diff options
| author | alk3pInjection <webmaster@raspii.tech> | 2024-02-04 16:16:35 +0800 |
|---|---|---|
| committer | alk3pInjection <webmaster@raspii.tech> | 2024-02-04 16:16:35 +0800 |
| commit | abdaadbcae30fe0c9a66c7516798279fdfd97750 (patch) | |
| tree | 00a54a6e25601e43876d03c1a4a12a749d4a914c /share/doc/gcc/x86-Options.html | |
https://developer.arm.com/downloads/-/arm-gnu-toolchain-downloads
Change-Id: I7303388733328cd98ab9aa3c30236db67f2e9e9c
Diffstat (limited to 'share/doc/gcc/x86-Options.html')
| -rw-r--r-- | share/doc/gcc/x86-Options.html | 2246 |
1 files changed, 2246 insertions, 0 deletions
diff --git a/share/doc/gcc/x86-Options.html b/share/doc/gcc/x86-Options.html new file mode 100644 index 0000000..51c167a --- /dev/null +++ b/share/doc/gcc/x86-Options.html @@ -0,0 +1,2246 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> +<html> +<!-- This file documents the use of the GNU compilers. + +Copyright (C) 1988-2023 Free Software Foundation, Inc. + +Permission is granted to copy, distribute and/or modify this document +under the terms of the GNU Free Documentation License, Version 1.3 or +any later version published by the Free Software Foundation; with the +Invariant Sections being "Funding Free Software", the Front-Cover +Texts being (a) (see below), and with the Back-Cover Texts being (b) +(see below). A copy of the license is included in the section entitled +"GNU Free Documentation License". + +(a) The FSF's Front-Cover Text is: + +A GNU Manual + +(b) The FSF's Back-Cover Text is: + +You have freedom to copy and modify this GNU Manual, like GNU + software. Copies published by the Free Software Foundation raise + funds for GNU development. --> +<!-- Created by GNU Texinfo 5.1, http://www.gnu.org/software/texinfo/ --> +<head> +<title>Using the GNU Compiler Collection (GCC): x86 Options</title> + +<meta name="description" content="Using the GNU Compiler Collection (GCC): x86 Options"> +<meta name="keywords" content="Using the GNU Compiler Collection (GCC): x86 Options"> +<meta name="resource-type" content="document"> +<meta name="distribution" content="global"> +<meta name="Generator" content="makeinfo"> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8"> +<link href="index.html#Top" rel="start" title="Top"> +<link href="Indices.html#Indices" rel="index" title="Indices"> +<link href="index.html#SEC_Contents" rel="contents" title="Table of Contents"> +<link href="Submodel-Options.html#Submodel-Options" rel="up" title="Submodel Options"> +<link href="x86-Windows-Options.html#x86-Windows-Options" rel="next" title="x86 Windows Options"> +<link href="VxWorks-Options.html#VxWorks-Options" rel="previous" title="VxWorks Options"> +<style type="text/css"> +<!-- +a.summary-letter {text-decoration: none} +blockquote.smallquotation {font-size: smaller} +div.display {margin-left: 3.2em} +div.example {margin-left: 3.2em} +div.indentedblock {margin-left: 3.2em} +div.lisp {margin-left: 3.2em} +div.smalldisplay {margin-left: 3.2em} +div.smallexample {margin-left: 3.2em} +div.smallindentedblock {margin-left: 3.2em; font-size: smaller} +div.smalllisp {margin-left: 3.2em} +kbd {font-style:oblique} +pre.display {font-family: inherit} +pre.format {font-family: inherit} +pre.menu-comment {font-family: serif} +pre.menu-preformatted {font-family: serif} +pre.smalldisplay {font-family: inherit; font-size: smaller} +pre.smallexample {font-size: smaller} +pre.smallformat {font-family: inherit; font-size: smaller} +pre.smalllisp {font-size: smaller} +span.nocodebreak {white-space:nowrap} +span.nolinebreak {white-space:nowrap} +span.roman {font-family:serif; font-weight:normal} +span.sansserif {font-family:sans-serif; font-weight:normal} +ul.no-bullet {list-style: none} +--> +</style> + + +</head> + +<body lang="en_US" bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#800080" alink="#FF0000"> +<a name="x86-Options"></a> +<div class="header"> +<p> +Next: <a href="x86-Windows-Options.html#x86-Windows-Options" accesskey="n" rel="next">x86 Windows Options</a>, Previous: <a href="VxWorks-Options.html#VxWorks-Options" accesskey="p" rel="previous">VxWorks Options</a>, Up: <a href="Submodel-Options.html#Submodel-Options" accesskey="u" rel="up">Submodel Options</a> [<a href="index.html#SEC_Contents" title="Table of contents" rel="contents">Contents</a>][<a href="Indices.html#Indices" title="Index" rel="index">Index</a>]</p> +</div> +<hr> +<a name="x86-Options-1"></a> +<h4 class="subsection">3.19.54 x86 Options</h4> +<a name="index-x86-Options"></a> + +<p>These ‘<samp>-m</samp>’ options are defined for the x86 family of computers. +</p> +<dl compact="compact"> +<dd> +<a name="index-march-16"></a> +</dd> +<dt><code>-march=<var>cpu-type</var></code></dt> +<dd><p>Generate instructions for the machine type <var>cpu-type</var>. In contrast to +<samp>-mtune=<var>cpu-type</var></samp>, which merely tunes the generated code +for the specified <var>cpu-type</var>, <samp>-march=<var>cpu-type</var></samp> allows GCC +to generate code that may not run at all on processors other than the one +indicated. Specifying <samp>-march=<var>cpu-type</var></samp> implies +<samp>-mtune=<var>cpu-type</var></samp>, except where noted otherwise. +</p> +<p>The choices for <var>cpu-type</var> are: +</p> +<dl compact="compact"> +<dt>‘<samp>native</samp>’</dt> +<dd><p>This selects the CPU to generate code for at compilation time by determining +the processor type of the compiling machine. Using <samp>-march=native</samp> +enables all instruction subsets supported by the local machine (hence +the result might not run on different machines). Using <samp>-mtune=native</samp> +produces code optimized for the local machine under the constraints +of the selected instruction set. +</p> +</dd> +<dt>‘<samp>x86-64</samp>’</dt> +<dd><p>A generic CPU with 64-bit extensions. +</p> +</dd> +<dt>‘<samp>x86-64-v2</samp>’</dt> +<dt>‘<samp>x86-64-v3</samp>’</dt> +<dt>‘<samp>x86-64-v4</samp>’</dt> +<dd><p>These choices for <var>cpu-type</var> select the corresponding +micro-architecture level from the x86-64 psABI. On ABIs other than +the x86-64 psABI they select the same CPU features as the x86-64 psABI +documents for the particular micro-architecture level. +</p> +<p>Since these <var>cpu-type</var> values do not have a corresponding +<samp>-mtune</samp> setting, using <samp>-march</samp> with these values enables +generic tuning. Specific tuning can be enabled using the +<samp>-mtune=<var>other-cpu-type</var></samp> option with an appropriate +<var>other-cpu-type</var> value. +</p> +</dd> +<dt>‘<samp>i386</samp>’</dt> +<dd><p>Original Intel i386 CPU. +</p> +</dd> +<dt>‘<samp>i486</samp>’</dt> +<dd><p>Intel i486 CPU. (No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>i586</samp>’</dt> +<dt>‘<samp>pentium</samp>’</dt> +<dd><p>Intel Pentium CPU with no MMX support. +</p> +</dd> +<dt>‘<samp>lakemont</samp>’</dt> +<dd><p>Intel Lakemont MCU, based on Intel Pentium CPU. +</p> +</dd> +<dt>‘<samp>pentium-mmx</samp>’</dt> +<dd><p>Intel Pentium MMX CPU, based on Pentium core with MMX instruction set support. +</p> +</dd> +<dt>‘<samp>pentiumpro</samp>’</dt> +<dd><p>Intel Pentium Pro CPU. +</p> +</dd> +<dt>‘<samp>i686</samp>’</dt> +<dd><p>When used with <samp>-march</samp>, the Pentium Pro +instruction set is used, so the code runs on all i686 family chips. +When used with <samp>-mtune</samp>, it has the same meaning as ‘<samp>generic</samp>’. +</p> +</dd> +<dt>‘<samp>pentium2</samp>’</dt> +<dd><p>Intel Pentium II CPU, based on Pentium Pro core with MMX and FXSR instruction +set support. +</p> +</dd> +<dt>‘<samp>pentium3</samp>’</dt> +<dt>‘<samp>pentium3m</samp>’</dt> +<dd><p>Intel Pentium III CPU, based on Pentium Pro core with MMX, FXSR and SSE +instruction set support. +</p> +</dd> +<dt>‘<samp>pentium-m</samp>’</dt> +<dd><p>Intel Pentium M; low-power version of Intel Pentium III CPU +with MMX, SSE, SSE2 and FXSR instruction set support. Used by Centrino +notebooks. +</p> +</dd> +<dt>‘<samp>pentium4</samp>’</dt> +<dt>‘<samp>pentium4m</samp>’</dt> +<dd><p>Intel Pentium 4 CPU with MMX, SSE, SSE2 and FXSR instruction set support. +</p> +</dd> +<dt>‘<samp>prescott</samp>’</dt> +<dd><p>Improved version of Intel Pentium 4 CPU with MMX, SSE, SSE2, SSE3 and FXSR +instruction set support. +</p> +</dd> +<dt>‘<samp>nocona</samp>’</dt> +<dd><p>Improved version of Intel Pentium 4 CPU with 64-bit extensions, MMX, SSE, +SSE2, SSE3 and FXSR instruction set support. +</p> +</dd> +<dt>‘<samp>core2</samp>’</dt> +<dd><p>Intel Core 2 CPU with 64-bit extensions, MMX, SSE, SSE2, SSE3, SSSE3, CX16, +SAHF and FXSR instruction set support. +</p> +</dd> +<dt>‘<samp>nehalem</samp>’</dt> +<dd><p>Intel Nehalem CPU with 64-bit extensions, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF and FXSR instruction set support. +</p> +</dd> +<dt>‘<samp>westmere</samp>’</dt> +<dd><p>Intel Westmere CPU with 64-bit extensions, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR and PCLMUL instruction set support. +</p> +</dd> +<dt>‘<samp>sandybridge</samp>’</dt> +<dd><p>Intel Sandy Bridge CPU with 64-bit extensions, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE and PCLMUL instruction set +support. +</p> +</dd> +<dt>‘<samp>ivybridge</samp>’</dt> +<dd><p>Intel Ivy Bridge CPU with 64-bit extensions, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, RDRND +and F16C instruction set support. +</p> +</dd> +<dt>‘<samp>haswell</samp>’</dt> +<dd><p>Intel Haswell CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, RDRND, +F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE and HLE instruction set support. +</p> +</dd> +<dt>‘<samp>broadwell</samp>’</dt> +<dd><p>Intel Broadwell CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, RDRND, +F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX and PREFETCHW +instruction set support. +</p> +</dd> +<dt>‘<samp>skylake</samp>’</dt> +<dd><p>Intel Skylake CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, RDRND, +F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, AES, +CLFLUSHOPT, XSAVEC, XSAVES and SGX instruction set support. +</p> +</dd> +<dt>‘<samp>bonnell</samp>’</dt> +<dd><p>Intel Bonnell CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3 and SSSE3 +instruction set support. +</p> +</dd> +<dt>‘<samp>silvermont</samp>’</dt> +<dd><p>Intel Silvermont CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, PCLMUL, PREFETCHW and RDRND +instruction set support. +</p> +</dd> +<dt>‘<samp>goldmont</samp>’</dt> +<dd><p>Intel Goldmont CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, PCLMUL, PREFETCHW, RDRND, AES, SHA, +RDSEED, XSAVE, XSAVEC, XSAVES, XSAVEOPT, CLFLUSHOPT and FSGSBASE instruction +set support. +</p> +</dd> +<dt>‘<samp>goldmont-plus</samp>’</dt> +<dd><p>Intel Goldmont Plus CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, PCLMUL, PREFETCHW, RDRND, AES, +SHA, RDSEED, XSAVE, XSAVEC, XSAVES, XSAVEOPT, CLFLUSHOPT, FSGSBASE, PTWRITE, +RDPID and SGX instruction set support. +</p> +</dd> +<dt>‘<samp>tremont</samp>’</dt> +<dd><p>Intel Tremont CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, PCLMUL, PREFETCHW, RDRND, AES, SHA, +RDSEED, XSAVE, XSAVEC, XSAVES, XSAVEOPT, CLFLUSHOPT, FSGSBASE, PTWRITE, RDPID, +SGX, CLWB, GFNI-SSE, MOVDIRI, MOVDIR64B, CLDEMOTE and WAITPKG instruction set +support. +</p> +</dd> +<dt>‘<samp>sierraforest</samp>’</dt> +<dd><p>Intel Sierra Forest CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, AES, PREFETCHW, PCLMUL, RDRND, XSAVE, XSAVEC, +XSAVES, XSAVEOPT, FSGSBASE, PTWRITE, RDPID, SGX, GFNI-SSE, CLWB, MOVDIRI, +MOVDIR64B, CLDEMOTE, WAITPKG, ADCX, AVX, AVX2, BMI, BMI2, F16C, FMA, LZCNT, +PCONFIG, PKU, VAES, VPCLMULQDQ, SERIALIZE, HRESET, KL, WIDEKL, AVX-VNNI, +AVXIFMA, AVXVNNIINT8, AVXNECONVERT, CMPCCXADD, ENQCMD and UINTR instruction set +support. +</p> +</dd> +<dt>‘<samp>grandridge</samp>’</dt> +<dd><p>Intel Grand Ridge CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, AES, PREFETCHW, PCLMUL, RDRND, XSAVE, XSAVEC, +XSAVES, XSAVEOPT, FSGSBASE, PTWRITE, RDPID, SGX, GFNI-SSE, CLWB, MOVDIRI, +MOVDIR64B, CLDEMOTE, WAITPKG, ADCX, AVX, AVX2, BMI, BMI2, F16C, FMA, LZCNT, +PCONFIG, PKU, VAES, VPCLMULQDQ, SERIALIZE, HRESET, KL, WIDEKL, AVX-VNNI, +AVXIFMA, AVXVNNIINT8, AVXNECONVERT, CMPCCXADD, ENQCMD, UINTR and RAOINT +instruction set support. +</p> +</dd> +<dt>‘<samp>knl</samp>’</dt> +<dd><p>Intel Knight’s Landing CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, +RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, +AVX512PF, AVX512ER, AVX512F, AVX512CD and PREFETCHWT1 instruction set support. +</p> +</dd> +<dt>‘<samp>knm</samp>’</dt> +<dd><p>Intel Knights Mill CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, +RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, +AVX512PF, AVX512ER, AVX512F, AVX512CD and PREFETCHWT1, AVX5124VNNIW, +AVX5124FMAPS and AVX512VPOPCNTDQ instruction set support. +</p> +</dd> +<dt>‘<samp>skylake-avx512</samp>’</dt> +<dd><p>Intel Skylake Server CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, +RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, +AES, CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, CLWB, AVX512VL, AVX512BW, +AVX512DQ and AVX512CD instruction set support. +</p> +</dd> +<dt>‘<samp>cannonlake</samp>’</dt> +<dd><p>Intel Cannonlake Server CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, +SSE3, SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, +FSGSBASE, RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, +PREFETCHW, AES, CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, AVX512VL, AVX512BW, +AVX512DQ, AVX512CD, PKU, AVX512VBMI, AVX512IFMA and SHA instruction set +support. +</p> +</dd> +<dt>‘<samp>icelake-client</samp>’</dt> +<dd><p>Intel Icelake Client CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, +RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, +AES, CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, AVX512VL, AVX512BW, AVX512DQ, +AVX512CD, PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2 +, VPCLMULQDQ, AVX512BITALG, RDPID and AVX512VPOPCNTDQ instruction set support. +</p> +</dd> +<dt>‘<samp>icelake-server</samp>’</dt> +<dd><p>Intel Icelake Server CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, +RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, +AES, CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, AVX512VL, AVX512BW, AVX512DQ, +AVX512CD, PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2 +, VPCLMULQDQ, AVX512BITALG, RDPID, AVX512VPOPCNTDQ, PCONFIG, WBNOINVD and CLWB +instruction set support. +</p> +</dd> +<dt>‘<samp>cascadelake</samp>’</dt> +<dd><p>Intel Cascadelake CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, RDRND, +F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, AES, +CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, CLWB, AVX512VL, AVX512BW, AVX512DQ, +AVX512CD and AVX512VNNI instruction set support. +</p> +</dd> +<dt>‘<samp>cooperlake</samp>’</dt> +<dd><p>Intel cooperlake CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, RDRND, +F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, AES, +CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, CLWB, AVX512VL, AVX512BW, AVX512DQ, +AVX512CD, AVX512VNNI and AVX512BF16 instruction set support. +</p> +</dd> +<dt>‘<samp>tigerlake</samp>’</dt> +<dd><p>Intel Tigerlake CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, RDRND, +F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, AES, +CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, AVX512VL, AVX512BW, AVX512DQ, AVX512CD +PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2, +VPCLMULQDQ, AVX512BITALG, RDPID, AVX512VPOPCNTDQ, MOVDIRI, MOVDIR64B, CLWB, +AVX512VP2INTERSECT and KEYLOCKER instruction set support. +</p> +</dd> +<dt>‘<samp>sapphirerapids</samp>’</dt> +<dd><p>Intel sapphirerapids CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, +RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, +AES, CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, AVX512VL, AVX512BW, AVX512DQ, +AVX512CD, PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2, +VPCLMULQDQ, AVX512BITALG, RDPID, AVX512VPOPCNTDQ, PCONFIG, WBNOINVD, CLWB, +MOVDIRI, MOVDIR64B, ENQCMD, CLDEMOTE, PTWRITE, WAITPKG, SERIALIZE, TSXLDTRK, +UINTR, AMX-BF16, AMX-TILE, AMX-INT8, AVX-VNNI, AVX512-FP16 and AVX512BF16 +instruction set support. +</p> +</dd> +<dt>‘<samp>alderlake</samp>’</dt> +<dd><p>Intel Alderlake CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, +SSE4.1, SSE4.2, POPCNT, AES, PREFETCHW, PCLMUL, RDRND, XSAVE, XSAVEC, XSAVES, +XSAVEOPT, FSGSBASE, PTWRITE, RDPID, SGX, GFNI-SSE, CLWB, MOVDIRI, MOVDIR64B, +CLDEMOTE, WAITPKG, ADCX, AVX, AVX2, BMI, BMI2, F16C, FMA, LZCNT, PCONFIG, PKU, +VAES, VPCLMULQDQ, SERIALIZE, HRESET, KL, WIDEKL and AVX-VNNI instruction set +support. +</p> +</dd> +<dt>‘<samp>rocketlake</samp>’</dt> +<dd><p>Intel Rocketlake CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3 +, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, RDRND, +F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, AES, +CLFLUSHOPT, XSAVEC, XSAVES, AVX512F, AVX512VL, AVX512BW, AVX512DQ, AVX512CD +PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2, +VPCLMULQDQ, AVX512BITALG, RDPID and AVX512VPOPCNTDQ instruction set support. +</p> +</dd> +<dt>‘<samp>graniterapids</samp>’</dt> +<dd><p>Intel graniterapids CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, +RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, +AES, CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, AVX512VL, AVX512BW, AVX512DQ, +AVX512CD, PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2, +VPCLMULQDQ, AVX512BITALG, RDPID, AVX512VPOPCNTDQ, PCONFIG, WBNOINVD, CLWB, +MOVDIRI, MOVDIR64B, ENQCMD, CLDEMOTE, PTWRITE, WAITPKG, SERIALIZE, TSXLDTRK, +UINTR, AMX-BF16, AMX-TILE, AMX-INT8, AVX-VNNI, AVX512-FP16, AVX512BF16, AMX-FP16 +and PREFETCHI instruction set support. +</p> +</dd> +<dt>‘<samp>graniterapids-d</samp>’</dt> +<dd><p>Intel graniterapids D CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, +SSSE3, SSE4.1, SSE4.2, POPCNT, CX16, SAHF, FXSR, AVX, XSAVE, PCLMUL, FSGSBASE, +RDRND, F16C, AVX2, BMI, BMI2, LZCNT, FMA, MOVBE, HLE, RDSEED, ADCX, PREFETCHW, +AES, CLFLUSHOPT, XSAVEC, XSAVES, SGX, AVX512F, AVX512VL, AVX512BW, AVX512DQ, +AVX512CD, PKU, AVX512VBMI, AVX512IFMA, SHA, AVX512VNNI, GFNI, VAES, AVX512VBMI2, +VPCLMULQDQ, AVX512BITALG, RDPID, AVX512VPOPCNTDQ, PCONFIG, WBNOINVD, CLWB, +MOVDIRI, MOVDIR64B, ENQCMD, CLDEMOTE, PTWRITE, WAITPKG, SERIALIZE, TSXLDTRK, +UINTR, AMX-BF16, AMX-TILE, AMX-INT8, AVX-VNNI, AVX512FP16, AVX512BF16, AMX-FP16, +PREFETCHI and AMX-COMPLEX instruction set support. +</p> +</dd> +<dt>‘<samp>k6</samp>’</dt> +<dd><p>AMD K6 CPU with MMX instruction set support. +</p> +</dd> +<dt>‘<samp>k6-2</samp>’</dt> +<dt>‘<samp>k6-3</samp>’</dt> +<dd><p>Improved versions of AMD K6 CPU with MMX and 3DNow! instruction set support. +</p> +</dd> +<dt>‘<samp>athlon</samp>’</dt> +<dt>‘<samp>athlon-tbird</samp>’</dt> +<dd><p>AMD Athlon CPU with MMX, 3dNOW!, enhanced 3DNow! and SSE prefetch instructions +support. +</p> +</dd> +<dt>‘<samp>athlon-4</samp>’</dt> +<dt>‘<samp>athlon-xp</samp>’</dt> +<dt>‘<samp>athlon-mp</samp>’</dt> +<dd><p>Improved AMD Athlon CPU with MMX, 3DNow!, enhanced 3DNow! and full SSE +instruction set support. +</p> +</dd> +<dt>‘<samp>k8</samp>’</dt> +<dt>‘<samp>opteron</samp>’</dt> +<dt>‘<samp>athlon64</samp>’</dt> +<dt>‘<samp>athlon-fx</samp>’</dt> +<dd><p>Processors based on the AMD K8 core with x86-64 instruction set support, +including the AMD Opteron, Athlon 64, and Athlon 64 FX processors. +(This supersets MMX, SSE, SSE2, 3DNow!, enhanced 3DNow! and 64-bit +instruction set extensions.) +</p> +</dd> +<dt>‘<samp>k8-sse3</samp>’</dt> +<dt>‘<samp>opteron-sse3</samp>’</dt> +<dt>‘<samp>athlon64-sse3</samp>’</dt> +<dd><p>Improved versions of AMD K8 cores with SSE3 instruction set support. +</p> +</dd> +<dt>‘<samp>amdfam10</samp>’</dt> +<dt>‘<samp>barcelona</samp>’</dt> +<dd><p>CPUs based on AMD Family 10h cores with x86-64 instruction set support. (This +supersets MMX, SSE, SSE2, SSE3, SSE4A, 3DNow!, enhanced 3DNow!, ABM and 64-bit +instruction set extensions.) +</p> +</dd> +<dt>‘<samp>bdver1</samp>’</dt> +<dd><p>CPUs based on AMD Family 15h cores with x86-64 instruction set support. (This +supersets FMA4, AVX, XOP, LWP, AES, PCLMUL, CX16, MMX, SSE, SSE2, SSE3, SSE4A, +SSSE3, SSE4.1, SSE4.2, ABM and 64-bit instruction set extensions.) +</p> +</dd> +<dt>‘<samp>bdver2</samp>’</dt> +<dd><p>AMD Family 15h core based CPUs with x86-64 instruction set support. (This +supersets BMI, TBM, F16C, FMA, FMA4, AVX, XOP, LWP, AES, PCLMUL, CX16, MMX, +SSE, SSE2, SSE3, SSE4A, SSSE3, SSE4.1, SSE4.2, ABM and 64-bit instruction set +extensions.) +</p> +</dd> +<dt>‘<samp>bdver3</samp>’</dt> +<dd><p>AMD Family 15h core based CPUs with x86-64 instruction set support. (This +supersets BMI, TBM, F16C, FMA, FMA4, FSGSBASE, AVX, XOP, LWP, AES, +PCLMUL, CX16, MMX, SSE, SSE2, SSE3, SSE4A, SSSE3, SSE4.1, SSE4.2, ABM and +64-bit instruction set extensions.) +</p> +</dd> +<dt>‘<samp>bdver4</samp>’</dt> +<dd><p>AMD Family 15h core based CPUs with x86-64 instruction set support. (This +supersets BMI, BMI2, TBM, F16C, FMA, FMA4, FSGSBASE, AVX, AVX2, XOP, LWP, +AES, PCLMUL, CX16, MOVBE, MMX, SSE, SSE2, SSE3, SSE4A, SSSE3, SSE4.1, +SSE4.2, ABM and 64-bit instruction set extensions.) +</p> +</dd> +<dt>‘<samp>znver1</samp>’</dt> +<dd><p>AMD Family 17h core based CPUs with x86-64 instruction set support. (This +supersets BMI, BMI2, F16C, FMA, FSGSBASE, AVX, AVX2, ADCX, RDSEED, MWAITX, +SHA, CLZERO, AES, PCLMUL, CX16, MOVBE, MMX, SSE, SSE2, SSE3, SSE4A, SSSE3, +SSE4.1, SSE4.2, ABM, XSAVEC, XSAVES, CLFLUSHOPT, POPCNT, and 64-bit +instruction set extensions.) +</p> +</dd> +<dt>‘<samp>znver2</samp>’</dt> +<dd><p>AMD Family 17h core based CPUs with x86-64 instruction set support. (This +supersets BMI, BMI2, CLWB, F16C, FMA, FSGSBASE, AVX, AVX2, ADCX, RDSEED, +MWAITX, SHA, CLZERO, AES, PCLMUL, CX16, MOVBE, MMX, SSE, SSE2, SSE3, SSE4A, +SSSE3, SSE4.1, SSE4.2, ABM, XSAVEC, XSAVES, CLFLUSHOPT, POPCNT, RDPID, +WBNOINVD, and 64-bit instruction set extensions.) +</p> +</dd> +<dt>‘<samp>znver3</samp>’</dt> +<dd><p>AMD Family 19h core based CPUs with x86-64 instruction set support. (This +supersets BMI, BMI2, CLWB, F16C, FMA, FSGSBASE, AVX, AVX2, ADCX, RDSEED, +MWAITX, SHA, CLZERO, AES, PCLMUL, CX16, MOVBE, MMX, SSE, SSE2, SSE3, SSE4A, +SSSE3, SSE4.1, SSE4.2, ABM, XSAVEC, XSAVES, CLFLUSHOPT, POPCNT, RDPID, +WBNOINVD, PKU, VPCLMULQDQ, VAES, and 64-bit instruction set extensions.) +</p> +</dd> +<dt>‘<samp>znver4</samp>’</dt> +<dd><p>AMD Family 19h core based CPUs with x86-64 instruction set support. (This +supersets BMI, BMI2, CLWB, F16C, FMA, FSGSBASE, AVX, AVX2, ADCX, RDSEED, +MWAITX, SHA, CLZERO, AES, PCLMUL, CX16, MOVBE, MMX, SSE, SSE2, SSE3, SSE4A, +SSSE3, SSE4.1, SSE4.2, ABM, XSAVEC, XSAVES, CLFLUSHOPT, POPCNT, RDPID, +WBNOINVD, PKU, VPCLMULQDQ, VAES, AVX512F, AVX512DQ, AVX512IFMA, AVX512CD, +AVX512BW, AVX512VL, AVX512BF16, AVX512VBMI, AVX512VBMI2, AVX512VNNI, +AVX512BITALG, AVX512VPOPCNTDQ, GFNI and 64-bit instruction set extensions.) +</p> +</dd> +<dt>‘<samp>btver1</samp>’</dt> +<dd><p>CPUs based on AMD Family 14h cores with x86-64 instruction set support. (This +supersets MMX, SSE, SSE2, SSE3, SSSE3, SSE4A, CX16, ABM and 64-bit +instruction set extensions.) +</p> +</dd> +<dt>‘<samp>btver2</samp>’</dt> +<dd><p>CPUs based on AMD Family 16h cores with x86-64 instruction set support. This +includes MOVBE, F16C, BMI, AVX, PCLMUL, AES, SSE4.2, SSE4.1, CX16, ABM, +SSE4A, SSSE3, SSE3, SSE2, SSE, MMX and 64-bit instruction set extensions. +</p> +</dd> +<dt>‘<samp>winchip-c6</samp>’</dt> +<dd><p>IDT WinChip C6 CPU, dealt in same way as i486 with additional MMX instruction +set support. +</p> +</dd> +<dt>‘<samp>winchip2</samp>’</dt> +<dd><p>IDT WinChip 2 CPU, dealt in same way as i486 with additional MMX and 3DNow! +instruction set support. +</p> +</dd> +<dt>‘<samp>c3</samp>’</dt> +<dd><p>VIA C3 CPU with MMX and 3DNow! instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>c3-2</samp>’</dt> +<dd><p>VIA C3-2 (Nehemiah/C5XL) CPU with MMX and SSE instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>c7</samp>’</dt> +<dd><p>VIA C7 (Esther) CPU with MMX, SSE, SSE2 and SSE3 instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>samuel-2</samp>’</dt> +<dd><p>VIA Eden Samuel 2 CPU with MMX and 3DNow! instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>nehemiah</samp>’</dt> +<dd><p>VIA Eden Nehemiah CPU with MMX and SSE instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>esther</samp>’</dt> +<dd><p>VIA Eden Esther CPU with MMX, SSE, SSE2 and SSE3 instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>eden-x2</samp>’</dt> +<dd><p>VIA Eden X2 CPU with x86-64, MMX, SSE, SSE2 and SSE3 instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>eden-x4</samp>’</dt> +<dd><p>VIA Eden X4 CPU with x86-64, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, +AVX and AVX2 instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>nano</samp>’</dt> +<dd><p>Generic VIA Nano CPU with x86-64, MMX, SSE, SSE2, SSE3 and SSSE3 +instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>nano-1000</samp>’</dt> +<dd><p>VIA Nano 1xxx CPU with x86-64, MMX, SSE, SSE2, SSE3 and SSSE3 +instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>nano-2000</samp>’</dt> +<dd><p>VIA Nano 2xxx CPU with x86-64, MMX, SSE, SSE2, SSE3 and SSSE3 +instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>nano-3000</samp>’</dt> +<dd><p>VIA Nano 3xxx CPU with x86-64, MMX, SSE, SSE2, SSE3, SSSE3 and SSE4.1 +instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>nano-x2</samp>’</dt> +<dd><p>VIA Nano Dual Core CPU with x86-64, MMX, SSE, SSE2, SSE3, SSSE3 and SSE4.1 +instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>nano-x4</samp>’</dt> +<dd><p>VIA Nano Quad Core CPU with x86-64, MMX, SSE, SSE2, SSE3, SSSE3 and SSE4.1 +instruction set support. +(No scheduling is implemented for this chip.) +</p> +</dd> +<dt>‘<samp>lujiazui</samp>’</dt> +<dd><p>ZHAOXIN lujiazui CPU with x86-64, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, +SSE4.2, AVX, POPCNT, AES, PCLMUL, RDRND, XSAVE, XSAVEOPT, FSGSBASE, CX16, +ABM, BMI, BMI2, F16C, FXSR, RDSEED instruction set support. +</p> +</dd> +<dt>‘<samp>geode</samp>’</dt> +<dd><p>AMD Geode embedded processor with MMX and 3DNow! instruction set support. +</p></dd> +</dl> + +<a name="index-mtune-17"></a> +</dd> +<dt><code>-mtune=<var>cpu-type</var></code></dt> +<dd><p>Tune to <var>cpu-type</var> everything applicable about the generated code, except +for the ABI and the set of available instructions. +While picking a specific <var>cpu-type</var> schedules things appropriately +for that particular chip, the compiler does not generate any code that +cannot run on the default machine type unless you use a +<samp>-march=<var>cpu-type</var></samp> option. +For example, if GCC is configured for i686-pc-linux-gnu +then <samp>-mtune=pentium4</samp> generates code that is tuned for Pentium 4 +but still runs on i686 machines. +</p> +<p>The choices for <var>cpu-type</var> are the same as for <samp>-march</samp>. +In addition, <samp>-mtune</samp> supports 2 extra choices for <var>cpu-type</var>: +</p> +<dl compact="compact"> +<dt>‘<samp>generic</samp>’</dt> +<dd><p>Produce code optimized for the most common IA32/AMD64/EM64T processors. +If you know the CPU on which your code will run, then you should use +the corresponding <samp>-mtune</samp> or <samp>-march</samp> option instead of +<samp>-mtune=generic</samp>. But, if you do not know exactly what CPU users +of your application will have, then you should use this option. +</p> +<p>As new processors are deployed in the marketplace, the behavior of this +option will change. Therefore, if you upgrade to a newer version of +GCC, code generation controlled by this option will change to reflect +the processors +that are most common at the time that version of GCC is released. +</p> +<p>There is no <samp>-march=generic</samp> option because <samp>-march</samp> +indicates the instruction set the compiler can use, and there is no +generic instruction set applicable to all processors. In contrast, +<samp>-mtune</samp> indicates the processor (or, in this case, collection of +processors) for which the code is optimized. +</p> +</dd> +<dt>‘<samp>intel</samp>’</dt> +<dd><p>Produce code optimized for the most current Intel processors, which are +Haswell and Silvermont for this version of GCC. If you know the CPU +on which your code will run, then you should use the corresponding +<samp>-mtune</samp> or <samp>-march</samp> option instead of <samp>-mtune=intel</samp>. +But, if you want your application performs better on both Haswell and +Silvermont, then you should use this option. +</p> +<p>As new Intel processors are deployed in the marketplace, the behavior of +this option will change. Therefore, if you upgrade to a newer version of +GCC, code generation controlled by this option will change to reflect +the most current Intel processors at the time that version of GCC is +released. +</p> +<p>There is no <samp>-march=intel</samp> option because <samp>-march</samp> indicates +the instruction set the compiler can use, and there is no common +instruction set applicable to all processors. In contrast, +<samp>-mtune</samp> indicates the processor (or, in this case, collection of +processors) for which the code is optimized. +</p></dd> +</dl> + +<a name="index-mcpu-14"></a> +</dd> +<dt><code>-mcpu=<var>cpu-type</var></code></dt> +<dd><p>A deprecated synonym for <samp>-mtune</samp>. +</p> +<a name="index-mfpmath-1"></a> +</dd> +<dt><code>-mfpmath=<var>unit</var></code></dt> +<dd><p>Generate floating-point arithmetic for selected unit <var>unit</var>. The choices +for <var>unit</var> are: +</p> +<dl compact="compact"> +<dt>‘<samp>387</samp>’</dt> +<dd><p>Use the standard 387 floating-point coprocessor present on the majority of chips and +emulated otherwise. Code compiled with this option runs almost everywhere. +The temporary results are computed in 80-bit precision instead of the precision +specified by the type, resulting in slightly different results compared to most +of other chips. See <samp>-ffloat-store</samp> for more detailed description. +</p> +<p>This is the default choice for non-Darwin x86-32 targets. +</p> +</dd> +<dt>‘<samp>sse</samp>’</dt> +<dd><p>Use scalar floating-point instructions present in the SSE instruction set. +This instruction set is supported by Pentium III and newer chips, +and in the AMD line +by Athlon-4, Athlon XP and Athlon MP chips. The earlier version of the SSE +instruction set supports only single-precision arithmetic, thus the double and +extended-precision arithmetic are still done using 387. A later version, present +only in Pentium 4 and AMD x86-64 chips, supports double-precision +arithmetic too. +</p> +<p>For the x86-32 compiler, you must use <samp>-march=<var>cpu-type</var></samp>, <samp>-msse</samp> +or <samp>-msse2</samp> switches to enable SSE extensions and make this option +effective. For the x86-64 compiler, these extensions are enabled by default. +</p> +<p>The resulting code should be considerably faster in the majority of cases and avoid +the numerical instability problems of 387 code, but may break some existing +code that expects temporaries to be 80 bits. +</p> +<p>This is the default choice for the x86-64 compiler, Darwin x86-32 targets, +and the default choice for x86-32 targets with the SSE2 instruction set +when <samp>-ffast-math</samp> is enabled. +</p> +</dd> +<dt>‘<samp>sse,387</samp>’</dt> +<dt>‘<samp>sse+387</samp>’</dt> +<dt>‘<samp>both</samp>’</dt> +<dd><p>Attempt to utilize both instruction sets at once. This effectively doubles the +amount of available registers, and on chips with separate execution units for +387 and SSE the execution resources too. Use this option with care, as it is +still experimental, because the GCC register allocator does not model separate +functional units well, resulting in unstable performance. +</p></dd> +</dl> + +<a name="index-masm_003ddialect"></a> +</dd> +<dt><code>-masm=<var>dialect</var></code></dt> +<dd><p>Output assembly instructions using selected <var>dialect</var>. Also affects +which dialect is used for basic <code>asm</code> (see <a href="Basic-Asm.html#Basic-Asm">Basic Asm</a>) and +extended <code>asm</code> (see <a href="Extended-Asm.html#Extended-Asm">Extended Asm</a>). Supported choices (in dialect +order) are ‘<samp>att</samp>’ or ‘<samp>intel</samp>’. The default is ‘<samp>att</samp>’. Darwin does +not support ‘<samp>intel</samp>’. +</p> +<a name="index-mieee_002dfp"></a> +<a name="index-mno_002dieee_002dfp"></a> +</dd> +<dt><code>-mieee-fp</code></dt> +<dt><code>-mno-ieee-fp</code></dt> +<dd><p>Control whether or not the compiler uses IEEE floating-point +comparisons. These correctly handle the case where the result of a +comparison is unordered. +</p> +<a name="index-m80387"></a> +<a name="index-mhard_002dfloat-11"></a> +</dd> +<dt><code>-m80387</code></dt> +<dt><code>-mhard-float</code></dt> +<dd><p>Generate output containing 80387 instructions for floating point. +</p> +<a name="index-no_002d80387"></a> +<a name="index-msoft_002dfloat-16"></a> +</dd> +<dt><code>-mno-80387</code></dt> +<dt><code>-msoft-float</code></dt> +<dd><p>Generate output containing library calls for floating point. +</p> +<p><strong>Warning:</strong> the requisite libraries are not part of GCC. +Normally the facilities of the machine’s usual C compiler are used, but +this cannot be done directly in cross-compilation. You must make your +own arrangements to provide suitable library functions for +cross-compilation. +</p> +<p>On machines where a function returns floating-point results in the 80387 +register stack, some floating-point opcodes may be emitted even if +<samp>-msoft-float</samp> is used. +</p> +<a name="index-mno_002dfp_002dret_002din_002d387"></a> +<a name="index-mfp_002dret_002din_002d387"></a> +</dd> +<dt><code>-mno-fp-ret-in-387</code></dt> +<dd><p>Do not use the FPU registers for return values of functions. +</p> +<p>The usual calling convention has functions return values of types +<code>float</code> and <code>double</code> in an FPU register, even if there +is no FPU. The idea is that the operating system should emulate +an FPU. +</p> +<p>The option <samp>-mno-fp-ret-in-387</samp> causes such values to be returned +in ordinary CPU registers instead. +</p> +<a name="index-mno_002dfancy_002dmath_002d387"></a> +<a name="index-mfancy_002dmath_002d387"></a> +</dd> +<dt><code>-mno-fancy-math-387</code></dt> +<dd><p>Some 387 emulators do not support the <code>sin</code>, <code>cos</code> and +<code>sqrt</code> instructions for the 387. Specify this option to avoid +generating those instructions. +This option is overridden when <samp>-march</samp> +indicates that the target CPU always has an FPU and so the +instruction does not need emulation. These +instructions are not generated unless you also use the +<samp>-funsafe-math-optimizations</samp> switch. +</p> +<a name="index-malign_002ddouble"></a> +<a name="index-mno_002dalign_002ddouble"></a> +</dd> +<dt><code>-malign-double</code></dt> +<dt><code>-mno-align-double</code></dt> +<dd><p>Control whether GCC aligns <code>double</code>, <code>long double</code>, and +<code>long long</code> variables on a two-word boundary or a one-word +boundary. Aligning <code>double</code> variables on a two-word boundary +produces code that runs somewhat faster on a Pentium at the +expense of more memory. +</p> +<p>On x86-64, <samp>-malign-double</samp> is enabled by default. +</p> +<p><strong>Warning:</strong> if you use the <samp>-malign-double</samp> switch, +structures containing the above types are aligned differently than +the published application binary interface specifications for the x86-32 +and are not binary compatible with structures in code compiled +without that switch. +</p> +<a name="index-m96bit_002dlong_002ddouble"></a> +<a name="index-m128bit_002dlong_002ddouble"></a> +</dd> +<dt><code>-m96bit-long-double</code></dt> +<dt><code>-m128bit-long-double</code></dt> +<dd><p>These switches control the size of <code>long double</code> type. The x86-32 +application binary interface specifies the size to be 96 bits, +so <samp>-m96bit-long-double</samp> is the default in 32-bit mode. +</p> +<p>Modern architectures (Pentium and newer) prefer <code>long double</code> +to be aligned to an 8- or 16-byte boundary. In arrays or structures +conforming to the ABI, this is not possible. So specifying +<samp>-m128bit-long-double</samp> aligns <code>long double</code> +to a 16-byte boundary by padding the <code>long double</code> with an additional +32-bit zero. +</p> +<p>In the x86-64 compiler, <samp>-m128bit-long-double</samp> is the default choice as +its ABI specifies that <code>long double</code> is aligned on 16-byte boundary. +</p> +<p>Notice that neither of these options enable any extra precision over the x87 +standard of 80 bits for a <code>long double</code>. +</p> +<p><strong>Warning:</strong> if you override the default value for your target ABI, this +changes the size of +structures and arrays containing <code>long double</code> variables, +as well as modifying the function calling convention for functions taking +<code>long double</code>. Hence they are not binary-compatible +with code compiled without that switch. +</p> +<a name="index-mlong_002ddouble_002d64-1"></a> +<a name="index-mlong_002ddouble_002d80"></a> +<a name="index-mlong_002ddouble_002d128-1"></a> +</dd> +<dt><code>-mlong-double-64</code></dt> +<dt><code>-mlong-double-80</code></dt> +<dt><code>-mlong-double-128</code></dt> +<dd><p>These switches control the size of <code>long double</code> type. A size +of 64 bits makes the <code>long double</code> type equivalent to the <code>double</code> +type. This is the default for 32-bit Bionic C library. A size +of 128 bits makes the <code>long double</code> type equivalent to the +<code>__float128</code> type. This is the default for 64-bit Bionic C library. +</p> +<p><strong>Warning:</strong> if you override the default value for your target ABI, this +changes the size of +structures and arrays containing <code>long double</code> variables, +as well as modifying the function calling convention for functions taking +<code>long double</code>. Hence they are not binary-compatible +with code compiled without that switch. +</p> +<a name="index-malign_002ddata-1"></a> +</dd> +<dt><code>-malign-data=<var>type</var></code></dt> +<dd><p>Control how GCC aligns variables. Supported values for <var>type</var> are +‘<samp>compat</samp>’ uses increased alignment value compatible uses GCC 4.8 +and earlier, ‘<samp>abi</samp>’ uses alignment value as specified by the +psABI, and ‘<samp>cacheline</samp>’ uses increased alignment value to match +the cache line size. ‘<samp>compat</samp>’ is the default. +</p> +<a name="index-mlarge_002ddata_002dthreshold"></a> +</dd> +<dt><code>-mlarge-data-threshold=<var>threshold</var></code></dt> +<dd><p>When <samp>-mcmodel=medium</samp> is specified, data objects larger than +<var>threshold</var> are placed in the large data section. This value must be the +same across all objects linked into the binary, and defaults to 65535. +</p> +<a name="index-mrtd-1"></a> +</dd> +<dt><code>-mrtd</code></dt> +<dd><p>Use a different function-calling convention, in which functions that +take a fixed number of arguments return with the <code>ret <var>num</var></code> +instruction, which pops their arguments while returning. This saves one +instruction in the caller since there is no need to pop the arguments +there. +</p> +<p>You can specify that an individual function is called with this calling +sequence with the function attribute <code>stdcall</code>. You can also +override the <samp>-mrtd</samp> option by using the function attribute +<code>cdecl</code>. See <a href="Function-Attributes.html#Function-Attributes">Function Attributes</a>. +</p> +<p><strong>Warning:</strong> this calling convention is incompatible with the one +normally used on Unix, so you cannot use it if you need to call +libraries compiled with the Unix compiler. +</p> +<p>Also, you must provide function prototypes for all functions that +take variable numbers of arguments (including <code>printf</code>); +otherwise incorrect code is generated for calls to those +functions. +</p> +<p>In addition, seriously incorrect code results if you call a +function with too many arguments. (Normally, extra arguments are +harmlessly ignored.) +</p> +<a name="index-mregparm"></a> +</dd> +<dt><code>-mregparm=<var>num</var></code></dt> +<dd><p>Control how many registers are used to pass integer arguments. By +default, no registers are used to pass arguments, and at most 3 +registers can be used. You can control this behavior for a specific +function by using the function attribute <code>regparm</code>. +See <a href="Function-Attributes.html#Function-Attributes">Function Attributes</a>. +</p> +<p><strong>Warning:</strong> if you use this switch, and +<var>num</var> is nonzero, then you must build all modules with the same +value, including any libraries. This includes the system libraries and +startup modules. +</p> +<a name="index-msseregparm"></a> +</dd> +<dt><code>-msseregparm</code></dt> +<dd><p>Use SSE register passing conventions for float and double arguments +and return values. You can control this behavior for a specific +function by using the function attribute <code>sseregparm</code>. +See <a href="Function-Attributes.html#Function-Attributes">Function Attributes</a>. +</p> +<p><strong>Warning:</strong> if you use this switch then you must build all +modules with the same value, including any libraries. This includes +the system libraries and startup modules. +</p> +<a name="index-mvect8_002dret_002din_002dmem"></a> +</dd> +<dt><code>-mvect8-ret-in-mem</code></dt> +<dd><p>Return 8-byte vectors in memory instead of MMX registers. This is the +default on VxWorks to match the ABI of the Sun Studio compilers until +version 12. <em>Only</em> use this option if you need to remain +compatible with existing code produced by those previous compiler +versions or older versions of GCC. +</p> +<a name="index-mpc32"></a> +<a name="index-mpc64"></a> +<a name="index-mpc80"></a> +</dd> +<dt><code>-mpc32</code></dt> +<dt><code>-mpc64</code></dt> +<dt><code>-mpc80</code></dt> +<dd> +<p>Set 80387 floating-point precision to 32, 64 or 80 bits. When <samp>-mpc32</samp> +is specified, the significands of results of floating-point operations are +rounded to 24 bits (single precision); <samp>-mpc64</samp> rounds the +significands of results of floating-point operations to 53 bits (double +precision) and <samp>-mpc80</samp> rounds the significands of results of +floating-point operations to 64 bits (extended double precision), which is +the default. When this option is used, floating-point operations in higher +precisions are not available to the programmer without setting the FPU +control word explicitly. +</p> +<p>Setting the rounding of floating-point operations to less than the default +80 bits can speed some programs by 2% or more. Note that some mathematical +libraries assume that extended-precision (80-bit) floating-point operations +are enabled by default; routines in such libraries could suffer significant +loss of accuracy, typically through so-called “catastrophic cancellation”, +when this option is used to set the precision to less than extended precision. +</p> +<a name="index-mdaz_002dftz"></a> +</dd> +<dt><code>-mdaz-ftz</code></dt> +<dd> +<p>The flush-to-zero (FTZ) and denormals-are-zero (DAZ) flags in the MXCSR register +are used to control floating-point calculations.SSE and AVX instructions +including scalar and vector instructions could benefit from enabling the FTZ +and DAZ flags when <samp>-mdaz-ftz</samp> is specified. Don’t set FTZ/DAZ flags +when <samp>-mno-daz-ftz</samp> or <samp>-shared</samp> is specified, <samp>-mdaz-ftz</samp> +will set FTZ/DAZ flags even with <samp>-shared</samp>. +</p> +<a name="index-mstackrealign"></a> +</dd> +<dt><code>-mstackrealign</code></dt> +<dd><p>Realign the stack at entry. On the x86, the <samp>-mstackrealign</samp> +option generates an alternate prologue and epilogue that realigns the +run-time stack if necessary. This supports mixing legacy codes that keep +4-byte stack alignment with modern codes that keep 16-byte stack alignment for +SSE compatibility. See also the attribute <code>force_align_arg_pointer</code>, +applicable to individual functions. +</p> +<a name="index-mpreferred_002dstack_002dboundary-1"></a> +</dd> +<dt><code>-mpreferred-stack-boundary=<var>num</var></code></dt> +<dd><p>Attempt to keep the stack boundary aligned to a 2 raised to <var>num</var> +byte boundary. If <samp>-mpreferred-stack-boundary</samp> is not specified, +the default is 4 (16 bytes or 128 bits). +</p> +<p><strong>Warning:</strong> When generating code for the x86-64 architecture with +SSE extensions disabled, <samp>-mpreferred-stack-boundary=3</samp> can be +used to keep the stack boundary aligned to 8 byte boundary. Since +x86-64 ABI require 16 byte stack alignment, this is ABI incompatible and +intended to be used in controlled environment where stack space is +important limitation. This option leads to wrong code when functions +compiled with 16 byte stack alignment (such as functions from a standard +library) are called with misaligned stack. In this case, SSE +instructions may lead to misaligned memory access traps. In addition, +variable arguments are handled incorrectly for 16 byte aligned +objects (including x87 long double and __int128), leading to wrong +results. You must build all modules with +<samp>-mpreferred-stack-boundary=3</samp>, including any libraries. This +includes the system libraries and startup modules. +</p> +<a name="index-mincoming_002dstack_002dboundary"></a> +</dd> +<dt><code>-mincoming-stack-boundary=<var>num</var></code></dt> +<dd><p>Assume the incoming stack is aligned to a 2 raised to <var>num</var> byte +boundary. If <samp>-mincoming-stack-boundary</samp> is not specified, +the one specified by <samp>-mpreferred-stack-boundary</samp> is used. +</p> +<p>On Pentium and Pentium Pro, <code>double</code> and <code>long double</code> values +should be aligned to an 8-byte boundary (see <samp>-malign-double</samp>) or +suffer significant run time performance penalties. On Pentium III, the +Streaming SIMD Extension (SSE) data type <code>__m128</code> may not work +properly if it is not 16-byte aligned. +</p> +<p>To ensure proper alignment of this values on the stack, the stack boundary +must be as aligned as that required by any value stored on the stack. +Further, every function must be generated such that it keeps the stack +aligned. Thus calling a function compiled with a higher preferred +stack boundary from a function compiled with a lower preferred stack +boundary most likely misaligns the stack. It is recommended that +libraries that use callbacks always use the default setting. +</p> +<p>This extra alignment does consume extra stack space, and generally +increases code size. Code that is sensitive to stack space usage, such +as embedded systems and operating system kernels, may want to reduce the +preferred alignment to <samp>-mpreferred-stack-boundary=2</samp>. +</p> +<a name="index-mmmx"></a> +</dd> +<dt><code>-mmmx</code></dt> +<dd><a name="index-msse"></a> +</dd> +<dt><code>-msse</code></dt> +<dd><a name="index-msse2"></a> +</dd> +<dt><code>-msse2</code></dt> +<dd><a name="index-msse3"></a> +</dd> +<dt><code>-msse3</code></dt> +<dd><a name="index-mssse3"></a> +</dd> +<dt><code>-mssse3</code></dt> +<dd><a name="index-msse4"></a> +</dd> +<dt><code>-msse4</code></dt> +<dd><a name="index-msse4a"></a> +</dd> +<dt><code>-msse4a</code></dt> +<dd><a name="index-msse4_002e1"></a> +</dd> +<dt><code>-msse4.1</code></dt> +<dd><a name="index-msse4_002e2"></a> +</dd> +<dt><code>-msse4.2</code></dt> +<dd><a name="index-mavx"></a> +</dd> +<dt><code>-mavx</code></dt> +<dd><a name="index-mavx2"></a> +</dd> +<dt><code>-mavx2</code></dt> +<dd><a name="index-mavx512f"></a> +</dd> +<dt><code>-mavx512f</code></dt> +<dd><a name="index-mavx512pf"></a> +</dd> +<dt><code>-mavx512pf</code></dt> +<dd><a name="index-mavx512er"></a> +</dd> +<dt><code>-mavx512er</code></dt> +<dd><a name="index-mavx512cd"></a> +</dd> +<dt><code>-mavx512cd</code></dt> +<dd><a name="index-mavx512vl"></a> +</dd> +<dt><code>-mavx512vl</code></dt> +<dd><a name="index-mavx512bw"></a> +</dd> +<dt><code>-mavx512bw</code></dt> +<dd><a name="index-mavx512dq"></a> +</dd> +<dt><code>-mavx512dq</code></dt> +<dd><a name="index-mavx512ifma"></a> +</dd> +<dt><code>-mavx512ifma</code></dt> +<dd><a name="index-mavx512vbmi"></a> +</dd> +<dt><code>-mavx512vbmi</code></dt> +<dd><a name="index-msha"></a> +</dd> +<dt><code>-msha</code></dt> +<dd><a name="index-maes"></a> +</dd> +<dt><code>-maes</code></dt> +<dd><a name="index-mpclmul"></a> +</dd> +<dt><code>-mpclmul</code></dt> +<dd><a name="index-mclflushopt"></a> +</dd> +<dt><code>-mclflushopt</code></dt> +<dd><a name="index-mclwb"></a> +</dd> +<dt><code>-mclwb</code></dt> +<dd><a name="index-mfsgsbase"></a> +</dd> +<dt><code>-mfsgsbase</code></dt> +<dd><a name="index-mptwrite"></a> +</dd> +<dt><code>-mptwrite</code></dt> +<dd><a name="index-mrdrnd"></a> +</dd> +<dt><code>-mrdrnd</code></dt> +<dd><a name="index-mf16c"></a> +</dd> +<dt><code>-mf16c</code></dt> +<dd><a name="index-mfma"></a> +</dd> +<dt><code>-mfma</code></dt> +<dd><a name="index-mpconfig"></a> +</dd> +<dt><code>-mpconfig</code></dt> +<dd><a name="index-mwbnoinvd"></a> +</dd> +<dt><code>-mwbnoinvd</code></dt> +<dd><a name="index-mfma4"></a> +</dd> +<dt><code>-mfma4</code></dt> +<dd><a name="index-mprfchw"></a> +</dd> +<dt><code>-mprfchw</code></dt> +<dd><a name="index-mrdpid"></a> +</dd> +<dt><code>-mrdpid</code></dt> +<dd><a name="index-mprefetchwt1"></a> +</dd> +<dt><code>-mprefetchwt1</code></dt> +<dd><a name="index-mrdseed"></a> +</dd> +<dt><code>-mrdseed</code></dt> +<dd><a name="index-msgx"></a> +</dd> +<dt><code>-msgx</code></dt> +<dd><a name="index-mxop"></a> +</dd> +<dt><code>-mxop</code></dt> +<dd><a name="index-mlwp"></a> +</dd> +<dt><code>-mlwp</code></dt> +<dd><a name="index-m3dnow"></a> +</dd> +<dt><code>-m3dnow</code></dt> +<dd><a name="index-m3dnowa"></a> +</dd> +<dt><code>-m3dnowa</code></dt> +<dd><a name="index-mpopcnt"></a> +</dd> +<dt><code>-mpopcnt</code></dt> +<dd><a name="index-mabm"></a> +</dd> +<dt><code>-mabm</code></dt> +<dd><a name="index-madx"></a> +</dd> +<dt><code>-madx</code></dt> +<dd><a name="index-mbmi"></a> +</dd> +<dt><code>-mbmi</code></dt> +<dd><a name="index-mbmi2"></a> +</dd> +<dt><code>-mbmi2</code></dt> +<dd><a name="index-mlzcnt"></a> +</dd> +<dt><code>-mlzcnt</code></dt> +<dd><a name="index-mfxsr"></a> +</dd> +<dt><code>-mfxsr</code></dt> +<dd><a name="index-mxsave"></a> +</dd> +<dt><code>-mxsave</code></dt> +<dd><a name="index-mxsaveopt"></a> +</dd> +<dt><code>-mxsaveopt</code></dt> +<dd><a name="index-mxsavec"></a> +</dd> +<dt><code>-mxsavec</code></dt> +<dd><a name="index-mxsaves"></a> +</dd> +<dt><code>-mxsaves</code></dt> +<dd><a name="index-mrtm"></a> +</dd> +<dt><code>-mrtm</code></dt> +<dd><a name="index-mhle"></a> +</dd> +<dt><code>-mhle</code></dt> +<dd><a name="index-mtbm"></a> +</dd> +<dt><code>-mtbm</code></dt> +<dd><a name="index-mmwaitx"></a> +</dd> +<dt><code>-mmwaitx</code></dt> +<dd><a name="index-mclzero"></a> +</dd> +<dt><code>-mclzero</code></dt> +<dd><a name="index-mpku"></a> +</dd> +<dt><code>-mpku</code></dt> +<dd><a name="index-mavx512vbmi2"></a> +</dd> +<dt><code>-mavx512vbmi2</code></dt> +<dd><a name="index-mavx512bf16"></a> +</dd> +<dt><code>-mavx512bf16</code></dt> +<dd><a name="index-mavx512fp16"></a> +</dd> +<dt><code>-mavx512fp16</code></dt> +<dd><a name="index-mgfni"></a> +</dd> +<dt><code>-mgfni</code></dt> +<dd><a name="index-mvaes"></a> +</dd> +<dt><code>-mvaes</code></dt> +<dd><a name="index-mwaitpkg"></a> +</dd> +<dt><code>-mwaitpkg</code></dt> +<dd><a name="index-mvpclmulqdq"></a> +</dd> +<dt><code>-mvpclmulqdq</code></dt> +<dd><a name="index-mavx512bitalg"></a> +</dd> +<dt><code>-mavx512bitalg</code></dt> +<dd><a name="index-mmovdiri"></a> +</dd> +<dt><code>-mmovdiri</code></dt> +<dd><a name="index-mmovdir64b"></a> +</dd> +<dt><code>-mmovdir64b</code></dt> +<dd><a name="index-menqcmd"></a> +<a name="index-muintr"></a> +</dd> +<dt><code>-menqcmd</code></dt> +<dt><code>-muintr</code></dt> +<dd><a name="index-mtsxldtrk"></a> +</dd> +<dt><code>-mtsxldtrk</code></dt> +<dd><a name="index-mavx512vpopcntdq"></a> +</dd> +<dt><code>-mavx512vpopcntdq</code></dt> +<dd><a name="index-mavx512vp2intersect"></a> +</dd> +<dt><code>-mavx512vp2intersect</code></dt> +<dd><a name="index-mavx5124fmaps"></a> +</dd> +<dt><code>-mavx5124fmaps</code></dt> +<dd><a name="index-mavx512vnni"></a> +</dd> +<dt><code>-mavx512vnni</code></dt> +<dd><a name="index-mavxvnni"></a> +</dd> +<dt><code>-mavxvnni</code></dt> +<dd><a name="index-mavx5124vnniw"></a> +</dd> +<dt><code>-mavx5124vnniw</code></dt> +<dd><a name="index-mcldemote"></a> +</dd> +<dt><code>-mcldemote</code></dt> +<dd><a name="index-mserialize"></a> +</dd> +<dt><code>-mserialize</code></dt> +<dd><a name="index-mamx_002dtile"></a> +</dd> +<dt><code>-mamx-tile</code></dt> +<dd><a name="index-mamx_002dint8"></a> +</dd> +<dt><code>-mamx-int8</code></dt> +<dd><a name="index-mamx_002dbf16"></a> +</dd> +<dt><code>-mamx-bf16</code></dt> +<dd><a name="index-mhreset"></a> +<a name="index-mkl"></a> +</dd> +<dt><code>-mhreset</code></dt> +<dt><code>-mkl</code></dt> +<dd><a name="index-mwidekl"></a> +</dd> +<dt><code>-mwidekl</code></dt> +<dd><a name="index-mavxifma"></a> +</dd> +<dt><code>-mavxifma</code></dt> +<dd><a name="index-mavxvnniint8"></a> +</dd> +<dt><code>-mavxvnniint8</code></dt> +<dd><a name="index-mavxneconvert"></a> +</dd> +<dt><code>-mavxneconvert</code></dt> +<dd><a name="index-mcmpccxadd"></a> +</dd> +<dt><code>-mcmpccxadd</code></dt> +<dd><a name="index-mamx_002dfp16"></a> +</dd> +<dt><code>-mamx-fp16</code></dt> +<dd><a name="index-mprefetchi"></a> +</dd> +<dt><code>-mprefetchi</code></dt> +<dd><a name="index-mraoint"></a> +</dd> +<dt><code>-mraoint</code></dt> +<dd><a name="index-mamx_002dcomplex"></a> +</dd> +<dt><code>-mamx-complex</code></dt> +<dd><p>These switches enable the use of instructions in the MMX, SSE, +SSE2, SSE3, SSSE3, SSE4, SSE4A, SSE4.1, SSE4.2, AVX, AVX2, AVX512F, AVX512PF, +AVX512ER, AVX512CD, AVX512VL, AVX512BW, AVX512DQ, AVX512IFMA, AVX512VBMI, SHA, +AES, PCLMUL, CLFLUSHOPT, CLWB, FSGSBASE, PTWRITE, RDRND, F16C, FMA, PCONFIG, +WBNOINVD, FMA4, PREFETCHW, RDPID, PREFETCHWT1, RDSEED, SGX, XOP, LWP, +3DNow!, enhanced 3DNow!, POPCNT, ABM, ADX, BMI, BMI2, LZCNT, FXSR, XSAVE, +XSAVEOPT, XSAVEC, XSAVES, RTM, HLE, TBM, MWAITX, CLZERO, PKU, AVX512VBMI2, +GFNI, VAES, WAITPKG, VPCLMULQDQ, AVX512BITALG, MOVDIRI, MOVDIR64B, AVX512BF16, +ENQCMD, AVX512VPOPCNTDQ, AVX5124FMAPS, AVX512VNNI, AVX5124VNNIW, SERIALIZE, +UINTR, HRESET, AMXTILE, AMXINT8, AMXBF16, KL, WIDEKL, AVXVNNI, AVX512-FP16, +AVXIFMA, AVXVNNIINT8, AVXNECONVERT, CMPCCXADD, AMX-FP16, PREFETCHI, RAOINT, +AMX-COMPLEX or CLDEMOTE extended instruction sets. Each has a corresponding +<samp>-mno-</samp> option to disable use of these instructions. +</p> +<p>These extensions are also available as built-in functions: see +<a href="x86-Built_002din-Functions.html#x86-Built_002din-Functions">x86 Built-in Functions</a>, for details of the functions enabled and +disabled by these switches. +</p> +<p>To generate SSE/SSE2 instructions automatically from floating-point +code (as opposed to 387 instructions), see <samp>-mfpmath=sse</samp>. +</p> +<p>GCC depresses SSEx instructions when <samp>-mavx</samp> is used. Instead, it +generates new AVX instructions or AVX equivalence for all SSEx instructions +when needed. +</p> +<p>These options enable GCC to use these extended instructions in +generated code, even without <samp>-mfpmath=sse</samp>. Applications that +perform run-time CPU detection must compile separate files for each +supported architecture, using the appropriate flags. In particular, +the file containing the CPU detection code should be compiled without +these options. +</p> +<a name="index-mdump_002dtune_002dfeatures"></a> +</dd> +<dt><code>-mdump-tune-features</code></dt> +<dd><p>This option instructs GCC to dump the names of the x86 performance +tuning features and default settings. The names can be used in +<samp>-mtune-ctrl=<var>feature-list</var></samp>. +</p> +<a name="index-mtune_002dctrl_003dfeature_002dlist"></a> +</dd> +<dt><code>-mtune-ctrl=<var>feature-list</var></code></dt> +<dd><p>This option is used to do fine grain control of x86 code generation features. +<var>feature-list</var> is a comma separated list of <var>feature</var> names. See also +<samp>-mdump-tune-features</samp>. When specified, the <var>feature</var> is turned +on if it is not preceded with ‘<samp>^</samp>’, otherwise, it is turned off. +<samp>-mtune-ctrl=<var>feature-list</var></samp> is intended to be used by GCC +developers. Using it may lead to code paths not covered by testing and can +potentially result in compiler ICEs or runtime errors. +</p> +<a name="index-mno_002ddefault"></a> +</dd> +<dt><code>-mno-default</code></dt> +<dd><p>This option instructs GCC to turn off all tunable features. See also +<samp>-mtune-ctrl=<var>feature-list</var></samp> and <samp>-mdump-tune-features</samp>. +</p> +<a name="index-mcld"></a> +</dd> +<dt><code>-mcld</code></dt> +<dd><p>This option instructs GCC to emit a <code>cld</code> instruction in the prologue +of functions that use string instructions. String instructions depend on +the DF flag to select between autoincrement or autodecrement mode. While the +ABI specifies the DF flag to be cleared on function entry, some operating +systems violate this specification by not clearing the DF flag in their +exception dispatchers. The exception handler can be invoked with the DF flag +set, which leads to wrong direction mode when string instructions are used. +This option can be enabled by default on 32-bit x86 targets by configuring +GCC with the <samp>--enable-cld</samp> configure option. Generation of <code>cld</code> +instructions can be suppressed with the <samp>-mno-cld</samp> compiler option +in this case. +</p> +<a name="index-mvzeroupper"></a> +</dd> +<dt><code>-mvzeroupper</code></dt> +<dd><p>This option instructs GCC to emit a <code>vzeroupper</code> instruction +before a transfer of control flow out of the function to minimize +the AVX to SSE transition penalty as well as remove unnecessary <code>zeroupper</code> +intrinsics. +</p> +<a name="index-mprefer_002davx128"></a> +</dd> +<dt><code>-mprefer-avx128</code></dt> +<dd><p>This option instructs GCC to use 128-bit AVX instructions instead of +256-bit AVX instructions in the auto-vectorizer. +</p> +<a name="index-mprefer_002dvector_002dwidth"></a> +</dd> +<dt><code>-mprefer-vector-width=<var>opt</var></code></dt> +<dd><p>This option instructs GCC to use <var>opt</var>-bit vector width in instructions +instead of default on the selected platform. +</p> +<a name="index-mmove_002dmax"></a> +</dd> +<dt><code>-mmove-max=<var>bits</var></code></dt> +<dd><p>This option instructs GCC to set the maximum number of bits can be +moved from memory to memory efficiently to <var>bits</var>. The valid +<var>bits</var> are 128, 256 and 512. +</p> +<a name="index-mstore_002dmax"></a> +</dd> +<dt><code>-mstore-max=<var>bits</var></code></dt> +<dd><p>This option instructs GCC to set the maximum number of bits can be +stored to memory efficiently to <var>bits</var>. The valid <var>bits</var> are +128, 256 and 512. +</p> +<dl compact="compact"> +<dt>‘<samp>none</samp>’</dt> +<dd><p>No extra limitations applied to GCC other than defined by the selected platform. +</p> +</dd> +<dt>‘<samp>128</samp>’</dt> +<dd><p>Prefer 128-bit vector width for instructions. +</p> +</dd> +<dt>‘<samp>256</samp>’</dt> +<dd><p>Prefer 256-bit vector width for instructions. +</p> +</dd> +<dt>‘<samp>512</samp>’</dt> +<dd><p>Prefer 512-bit vector width for instructions. +</p></dd> +</dl> + +<a name="index-mcx16"></a> +</dd> +<dt><code>-mcx16</code></dt> +<dd><p>This option enables GCC to generate <code>CMPXCHG16B</code> instructions in 64-bit +code to implement compare-and-exchange operations on 16-byte aligned 128-bit +objects. This is useful for atomic updates of data structures exceeding one +machine word in size. The compiler uses this instruction to implement +<a href="_005f_005fsync-Builtins.html#g_t_005f_005fsync-Builtins">__sync Builtins</a>. However, for <a href="_005f_005fatomic-Builtins.html#g_t_005f_005fatomic-Builtins">__atomic Builtins</a> operating on +128-bit integers, a library call is always used. +</p> +<a name="index-msahf"></a> +</dd> +<dt><code>-msahf</code></dt> +<dd><p>This option enables generation of <code>SAHF</code> instructions in 64-bit code. +Early Intel Pentium 4 CPUs with Intel 64 support, +prior to the introduction of Pentium 4 G1 step in December 2005, +lacked the <code>LAHF</code> and <code>SAHF</code> instructions +which are supported by AMD64. +These are load and store instructions, respectively, for certain status flags. +In 64-bit mode, the <code>SAHF</code> instruction is used to optimize <code>fmod</code>, +<code>drem</code>, and <code>remainder</code> built-in functions; +see <a href="Other-Builtins.html#Other-Builtins">Other Builtins</a> for details. +</p> +<a name="index-mmovbe"></a> +</dd> +<dt><code>-mmovbe</code></dt> +<dd><p>This option enables use of the <code>movbe</code> instruction to implement +<code>__builtin_bswap32</code> and <code>__builtin_bswap64</code>. +</p> +<a name="index-mshstk"></a> +</dd> +<dt><code>-mshstk</code></dt> +<dd><p>The <samp>-mshstk</samp> option enables shadow stack built-in functions +from x86 Control-flow Enforcement Technology (CET). +</p> +<a name="index-mcrc32"></a> +</dd> +<dt><code>-mcrc32</code></dt> +<dd><p>This option enables built-in functions <code>__builtin_ia32_crc32qi</code>, +<code>__builtin_ia32_crc32hi</code>, <code>__builtin_ia32_crc32si</code> and +<code>__builtin_ia32_crc32di</code> to generate the <code>crc32</code> machine instruction. +</p> +<a name="index-mmwait"></a> +</dd> +<dt><code>-mmwait</code></dt> +<dd><p>This option enables built-in functions <code>__builtin_ia32_monitor</code>, +and <code>__builtin_ia32_mwait</code> to generate the <code>monitor</code> and +<code>mwait</code> machine instructions. +</p> +<a name="index-mrecip-1"></a> +</dd> +<dt><code>-mrecip</code></dt> +<dd><p>This option enables use of <code>RCPSS</code> and <code>RSQRTSS</code> instructions +(and their vectorized variants <code>RCPPS</code> and <code>RSQRTPS</code>) +with an additional Newton-Raphson step +to increase precision instead of <code>DIVSS</code> and <code>SQRTSS</code> +(and their vectorized +variants) for single-precision floating-point arguments. These instructions +are generated only when <samp>-funsafe-math-optimizations</samp> is enabled +together with <samp>-ffinite-math-only</samp> and <samp>-fno-trapping-math</samp>. +Note that while the throughput of the sequence is higher than the throughput +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). +</p> +<p>Note that GCC implements <code>1.0f/sqrtf(<var>x</var>)</code> in terms of <code>RSQRTSS</code> +(or <code>RSQRTPS</code>) already with <samp>-ffast-math</samp> (or the above option +combination), and doesn’t need <samp>-mrecip</samp>. +</p> +<p>Also note that GCC emits the above sequence with additional Newton-Raphson step +for vectorized single-float division and vectorized <code>sqrtf(<var>x</var>)</code> +already with <samp>-ffast-math</samp> (or the above option combination), and +doesn’t need <samp>-mrecip</samp>. +</p> +<a name="index-mrecip_003dopt-1"></a> +</dd> +<dt><code>-mrecip=<var>opt</var></code></dt> +<dd><p>This option controls which reciprocal estimate instructions +may be used. <var>opt</var> is a comma-separated list of options, which may +be preceded by a ‘<samp>!</samp>’ to invert the option: +</p> +<dl compact="compact"> +<dt>‘<samp>all</samp>’</dt> +<dd><p>Enable all estimate instructions. +</p> +</dd> +<dt>‘<samp>default</samp>’</dt> +<dd><p>Enable the default instructions, equivalent to <samp>-mrecip</samp>. +</p> +</dd> +<dt>‘<samp>none</samp>’</dt> +<dd><p>Disable all estimate instructions, equivalent to <samp>-mno-recip</samp>. +</p> +</dd> +<dt>‘<samp>div</samp>’</dt> +<dd><p>Enable the approximation for scalar division. +</p> +</dd> +<dt>‘<samp>vec-div</samp>’</dt> +<dd><p>Enable the approximation for vectorized division. +</p> +</dd> +<dt>‘<samp>sqrt</samp>’</dt> +<dd><p>Enable the approximation for scalar square root. +</p> +</dd> +<dt>‘<samp>vec-sqrt</samp>’</dt> +<dd><p>Enable the approximation for vectorized square root. +</p></dd> +</dl> + +<p>So, for example, <samp>-mrecip=all,!sqrt</samp> enables +all of the reciprocal approximations, except for square root. +</p> +<a name="index-mveclibabi-1"></a> +</dd> +<dt><code>-mveclibabi=<var>type</var></code></dt> +<dd><p>Specifies the ABI type to use for vectorizing intrinsics using an +external library. Supported values for <var>type</var> are ‘<samp>svml</samp>’ +for the Intel short +vector math library and ‘<samp>acml</samp>’ for the AMD math core library. +To use this option, both <samp>-ftree-vectorize</samp> and +<samp>-funsafe-math-optimizations</samp> have to be enabled, and an SVML or ACML +ABI-compatible library must be specified at link time. +</p> +<p>GCC currently emits calls to <code>vmldExp2</code>, +<code>vmldLn2</code>, <code>vmldLog102</code>, <code>vmldPow2</code>, +<code>vmldTanh2</code>, <code>vmldTan2</code>, <code>vmldAtan2</code>, <code>vmldAtanh2</code>, +<code>vmldCbrt2</code>, <code>vmldSinh2</code>, <code>vmldSin2</code>, <code>vmldAsinh2</code>, +<code>vmldAsin2</code>, <code>vmldCosh2</code>, <code>vmldCos2</code>, <code>vmldAcosh2</code>, +<code>vmldAcos2</code>, <code>vmlsExp4</code>, <code>vmlsLn4</code>, +<code>vmlsLog104</code>, <code>vmlsPow4</code>, <code>vmlsTanh4</code>, <code>vmlsTan4</code>, +<code>vmlsAtan4</code>, <code>vmlsAtanh4</code>, <code>vmlsCbrt4</code>, <code>vmlsSinh4</code>, +<code>vmlsSin4</code>, <code>vmlsAsinh4</code>, <code>vmlsAsin4</code>, <code>vmlsCosh4</code>, +<code>vmlsCos4</code>, <code>vmlsAcosh4</code> and <code>vmlsAcos4</code> for corresponding +function type when <samp>-mveclibabi=svml</samp> is used, and <code>__vrd2_sin</code>, +<code>__vrd2_cos</code>, <code>__vrd2_exp</code>, <code>__vrd2_log</code>, <code>__vrd2_log2</code>, +<code>__vrd2_log10</code>, <code>__vrs4_sinf</code>, <code>__vrs4_cosf</code>, +<code>__vrs4_expf</code>, <code>__vrs4_logf</code>, <code>__vrs4_log2f</code>, +<code>__vrs4_log10f</code> and <code>__vrs4_powf</code> for the corresponding function type +when <samp>-mveclibabi=acml</samp> is used. +</p> +<a name="index-mabi-6"></a> +</dd> +<dt><code>-mabi=<var>name</var></code></dt> +<dd><p>Generate code for the specified calling convention. Permissible values +are ‘<samp>sysv</samp>’ for the ABI used on GNU/Linux and other systems, and +‘<samp>ms</samp>’ for the Microsoft ABI. The default is to use the Microsoft +ABI when targeting Microsoft Windows and the SysV ABI on all other systems. +You can control this behavior for specific functions by +using the function attributes <code>ms_abi</code> and <code>sysv_abi</code>. +See <a href="Function-Attributes.html#Function-Attributes">Function Attributes</a>. +</p> +<a name="index-mforce_002dindirect_002dcall"></a> +</dd> +<dt><code>-mforce-indirect-call</code></dt> +<dd><p>Force all calls to functions to be indirect. This is useful +when using Intel Processor Trace where it generates more precise timing +information for function calls. +</p> +<a name="index-mmanual_002dendbr"></a> +</dd> +<dt><code>-mmanual-endbr</code></dt> +<dd><p>Insert ENDBR instruction at function entry only via the <code>cf_check</code> +function attribute. This is useful when used with the option +<samp>-fcf-protection=branch</samp> to control ENDBR insertion at the +function entry. +</p> +<a name="index-mcet_002dswitch"></a> +</dd> +<dt><code>-mcet-switch</code></dt> +<dd><p>By default, CET instrumentation is turned off on switch statements that +use a jump table and indirect branch track is disabled. Since jump +tables are stored in read-only memory, this does not result in a direct +loss of hardening. But if the jump table index is attacker-controlled, +the indirect jump may not be constrained by CET. This option turns on +CET instrumentation to enable indirect branch track for switch statements +with jump tables which leads to the jump targets reachable via any indirect +jumps. +</p> +<a name="index-mcall_002dms2sysv_002dxlogues"></a> +<a name="index-mno_002dcall_002dms2sysv_002dxlogues"></a> +</dd> +<dt><code>-mcall-ms2sysv-xlogues</code></dt> +<dd><p>Due to differences in 64-bit ABIs, any Microsoft ABI function that calls a +System V ABI function must consider RSI, RDI and XMM6-15 as clobbered. By +default, the code for saving and restoring these registers is emitted inline, +resulting in fairly lengthy prologues and epilogues. Using +<samp>-mcall-ms2sysv-xlogues</samp> emits prologues and epilogues that +use stubs in the static portion of libgcc to perform these saves and restores, +thus reducing function size at the cost of a few extra instructions. +</p> +<a name="index-mtls_002ddialect-1"></a> +</dd> +<dt><code>-mtls-dialect=<var>type</var></code></dt> +<dd><p>Generate code to access thread-local storage using the ‘<samp>gnu</samp>’ or +‘<samp>gnu2</samp>’ conventions. ‘<samp>gnu</samp>’ is the conservative default; +‘<samp>gnu2</samp>’ is more efficient, but it may add compile- and run-time +requirements that cannot be satisfied on all systems. +</p> +<a name="index-mpush_002dargs"></a> +<a name="index-mno_002dpush_002dargs"></a> +</dd> +<dt><code>-mpush-args</code></dt> +<dt><code>-mno-push-args</code></dt> +<dd><p>Use PUSH operations to store outgoing parameters. This method is shorter +and usually equally fast as method using SUB/MOV operations and is enabled +by default. In some cases disabling it may improve performance because of +improved scheduling and reduced dependencies. +</p> +<a name="index-maccumulate_002doutgoing_002dargs-1"></a> +</dd> +<dt><code>-maccumulate-outgoing-args</code></dt> +<dd><p>If enabled, the maximum amount of space required for outgoing arguments is +computed in the function prologue. This is faster on most modern CPUs +because of reduced dependencies, improved scheduling and reduced stack usage +when the preferred stack boundary is not equal to 2. The drawback is a notable +increase in code size. This switch implies <samp>-mno-push-args</samp>. +</p> +<a name="index-mthreads"></a> +</dd> +<dt><code>-mthreads</code></dt> +<dd><p>Support thread-safe exception handling on MinGW. Programs that rely +on thread-safe exception handling must compile and link all code with the +<samp>-mthreads</samp> option. When compiling, <samp>-mthreads</samp> defines +<samp>-D_MT</samp>; when linking, it links in a special thread helper library +<samp>-lmingwthrd</samp> which cleans up per-thread exception-handling data. +</p> +<a name="index-mms_002dbitfields"></a> +<a name="index-mno_002dms_002dbitfields"></a> +</dd> +<dt><code>-mms-bitfields</code></dt> +<dt><code>-mno-ms-bitfields</code></dt> +<dd> +<p>Enable/disable bit-field layout compatible with the native Microsoft +Windows compiler. +</p> +<p>If <code>packed</code> is used on a structure, or if bit-fields are used, +it may be that the Microsoft ABI lays out the structure differently +than the way GCC normally does. Particularly when moving packed +data between functions compiled with GCC and the native Microsoft compiler +(either via function call or as data in a file), it may be necessary to access +either format. +</p> +<p>This option is enabled by default for Microsoft Windows +targets. This behavior can also be controlled locally by use of variable +or type attributes. For more information, see <a href="x86-Variable-Attributes.html#x86-Variable-Attributes">x86 Variable Attributes</a> +and <a href="x86-Type-Attributes.html#x86-Type-Attributes">x86 Type Attributes</a>. +</p> +<p>The Microsoft structure layout algorithm is fairly simple with the exception +of the bit-field packing. +The padding and alignment of members of structures and whether a bit-field +can straddle a storage-unit boundary are determine by these rules: +</p> +<ol> +<li> Structure members are stored sequentially in the order in which they are +declared: the first member has the lowest memory address and the last member +the highest. + +</li><li> Every data object has an alignment requirement. The alignment requirement +for all data except structures, unions, and arrays is either the size of the +object or the current packing size (specified with either the +<code>aligned</code> attribute or the <code>pack</code> pragma), +whichever is less. For structures, unions, and arrays, +the alignment requirement is the largest alignment requirement of its members. +Every object is allocated an offset so that: + +<div class="smallexample"> +<pre class="smallexample">offset % alignment_requirement == 0 +</pre></div> + +</li><li> Adjacent bit-fields are packed into the same 1-, 2-, or 4-byte allocation +unit if the integral types are the same size and if the next bit-field fits +into the current allocation unit without crossing the boundary imposed by the +common alignment requirements of the bit-fields. +</li></ol> + +<p>MSVC interprets zero-length bit-fields in the following ways: +</p> +<ol> +<li> If a zero-length bit-field is inserted between two bit-fields that +are normally coalesced, the bit-fields are not coalesced. + +<p>For example: +</p> +<div class="smallexample"> +<pre class="smallexample">struct + { + unsigned long bf_1 : 12; + unsigned long : 0; + unsigned long bf_2 : 12; + } t1; +</pre></div> + +<p>The size of <code>t1</code> is 8 bytes with the zero-length bit-field. If the +zero-length bit-field were removed, <code>t1</code>’s size would be 4 bytes. +</p> +</li><li> If a zero-length bit-field is inserted after a bit-field, <code>foo</code>, and the +alignment of the zero-length bit-field is greater than the member that follows it, +<code>bar</code>, <code>bar</code> is aligned as the type of the zero-length bit-field. + +<p>For example: +</p> +<div class="smallexample"> +<pre class="smallexample">struct + { + char foo : 4; + short : 0; + char bar; + } t2; + +struct + { + char foo : 4; + short : 0; + double bar; + } t3; +</pre></div> + +<p>For <code>t2</code>, <code>bar</code> is placed at offset 2, rather than offset 1. +Accordingly, the size of <code>t2</code> is 4. For <code>t3</code>, the zero-length +bit-field does not affect the alignment of <code>bar</code> or, as a result, the size +of the structure. +</p> +<p>Taking this into account, it is important to note the following: +</p> +<ol> +<li> If a zero-length bit-field follows a normal bit-field, the type of the +zero-length bit-field may affect the alignment of the structure as whole. For +example, <code>t2</code> has a size of 4 bytes, since the zero-length bit-field follows a +normal bit-field, and is of type short. + +</li><li> Even if a zero-length bit-field is not followed by a normal bit-field, it may +still affect the alignment of the structure: + +<div class="smallexample"> +<pre class="smallexample">struct + { + char foo : 6; + long : 0; + } t4; +</pre></div> + +<p>Here, <code>t4</code> takes up 4 bytes. +</p></li></ol> + +</li><li> Zero-length bit-fields following non-bit-field members are ignored: + +<div class="smallexample"> +<pre class="smallexample">struct + { + char foo; + long : 0; + char bar; + } t5; +</pre></div> + +<p>Here, <code>t5</code> takes up 2 bytes. +</p></li></ol> + + +<a name="index-mno_002dalign_002dstringops"></a> +<a name="index-malign_002dstringops"></a> +</dd> +<dt><code>-mno-align-stringops</code></dt> +<dd><p>Do not align the destination of inlined string operations. This switch reduces +code size and improves performance in case the destination is already aligned, +but GCC doesn’t know about it. +</p> +<a name="index-minline_002dall_002dstringops"></a> +</dd> +<dt><code>-minline-all-stringops</code></dt> +<dd><p>By default GCC inlines string operations only when the destination is +known to be aligned to least a 4-byte boundary. +This enables more inlining and increases code +size, but may improve performance of code that depends on fast +<code>memcpy</code> and <code>memset</code> for short lengths. +The option enables inline expansion of <code>strlen</code> for all +pointer alignments. +</p> +<a name="index-minline_002dstringops_002ddynamically"></a> +</dd> +<dt><code>-minline-stringops-dynamically</code></dt> +<dd><p>For string operations of unknown size, use run-time checks with +inline code for small blocks and a library call for large blocks. +</p> +<a name="index-mstringop_002dstrategy_003dalg"></a> +</dd> +<dt><code>-mstringop-strategy=<var>alg</var></code></dt> +<dd><p>Override the internal decision heuristic for the particular algorithm to use +for inlining string operations. The allowed values for <var>alg</var> are: +</p> +<dl compact="compact"> +<dt>‘<samp>rep_byte</samp>’</dt> +<dt>‘<samp>rep_4byte</samp>’</dt> +<dt>‘<samp>rep_8byte</samp>’</dt> +<dd><p>Expand using i386 <code>rep</code> prefix of the specified size. +</p> +</dd> +<dt>‘<samp>byte_loop</samp>’</dt> +<dt>‘<samp>loop</samp>’</dt> +<dt>‘<samp>unrolled_loop</samp>’</dt> +<dd><p>Expand into an inline loop. +</p> +</dd> +<dt>‘<samp>libcall</samp>’</dt> +<dd><p>Always use a library call. +</p></dd> +</dl> + +<a name="index-mmemcpy_002dstrategy_003dstrategy"></a> +</dd> +<dt><code>-mmemcpy-strategy=<var>strategy</var></code></dt> +<dd><p>Override the internal decision heuristic to decide if <code>__builtin_memcpy</code> +should be inlined and what inline algorithm to use when the expected size +of the copy operation is known. <var>strategy</var> +is a comma-separated list of <var>alg</var>:<var>max_size</var>:<var>dest_align</var> triplets. +<var>alg</var> is specified in <samp>-mstringop-strategy</samp>, <var>max_size</var> specifies +the max byte size with which inline algorithm <var>alg</var> is allowed. For the last +triplet, the <var>max_size</var> must be <code>-1</code>. The <var>max_size</var> of the triplets +in the list must be specified in increasing order. The minimal byte size for +<var>alg</var> is <code>0</code> for the first triplet and <code><var>max_size</var> + 1</code> of the +preceding range. +</p> +<a name="index-mmemset_002dstrategy_003dstrategy"></a> +</dd> +<dt><code>-mmemset-strategy=<var>strategy</var></code></dt> +<dd><p>The option is similar to <samp>-mmemcpy-strategy=</samp> except that it is to control +<code>__builtin_memset</code> expansion. +</p> +<a name="index-momit_002dleaf_002dframe_002dpointer-2"></a> +</dd> +<dt><code>-momit-leaf-frame-pointer</code></dt> +<dd><p>Don’t keep the frame pointer in a register for leaf functions. This +avoids the instructions to save, set up, and restore frame pointers and +makes an extra register available in leaf functions. The option +<samp>-fomit-leaf-frame-pointer</samp> removes the frame pointer for leaf functions, +which might make debugging harder. +</p> +<a name="index-mtls_002ddirect_002dseg_002drefs"></a> +</dd> +<dt><code>-mtls-direct-seg-refs</code></dt> +<dt><code>-mno-tls-direct-seg-refs</code></dt> +<dd><p>Controls whether TLS variables may be accessed with offsets from the +TLS segment register (<code>%gs</code> for 32-bit, <code>%fs</code> for 64-bit), +or whether the thread base pointer must be added. Whether or not this +is valid depends on the operating system, and whether it maps the +segment to cover the entire TLS area. +</p> +<p>For systems that use the GNU C Library, the default is on. +</p> +<a name="index-msse2avx"></a> +</dd> +<dt><code>-msse2avx</code></dt> +<dt><code>-mno-sse2avx</code></dt> +<dd><p>Specify that the assembler should encode SSE instructions with VEX +prefix. The option <samp>-mavx</samp> turns this on by default. +</p> +<a name="index-mfentry"></a> +</dd> +<dt><code>-mfentry</code></dt> +<dt><code>-mno-fentry</code></dt> +<dd><p>If profiling is active (<samp>-pg</samp>), put the profiling +counter call before the prologue. +Note: On x86 architectures the attribute <code>ms_hook_prologue</code> +isn’t possible at the moment for <samp>-mfentry</samp> and <samp>-pg</samp>. +</p> +<a name="index-mrecord_002dmcount"></a> +</dd> +<dt><code>-mrecord-mcount</code></dt> +<dt><code>-mno-record-mcount</code></dt> +<dd><p>If profiling is active (<samp>-pg</samp>), generate a __mcount_loc section +that contains pointers to each profiling call. This is useful for +automatically patching and out calls. +</p> +<a name="index-mnop_002dmcount"></a> +</dd> +<dt><code>-mnop-mcount</code></dt> +<dt><code>-mno-nop-mcount</code></dt> +<dd><p>If profiling is active (<samp>-pg</samp>), generate the calls to +the profiling functions as NOPs. This is useful when they +should be patched in later dynamically. This is likely only +useful together with <samp>-mrecord-mcount</samp>. +</p> +<a name="index-minstrument_002dreturn"></a> +</dd> +<dt><code>-minstrument-return=<var>type</var></code></dt> +<dd><p>Instrument function exit in -pg -mfentry instrumented functions with +call to specified function. This only instruments true returns ending +with ret, but not sibling calls ending with jump. Valid types +are <var>none</var> to not instrument, <var>call</var> to generate a call to __return__, +or <var>nop5</var> to generate a 5 byte nop. +</p> +<a name="index-mrecord_002dreturn"></a> +</dd> +<dt><code>-mrecord-return</code></dt> +<dt><code>-mno-record-return</code></dt> +<dd><p>Generate a __return_loc section pointing to all return instrumentation code. +</p> +<a name="index-mfentry_002dname"></a> +</dd> +<dt><code>-mfentry-name=<var>name</var></code></dt> +<dd><p>Set name of __fentry__ symbol called at function entry for -pg -mfentry functions. +</p> +<a name="index-mfentry_002dsection"></a> +</dd> +<dt><code>-mfentry-section=<var>name</var></code></dt> +<dd><p>Set name of section to record -mrecord-mcount calls (default __mcount_loc). +</p> +<a name="index-mskip_002drax_002dsetup"></a> +</dd> +<dt><code>-mskip-rax-setup</code></dt> +<dt><code>-mno-skip-rax-setup</code></dt> +<dd><p>When generating code for the x86-64 architecture with SSE extensions +disabled, <samp>-mskip-rax-setup</samp> can be used to skip setting up RAX +register when there are no variable arguments passed in vector registers. +</p> +<p><strong>Warning:</strong> Since RAX register is used to avoid unnecessarily +saving vector registers on stack when passing variable arguments, the +impacts of this option are callees may waste some stack space, +misbehave or jump to a random location. GCC 4.4 or newer don’t have +those issues, regardless the RAX register value. +</p> +<a name="index-m8bit_002didiv"></a> +</dd> +<dt><code>-m8bit-idiv</code></dt> +<dt><code>-mno-8bit-idiv</code></dt> +<dd><p>On some processors, like Intel Atom, 8-bit unsigned integer divide is +much faster than 32-bit/64-bit integer divide. This option generates a +run-time check. If both dividend and divisor are within range of 0 +to 255, 8-bit unsigned integer divide is used instead of +32-bit/64-bit integer divide. +</p> +<a name="index-mavx256_002dsplit_002dunaligned_002dload"></a> +<a name="index-mavx256_002dsplit_002dunaligned_002dstore"></a> +</dd> +<dt><code>-mavx256-split-unaligned-load</code></dt> +<dt><code>-mavx256-split-unaligned-store</code></dt> +<dd><p>Split 32-byte AVX unaligned load and store. +</p> +<a name="index-mstack_002dprotector_002dguard-4"></a> +<a name="index-mstack_002dprotector_002dguard_002dreg-3"></a> +<a name="index-mstack_002dprotector_002dguard_002doffset-4"></a> +</dd> +<dt><code>-mstack-protector-guard=<var>guard</var></code></dt> +<dt><code>-mstack-protector-guard-reg=<var>reg</var></code></dt> +<dt><code>-mstack-protector-guard-offset=<var>offset</var></code></dt> +<dd><p>Generate stack protection code using canary at <var>guard</var>. Supported +locations are ‘<samp>global</samp>’ for global canary or ‘<samp>tls</samp>’ for per-thread +canary in the TLS block (the default). This option has effect only when +<samp>-fstack-protector</samp> or <samp>-fstack-protector-all</samp> is specified. +</p> +<p>With the latter choice the options +<samp>-mstack-protector-guard-reg=<var>reg</var></samp> and +<samp>-mstack-protector-guard-offset=<var>offset</var></samp> furthermore specify +which segment register (<code>%fs</code> or <code>%gs</code>) to use as base register +for reading the canary, and from what offset from that base register. +The default for those is as specified in the relevant ABI. +</p> +<a name="index-mgeneral_002dregs_002donly-2"></a> +</dd> +<dt><code>-mgeneral-regs-only</code></dt> +<dd><p>Generate code that uses only the general-purpose registers. This +prevents the compiler from using floating-point, vector, mask and bound +registers. +</p> +<a name="index-mrelax_002dcmpxchg_002dloop"></a> +</dd> +<dt><code>-mrelax-cmpxchg-loop</code></dt> +<dd><p>When emitting a compare-and-swap loop for <a href="_005f_005fsync-Builtins.html#g_t_005f_005fsync-Builtins">__sync Builtins</a> +and <a href="_005f_005fatomic-Builtins.html#g_t_005f_005fatomic-Builtins">__atomic Builtins</a> lacking a native instruction, optimize +for the highly contended case by issuing an atomic load before the +<code>CMPXCHG</code> instruction, and using the <code>PAUSE</code> instruction +to save CPU power when restarting the loop. +</p> +<a name="index-mindirect_002dbranch"></a> +</dd> +<dt><code>-mindirect-branch=<var>choice</var></code></dt> +<dd><p>Convert indirect call and jump with <var>choice</var>. The default is +‘<samp>keep</samp>’, which keeps indirect call and jump unmodified. +‘<samp>thunk</samp>’ converts indirect call and jump to call and return thunk. +‘<samp>thunk-inline</samp>’ converts indirect call and jump to inlined call +and return thunk. ‘<samp>thunk-extern</samp>’ converts indirect call and jump +to external call and return thunk provided in a separate object file. +You can control this behavior for a specific function by using the +function attribute <code>indirect_branch</code>. See <a href="Function-Attributes.html#Function-Attributes">Function Attributes</a>. +</p> +<p>Note that <samp>-mcmodel=large</samp> is incompatible with +<samp>-mindirect-branch=thunk</samp> and +<samp>-mindirect-branch=thunk-extern</samp> since the thunk function may +not be reachable in the large code model. +</p> +<p>Note that <samp>-mindirect-branch=thunk-extern</samp> is compatible with +<samp>-fcf-protection=branch</samp> since the external thunk can be made +to enable control-flow check. +</p> +<a name="index-mfunction_002dreturn"></a> +</dd> +<dt><code>-mfunction-return=<var>choice</var></code></dt> +<dd><p>Convert function return with <var>choice</var>. The default is ‘<samp>keep</samp>’, +which keeps function return unmodified. ‘<samp>thunk</samp>’ converts function +return to call and return thunk. ‘<samp>thunk-inline</samp>’ converts function +return to inlined call and return thunk. ‘<samp>thunk-extern</samp>’ converts +function return to external call and return thunk provided in a separate +object file. You can control this behavior for a specific function by +using the function attribute <code>function_return</code>. +See <a href="Function-Attributes.html#Function-Attributes">Function Attributes</a>. +</p> +<p>Note that <samp>-mindirect-return=thunk-extern</samp> is compatible with +<samp>-fcf-protection=branch</samp> since the external thunk can be made +to enable control-flow check. +</p> +<p>Note that <samp>-mcmodel=large</samp> is incompatible with +<samp>-mfunction-return=thunk</samp> and +<samp>-mfunction-return=thunk-extern</samp> since the thunk function may +not be reachable in the large code model. +</p> + +<a name="index-mindirect_002dbranch_002dregister"></a> +</dd> +<dt><code>-mindirect-branch-register</code></dt> +<dd><p>Force indirect call and jump via register. +</p> +<a name="index-mharden_002dsls-1"></a> +</dd> +<dt><code>-mharden-sls=<var>choice</var></code></dt> +<dd><p>Generate code to mitigate against straight line speculation (SLS) with +<var>choice</var>. The default is ‘<samp>none</samp>’ which disables all SLS +hardening. ‘<samp>return</samp>’ enables SLS hardening for function returns. +‘<samp>indirect-jmp</samp>’ enables SLS hardening for indirect jumps. +‘<samp>all</samp>’ enables all SLS hardening. +</p> +<a name="index-mindirect_002dbranch_002dcs_002dprefix"></a> +</dd> +<dt><code>-mindirect-branch-cs-prefix</code></dt> +<dd><p>Add CS prefix to call and jmp to indirect thunk with branch target in +r8-r15 registers so that the call and jmp instruction length is 6 bytes +to allow them to be replaced with ‘<samp>lfence; call *%r8-r15</samp>’ or +‘<samp>lfence; jmp *%r8-r15</samp>’ at run-time. +</p> +</dd> +</dl> + +<p>These ‘<samp>-m</samp>’ switches are supported in addition to the above +on x86-64 processors in 64-bit environments. +</p> +<dl compact="compact"> +<dd><a name="index-m32-2"></a> +<a name="index-m64-4"></a> +<a name="index-mx32"></a> +<a name="index-m16"></a> +<a name="index-miamcu"></a> +</dd> +<dt><code>-m32</code></dt> +<dt><code>-m64</code></dt> +<dt><code>-mx32</code></dt> +<dt><code>-m16</code></dt> +<dt><code>-miamcu</code></dt> +<dd><p>Generate code for a 16-bit, 32-bit or 64-bit environment. +The <samp>-m32</samp> option sets <code>int</code>, <code>long</code>, and pointer types +to 32 bits, and +generates code that runs in 32-bit mode. +</p> +<p>The <samp>-m64</samp> option sets <code>int</code> to 32 bits and <code>long</code> and pointer +types to 64 bits, and generates code for the x86-64 architecture. +For Darwin only the <samp>-m64</samp> option also turns off the <samp>-fno-pic</samp> +and <samp>-mdynamic-no-pic</samp> options. +</p> +<p>The <samp>-mx32</samp> option sets <code>int</code>, <code>long</code>, and pointer types +to 32 bits, and +generates code for the x86-64 architecture. +</p> +<p>The <samp>-m16</samp> option is the same as <samp>-m32</samp>, except for that +it outputs the <code>.code16gcc</code> assembly directive at the beginning of +the assembly output so that the binary can run in 16-bit mode. +</p> +<p>The <samp>-miamcu</samp> option generates code which conforms to Intel MCU +psABI. It requires the <samp>-m32</samp> option to be turned on. +</p> +<a name="index-mno_002dred_002dzone"></a> +<a name="index-mred_002dzone"></a> +</dd> +<dt><code>-mno-red-zone</code></dt> +<dd><p>Do not use a so-called “red zone” for x86-64 code. The red zone is mandated +by the x86-64 ABI; it is a 128-byte area beyond the location of the +stack pointer that is not modified by signal or interrupt handlers +and therefore can be used for temporary data without adjusting the stack +pointer. The flag <samp>-mno-red-zone</samp> disables this red zone. +</p> +<a name="index-mcmodel_003dsmall-3"></a> +</dd> +<dt><code>-mcmodel=small</code></dt> +<dd><p>Generate code for the small code model: the program and its symbols must +be linked in the lower 2 GB of the address space. Pointers are 64 bits. +Programs can be statically or dynamically linked. This is the default +code model. +</p> +<a name="index-mcmodel_003dkernel"></a> +</dd> +<dt><code>-mcmodel=kernel</code></dt> +<dd><p>Generate code for the kernel code model. The kernel runs in the +negative 2 GB of the address space. +This model has to be used for Linux kernel code. +</p> +<a name="index-mcmodel_003dmedium-1"></a> +</dd> +<dt><code>-mcmodel=medium</code></dt> +<dd><p>Generate code for the medium model: the program is linked in the lower 2 +GB of the address space. Small symbols are also placed there. Symbols +with sizes larger than <samp>-mlarge-data-threshold</samp> are put into +large data or BSS sections and can be located above 2GB. Programs can +be statically or dynamically linked. +</p> +<a name="index-mcmodel_003dlarge-3"></a> +</dd> +<dt><code>-mcmodel=large</code></dt> +<dd><p>Generate code for the large model. This model makes no assumptions +about addresses and sizes of sections. +</p> +<a name="index-maddress_002dmode_003dlong"></a> +</dd> +<dt><code>-maddress-mode=long</code></dt> +<dd><p>Generate code for long address mode. This is only supported for 64-bit +and x32 environments. It is the default address mode for 64-bit +environments. +</p> +<a name="index-maddress_002dmode_003dshort"></a> +</dd> +<dt><code>-maddress-mode=short</code></dt> +<dd><p>Generate code for short address mode. This is only supported for 32-bit +and x32 environments. It is the default address mode for 32-bit and +x32 environments. +</p> +<a name="index-mneeded"></a> +</dd> +<dt><code>-mneeded</code></dt> +<dt><code>-mno-needed</code></dt> +<dd><p>Emit GNU_PROPERTY_X86_ISA_1_NEEDED GNU property for Linux target to +indicate the micro-architecture ISA level required to execute the binary. +</p> +<a name="index-mno_002ddirect_002dextern_002daccess"></a> +<a name="index-mdirect_002dextern_002daccess-1"></a> +</dd> +<dt><code>-mno-direct-extern-access</code></dt> +<dd><p>Without <samp>-fpic</samp> nor <samp>-fPIC</samp>, always use the GOT pointer +to access external symbols. With <samp>-fpic</samp> or <samp>-fPIC</samp>, +treat access to protected symbols as local symbols. The default is +<samp>-mdirect-extern-access</samp>. +</p> +<p><strong>Warning:</strong> shared libraries compiled with +<samp>-mno-direct-extern-access</samp> and executable compiled with +<samp>-mdirect-extern-access</samp> may not be binary compatible if +protected symbols are used in shared libraries and executable. +</p> +<a name="index-munroll_002donly_002dsmall_002dloops"></a> +<a name="index-mno_002dunroll_002donly_002dsmall_002dloops"></a> +</dd> +<dt><code>-munroll-only-small-loops</code></dt> +<dd><p>Controls conservative small loop unrolling. It is default enabled by +O2, and unrolls loop with less than 4 insns by 1 time. Explicit +-f[no-]unroll-[all-]loops would disable this flag to avoid any +unintended unrolling behavior that user does not want. +</p> +<a name="index-mlam"></a> +</dd> +<dt><code>-mlam=<var>choice</var></code></dt> +<dd><p>LAM(linear-address masking) allows special bits in the pointer to be used +for metadata. The default is ‘<samp>none</samp>’. With ‘<samp>u48</samp>’, pointer bits in +positions 62:48 can be used for metadata; With ‘<samp>u57</samp>’, pointer bits in +positions 62:57 can be used for metadata. +</p></dd> +</dl> + +<hr> +<div class="header"> +<p> +Next: <a href="x86-Windows-Options.html#x86-Windows-Options" accesskey="n" rel="next">x86 Windows Options</a>, Previous: <a href="VxWorks-Options.html#VxWorks-Options" accesskey="p" rel="previous">VxWorks Options</a>, Up: <a href="Submodel-Options.html#Submodel-Options" accesskey="u" rel="up">Submodel Options</a> [<a href="index.html#SEC_Contents" title="Table of contents" rel="contents">Contents</a>][<a href="Indices.html#Indices" title="Index" rel="index">Index</a>]</p> +</div> + + + +</body> +</html> |