mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-01-31 03:27:39 +00:00
957c61cbbf
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.
76 lines
2.8 KiB
C
76 lines
2.8 KiB
C
#if defined(__x86_64__) && !(__ASSEMBLER__ + __LINKER__ + 0)
|
|
#ifndef _PMMINTRIN_H_INCLUDED
|
|
#define _PMMINTRIN_H_INCLUDED
|
|
#include "third_party/intel/emmintrin.internal.h"
|
|
#include "third_party/intel/mwaitintrin.internal.h"
|
|
#ifndef __SSE3__
|
|
#pragma GCC push_options
|
|
#pragma GCC target("sse3")
|
|
#define __DISABLE_SSE3__
|
|
#endif
|
|
#define _MM_DENORMALS_ZERO_MASK 0x0040
|
|
#define _MM_DENORMALS_ZERO_ON 0x0040
|
|
#define _MM_DENORMALS_ZERO_OFF 0x0000
|
|
#define _MM_SET_DENORMALS_ZERO_MODE(mode) _mm_setcsr ((_mm_getcsr () & ~_MM_DENORMALS_ZERO_MASK) | (mode))
|
|
#define _MM_GET_DENORMALS_ZERO_MODE() (_mm_getcsr() & _MM_DENORMALS_ZERO_MASK)
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_addsub_ps (__m128 __X, __m128 __Y)
|
|
{
|
|
return (__m128) __builtin_ia32_addsubps ((__v4sf)__X, (__v4sf)__Y);
|
|
}
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_hadd_ps (__m128 __X, __m128 __Y)
|
|
{
|
|
return (__m128) __builtin_ia32_haddps ((__v4sf)__X, (__v4sf)__Y);
|
|
}
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_hsub_ps (__m128 __X, __m128 __Y)
|
|
{
|
|
return (__m128) __builtin_ia32_hsubps ((__v4sf)__X, (__v4sf)__Y);
|
|
}
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_movehdup_ps (__m128 __X)
|
|
{
|
|
return (__m128) __builtin_ia32_movshdup ((__v4sf)__X);
|
|
}
|
|
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_moveldup_ps (__m128 __X)
|
|
{
|
|
return (__m128) __builtin_ia32_movsldup ((__v4sf)__X);
|
|
}
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_addsub_pd (__m128d __X, __m128d __Y)
|
|
{
|
|
return (__m128d) __builtin_ia32_addsubpd ((__v2df)__X, (__v2df)__Y);
|
|
}
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_hadd_pd (__m128d __X, __m128d __Y)
|
|
{
|
|
return (__m128d) __builtin_ia32_haddpd ((__v2df)__X, (__v2df)__Y);
|
|
}
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_hsub_pd (__m128d __X, __m128d __Y)
|
|
{
|
|
return (__m128d) __builtin_ia32_hsubpd ((__v2df)__X, (__v2df)__Y);
|
|
}
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_loaddup_pd (double const *__P)
|
|
{
|
|
return _mm_load1_pd (__P);
|
|
}
|
|
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_movedup_pd (__m128d __X)
|
|
{
|
|
return _mm_shuffle_pd (__X, __X, _MM_SHUFFLE2 (0,0));
|
|
}
|
|
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
|
|
_mm_lddqu_si128 (__m128i const *__P)
|
|
{
|
|
return (__m128i) __builtin_ia32_lddqu ((char const *)__P);
|
|
}
|
|
#ifdef __DISABLE_SSE3__
|
|
#undef __DISABLE_SSE3__
|
|
#pragma GCC pop_options
|
|
#endif
|
|
#endif
|
|
#endif
|