From: Pádraig Brady
Date: Thu, 1 Feb 2024 17:59:51 +0000 (+0000)
Subject: od: support half precision floating point
X-Git-Tag: v9.5~72
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=76604db7d2da0ceb4de4542ebf315b3d6415f972;p=thirdparty%2Fcoreutils.git
od: support half precision floating point
Rely on compiler support for _Float16 and __bf16
to support -fH and -fB formats respectively.
I.e. IEEE 16 bit, and brain 16 bit floats respectively.
Modern GCC and LLVM compilers support both types.
clang-sect=half-precision-floating-point
https://gcc.gnu.org/onlinedocs/gcc/Half-Precision.html
https://clang.llvm.org/docs/LanguageExtensions.html#$clang-sect
https://www.open-std.org/jtc1/sc22/wg21/docs/papers/2018/p0192r4.html
https://www.open-std.org/jtc1/sc22/wg21/docs/papers/2022/p1467r9.html
This was tested on:
gcc 13, clang 17 x86 (Both types supported)
gcc 7 aarch64 (Only -fH supported)
gcc 13 ppc(be) (Neither supported. Both will be with GCC 14)
* src/od.c: Support -tf2 or -tfH to print IEEE 16 bit floating point,
or -tfB to print Brain 16 bit floating point.
* configure.ac: Check for _Float16 and __bf16 types.
* doc/coreutils.texi (od invocation): Mention the new -f types.
* tests/od/od-float.sh: Add test cases.
* NEWS: Mention the new feature.
Addresses https://bugs.gnu.org/68871
---
diff --git a/NEWS b/NEWS
index dc5d875ddc..5b5befd2cb 100644
--- a/NEWS
+++ b/NEWS
@@ -57,6 +57,9 @@ GNU coreutils NEWS -*- outline -*-
chgrp now accepts the --from=OWNER:GROUP option to restrict changes to files
with matching current OWNER and/or GROUP, as already supported by chown(1).
+ od now supports printing IEEE half precision floating point with -t fH,
+ or brain 16 bit floating point with -t fB, where supported by the compiler.
+
tail now supports following multiple processes, with repeated --pid options.
** Improvements
diff --git a/configure.ac b/configure.ac
index 48ab4ef533..64ff32a96f 100644
--- a/configure.ac
+++ b/configure.ac
@@ -522,6 +522,9 @@ CFLAGS=$ac_save_CFLAGS
LDFLAGS=$ac_save_LDFLAGS
ac_c_werror_flag=$cu_save_c_werror_flag
+# Test compiler support for half precision floating point types (for od)
+AC_CHECK_TYPES([_Float16, __bf16])
+
ac_save_CFLAGS=$CFLAGS
CFLAGS="-mavx -mpclmul $CFLAGS"
AC_MSG_CHECKING([if pclmul intrinsic exists])
diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index d13e0f834d..d7cf5e08aa 100644
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -2127,6 +2127,12 @@ long
For floating point (@code{f}):
@table @asis
+@item B
+@uref{https://en.wikipedia.org/wiki/Bfloat16_floating-point_format,
+brain 16 bit float}
+@item H
+@uref{https://en.wikipedia.org/wiki/Half-precision_floating-point_format,
+half precision float}
@item F
float
@item D
diff --git a/src/od.c b/src/od.c
index 75bed5e7db..1e24893671 100644
--- a/src/od.c
+++ b/src/od.c
@@ -19,6 +19,7 @@
#include
#include
+#include
#include
#include
#include
@@ -49,6 +50,26 @@ typedef unsigned long long int unsigned_long_long_int;
typedef unsigned long int unsigned_long_long_int;
#endif
+#if HAVE__FLOAT16
+ /* Available since clang 6 (2018), and gcc 7 (2017). */
+ typedef _Float16 float16;
+#else
+# define HAVE__FLOAT16 0
+ /* This is just a place-holder to avoid a few '#if' directives.
+ In this case, the type isn't actually used. */
+ typedef float float16;
+#endif
+
+#if HAVE___BF16
+ /* Available since clang 11 (2020), and gcc 13 (2023). */
+ typedef __bf16 bfloat16;
+#else
+# define HAVE___BF16 0
+ /* This is just a place-holder to avoid a few '#if' directives.
+ In this case, the type isn't actually used. */
+ typedef float bfloat16;
+#endif
+
enum size_spec
{
NO_SIZE,
@@ -58,6 +79,7 @@ enum size_spec
LONG,
LONG_LONG,
/* FIXME: add INTMAX support, too */
+ FLOAT_HALF,
FLOAT_SINGLE,
FLOAT_DOUBLE,
FLOAT_LONG_DOUBLE,
@@ -71,6 +93,8 @@ enum output_format
OCTAL,
HEXADECIMAL,
FLOATING_POINT,
+ HFLOATING_POINT,
+ BFLOATING_POINT,
NAMED_CHARACTER,
CHARACTER
};
@@ -156,6 +180,11 @@ static const int width_bytes[] =
sizeof (int),
sizeof (long int),
sizeof (unsigned_long_long_int),
+#if HAVE___BF16
+ sizeof (bfloat16),
+#else
+ sizeof (float16),
+#endif
sizeof (float),
sizeof (double),
sizeof (long double)
@@ -400,8 +429,9 @@ TYPE is made up of one or more of these specifications:\n\
\n\
SIZE is a number. For TYPE in [doux], SIZE may also be C for\n\
sizeof(char), S for sizeof(short), I for sizeof(int) or L for\n\
-sizeof(long). If TYPE is f, SIZE may also be F for sizeof(float), D\n\
-for sizeof(double) or L for sizeof(long double).\n\
+sizeof(long). If TYPE is f, SIZE may also be B for Brain 16 bit,\n\
+H for Half precision float, F for sizeof(float), D for sizeof(double),\n\
+or L for sizeof(long double).\n\
"), stdout);
fputs (_("\
\n\
@@ -477,6 +507,8 @@ PRINT_TYPE (print_int, unsigned int)
PRINT_TYPE (print_long, unsigned long int)
PRINT_TYPE (print_long_long, unsigned_long_long_int)
+PRINT_FLOATTYPE (print_bfloat, bfloat16, ftoastr, FLT_BUFSIZE_BOUND)
+PRINT_FLOATTYPE (print_halffloat, float16, ftoastr, FLT_BUFSIZE_BOUND)
PRINT_FLOATTYPE (print_float, float, ftoastr, FLT_BUFSIZE_BOUND)
PRINT_FLOATTYPE (print_double, double, dtoastr, DBL_BUFSIZE_BOUND)
PRINT_FLOATTYPE (print_long_double, long double, ldtoastr, LDBL_BUFSIZE_BOUND)
@@ -773,6 +805,18 @@ decode_one_format (char const *s_orig, char const *s, char const **next,
++s;
switch (*s)
{
+ case 'B':
+ ++s;
+ fmt = BFLOATING_POINT;
+ size = sizeof (bfloat16);
+ break;
+
+ case 'H':
+ ++s;
+ fmt = HFLOATING_POINT;
+ size = sizeof (float16);
+ break;
+
case 'F':
++s;
size = sizeof (float);
@@ -802,7 +846,10 @@ decode_one_format (char const *s_orig, char const *s, char const **next,
else
{
if (size > MAX_FP_TYPE_SIZE
- || fp_type_size[size] == NO_SIZE)
+ || fp_type_size[size] == NO_SIZE
+ || (! HAVE__FLOAT16 && HAVE___BF16
+ && size == sizeof (bfloat16))
+ )
{
error (0, 0,
_("invalid type string %s;\n"
@@ -817,6 +864,15 @@ decode_one_format (char const *s_orig, char const *s, char const **next,
}
size_spec = fp_type_size[size];
+ if ((! HAVE__FLOAT16 && fmt == HFLOATING_POINT)
+ || (! HAVE___BF16 && fmt == BFLOATING_POINT))
+ {
+ error (0, 0,
+ _("this system doesn't provide a %s floating point type"),
+ quote (s_orig));
+ return false;
+ }
+
{
struct lconv const *locale = localeconv ();
size_t decimal_point_len =
@@ -824,6 +880,12 @@ decode_one_format (char const *s_orig, char const *s, char const **next,
switch (size_spec)
{
+ case FLOAT_HALF:
+ print_function = fmt == BFLOATING_POINT
+ ? print_bfloat : print_halffloat;
+ field_width = FLT_STRLEN_BOUND_L (decimal_point_len);
+ break;
+
case FLOAT_SINGLE:
print_function = print_float;
field_width = FLT_STRLEN_BOUND_L (decimal_point_len);
@@ -1598,6 +1660,11 @@ main (int argc, char **argv)
for (i = 0; i <= MAX_FP_TYPE_SIZE; i++)
fp_type_size[i] = NO_SIZE;
+#if HAVE__FLOAT16
+ fp_type_size[sizeof (float16)] = FLOAT_HALF;
+#elif HAVE___BF16
+ fp_type_size[sizeof (bfloat16)] = FLOAT_HALF;
+#endif
fp_type_size[sizeof (float)] = FLOAT_SINGLE;
/* The array entry for 'double' is filled in after that for 'long double'
so that if they are the same size, we avoid any overhead of
diff --git a/tests/od/od-float.sh b/tests/od/od-float.sh
index 35a6d1249a..239b5f10e4 100755
--- a/tests/od/od-float.sh
+++ b/tests/od/od-float.sh
@@ -69,4 +69,25 @@ set x $(printf 00000000ff000000 | tr 0f '\000\377' | od -t fL) || fail=1
#*) fail=1;;
#esac
+# Check Half precision IEEE 16 bit float
+if grep '^#define HAVE__FLOAT16 1' "$CONFIG_HEADER" >/dev/null; then
+ for fmt in '-tfH' '-tf2'; do
+ od_out=$(printf '\x3C\x00\x3C\x00' | od --endian=big -An $fmt | tr -d ' ')
+ test "$od_out" = '11' || fail=1
+ done
+else
+ echo "od: this system doesn't provide a 'fH' floating point type" > exp_err
+ returns_ 1 od -tfH /dev/null 2>err || fail=1
+ compare exp_err err || fail=1
+fi
+# Check Half precision Brain 16 bit float
+if grep '^#define HAVE___BF16 1' "$CONFIG_HEADER" >/dev/null; then
+ od_out=$(printf '\x3F\x80\x3F\x80' | od --endian=big -An -tfB | tr -d ' ')
+ test "$od_out" = '11' || fail=1
+else
+ echo "od: this system doesn't provide a 'fB' floating point type" > exp_err
+ returns_ 1 od -tfB /dev/null 2>err || fail=1
+ compare exp_err err || fail=1
+fi
+
Exit $fail