Function Table

Function names link to MSDN
Cycle times/'X' (no benchmark) link to implementation

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_abs_epi16 pabsw SSSE3 46 7 1.6

_mm_abs_epi32 pabsd SSSE3 22.5 7 1.6

_mm_abs_epi8 pabsb SSSE3 62 7 1.6

_mm_add_epi16 paddw SSE2 X

_mm_add_epi32 paddd SSE2 X

_mm_add_epi64 paddq SSE2 X

_mm_add_epi8 paddb SSE2 X

_mm_add_pd addpd SSE2 X

_mm_add_ps addps SSE X

_mm_add_sd addsd SSE2 X

_mm_add_si64 paddq SSE2 X

_mm_add_ss addss SSE X

_mm_adds_epi16 paddsw SSE2 X

_mm_adds_epi8 paddsb SSE2 X

_mm_adds_epu16 paddusw SSE2 X

_mm_adds_epu8 paddusb SSE2 X

_mm_addsub_pd addsubpd SSE3 5.8 6 4

_mm_addsub_ps addsubps SSE3 16.2 6 4

_mm_alignr_epi8 palignr SSSE3 63 4 3.2

_mm_and_pd amdpd SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_and_ps andps SSE X

_mm_and_si128 pand SSE2 X

_mm_andnot_pd amdnpd SSE2 X

_mm_andnot_ps andnps SSE X

_mm_andnot_si128 pandn SSE2 X

_mm_avg_epu16 pavgw SSE2 X

_mm_avg_epu8 pavgb SSE2 X

_mm_avg_pu16 pavgw SSE X

_mm_avg_pu8 pavgb SSE X

_mm_blend_epi16 pblendw SSE4_1 26 6 3.2

_mm_blend_pd blendpd SSE4_1 0.9 8 3.2

_mm_blend_ps blendps SSE4_1 2.4 6 3.2

_mm_blendv_epi8 pblendvb SSE4_1 36.3 6 4.8

_mm_blendv_pd blendvpd SSE4_1 3.9 8 4.8

_mm_blendv_ps blendvps SSE4_1 6.9 8 4.8

_mm_castpd_ps (comp) SSE2 X

_mm_castpd_si128 (comp) SSE2 X

_mm_castps_pd (comp) SSE2 X

_mm_castps_si128 (comp) SSE2 X

_mm_castsi128_pd (comp) SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_castsi128_ps (comp) SSE2 X

_mm_ceil_pd roundpd SSE4_1 75.5 38 4.8

_mm_ceil_ps roundps SSE4_1 173 32 4.8

_mm_ceil_sd roundsd SSE4_1 35 35 4.8

_mm_ceil_ss roundss SSE4_1 50 40 4.8

_mm_clflush clflush SSE2 X

_mm_cmov_si128 pcmov SSE5 X

_mm_cmpeq_epi16 pcmpeqw SSE2 X

_mm_cmpeq_epi32 pcmpeqd SSE2 X

_mm_cmpeq_epi64 pcmpeqq SSE4_1 27.8 6 3.2

_mm_cmpeq_epi8 pcmpeqb SSE2 X

_mm_cmpeq_pd cmpeqpd SSE2 X

_mm_cmpeq_ps cmpeqps SSE X

_mm_cmpeq_sd cmpeqsd SSE2 X

_mm_cmpeq_ss cmpeqss SSE X

_mm_cmpestra pcmpestri SSE4_2 X

_mm_cmpestrc pcmpestr SSE4_2 X

_mm_cmpestri pcmpestri SSE4_2 X

_mm_cmpestrm pcmpestrm SSE4_2 X

_mm_cmpestro pcmpestri SSE4_2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_cmpestrs pcmpestri SSE4_2 X

_mm_cmpestrz pcmpestri SSE4_2 X

_mm_cmpge_pd cmplepd SSE2 X

_mm_cmpge_ps cmpleps SSE X

_mm_cmpge_sd cmplesd SSE2 X

_mm_cmpge_ss cmpless SSE X

_mm_cmpgt_epi16 pcmpgtw SSE2 X

_mm_cmpgt_epi32 pcmpgtd SSE2 X

_mm_cmpgt_epi64 pcmpgtq SSE4_2 X

_mm_cmpgt_epi8 pcmpgtb SSE2 X

_mm_cmpgt_pd cmpltpd SSE2 X

_mm_cmpgt_ps cmpltps SSE X

_mm_cmpgt_sd cmpltsd SSE2 X

_mm_cmpgt_ss cmpltss SSE X

_mm_cmpistra pcmpistri SSE4_2 X

_mm_cmpistrc pcmpistri SSE4_2 X

_mm_cmpistri pcmpistri SSE4_2 X

_mm_cmpistrm pcmpistri SSE4_2 X

_mm_cmpistro pcmpistri SSE4_2 X

_mm_cmpistrs pcmpistri SSE4_2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_cmpistrz pcmpistri SSE4_2 X

_mm_cmple_pd cmplepd SSE2 X

_mm_cmple_ps cmpleps SSE X

_mm_cmple_sd cmplesd SSE2 X

_mm_cmple_ss cmpless SSE X

_mm_cmplt_epi16 pcmpgtwr SSE2 X

_mm_cmplt_epi32 pcmpgtdr SSE2 X

_mm_cmplt_epi8 pcmpgtbr SSE2 X

_mm_cmplt_pd cmpltpd SSE2 X

_mm_cmplt_ps cmpltps SSE X

_mm_cmplt_sd cmpltsd SSE2 X

_mm_cmplt_ss cmpltss SSE X

_mm_cmpneq_pd cmpneqpd SSE2 X

_mm_cmpneq_ps cmpneqps SSE X

_mm_cmpneq_sd cmpneqsd SSE2 X

_mm_cmpneq_ss cmpneqss SSE X

_mm_cmpnge_pd cmpnlepd SSE2 X

_mm_cmpnge_ps cmpnleps SSE X

_mm_cmpnge_sd cmpnlesd SSE2 X

_mm_cmpnge_ss cmpnless SSE X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_cmpngt_pd cmpnltpd SSE2 X

_mm_cmpngt_ps cmpnltps SSE X

_mm_cmpngt_sd cmpnltsd SSE2 X

_mm_cmpngt_ss cmpnltss SSE X

_mm_cmpnle_pd cmpnlepd SSE2 X

_mm_cmpnle_ps cmpnleps SSE X

_mm_cmpnle_sd cmpnlesd SSE2 X

_mm_cmpnle_ss cmpnless SSE X

_mm_cmpnlt_pd cmpnltpd SSE2 X

_mm_cmpnlt_ps cmpnltps SSE X

_mm_cmpnlt_sd cmpnltsd SSE2 X

_mm_cmpnlt_ss cmpnltss SSE X

_mm_cmpord_pd cmpordpd SSE2 X

_mm_cmpord_ps cmpordps SSE X

_mm_cmpord_sd cmpordsd SSE2 X

_mm_cmpord_ss cmpordss SSE X

_mm_cmpunord_pd cmpunordpd SSE2 X

_mm_cmpunord_ps cmpunordps SSE X

_mm_cmpunord_sd cmpunordsd SSE2 X

_mm_cmpunord_ss cmpunordss SSE X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_comeq_epi16 pcomw SSE5 47 2 X

_mm_comeq_epi32 pcomd SSE5 34 2 X

_mm_comeq_epi64 pcomq SSE5 25 10 X

_mm_comeq_epi8 pcomb SSE5 59 2 X

_mm_comeq_epu16 pcomuw SSE5 47 2 X

_mm_comeq_epu32 pcomud SSE5 34 2 X

_mm_comeq_epu64 pcomuq SSE5 25 10 X

_mm_comeq_epu8 pcomub SSE5 59 2 X

_mm_comeq_pd compd SSE5 27 2 X

_mm_comeq_ps comps SSE5 24.6 2 X

_mm_comeq_sd comsd SSE5 28 2 X

_mm_comeq_ss comss SSE5 11 2 X

_mm_comfalse_epi16 pcomw SSE5 0 0 X

_mm_comfalse_epi32 pcomd SSE5 0 0 X

_mm_comfalse_epi64 pcomq SSE5 0 0 X

_mm_comfalse_epi8 pcomb SSE5 0 0 X

_mm_comfalse_epu16 pcomuw SSE5 0 0 X

_mm_comfalse_epu32 pcomud SSE5 0 0 X

_mm_comfalse_epu64 pcomuq SSE5 0 0 X

_mm_comfalse_epu8 pcomub SSE5 0 0 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_comfalse_pd compd SSE5 0 0 X

_mm_comfalse_ps comps SSE5 0 0 X

_mm_comfalse_sd comsd SSE5 21.3 4 X

_mm_comfalse_ss comss SSE5 19.5 4 X

_mm_comge_epi16 pcomw SSE5 47 8 X

_mm_comge_epi32 pcomd SSE5 34 8 X

_mm_comge_epi64 pcomq SSE5 38.5 38.5 X

_mm_comge_epi8 pcomb SSE5 59 8 X

_mm_comge_epu16 pcomuw SSE5 44 12 X

_mm_comge_epu32 pcomud SSE5 37.3 12 X

_mm_comge_epu64 pcomuq SSE5 39 39 X

_mm_comge_epu8 pcomub SSE5 67 67 X

_mm_comge_pd compd SSE5 26.8 4 X

_mm_comge_ps comps SSE5 24.8 4 X

_mm_comge_sd comsd SSE5 28 11.3 X

_mm_comge_ss comss SSE5 11.1 18.2 X

_mm_comgt_epi16 pcomw SSE5 47 2 X

_mm_comgt_epi32 pcomd SSE5 34 2 X

_mm_comgt_epi64 pcomq SSE5 38.5 38.5 X

_mm_comgt_epi8 pcomb SSE5 59 2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_comgt_epu16 pcomuw SSE5 43.7 9 X

_mm_comgt_epu32 pcomud SSE5 32.8 9 X

_mm_comgt_epu64 pcomuq SSE5 38.4 38.4 X

_mm_comgt_epu8 pcomub SSE5 64 64 X

_mm_comgt_pd compd SSE5 28.3 4 X

_mm_comgt_ps comps SSE5 23.6 4 X

_mm_comgt_sd comsd SSE5 28 11.3 X

_mm_comgt_ss comss SSE5 11.1 18.2 X

_mm_comieq_sd comisd SSE2 X

_mm_comieq_ss comiss SSE X

_mm_comige_sd comisd SSE2 X

_mm_comige_ss comiss SSE X

_mm_comigt_sd comisd SSE2 X

_mm_comigt_ss comiss SSE X

_mm_comile_sd comisd SSE2 X

_mm_comile_ss comiss SSE X

_mm_comilt_sd comisd SSE2 X

_mm_comilt_ss comiss SSE X

_mm_comineq_sd comisd SSE2 X

_mm_comineq_ss comiss SSE X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_comle_epi16 pcomw SSE5 47 8 X

_mm_comle_epi32 pcomd SSE5 34 8 X

_mm_comle_epi64 pcomq SSE5 36.5 36 X

_mm_comle_epi8 pcomb SSE5 58.4 8 X

_mm_comle_epu16 pcomuw SSE5 43.5 43.5 X

_mm_comle_epu32 pcomud SSE5 37.3 37.3 X

_mm_comle_epu64 pcomuq SSE5 36.8 36.8 X

_mm_comle_epu8 pcomub SSE5 71 71 X

_mm_comle_pd compd SSE5 26.8 2 X

_mm_comle_ps comps SSE5 28.8 2 X

_mm_comle_sd comsd SSE5 28 2 X

_mm_comle_ss comss SSE5 11.1 2 X

_mm_comlt_epi16 pcomw SSE5 47 4 X

_mm_comlt_epi32 pcomd SSE5 34 4 X

_mm_comlt_epi64 pcomq SSE5 36 36 X

_mm_comlt_epi8 pcomb SSE5 59 4 X

_mm_comlt_epu16 pcomuw SSE5 44 9 X

_mm_comlt_epu32 pcomud SSE5 32.8 9 X

_mm_comlt_epu64 pcomuq SSE5 35 35 X

_mm_comlt_epu8 pcomub SSE5 66 66 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_comlt_pd compd SSE5 27.4 2 X

_mm_comlt_ps comps SSE5 24.4 2 X

_mm_comlt_sd comsd SSE5 27 2 X

_mm_comlt_ss comss SSE5 10.6 2 X

_mm_comneq_epi16 pcomw SSE5 47 4 X

_mm_comneq_epi32 pcomd SSE5 33.9 4 X

_mm_comneq_epi64 pcomq SSE5 26.2 12 X

_mm_comneq_epi8 pcomb SSE5 59 4 X

_mm_comneq_epu16 pcomuw SSE5 47 4 X

_mm_comneq_epu32 pcomud SSE5 33.9 4 X

_mm_comneq_epu64 pcomuq SSE5 26.2 12 X

_mm_comneq_epu8 pcomub SSE5 59 4 X

_mm_comneq_pd compd SSE5 27.4 2 X

_mm_comneq_ps comps SSE5 21.3 2 X

_mm_comneq_sd comsd SSE5 25.6 2 X

_mm_comneq_ss comss SSE5 9 2 X

_mm_comnge_pd compd SSE5 27.6 4 X

_mm_comnge_ps comps SSE5 24 4 X

_mm_comnge_sd comsd SSE5 28.4 11.3 X

_mm_comnge_ss comss SSE5 11.1 18.2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_comngt_pd compd SSE5 26.9 4 X

_mm_comngt_ps comps SSE5 24.9 4 X

_mm_comngt_sd comsd SSE5 28 11.3 X

_mm_comngt_ss comss SSE5 11.1 18.2 X

_mm_comnle_pd compd SSE5 26.8 2 X

_mm_comnle_ps comps SSE5 24.8 2 X

_mm_comnle_sd comsd SSE5 28 2 X

_mm_comnle_ss comss SSE5 11.1 2 X

_mm_comnlt_pd compd SSE5 26.8 2 X

_mm_comnlt_ps comps SSE5 24 2 X

_mm_comnlt_sd comsd SSE5 28 2 X

_mm_comnlt_ss comss SSE5 11.1 2 X

_mm_comoneq_pd compd SSE5 32 9 X

_mm_comoneq_ps comps SSE5 54.5 9 X

_mm_comoneq_sd comsd SSE5 28.9 11 X

_mm_comoneq_ss comss SSE5 11.8 11 X

_mm_comord_pd compd SSE5 33.7 2 X

_mm_comord_ps comps SSE5 60 2 X

_mm_comord_sd comsd SSE5 32.6 2 X

_mm_comord_ss comss SSE5 14.4 2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_comtrue_epi16 pcomw SSE5 0 0 X

_mm_comtrue_epi32 pcomd SSE5 0 0 X

_mm_comtrue_epi64 pcomq SSE5 0 0 X

_mm_comtrue_epi8 pcomb SSE5 0 0 X

_mm_comtrue_epu16 pcomw SSE5 0 0 X

_mm_comtrue_epu32 pcomd SSE5 0 0 X

_mm_comtrue_epu64 pcomq SSE5 0 0 X

_mm_comtrue_epu8 pcomb SSE5 0 0 X

_mm_comtrue_pd pcompd SSE5 0 0 X

_mm_comtrue_ps pcomps SSE5 0 0 X

_mm_comtrue_sd pcomsd SSE5 21.3 4 X

_mm_comtrue_ss pcomss SSE5 18.5 4 X

_mm_comueq_pd pcompd SSE5 31.5 9 X

_mm_comueq_ps pcomps SSE5 57 9 X

_mm_comueq_sd pcomsd SSE5 28.9 11 X

_mm_comueq_ss pcomss SSE5 12.8 10 X

_mm_comunord_pd pcompd SSE5 33.4 4 X

_mm_comunord_ps pcomps SSE5 51 4 X

_mm_comunord_sd pcomsd SSE5 28.2 7 X

_mm_comunord_ss pcomss SSE5 10.5 6 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_crc32_u16 crc32 SSE4_2 X

_mm_crc32_u32 crc32 SSE4_2 X

_mm_crc32_u64 crc32 SSE4_2 X

_mm_crc32_u8 crc32 SSE4_2 X

_mm_cvt_si2ss cvtsi2ss SSE X

_mm_cvt_ss2si cvtss2si SSE X

_mm_cvtepi16_epi32 pmovsxwd SSE4_1 32 10 3.2

_mm_cvtepi16_epi64 pmovsxwq SSE4_1 33 12 3.2

_mm_cvtepi32_epi64 pmovsxdq SSE4_1 32 10 3.2

_mm_cvtepi32_pd cvtdq2pd SSE2 X

_mm_cvtepi32_ps cvtdq2ps SSE2 X

_mm_cvtepi8_epi16 pmovsxbw SSE4_1 56 9 3.2

_mm_cvtepi8_epi32 pmovsxbd SSE4_1 35 12 3.2

_mm_cvtepi8_epi64 pmovsxbq SSE4_1 25.5 14 3.2

_mm_cvtepu16_epi32 pmovzxwd SSE4_1 32 2 3.2

_mm_cvtepu16_epi64 pmovzxwq SSE4_1 33 4 3.2

_mm_cvtepu32_epi64 pmovzxdq SSE4_1 30 2 3.2

_mm_cvtepu8_epi16 pmovzxbw SSE4_1 56 2 3.2

_mm_cvtepu8_epi32 pmovzxbd SSE4_1 35 4 3.2

_mm_cvtepu8_epi64 pmovzxbq SSE4_1 25.5 6 3.2

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_cvtpd_epi32 cvtpd2dq SSE2 X

_mm_cvtpd_ps cvtpd2ps SSE2 X

_mm_cvtps_epi32 cvtps2dq SSE2 X

_mm_cvtps_pd cvtps2pd SSE2 X

_mm_cvtsd_f64 (comp) SSE2 X

_mm_cvtsd_si32 cvttsd2si SSE2 X

_mm_cvtsd_si64 cvtsd2si SSE2 X

_mm_cvtsd_ss cvtsd2ss SSE2 X

_mm_cvtsi128_si32 movd SSE2 X

_mm_cvtsi128_si64 movq SSE2 X

_mm_cvtsi32_sd cvtsi2sd SSE2 X

_mm_cvtsi32_si128 movd SSE2 X

_mm_cvtsi32_ss cvtsi2ss SSE X

_mm_cvtsi64_sd cvtsi2sd SSE2 X

_mm_cvtsi64_si128 movq SSE2 X

_mm_cvtsi64_ss cvtsi2ss SSE X

_mm_cvtss_f32 cvtss2si SSE X

_mm_cvtss_sd cvtss2sd SSE2 X

_mm_cvtss_si32 cvtss2si SSE X

_mm_cvtss_si64 cvtss2si SSE X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_cvtt_ss2si cvttss2si SSE X

_mm_cvttpd_epi32 cvttpd2dq SSE2 X

_mm_cvttps_epi32 cvttps2dq SSE2 X

_mm_cvttsd_si32 cvttsd2si SSE2 X

_mm_cvttsd_si64 cvttsd2si SSE2 X

_mm_cvttss_si32 cvttss2si SSE X

_mm_cvttss_si64 cvttss2si SSE X

_mm_div_pd divpd SSE2 X

_mm_div_ps divps SSE X

_mm_div_sd divsd SSE2 X

_mm_div_ss divss SSE X

_mm_dp_pd dppd SSE4_1 12.2 22.5 9

_mm_dp_ps dpps SSE4_1 78.3 28 21.5 11

_mm_extract_epi16 pextrw SSE2 X

_mm_extract_epi32 pextrd SSE4_1 1 2 1

_mm_extract_epi64 pextrq SSE4_1 4.2 14

_mm_extract_epi8 pextrb SSE4_1 1 2 1

_mm_extract_ps extractps SSE4_1 1 4.3 1

_mm_extract_si64 extrq SSE4a 38 5.8 X

_mm_extracti_si64 extrq SSE4a 34 4 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_floor_pd roundpd SSE4_1 64 38 3

_mm_floor_ps roundps SSE4_1 150 32 3

_mm_floor_sd roundsd SSE4_1 8.9 35 3

_mm_floor_ss roundss SSE4_1 17.8 40 3

_mm_frcz_pd frczpd SSE5 99 X

_mm_frcz_ps frczps SSE5 88 X

_mm_frcz_sd frczsd SSE5 67.8 X

_mm_frcz_ss frczss SSE5 55 X

_mm_getcsr stmxcsr SSE X

_mm_hadd_epi16 phaddw SSSE3 43 9 5

_mm_hadd_epi32 phaddd SSSE3 34.5 8 5.1

_mm_hadd_pd haddpd SSE3 5.8 8 4

_mm_hadd_ps haddps SSE3 15.8 8 4

_mm_haddd_epi16 phaddwd SSE5 39.3 X

_mm_haddd_epi8 phaddbd SSE5 44.7 X

_mm_haddd_epu16 phadduwd SSE5 39.3 X

_mm_haddd_epu8 phaddubd SSE5 44.7 X

_mm_haddq_epi16 phaddwq SSE5 37 X

_mm_haddq_epi32 phadddq SSE5 37 X

_mm_haddq_epi8 phaddbq SSE5 47 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_haddq_epu16 phadduwq SSE5 37 X

_mm_haddq_epu32 phaddudq SSE5 31 X

_mm_haddq_epu8 phaddubq SSE5 47 X

_mm_hadds_epi16 phaddsw SSSE3 58.1 12 5.1

_mm_haddw_epi8 phaddbw SSE5 47 X

_mm_haddw_epu8 phaddubw SSE5 47 X

_mm_hsub_epi16 phsubw SSSE3 41.5 12 5.1

_mm_hsub_epi32 phsubd SSSE3 34.5 10 5

_mm_hsub_pd hsubpd SSE3 5.6 8 4

_mm_hsub_ps hsubps SSE3 16 10 4

_mm_hsubd_epi16 phsubwd SSE5 39.3 X

_mm_hsubq_epi32 phsubdq SSE5 35.7 X

_mm_hsubs_epi16 phsubsw SSSE3 58.7 12 5

_mm_hsubw_epi8 phsubbw SSE5 47 X

_mm_insert_epi16 pinsrw SSE2 X

_mm_insert_epi32 pinsrd SSE4_1 18.5 6.5 2

_mm_insert_epi64 pinsrq SSE4_1 X X

_mm_insert_epi8 pinsrb SSE4_1 20.7 10 2

_mm_insert_ps insertps SSE4_1 2.6 2

_mm_insert_si64 insertq SSE4a 59 6 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_inserti_si64 insertq SSE4a 35 6 X

_mm_lddqu_si128 lddqu SSE3 0 0

_mm_lfence lfence SSE2 X

_mm_load_pd movapd SSE2 X

_mm_load_ps movaps SSE X

_mm_load_ps1 (comp) SSE X

_mm_load_sd movsd SSE2 X

_mm_load_si128 movdqa SSE2 X

_mm_load_ss movss SSE X

_mm_load1_pd movlpd SSE2 X

_mm_load1_ps (comp) SSE X

_mm_loaddup_pd movddup SSE3 0.6 0

_mm_loadh_pd movhpd SSE2 X

_mm_loadl_epi64 movq SSE2 X

_mm_loadl_pd (comp) SSE2 X

_mm_loadr_pd (comp) SSE2 X

_mm_loadr_ps (comp) SSE X

_mm_loadu_pd movupd SSE2 X

_mm_loadu_ps movups SSE X

_mm_loadu_si128 movdqu SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_lzcnt lzcnt SSE4a 17 X

_mm_lzcnt16 lzcnt SSE4a 15 X

_mm_lzcnt64 lzcnt SSE4a 26 X

_mm_macc_epi16 pmacsww SSE5 98 5 X

_mm_macc_epi32 pmacsdd SSE5 40 16 X

_mm_macc_pd fmaddpd SSE5 9.8 8 X

_mm_macc_ps fmaddps SSE5 20 8 X

_mm_macc_sd fmaddsd SSE5 9.5 16 X

_mm_macc_ss fmaddss SSE5 18.3 16 X

_mm_maccd_epi16 pmacswd SSE5 34 16 X

_mm_macchi_epi32 pmacssdqh SSE5 43.8 24 X

_mm_macclo_epi32 pmacsdql SSE5 34.5 22 X

_mm_maccs_epi16 pmacssww SSE5 57.5 17.5 X

_mm_maccs_epi32 pmacssdd SSE5 51 37 X

_mm_maccsd_epi16 pmacsswd SSE5 47.7 X

_mm_maccshi_epi32 pmacssdqh SSE5 53 X

_mm_maccslo_epi32 pmacssdql SSE5 47.5 X

_mm_madd_epi16 pmaddwd SSE2 X

_mm_maddd_epi16 pmadcswd SSE5 46 X

_mm_maddsd_epi16 pmadcsswd SSE5 90.6 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_maddubs_epi16 pmaddubsw SSSE3 81 12 4.8

_mm_maskmove_si64 maskmovq SSE X

_mm_maskmoveu_si128 maskmovdqu SSE2 X

_mm_max_epi16 pmaxsw SSE2 X

_mm_max_epi32 pmaxsd SSE4_1 32.3 9 1

_mm_max_epi8 pmaxsb SSE4_1 58 9 1

_mm_max_epu16 pmaxuw SSE4_1 36 13 1

_mm_max_epu32 pmaxud SSE4_1 30.3 13 1

_mm_max_epu8 pmaxub SSE2 X

_mm_max_pd maxpd SSE2 X

_mm_max_ps maxps SSE X

_mm_max_pu8 pmaxub SSE X

_mm_max_sd maxsd SSE2 X

_mm_max_ss maxss SSE X

_mm_mfence mfence SSE2 X

_mm_min_epi16 pminsw SSE2 X

_mm_min_epi32 pminsd SSE4_1 33.5 7 1

_mm_min_epi8 pminsb SSE4_1 54 7 1

_mm_min_epu16 pminuw SSE4_1 38 13 1

_mm_min_epu32 pminud SSE4_1 33.5 13 1

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_min_epu8 pminub SSE2 X

_mm_min_pd minpd SSE2 X

_mm_min_ps minps SSE X

_mm_min_pu8 pminub SSE X

_mm_min_sd minsd SSE2 X

_mm_min_ss minss SSE X

_mm_minpos_epu16 phminposuw SSE4_1 44.5 5

_mm_move_epi64 movq SSE2 X

_mm_move_sd movsd SSE2 X

_mm_move_ss movss SSE X

_mm_movedup_pd movddup SSE3 0.9 2 2

_mm_movehdup_ps movshdup SSE3 3.4 3 2

_mm_movehl_ps movhlps SSE X

_mm_moveldup_ps movsldup SSE3 2.4 3 2

_mm_movelh_ps movlhps SSE X

_mm_movemask_epi8 pmovmskb SSE2 X

_mm_movemask_pd movmskpd SSE2 X

_mm_movemask_ps movmskps SSE X

_mm_movepi64_pi64 movdq2q SSE2 X

_mm_movpi64_epi64 movq2dq SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_mpsadbw_epu8 mpsadbw SSE4_1 38.4 70 7

_mm_msub_pd fmsubpd SSE5 9.8 8 X

_mm_msub_ps fmsubps SSE5 19.7 8 X

_mm_msub_sd fmsubsd SSE5 9.5 16 X

_mm_msub_ss fmsubss SSE5 18.3 16 X

_mm_mul_epi32 pmuldq SSE4_1 26 X

_mm_mul_epu32 pmuludq SSE2 X

_mm_mul_pd mulpd SSE2 X

_mm_mul_ps mulps SSE X

_mm_mul_sd mulsd SSE2 X

_mm_mul_ss mulss SSE X

_mm_mulhi_epi16 pmulhw SSE2 X

_mm_mulhi_epu16 pmulhuw SSE2 X

_mm_mulhrs_epi16 pmulhrsw SSSE3 45 18.5 4.8

_mm_mullo_epi16 pmullw SSE2 X

_mm_mullo_epi32 pmullud SSE4_1 45 2

_mm_nmacc_pd fnmaddpd SSE5 9.4 12 X

_mm_nmacc_ps fnmaddps SSE5 20 12 X

_mm_nmacc_sd fnmaddsd SSE5 9.5 20 X

_mm_nmacc_ss fnmaddss SSE5 18.2 20 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_nmsub_pd fnmsubpd SSE5 11.8 12 X

_mm_nmsub_ps fnmsubps SSE5 22 12 X

_mm_nmsub_sd fnmsubsd SSE5 11.6 20 X

_mm_nmsub_ss fnmsubss SSE5 20.2 20 X

_mm_or_pd orpd SSE2 X

_mm_or_ps orps SSE X

_mm_or_si128 por SSE2 X

_mm_packs_epi16 packsswb SSE2 X

_mm_packs_epi32 packssdw SSE2 X

_mm_packus_epi16 packuswb SSE2 X

_mm_packus_epi32 packusdw SSE4_1 46 6 2

_mm_pause SSE2 X

_mm_perm_epi8 pperm SSE5 505.3 X

_mm_perm_pd permpd SSE5 68 X

_mm_perm_ps permps SSE5 155 X

_mm_popcnt popcnt SSE4a 5 X

_mm_popcnt_u32 popcnt SSE4_2 X

_mm_popcnt_u64 popcnt SSE4_2 X

_mm_popcnt16 popcnt SSE4a 5 X

_mm_popcnt64 popcnt SSE4a 10 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_prefetch prefetch SSE X

_mm_rcp_ps rcpps SSE X

_mm_rcp_ss rcpss SSE X

_mm_rot_epi16 protw SSE5 107 107 X

_mm_rot_epi32 protd SSE5 44 44 X

_mm_rot_epi64 protq SSE5 235 39.3 X

_mm_rot_epi8 protb SSE5 155 155 X

_mm_roti_epi16 protw SSE5 50 9.3 X

_mm_roti_epi32 protd SSE5 36 9.3 X

_mm_roti_epi64 protq SSE5 63 9.3 X

_mm_roti_epi8 protb SSE5 93 19 X

_mm_round_pd roundpd SSE4&5 115 35 6 X

_mm_round_ps roundps SSE4&5 129.5 33 6 X

_mm_round_sd roundsd SSE4&5 61 6 X

_mm_round_ss roundss SSE4&5 42 37 6 X

_mm_rsqrt_ps rsqrtps SSE X

_mm_rsqrt_ss rsqrtss SSE X

_mm_sad_epu8 psadbw SSE2 X

_mm_set_epi16 (comp) SSE2 X

_mm_set_epi32 (comp) SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_set_epi64 (comp) SSE2 X

_mm_set_epi8 (comp) SSE2 X

_mm_set_pd (comp) SSE2 X

_mm_set_ps (comp) SSE X

_mm_set_ps1 (comp) SSE X

_mm_set_sd (comp) SSE2 X

_mm_set_ss (comp) SSE X

_mm_set1_epi16 (comp) SSE2 X

_mm_set1_epi32 (comp) SSE2 X

_mm_set1_epi64 (comp) SSE2 X

_mm_set1_epi8 (comp) SSE2 X

_mm_set1_pd (comp) SSE2 X

_mm_set1_ps (comp) SSE X

_mm_setcsr ldmxcsr SSE X

_mm_setr_epi16 (comp) SSE2 X

_mm_setr_epi32 (comp) SSE2 X

_mm_setr_epi8 (comp) SSE2 X

_mm_setr_pd (comp) SSE2 X

_mm_setr_ps (comp) SSE X

_mm_setzero_pd xorpd SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_setzero_ps (comp) SSE X

_mm_setzero_si128 pxor SSE2 X

_mm_sfence sfence SSE X

_mm_sha_epi16 pshaw SSE5 47.7 99 X

_mm_sha_epi32 pshad SSE5 35 54.3 X

_mm_sha_epi64 pshaq SSE5 49 51 X

_mm_sha_epi8 pshab SSE5 92 108 X

_mm_shl_epi16 pshaw SSE5 47.7 99 X

_mm_shl_epi32 pshad SSE5 35 54.3 X

_mm_shl_epi64 pshaq SSE5 48.9 24 X

_mm_shl_epi8 pshab SSE5 92 108 X

_mm_shuffle_epi32 pshufd SSE2 X

_mm_shuffle_epi8 pshufb SSSE3 82 62 3.5

_mm_shuffle_pd shufpd SSE2 X

_mm_shuffle_ps shufps SSE X

_mm_shufflehi_epi16 pshufhw SSE2 X

_mm_shufflelo_epi16 pshuflw SSE2 X

_mm_sign_epi16 psignw SSSE3 51 3 1.6

_mm_sign_epi32 psignd SSSE3 37.6 12 1.6

_mm_sign_epi8 psignb SSSE3 89 12 1.6

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_sll_epi16 psllw SSE2 X

_mm_sll_epi32 pslld SSE2 X

_mm_sll_epi64 psllq SSE2 X

_mm_slli_epi16 psllw SSE2 X

_mm_slli_epi32 pslld SSE2 X

_mm_slli_epi64 psllq SSE2 X

_mm_slli_si128 pslldq SSE2 X

_mm_sqrt_pd sqrtpd SSE2 X

_mm_sqrt_ps sqrtps SSE X

_mm_sqrt_sd sqrtsd SSE2 X

_mm_sqrt_ss sqrtss SSE X

_mm_sra_epi16 psraw SSE2 X

_mm_sra_epi32 psrad SSE2 X

_mm_srai_epi16 psraw SSE2 X

_mm_srai_epi32 psrad SSE2 X

_mm_srl_epi16 psrlw SSE2 X

_mm_srl_epi32 psrld SSE2 X

_mm_srl_epi64 psrlq SSE2 X

_mm_srli_epi16 psrlw SSE2 X

_mm_srli_epi32 psrld SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_srli_epi64 psrlq SSE2 X

_mm_srli_si128 psrldq SSE2 X

_mm_store_pd movapd SSE2 X

_mm_store_ps movaps SSE X

_mm_store_ps1 (comp) SSE X

_mm_store_sd movsd SSE2 X

_mm_store_si128 movdqa SSE2 X

_mm_store_ss movss SSE X

_mm_store1_pd (comp) SSE2 X

_mm_store1_ps (comp) SSE X

_mm_storeh_pd movhpd SSE2 X

_mm_storel_epi64 movq SSE2 X

_mm_storel_pd movlpd SSE2 X

_mm_storer_pd (comp) SSE2 X

_mm_storer_ps (comp) SSE X

_mm_storeu_pd movupd SSE2 X

_mm_storeu_ps movups SSE X

_mm_storeu_si128 movdqu SSE2 X

_mm_stream_load_si128 movntdqa SSE4_1 X X

_mm_stream_pd movlpd SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_stream_ps movlps SSE X

_mm_stream_sd movntsd SSE4a 0.2 X

_mm_stream_si128 movntdq SSE2 X

_mm_stream_si32 movnti SSE2 X

_mm_stream_ss movntss SSE4a 0.2 X

_mm_sub_epi16 psubw SSE2 X

_mm_sub_epi32 psubd SSE2 X

_mm_sub_epi64 psubq SSE2 X

_mm_sub_epi8 psubb SSE2 X

_mm_sub_pd subpd SSE2 X

_mm_sub_ps subps SSE X

_mm_sub_sd subsd SSE2 X

_mm_sub_ss subss SSE X

_mm_subs_epi16 psubsw SSE2 X

_mm_subs_epi8 psubsb SSE2 X

_mm_subs_epu16 psubusw SSE2 X

_mm_subs_epu8 psubusb SSE2 X

_mm_testc_si128 ptest SSE4&5 7 5 1 X

_mm_testnzc_si128 ptest SSE4&5 11 5 1 X

_mm_testz_si128 ptest SSE4&5 5 5 1 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_ucomieq_sd ucomisd SSE2 X

_mm_ucomieq_ss ucomiss SSE X

_mm_ucomige_sd ucomisd SSE2 X

_mm_ucomige_ss ucomiss SSE X

_mm_ucomigt_sd ucomisd SSE2 X

_mm_ucomigt_ss ucomiss SSE X

_mm_ucomile_sd ucomisd SSE2 X

_mm_ucomile_ss ucomiss SSE X

_mm_ucomilt_sd ucomisd SSE2 X

_mm_ucomilt_ss ucomiss SSE X

_mm_ucomineq_sd ucomisd SSE2 X

_mm_ucomineq_ss ucomiss SSE X

_mm_unpackhi_epi16 punpckhwd SSE2 X

_mm_unpackhi_epi32 punpckhdq SSE2 X

_mm_unpackhi_epi64 punpckhqdq SSE2 X

_mm_unpackhi_epi8 punpckhbw SSE2 X

_mm_unpackhi_pd unpckhpd SSE2 X

_mm_unpackhi_ps unpckhps SSE X

_mm_unpacklo_epi16 punpcklwd SSE2 X

_mm_unpacklo_epi32 punpckldq SSE2 X

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

_mm_unpacklo_epi64 punpcklqdq SSE2 X

_mm_unpacklo_epi8 punpcklbw SSE2 X

_mm_unpacklo_pd unpcklpd SSE2 X

_mm_unpacklo_ps unpcklps SSE X

_mm_xor_pd xorpd SSE2 X

_mm_xor_ps xorps SSE X

_mm_xor_si128 pxor SSE2 X

ssp_arithmetic_hadd4_epi16 (comp) SSP X

ssp_arithmetic_hadd4_epu16 (comp) SSP X

ssp_number_changeSNanToQNaN_F32 (comp) SSP X

ssp_number_changeSNanToQNaN_F64 (comp) SSP X

ssp_number_isValidNumber_F32 (comp) SSP X

ssp_number_isValidNumber_F64 (comp) SSP X

ssp_round_ps_neg_zero (comp) SSP X

ssp_arithmetic_hadd4_dup_ps (comp) SSP 25.8 18 12

ssp_convert_3c_3p_epi16 (comp) SSP 90.5 39

ssp_convert_3c_3p_epi32 (comp) SSP 95 30

ssp_convert_3c_3p_epi8 (comp) SSP 129 52.5

ssp_convert_3p_3c_epi16 (comp) SSP 116 88.5

ssp_convert_3p_3c_epi32 (comp) SSP 96 49.5

Function Assembly Source REF SSE SSE2 SSE3 SSSE3 SSE4A SSE4_1 SSE4_2 SSE5

ssp_convert_3p_3c_epi8 (comp) SSP 102.5 53

ssp_convert_4c_4p_epi16 (comp) SSP 96.5 53

ssp_convert_4c_4p_epi32 (comp) SSP 92 39

ssp_convert_4c_4p_epi8 (comp) SSP 118 68

ssp_convert_4p_4c_epi16 (comp) SSP 101 39

ssp_convert_4p_4c_epi32 (comp) SSP 125 39

ssp_convert_4p_4c_epi8 (comp) SSP 122 39

ssp_convert_reverse_transpose (comp) SSP 82 29

ssp_logical_bitwise_select (comp) SSP 4

ssp_memory_load1_epu8 (comp) SSP 0 0

ssp_movmask_imm8_to_epi32 (comp) SSP 3

Generated on Wed May 21 13:44:12 2008 for "SSEPlus" by

doxygen

1.5.4