2012-04-17 02:02:27 +00:00
|
|
|
.file "fmal.s"
|
|
|
|
|
|
|
|
|
|
|
|
// Copyright (c) 2001 - 2003, Intel Corporation
|
|
|
|
// All rights reserved.
|
|
|
|
//
|
|
|
|
//
|
|
|
|
// Redistribution and use in source and binary forms, with or without
|
|
|
|
// modification, are permitted provided that the following conditions are
|
|
|
|
// met:
|
|
|
|
//
|
|
|
|
// * Redistributions of source code must retain the above copyright
|
|
|
|
// notice, this list of conditions and the following disclaimer.
|
|
|
|
//
|
|
|
|
// * Redistributions in binary form must reproduce the above copyright
|
|
|
|
// notice, this list of conditions and the following disclaimer in the
|
|
|
|
// documentation and/or other materials provided with the distribution.
|
|
|
|
//
|
|
|
|
// * The name of Intel Corporation may not be used to endorse or promote
|
|
|
|
// products derived from this software without specific prior written
|
|
|
|
// permission.
|
|
|
|
|
2012-04-17 02:08:04 +00:00
|
|
|
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
|
|
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
2012-04-17 02:02:27 +00:00
|
|
|
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
2012-04-17 02:08:04 +00:00
|
|
|
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL OR ITS
|
2012-04-17 02:02:27 +00:00
|
|
|
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
2012-04-17 02:08:04 +00:00
|
|
|
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
|
|
|
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
|
|
|
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
2012-04-17 02:02:27 +00:00
|
|
|
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY OR TORT (INCLUDING
|
2012-04-17 02:08:04 +00:00
|
|
|
// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
|
|
|
// SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
//
|
2012-04-17 02:02:27 +00:00
|
|
|
// Intel Corporation is the author of this code, and requests that all
|
2012-04-17 02:08:04 +00:00
|
|
|
// problem reports or change requests be submitted to it directly at
|
2012-04-17 02:02:27 +00:00
|
|
|
// http://www.intel.com/software/products/opensource/libraries/num.htm.
|
|
|
|
//
|
|
|
|
// History
|
|
|
|
//==============================================================
|
2012-04-17 02:08:04 +00:00
|
|
|
// 06/07/01 Initial version
|
2012-04-17 02:02:27 +00:00
|
|
|
// 05/20/02 Cleaned up namespace and sf0 syntax
|
|
|
|
// 02/10/03 Reordered header: .section, .global, .proc, .align
|
|
|
|
//
|
|
|
|
// API
|
|
|
|
//==============================================================
|
|
|
|
// long double fmal (long double x, long double y, long double z)
|
|
|
|
//
|
|
|
|
// Overview of operation
|
|
|
|
//==============================================================
|
|
|
|
// returns x * y + z with one rounding error
|
|
|
|
|
|
|
|
// All the special cases are handled by the fma instruction itself
|
|
|
|
|
|
|
|
// floating-point registers used: 3
|
|
|
|
// f8, input x, output
|
|
|
|
// f9, input y
|
|
|
|
// f10, input z
|
|
|
|
|
|
|
|
.section .text
|
|
|
|
GLOBAL_LIBM_ENTRY(fmal)
|
|
|
|
|
|
|
|
{ .mfb
|
|
|
|
nop.m 999
|
|
|
|
fma.s0 f8 = f8, f9, f10 // Result = x * y + z
|
2012-04-17 02:08:04 +00:00
|
|
|
br.ret.sptk b0
|
2012-04-17 02:02:27 +00:00
|
|
|
}
|
|
|
|
;;
|
|
|
|
|
|
|
|
GLOBAL_LIBM_END(fmal)
|
2017-11-23 23:34:54 +00:00
|
|
|
libm_alias_ldouble_other (fma, fma)
|
Add narrowing fma functions
This patch adds the narrowing fused multiply-add functions from TS
18661-1 / TS 18661-3 / C2X to glibc's libm: ffma, ffmal, dfmal,
f32fmaf64, f32fmaf32x, f32xfmaf64 for all configurations; f32fmaf64x,
f32fmaf128, f64fmaf64x, f64fmaf128, f32xfmaf64x, f32xfmaf128,
f64xfmaf128 for configurations with _Float64x and _Float128;
__f32fmaieee128 and __f64fmaieee128 aliases in the powerpc64le case
(for calls to ffmal and dfmal when long double is IEEE binary128).
Corresponding tgmath.h macro support is also added.
The changes are mostly similar to those for the other narrowing
functions previously added, especially that for sqrt, so the
description of those generally applies to this patch as well. As with
sqrt, I reused the same test inputs in auto-libm-test-in as for
non-narrowing fma rather than adding extra or separate inputs for
narrowing fma. The tests in libm-test-narrow-fma.inc also follow
those for non-narrowing fma.
The non-narrowing fma has a known bug (bug 6801) that it does not set
errno on errors (overflow, underflow, Inf * 0, Inf - Inf). Rather
than fixing this or having narrowing fma check for errors when
non-narrowing does not (complicating the cases when narrowing fma can
otherwise be an alias for a non-narrowing function), this patch does
not attempt to check for errors from narrowing fma and set errno; the
CHECK_NARROW_FMA macro is still present, but as a placeholder that
does nothing, and this missing errno setting is considered to be
covered by the existing bug rather than needing a separate open bug.
missing-errno annotations are duly added to many of the
auto-libm-test-in test inputs for fma.
This completes adding all the new functions from TS 18661-1 to glibc,
so will be followed by corresponding stdc-predef.h changes to define
__STDC_IEC_60559_BFP__ and __STDC_IEC_60559_COMPLEX__, as the support
for TS 18661-1 will be at a similar level to that for C standard
floating-point facilities up to C11 (pragmas not implemented, but
library functions done). (There are still further changes to be done
to implement changes to the types of fromfp functions from N2548.)
Tested as followed: natively with the full glibc testsuite for x86_64
(GCC 11, 7, 6) and x86 (GCC 11); with build-many-glibcs.py with GCC
11, 7 and 6; cross testing of math/ tests for powerpc64le, powerpc32
hard float, mips64 (all three ABIs, both hard and soft float). The
different GCC versions are to cover the different cases in tgmath.h
and tgmath.h tests properly (GCC 6 has _Float* only as typedefs in
glibc headers, GCC 7 has proper _Float* support, GCC 8 adds
__builtin_tgmath).
2021-09-22 21:25:31 +00:00
|
|
|
libm_alias_ldouble_narrow (fma, fma)
|