Special x86 Intrinsics

SSSE3 Assembler Syntax and Corresponding Compiler Intrinsics

PSIGNB, PSIGNW, PSIGND
- Syntax: psignb/psignw/psignd mem64/mmxreg, mmxreg
psignb/psignw/psignd mem128/xmmxreg, xmmxreg
- Semantic: Packed Sign
- Corresponding intrinsics:
extern __m64 _mm_sign_pi8 (__m64 p1, __m64 p2);
extern __m64 _mm_sign_pi16 (__m64 p1, __m64 p2);
extern __m64 _mm_sign_pi32 (__m64 p1, __m64 p2);
extern __m128i _mm_sign_epi8 (__m128i p1, __m128i p2);
extern __m128i _mm_sign_epi16 (__m128i p1, __m128i p2);
extern __m128i _mm_sign_epi32 (__m128i p1, __m128i p2);



PABSB, PABSW, PABSD
- Syntax: pabsb/pabsw/pabsd mem64/mmxreg, mmxreg
pabsb/pabsw/pabsd mem128/xmmxreg, xmmxreg
- Semantic: Packed Absolute Value
- Corresponding intrinsics:
extern __m64 _mm_abs_pi8 (__m64 p);
extern __m64 _mm_abs_pi16 (__m64 p);
extern __m64 _mm_abs_pi32 (__m64 p);
extern __m128i _mm_abs_epi8 (__m128i p);
extern __m128i _mm_abs_epi16 (__m128i p);
extern __m128i _mm_abs_epi32 (__m128i p);



PALIGNR
- Syntax: palignr imm, mem64/mmxreg, mmxreg
palignr imm, mem128/xmmreg, xmmreg
- Semantic: Packed Align Right
- Corresponding intrinsics:
extern __m64 _mm_alignr_pi8 (__m64 p1, __m64 p2, int immd);
extern __m128i _mm_alignr_epi8 (__m128i p1, __m128i p2, int immd);



PSHUFB
- Syntax: pshufb mem64/mmxreg, mmxreg
pshufb mem128/xmmxreg, xmmxreg
- Semantic: Packed Shuffle Bytes
- Corresponding intrinsics:
extern __m64 _mm_shuffle_pi8 (__m64 p1, __m64 p2);
extern __m128i _mm_shuffle_epi8 (__m128i p1, __m128i p2);



PMULHRSW
- Syntax: pmulhrsw mem64/mmxreg, mmxreg
pmulhrsw mem128/xmmxreg, xmmxreg
- Semantic: Packed Multiply High with Round and Scale
- Corresponding intrinsics:
extern __m64 _mm_mulhrs_pi16 (__m64 p1, __m64 p2);
extern __m128i _mm_mulhrs_epi16 (__m128i p1, __m128i p2);



PMADDUBSW
- Syntax: pmaddubsw mem64/mmxreg, mmxreg
pmaddubsw mem128/xmmxreg, xmmxreg
- Semantic: Multiply and Add Packed Signed and Unsigned Bytes
- Corresponding intrinsics:
extern __m64 _mm_maddubs_pi16 (__m64 p1, __m64 p2);
extern __m128i _mm_maddubs_epi16 (__m128i p1, __m128i p2);



PHSUBW, PHSUBD
- Syntax: phsubw/phsubd mem64/mmxreg, mmxreg
phsubw/phsubd mem128/xmmxreg, xmmxreg
- Semantic: Packed Horizontal Subtract
- Corresponding intrinsics:
extern __m64 _mm_hsub_pi16 (__m64 p1, __m64 p2);
extern __m64 _mm_hsub_pi32 (__m64 p1, __m64 p2);
extern __m128i _mm_hsub_epi16 (__m128i p1, __m128i p2);
extern __m128i _mm_hsub_epi32 (__m128i p1, __m128i p2);



PHSUBSW
- Syntax: phsubsw mem64/mmxreg, mmxreg
phsubsw mem128/xmmxreg, xmmxreg
- Semantic: Packed Horizontal Subtract and Saturate Words
- Corresponding intrinsics:
extern __m64 _mm_hsubs_pi16 (__m64 p1, __m64 p2);
extern __m128i _mm_hsubs_epi16 (__m128i p1, __m128i p2);



PHADDW, PHADDD
- Syntax: phaddw/phaddd mem64/mmxreg, mmxreg
phaddw/phaddd mem128/xmmxreg, xmmxreg
- Semantic: Packed Horizontal Add
- Corresponding intrinsics:
extern __m64 _mm_hadd_pi16 (__m64 p1, __m64 p2);
extern __m64 _mm_hadd_pi32 (__m64 p1, __m64 p2);
extern __m128i _mm_hadd_epi16 (__m128i p1, __m128i p2);
extern __m128i _mm_hadd_epi32 (__m128i p1, __m128i p2);



PHADDSW
- Syntax: phaddsw mem64/mmxreg, mmxreg
phaddsw mem128/xmmxreg, xmmxreg
- Semantic: Packed Horizontal Add and Saturate Words
- Corresponding intrinsics:
extern __m64 _mm_hadds_pi16 (__m64 p1, __m64 p2);
extern __m128i _mm_hadds_epi16 (__m128i p1, __m128i p2);

SSE4.1 Assembler Syntax and Corresponding Compiler Intrinsics (Rev 1.0)

BLENDPD/BLENDPS
- Syntax: Blend packed double/single precision floating point values
blendpd/blendps $imm8, xmmreg/mem128, xmmreg
- Semantic: Copy elements from one location to another based on bits
of an immediate operand
- Corresponding intrinsics:
__m128d _mm_blend_pd(__m128d p1, __m128d p2, const int immd);
__m128 _mm_blend_ps(__m128 p1, __m128 p2, const int immd);

BLENDVPD/BLENDVPS
- Syntax: Variable blend double/single precision floating point values
blendvpd/blendvps xmmreg/mem128, xmmreg
blendvpd/blendvps XMMREG, xmmreg/mem128, xmmreg
- Semantic: Copy elements from one location to another based on bits
in register XMMREG
- Corresponding intrinsics:
__m128d _mm_blendv_pd(__m128d p1, __m128d p2, __m128d p3);
__m128 _mm_blendv_ps(__m128 p1, __m128 p2, __m128 p3);

DPPD/DPPS
- Syntax: Dot product of packed double/single precision floating
point values
dppd/dpps $imm8, xmmreg/mem128, xmmreg
- Semantic: Based on bits in the immediate operand to select which of the
entries in the input to multiply and accumulate, and to
select whether to put 0 or the dot-product in the correspondent
field of the result register
- Corresponding intrinsics:
__m128d _mm_dp_pd(__m128d p1, __m128d p2, const int immd);
__m128 _mm_dp_ps(__m128 p1, __m128 p2, const int immd);

EXTRACTPS
- Syntax: Extract packed single precision floating point value
extractps $imm8, xmmreg, reg32/mem32
extractps $imm8, xmmreg, reg64/mem64
- Semantic: Based on bits in the immediate operand to extract a field from
the source register and insert it into an x86 register or
memory address
- Corresponding intrinsics:
int _mm_extract_ps(__m128 p1, const int immd);

INSERTPS
- Syntax: Insert packed single precision floating point value
insertps $imm8, xmmreg/mem32, xmmreg
- Semantic: Load a floating point value from memory indicated by mem32
or based on bits in the immediate operand to select a single
precision floating point value from the source xmmreg and
insert it into the destination register also based on the
bits of the immediate operand
- Corresponding intrinsics:
__m128 _mm_insert_ps(__m128 p1, __m128 p2, const int immd);

MOVNTDQA
- Syntax: Load 16 bytes with non-temporal Algined Hint
movntdqa mem128, xmmreg
- Semantic: Load from write-combining memory area into xmm register
- Corresponding intrinsics:
__m128i _mm_stream_load_si128(__m128i *p);

MPSADBW
- Syntax: Calculate muliple packed sums of absolute difference
mpsadbw $imm8, xmmreg/mem128, xmmreg
- Semantic: Based on bits in the immediate operand to select the
destination and source fields to be used, compute
eight offset sums of absolute differences for
(|x0-y0|+|x1-y1|+|x2-y2|+...)
- Corresponding intrinsics:
__m128i _mm_mpsadbw_epu8(__m128i p1, __m128i p2, const int immd);

PACKUSDW
- Syntax: Pack with Unsigned Saturation
packusdw xmmreg/mem128, xmmreg
- Semantic: Convert signed 4 bytes in source and destination operands
into unsigned 2 bytes with saturation
- Corresponding intrinsics:
__m128i _mm_packus_epi32(__m128i p1, __m128i p2);

PBLENDW
- Syntax: Blend packed 16-byte words
pblendw $imm8, xmmreg/mem128, xmmreg
- Semantic: Based on bits in the immediate operand, select 16-byte
values from the second and destination operands to be
stored into the destination operand
- Corresponding intrinsics:
__m128i _mm_blend_epi16(__m128i p1, __m128i p2, const int p3);

PCMPEQQ
- Syntax: Compare packed 64-bit values for equality
pcmpeqq xmmreg/mem128, xmmreg
- Semantic: Compare packed 64-bit values in source and destination
operand for equality. Set all 0s or all 1s in destination
register as result
- Corresponding intrinsics:
__m128i _mm_cmpeq_epi64(__m128i p1, __m128i p2);

PEXTRB/PEXTRW/PEXTRD/PEXTRQ
- Syntax: Extract byte/16-bit value/32-bit value/64-bit value
pextrb $imm8, xmmreg, reg32/mem8
pextrb $imm8, xmmreg, reg64/mem8
pextrw $imm8, xmmreg, reg32/mem16
pextrw $imm8, xmmreg, reg64/mem16
pextrd $imm8, xmmreg, reg32/mem32
pextrq $imm8, xmmreg, reg64/mem64
- Semantic: Based on bits in the immediate operand to select and
extract a 8/16/32/64-bit value from the xmmreg and
store into the destination operand
- Corresponding intrinsics:
int _mm_extract_epi8(__m128i p1, const int immd);
int _mm_extract_epi16(__m128i p1, const int immd);
int _mm_extract_epi32(__m128i p1, const int immd);
long long _mm_extract_epi64(__m128i p1, const int immd);

PHMINPOSUW
- Syntax: Packed horizontal 16-bit value minimum
phminposuw xmmreg/mem128, xmmreg
- Semantic: Find the minimum unsigned 16-bit value in the source operand
and place the value and its index in the destination register
- Corresponding intrinsics:
__m128i _mm_minpos_epu16(__m128i p1);

PINSRB/PINSRD/PINSRQ
- Syntax: Insert byte, 32-bit value, 64-bit value
pinsrb $imm8, reg32/mem8, xmmreg
pinsrd $imm8, reg32/mem32, xmmreg
pinsrq $imm8, reg64/mem64, xmmreg
- Semantic: Based on the bits in the immediate operand to insert
the byte/32-bit/64-bit value from the source operand into
the destination xmm register
- Corresponding intrinsics:
__m128i _mm_insert_epi8(__m128i p1, int p2, const int immd);
__m128i _mm_insert_epi32(__m128i p1, int p2, const int immd);
__m128i _mm_insert_epi64(__m128i p1, long long p2, const int immd);

PMAXSB/PMAXSD
- Syntax: Maximum of packed signed byte/32-bit integers
pmaxsb xmmreg/mem128, xmmreg
pmaxsd xmmreg/mem128, xmmreg
- Semantic: Compare the packed signed byte/32-bit values in the 2
operands and store the maximum packed values in the destination
register
- Corresponding intrinsics:
__m128i _mm_max_epi8(__m128i p1, __m128i p2);
__m128i _mm_max_epi32(__m128i p1, __m128i p2);

PMAXUW/PMAXUD
- Syntax: Maximum of packed unsigned 16-bit/32-bit integers
pmaxuw xmmreg/mem128, xmmreg
pmaxud xmmreg/mem128, xmmreg
- Semantic: Compare the packed unsigned 16-bit/32-bit values in the
2 operands and store the maximum packed values in the
destination register
- Corresponding intrinsics:
__m128i _mm_max_epu16(__m128i p1, __m128i p2);
__m128i _mm_max_epu32(__m128i p1, __m128i p2);

PMINSB/PMINSD
- Syntax: Minimum of packed signed byte/32-bit integers
pminsb xmmreg/mem128, xmmreg
pminsd xmmreg/mem128, xmmreg
- Semantic: Compare the packed signed byte/32-bit values in the
2 operands and store the minimum packed values in the
destination register
- Corresponding intrinsics:
__m128i _mm_min_epi8(__m128i p1, __m128i p2);
__m128i _mm_min_epi32(__m128i p1, __m128i p2);

PMINUW/PMINUD
- Syntax: Minimum of packed unsigned 16-bit/32-bit integers
pminuw xmmreg/mem128, xmmreg
pminud xmmreg/mem128, xmmreg
- Semantic: Compare the packed unsigned 32-bit values in the 2 operands
and store the minimum packed values in the destination
register
- Corresponding intrinsics:
__m128i _mm_min_epu32(__m128i p1, __m128i p2);
__m128i _mm_min_epu16(__m128i p1, __m128i p2);

PMOVSXBW/PMOVSXBD/PMOVSXBQ/PMOVSXWD/PMOVSXWQ/PMOVSXDQ
- Syntax: Move packed values with sign extension
pmovsxbw xmmreg/mem64, xmmreg
pmovsxbd xmmreg/mem32, xmmreg
pmovsxbq xmmreg/mem16, xmmreg
pmovsxwd xmmreg/mem64, xmmreg
pmovsxwq xmmreg/mem32, xmmreg
pmovsxdq xmmreg/mem64, xmmreg
- Semantic: Sign extend 8/4/2 packed 8-bit values or 4/2 packed 16-bit
values or 2 packed 32-bit values in the source operand and
move it into 8/4/2 packed 16-bit/32-bit/64-bit values or
4/2 packed 32-bit/64-bit values or 2 packed 64-bit values
in the destination register respectively
- Corresponding intrinsics:
__m128i _mm_cvtepi8_epi16(__m128i p1);
__m128i _mm_cvtepi8_epi32(__m128i p1);
__m128i _mm_cvtepi8_epi64(__m128i p1);
__m128i _mm_cvtepi16_epi32(__m128i p1);
__m128i _mm_cvtepi16_epi64(__m128i p1);
__m128i _mm_cvtepi32_epi64(__m128i p1);

PMOVZXBW/PMOVZXBD/PMOVZXBQ/PMOVZXWD/PMOVZXWQ/PMOVZXDQ
- Syntax: Move packed values with zero extension
pmovzxbw xmmreg/mem64, xmmreg
pmovzxbd xmmreg/mem32, xmmreg
pmovzxbq xmmreg/mem16, xmmreg
pmovzxwd xmmreg/mem64, xmmreg
pmovzxwq xmmreg/mem32, xmmreg
pmovzxdq xmmreg/mem64, xmmreg
- Semantic: Zero extend 8/4/2 packed 8-bit values or 4/2 packed 16-bit
values or 2 packed 32-bit values in the source operand and
move it into 8/4/2 packed 16-bit/32-bit/64-bit values or
4/2 packed 32-bit/64-bit values or 2 packed 64-bit values
in the destination register respectively
- Corresponding intrinsics:
__m128i _mm_cvtepu8_epi16(__m128i p1);
__m128i _mm_cvtepu8_epi32(__m128i p1);
__m128i _mm_cvtepu8_epi64(__m128i p1);
__m128i _mm_cvtepu16_epi32(__m128i p1);
__m128i _mm_cvtepu16_epi64(__m128i p1);
__m128i _mm_cvtepu32_epi64(__m128i p1);

PMULDD/PMULDQ
- Syntax: Multiply packed signed 32-bit/64-bit integers
pmuldd xmmreg/mem128, xmmreg
pmuldq xmmreg/mem128, xmmreg
- Semantic: Multiply the packed signed 32-bit/64-bit values in the 2
operands and store the 32-bit/64-bit result in the destination
register
- Corresponding intrinsics:
__m128i _mm_mullo_epi32(__m128i p1, __m128i p2);
__m128i _mm_mul_epi32(__m128i p1, __m128i p2);

PTEST
- Syntax: Logical compare
ptest xmmreg/mem128, xmmreg
- Semantic: Set the Z flag if any of the bits in the 2 operands matched
and the C flag if all of them matched.
- Corresponding intrinsics:
int _mm_testz_si128(__m128i p1, __m128i p2);
int _mm_testc_si128(__m128i p1, __m128i p2);
int _mm_testnzc_si128(__m128i p1, __m128i p2);

ROUNDPS/ROUNDPD
- Syntax: Round packed single/double precision floating point values
roundps $imm8, xmmreg/mem128, xmmreg
roundpd $imm8, xmmreg/mem128, xmmreg
- Semantic: Based on the rounding mode in the immediate operand, round
the single/double precision packed values in the source
operand and place them in the destination register
- Corresponding intrinsics:
__m128 _mm_round_ps(__m128 p1, int immd);
__m128 _mm_floor_ps(__m128 p1);
__m128 _mm_cell_ps(__m128 p1);
__m128d _mm_round_pd(__m128d p1, int immd);
__m128d _mm_floor_pd(__m128d p1);
__m128d _mm_cell_pd(__m128d p1);

ROUNDSS/ROUNDSD
- Syntax: Round scalar single/double precision floating point values
roundss $imm8, xmmreg/mem64, xmmreg
roundsd $imm8, xmmreg/mem32, xmmreg
- Semantic: Based on the rounding mode in the immediate operand, round
the single/double precision scalar low value in the source
operand and place it in the destination register
- Corresponding intrinsics:
__m128 _mm_round_ss(__m128 p1, __m128 p2, int immd);
__m128 _mm_floor_ss(__m128 p1, __m128 p2);
__m128 _mm_cell_ss(__m128 p1, __m128 p2);
__m128d _mm_round_sd(__m128d p1, __m128d p2, int immd);
__m128d _mm_floor_sd(__m128d p1, __m128d p2);
__m128d _mm_cell_sd(__m128d p1, __m128d p2);

SSE4.2 Assembler Syntax and Corresponding Compiler Intrinsics

CRC32
- Syntax: Accumulate CRC32 value
crc32 reg8/reg16/reg32/mem8/mem16/mem32, reg32
crc32 reg8/reg64/mem8/mem64, reg64
crc32b reg8/mem8, reg32
crc32b reg8/mem8, reg64
crc32w reg16/mem16, reg32
crc32l reg32/mem32, reg32
crc32q reg64/mem64, reg64
- Semantic: Accumulate CRC32C value using the polynomial 0x11edc7f41
- Corresponding intrinsics:
unsigned int _mm_crc32_u8(unsigned int crc, unsigned char data);
unsigned int _mm_crc32_u16(unsigned int crc, unsigned short data);
unsigned int _mm_crc32_u32(unsigned int crc, unsigned int data);
unsigned long long _mm_crc32_u64(unsigned long long crc,
unsigned long long data);

PCMPESTRI
- Syntax: Packed compare explicit length strings, return index
pcmestri $imm8, xmmreg/mem128, xmmreg
- Semantic: Perform packed comparison of string data with explicit lengths,
generate an index stored to %ecx
- Corresponding intrinsics:
int _mm_cmpestri(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestra(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrc(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestro(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrs(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrz(__m128i a, int len_a, __m128i b, int len_b, const int imm);

PCMPESTRM
- Syntax: Packed compare explicit length strings, return mask
pcmestrm $imm8, xmmreg/mem128, xmmreg
- Semantic: Perform packed comparison of string data with explicit lengths,
generate a mask stored to %xmm0
- Corresponding intrinsics:
int _mm_cmpestrm(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestra(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrc(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestro(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrs(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrz(__m128i a, int len_a, __m128i b, int len_b, const int imm);

PCMISPTRI
- Syntax: Packed compare implicit length strings, return index
pcmistri $imm8, xmmreg/mem128, xmmreg
- Semantic: Perform packed comparison of string data with implicit lengths,
generate an index stored to %ecx
- Corresponding intrinsics:
int _mm_cmpistri(__m128i a, __m128i b, const int imm);
int _mm_cmpistra(__m128i a, __m128i b, const int imm);
int _mm_cmpistrc(__m128i a, __m128i b, const int imm);
int _mm_cmpistro(__m128i a, __m128i b, const int imm);
int _mm_cmpistrs(__m128i a, __m128i b, const int imm);
int _mm_cmpistrz(__m128i a, __m128i b, const int imm);

PCMPESTRM
- Syntax: Packed compare explicit length strings, return mask
pcmestrm $imm8, xmmreg/mem128, xmmreg
- Semantic: Perform packed comparison of string data with explicit lengths,
generate a mask stored to %xmm0
- Corresponding intrinsics:
int _mm_cmpestrm(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestra(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrc(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestro(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrs(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrz(__m128i a, int len_a, __m128i b, int len_b, const int imm);

PCMISPTRI
- Syntax: Packed compare implicit length strings, return index
pcmistri $imm8, xmmreg/mem128, xmmreg
- Semantic: Perform packed comparison of string data with implicit lengths,
generate an index stored to %ecx
- Corresponding intrinsics:
int _mm_cmpistri(__m128i a, __m128i b, const int imm);
int _mm_cmpistra(__m128i a, __m128i b, const int imm);
int _mm_cmpistrc(__m128i a, __m128i b, const int imm);
int _mm_cmpistro(__m128i a, __m128i b, const int imm);
int _mm_cmpistrs(__m128i a, __m128i b, const int imm);
int _mm_cmpistrz(__m128i a, __m128i b, const int imm);

PCMPESTRM
- Syntax: Packed compare explicit length strings, return mask
pcmestrm $imm8, xmmreg/mem128, xmmreg
- Semantic: Perform packed comparison of string data with explicit lengths,
generate a mask stored to %xmm0
- Corresponding intrinsics:
int _mm_cmpestrm(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestra(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrc(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestro(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrs(__m128i a, int len_a, __m128i b, int len_b, const int imm);
int _mm_cmpestrz(__m128i a, int len_a, __m128i b, int len_b, const int imm);

PCMISPTRI
- Syntax: Packed compare implicit length strings, return index
pcmistri $imm8, xmmreg/mem128, xmmreg
- Semantic: Perform packed comparison of string data with implicit lengths,
generate an index stored to %ecx
- Corresponding intrinsics:
int _mm_cmpistri(__m128i a, __m128i b, const int imm);
int _mm_cmpistra(__m128i a, __m128i b, const int imm);
int _mm_cmpistrc(__m128i a, __m128i b, const int imm);
int _mm_cmpistro(__m128i a, __m128i b, const int imm);
int _mm_cmpistrs(__m128i a, __m128i b, const int imm);
int _mm_cmpistrz(__m128i a, __m128i b, const int imm);

PCMPISTRM
- Syntax: Packed compare implicit length strings, return mask
pcmistrm $imm8, xmmreg/mem128, xmmreg
- Semantic: Perform packed comparison of string data with implicit lengths,
generate a mask stored to %xmm0
- Corresponding intrinsics:
int _mm_cmpistrm(__m128i a, __m128i b, const int imm);
int _mm_cmpistra(__m128i a, __m128i b, const int imm);
int _mm_cmpistrc(__m128i a, __m128i b, const int imm);
int _mm_cmpistro(__m128i a, __m128i b, const int imm);
int _mm_cmpistrs(__m128i a, __m128i b, const int imm);
int _mm_cmpistrz(__m128i a, __m128i b, const int imm);

PCMPGTQ
- Syntax: Compare packed data for greater than
pcmpgtq xmmreg/mem128, xmmreg
- Semantic: Compare packed 64-bit values in xmmreg/mem128 with xmmreg. Set
corresponding data in destination register to all 1s or 0s
based on the result of the greater than compare.
- Corresponding intrinsics:
__m128i _mm_cmpgt_epi64(__m128i a, __m128i b);

POPCNT
- Syntax: Population count
popcnt reg16/mem16, reg16
popcnt reg32/mem32, reg32
popcnt reg64/mem64, reg64
- Semantic: Count the number of set bits in reg/mem
- Corresponding intrinsics:
int _mm_popcnt_u32(unsigned int a);
long long _mm_popcnt_u64(unsigned long long a);