AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-12-26 04:31:03 +00:00
Code Issues Packages Projects Releases Wiki Activity
2702856bf4
glibc/sysdeps/x86_64/dl-trampoline.S
H.J. Lu fb0f7a6755 X86-64: Add _dl_runtime_resolve_avx[512]_{opt|slow} [BZ #20508] 
There is transition penalty when SSE instructions are mixed with 256-bit
AVX or 512-bit AVX512 load instructions.  Since _dl_runtime_resolve_avx
and _dl_runtime_profile_avx512 save/restore 256-bit YMM/512-bit ZMM
registers, there is transition penalty when SSE instructions are used
with lazy binding on AVX and AVX512 processors.

To avoid SSE transition penalty, if only the lower 128 bits of the first
8 vector registers are non-zero, we can preserve %xmm0 - %xmm7 registers
with the zero upper bits.

For AVX and AVX512 processors which support XGETBV with ECX == 1, we can
use XGETBV with ECX == 1 to check if the upper 128 bits of YMM registers
or the upper 256 bits of ZMM registers are zero.  We can restore only the
non-zero portion of vector registers with AVX/AVX512 load instructions
which will zero-extend upper bits of vector registers.

This patch adds _dl_runtime_resolve_sse_vex which saves and restores
XMM registers with 128-bit AVX store/load instructions.  It is used to
preserve YMM/ZMM registers when only the lower 128 bits are non-zero.
_dl_runtime_resolve_avx_opt and _dl_runtime_resolve_avx512_opt are added
and used on AVX/AVX512 processors supporting XGETBV with ECX == 1 so
that we store and load only the non-zero portion of vector registers.
This avoids SSE transition penalty caused by _dl_runtime_resolve_avx and
_dl_runtime_profile_avx512 when only the lower 128 bits of vector
registers are used.

_dl_runtime_resolve_avx_slow is added and used for AVX processors which
don't support XGETBV with ECX == 1.  Since there is no SSE transition
penalty on AVX512 processors which don't support XGETBV with ECX == 1,
_dl_runtime_resolve_avx512_slow isn't provided.

	[BZ #20495]
	[BZ #20508]
	* sysdeps/x86/cpu-features.c (init_cpu_features): For Intel
	processors, set Use_dl_runtime_resolve_slow and set
	Use_dl_runtime_resolve_opt if XGETBV suports ECX == 1.
	* sysdeps/x86/cpu-features.h (bit_arch_Use_dl_runtime_resolve_opt):
	New.
	(bit_arch_Use_dl_runtime_resolve_slow): Likewise.
	(index_arch_Use_dl_runtime_resolve_opt): Likewise.
	(index_arch_Use_dl_runtime_resolve_slow): Likewise.
	* sysdeps/x86_64/dl-machine.h (elf_machine_runtime_setup): Use
	_dl_runtime_resolve_avx512_opt and _dl_runtime_resolve_avx_opt
	if Use_dl_runtime_resolve_opt is set.  Use
	_dl_runtime_resolve_slow if Use_dl_runtime_resolve_slow is set.
	* sysdeps/x86_64/dl-trampoline.S: Include <cpu-features.h>.
	(_dl_runtime_resolve_opt): New.  Defined for AVX and AVX512.
	(_dl_runtime_resolve): Add one for _dl_runtime_resolve_sse_vex.
	* sysdeps/x86_64/dl-trampoline.h (_dl_runtime_resolve_avx_slow):
	New.
	(_dl_runtime_resolve_opt): Likewise.
	(_dl_runtime_profile): Define only if _dl_runtime_profile is
	defined.
2016-09-06 08:51:07 -07:00

149 lines
4.9 KiB
ArmAsm
Raw Blame History

/* PLT trampolines. x86-64 version.
Copyright (C) 2004-2016 Free Software Foundation, Inc.
This file is part of the GNU C Library.
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 <config.h>
#include <sysdep.h>
#include <cpu-features.h>
#include <link-defines.h>
#ifndef DL_STACK_ALIGNMENT
/* Due to GCC bug:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58066
__tls_get_addr may be called with 8-byte stack alignment. Although
this bug has been fixed in GCC 4.9.4, 5.3 and 6, we can't assume
that stack will be always aligned at 16 bytes. We use unaligned
16-byte move to load and store SSE registers, which has no penalty
on modern processors if stack is 16-byte aligned. */
# define DL_STACK_ALIGNMENT 8
#endif
#ifndef DL_RUNTIME_UNALIGNED_VEC_SIZE
/* The maximum size in bytes of unaligned vector load and store in the
dynamic linker. Since SSE optimized memory/string functions with
aligned SSE register load and store are used in the dynamic linker,
we must set this to 8 so that _dl_runtime_resolve_sse will align the
stack before calling _dl_fixup. */
# define DL_RUNTIME_UNALIGNED_VEC_SIZE 8
#endif
/* True if _dl_runtime_resolve should align stack to VEC_SIZE bytes. */
#define DL_RUNTIME_RESOLVE_REALIGN_STACK \
(VEC_SIZE > DL_STACK_ALIGNMENT \
&& VEC_SIZE > DL_RUNTIME_UNALIGNED_VEC_SIZE)
/* Align vector register save area to 16 bytes. */
#define REGISTER_SAVE_VEC_OFF 0
/* Area on stack to save and restore registers used for parameter
passing when calling _dl_fixup. */
#ifdef __ILP32__
# define REGISTER_SAVE_RAX (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 8)
# define PRESERVE_BND_REGS_PREFIX
#else
/* Align bound register save area to 16 bytes. */
# define REGISTER_SAVE_BND0 (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 8)
# define REGISTER_SAVE_BND1 (REGISTER_SAVE_BND0 + 16)
# define REGISTER_SAVE_BND2 (REGISTER_SAVE_BND1 + 16)
# define REGISTER_SAVE_BND3 (REGISTER_SAVE_BND2 + 16)
# define REGISTER_SAVE_RAX (REGISTER_SAVE_BND3 + 16)
# ifdef HAVE_MPX_SUPPORT
# define PRESERVE_BND_REGS_PREFIX bnd
# else
# define PRESERVE_BND_REGS_PREFIX .byte 0xf2
# endif
#endif
#define REGISTER_SAVE_RCX (REGISTER_SAVE_RAX + 8)
#define REGISTER_SAVE_RDX (REGISTER_SAVE_RCX + 8)
#define REGISTER_SAVE_RSI (REGISTER_SAVE_RDX + 8)
#define REGISTER_SAVE_RDI (REGISTER_SAVE_RSI + 8)
#define REGISTER_SAVE_R8 (REGISTER_SAVE_RDI + 8)
#define REGISTER_SAVE_R9 (REGISTER_SAVE_R8 + 8)
#define RESTORE_AVX
#define VEC_SIZE 64
#define VMOVA vmovdqa64
#if DL_RUNTIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
# define VMOV vmovdqa64
#else
# define VMOV vmovdqu64
#endif
#define VEC(i) zmm##i
#define _dl_runtime_resolve _dl_runtime_resolve_avx512
#define _dl_runtime_resolve_opt _dl_runtime_resolve_avx512_opt
#define _dl_runtime_profile _dl_runtime_profile_avx512
#include "dl-trampoline.h"
#undef _dl_runtime_resolve
#undef _dl_runtime_resolve_opt
#undef _dl_runtime_profile
#undef VEC
#undef VMOV
#undef VMOVA
#undef VEC_SIZE
#define VEC_SIZE 32
#define VMOVA vmovdqa
#if DL_RUNTIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
# define VMOV vmovdqa
#else
# define VMOV vmovdqu
#endif
#define VEC(i) ymm##i
#define _dl_runtime_resolve _dl_runtime_resolve_avx
#define _dl_runtime_resolve_opt _dl_runtime_resolve_avx_opt
#define _dl_runtime_profile _dl_runtime_profile_avx
#include "dl-trampoline.h"
#undef _dl_runtime_resolve
#undef _dl_runtime_resolve_opt
#undef _dl_runtime_profile
#undef VEC
#undef VMOV
#undef VMOVA
#undef VEC_SIZE
/* movaps/movups is 1-byte shorter. */
#define VEC_SIZE 16
#define VMOVA movaps
#if DL_RUNTIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
# define VMOV movaps
#else
# define VMOV movups
#endif
#define VEC(i) xmm##i
#define _dl_runtime_resolve _dl_runtime_resolve_sse
#define _dl_runtime_profile _dl_runtime_profile_sse
#undef RESTORE_AVX
#include "dl-trampoline.h"
#undef _dl_runtime_resolve
#undef _dl_runtime_profile
#undef VMOV
#undef VMOVA
/* Used by _dl_runtime_resolve_avx_opt/_dl_runtime_resolve_avx512_opt
to preserve the full vector registers with zero upper bits. */
#define VMOVA vmovdqa
#if DL_RUNTIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
# define VMOV vmovdqa
#else
# define VMOV vmovdqu
#endif
#define _dl_runtime_resolve _dl_runtime_resolve_sse_vex
#include "dl-trampoline.h"
Reference in New Issue View Git Blame Copy Permalink