------------------------
JOB=size [unit] Specify the large page memory resource size for
in-job processes. "unit" can be T (terra byte),
G (giga byte), or M (mega byte) after size.
LIMITPOLICY=[job|proc] Define the memory allocation/limitation type.
Default is job.
job Limits for each job in Node.
proc Limits for each process resource set.
SHMSEGSIZE=size[unit] Size of large page segment. "unit" can be M for
mega-byte and G for giga-byte.
TSS=size[unit] Size of total memory, to be used for large page
segments. At start of the system, this amount of
memory is reserved and initialized. "unit" can be M
for mega-byte and G for giga-byte.
--------------------------------------------------------------------------------
[7] Commands for feedback control
Command Remark
--------------------------------------------------------------------------------
Paralllenavi compiler:
fdo_pre0 = rm -rf `pwd`*.f.d
fdo_pre0 = rm -rf `pwd`*.fbk
remove the profile data generated at the last
feedback-optimized compilation.
Sun Studio 8 compiler:
fdo_pre0 = rm -rf `pwd`/..feedback.profile
fdo_pre0 = rm -rf `pwd`/SunWS_cache
remove the profile data generated at the last
feedback-optimized compilation.
--------------------------------------------------------------------------------