Differences

This shows you the differences between two versions of the page.


Previous revision
fuss:gcc_compile_flags [2022/04/19 08:28] (current) – external edit 127.0.0.1
Line 1: Line 1:
 +====== Optimisation Level ======
 +
 +^ Flag ^ Description ^
 +| ''-O0'' | Disables all optimisations and is useful for debugging. |
 +| ''-O1'' | Optimize. |
 +| ''-Os'' | Enables all the flags for ''-O2'' but disables the flags that increase the binary size. |
 +| ''-O2'' | Safest optimisation level for speed. |
 +| ''-O3'' | Enables aggressive optimisations. |
 +| ''-Ofast'' | Only in recent compilers, enables even more optimisations by violating standards compliance. |
 +
 +The most common optimisation levels are ''-Os'' and ''-O2''. Anything more aggressive than than that is bound to break code on a large scale. The optimisation levels are cumulative such that specifying ''-O3'' will include the optimisations from ''-O2''.
 +
 +Note that you will find many instances along the following lines:
 +<code>
 +-O2 -fomit-frame-pointer
 +</code>
 +however, ''-fomit-frame-pointer'' is already included in ''-O1'' which is included in ''-O2'' which makes specifying the flag redundant. When in doubt, consult the [[https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html|official optimisation options manual]].
 +
 +
 +====== Specifying the Architecture, CPU Tune and CPU Type ======
 +
 +The safest ''-march'' that can be set is ''-march=native'' which allows the compiler to guess the processor's features and use them during compilation. This is a feature supported from ''GCC 4'' and up and eliminates the need to supply an ''-march'' manually.
 +
 +However, if you need to specify a ''-march'', ''-mcpu'' or ''-mtune'', then a good procedure is as follows:
 +  * determine which ''CPU'' you have and on Linux you can issue ''cat /proc/cpuflags'' to see the flags supported by your ''CPU''. A description of those features can be found on the [[fuss:cpuflags|cpuflags page]].
 +  * issue ''gcc -v'' in a terminal to determine which compiler version you have.
 +  * [[https://gcc.gnu.org/onlinedocs/|browse the manual page]] of ''gcc'' corresponding to your version and locate the architecture you are on. For example, for ''i386'' and ''x86_64'' with ''gcc'' version ''4.2.4'' we [[https://gcc.gnu.org/onlinedocs/gcc-4.2.4/gcc/i386-and-x86_002d64-Options.html#i386-and-x86_002d64-Options|find the manual page listing the modifiers]].
 +  * finally, you have to chose a ''-march'', ''-mcpu'', or ''-mtune'' that closely matches the ''CPU'' features you have. It is important to specify a processor that has less or the same set of features matching your ''CPU''.
 +
 +As an example, suppose we have an Intel ''i7'' running on ''gcc'' version ''4.2.4''. Looking at the list on the manual page above, we find:
 +
 +<code>
 +pentium4, pentium4m
 +    Intel Pentium4 CPU with MMX, SSE and SSE2 instruction set support. 
 +prescott
 +    Improved version of Intel Pentium4 CPU with MMX, SSE, SSE2 and SSE3 instruction set support. 
 +nocona
 +    Improved version of Intel Pentium4 CPU with 64-bit extensions, MMX, SSE, SSE2 and SSE3 instruction set support. 
 +</code>
 +
 +Since we are running a ''64''-bit processor, and because the Intel ''i7'' supports the ''MMX'', ''SSE'', ''SSE2'' and ''SSE3'' instruction set, the most suiting for us in ''gcc'' version ''4.2.4'' is ''nocona''. However, ''prescott'' and even ''pentium4'' will be fine.
 +====== 64bit vs 32bit ======
 +
 +To switch between 64bit and 32bit use the flag ''-m64'', respectively ''-m32''.
 +
 +====== Streaming SIMD Extensions (SSE) ======
 +
 +The following is the list of ''SSE'' flags for the ''gcc'' compiler.
 +<code>
 +-msse2 -msse3 -mssse3 -msse4.1 -msse4.2
 +</code>
 +
 +They do not need to all be listed in the ''CFLAGS'' as the compiler will choose the most advanced one during compilation.
 +
 +====== 3DNow! ======
 +
 +For ''AMD''-based systems:
 +<code>
 +-m3dnow
 +</code>
 +
 +can be added in order to enable multimedia extensions.
 +
 +====== Intel i5 and i7 ======
 +
 +Both support ''SSE4.1'':
 +
 +<code>
 +-O2 -m64 -flto -msse4.1 -mfpmath=sse -ffast-math -funroll-loops
 +</code>
 +
 +For ''i7'' with ''Nehalem'' processors which support ''SSE4.2'', replace ''-msse4.1'' with ''-msse4.2''.
 +
 +====== Intel Atom N2xx and Z5xx ======
 +
 +<code>
 +-O2 -flto -mssse3 -mfpmath=sse
 +</code>
  

fuss/gcc_compile_flags.txt · Last modified: 2022/04/19 08:28 by 127.0.0.1

Access website using Tor Access website using i2p Wizardry and Steamworks PGP Key


For the contact, copyright, license, warranty and privacy terms for the usage of this website please see the contact, license, privacy, copyright.