Index: cfe/trunk/lib/Headers/pmmintrin.h =================================================================== --- cfe/trunk/lib/Headers/pmmintrin.h +++ cfe/trunk/lib/Headers/pmmintrin.h @@ -27,64 +27,231 @@ #include /* Define the default attributes for the functions in this file. */ -#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("sse3"))) +#define __DEFAULT_FN_ATTRS \ + __attribute__((__always_inline__, __nodebug__, __target__("sse3"))) +/// \brief Loads data from an unaligned memory location to elements in a 128-bit +/// vector. If the address of the data is not 16-byte aligned, the +/// instruction may read two adjacent aligned blocks of memory to retrieve +/// the requested data. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VLDDQU instruction. +/// +/// \param __p +/// A pointer to a 128-bit integer vector containing integer values. +/// \returns A 128-bit vector containing the moved values. static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_lddqu_si128(__m128i const *__p) { return (__m128i)__builtin_ia32_lddqu((char const *)__p); } +/// \brief Adds the even-indexed values and subtracts the odd-indexed values of +/// two 128-bit vectors of [4 x float]. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VADDSUBPS instruction. +/// +/// \param __a +/// A 128-bit vector of [4 x float] containing the left source operand. +/// \param __b +/// A 128-bit vector of [4 x float] containing the right source operand. +/// \returns A 128-bit vector of [4 x float] containing the alternating sums and +/// differences of both operands. static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_addsub_ps(__m128 __a, __m128 __b) { return __builtin_ia32_addsubps(__a, __b); } +/// \brief Horizontally adds the adjacent pairs of values contained in two +/// 128-bit vectors of [4 x float]. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VHADDPS instruction. +/// +/// \param __a +/// A 128-bit vector of [4 x float] containing one of the source operands. +/// The horizontal sums of the values are stored in the lower bits of the +/// destination. +/// \param __b +/// A 128-bit vector of [4 x float] containing one of the source operands. +/// The horizontal sums of the values are stored in the upper bits of the +/// destination. +/// \returns A 128-bit vector of [4 x float] containing the horizontal sums of +/// both operands. static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_hadd_ps(__m128 __a, __m128 __b) { return __builtin_ia32_haddps(__a, __b); } +/// \brief Horizontally subtracts the adjacent pairs of values contained in two +/// 128-bit vectors of [4 x float]. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VHSUBPS instruction. +/// +/// \param __a +/// A 128-bit vector of [4 x float] containing one of the source operands. +/// The horizontal differences between the values are stored in the lower +/// bits of the destination. +/// \param __b +/// A 128-bit vector of [4 x float] containing one of the source operands. +/// The horizontal differences between the values are stored in the upper +/// bits of the destination. +/// \returns A 128-bit vector of [4 x float] containing the horizontal +/// differences of both operands. static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_hsub_ps(__m128 __a, __m128 __b) { return __builtin_ia32_hsubps(__a, __b); } +/// \brief Moves and duplicates high-order (odd-indexed) values from a 128-bit +/// vector of [4 x float] to float values stored in a 128-bit vector of +/// [4 x float]. +/// Bits [127:96] of the source are written to bits [127:96] and [95:64] of +/// the destination. +/// Bits [63:32] of the source are written to bits [63:32] and [31:0] of the +/// destination. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VMOVSHDUP instruction. +/// +/// \param __a +/// A 128-bit vector of [4 x float]. +/// \returns A 128-bit vector of [4 x float] containing the moved and duplicated +/// values. static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_movehdup_ps(__m128 __a) { return __builtin_shufflevector(__a, __a, 1, 1, 3, 3); } +/// \brief Duplicates low-order (even-indexed) values from a 128-bit +/// vector of [4 x float] to float values stored in a 128-bit vector of +/// [4 x float]. +/// Bits [95:64] of the source are written to bits [127:96] and [95:64] of +/// the destination. +/// Bits [31:0] of the source are written to bits [63:32] and [31:0] of the +/// destination. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VMOVSLDUP instruction. +/// +/// \param __a +/// A 128-bit vector of [4 x float]. +/// \returns A 128-bit vector of [4 x float] containing the moved and duplicated +/// values. static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_moveldup_ps(__m128 __a) { return __builtin_shufflevector(__a, __a, 0, 0, 2, 2); } +/// \brief Adds the even-indexed values and subtracts the odd-indexed values of +/// two 128-bit vectors of [2 x double]. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VADDSUBPD instruction. +/// +/// \param __a +/// A 128-bit vector of [2 x double] containing the left source operand. +/// \param __b +/// A 128-bit vector of [2 x double] containing the right source operand. +/// \returns A 128-bit vector of [2 x double] containing the alternating sums +/// and differences of both operands. static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_addsub_pd(__m128d __a, __m128d __b) { return __builtin_ia32_addsubpd(__a, __b); } +/// \brief Horizontally adds the pairs of values contained in two 128-bit +/// vectors of [2 x double]. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VHADDPD instruction. +/// +/// \param __a +/// A 128-bit vector of [2 x double] containing one of the source operands. +/// The horizontal sum of the values is stored in the lower bits of the +/// destination. +/// \param __b +/// A 128-bit vector of [2 x double] containing one of the source operands. +/// The horizontal sum of the values is stored in the upper bits of the +/// destination. +/// \returns A 128-bit vector of [2 x double] containing the horizontal sums of +/// both operands. static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_hadd_pd(__m128d __a, __m128d __b) { return __builtin_ia32_haddpd(__a, __b); } +/// \brief Horizontally subtracts the pairs of values contained in two 128-bit +/// vectors of [2 x double]. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VHSUBPD instruction. +/// +/// \param __a +/// A 128-bit vector of [2 x double] containing one of the source operands. +/// The horizontal difference of the values is stored in the lower bits of +/// the destination. +/// \param __b +/// A 128-bit vector of [2 x double] containing one of the source operands. +/// The horizontal difference of the values is stored in the upper bits of +/// the destination. +/// \returns A 128-bit vector of [2 x double] containing the horizontal +/// differences of both operands. static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_hsub_pd(__m128d __a, __m128d __b) { return __builtin_ia32_hsubpd(__a, __b); } +/// \brief Moves and duplicates one double-precision value to double-precision +/// values stored in a 128-bit vector of [2 x double]. +/// +/// \headerfile +/// +/// \code +/// __m128d _mm_loaddup_pd(double const * dp); +/// \endcode +/// +/// This intrinsic corresponds to the \c VMOVDDUP instruction. +/// +/// \param dp +/// A pointer to a double-precision value to be moved and duplicated. +/// \returns A 128-bit vector of [2 x double] containing the moved and +/// duplicated values. #define _mm_loaddup_pd(dp) _mm_load1_pd(dp) +/// \brief Moves and duplicates the double-precision value in the lower bits of +/// a 128-bit vector of [2 x double] to double-precision values stored in a +/// 128-bit vector of [2 x double]. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c VMOVDDUP instruction. +/// +/// \param __a +/// A 128-bit vector of [2 x double]. Bits [63:0] are written to bits +/// [127:64] and [63:0] of the destination. +/// \returns A 128-bit vector of [2 x double] containing the moved and +/// duplicated values. static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_movedup_pd(__m128d __a) { @@ -99,12 +266,40 @@ #define _MM_GET_DENORMALS_ZERO_MODE() (_mm_getcsr() & _MM_DENORMALS_ZERO_MASK) #define _MM_SET_DENORMALS_ZERO_MODE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_DENORMALS_ZERO_MASK) | (x))) +/// \brief Establishes a linear address memory range to be monitored and puts +/// the processor in the monitor event pending state. Data stored in the +/// monitored address range causes the processor to exit the pending state. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c MONITOR instruction. +/// +/// \param __p +/// The memory range to be monitored. The size of the range is determined by +/// CPUID function 0000_0005h. +/// \param __extensions +/// Optional extensions for the monitoring state. +/// \param __hints +/// Optional hints for the monitoring state. static __inline__ void __DEFAULT_FN_ATTRS _mm_monitor(void const *__p, unsigned __extensions, unsigned __hints) { __builtin_ia32_monitor((void *)__p, __extensions, __hints); } +/// \brief Used with the MONITOR instruction to wait while the processor is in +/// the monitor event pending state. Data stored in the monitored address +/// range causes the processor to exit the pending state. +/// +/// \headerfile +/// +/// This intrinsic corresponds to the \c MWAIT instruction. +/// +/// \param __extensions +/// Optional extensions for the monitoring state, which may vary by +/// processor. +/// \param __hints +/// Optional hints for the monitoring state, which may vary by processor. static __inline__ void __DEFAULT_FN_ATTRS _mm_mwait(unsigned __extensions, unsigned __hints) {