C-8
COMPILER INTRINSICS AND FUNCTIONAL EQUIVALENTS
PSRLW
__m64 _m_psrlw (__m64 m, __m64 count)
__m64 _mm_srl_pi16 (__m64 m, __m64 count)
Shift four 16-bit values in m right the
amount specified by count while shifting in
zeroes.
__m64 _m_psrlwi (__m64 m, int count)
__m64 _mm_srli_pi16(__m64 m, int count)
Shift four 16-bit values in m right the
amount specified by count while shifting in
zeroes. For the best performance, count
should be a constant.
PSRLD
__m64 _m_psrld (__m64 m, __m64 count)
__m64 _mm_srl_pi32 (__m64 m, __m64 count)
Shift two 32-bit values in m right the
amount specified by count while shifting in
zeroes.
__m64 _m_psrldi (__m64 m, int count)
__m64 _mm_srli_pi32 (__m64 m, int count)
Shift two 32-bit values in m right the
amount specified by count while shifting in
zeroes. For the best performance, count
should be a constant.
PSRLQ
__m64 _m_psrlq (__m64 m, __m64 count)
__m64 _mm_srl_si64 (__m64 m, __m64 count)
Shift the 64-bit value in m right the amount
specified by count while shifting in zeroes.
__m64 _m_psrlqi (__m64 m, int count)
__m64 _mm_srli_si64 (__m64 m, int count)
Shift the 64-bit value in m right the amount
specified by count while shifting in zeroes.
For the best performance, count should be
a constant.
PSUBB
__m64 _m_psubb(__m64 m1, __m64 m2)
__m64 _mm_sub_pi8(__m64 m1, __m64 m2)
Subtract the eight 8-bit values in m2 from
the eight 8-bit values in m1.
PSUBW
__m64 _m_psubw(__m64 m1, __m64 m2)
__m64 _mm_sub_pi16(__m64 m1, __m64 m2)
Subtract the four 16-bit values in m2 from
the four 16-bit values in m1.
PSUBD
__m64 _m_psubd(__m64 m1, __m64 m2)
__m64 _mm_sub_pi32(__m64 m1, __m64 m2)
Subtract the two 32-bit values in m2 from
the two 32-bit values in m1.
PSUBSB__m64 _m_psubsb(__m64 m1, __m64 m2)
__m64 _mm_subs_pi8(__m64 m1, __m64 m2)
Subtract the eight signed 8-bit values in m2
from the eight signed 8-bit values in m1 and
saturate.
PSUBSW__m64 _m_psubsw(__m64 m1, __m64 m2)
__m64 _mm_subs_pi16(__m64 m1, __m64 m2)
Subtract the four signed 16-bit values in m2
from the four signed 16-bit values in m1
and saturate.
PSUBUSB__m64 _m_psubusb(__m64 m1, __m64 m2)
__m64 _mm_sub_pu8(__m64 m1, __m64 m2)
Subtract the eight unsigned 8-bit values in
m2 from the eight unsigned 8-bit values in
m1 and saturate.
PSUBUSW__m64 _m_psubusw(__m64 m1, __m64 m2)
__m64 _mm_sub_pu16(__m64 m1, __m64 m2)
Subtract the four unsigned 16-bit values in
m2 from the four unsigned 16-bit values in
m1 and saturate.
PUNPCKHBW__m64 _m_punpckhbw (__m64 m1, __m64 m2)
__m64 _mm_unpackhi_pi8(__m64 m1, __m64 m2)
Interleave the four 8-bit values from the
high half of m1 with the four values from the
high half of m2 and take the least
significant element from m1.
PUNPCKHWD__m64 _m_punpckhwd (__m64 m1, __m64 m2)
__m64 _mm_unpackhi_pi16(__m64 m1,__m64 m2)
Interleave the two 16-bit values from the
high half of m1 with the two values from the
high half of m2 and take the least
significant element from m1.
PUNPCKHDQ__m64 _m_punpckhdq (__m64 m1, __m64 m2)
__m64 _mm_unpackhi_pi32(__m64 m1, __m64 m2)
Interleave the 32-bit value from the high
half of m1 with the 32-bit value from the
high half of m2 and take the least
significant element from m1.
PUNPCKLBW__m64 _m_punpcklbw (__m64 m1, __m64 m2)
__m64 _mm_unpacklo_pi8 (__m64 m1, __m64 m2)
Interleave the four 8-bit values from the low
half of m1 with the four values from the low
half of m2 and take the least significant
element from m1.
Table C-1. Simple Intrinsics
Mnemonic
Intrinsic
Description
