SSE4A
[Native]

Native SSE4A Operations{
SSP_FORCEINLINE __m128i	ssp_extract_si64_SSE4A (__m128i a, __m128i b)
SSP_FORCEINLINE __m128i	ssp_extracti_si64_SSE4A (__m128i a, int len, int ndx)
SSP_FORCEINLINE __m128i	ssp_insert_si64_SSE4A (__m128i a, __m128i b)
SSP_FORCEINLINE __m128i	ssp_inserti_si64_SSE4A (__m128i a, __m128i b, int len, int ndx)
SSP_FORCEINLINE void	ssp_stream_sd_SSE4A (double *dst, __m128d src)
SSP_FORCEINLINE void	ssp_stream_ss_SSE4A (float *dst, __m128 src)
SSP_FORCEINLINE unsigned short	ssp_lzcnt16_SSE4A (unsigned short val)
SSP_FORCEINLINE unsigned int	ssp_lzcnt_SSE4A (unsigned int val)
SSP_FORCEINLINE unsigned short	ssp_popcnt16_SSE4A (unsigned short val)
SSP_FORCEINLINE unsigned int	ssp_popcnt_SSE4A (unsigned int val)

---

Function Documentation

SSP_FORCEINLINE __m128i ssp_extract_si64_SSE4A	(	__m128i	a,
		__m128i	b
	)

Native implementation of _mm_extract_si64 [SSE4a]. (Searches MSDN)

Definition at line 17 of file SSEPlus_native_SSE4a.h.

{
    return _mm_extract_si64( a, b );
}

SSP_FORCEINLINE __m128i ssp_extracti_si64_SSE4A	(	__m128i	a,
		int	len,
		int	ndx
	)

Native implementation of _mm_extracti_si64 [SSE4a]. (Searches MSDN)

Definition at line 22 of file SSEPlus_native_SSE4a.h.

{
    return _mm_extracti_si64( a, len, ndx );
}

SSP_FORCEINLINE __m128i ssp_insert_si64_SSE4A	(	__m128i	a,
		__m128i	b
	)

Native implementation of _mm_insert_si64 [SSE4a]. (Searches MSDN)

Definition at line 27 of file SSEPlus_native_SSE4a.h.

{
    return _mm_insert_si64( a, b );
}

SSP_FORCEINLINE __m128i ssp_inserti_si64_SSE4A	(	__m128i	a,
		__m128i	b,
		int	len,
		int	ndx
	)

Native implementation of _mm_inserti_si64 [SSE4a]. (Searches MSDN)

Definition at line 32 of file SSEPlus_native_SSE4a.h.

{
    return _mm_inserti_si64( a, b, len, ndx );
}

SSP_FORCEINLINE unsigned short ssp_lzcnt16_SSE4A

(

unsigned short

val

)

Native implementation of __lzcnt16 [SSE4a]. (Searches MSDN)
NOTE: Support for the LZCNT instruction is indicated by ECX bit 5 (LZCNT) as returned by CPUID function 8000_0001h. If the LZCNT instruction is not available, the encoding is treated as the BSR instruction. Software MUST check the CPUID bit once per program or library initialization before using the LZCNT instruction, or inconsistent behavior may result.

Definition at line 50 of file SSEPlus_native_SSE4a.h.

{
    return __lzcnt16( val );
}

SSP_FORCEINLINE unsigned int ssp_lzcnt_SSE4A

(

unsigned int

val

)

Native implementation of __lzcnt [SSE4a]. (Searches MSDN)
NOTE: Support for the LZCNT instruction is indicated by ECX bit 5 (LZCNT) as returned by CPUID function 8000_0001h. If the LZCNT instruction is not available, the encoding is treated as the BSR instruction. Software MUST check the CPUID bit once per program or library initialization before using the LZCNT instruction, or inconsistent behavior may result.

Definition at line 57 of file SSEPlus_native_SSE4a.h.

{
    return __lzcnt( val );
}

SSP_FORCEINLINE unsigned short ssp_popcnt16_SSE4A

(

unsigned short

val

)

Native implementation of __popcnt16 [SSE4a]. (Searches MSDN)

Definition at line 70 of file SSEPlus_native_SSE4a.h.

          {Native,__popcnt16} */ 
SSP_FORCEINLINE unsigned short ssp_popcnt16_SSE4A( unsigned short val )
{
    return __popcnt16( val );

SSP_FORCEINLINE unsigned int ssp_popcnt_SSE4A

(

unsigned int

val

)

Native implementation of __popcnt [SSE4a]. (Searches MSDN)

Definition at line 75 of file SSEPlus_native_SSE4a.h.

          {Native,__popcnt} */ 
SSP_FORCEINLINE unsigned int ssp_popcnt_SSE4A( unsigned int val )
{
    return __popcnt( val );

SSP_FORCEINLINE void ssp_stream_sd_SSE4A	(	double *	dst,
		__m128d	src
	)

Native implementation of _mm_stream_sd [SSE4a]. (Searches MSDN)

Definition at line 37 of file SSEPlus_native_SSE4a.h.

{
    _mm_stream_sd( dst, src );
}

SSP_FORCEINLINE void ssp_stream_ss_SSE4A	(	float *	dst,
		__m128	src
	)

Native implementation of _mm_stream_ss [SSE4a]. (Searches MSDN)

Definition at line 42 of file SSEPlus_native_SSE4a.h.

{
    _mm_stream_ss( dst, src );
}

---