mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-01-31 03:27:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
cosmopolitan/third_party/intel/bmiintrin.internal.h
Justine Tunney 957c61cbbf
Release Cosmopolitan v3.3 
This change upgrades to GCC 12.3 and GNU binutils 2.42. The GNU linker
appears to have changed things so that only a single de-duplicated str
table is present in the binary, and it gets placed wherever the linker
wants, regardless of what the linker script says. To cope with that we
need to stop using .ident to embed licenses. As such, this change does
significant work to revamp how third party licenses are defined in the
codebase, using `.section .notice,"aR",@progbits`.

This new GCC 12.3 toolchain has support for GNU indirect functions. It
lets us support __target_clones__ for the first time. This is used for
optimizing the performance of libc string functions such as strlen and
friends so far on x86, by ensuring AVX systems favor a second codepath
that uses VEX encoding. It shaves some latency off certain operations.
It's a useful feature to have for scientific computing for the reasons
explained by the test/libcxx/openmp_test.cc example which compiles for
fifteen different microarchitectures. Thanks to the upgrades, it's now
also possible to use newer instruction sets, such as AVX512FP16, VNNI.

Cosmo now uses the %gs register on x86 by default for TLS. Doing it is
helpful for any program that links `cosmo_dlopen()`. Such programs had
to recompile their binaries at startup to change the TLS instructions.
That's not great, since it means every page in the executable needs to
be faulted. The work of rewriting TLS-related x86 opcodes, is moved to
fixupobj.com instead. This is great news for MacOS x86 users, since we
previously needed to morph the binary every time for that platform but
now that's no longer necessary. The only platforms where we need fixup
of TLS x86 opcodes at runtime are now Windows, OpenBSD, and NetBSD. On
Windows we morph TLS to point deeper into the TIB, based on a TlsAlloc
assignment, and on OpenBSD/NetBSD we morph %gs back into %fs since the
kernels do not allow us to specify a value for the %gs register.

OpenBSD users are now required to use APE Loader to run Cosmo binaries
and assimilation is no longer possible. OpenBSD kernel needs to change
to allow programs to specify a value for the %gs register, or it needs
to stop marking executable pages loaded by the kernel as mimmutable().

This release fixes __constructor__, .ctor, .init_array, and lastly the
.preinit_array so they behave the exact same way as glibc.

We no longer use hex constants to define math.h symbols like M_PI.
2024-02-20 13:27:59 -08:00

149 lines
5 KiB
C
Raw Blame History

#if defined(__x86_64__) && !(__ASSEMBLER__ + __LINKER__ + 0)
#ifndef _X86GPRINTRIN_H_INCLUDED
# error "Never use <bmiintrin.h> directly; include <x86gprintrin.h> instead."
#endif
#ifndef _BMIINTRIN_H_INCLUDED
#define _BMIINTRIN_H_INCLUDED
#ifndef __BMI__
#pragma GCC push_options
#pragma GCC target("bmi")
#define __DISABLE_BMI__
#endif
extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__tzcnt_u16 (unsigned short __X)
{
return __builtin_ia32_tzcnt_u16 (__X);
}
extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_tzcnt_u16 (unsigned short __X)
{
return __builtin_ia32_tzcnt_u16 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__andn_u32 (unsigned int __X, unsigned int __Y)
{
return ~__X & __Y;
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_andn_u32 (unsigned int __X, unsigned int __Y)
{
return __andn_u32 (__X, __Y);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__bextr_u32 (unsigned int __X, unsigned int __Y)
{
return __builtin_ia32_bextr_u32 (__X, __Y);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_bextr_u32 (unsigned int __X, unsigned int __Y, unsigned __Z)
{
return __builtin_ia32_bextr_u32 (__X, ((__Y & 0xff) | ((__Z & 0xff) << 8)));
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__blsi_u32 (unsigned int __X)
{
return __X & -__X;
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_blsi_u32 (unsigned int __X)
{
return __blsi_u32 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__blsmsk_u32 (unsigned int __X)
{
return __X ^ (__X - 1);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_blsmsk_u32 (unsigned int __X)
{
return __blsmsk_u32 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__blsr_u32 (unsigned int __X)
{
return __X & (__X - 1);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_blsr_u32 (unsigned int __X)
{
return __blsr_u32 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__tzcnt_u32 (unsigned int __X)
{
return __builtin_ia32_tzcnt_u32 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_tzcnt_u32 (unsigned int __X)
{
return __builtin_ia32_tzcnt_u32 (__X);
}
#ifdef __x86_64__
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__andn_u64 (unsigned long long __X, unsigned long long __Y)
{
return ~__X & __Y;
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_andn_u64 (unsigned long long __X, unsigned long long __Y)
{
return __andn_u64 (__X, __Y);
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__bextr_u64 (unsigned long long __X, unsigned long long __Y)
{
return __builtin_ia32_bextr_u64 (__X, __Y);
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_bextr_u64 (unsigned long long __X, unsigned int __Y, unsigned int __Z)
{
return __builtin_ia32_bextr_u64 (__X, ((__Y & 0xff) | ((__Z & 0xff) << 8)));
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__blsi_u64 (unsigned long long __X)
{
return __X & -__X;
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_blsi_u64 (unsigned long long __X)
{
return __blsi_u64 (__X);
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__blsmsk_u64 (unsigned long long __X)
{
return __X ^ (__X - 1);
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_blsmsk_u64 (unsigned long long __X)
{
return __blsmsk_u64 (__X);
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__blsr_u64 (unsigned long long __X)
{
return __X & (__X - 1);
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_blsr_u64 (unsigned long long __X)
{
return __blsr_u64 (__X);
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__tzcnt_u64 (unsigned long long __X)
{
return __builtin_ia32_tzcnt_u64 (__X);
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_tzcnt_u64 (unsigned long long __X)
{
return __builtin_ia32_tzcnt_u64 (__X);
}
#endif
#ifdef __DISABLE_BMI__
#undef __DISABLE_BMI__
#pragma GCC pop_options
#endif
#endif
#endif
Reference in a new issue View git blame Copy permalink