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/Half_002dPrecision.html | |
https://developer.arm.com/downloads/-/arm-gnu-toolchain-downloads
Change-Id: I7303388733328cd98ab9aa3c30236db67f2e9e9c
Diffstat (limited to 'share/doc/gcc/Half_002dPrecision.html')
| -rw-r--r-- | share/doc/gcc/Half_002dPrecision.html | 159 |
1 files changed, 159 insertions, 0 deletions
diff --git a/share/doc/gcc/Half_002dPrecision.html b/share/doc/gcc/Half_002dPrecision.html new file mode 100644 index 0000000..ae90d35 --- /dev/null +++ b/share/doc/gcc/Half_002dPrecision.html @@ -0,0 +1,159 @@ +<!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): Half-Precision</title> + +<meta name="description" content="Using the GNU Compiler Collection (GCC): Half-Precision"> +<meta name="keywords" content="Using the GNU Compiler Collection (GCC): Half-Precision"> +<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="C-Extensions.html#C-Extensions" rel="up" title="C Extensions"> +<link href="Decimal-Float.html#Decimal-Float" rel="next" title="Decimal Float"> +<link href="Floating-Types.html#Floating-Types" rel="previous" title="Floating Types"> +<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="Half_002dPrecision"></a> +<div class="header"> +<p> +Next: <a href="Decimal-Float.html#Decimal-Float" accesskey="n" rel="next">Decimal Float</a>, Previous: <a href="Floating-Types.html#Floating-Types" accesskey="p" rel="previous">Floating Types</a>, Up: <a href="C-Extensions.html#C-Extensions" accesskey="u" rel="up">C Extensions</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="Half_002dPrecision-Floating-Point"></a> +<h3 class="section">6.13 Half-Precision Floating Point</h3> +<a name="index-half_002dprecision-floating-point"></a> +<a name="index-_005f_005ffp16-data-type"></a> +<a name="index-_005f_005fFloat16-data-type"></a> + +<p>On ARM and AArch64 targets, GCC supports half-precision (16-bit) floating +point via the <code>__fp16</code> type defined in the ARM C Language Extensions. +On ARM systems, you must enable this type explicitly with the +<samp>-mfp16-format</samp> command-line option in order to use it. +On x86 targets with SSE2 enabled, GCC supports half-precision (16-bit) +floating point via the <code>_Float16</code> type. For C++, x86 provides a builtin +type named <code>_Float16</code> which contains same data format as C. +</p> +<p>ARM targets support two incompatible representations for half-precision +floating-point values. You must choose one of the representations and +use it consistently in your program. +</p> +<p>Specifying <samp>-mfp16-format=ieee</samp> selects the IEEE 754-2008 format. +This format can represent normalized values in the range of <em>2^{-14}</em> to 65504. +There are 11 bits of significand precision, approximately 3 +decimal digits. +</p> +<p>Specifying <samp>-mfp16-format=alternative</samp> selects the ARM +alternative format. This representation is similar to the IEEE +format, but does not support infinities or NaNs. Instead, the range +of exponents is extended, so that this format can represent normalized +values in the range of <em>2^{-14}</em> to 131008. +</p> +<p>The GCC port for AArch64 only supports the IEEE 754-2008 format, and does +not require use of the <samp>-mfp16-format</samp> command-line option. +</p> +<p>The <code>__fp16</code> type may only be used as an argument to intrinsics defined +in <code><arm_fp16.h></code>, or as a storage format. For purposes of +arithmetic and other operations, <code>__fp16</code> values in C or C++ +expressions are automatically promoted to <code>float</code>. +</p> +<p>The ARM target provides hardware support for conversions between +<code>__fp16</code> and <code>float</code> values +as an extension to VFP and NEON (Advanced SIMD), and from ARMv8-A provides +hardware support for conversions between <code>__fp16</code> and <code>double</code> +values. GCC generates code using these hardware instructions if you +compile with options to select an FPU that provides them; +for example, <samp>-mfpu=neon-fp16 -mfloat-abi=softfp</samp>, +in addition to the <samp>-mfp16-format</samp> option to select +a half-precision format. +</p> +<p>Language-level support for the <code>__fp16</code> data type is +independent of whether GCC generates code using hardware floating-point +instructions. In cases where hardware support is not specified, GCC +implements conversions between <code>__fp16</code> and other types as library +calls. +</p> +<p>It is recommended that portable code use the <code>_Float16</code> type defined +by ISO/IEC TS 18661-3:2015. See <a href="Floating-Types.html#Floating-Types">Floating Types</a>. +</p> +<p>On x86 targets with SSE2 enabled, without <samp>-mavx512fp16</samp>, +all operations will be emulated by software emulation and the <code>float</code> +instructions. The default behavior for <code>FLT_EVAL_METHOD</code> is to keep the +intermediate result of the operation as 32-bit precision. This may lead to +inconsistent behavior between software emulation and AVX512-FP16 instructions. +Using <samp>-fexcess-precision=16</samp> will force round back after each operation. +</p> +<p>Using <samp>-mavx512fp16</samp> will generate AVX512-FP16 instructions instead of +software emulation. The default behavior of <code>FLT_EVAL_METHOD</code> is to round +after each operation. The same is true with <samp>-fexcess-precision=standard</samp> +and <samp>-mfpmath=sse</samp>. If there is no <samp>-mfpmath=sse</samp>, +<samp>-fexcess-precision=standard</samp> alone does the same thing as before, +It is useful for code that does not have <code>_Float16</code> and runs on the x87 +FPU. +</p> +<hr> +<div class="header"> +<p> +Next: <a href="Decimal-Float.html#Decimal-Float" accesskey="n" rel="next">Decimal Float</a>, Previous: <a href="Floating-Types.html#Floating-Types" accesskey="p" rel="previous">Floating Types</a>, Up: <a href="C-Extensions.html#C-Extensions" accesskey="u" rel="up">C Extensions</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> |