You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

170 lines
10 KiB
HTML

<html lang="en">
<head>
<title>Adapteva Epiphany Options - Using the GNU Compiler Collection (GCC)</title>
<meta http-equiv="Content-Type" content="text/html">
<meta name="description" content="Using the GNU Compiler Collection (GCC)">
<meta name="generator" content="makeinfo 4.13">
<link title="Top" rel="start" href="index.html#Top">
<link rel="up" href="Submodel-Options.html#Submodel-Options" title="Submodel Options">
<link rel="prev" href="AArch64-Options.html#AArch64-Options" title="AArch64 Options">
<link rel="next" href="ARC-Options.html#ARC-Options" title="ARC Options">
<link href="http://www.gnu.org/software/texinfo/" rel="generator-home" title="Texinfo Homepage">
<!--
Copyright (C) 1988-2015 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.-->
<meta http-equiv="Content-Style-Type" content="text/css">
<style type="text/css"><!--
pre.display { font-family:inherit }
pre.format { font-family:inherit }
pre.smalldisplay { font-family:inherit; font-size:smaller }
pre.smallformat { font-family:inherit; font-size:smaller }
pre.smallexample { font-size:smaller }
pre.smalllisp { font-size:smaller }
span.sc { font-variant:small-caps }
span.roman { font-family:serif; font-weight:normal; }
span.sansserif { font-family:sans-serif; font-weight:normal; }
--></style>
</head>
<body>
<div class="node">
<a name="Adapteva-Epiphany-Options"></a>
<p>
Next:&nbsp;<a rel="next" accesskey="n" href="ARC-Options.html#ARC-Options">ARC Options</a>,
Previous:&nbsp;<a rel="previous" accesskey="p" href="AArch64-Options.html#AArch64-Options">AArch64 Options</a>,
Up:&nbsp;<a rel="up" accesskey="u" href="Submodel-Options.html#Submodel-Options">Submodel Options</a>
<hr>
</div>
<h4 class="subsection">3.17.2 Adapteva Epiphany Options</h4>
<p>These &lsquo;<samp><span class="samp">-m</span></samp>&rsquo; options are defined for Adapteva Epiphany:
<dl>
<dt><code>-mhalf-reg-file</code><dd><a name="index-mhalf_002dreg_002dfile-1291"></a>Don't allocate any register in the range <code>r32</code><small class="dots">...</small><code>r63</code>.
That allows code to run on hardware variants that lack these registers.
<br><dt><code>-mprefer-short-insn-regs</code><dd><a name="index-mprefer_002dshort_002dinsn_002dregs-1292"></a>Preferrentially allocate registers that allow short instruction generation.
This can result in increased instruction count, so this may either reduce or
increase overall code size.
<br><dt><code>-mbranch-cost=</code><var>num</var><dd><a name="index-mbranch_002dcost-1293"></a>Set the cost of branches to roughly <var>num</var> &ldquo;simple&rdquo; instructions.
This cost is only a heuristic and is not guaranteed to produce
consistent results across releases.
<br><dt><code>-mcmove</code><dd><a name="index-mcmove-1294"></a>Enable the generation of conditional moves.
<br><dt><code>-mnops=</code><var>num</var><dd><a name="index-mnops-1295"></a>Emit <var>num</var> NOPs before every other generated instruction.
<br><dt><code>-mno-soft-cmpsf</code><dd><a name="index-mno_002dsoft_002dcmpsf-1296"></a>For single-precision floating-point comparisons, emit an <code>fsub</code> instruction
and test the flags. This is faster than a software comparison, but can
get incorrect results in the presence of NaNs, or when two different small
numbers are compared such that their difference is calculated as zero.
The default is <samp><span class="option">-msoft-cmpsf</span></samp>, which uses slower, but IEEE-compliant,
software comparisons.
<br><dt><code>-mstack-offset=</code><var>num</var><dd><a name="index-mstack_002doffset-1297"></a>Set the offset between the top of the stack and the stack pointer.
E.g., a value of 8 means that the eight bytes in the range <code>sp+0...sp+7</code>
can be used by leaf functions without stack allocation.
Values other than &lsquo;<samp><span class="samp">8</span></samp>&rsquo; or &lsquo;<samp><span class="samp">16</span></samp>&rsquo; are untested and unlikely to work.
Note also that this option changes the ABI; compiling a program with a
different stack offset than the libraries have been compiled with
generally does not work.
This option can be useful if you want to evaluate if a different stack
offset would give you better code, but to actually use a different stack
offset to build working programs, it is recommended to configure the
toolchain with the appropriate <samp><span class="option">--with-stack-offset=</span><var>num</var></samp> option.
<br><dt><code>-mno-round-nearest</code><dd><a name="index-mno_002dround_002dnearest-1298"></a>Make the scheduler assume that the rounding mode has been set to
truncating. The default is <samp><span class="option">-mround-nearest</span></samp>.
<br><dt><code>-mlong-calls</code><dd><a name="index-mlong_002dcalls-1299"></a>If not otherwise specified by an attribute, assume all calls might be beyond
the offset range of the <code>b</code> / <code>bl</code> instructions, and therefore load the
function address into a register before performing a (otherwise direct) call.
This is the default.
<br><dt><code>-mshort-calls</code><dd><a name="index-short_002dcalls-1300"></a>If not otherwise specified by an attribute, assume all direct calls are
in the range of the <code>b</code> / <code>bl</code> instructions, so use these instructions
for direct calls. The default is <samp><span class="option">-mlong-calls</span></samp>.
<br><dt><code>-msmall16</code><dd><a name="index-msmall16-1301"></a>Assume addresses can be loaded as 16-bit unsigned values. This does not
apply to function addresses for which <samp><span class="option">-mlong-calls</span></samp> semantics
are in effect.
<br><dt><code>-mfp-mode=</code><var>mode</var><dd><a name="index-mfp_002dmode-1302"></a>Set the prevailing mode of the floating-point unit.
This determines the floating-point mode that is provided and expected
at function call and return time. Making this mode match the mode you
predominantly need at function start can make your programs smaller and
faster by avoiding unnecessary mode switches.
<p><var>mode</var> can be set to one the following values:
<dl>
<dt>&lsquo;<samp><span class="samp">caller</span></samp>&rsquo;<dd>Any mode at function entry is valid, and retained or restored when
the function returns, and when it calls other functions.
This mode is useful for compiling libraries or other compilation units
you might want to incorporate into different programs with different
prevailing FPU modes, and the convenience of being able to use a single
object file outweighs the size and speed overhead for any extra
mode switching that might be needed, compared with what would be needed
with a more specific choice of prevailing FPU mode.
<br><dt>&lsquo;<samp><span class="samp">truncate</span></samp>&rsquo;<dd>This is the mode used for floating-point calculations with
truncating (i.e. round towards zero) rounding mode. That includes
conversion from floating point to integer.
<br><dt>&lsquo;<samp><span class="samp">round-nearest</span></samp>&rsquo;<dd>This is the mode used for floating-point calculations with
round-to-nearest-or-even rounding mode.
<br><dt>&lsquo;<samp><span class="samp">int</span></samp>&rsquo;<dd>This is the mode used to perform integer calculations in the FPU, e.g.
integer multiply, or integer multiply-and-accumulate.
</dl>
<p>The default is <samp><span class="option">-mfp-mode=caller</span></samp>
<br><dt><code>-mnosplit-lohi</code><dt><code>-mno-postinc</code><dt><code>-mno-postmodify</code><dd><a name="index-mnosplit_002dlohi-1303"></a><a name="index-mno_002dpostinc-1304"></a><a name="index-mno_002dpostmodify-1305"></a>Code generation tweaks that disable, respectively, splitting of 32-bit
loads, generation of post-increment addresses, and generation of
post-modify addresses. The defaults are <samp><span class="option">msplit-lohi</span></samp>,
<samp><span class="option">-mpost-inc</span></samp>, and <samp><span class="option">-mpost-modify</span></samp>.
<br><dt><code>-mnovect-double</code><dd><a name="index-mno_002dvect_002ddouble-1306"></a>Change the preferred SIMD mode to SImode. The default is
<samp><span class="option">-mvect-double</span></samp>, which uses DImode as preferred SIMD mode.
<br><dt><code>-max-vect-align=</code><var>num</var><dd><a name="index-max_002dvect_002dalign-1307"></a>The maximum alignment for SIMD vector mode types.
<var>num</var> may be 4 or 8. The default is 8.
Note that this is an ABI change, even though many library function
interfaces are unaffected if they don't use SIMD vector modes
in places that affect size and/or alignment of relevant types.
<br><dt><code>-msplit-vecmove-early</code><dd><a name="index-msplit_002dvecmove_002dearly-1308"></a>Split vector moves into single word moves before reload. In theory this
can give better register allocation, but so far the reverse seems to be
generally the case.
<br><dt><code>-m1reg-</code><var>reg</var><dd><a name="index-m1reg_002d-1309"></a>Specify a register to hold the constant &minus;1, which makes loading small negative
constants and certain bitmasks faster.
Allowable values for <var>reg</var> are &lsquo;<samp><span class="samp">r43</span></samp>&rsquo; and &lsquo;<samp><span class="samp">r63</span></samp>&rsquo;,
which specify use of that register as a fixed register,
and &lsquo;<samp><span class="samp">none</span></samp>&rsquo;, which means that no register is used for this
purpose. The default is <samp><span class="option">-m1reg-none</span></samp>.
</dl>
</body></html>