@nativescript/linux 0.0.0-stage → 0.1.0-alpha.0

package/framework/tools/x64/lib/clang/17/include/ammintrin.h

@@ -0,0 +1,183 @@
+/*===---- ammintrin.h - SSE4a intrinsics -----------------------------------===
+ *
+ * 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 __AMMINTRIN_H
+#define __AMMINTRIN_H
+
+#if !defined(__i386__) && !defined(__x86_64__)
+#error "This header is only meant to be used on x86 and x64 architecture"
+#endif
+
+#include <pmmintrin.h>
+
+/* Define the default attributes for the functions in this file. */
+#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("sse4a"), __min_vector_width__(128)))
+
+/// Extracts the specified bits from the lower 64 bits of the 128-bit
+///    integer vector operand at the index \a idx and of the length \a len.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128i _mm_extracti_si64(__m128i x, const int len, const int idx);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> EXTRQ </c> instruction.
+///
+/// \param x
+///    The value from which bits are extracted.
+/// \param len
+///    Bits [5:0] specify the length; the other bits are ignored. If bits [5:0]
+///    are zero, the length is interpreted as 64.
+/// \param idx
+///    Bits [5:0] specify the index of the least significant bit; the other
+///    bits are ignored. If the sum of the index and length is greater than 64,
+///    the result is undefined. If the length and index are both zero, bits
+///    [63:0] of parameter \a x are extracted. If the length is zero but the
+///    index is non-zero, the result is undefined.
+/// \returns A 128-bit integer vector whose lower 64 bits contain the bits
+///    extracted from the source operand.
+#define _mm_extracti_si64(x, len, idx) \
+  ((__m128i)__builtin_ia32_extrqi((__v2di)(__m128i)(x), \
+                                  (char)(len), (char)(idx)))
+
+/// Extracts the specified bits from the lower 64 bits of the 128-bit
+///    integer vector operand at the index and of the length specified by
+///    \a __y.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> EXTRQ </c> instruction.
+///
+/// \param __x
+///    The value from which bits are extracted.
+/// \param __y
+///    Specifies the index of the least significant bit at [13:8] and the
+///    length at [5:0]; all other bits are ignored. If bits [5:0] are zero, the
+///    length is interpreted as 64. If the sum of the index and length is
+///    greater than 64, the result is undefined. If the length and index are
+///    both zero, bits [63:0] of parameter \a __x are extracted. If the length
+///    is zero but the index is non-zero, the result is undefined.
+/// \returns A 128-bit vector whose lower 64 bits contain the bits extracted
+///    from the source operand.
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_extract_si64(__m128i __x, __m128i __y)
+{
+  return (__m128i)__builtin_ia32_extrq((__v2di)__x, (__v16qi)__y);
+}
+
+/// Inserts bits of a specified length from the source integer vector
+///    \a y into the lower 64 bits of the destination integer vector \a x at
+///    the index \a idx and of the length \a len.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128i _mm_inserti_si64(__m128i x, __m128i y, const int len,
+/// const int idx);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> INSERTQ </c> instruction.
+///
+/// \param x
+///    The destination operand where bits will be inserted. The inserted bits
+///    are defined by the length \a len and by the index \a idx specifying the
+///    least significant bit.
+/// \param y
+///    The source operand containing the bits to be extracted. The extracted
+///    bits are the least significant bits of operand \a y of length \a len.
+/// \param len
+///    Bits [5:0] specify the length; the other bits are ignored. If bits [5:0]
+///    are zero, the length is interpreted as 64.
+/// \param idx
+///    Bits [5:0] specify the index of the least significant bit; the other
+///    bits are ignored. If the sum of the index and length is greater than 64,
+///    the result is undefined. If the length and index are both zero, bits
+///    [63:0] of parameter \a y are inserted into parameter \a x. If the length
+///    is zero but the index is non-zero, the result is undefined.
+/// \returns A 128-bit integer vector containing the original lower 64-bits of
+///    destination operand \a x with the specified bitfields replaced by the
+///    lower bits of source operand \a y. The upper 64 bits of the return value
+///    are undefined.
+#define _mm_inserti_si64(x, y, len, idx) \
+  ((__m128i)__builtin_ia32_insertqi((__v2di)(__m128i)(x), \
+                                    (__v2di)(__m128i)(y), \
+                                    (char)(len), (char)(idx)))
+
+/// Inserts bits of a specified length from the source integer vector
+///    \a __y into the lower 64 bits of the destination integer vector \a __x
+///    at the index and of the length specified by \a __y.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> INSERTQ </c> instruction.
+///
+/// \param __x
+///    The destination operand where bits will be inserted. The inserted bits
+///    are defined by the length and by the index of the least significant bit
+///    specified by operand \a __y.
+/// \param __y
+///    The source operand containing the bits to be extracted. The extracted
+///    bits are the least significant bits of operand \a __y with length
+///    specified by bits [69:64]. These are inserted into the destination at the
+///    index specified by bits [77:72]; all other bits are ignored. If bits
+///    [69:64] are zero, the length is interpreted as 64. If the sum of the
+///    index and length is greater than 64, the result is undefined. If the
+///    length and index are both zero, bits [63:0] of parameter \a __y are
+///    inserted into parameter \a __x. If the length is zero but the index is
+///    non-zero, the result is undefined.
+/// \returns A 128-bit integer vector containing the original lower 64-bits of
+///    destination operand \a __x with the specified bitfields replaced by the
+///    lower bits of source operand \a __y. The upper 64 bits of the return
+///    value are undefined.
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_insert_si64(__m128i __x, __m128i __y)
+{
+  return (__m128i)__builtin_ia32_insertq((__v2di)__x, (__v2di)__y);
+}
+
+/// Stores a 64-bit double-precision value in a 64-bit memory location.
+///    To minimize caching, the data is flagged as non-temporal (unlikely to be
+///    used again soon).
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> MOVNTSD </c> instruction.
+///
+/// \param __p
+///    The 64-bit memory location used to store the register value.
+/// \param __a
+///    The 64-bit double-precision floating-point register value to be stored.
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm_stream_sd(double *__p, __m128d __a)
+{
+  __builtin_ia32_movntsd(__p, (__v2df)__a);
+}
+
+/// Stores a 32-bit single-precision floating-point value in a 32-bit
+///    memory location. To minimize caching, the data is flagged as
+///    non-temporal (unlikely to be used again soon).
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> MOVNTSS </c> instruction.
+///
+/// \param __p
+///    The 32-bit memory location used to store the register value.
+/// \param __a
+///    The 32-bit single-precision floating-point register value to be stored.
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm_stream_ss(float *__p, __m128 __a)
+{
+  __builtin_ia32_movntss(__p, (__v4sf)__a);
+}
+
+#undef __DEFAULT_FN_ATTRS
+
+#endif /* __AMMINTRIN_H */

package/framework/tools/x64/lib/clang/17/include/amxcomplexintrin.h

@@ -0,0 +1,169 @@
+/*===--------- amxcomplexintrin.h - AMXCOMPLEX 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 <amxcomplexintrin.h> directly; include <immintrin.h> instead."
+#endif // __IMMINTRIN_H
+
+#ifndef __AMX_COMPLEXINTRIN_H
+#define __AMX_COMPLEXINTRIN_H
+#ifdef __x86_64__
+
+#define __DEFAULT_FN_ATTRS_COMPLEX                                             \
+  __attribute__((__always_inline__, __nodebug__, __target__("amx-complex")))
+
+/// Perform matrix multiplication of two tiles containing complex elements and
+///    accumulate the results into a packed single precision tile. Each dword
+///    element in input tiles \a a and \a b is interpreted as a complex number
+///    with FP16 real part and FP16 imaginary part.
+/// Calculates the imaginary part of the result. For each possible combination
+///    of (row of \a a, column of \a b), it performs a set of multiplication
+///    and accumulations on all corresponding complex numbers (one from \a a
+///    and one from \a b). The imaginary part of the \a a element is multiplied
+///    with the real part of the corresponding \a b element, and the real part
+///    of the \a a element is multiplied with the imaginary part of the
+///    corresponding \a b elements. The two accumulated results are added, and
+///    then accumulated into the corresponding row and column of \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// void _tile_cmmimfp16ps(__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+1])
+///			tmp.fp32[n] += FP32(a.row[m].fp16[2*k+1]) * FP32(b.row[k].fp16[2*n+0])
+///		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 TCMMIMFP16PS 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_cmmimfp16ps(dst, a, b) __builtin_ia32_tcmmimfp16ps(dst, a, b)
+
+/// Perform matrix multiplication of two tiles containing complex elements and
+///    accumulate the results into a packed single precision tile. Each dword
+///    element in input tiles \a a and \a b is interpreted as a complex number
+///    with FP16 real part and FP16 imaginary part.
+/// Calculates the real part of the result. For each possible combination
+///    of (row of \a a, column of \a b), it performs a set of multiplication
+///    and accumulations on all corresponding complex numbers (one from \a a
+///    and one from \a b). The real part of the \a a element is multiplied
+///    with the real part of the corresponding \a b element, and the negated
+///    imaginary part of the \a a element is multiplied with the imaginary
+///    part of the corresponding \a b elements. The two accumulated results
+///    are added, and then accumulated into the corresponding row and column
+///    of \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// void _tile_cmmrlfp16ps(__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 TCMMIMFP16PS 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_cmmrlfp16ps(dst, a, b) __builtin_ia32_tcmmrlfp16ps(dst, a, b)
+
+static __inline__ _tile1024i __DEFAULT_FN_ATTRS_COMPLEX
+_tile_cmmimfp16ps_internal(unsigned short m, unsigned short n, unsigned short k,
+                           _tile1024i dst, _tile1024i src1, _tile1024i src2) {
+  return __builtin_ia32_tcmmimfp16ps_internal(m, n, k, dst, src1, src2);
+}
+
+static __inline__ _tile1024i __DEFAULT_FN_ATTRS_COMPLEX
+_tile_cmmrlfp16ps_internal(unsigned short m, unsigned short n, unsigned short k,
+                           _tile1024i dst, _tile1024i src1, _tile1024i src2) {
+  return __builtin_ia32_tcmmrlfp16ps_internal(m, n, k, dst, src1, src2);
+}
+
+/// Perform matrix multiplication of two tiles containing complex elements and
+/// accumulate the results into a packed single precision tile. Each dword
+/// element in input tiles src0 and src1 is interpreted as a complex number with
+/// FP16 real part and FP16 imaginary part.
+/// This function calculates the imaginary part of the result.
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the <c> TCMMIMFP16PS </c> instruction.
+///
+/// \param dst
+///    The destination tile. Max size is 1024 Bytes.
+/// \param src0
+///    The 1st source tile. Max size is 1024 Bytes.
+/// \param src1
+///    The 2nd source tile. Max size is 1024 Bytes.
+__DEFAULT_FN_ATTRS_COMPLEX
+static void __tile_cmmimfp16ps(__tile1024i *dst, __tile1024i src0,
+                               __tile1024i src1) {
+  dst->tile = _tile_cmmimfp16ps_internal(src0.row, src1.col, src0.col,
+                                         dst->tile, src0.tile, src1.tile);
+}
+
+/// Perform matrix multiplication of two tiles containing complex elements and
+/// accumulate the results into a packed single precision tile. Each dword
+/// element in input tiles src0 and src1 is interpreted as a complex number with
+/// FP16 real part and FP16 imaginary part.
+/// This function calculates the real part of the result.
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the <c> TCMMRLFP16PS </c> instruction.
+///
+/// \param dst
+///    The destination tile. Max size is 1024 Bytes.
+/// \param src0
+///    The 1st source tile. Max size is 1024 Bytes.
+/// \param src1
+///    The 2nd source tile. Max size is 1024 Bytes.
+__DEFAULT_FN_ATTRS_COMPLEX
+static void __tile_cmmrlfp16ps(__tile1024i *dst, __tile1024i src0,
+                               __tile1024i src1) {
+  dst->tile = _tile_cmmrlfp16ps_internal(src0.row, src1.col, src0.col,
+                                         dst->tile, src0.tile, src1.tile);
+}
+
+#endif // __x86_64__
+#endif // __AMX_COMPLEXINTRIN_H

package/framework/tools/x64/lib/clang/17/include/amxfp16intrin.h

@@ -0,0 +1,58 @@
+/*===------------- 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 */