CC
[-c]
[-C]
[-D macro[=def]]
[-E]
[-g]
[-G level]
[-h arg]
[-I incldir]
[-K trap=opt[,opt]...]
[-l libfile]
[-L ldir]
[-M]
[-nostdinc]
[-o outfile]
[-O level]
[-P]
[-S]
[-U macro]
[-V]
[-W phase,"opt..."]
[-X npes]
[-Y phase,dirname]
[-#] [-##] [-###]
files ...
IMPLEMENTATION
Cray Linux Environment (CLE)
DESCRIPTION
The CC command invokes the Cray C++ compiler. The compiler conforms to
the ISO/IEC 14882:2003 standard, with some exceptions. The exceptions
are noted in the Cray C and C++ Reference Manual.
Typically, the CC command processes the source files named on the
command line, generates a binary object file (sourcefile.o), links the
binary object file, and generates an executable file (named a.out by
default). Other files used and created by the C++ compiler are
discussed under the FILES section.
For a more detailed description of the CC command, see the Cray C and
C++ Reference Manual. Information contained in this man page may
differ from the reference manual. Where the information differs, this
man page supersedes the information contained in the reference manual.
Conflicting Options
If you specify conflicting options, the option specified last on the
command line overrides the previously specified option. Exceptions to
this rule are noted in the individual option descriptions.
Conflicts between Options and #pragma Directives
Most #pragma directives override corresponding command-line options.
Specifies strict conformance to the ISO C++ standard. The
-h noconform option specifies partial conformance to the
standard. The -h const_string_literals, -h dep_name,
-h exceptions, and -h parse_templates options are enabled by
the -h conform option in Cray C++. The default is -h
noconform.
-h cfront Causes the Cray C++ compiler to accept constructs that were
accepted by previous cfront-based compilers (such as Cray
C++ 1.0) but which are not accepted in the C++ standard. The
-h anachronisms option is implied when -h cfront is
specified.
-h [no]parse_templates
Allows existing code that defines templates using previous
versions of the Cray Standard Template Library (STL) (before
Programming Environment 3.6) to compile successfully with
the -h conform option. Consequently, this allows you to
compile existing code without having to use the Cray C++
STL. To do this, use the noparse_templates option. Also, the
compiler defaults to this mode when the -h dep_name option
is used. To have the compiler verify that your code uses the
Cray C++ STL properly, use the parse_templates option. The
default is -h noparse_templates.
-h [no]dep_name
Enables or disables dependent name processing (that is, the
separate lookup of names in templates when the template is
parsed and when it is instantiated). The -h dep_name option
cannot be used with the -h noparse_templates option. The
default is -h nodep_name.
-h [no]exceptions
Enables support for exception handling. The -h noexceptions
option issues an error whenever an exception construct, a
try block, a throw expression, or a throw specification on a
function declaration is encountered. The -h exceptions
option is enabled by -h conform.
The default is -h exceptions; however, if the CRAYOLDCPPLIB
environment variable is set to a nonzero value, the default
is -h noexceptions.
-h [no]anachronisms
Disables or enables anachronisms in Cray C++. This option is
overridden by -h conform. The default is -h noanachronisms.
-h [no]new_for_init
Enables the new scoping rules for a declaration in a for-
init-statement. This means that the new standard-conforming
rules are in effect; the entire for statement is wrapped in
its own implicitly generated scope. The -h new_for_init
.
.
} // scope of i ends here for -h nonew_for_init
Default: -h new_for_init
-h [no]const_string_literals
Controls whether string literals are const (as required by
the standard) or non-const (as was true in earlier versions
of the C++ language). The default is -h
noconst_string_literals.
-h [no]gnu
Enables the compiler to recognize the GCC C++ Language
Extensions. The default is -h nognu.
For descriptions of the GCC C and C++ language extensions,
see http://gnu.gcc.org/onlinedocs (link to URL
http://gnu.gcc.org/onlinedocs) .
GCC C++ Language Extensions
------------------------------------------------------------------------
GCC C++ Extensions Description
------------------------------------------------------------------------
Min and Max C++ minimum and maximum operators
Restricted Pointers C99 restricted pointers and
references
Backwards Compatibility Compatibilities with earlier
definitions of C++
Strong Using A using-directive with __attribute
((strong))
Explicit template specializations Attributes may be used on explicit
template specializations
------------------------------------------------------------------------
Table 1. Virtual Function Options
-h forcevtbl
Forces the definition of virtual function tables in cases
where the heuristic methods used by the compiler to decide
on definition of virtual function tables provide no
guidance. The virtual function table for a class is defined
in a compilation if the compilation contains a definition of
the first non-inline, non-pure virtual function of the
class. For classes that contain no such function, the
default behavior is to define the virtual function table
(but to define it as a local static entity). The
does not have a C++ compiler. The use of this option
requires that the main function must be compiled by C++, and
the static constructor/destructor function must be included
in the link. With these precautions, mixed object files
(files with .o suffixes) from C and C++ compilations can be
linked into executables by using the linker command instead
of the CC command.
-h restrict=args
Globally tells the compiler to treat certain classes of
pointers as restricted pointers. You can use this option to
enhance optimizations (this includes vectorization).
Classes of affected pointers are determined by the value
contained in args, as follows:
--------------------------------------------------------------
args Description
--------------------------------------------------------------
a All pointers to object and incomplete types are
to be considered restricted pointers, regardless
of where they appear in the source code. This
includes pointers in class, struct, and union
declarations, type casts, function prototypes,
and so on.
f All function parameters that are pointers to
objects or incomplete types can be treated as
restricted pointers.
t (Cray C++ All parameters that are this pointers can be
only) treated as restricted pointers.
--------------------------------------------------------------
Caution:
Do not specify restrict=a if, during execution of any
function, an object is modified and that object is
referenced through either two different pointers or
through the declared name of the object and a pointer.
Undefined behavior may result.
Do not specify restrict=f if, during execution of any
function, an object is modified and that object is
referenced through either two different pointer
function parameters or through the declared name of the
object and a pointer function parameter. Undefined
behavior may result.
Do not specify restrict=t if, during execution of any
function, an object is modified and that object is
The arguments make assertions about your program that,
if incorrect, can introduce undefined behavior. You
should not use -h restrict=a if, during the execution
of any function, an object is modified and that object
is referenced through either of the following:
· Two different pointers
· The declared name of the object and a pointer
The -h restrict=f and -h restrict=t options are subject
to the analogous restriction, with "function parameter
pointer" replacing "pointer."
-h [no]calchars
Allows the use of the $ character in identifier names. This
option is useful for porting codes in which identifiers
include this character. With -h nocalchars, this character
is not allowed in identifier names.
The default is -h nocalchars.
Caution:
Use this option with extreme care, because identifiers
with this character are within CNL name space and are
included in many library identifiers, internal compiler
labels, objects, and functions. You must prevent
conflicts between any of these uses, current or future,
and identifier declarations or references in your code;
any such conflict is an error.
-h [no]signedshifts
Affects the result of the right shift operator. For the
expression e1 >> e2 where e1 has a signed type, when
-h signedshifts is in effect, the vacated bits are filled
with the sign bit of e1. When -h nosignedshifts is in
effect, the vacated bits are filled with zeros, identical to
the behavior when e1 has an unsigned type.
The default is -h nosignedshifts.
General Optimization Options
-h [no]add_paren
Forces the compiler to evaluate selected associative
operations (+,-,*) from left to right if the result type is
float or complex. Left to right evaluation is not required
by the language standards, but some applications may expect
it.
The default is -h noadd_paren.
Controls automatic prefetch optimization. Does not affect
loop_info [no]prefetch directive.
Default: autoprefetch.
-h [no]autothread
Enables or disables automatic threading. The default is -h
noautothread.
-h display_opt
Displays the current optimization settings for this
compilation.
-h [no]dwarf
Controls whether DWARF debugging information is generated
during compilation. The default is -h dwarf.
-h flex_mp=level
Controls the aggressiveness of optimizations which may
affect floating point and complex repeatability when
application requirements require identical results when
varying the number of ranks or threads. The default is -h
flex_mp=default.
The values for level are:
------------------------------------------------------------------------
level Description
------------------------------------------------------------------------
intolerant Has the highest probability of repeatable results, but
also has the highest performance penalty.
conservative Uses more aggressive optimization and yields higher
performance than intolerant, but results may not be
sufficiently repeatable for some applications.
default Uses more aggressive optimization and yields higher
performance than conservative, but results may not be
sufficiently repeatable for some applications.
tolerant Uses most aggressive optimization and yields highest
performance, but results may not be sufficiently
repeatable for some applications.
------------------------------------------------------------------------
-h fusionn
Controls loop fusion and changes the assertiveness of the
fusion pragma. Loop fusion can improve the performance of
loops, although in rare cases it may degrade performance.
The n argument allows you to turn loop fusion on or off and
determine where fusion should occur.
fusion pragma.
2 Attempt to fuse all loops (includes array syntax
implied loops), except those marked with the
nofusion pragma.
--------------------------------------------------------------
-h [no]intrinsics
Allows the use of intrinsic hardware functions, which allow
direct access to some hardware instructions or generate
inline code for some functions. This option has no effect on
specially handled library functions.
The default is -h intrinsics.
See the Cray C and C++ Reference Manual for a complete list
of hardware intrinsic functions.
-h [no]keep_frame_pointer
Retain call stack information back to main entry point for
CrayPat performance sampling.
The default is -h nokeep_frame_pointer.
-h list=opt
Allows you to create listings and control their formats. The
listings are written to source_file_name_without_suffix.lst.
The values for opt are:
--------------------------------------------------------------
opt Description
--------------------------------------------------------------
a Use all list options;
source_file_name_without_suffix.lst includes
summary report, options report, and source
listing.
d Decompiles (translates) the intermediate
representation of the compiler into listings that
resemble the format of the source code. This is
performed twice, resulting in two output files,
at different points during the optimization
process. You can use these files to examine the
restructuring and optimization changes made by
the compiler, which can lead to insights about
changes you can make to your source code to
improve its performance.
The compiler produces two decompilation listing
files with these extensions per specified source
file: .opt and .cg. The compiler generates the
architecture of the system is helpful to
understanding this listing.
The .opt and .cg files are intended as a tool for
performance analysis and are not valid source
code. The format and contents of the files can be
expected to change from release to release.
e Expand include files.
Using this option may result in a very large
listing file. All system include files are also
expanded.
i Intersperse optimization messages within the
source listing rather than at the end.
m Create loopmark listing;
source_file_name_without_suffix.lst includes
summary report and source listing.
s Create a complete source listing (include files
not expanded).
T Retains file.T after processing rather than
deleting it.
--------------------------------------------------------------
-h [no]msgs
Causes the compiler to write optimization messages to
stderr.
When the -h msgs option is in effect, you may request that a
listing be produced so that you can see the optimization
messages in the listing. For information about obtaining
listings, see -h list=opt.
The default is -h nomsgs.
-h [no]negmsgs
Causes the compiler to generate messages to stderr that
indicate why optimizations such as vectorization or inlining
did not occur in a given instance.
The -h negmsgs option enables the -h msgs option. The -h
list=a option enables the -h negmsgs option.
The default is -h nonegmsgs.
-h [no]omp_trace
Turns the insertion of the CrayPat OpenMP tracing calls on
and off.
The default is -h noomp_trace; tracing is off.
-h [no]func_trace
For use only with CrayPat. If this option is specified, the
-h [no]overindex
Declares that there are array subscripts that index a
dimension of an array that is outside the declared bounds of
that array. The -h nooverindex option declares that there
are no array subscripts that index a dimension of an array
that is outside the declared bounds of that array.
The default is -h nooverindex.
-h [no]pattern
Globally enables or disables pattern matching. Pattern
matching is on by default.
When the compiler recognizes certain patterns in the source
code, it replaces the construct with a call to an optimized
library routine. A loop or statement that has been pattern
matched and replaced with a call to a library routine is
indicated with an A in the loopmark listing.
Note: Pattern matching is not always worthwhile. If there
is a small amount of work in the pattern-matched construct,
the call overhead may outweigh the time saved by using the
optimized library routine. When compiling using the default
optimization settings, the compiler attempts to determine
whether each given candidate for pattern matching will in
fact yield improved performance.
-h pl=program_library
Create and use a persistent repository of compiler
information specified by program_library. When used with -h
wp, this option provides application-wide, cross-file,
automatic inlining. See -h wp.
The program_library repository is implemented as a directory
and the information contained in program library is built up
with each compiler invocation. Any compilation that does not
have the -hpl option will not add information to this
repository.
Because of the persistence of program_library, it is the
user's responsibility to manage it. For example, rm -r
program_library might be added to the make clean target in
an application makefile. Because program_library is a
directory, use rm -r to remove it.
If an application makefile works by creating files in
multiple directories during a single build, the
program_library should be an absolute path, otherwise
multiple and incomplete program library repositories will be
created. For example, avoid -hpl=./PL.1 and use
-hpl=/fullpath/builddir/PL.1 instead.
The values for n are:
--------------------------------------------------------------
n Description
--------------------------------------------------------------
0 No autothreading or OMP threading.
1 No parallel region expansion, no loop
restructuring for OMP loops, no optimization
across OMP constructs.
2 Parallel region expansion, limited loop
restructuring, optimization across OMP
constructs.
3 Reduction results may not be repeatable. Loop
restructuring, including modifying iteration
space for static schedules (breaking standard
compliance).
--------------------------------------------------------------
-h unrolln
Globally controls loop unrolling and changes the
assertiveness of the unroll pragma. By default, the compiler
attempts to unroll all loops, unless the nounroll pragma is
specified for a loop. Generally, unrolling loops increases
single processor performance at the cost of increased
compile time and code size.
The n argument allows you to turn loop unrolling on or off
and specify where unrolling should occur. It also affects
the assertiveness of the unroll pragma.
The default is -h unroll2.
The values for n are:
--------------------------------------------------------------
n Description
--------------------------------------------------------------
0 No unrolling (ignore all unroll pragmas and do
not attempt to unroll other loops).
1 Attempt to unroll loops that are marked by the
unroll pragma.
2 Unroll loops when performance is expected to
improve. Loops marked with the unroll or nounroll
pragma override automatic unrolling.
--------------------------------------------------------------
The options -h pl=program_library and -h wp should be
specified on all compiler invocations and on the compiler
link invocation. Since -h wp delays the compiler
optimization step until link time, -c compiles will take
less time and the link step will take longer. Normally, this
is just a time shift from one build phase to another with
roughly the same overall compile time. In some cases
increased inlining may cause an increase in overall compile
time. Using -h wp allows the compiler backend to be invoked
in parallel during a build. Setting the environment variable
NPROC controls the number of concurrent compiler backend
invocations and this parallelism may reduce overall compile
time.
-O level Specifies the optimization level for a group of compiler
features. Specifying -O with no argument is the same as not
specifying the -O level option; this syntax is supported for
compatibility with other vendors.
The level values 0, 1, 2, and 3 enable you to specify
increasing general levels of optimization.
The -O 1, -O 2, and -O 3 specifications do not directly
correspond to the numeric optimization levels for scalar
optimization and vectorization. For example, specifying -O 3
does not necessarily enable scalar3 and vector3. Cray
reserves the right to alter the specific optimizations
performed at these levels from release to release. You can
use the -e o option to display the optimization options used
during compilation.
The valid level values are:
level Optimization Provided
-O 0 Disables all optimizations including floating
point optimizations. Implies -h fp0.
-O 1, -O 2, -O 3
Default: 2.
See the Cray C and C++ Reference Manual for the -O and -h
equivalent values.
Automatic Cache Management Options
-h [no]align_arrays
Controls padding of arrays in static data. By default, some
statically allocated arrays are aligned and padded for
better cache behavior. Common block data is not affected.
Default: align_arrays
1 Conservative automatic cache management.
Characteristics include moderate compile time.
Symbols are placed in the cache when the
possibility of cache reuse exists and the
predicted cache footprint of the symbol in
isolation is small enough to experience the
reuse.
2 Moderately aggressive automatic cache management.
Characteristics include moderate compile time.
Symbols are placed in the cache when the
possibility of cache reuse exists and the
predicted state of the cache model is such that
the symbol will experience the reuse.
3 Aggressive automatic cache management.
Characteristics include potentially high compile
time. Symbols are placed in the cache when the
possibility of cache reuse exists and the
allocation of the symbol to the cache is
predicted to increase the number of cache hits.
--------------------------------------------------------------
For more information on automatic cache management, see the
Cray C and C++ Reference Manual.
Vector Optimization Options
-h vectorn
Specifies the level of automatic vectorizing to be
performed. Vectorization results in dramatic performance
improvements with a small increase in object code size.
Vectorization directives are unaffected by this option.
The default is -h vector2.
The values of n are:
--------------------------------------------------------------
n Description
--------------------------------------------------------------
0 No automatic vectorization. Characteristics
include low compile time and small compile size.
This option is compatible with all scalar
optimization levels.
1 Specifies conservative vectorization.
Characteristics include moderate compile time and
size.
The -h vector1 option is compatible with
-h scalar1, -h scalar2, and -h scalar3.
2 Specifies moderate vectorization. Characteristics
include moderate compile time and size. Loop
targets for inline expansion include all the procedures
within the input file to the compilation.
--------------------------------------------------------------
Inlining
level Description
--------------------------------------------------------------
0 All interprocedural analysis and optimizations
disabled. All inlining and cloning compiler
directives are ignored.
1 Directive inlining. Inlining is attempted for
call sites and routines that are under the
control of an inlining compiler directive.
Cloning disabled and cloning directives are
ignored.
2 Inlining. Inline a call site to an arbitrary
depth as long as the expansion does not exceed
some compiler-determined threshold. The call site
must flatten for any expansion to occur. The call
site is said to "flatten" when there are no calls
present in the expanded code. The call site must
reside within the body of a loop and the entire
loop body must flatten. A loop body is said to
"flatten" when all call sites within the body of
the loop are flattened.
Cloning disabled and cloning directives are
ignored.
3 Constant actual argument inlining and tiny
routine inlining. Default level for inlining.
This includes levels 1 and 2, plus any call site
that contains a constant actual argument.
Additionally, any call nest (regardless of
location) that is below some small compiler-
determined threshold will be inlined provided
that call nest completely flattens.
Cloning disabled and cloning directives are
ignored.
4 Aggressive inlining. This includes levels 1, 2,
and 3, plus a call site does not have to reside
in a loop body to inline nor does the call site
have to necessarily flatten.
Cloning disabled and cloning directives are
ignored.
5 Cloning. Includes levels 1, 2, 3, 4, plus routine
cloning is attempted if inlining fails at a given
call site. Cloning directives are enabled.
--------------------------------------------------------------
The default is -h ipa3.
Note: The routines in source are not actually linked with
the final program. They are simply templates for the
inliner. To have a routine contained in source linked with
the program, you must include it in an input file to the
compilation.
Use one or more of the following objects in the source
argument:
C++ source files
The routines in C++ source files are candidates
for inline expansion and must contain error-free
code.
dir A directory that contains any of the C file types.
For a description of combined inlining, see the Cray C and
C++ Reference Manual.
Scalar Optimization Options
-h [no]interchange
Allows the compiler to attempt to interchange all loops, a
technique that is used to gain performance by having the
compiler swap an inner loop with an outer loop. The compiler
attempts the interchange only if the interchange will
increase performance. Loop interchange is performed only at
scalar optimization level 2 or higher.
The -h nointerchange option prevents the compiler from
attempting to interchange any loops. To disable interchange
of loops individually, use the #pragma _CRI nointerchange
directive.
The default is -h interchange.
-h scalarn
Specifies the level of automatic scalar optimization to be
performed. Scalar optimization directives are unaffected by
this option.
The default is -h scalar2.
The values for n are:
--------------------------------------------------------------
n Description
--------------------------------------------------------------
0 Minimal automatic scalar optimization. The
-h matherror=errno and -h zeroinc options are
implied by -h scalar0.
-h [no]zeroinc
Improves run time performance by causing the compiler to
assume that constant increment variables (CIVs) in loops are
not incremented by expressions with a value of 0.
This option causes the compiler to assume that some constant
increment variables (CIVs) in loops might be incremented by
0 for each pass through the loop, preventing generation of
optimized code.
For example, in a loop with index i, the expression expr in
the statement i += expr can evaluate to 0. This rarely
happens in actual code. -h zeroinc is the safer and slower
option. This option is affected by the -h scalarn option.
The default is -h nozeroinc.
Math Options
-h fpn Allows you to control the level of floating-point and
complex arithmetic optimizations. The n argument controls
the level of allowable optimization; 0 gives the compiler
minimum freedom to optimize floating-point and complex
operations , while 4 gives it maximum freedom. The higher
the level, the lesser the floating-point operations conform
to the IEEE standard.
This option is useful for code using algorithms that are
unstable but optimizable.
Generally, this is the behavior and usage for each -h fp
level:
· The -h fp0 causes your program's executable code to
conform more closely to the IEEE floating-point standard
than the default mode (-h fp2). When you specify this
level, many identity optimizations are disabled,
vectorization of floating-point and complex reductions
are disabled, executable code is slower than higher
floating-point optimization levels.
Note: Use the -h fp0 option only when your code
pushes the limits of IEEE accuracy or requires
strong IEEE standard conformance.
· The -h fp1 option performs various generally safe, non-
conforming IEEE optimizations, such as folding a == a to
true, where a is a floating point object. At this level,
a scaled complex divide mechanism is enabled that
increases the range of complex values that can be handled
without producing an underflow, and rewrite of division
into multiplication by reciprocal is inhibited.
You should only use -h fp4 if your application uses
algorithms which are tolerant of reduced precision.
The Floating-point Optimization Levels table compares the
various optimization levels of the -h fp option The table
lists some of the optimizations performed; the compiler may
perform other optimizations not listed.
Floating-point Optimization Levels
--------------------------------------------------------------------------
fp2
Optimization Type fp0 fp1 (default) fp3 fp4
--------------------------------------------------------------------------
Complex divisions Accurate Accurate Fast Fast Fast
and slower and slower
Exponentiation None None When Always Always
rewrite beneficial
Strength reduction None None Fast Fast Fast
Rewrite division as None None Yes Aggressive Aggressive
reciprocal equivalent
( x/y -> x * 1.0/y)
Floating point Slow Fast Fast Fast Fast
reductions
Safety Maximum High High Moderate Low
Expression factoring None Yes Yes Yes Yes
Expression tree None None Yes Yes Yes
balancing
Precision Best Very High High Good Acceptable
--------------------------------------------------------------------------
-h matherror=method
Specifies the method of error processing used if a standard
math function encounters an error. The method argument can
have one of the following values:
--------------------------------------------------------------
method Description
--------------------------------------------------------------
abort If an error is detected, errno is not set.
Instead, a message is issued and the program
aborts. An exception may be raised.
errno If an error is detected, errno is set, and the
math function returns to the caller. This method
is implied by the -h conform, -h scalar0, -O0,
-Gn, and -g options.
Table 3. -G level Definitions
--------------------------------------------------------------------------
level Optimization Breakpoints allowed on Debugging Execution speed
--------------------------------------------------------------------------
-Gf Full Function entry and exit Limited Best
-Gp Partial Block boundaries Better Better
-Gn None Every executable Best Limited
statement
-Gfast Full Every executable Best: Best
statement requires
fast-track
debugger
--------------------------------------------------------------------------
Better debugging information comes at the cost of inhibiting
certain optimization techniques, so choose the option that
best fits the debugging needs of any particular source file
in an application.
The -g option is equivalent to -Gn. The -g option is
included for compatibility with earlier versions of the
compiler and many other UNIX systems; the -G option is the
preferred specification. The -Gn and -g options disable all
optimizations and imply -O0 and -h fp0.
The -Gfast option permits both full code optimization and
the greatest flexibility in setting breakpoints, but
requires use of the Cray fast-track debugger. For more
information, see the lgdb(1) man page.
The debugging options take precedence over any conflicting
options that appear on the command line. If more than one
debugging option appears, the last one specified overrides
the others.
-h [no]bounds
Provides checking of pointer and array references to ensure
that they are within acceptable boundaries. -h nobounds
disables these checks.
The pointer check verifies that the pointer is greater than
0 and less than the machine memory limit. The array check
verifies that the subscript is greater than or equal to 0
and is less than the array size, if declared.
-h dir_check
-h zero Causes stack-allocated memory to be initialized to all
zeros.
Compiler Message Options
-h msglevel_n
Specifies the lowest level of severity of messages to be
issued. Messages at the specified level and above are
issued.
The default is -h msglevel_3.
Values for n are:
--------------------------------------------------------------
n Description
--------------------------------------------------------------
0 Comment
1 Note
2 Caution
3 Warning
4 Error
--------------------------------------------------------------
-h [no]message=n[:n...]
Enables or disables specified compiler messages, where n is
the number of a message to be enabled or disabled. You can
specify more than one message number; multiple numbers must
be separated by a colon with no intervening spaces. For
example, to disable messages CC-1trunk and CC-9, specify:
-h nomessage=174:9
The -h [no]message=n option overrides -h msglevel_n for the
specified messages. If n is not a valid message number, it
is ignored. Any compiler message except ERROR, INTERNAL, and
LIMIT messages can be disabled; attempts to disable these
messages by using the -h nomessage=n option are ignored.
-h report=args
Generates report messages specified in args and lets you
direct the specified messages to a file. The values of args
are:
--------------------------------------------------------------
args Description
--------------------------------------------------------------
f Writes specified messages to file.V, where file
% CC -h report=is myfile.C
-h [no]abort
Controls whether a compilation aborts if an error is
detected.
The default is -h noabort.
-h errorlimit[=n]
Specifies the maximum number of error messages the compiler
prints before it exits, where n is a positive integer.
Specifying -h errorlimit=0 disables exiting on the basis of
the number of errors. Specifying -h errorlimit with no
qualifier is the same as setting n to 1.
The default is -h errorlimit=100.
Compilation Phase Options
-E Directs the compiler to execute only the preprocessor phase
of the compiler. The -E and -P options are equivalent,
except that -E directs output to stdout and inserts
appropriate #line linenumber preprocessing directives. The
-E option takes precedence over the -h feonly, -S, and -c
options.
-P Directs the compiler to execute only the preprocessor phase
of the compiler for each source file specified. The
preprocessed output for each source file is written to a
file with a name that corresponds to the name of the source
file and has a .i suffix substituted for the suffix of the
source file. The -P option is similar to the -E option,
except that #line linenumber directives are suppressed, and
the preprocessed source does not go to stdout. This option
takes precedence over -h feonly, -S, and -c.
When both the -P and -E options are specified, the last one
specified takes precedence.
-h feonly Limits the compiler to syntax checking. The optimizer and
code generator are not executed. This option takes
precedence over -S and -c.
-S Compiles the named source files and leaves the assembly
language output in the corresponding files suffixed with a
.s. If this option is used with -G or -g, debugging
information is not generated. This option takes precedence
over -c.
-c Creates a relocatable object file for each named source file
but does not link the object files. The relocatable object
file name corresponds to the name of the source file. The .o
system.
The values of phase are:
----------------------------------------------------------------
phase System Phase Command
----------------------------------------------------------------
0 (zero) Compiler CC
a Assembler as
l Linker ld
----------------------------------------------------------------
Arguments to be passed to system phases can be entered in
either of two styles. If spaces appear within a string to be
passed, the string is enclosed in double quotes. When double
quotes are not used, spaces cannot appear in the string.
Commas can appear wherever spaces normally appear; an option
and its argument can be either separated by a comma or not
separated. If a comma is part of an argument, it must be
preceded by the \ character. For example, any of the
following command lines would send -e name to the linker:
% CC -Wl,"-e name" file.C
% CC -Wl,-e,name file.C
% CC -Wl,"-ename" file.C
Because the preprocessor is built into the compiler, -Wp and
-W0 are equivalent.
The -Wl,-rpath ldir linker option changes the runtime
library search algorithm to look for files in directory
ldir. To request more than one library directory, specify
multiple -rpath options. Note that a library may be found at
link time with a -L option, but may not be found at run time
if a corresponding -rpath option is not found. Also note
that the compiler driver does not pass the -rpath option to
the linker. You must explicitly specify -Wl when using this
option.
Caution:
At link time, all ldir arguments are added to the
executable. The dynamic linker will search these paths
first for shared dynamic libraries at runtime, with one
exception. The Linux environment variable
LD_LIBRARY_PATH precedes all other search paths for
0 (zero) Compiler CC
a Assembler as
l Linker ld
----------------------------------------------------------------
Because there is no separate preprocessor, -Yp and -Y0 are
equivalent.
Preprocessing Options
-C Retains all comments in the preprocessed source code, except
those on preprocessor directive lines. By default, the
preprocessor phase strips comments from the source code.
This option is useful in combination with the -P or -E
option.
-D macro[=def]
Defines macro as if it were defined by a #define directive.
If no =def argument is specified, macro is defined as 1.
Predefined macros also exist and are described in the Cray C
and C++ Reference Manual. Any predefined macro except those
required by the standard can be redefined by the -D option.
The -U option overrides the -D option when the same macro
name is specified, regardless of the order of options on the
command line.
-h [no]pragma=name[:name ...]
Enables or disables the processing of specified directives
in the source code, where name can be the name of a
directive or a word shown in the following table to specify
a group of directives. More than one name can be specified.
Multiple names must be separated by a colon and have no
intervening spaces.
----------------------------------------------------------------
name Group Directives affected
----------------------------------------------------------------
all All All directives
allinline Inlining inline_enable,
inline_disable,
inline_reset,
inline_always,
inline_never
allscalar Scalar optimization concurrent,
nointerchange,
noreduction,
suppress,
unroll/nounroll
allvector Vectorization novector, loop_info,
OpenMP accelerator
directives.
----------------------------------------------------------------
When using this option to enable or disable individual
directives, note that some directives must occur in pairs.
For these directives, you must disable both directives if
you want to disable either; otherwise, the disabling of one
of the directives may cause errors when the other directive
is (or is not) present in the compilation unit.
By default, no directives are disabled.
-I incldir
Specifies a directory for files named in #include directives
when the #include file names do not have a specified path.
Each directory specified must be specified by a separate -I
option.
The order in which directories are searched for files named
on #include directives is determined by enclosing the file
name in either quotation marks ("") or angle brackets (< and
>).
Directories for #include "file" are searched in the
following order:
1. Directory of the input file.
2. Directories named in -I options, in command-line order.
3. Site-specific and compiler release-specific include files
directories.
4. Directory /usr/include.
Directories for #include <file> are searched in the
following order:
1. Directories named in -I options, in command-line order.
2. Site-specific and compiler release-specific include files
directories.
3. Directory /usr/include.
If the -I option specifies a directory name that does not
begin with a slash (/), the directory is interpreted as
relative to the current working directory and not relative
to the directory of the input file (if different from the
3. yourdir (relative to the current working directory),
specified by -I yourdir.
4. Site-specific and compiler release-specific include files
directories.
5. Directory /usr/include.
-M Provides information about recompilation dependencies that
the source file invokes on #include files and other source
files. This information is printed in the form expected by
make. Such dependencies are introduced by the #include
directive. The output is directed to stdout.
-nostdinc Stops the preprocessor from searching for include files in
the standard directories (/usr/include/c++ and
/usr/include).
-U macro Removes any initial definition of macro. Any predefined
macro except those required by the standard can be undefined
by the -U option. The -U option overrides the -D option when
the same macro name is specified, regardless of the order of
options on the command line.
Predefined macros are described in the Cray C and C++
Reference Manual. Macros defined in the system headers are
not predefined macros and are not affected by the -U option.
Linker Options
-h [system|default]_alloc
The -h system_alloc option causes the compiler to use the
native malloc implementation provided by the OS. By default,
the compiler uses a modified malloc implementation which
offers better support for Cray XE memory needs.
Default: default_alloc
-h dynamic
Directs the compiler driver to link dynamic libraries at
runtime. This option is used to create dynamically linked
executable files and may not be used with the -h static or
-h shared options. Note that the preferred invocation is to
call the generic CC command with the -dynamic option, rather
than using this compiler specific option. See the CC(1) man
page.
-h [no]pgas_runtime
The -h pgas_runtime option directs the CC compiler driver to
link with the PGAS (coarray Fortran or UPC) runtime
libraries. This may be necessary when the application uses
Fortran or UPC source code.
Directs the compiler driver to search for the specified
object library file when linking an executable file. To
request more than one library file, specify multiple -l
options.
When statically linking, the compiler driver searches for
libraries by prepending ldir/lib on the front of libname and
appending .a on the end of it, for each ldir that has been
specified by using the -L option. It uses the first file it
finds.
When dynamically linking, the library search process is
similar to the static case, with a few differences. The
compiler driver searches for libraries by prepending
ldir/lib on the front of libname and appending .so on the
end of it, for each ldir that has been specified by using
the -L option. If a matching .so is not found, the compiler
driver replaces .so with .a and repeats the process from the
beginning. It uses the first file it finds.
There is no search order dependency for libraries.
If you specify personal libraries by using the -l command
line option, as in the following example, those libraries
are added before the default CCE library list. (The -l
option is passed to the linker.)
% cc -l mylib target.c
When the previous command line is issued, the linker looks
for a library named libmylib.a (following the naming
convention) and adds it to the top of the list of default
libraries.
-L ldir Changes the -l option search algorithm to look for library
files in directory ldir during link time. To request more
than one library directory, specify multiple -L options.
The linker searches for library files in the compiler
release-specific directories.
Note: Multiple -L options are treated cumulatively as if
all ldir arguments appeared on one -L option preceding all
-l options. Therefore, do not attempt to link functions of
the same name from different libraries through the use of
alternating -L and -l options.
-o outfile
Produces an absolute binary file named outfile. A file named
a.out is produced by default. When this option is used in
conjunction with the -c option and a single source file, a
identify the type of behavior desired. There are three
option sets, only one member of a set may be used at a time;
however, all three sets may be used together.
Default: auto_async_kernel:no_fast_addr:no_deep_copy
option Set 1:
auto_async_none
Execute kernels and updates synchronously, unless
there is an async clause present on the kernels or
update directive.
auto_async_kernel
Default. Execute all kernels asynchronously
ensuring program order is maintained.
auto_async_all
Execute all kernels and data transfers
asynchronously, ensuring program order is
maintained.
option Set 2:
no_fast_addr
Default. Use default types for addressing.
fast_addr Attempt to use 32 bit integers in all addressing
to improve performance. This optimization may
result in incorrect behavior for some codes.
option Set 3:
no_deep_copy
Default. Do not look inside of an object type to
transfer sub-objects. Allocatable members of
derived type objects will not be allocated on the
device.
deep_copy (Fortran only) Look inside of derived type objects
and recreate the derived type on the accelerator
recursively. A derived type object that contains
an allocatable member will have memory allocated
on the device for the member.
-h cpu=target_system
Specifies the target Cray system on which the absolute
binary file is to be executed, where target_system can be
either x86-64 or opteron (single or dual-core), barcelona or
shanghai (quad-core), istanbul (6-core), mc8 (8-core), mc12
(12-core), interlagos (16-core), interlagos-cu (8-compute
unit), abudhabi (16-core) or abudhabi-cu (8-compute unit).
one of the targeting modules (craype-mc12 or craype-
interlagos-cu, for example). The targeting modules set
CRAY_CPU_TARGET and define paths to the corresponding
libraries. The compiler driver script translates
CRAY_CPU_TARGET to the corresponding cpu=target_system
option when calling the compiler.
If a user wishes to override the current target_system value
set by the module environment (via the CRAY_CPU_TARGET
definition), they should do so by specifying
-hcpu=target_system on the compiler command line.
-h [no]fp_trap
Controls whether the compiler generates code compatible with
floating point traps being enabled.
Default: fp_trap, if traps are enabled using the -K trap
option, or if -Ofp[0,1] is in effect. Otherwise, the default
is nofp_trap.
-h ident=name
Changes the ident name to name. This name is used as the
module name in the object file (.o suffix) and assembler
file (.s suffix). Regardless of whether name is specified or
the default is used, the following transformations are
performed on name:
· All . characters in the ident name are changed to $.
· If the ident name starts with a number, a $ is added to
the beginning of the ident name.
The default is the file name specified on the command line.
-h keepfiles
Prevents the removal of the object (.o) and temporary
assembly (.s) files after an executable is created.
Normally, the compiler automatically removes these files
after linking them to create an executable. Since the
original object files are required to instrument a program
for performance analysis, if you plan to use CrayPat to
conduct performance analysis experiments, you can use this
option to preserve the object files.
-h loop_trips=[tiny|small|medium|large|huge]
Specifies runtime loop trip counts for all loops in a
compiled source file. This information is used to better
tune optimizations to the runtime characteristics of the
application.
-h mpin Enables or disables optimization around a selected subset of
MPI library calls. -h mpi0 disables this option. The default
accelerator directives. The default is -h omp_acc. For
details, see the Cray C and C++ Reference Manual.
-h pic, -h PIC
Generates position independent code (PIC), which allows a
virtual address change from one process to another, as is
necessary in the case of shared, dynamically linked objects.
The virtual addresses of the instructions and data in PIC
code are not known until dynamic link time.
-h prototype_intrinsics
Simulates the effect of including intrinsics.h at the
beginning of a compilation. Use this option if the source
code does not include the intrinsics.h statement and you
cannot modify the code. This option is off by default.
-h [no]threadsafe
Enables or disables the generation of threadsafe code. Code
that is threadsafe can be used with pthreads and OpenMP.
C code compiled with -h threadsafe (the default) cannot be
linked with C code compiled with -h nothreadsafe.
The default is -h threadsafe.
-K trap=opt[,opt] ...
Enable traps for the specified exceptions. By default, no
exceptions are trapped. Enabling traps using this option
also has the effect of setting -h fp_trap.
If the specified options contradict each other, the last
option has priority. For example, -Ktrap=none,fp is
equivalent to -Ktrap=fp.
This option does not affect compile time optimizations; it
detects runtime exceptions. This option is processed only at
link time and affects the entire program; it is not
processed when compiling subprograms. Therefore, traps may
be set using this command line option at the beginning of
execution of the main program only. The program may
subsequently change these settings by calling intrinsic or
library procedures. Use of this option may require the
specification of -hfp_trap when compiling other files of the
application.
opt Exceptions
denorm Trap on denormalized operands.
divz Trap on divide-by-zero.
fp Trap on divz, inv, or ovf exceptions.
-V Displays compiler version information. If the command line
specifies no source file, no compilation occurs. Version
information consists of the product name, the version
number, and the current date and time.
-X npes Specifies the number of processing elements (PEs) that will
be specified through aprun at job launch. The value for npes
can range from 1 through 2**31 - 1 inclusive on Cray XE
systems.
Ensure that you compile all object files with the same -X
npes value and run the resulting executable with that number
of PEs. If you use mixed -X npes values or if the number of
PEs provided at run time differs from the -X npes value, a
run time error is generated.
The number of PEs to use cannot be changed at link or run
time. You must recompile the program with a different value
for npes to change the number of PEs.
#pragma DIRECTIVES
For a description of #pragma directives, including OpenMP, OpenACC,
and UPC directives, see the Cray C and C++ Reference Manual and the
intro_pragmas(1) man page.
COMPILE TIME ENVIRONMENT VARIABLES
For compile time, run time, and OpenMP environment variables, refer to
the Cray C and C++ Reference Manual.
FILES
By default, the compilation process creates an absolute binary file
named a.out that reflects the contents of the source files and any
referenced library functions. File a.out can then be executed on the
target Cray compute nodes. The compiler commands accept several types
of file arguments, as explained in the following paragraphs.
The CC command interprets files with .C, .c, .i, .c++, .C++, .cc,
.cxx, .CXX, or .CC suffixes as C++ source files. The source files are
compiled, and each corresponding object code is left in a file whose
name is that of the source file, with .o substituted for the previous
suffix. If no options are selected to control the compilation process,
the CC command automatically calls the linker. The linker uses file.o
as input and produces the executable file.
Files whose names end with .s are interpreted as Cray Assembly
Language (CAL) source files. They are assembled, and each
corresponding object code is left in a file. The file name is that of
the source file, with .o substituted for .s. Again, the linker uses
file.o as input and produces the executable file.
Any compatible object files whose names end with .o, plus files whose
does not translate C++ into an intermediate C form, but instead
translates source code directly into machine code for the target
machine.
The following summarizes the files used by the C++ compiler:
--------------------------------------------------------------
File Name Description
--------------------------------------------------------------
a.out Default name of the executable output file
file.a Library input file
file.c C++ source file
file.C, C++ source file
file.c++
file.CC C++ source file
file.C++, C++ source file
file.cc
file.cxx, C++ source file
file.CXX
file.i Preprocessor output file
file.L Pseudo-CAL listing file
file.o Object file
file.s Assembly language source file
file.V Report file for -h report
--------------------------------------------------------------
SEE ALSO
craycc(1), crayftn(1), aprun(1), explain(1)
Cray C and C++ Reference Manual
Cray Application Developer's Environment User's Guide
Cray Fortran Reference Manual
Man(1) output converted with
man2html