mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-01-31 11:37:35 +00:00
c9152b6f14
This change switches c++ exception handling from sjlj to standard dwarf. It's needed because clang for aarch64 doesn't support sjlj. It turns out that libunwind had a bare-metal configuration that made this easy to do. This change gets the new experimental cosmocc -mclang flag in a state of working so well that it can now be used to build all of llamafile and it goes 3x faster in terms of build latency, without trading away any perf. The int_fast16_t and int_fast32_t types are now always defined as 32-bit in the interest of having more abi consistency between cosmocc -mgcc and -mclang mode.
60 lines
2.1 KiB
C
60 lines
2.1 KiB
C
/*===---- prfchwintrin.h - PREFETCHW intrinsic -----------------------------===
|
|
*
|
|
* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
* See https://llvm.org/LICENSE.txt for license information.
|
|
* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
*
|
|
*===-----------------------------------------------------------------------===
|
|
*/
|
|
|
|
#if !defined(__X86INTRIN_H) && !defined(_MM3DNOW_H_INCLUDED)
|
|
#error "Never use <prfchwintrin.h> directly; include <x86intrin.h> instead."
|
|
#endif
|
|
|
|
#ifndef __PRFCHWINTRIN_H
|
|
#define __PRFCHWINTRIN_H
|
|
|
|
/// Loads a memory sequence containing the specified memory address into
|
|
/// all data cache levels.
|
|
///
|
|
/// The cache-coherency state is set to exclusive. Data can be read from
|
|
/// and written to the cache line without additional delay.
|
|
///
|
|
/// \headerfile <x86intrin.h>
|
|
///
|
|
/// This intrinsic corresponds to the \c PREFETCHT0 instruction.
|
|
///
|
|
/// \param __P
|
|
/// A pointer specifying the memory address to be prefetched.
|
|
static __inline__ void __attribute__((__always_inline__, __nodebug__))
|
|
_m_prefetch(void *__P)
|
|
{
|
|
__builtin_prefetch (__P, 0, 3 /* _MM_HINT_T0 */);
|
|
}
|
|
|
|
/// Loads a memory sequence containing the specified memory address into
|
|
/// the L1 data cache and sets the cache-coherency state to modified.
|
|
///
|
|
/// This provides a hint to the processor that the cache line will be
|
|
/// modified. It is intended for use when the cache line will be written to
|
|
/// shortly after the prefetch is performed.
|
|
///
|
|
/// Note that the effect of this intrinsic is dependent on the processor
|
|
/// implementation.
|
|
///
|
|
/// \headerfile <x86intrin.h>
|
|
///
|
|
/// This intrinsic corresponds to the \c PREFETCHW instruction.
|
|
///
|
|
/// \param __P
|
|
/// A pointer specifying the memory address to be prefetched.
|
|
static __inline__ void __attribute__((__always_inline__, __nodebug__))
|
|
_m_prefetchw(volatile const void *__P)
|
|
{
|
|
#pragma clang diagnostic push
|
|
#pragma clang diagnostic ignored "-Wcast-qual"
|
|
__builtin_prefetch ((const void*)__P, 1, 3 /* _MM_HINT_T0 */);
|
|
#pragma clang diagnostic pop
|
|
}
|
|
|
|
#endif /* __PRFCHWINTRIN_H */
|