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.
58 lines
1.8 KiB
C++
58 lines
1.8 KiB
C++
/*===------------- amxfp16intrin.h - AMX_FP16 intrinsics -*- C++ -*---------===
|
|
*
|
|
* 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
|
|
*
|
|
*===------------------------------------------------------------------------===
|
|
*/
|
|
|
|
#ifndef __IMMINTRIN_H
|
|
#error "Never use <amxfp16intrin.h> directly; use <immintrin.h> instead."
|
|
#endif /* __IMMINTRIN_H */
|
|
|
|
#ifndef __AMX_FP16INTRIN_H
|
|
#define __AMX_FP16INTRIN_H
|
|
#ifdef __x86_64__
|
|
|
|
/// Compute dot-product of FP16 (16-bit) floating-point pairs in tiles \a a
|
|
/// and \a b, accumulating the intermediate single-precision (32-bit)
|
|
/// floating-point elements with elements in \a dst, and store the 32-bit
|
|
/// result back to tile \a dst.
|
|
///
|
|
/// \headerfile <immintrin.h>
|
|
///
|
|
/// \code
|
|
/// void _tile_dpfp16ps (__tile dst, __tile a, __tile b)
|
|
/// \endcode
|
|
///
|
|
/// \code{.operation}
|
|
/// FOR m := 0 TO dst.rows - 1
|
|
/// tmp := dst.row[m]
|
|
/// FOR k := 0 TO (a.colsb / 4) - 1
|
|
/// FOR n := 0 TO (dst.colsb / 4) - 1
|
|
/// tmp.fp32[n] += FP32(a.row[m].fp16[2*k+0]) *
|
|
/// FP32(b.row[k].fp16[2*n+0])
|
|
/// tmp.fp32[n] += FP32(a.row[m].fp16[2*k+1]) *
|
|
/// FP32(b.row[k].fp16[2*n+1])
|
|
/// ENDFOR
|
|
/// ENDFOR
|
|
/// write_row_and_zero(dst, m, tmp, dst.colsb)
|
|
/// ENDFOR
|
|
/// zero_upper_rows(dst, dst.rows)
|
|
/// zero_tileconfig_start()
|
|
/// \endcode
|
|
///
|
|
/// This intrinsic corresponds to the \c TDPFP16PS instruction.
|
|
///
|
|
/// \param dst
|
|
/// The destination tile. Max size is 1024 Bytes.
|
|
/// \param a
|
|
/// The 1st source tile. Max size is 1024 Bytes.
|
|
/// \param b
|
|
/// The 2nd source tile. Max size is 1024 Bytes.
|
|
#define _tile_dpfp16ps(dst, a, b) \
|
|
__builtin_ia32_tdpfp16ps(dst, a, b)
|
|
|
|
#endif /* __x86_64__ */
|
|
#endif /* __AMX_FP16INTRIN_H */
|