mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-29 16:21:07 +00:00
30dcf959d2
As discussed in <https://sourceware.org/ml/libc-alpha/2016-05/msg00577.html>, TS 18661-1 disallows ceil, floor, round and trunc functions from raising the "inexact" exception, in accordance with general IEEE 754 semantics for when that exception is raised. Fixing this for x87 floating point is more complicated than for the other versions of these functions, because they use the frndint instruction that raises "inexact" and this can only be avoided by saving and restoring the whole floating-point environment. As I noted in <https://sourceware.org/ml/libc-alpha/2016-06/msg00128.html>, I have now implemented a GCC option -fno-fp-int-builtin-inexact for GCC 7, such that GCC will inline these functions on x86, without caring about "inexact", when the default -ffp-int-builtin-inexact is in effect. This allows users to get optimized code depending on the options they pass to the compiler, while making the out-of-line functions follow TS 18661-1 semantics and avoid "inexact". This patch duly fixes the out-of-line trunc function implementations to avoid "inexact", in the same way as the nearbyint implementations. I do not know how the performance of implementations such as these based on saving the environment and changing the rounding mode temporarily compares to that of the C versions or SSE 4.1 versions (of course, for 32-bit x86 SSE implementations still need to get the return value in an x87 register); it's entirely possible other implementations could be faster in some cases. Tested for x86_64 and x86. [BZ #15479] * sysdeps/i386/fpu/s_trunc.S (__trunc): Save and restore floating-point environment rather than just control word. * sysdeps/i386/fpu/s_truncf.S (__truncf): Likewise. * sysdeps/i386/fpu/s_truncl.S (__truncl): Save and restore floating-point environment, with "invalid" exceptions merged in, rather than just control word. * sysdeps/x86_64/fpu/s_truncl.S (__truncl): Likewise. * math/libm-test.inc (trunc_test_data): Do not allow spurious "inexact" exceptions.
41 lines
1.2 KiB
ArmAsm
41 lines
1.2 KiB
ArmAsm
/* Truncate long double value.
|
|
Copyright (C) 1997-2016 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
Contributed by Ulrich Drepper <drepper@cygnus.com>, 1997.
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Lesser General Public
|
|
License as published by the Free Software Foundation; either
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with the GNU C Library; if not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#include <machine/asm.h>
|
|
|
|
ENTRY(__truncl)
|
|
fldt 4(%esp)
|
|
subl $32, %esp
|
|
cfi_adjust_cfa_offset (32)
|
|
fnstenv 4(%esp)
|
|
movl $0xc00, %edx
|
|
orl 4(%esp), %edx
|
|
movl %edx, (%esp)
|
|
fldcw (%esp)
|
|
frndint
|
|
fnstsw
|
|
andl $0x1, %eax
|
|
orl %eax, 8(%esp)
|
|
fldenv 4(%esp)
|
|
addl $32, %esp
|
|
cfi_adjust_cfa_offset (-32)
|
|
ret
|
|
END(__truncl)
|
|
weak_alias (__truncl, truncl)
|