@item C Language Options
@xref{C Dialect Options,,Options Controlling C Dialect}.
@gccoptlist{-ansi -std=@var{standard} -fgnu89-inline @gol
--aux-info @var{filename} @gol
+-aux-info @var{filename} -fallow-parameterless-variadic-functions @gol
-fno-asm -fno-builtin -fno-builtin-@var{function} @gol
-fhosted -ffreestanding -fopenmp -fms-extensions -fplan9-extensions @gol
-trigraphs -no-integrated-cpp -traditional -traditional-cpp @gol
-Wfatal-errors -Wfloat-equal -Wformat -Wformat=2 @gol
-Wno-format-contains-nul -Wno-format-extra-args -Wformat-nonliteral @gol
-Wformat-security -Wformat-y2k @gol
--Wframe-larger-than=@var{len} -Wjump-misses-init -Wignored-qualifiers @gol
+-Wframe-larger-than=@var{len} -Wno-free-nonheap-object -Wjump-misses-init @gol
+-Wignored-qualifiers @gol
-Wimplicit -Wimplicit-function-declaration -Wimplicit-int @gol
-Winit-self -Winline -Wmaybe-uninitialized @gol
-Wno-int-to-pointer-cast -Wno-invalid-offsetof @gol
-Wsystem-headers -Wtrampolines -Wtrigraphs -Wtype-limits -Wundef @gol
-Wuninitialized -Wunknown-pragmas -Wno-pragmas @gol
-Wunsuffixed-float-constants -Wunused -Wunused-function @gol
--Wunused-label -Wunused-parameter -Wno-unused-result -Wunused-value @gol
--Wunused-variable -Wunused-but-set-parameter -Wunused-but-set-variable @gol
--Wvariadic-macros -Wvla -Wvolatile-register-var -Wwrite-strings}
+-Wunused-label -Wunused-local-typedefs -Wunused-parameter @gol
+-Wno-unused-result -Wunused-value @gol -Wunused-variable @gol
+-Wunused-but-set-parameter -Wunused-but-set-variable @gol
+-Wvariadic-macros -Wvector-operation-performance -Wvla
+-Wvolatile-register-var -Wwrite-strings}
@item C and Objective-C-only Warning Options
@gccoptlist{-Wbad-function-cast -Wmissing-declarations @gol
-fcx-limited-range @gol
-fdata-sections -fdce -fdce -fdelayed-branch @gol
-fdelete-null-pointer-checks -fdse -fdevirtualize -fdse @gol
--fearly-inlining -fipa-sra -fexpensive-optimizations -ffast-math @gol
--ffinite-math-only -ffloat-store -fexcess-precision=@var{style} @gol
+-fearly-inlining -fipa-sra -fexpensive-optimizations -ffat-lto-objects @gol
+-ffast-math -ffinite-math-only -ffloat-store -fexcess-precision=@var{style} @gol
-fforward-propagate -ffp-contract=@var{style} -ffunction-sections @gol
-fgcse -fgcse-after-reload -fgcse-las -fgcse-lm -fgraphite-identity @gol
-fgcse-sm -fif-conversion -fif-conversion2 -findirect-inlining @gol
-fschedule-insns -fschedule-insns2 -fsection-anchors @gol
-fselective-scheduling -fselective-scheduling2 @gol
-fsel-sched-pipelining -fsel-sched-pipelining-outer-loops @gol
--fsignaling-nans -fsingle-precision-constant -fsplit-ivs-in-unroller @gol
--fsplit-wide-types -fstack-protector -fstack-protector-all @gol
--fstrict-aliasing -fstrict-overflow -fthread-jumps -ftracer @gol
--ftree-bit-ccp @gol
+-fshrink-wrap -fsignaling-nans -fsingle-precision-constant @gol
+-fsplit-ivs-in-unroller -fsplit-wide-types -fstack-protector @gol
+-fstack-protector-all -fstrict-aliasing -fstrict-overflow @gol
+-fthread-jumps -ftracer -ftree-bit-ccp @gol
-ftree-builtin-call-dce -ftree-ccp -ftree-ch -ftree-copy-prop @gol
-ftree-copyrename -ftree-dce -ftree-dominator-opts -ftree-dse @gol
-ftree-forwprop -ftree-fre -ftree-loop-if-convert @gol
-ftree-phiprop -ftree-loop-distribution -ftree-loop-distribute-patterns @gol
-ftree-loop-ivcanon -ftree-loop-linear -ftree-loop-optimize @gol
-ftree-parallelize-loops=@var{n} -ftree-pre -ftree-pta -ftree-reassoc @gol
--ftree-sink -ftree-sra -ftree-switch-conversion @gol
+-ftree-sink -ftree-sra -ftree-switch-conversion -ftree-tail-merge @gol
-ftree-ter -ftree-vect-loop-version -ftree-vectorize -ftree-vrp @gol
-funit-at-a-time -funroll-all-loops -funroll-loops @gol
-funsafe-loop-optimizations -funsafe-math-optimizations -funswitch-loops @gol
-iwithprefixbefore @var{dir} -isystem @var{dir} @gol
-imultilib @var{dir} -isysroot @var{dir} @gol
-M -MM -MF -MG -MP -MQ -MT -nostdinc @gol
--P -fworking-directory -remap @gol
--trigraphs -undef -U@var{macro} -Wp,@var{option} @gol
--Xpreprocessor @var{option}}
+-P -fdebug-cpp -ftrack-macro-expansion -fworking-directory @gol
+-remap -trigraphs -undef -U@var{macro} @gol
+-Wp,@var{option} -Xpreprocessor @var{option}}
@item Assembler Option
@xref{Assembler Options,,Passing Options to the Assembler}.
@emph{AVR Options}
@gccoptlist{-mmcu=@var{mcu} -mno-interrupts @gol
--mcall-prologues -mtiny-stack -mint8}
+-mcall-prologues -mtiny-stack -mint8 -mstrict-X}
@emph{Blackfin Options}
@gccoptlist{-mcpu=@var{cpu}@r{[}-@var{sirevision}@r{]} @gol
-mno-wide-multiply -mrtd -malign-double @gol
-mpreferred-stack-boundary=@var{num} @gol
-mincoming-stack-boundary=@var{num} @gol
--mcld -mcx16 -msahf -mmovbe -mcrc32 -mrecip -mvzeroupper @gol
+-mcld -mcx16 -msahf -mmovbe -mcrc32 @gol
+-mrecip -mrecip=@var{opt} @gol
+-mvzeroupper @gol
-mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4 -mavx @gol
--maes -mpclmul -mfsgsbase -mrdrnd -mf16c -mfma @gol
--msse4a -m3dnow -mpopcnt -mabm -mbmi -mtbm -mfma4 -mxop -mlwp @gol
--mthreads -mno-align-stringops -minline-all-stringops @gol
+-mavx2 -maes -mpclmul -mfsgsbase -mrdrnd -mf16c -mfma @gol
+-msse4a -m3dnow -mpopcnt -mabm -mbmi -mtbm -mfma4 -mxop -mlzcnt @gol
+-mbmi2 -mlwp -mthreads -mno-align-stringops -minline-all-stringops @gol
-minline-stringops-dynamically -mstringop-strategy=@var{alg} @gol
-mpush-args -maccumulate-outgoing-args -m128bit-long-double @gol
-m96bit-long-double -mregparm=@var{num} -msseregparm @gol
-mrecip -mrecip=@var{opt} -mno-recip -mrecip-precision @gol
-mno-recip-precision @gol
-mveclibabi=@var{type} -mfriz -mno-friz @gol
--mpointers-to-nested-functions -mno-pointers-to-nested-functions}
+-mpointers-to-nested-functions -mno-pointers-to-nested-functions @gol
+-msave-toc-indirect -mno-save-toc-indirect}
@emph{RX Options}
@gccoptlist{-m64bit-doubles -m32bit-doubles -fpu -nofpu@gol
-mrelax@gol
-mmax-constant-size=@gol
-mint-register=@gol
+-mpid@gol
-msave-acc-in-interrupts}
@emph{S/390 and zSeries Options}
-mfaster-structs -mno-faster-structs -mflat -mno-flat @gol
-mfpu -mno-fpu -mhard-float -msoft-float @gol
-mhard-quad-float -msoft-quad-float @gol
--mlittle-endian @gol
-mstack-bias -mno-stack-bias @gol
-munaligned-doubles -mno-unaligned-doubles @gol
--mv8plus -mno-v8plus -mvis -mno-vis}
+-mv8plus -mno-v8plus -mvis -mno-vis @gol
+-mvis2 -mno-vis2 -mvis3 -mno-vis3 @gol
+-mfmaf -mno-fmaf -mpopc -mno-popc @gol
+-mfix-at697f}
@emph{SPU Options}
@gccoptlist{-mwarn-reloc -merror-reloc @gol
arguments followed by their declarations is also provided, inside
comments, after the declaration.
+@item -fallow-parameterless-variadic-functions
+Accept variadic functions without named parameters.
+
+Although it is possible to define such a function, this is not very
+useful as it is not possible to read the arguments. This is only
+supported for C as this construct is allowed by C++.
+
@item -fno-asm
@opindex fno-asm
Do not recognize @code{asm}, @code{inline} or @code{typeof} as a
int i = @{ 2.2 @}; // error: narrowing from double to int
@end smallexample
-This flag can be useful for compiling valid C++98 code in C++0x mode.
+This flag can be useful for compiling valid C++98 code in C++0x mode
@item -Wnoexcept @r{(C++ and Objective-C++ only)}
@opindex Wnoexcept
warning if the unused arguments are all pointers, since the Single
Unix Specification says that such unused arguments are allowed.
-@item -Wno-format-zero-length @r{(C and Objective-C only)}
+@item -Wno-format-zero-length
@opindex Wno-format-zero-length
@opindex Wformat-zero-length
If @option{-Wformat} is specified, do not warn about zero-length formats.
@option{-Wformat}. Currently equivalent to @samp{-Wformat
-Wformat-nonliteral -Wformat-security -Wformat-y2k}.
-@item -Wnonnull @r{(C and Objective-C only)}
+@item -Wnonnull
@opindex Wnonnull
@opindex Wno-nonnull
Warn about passing a null pointer for arguments marked as
To suppress this warning use the @samp{unused} attribute
(@pxref{Variable Attributes}).
+@item -Wunused-local-typedefs @r{(C, Objective-C, C++ and Objective-C++ only)}
+@opindex Wunused-local-typedefs
+Warn when a typedef locally defined in a function is not used.
+
@item -Wunused-parameter
@opindex Wunused-parameter
@opindex Wno-unused-parameter
is not included by the compiler when determining
whether or not to issue a warning.
+@item -Wno-free-nonheap-object
+@opindex Wno-free-nonheap-object
+@opindex Wfree-nonheap-object
+Do not warn when attempting to free an object which was not allocated
+on the heap.
+
@item -Wstack-usage=@var{len}
@opindex Wstack-usage
Warn if the stack usage of a function might be larger than @var{len} bytes.
If the stack usage is fully static but exceeds the specified amount, it's:
@smallexample
- warning: stack usage is 1120 bytes
+ warning: stack usage is 1120 bytes
@end smallexample
@item
If the stack usage is (partly) dynamic but bounded, it's:
@smallexample
- warning: stack usage might be 1648 bytes
+ warning: stack usage might be 1648 bytes
@end smallexample
@item
If the stack usage is (partly) dynamic and not bounded, it's:
@smallexample
- warning: stack usage might be unbounded
+ warning: stack usage might be unbounded
@end smallexample
@end itemize
alternate syntax when in pedantic ISO C99 mode. This is default.
To inhibit the warning messages, use @option{-Wno-variadic-macros}.
+@item -Wvector-operation-performance
+@opindex Wvector-operation-performance
+@opindex Wno-vector-operation-performance
+Warn if vector operation is not implemented via SIMD capabilities of the
+architecture. Mainly useful for the performance tuning.
+Vector operation can be implemented @code{piecewise} which means that the
+scalar operation is performed on every vector element;
+@code{in parallel} which means that the vector operation is implemented
+using scalars of wider type, which normally is more performance efficient;
+and @code{as a single scalar} which means that vector fits into a
+scalar type.
+
@item -Wvla
@opindex Wvla
@opindex Wno-vla
-fsched-interblock -fsched-spec @gol
-fschedule-insns -fschedule-insns2 @gol
-fstrict-aliasing -fstrict-overflow @gol
--ftree-switch-conversion @gol
+-ftree-switch-conversion -ftree-tail-merge @gol
-ftree-pre @gol
-ftree-vrp}
When pipelining loops during selective scheduling, also pipeline outer loops.
This option has no effect until @option{-fsel-sched-pipelining} is turned on.
+@item -fshrink-wrap
+@opindex fshrink-wrap
+Emit function prologues only before parts of the function that need it,
+rather than at the top of the function. This flag is enabled by default at
+@option{-O} and higher.
+
@item -fcaller-saves
@opindex fcaller-saves
Enable values to be allocated in registers that will be clobbered by
initializations from a scalar array. This flag is enabled by default
at @option{-O2} and higher.
+@item -ftree-tail-merge
+Look for identical code sequences. When found, replace one with a jump to the
+other. This optimization is known as tail merging or cross jumping. This flag
+is enabled by default at @option{-O2} and higher. The run time of this pass can
+be limited using @option{max-tail-merge-comparisons} parameter and
+@option{max-tail-merge-iterations} parameter.
+
@item -ftree-dce
@opindex ftree-dce
Perform dead code elimination (DCE) on trees. This flag is enabled by
Enabled by default when LTO support in GCC is enabled and GCC was compiled
with a linker supporting plugins (GNU ld 2.21 or newer or gold).
+@item -ffat-lto-objects
+@opindex ffat-lto-objects
+Fat LTO objects are object files that contain both the intermediate language
+and the object code. This makes them useable for both LTO linking and normal
+linking. This option makes effect only with @option{-flto} and is ignored
+at linktime.
+
+@option{-fno-fat-lto-objects} improves compilation time over plain LTO, but
+requires the complete toolchain to be aware of LTO. It requires a linker with
+linker plugin support for basic functionality. Additionally, nm, ar and ranlib
+need to support linker plugins to allow a full-featured build environment
+(capable of building static libraries etc).
+
+The default is @option{-ffat-lto-objects} but this default is intended to
+change in future releases when linker plugin enabled environments become more
+common.
@item -fcompare-elim
@opindex fcompare-elim
After register allocation and post-register allocation instruction splitting,
with few branches or calls can create excessively large lists which
needlessly consume memory and resources.
+@item max-modulo-backtrack-attempts
+The maximum number of backtrack attempts the scheduler should make
+when modulo scheduling a loop. Larger values can exponentially increase
+compile time.
+
@item max-inline-insns-single
Several parameters control the tree inliner used in gcc.
This number sets the maximum number of instructions (counted in GCC's
The value of 0 will avoid limiting the search, but may slow down compilation
of huge functions. The default value is 30.
+@item max-tail-merge-comparisons
+The maximum amount of similar bbs to compare a bb with. This is used to
+avoid quadratic behaviour in tree tail merging. The default value is 10.
+
+@item max-tail-merge-iterations
+The maximum amount of iterations of the pass over the function. This is used to
+limit run time in tree tail merging. The default value is 2.
+
@item max-unrolled-insns
The maximum number of instructions that a loop should have if that loop
is unrolled, and if the loop is unrolled, it determines how many times
low, value expressions that are available and could be represented in
debug information may end up not being used; setting this higher may
enable the compiler to find more complex debug expressions, but compile
-time may grow exponentially, and even then, it may fail to find more
-usable expressions. The default is 10.
+time and memory use may grow. The default is 12.
@item min-nondebug-insn-uid
Use uids starting at this parameter for nondebug insns. The range below
jump-table instead of a tree of conditional branches. If the value is
0, use the default for the machine. The default is 0.
+@item tree-reassoc-width
+Set the maximum number of instructions executed in parallel in
+reassociated tree. This parameter overrides target dependent
+heuristics used by default if has non zero value.
+
@end table
@end table
@samp{fa526}, @samp{fa626},
@samp{fa606te}, @samp{fa626te}, @samp{fmp626}, @samp{fa726te}.
+
+@option{-mcpu=generic-@var{arch}} is also permissible, and is
+equivalent to @option{-march=@var{arch} -mtune=generic-@var{arch}}.
+See @option{-mtune} for more information.
+
+@option{-mcpu=native} causes the compiler to auto-detect the CPU
+of the build computer. At present, this feature is only supported on
+Linux, and not all architectures are recognised. If the auto-detect is
+unsuccessful the option has no effect.
+
@item -mtune=@var{name}
@opindex mtune
This option is very similar to the @option{-mcpu=} option, except that
For some ARM implementations better performance can be obtained by using
this option.
+@option{-mtune=generic-@var{arch}} specifies that GCC should tune the
+performance for a blend of processors within architecture @var{arch}.
+The aim is to generate code that run well on the current most popular
+processors, balancing between optimizations that benefit some CPUs in the
+range, and avoiding performance pitfalls of other CPUs. The effects of
+this option may change in future GCC versions as CPU models come and go.
+
+@option{-mtune=native} causes the compiler to auto-detect the CPU
+of the build computer. At present, this feature is only supported on
+Linux, and not all architectures are recognised. If the auto-detect is
+unsuccessful the option has no effect.
+
@item -march=@var{name}
@opindex march
This specifies the name of the target ARM architecture. GCC uses this
@samp{armv7}, @samp{armv7-a}, @samp{armv7-r}, @samp{armv7-m},
@samp{iwmmxt}, @samp{iwmmxt2}, @samp{ep9312}.
+@option{-march=native} causes the compiler to auto-detect the architecture
+of the build computer. At present, this feature is only supported on
+Linux, and not all architectures are recognised. If the auto-detect is
+unsuccessful the option has no effect.
+
@item -mfpu=@var{name}
@itemx -mfpe=@var{number}
@itemx -mfp=@var{number}
and long long will be 4 bytes. Please note that this option does not
comply to the C standards, but it will provide you with smaller code
size.
+
+@item -mstrict-X
+@opindex mstrict-X
+Use register @code{X} in a way proposed by the hardware. This means
+that @code{X} will only be used in indirect, post-increment or
+pre-decrement addressing.
+
+Without this option, the @code{X} register may be used in the same way
+as @code{Y} or @code{Z} which then is emulated by additional
+instructions.
+For example, loading a value with @code{X+const} addressing with a
+small @code{const <= 63} to a register @var{Rn} will be printed as
+@example
+adiw r26, const
+ld @var{Rn}, X
+sbiw r26, const
+@end example
@end table
+@subsubsection @code{EIND} and Devices with more than 128k Bytes of Flash
+
+Pointers in the implementation are 16 bits wide.
+The address of a function or label is represented as word address so
+that indirect jumps and calls can address any code address in the
+range of 64k words.
+
+In order to faciliate indirect jump on devices with more than 128k
+bytes of program memory space, there is a special function register called
+@code{EIND} that serves as most significant part of the target address
+when @code{EICALL} or @code{EIJMP} instructions are used.
+
+Indirect jumps and calls on these devices are handled as follows and
+are subject to some limitations:
+
+@itemize @bullet
+
+@item
+The compiler never sets @code{EIND}.
+
+@item
+The startup code from libgcc never sets @code{EIND}.
+Notice that startup code is a blend of code from libgcc and avr-libc.
+For the impact of avr-libc on @code{EIND}, see the
+@w{@uref{http://nongnu.org/avr-libc/user-manual,avr-libc user manual}}.
+
+@item
+The compiler uses @code{EIND} implicitely in @code{EICALL}/@code{EIJMP}
+instructions or might read @code{EIND} directly.
+
+@item
+The compiler assumes that @code{EIND} never changes during the startup
+code or run of the application. In particular, @code{EIND} is not
+saved/restored in function or interrupt service routine
+prologue/epilogue.
+
+@item
+It is legitimate for user-specific startup code to set up @code{EIND}
+early, for example by means of initialization code located in
+section @code{.init3}, and thus prior to general startup code that
+initializes RAM and calls constructors.
+
+@item
+For indirect calls to functions and computed goto, the linker will
+generate @emph{stubs}. Stubs are jump pads sometimes also called
+@emph{trampolines}. Thus, the indirect call/jump will jump to such a stub.
+The stub contains a direct jump to the desired address.
+
+@item
+Stubs will be generated automatically by the linker if
+the following two conditions are met:
+@itemize @minus
+
+@item The address of a label is taken by means of the @code{gs} modifier
+(short for @emph{generate stubs}) like so:
+@example
+LDI r24, lo8(gs(@var{func}))
+LDI r25, hi8(gs(@var{func}))
+@end example
+@item The final location of that label is in a code segment
+@emph{outside} the segment where the stubs are located.
+@end itemize
+
+@item
+The compiler will emit such @code{gs} modifiers for code labels in the
+following situations:
+@itemize @minus
+@item Taking address of a function or code label.
+@item Computed goto.
+@item If prologue-save function is used, see @option{-mcall-prologues}
+command line option.
+@item Switch/case dispatch tables. If you do not want such dispatch
+tables you can specify the @option{-fno-jump-tables} command line option.
+@item C and C++ constructors/destructors called during startup/shutdown.
+@item If the tools hit a @code{gs()} modifier explained above.
+@end itemize
+
+@item
+The default linker script is arranged for code with @code{EIND = 0}.
+If code is supposed to work for a setup with @code{EIND != 0}, a custom
+linker script has to be used in order to place the sections whose
+name start with @code{.trampolines} into the segment where @code{EIND}
+points to.
+
+@item
+Jumping to non-symbolic addresses like so is @emph{not} supported:
+
+@example
+int main (void)
+@{
+ /* Call function at word address 0x2 */
+ return ((int(*)(void)) 0x2)();
+@}
+@end example
+
+Instead, a stub has to be set up:
+
+@example
+int main (void)
+@{
+ extern int func_4 (void);
+
+ /* Call function at byte address 0x4 */
+ return func_4();
+@}
+@end example
+
+and the application be linked with @code{-Wl,--defsym,func_4=0x4}.
+Alternatively, @code{func_4} can be defined in the linker script.
+@end itemize
+
@node Blackfin Options
@subsection Blackfin Options
@cindex Blackfin Options
Schedules as an EV6 and supports the BWX, CIX, FIX, and MAX extensions.
@end table
-Native Linux/GNU toolchains also support the value @samp{native},
+Native toolchains also support the value @samp{native},
which selects the best architecture option for the host processor.
@option{-mcpu=native} has no effect if GCC does not recognize
the processor.
Set only the instruction scheduling parameters for machine type
@var{cpu_type}. The instruction set is not changed.
-Native Linux/GNU toolchains also support the value @samp{native},
+Native toolchains also support the value @samp{native},
which selects the best architecture option for the host processor.
@option{-mtune=native} has no effect if GCC does not recognize
the processor.
@item corei7-avx
Intel Core i7 CPU with 64-bit extensions, MMX, SSE, SSE2, SSE3, SSSE3,
SSE4.1, SSE4.2, AVX, AES and PCLMUL instruction set support.
+@item core-avx-i
+Intel Core CPU with 64-bit extensions, MMX, SSE, SSE2, SSE3, SSSE3,
+SSE4.1, SSE4.2, AVX, AES, PCLMUL, FSGSBASE, RDRND and F16C instruction
+set support.
@item atom
Intel Atom CPU with 64-bit extensions, MMX, SSE, SSE2, SSE3 and SSSE3
instruction set support.
@itemx -mno-sse4
@itemx -mavx
@itemx -mno-avx
+@itemx -mavx2
+@itemx -mno-avx2
@itemx -maes
@itemx -mno-aes
@itemx -mpclmul
@itemx -mabm
@itemx -mno-abm
@itemx -mbmi
+@itemx -mbmi2
@itemx -mno-bmi
+@itemx -mno-bmi2
+@itemx -mlzcnt
+@itemx -mno-lzcnt
@itemx -mtbm
@itemx -mno-tbm
@opindex mmmx
@opindex m3dnow
@opindex mno-3dnow
These switches enable or disable the use of instructions in the MMX, SSE,
-SSE2, SSE3, SSSE3, SSE4.1, AVX, AES, PCLMUL, FSGSBASE, RDRND, F16C, FMA,
-SSE4A, FMA4, XOP, LWP, ABM, BMI, or 3DNow!@: extended instruction sets.
+SSE2, SSE3, SSSE3, SSE4.1, AVX, AVX2, AES, PCLMUL, FSGSBASE, RDRND, F16C,
+FMA, SSE4A, FMA4, XOP, LWP, ABM, BMI, BMI2, LZCNT or 3DNow!
+@: extended instruction sets.
These extensions are also available as built-in functions: see
@ref{X86 Built-in Functions}, for details of the functions enabled and
disabled by these switches.
of the non-reciprocal instruction, the precision of the sequence can be
decreased by up to 2 ulp (i.e. the inverse of 1.0 equals 0.99999994).
-Note that GCC implements 1.0f/sqrtf(x) in terms of RSQRTSS (or RSQRTPS)
+Note that GCC implements @code{1.0f/sqrtf(@var{x})} in terms of RSQRTSS
+(or RSQRTPS) already with @option{-ffast-math} (or the above option
+combination), and doesn't need @option{-mrecip}.
+
+Also note that GCC emits the above sequence with additional Newton-Raphson step
+for vectorized single float division and vectorized @code{sqrtf(@var{x})}
already with @option{-ffast-math} (or the above option combination), and
doesn't need @option{-mrecip}.
+@item -mrecip=@var{opt}
+@opindex mrecip=opt
+This option allows to control which reciprocal estimate instructions
+may be used. @var{opt} is a comma separated list of options, that may
+be preceded by a @code{!} to invert the option:
+@code{all}: enable all estimate instructions,
+@code{default}: enable the default instructions, equivalent to @option{-mrecip},
+@code{none}: disable all estimate instructions, equivalent to @option{-mno-recip},
+@code{div}: enable the approximation for scalar division,
+@code{vec-div}: enable the approximation for vectorized division,
+@code{sqrt}: enable the approximation for scalar square root,
+@code{vec-sqrt}: enable the approximation for vectorized square root.
+
+So for example, @option{-mrecip=all,!sqrt} would enable
+all of the reciprocal approximations, except for square root.
+
@item -mveclibabi=@var{type}
@opindex mveclibabi
Specifies the ABI type to use for vectorizing intrinsics using an
most compatible architecture for the selected ABI (that is,
@samp{mips1} for 32-bit ABIs and @samp{mips3} for 64-bit ABIs)@.
-Native Linux/GNU toolchains also support the value @samp{native},
+Native Linux/GNU and IRIX toolchains also support the value @samp{native},
which selects the best architecture option for the host processor.
@option{-march=native} has no effect if GCC does not recognize
the processor.
not be able to call through pointers to nested functions or pointers
to functions compiled in other languages that use the static chain if
you use the @option{-mno-pointers-to-nested-functions}.
+
+@item -msave-toc-indirect
+@itemx -mno-save-toc-indirect
+@opindex msave-toc-indirect
+Generate (do not generate) code to save the TOC value in the reserved
+stack location in the function prologue if the function calls through
+a pointer on AIX and 64-bit Linux systems. If the TOC value is not
+saved in the prologue, it is saved just before the call through the
+pointer. The @option{-mno-save-toc-indirect} option is the default.
@end table
@node RX Options
area can lead to smaller and faster code, but the size of area is
limited and it is up to the programmer to ensure that the area does
not overflow. Also when the small data area is used one of the RX's
-registers (@code{r13}) is reserved for use pointing to this area, so
-it is no longer available for use by the compiler. This could result
-in slower and/or larger code if variables which once could have been
-held in @code{r13} are now pushed onto the stack.
+registers (usually @code{r13}) is reserved for use pointing to this
+area, so it is no longer available for use by the compiler. This
+could result in slower and/or larger code if variables which once
+could have been held in the reserved register are now pushed onto the
+stack.
Note, common variables (variables which have not been initialised) and
constants are not placed into the small data area as they are assigned
The default value is zero, which disables this feature. Note, this
feature is not enabled by default with higher optimization levels
(@option{-O2} etc) because of the potentially detrimental effects of
-reserving register @code{r13}. It is up to the programmer to
-experiment and discover whether this feature is of benefit to their
-program.
+reserving a register. It is up to the programmer to experiment and
+discover whether this feature is of benefit to their program. See the
+description of the @option{-mpid} option for a description of how the
+actual register to hold the small data area pointer is chosen.
@item -msim
@itemx -mno-sim
multiplications. The default is to ignore the accumulator as this
makes the interrupt handlers faster.
+@item -mpid
+@itemx -mno-pid
+@opindex mpid
+@opindex mno-pid
+Enables the generation of position independent data. When enabled any
+access to constant data will done via an offset from a base address
+held in a register. This allows the location of constant data to be
+determined at run-time without requiring the executable to be
+relocated, which is a benefit to embedded applications with tight
+memory constraints. Data that can be modified is not affected by this
+option.
+
+Note, using this feature reserves a register, usually @code{r13}, for
+the constant data base address. This can result in slower and/or
+larger code, especially in complicated functions.
+
+The actual register chosen to hold the constant data base address
+depends upon whether the @option{-msmall-data-limit} and/or the
+@option{-mint-register} command line options are enabled. Starting
+with register @code{r13} and proceeding downwards, registers are
+allocated first to satisfy the requirements of @option{-mint-register},
+then @option{-mpid} and finally @option{-msmall-data-limit}. Thus it
+is possible for the small data area register to be @code{r8} if both
+@option{-mint-register=4} and @option{-mpid} are specified on the
+command line.
+
+By default this feature is not enabled. The default can be restored
+via the @option{-mno-pid} command line option.
+
@end table
@emph{Note:} The generic GCC command line @option{-ffixed-@var{reg}}
@samp{v7}, @samp{cypress}, @samp{v8}, @samp{supersparc}, @samp{hypersparc},
@samp{leon}, @samp{sparclite}, @samp{f930}, @samp{f934}, @samp{sparclite86x},
@samp{sparclet}, @samp{tsc701}, @samp{v9}, @samp{ultrasparc},
-@samp{ultrasparc3}, @samp{niagara} and @samp{niagara2}.
+@samp{ultrasparc3}, @samp{niagara}, @samp{niagara2}, @samp{niagara3},
+and @samp{niagara4}.
+
+Native Solaris and GNU/Linux toolchains also support the value @samp{native},
+which selects the best architecture option for the host processor.
+@option{-mcpu=native} has no effect if GCC does not recognize
+the processor.
Default instruction scheduling parameters are used for values that select
an architecture and not an implementation. These are @samp{v7}, @samp{v8},
v8: supersparc, hypersparc, leon
sparclite: f930, f934, sparclite86x
sparclet: tsc701
- v9: ultrasparc, ultrasparc3, niagara, niagara2
+ v9: ultrasparc, ultrasparc3, niagara, niagara2, niagara3, niagara4
@end smallexample
By default (unless configured otherwise), GCC generates code for the V7
Sun UltraSPARC III/III+/IIIi/IIIi+/IV/IV+ chips. With
@option{-mcpu=niagara}, the compiler additionally optimizes it for
Sun UltraSPARC T1 chips. With @option{-mcpu=niagara2}, the compiler
-additionally optimizes it for Sun UltraSPARC T2 chips.
+additionally optimizes it for Sun UltraSPARC T2 chips. With
+@option{-mcpu=niagara3}, the compiler additionally optimizes it for Sun
+UltraSPARC T3 chips. With @option{-mcpu=niagara4}, the compiler
+additionally optimizes it for Sun UltraSPARC T4 chips.
@item -mtune=@var{cpu_type}
@opindex mtune
that select a particular CPU implementation. Those are @samp{cypress},
@samp{supersparc}, @samp{hypersparc}, @samp{leon}, @samp{f930}, @samp{f934},
@samp{sparclite86x}, @samp{tsc701}, @samp{ultrasparc}, @samp{ultrasparc3},
-@samp{niagara}, and @samp{niagara2}.
+@samp{niagara}, @samp{niagara2}, @samp{niagara3} and @samp{niagara4}. With
+native Solaris and GNU/Linux toolchains, @samp{native} can also be used.
@item -mv8plus
@itemx -mno-v8plus
@opindex mno-vis
With @option{-mvis}, GCC generates code that takes advantage of the UltraSPARC
Visual Instruction Set extensions. The default is @option{-mno-vis}.
+
+@item -mvis2
+@itemx -mno-vis2
+@opindex mvis2
+@opindex mno-vis2
+With @option{-mvis2}, GCC generates code that takes advantage of
+version 2.0 of the UltraSPARC Visual Instruction Set extensions. The
+default is @option{-mvis2} when targetting a cpu that supports such
+instructions, such as UltraSPARC-III and later. Setting @option{-mvis2}
+also sets @option{-mvis}.
+
+@item -mvis3
+@itemx -mno-vis3
+@opindex mvis3
+@opindex mno-vis3
+With @option{-mvis3}, GCC generates code that takes advantage of
+version 3.0 of the UltraSPARC Visual Instruction Set extensions. The
+default is @option{-mvis3} when targetting a cpu that supports such
+instructions, such as niagara-3 and later. Setting @option{-mvis3}
+also sets @option{-mvis2} and @option{-mvis}.
+
+@item -mpopc
+@itemx -mno-popc
+@opindex mpopc
+@opindex mno-popc
+With @option{-mpopc}, GCC generates code that takes advantage of the UltraSPARC
+population count instruction. The default is @option{-mpopc}
+when targetting a cpu that supports such instructions, such as Niagara-2 and
+later.
+
+@item -mfmaf
+@itemx -mno-fmaf
+@opindex mfmaf
+@opindex mno-fmaf
+With @option{-mfmaf}, GCC generates code that takes advantage of the UltraSPARC
+Fused Multiply-Add Floating-point extensions. The default is @option{-mfmaf}
+when targetting a cpu that supports such instructions, such as Niagara-3 and
+later.
+
+@item -mfix-at697f
+@opindex mfix-at697f
+Enable the documented workaround for the single erratum of the Atmel AT697F
+processor (which corresponds to erratum #13 of the AT697E processor).
@end table
These @samp{-m} options are supported in addition to the above
on SPARC-V9 processors in 64-bit environments:
@table @gcctabopt
-@item -mlittle-endian
-@opindex mlittle-endian
-Generate code for a processor running in little-endian mode. It is only
-available for a few configurations and most notably not on Solaris and Linux.
-
@item -m32
@itemx -m64
@opindex m32
OSDN Git Service
