ÿØÿà JFIF 

  
 
  ÿÛ „ 	 ( %"1!%)+...383,7(-.+




-+++--++++---+-+-----+---------------+---+-++7-----ÿÀ  ß â
" 

ÿÄ   

           
 ÿÄ H 
     
 !1AQaq"‘¡2B±ÁÑð#R“Ò Tbr‚²á3csƒ’ÂñDS¢³$CÿÄ 
 


            
ÿÄ %

 
       
!1AQa"23‘ÿÚ 
  ? ôÿ ¨pŸªáÿ —åYõõ\?àÒü©ŠÄï¨pŸªáÿ —åYõõ\?àÓü©ŠÄá 0Ÿªáÿ Ÿå[úƒ	ú®ði~TÁb
qÐ8OÕpÿ ƒOò¤Oè`–RÂáœá™êi€ßÉ< FtŸI“öÌ8úDf´°å}“¾œ6
öFá°y¥jñÇh†ˆ¢ã/ÃÐ:ªcÈ
"Y¡ðÑl>ÿ ”ÏËte:qž\oäŠe÷󲍷˜HT4&ÿ ÓÐü6ö®¿øþßèô	Ÿ•7Ñi’•j|“ñì>b…þS?*Óôÿ ÓÐü*h¥£ír¶ü UãSç‚Ÿ[AÐaè[ûª•õ&õj?†Éö+EzP—WeÒírJFt	‘BŒ†Ï‡%#tE Øz ¥OÛ«!1›üä±Í™%º<!vB™'èÔ6´Ña¿«e`Àà0U[-ÂБ4)M÷YK*³hï÷%ÎÎkÇ«m‘-íWŽLsã?nÂ~«†üö®þ¡ÂlÃaÿ ‰ÿ l©°Õ¥ åÜá¿r ºL[Çâ°(Çè'Vãôl8´ÏRÀvLvPõ:…ÙNçF™÷ë>Íãö]°î(–:@<‹ŒÊö×òÆt¦ãº+‡¦%ÌÁ²h´OƒJŒtMÜ>ÀÜÊw3
Y´•牋4ǍýʏTì>œú=Íwhyë,¾Ôò×õ¿ßÊa»«þˆѪQ|%6ž™A	õ%:øj<>É—ÿ Å_ˆCbõ¥š±ý¯Ýƒï…¶|RëócÍf溪“t.СøTÿ *Ä¿-{†çàczůŽ_–^XþŒ±miB[X±d 1,é”zEù»&
î9gœf™9Ð'.;—™i}!ôšåîqêÛ٤ёý£½ÆA–àôe"A$˝Úsäÿ 
÷Û	#°xŸëí(l
	 »ý3—¥5m!
rt`†0~'j2(]S¦¦kv,ÚÇl¦øJA£Šƒ
J3E8ÙiŽ:cÉžúeZ°€¯\®kÖ(79«Ž:¯X”¾³Š&¡* ….‰Ž(ÜíŸ2¥ª‡×Hi²TF¤ò[¨íÈRëÉ䢍mgÑ.Ÿ<öäS0í„ǹÁU´f#Vß;Õ–…P@3ío<ä-±»Ž.L|kªÀê›fÂ6@»eu‚|ÓaÞÆŸ…¨ááå>åŠ?cKü6ùTÍÆ”†sĤÚ;H2RÚ†õ\Ö·Ÿn'¾ ñ#ºI¤Å´%çÁ­‚â7›‹qT3Iï¨Ö
Ú5I7Ë!ÅOóŸ¶øÝñØôת¦$Tcö‘[«Ö³šÒ';Aþ ¸èíg
A2Z
"i¸vdÄ÷.iõ®§)¿]¤À†–‡É&ä{V¶iŽ”.Ó×Õÿ û?h¬Mt–íª[ÿ Ñÿ ÌV(í}=ibÔ¡›¥¢±b
 Lô¥‡piη_Z<‡z§èŒ)iÖwiÇ 2hÙ3·=’d÷8éŽ1¦¸c¤µ€7›7Ø	ð\á)}	¹fËí›pAÃL%âc2 í§æQz¿;T8sæ°qø)QFMð‰XŒÂ±
N¢aF¨…8¯!U		Z©RÊ ÖPVÄÀÍin™Ì-GˆªÅËŠ›•zË}º±ŽÍFò¹}Uw×#ä5B¤{î}Ð<ÙD
é©¤&‡ïDbàÁôMÁ."
¤‡ú*õ'VŽ|¼´Úgllº¼klz[Æüï÷Aób‡Eÿ dÑ»Xx9ÃÜ£ÁT/`¼¸vI±Ýµ·Ë‚“G³þ*Ÿû´r|*}<¨îºœ @¦mÄ’M¹”.œ«Y–|6ÏU¤jç¥ÕÞqO
˜kDÆÁ¨5ÿ š;Њ¦¦€GÙk \
	–Þ=â¼=SͧµªS°ÚÍpÜãQűÀõ¬?ÃÁ1Ñ•õZà?hóœ€
L¦l{Y*K˜Ù›zc˜–ˆâø+¾	­-Ök¥%ùEÜA'}ˆ><ÊIè“bpÍ/qÞâvoX€w,\úªò6Z[XdÒæ­@Ö—€$òJí#é>'°Ú
ôª˜<)4ryÙ£|óAÅn5žêŸyÒäMÝ2{"}‰–¤l÷ûWX\l¾Á¸góÉOÔ /óñB¤f¸çñ[.P˜ZsÊË*ßT܈§QN¢’¡¨§V¼(Üù*eÕ“”5T¨‹Âê¥FŒã½Dü[8'Ò¥a…Ú¶k7a
*•›¼'Ò·\8¨ª\@\õ¢¦íq+DÙrmÎ…_ªæ»ŠÓœ¡¯’Ré9MÅ×D™lælffc+ŒÑ,ý™ÿ ¯þǤ=Å’Á7µ÷ÚÛ/“Ü
€ñýã¼àí¾ÕÑ+ƒ,uµMâÀÄbm:ÒÎPæ{˜Gz[ƒ¯«® KHà`ßØŠéí¯P8Aq.C‰ à€kòpj´kN¶qô€…Õ,ÜNŠª-­{Zö’æû44‰sŽè‰îVíRœÕm"
6?³D9¡ÇTíÅꋇ`4«¸ÝÁô ï’ýorqКÇZ«x4Žâéþuïf¹µö[P ,Q£éaX±`PÉÍZ ¸äYúgüAx
’6Lê‚xÝÓ*äQ
Ï’¨hÍ
=²,6ï#rÃ<¯–£»ƒ‹,–ê•€ aÛsñ'%Æ"®ÛüìBᝠHÚ3ß°©$“XnœÖ’î2ËTeûìxîß
¦å¿çÉ
ðK§þ{‘t‚Ϋ¬jéîZ[”š7L¥4VÚCE×]m¤Øy”ä4-dz£œ§¸x.*ã
ÊÊ b÷•h:©‡¦s`BTÁRû¾g⻩‹jø sF¢àJøFl‘È•Xᓁà~*j¯ +(ÚÕ6-£¯÷GŠØy‚<Ç’.F‹Hœw(+)ÜÜâÈzÄäT§FߘãÏ;DmVœ3Àu@mÚüXÝü•3B¨òÌÁÛ<·ÃÜz,Ì@õÅ·d2]ü8s÷IôÞ¯^Ç9¢u„~ëAŸï4«M?
K]­ÅàPl@s_ p:°¬ZR”´›JC[CS.h‹ƒïËœ«Æ]–÷ó‚wR×k7X‰k›‘´ù¦=¡«‰¨¨Â')—71ó’c‡Ðúµ
`é.{§p¹ój\Ž{1h{o±Ý=áUÊïGÖŒõ–-BÄm+AZX¶¡
ïHðæ¥JmÙ;…ä¡Ÿˆ¦ ° äšiÉg«$üMk5¤L“’çÊvïâï	,=f“"íἊ5ô¬x6{ɏžID0e¸vçmi'︧ºð9$ò¹÷*£’9ÿ ²TÔ…×>JV¥}Œ}$p[bÔ®*[jzS*8
”·T›Í–ñUîƒwo$áè=LT™ç—~ô·¤ÈÚ$榍q‰„+´kFm)ž‹©i–ËqÞŠ‰à¶ü( ‚•§ •°ò·‡#5ª•µÊ﯅¡X¨šÁ*F#TXJÊ
ušJVÍ&=iÄs1‚3•'fý§5Ñ<=[íÞ­
PÚ;ѱÌ_~Ä££8rÞ
²w;’hDT°>ÈG¬8Á²ÚzŽ®ò®qZcqJêäÞ-ö[ܘbň±çb“Š¶31²n×iƒðÕ;1¶þÉ
ªX‰,ßqÏ$>•î íZ¥Z 1{ç൵+ƒÕµ¥°T$§K]á»Ûï*·¤tMI’ÂZbŽÕiÒ˜}bÓ0£ª5›¨[5Ž^ÝœWøÂÝh°
¢OWun£¤5 a2Z.G2³YL]jåtì”
ä	ÁÓ‘%"©<ÔúÊ°sº UZvä‡ÄiÆÒM .÷V·™ø#kèýií<NçŽôª¦„lË»{ƒ®<
[¦Y‹éƒ}j•*‚±€I‡e&gbéšp9å^!®€ö?ù^àTzo@Q¨Aêœ& [”…üÔ}пF’Hq‚©´{“ëH·?.½%úå»É Á´9¿¼Ò‰Á¼Ì¥Ús¼zW¶aÃhwÖ…ÑÏ$mò´ë:×Ñγ|”x§
µ0Âз$·aÆn µ†šÇ³£‰Ì®ž
õ@kŽ«gtí䢩ÒP×5¤?µÿ m´Ì^ ‡8¸Á8‹”žÆWÑ ¡™„,Ì“»à‹ÃéV¸®á›ÐÇŽBÀ®Ã…Z”ØÛë8;é|Ñ5)7aÕ&2Ù¸÷©ö—Ð;‡¬7"¿"7M·d
ñœÒÌf5”ê ;"Ãp5¯¬3‹ùJÚÝG›½&¯<{òñKÎÖ“3:¦ÀòGPÅS¨;
à‘Ün´öpð±W)z'¬öÀÖ#Xf2& æ
Œ‹é¾"‹\!Ñ9…
0±2A›*ØMÄ $X
끫ØXÖ,X¥ ô'ËnFÍãlqJXçuaJ4¦„ëµ7ê;h"Zã¾Áä£,vÛ‹’N©E(Öu÷)…ÁaÜÇÔkˆ$‘1kmG¨øtÛ>Ì–ª)µT[)BˆõÑ
xB¾B€ÖT¨.¥~ð@VĶr#¸ü*åZNDŽH;âi 
],©£öØpù(šºãö¼T.uCê•4@ÿ GÕÛ)Cx›®0ø#:ÏðFÒbR\(€€Ä
®fã4Þ‰Fä¯HXƒÅ,†öEÑÔÜ]Öv²?tLÃvBY£ú6Êu5ÅAQ³1‘’¬x–HŒÐ‡ ^	¸KwJôÖŽ5×CÚ¨vÜ«/B0$×k°=ðbÇ(Ï)w±A†Á†	11Í=èQšµ626ŒÜ/`G«µ<}—-Ö7KEHÈÉðóȤmݱû±·ø«Snmá=“ä«šmݱŸ¡¶~ó·“äUóJæúòB|E LêŽy´jDÔ$G¢þÐñ7óR8ýÒ…Ç›	WVe#·Ÿ	p·Fx~•ݤF÷0Èÿ K¯æS<6’¡WШ
;´ÿ ¥Êø\Òuî†åÝ–VNœkÒ7oòX¨Á­Ø÷FÎÑä±g÷ÿ M~Çî=p,X´
ÝÌÚÅ‹
’ÃjÖ.ØöÏñ
qïQ¤ÓZE†° =6·]܈ s¸>v•Ž^Ý\wq9r‰Î\¸¡kURÒ$­*‹Nq?Þª*!sŠÆ:TU_u±T+øX¡
®¹¡,ÄâÃBTsÜ$Ø›4m椴zÜK]’’›Pƒ@€#â˜`é¹=I‡fiV•Ôî“nRm+µFPOhÍ0B£
€+¬5c
v•:P'ÒyÎ ‰V~‚Ó†ÖuókDoh$å\*ö%Ю=£«…aȼ½÷Û.-½VŒŠ¼'lyî±1¬3ó#ÞE¿ÔS¤gV£m›<HqÚ,sVºóÆß¼Hïô…¹…Méi‡Ò" µùEîØÏj|ÓøVOuœ"f’aÞÞëx…˜ÌO`dHHš×4K*H$‡5×
ÚÄ
Â×CUÅAŠŒsr»2°ÄÁiÚ±Çéõe•¶_SÕÆÃ3ˆ•-3´‘¸¡‡cgDîÚ¦ÃcX}'êûJè½9ñìÓ­ä±	×ÓûçÁmO”üVÞ¸÷¥ I~“ÒôhhûýÑwxlïZ¹G¡4ž=”)º£ò
®vÆŽ%UqÝ4qž©­hûÎí‡š§é1R±cÜèðà y' °ôy¦£q§Ýï¬;šÖõ„Sÿ ›  z('S†$Ï}*evÚ¾Kýº8ý
¨å	jÛ]´-‚6«¶ÖK+8ÊiS45jrœèËQDüDØ]R”˜SPÃ
xJÕl>
=§\û"—WU¤ÚǼÿ ÂnÁ
GŒÃ
‚õN	D³õNÚíŒÕ;HôyÄÈ©P¹Ä{:?R‘Ô¨âF÷ø£bÅó® JS|‚R÷ivýáâ€Æé¡è³´IئÑT!§˜•Øª‚¬â@q€wnïCWÄ@JU€ê¯m6]Ï:£âx
'+ÒðXvÓ¦Úm=–´7œ $ì“B£~p%ÕŸUþ« N@¼üï~w˜ñø5®—'Ôe»¤5ã//€ž~‰Tþ›Å7•#¤×Íö
pÄ$ùeåì*«ÓŠEØWEÈsßg¦ûvžSsLpºÊW–âµEWöˬH;™!CYõZÃÄf æ#1W.
\uWâ\,\Çfj’<qTbên›Î[vxx£ë 'ö¨1›˜ÀM¼Pÿ H)ƒêêŒA7s,|F“꺸k³9Ìö*ç®;Ö!Ö$Eiž•¹ÒÚ†ýóéÝû¾ÕS®ó$’NÝäŸz¤5r¦ãÄÃD÷Üø!°ø‡Ô&@m™Ì^Ãä­d	q5Lnÿ N;.6½·N|#ä"1Nƒx“ã<3('&ñß
t  ~ªu”1Tb㫨9ê–›–bìd$ߣ=#ÕãÒmU¯eí$EFù5ýYô櫨æ왍Ǘ±ssM]·á¿
0ÕåJRÓªîiƒ+O58ÖñªŠÒx"	\µâá¨i’¤i
—Ö
”
M+M¤ë9‚‰A¦°Qõ¾ßøK~¼Ã‘g…Ö´~÷Ï[3GUœÒ½#…kàÔ®Ò”‰³·dWV‰IP‰Ú8u¹”E
ÖqLj¾êÕCBš{A^Âß;–¨`¯¬ìö
˼	×tìø.tƐm*n¨y4o&Àx¥n¦×î‡aupáÛj8¿m›è¶ã!o½;ß0y^ý×^EÑ¿ÒjzŒ­)vÚÑnÄL
…^ªô× ‡—‚3k	Îý­hï]içå–îÏ*÷ñþ»Ô
CÒjøjÍznˆ´
¹#b'Fô‹
‰v¥'’à'T´ƒHýÍ%M‰ ƒ&ÆÇŒï1 ‘	–Þ
‰i¬s žR-Ÿ kŠ¬á¬7:þ 0ŒÅÒÕ/aÙ¬ÃÝ#Úøœ
©aiVc‰. ¹¦ãµ”
›Yg¦›ÆÎýº°f³7ƒhá·¸­}&D9¡ÂsÉÙÞèŠõØàC™¨ñbFC|´Ü(ŸƒÚÒ-%»'a	Ì¿)ËÇn¿úÿ ÞŽX…4ÊÅH^ôΑí@ù¹Eh¶“L8Çjù
¼ÎåVªóR©Ï5uÃ
V4lZß®=€xÖŸ–ÑÈ
÷”¨°¾__yM1tÉ?uÆþIkÄgæ@þ[¢†°XÃJ£j·:nkÅ¢u‘}âGzö­/IµèŠ¬¼48q¦F°ŽR¼=ûì{´¯RýicS
ÕÛ íNtÍÙï£,w4rêì®»~x(©Uñ§#Ñ&œÕ¤>ÎåÍÓ9’Ö{9eV­[Öjâ²ãu]˜å2›qÑšÕJç0€sÄ|Êëè0튔bÁ>“{×_F`Ø©ºê:µä,v¤ðfc1±"«ÔÍän1#=·
Âøv~H<Q-Ìk7Æ;•L´©ÙC°.7
¯hKL@ävÊâž$´4¸ð‚¦­R–ÂZ7ÕÃj±·¿rÓrªJ_PÕ.#g¤gÀ)©`ª<KžèÝ'ä©èÒ3rwû€Ø¦ÒƒLf¤
,¿I½{Ƕ8‘$KÝU/Oi>½ÐßA¾¿Ü€Óš]Õ; I¾÷ç‚Qi†î¹9ywÔKG˜áñ zQY—§ÃÕZ07§X‚Áh;ÁM)iÌCH-¯T‘ë|A0{Ò½LÚ–TâÖkÜ’dÀ“rmm»”جPF³ÖcbE§T€ÒxKºû’Ó®7±²(\4ŽÃ¸Uu@j™yĵ;³µ!Á¢b.W¤=mõ´êµKk
¸K^ÜÛ#p*Ü14qkZç5ïë†°5Ï%ÍÛ<Õ¤×Ô¥ê†C	Õ´¼ú$ƒÖ“”]Ù¬qÞÚ[4©ý!ûÏ—Áb쳐XµA¬â~`›Çr¸8ìùÝ䫦<>ä÷«?xs´ÇÑ	/á;¹øüÊÈÙà{"@Žïzâ¬[âß‚ U_<ÇŸ½4èN˜ú61®qŠu ¦þF£»äJ_ˆÙÎ~ ÞAã–Ý„Ï—rŠD;xTž‘ô`É«…suãO`?³à™ô
Lý#Íc5öoæØ‚y´´÷«ZR§<&JÇ+éâô´€i!Àˆ0æAoàðLèÖ-2ŸõW.’t^–(KÁmHµV@xÜÇy®Ñø­â^:Ú3w· 7½¹°ñ¸â¹®:',«Mœ—n­Á+Ãbš
LÈ‘ÄnRÓÅœ%¦²‰¨ùQ:¤f‚ "PÕtô¸…cæl…&˜Ú˜Ôkv‹ž+vŠ,=¢v­6—X
y*¥t£«<™:“aï<QÝ&Ó]i4音äzçáíHÚÕxcòãæäÝÔm퐡 `Â)C×ehÀdHP6ÅMEöZ®Í¨	é¾Tr뢘6*¶;´sÙì]ÊŽŽÛíÉwRÈ´up* Ã	‚m´:Û{·”MUë©õ̤êÔo7:ŽÕ
qÏ'E ˆk^uãT€$Ú$Æ{•ŸBP°al¾Ž©ŒÃ^}äA
,º­$Ü]ºÚ.í:‹¤ÜöXnno7X€¥BÂà ±1ã>Œºîϲ=¦6rO]XI¿Œ÷¤zÚ­›¶ 6÷”w\dü~v®ˆÌk«^m<ÿ ¢‰Õ\)ùºŽ;… lîÙÅEŠ®cѾ@vnMÏ,¼“
ñ•ŽBxðÃzãÇç%3ˆ"}Ù•Åî>
BÉú;Ò]V+P˜F_´ßé>
Øše|ï‡ÄOmFæÇ ãqÞ$/xÐx­z`ï9"œÜij‚!7.\Td…9M‡•iŽ‹¾‘50ÞŽn¥ß4ÉôO¹*í^QêËÜÇÌ8=Ž
§s‰'ÂëÙ«á%Pú[O
†ÅP¯VsŽ°.‰,kc¶ ¬A9n˜XÎ-ÞšN["¹QÕ‰ƒMýÁߺXJæÍaLj¾×Ãmã¾ãÚ uñÒþåQô¦¥
/ÄUx:‚ÍÜ’ Đ©ØÝ3V¨‰ÕnÐ6ó*óúK­«…c ¯U òhsý­jóÔj#,ímŒRµ«lbïUTŒÑ8†Ä0œÏr`ð¡¬É	Ї
ë"À²

™	6¥ f¶¢ÚoܱԷ-<Àî)†a¶ž'Ú»¨TXqØæ¶÷Y
ÄHy˜9ÈIW­YÀuMFë
ºÏ’AqÌ4·/Ú
†ô'i$øä­=Ä
Ý|öK×40è|È6p‘0§)o¥ctî§H+CA-“ xØ|ÐXŠç
l8íºð3Ø:³¤¬KX¯UÿÙ
/* Copyright (C) 2003-2019 Free Software Foundation, Inc.

   This file is part of GCC.

   GCC is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 3, or (at your option)
   any later version.

   GCC is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   Under Section 7 of GPL version 3, you are granted additional
   permissions described in the GCC Runtime Library Exception, version
   3.1, as published by the Free Software Foundation.

   You should have received a copy of the GNU General Public License and
   a copy of the GCC Runtime Library Exception along with this program;
   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
   <http://www.gnu.org/licenses/>.  */

/* Implemented from the specification included in the Intel C++ Compiler
   User Guide and Reference, version 9.0.  */

#ifndef _EMMINTRIN_H_INCLUDED
#define _EMMINTRIN_H_INCLUDED

/* We need definitions from the SSE header files*/
#include <xmmintrin.h>

#ifndef __SSE2__
#pragma GCC push_options
#pragma GCC target("sse2")
#define __DISABLE_SSE2__
#endif /* __SSE2__ */

/* SSE2 */
typedef double __v2df __attribute__ ((__vector_size__ (16)));
typedef long long __v2di __attribute__ ((__vector_size__ (16)));
typedef unsigned long long __v2du __attribute__ ((__vector_size__ (16)));
typedef int __v4si __attribute__ ((__vector_size__ (16)));
typedef unsigned int __v4su __attribute__ ((__vector_size__ (16)));
typedef short __v8hi __attribute__ ((__vector_size__ (16)));
typedef unsigned short __v8hu __attribute__ ((__vector_size__ (16)));
typedef char __v16qi __attribute__ ((__vector_size__ (16)));
typedef signed char __v16qs __attribute__ ((__vector_size__ (16)));
typedef unsigned char __v16qu __attribute__ ((__vector_size__ (16)));

/* The Intel API is flexible enough that we must allow aliasing with other
   vector types, and their scalar components.  */
typedef long long __m128i __attribute__ ((__vector_size__ (16), __may_alias__));
typedef double __m128d __attribute__ ((__vector_size__ (16), __may_alias__));

/* Unaligned version of the same types.  */
typedef long long __m128i_u __attribute__ ((__vector_size__ (16), __may_alias__, __aligned__ (1)));
typedef double __m128d_u __attribute__ ((__vector_size__ (16), __may_alias__, __aligned__ (1)));

/* Create a selector for use with the SHUFPD instruction.  */
#define _MM_SHUFFLE2(fp1,fp0) \
 (((fp1) << 1) | (fp0))

/* Create a vector with element 0 as F and the rest zero.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_sd (double __F)
{
  return __extension__ (__m128d){ __F, 0.0 };
}

/* Create a vector with both elements equal to F.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_pd (double __F)
{
  return __extension__ (__m128d){ __F, __F };
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pd1 (double __F)
{
  return _mm_set1_pd (__F);
}

/* Create a vector with the lower value X and upper value W.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pd (double __W, double __X)
{
  return __extension__ (__m128d){ __X, __W };
}

/* Create a vector with the lower value W and upper value X.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_pd (double __W, double __X)
{
  return __extension__ (__m128d){ __W, __X };
}

/* Create an undefined vector.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_undefined_pd (void)
{
  __m128d __Y = __Y;
  return __Y;
}

/* Create a vector of zeros.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setzero_pd (void)
{
  return __extension__ (__m128d){ 0.0, 0.0 };
}

/* Sets the low DPFP value of A from the low value of B.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_move_sd (__m128d __A, __m128d __B)
{
  return __extension__ (__m128d) __builtin_shuffle ((__v2df)__A, (__v2df)__B, (__v2di){2, 1});
}

/* Load two DPFP values from P.  The address must be 16-byte aligned.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_load_pd (double const *__P)
{
  return *(__m128d *)__P;
}

/* Load two DPFP values from P.  The address need not be 16-byte aligned.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_loadu_pd (double const *__P)
{
  return *(__m128d_u *)__P;
}

/* Create a vector with all two elements equal to *P.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_load1_pd (double const *__P)
{
  return _mm_set1_pd (*__P);
}

/* Create a vector with element 0 as *P and the rest zero.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_load_sd (double const *__P)
{
  return _mm_set_sd (*__P);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_load_pd1 (double const *__P)
{
  return _mm_load1_pd (__P);
}

/* Load two DPFP values in reverse order.  The address must be aligned.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_loadr_pd (double const *__P)
{
  __m128d __tmp = _mm_load_pd (__P);
  return __builtin_ia32_shufpd (__tmp, __tmp, _MM_SHUFFLE2 (0,1));
}

/* Store two DPFP values.  The address must be 16-byte aligned.  */
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_store_pd (double *__P, __m128d __A)
{
  *(__m128d *)__P = __A;
}

/* Store two DPFP values.  The address need not be 16-byte aligned.  */
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_storeu_pd (double *__P, __m128d __A)
{
  *(__m128d_u *)__P = __A;
}

/* Stores the lower DPFP value.  */
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_store_sd (double *__P, __m128d __A)
{
  *__P = ((__v2df)__A)[0];
}

extern __inline double __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsd_f64 (__m128d __A)
{
  return ((__v2df)__A)[0];
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_storel_pd (double *__P, __m128d __A)
{
  _mm_store_sd (__P, __A);
}

/* Stores the upper DPFP value.  */
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_storeh_pd (double *__P, __m128d __A)
{
  *__P = ((__v2df)__A)[1];
}

/* Store the lower DPFP value across two words.
   The address must be 16-byte aligned.  */
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_store1_pd (double *__P, __m128d __A)
{
  _mm_store_pd (__P, __builtin_ia32_shufpd (__A, __A, _MM_SHUFFLE2 (0,0)));
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_store_pd1 (double *__P, __m128d __A)
{
  _mm_store1_pd (__P, __A);
}

/* Store two DPFP values in reverse order.  The address must be aligned.  */
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_storer_pd (double *__P, __m128d __A)
{
  _mm_store_pd (__P, __builtin_ia32_shufpd (__A, __A, _MM_SHUFFLE2 (0,1)));
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi128_si32 (__m128i __A)
{
  return __builtin_ia32_vec_ext_v4si ((__v4si)__A, 0);
}

#ifdef __x86_64__
/* Intel intrinsic.  */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi128_si64 (__m128i __A)
{
  return ((__v2di)__A)[0];
}

/* Microsoft intrinsic.  */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi128_si64x (__m128i __A)
{
  return ((__v2di)__A)[0];
}
#endif

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_pd (__m128d __A, __m128d __B)
{
  return (__m128d) ((__v2df)__A + (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_addsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_pd (__m128d __A, __m128d __B)
{
  return (__m128d) ((__v2df)__A - (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_subsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mul_pd (__m128d __A, __m128d __B)
{
  return (__m128d) ((__v2df)__A * (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mul_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_mulsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_div_pd (__m128d __A, __m128d __B)
{
  return (__m128d) ((__v2df)__A / (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_div_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_divsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sqrt_pd (__m128d __A)
{
  return (__m128d)__builtin_ia32_sqrtpd ((__v2df)__A);
}

/* Return pair {sqrt (B[0]), A[1]}.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sqrt_sd (__m128d __A, __m128d __B)
{
  __v2df __tmp = __builtin_ia32_movsd ((__v2df)__A, (__v2df)__B);
  return (__m128d)__builtin_ia32_sqrtsd ((__v2df)__tmp);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_minpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_minsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_maxpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_maxsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_and_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_andpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_andnot_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_andnpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_or_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_orpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_xor_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_xorpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpeqpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmplt_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpltpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmple_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmplepd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpgtpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpge_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpgepd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpneq_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpneqpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpnlt_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpnltpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpnle_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpnlepd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpngt_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpngtpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpnge_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpngepd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpord_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpordpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpunord_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpunordpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpeqsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmplt_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpltsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmple_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmplesd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_sd (__m128d __A, __m128d __B)
{
  return (__m128d) __builtin_ia32_movsd ((__v2df) __A,
					 (__v2df)
					 __builtin_ia32_cmpltsd ((__v2df) __B,
								 (__v2df)
								 __A));
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpge_sd (__m128d __A, __m128d __B)
{
  return (__m128d) __builtin_ia32_movsd ((__v2df) __A,
					 (__v2df)
					 __builtin_ia32_cmplesd ((__v2df) __B,
								 (__v2df)
								 __A));
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpneq_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpneqsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpnlt_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpnltsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpnle_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpnlesd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpngt_sd (__m128d __A, __m128d __B)
{
  return (__m128d) __builtin_ia32_movsd ((__v2df) __A,
					 (__v2df)
					 __builtin_ia32_cmpnltsd ((__v2df) __B,
								  (__v2df)
								  __A));
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpnge_sd (__m128d __A, __m128d __B)
{
  return (__m128d) __builtin_ia32_movsd ((__v2df) __A,
					 (__v2df)
					 __builtin_ia32_cmpnlesd ((__v2df) __B,
								  (__v2df)
								  __A));
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpord_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpordsd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpunord_sd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_cmpunordsd ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_comieq_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_comisdeq ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_comilt_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_comisdlt ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_comile_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_comisdle ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_comigt_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_comisdgt ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_comige_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_comisdge ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_comineq_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_comisdneq ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomieq_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_ucomisdeq ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomilt_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_ucomisdlt ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomile_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_ucomisdle ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomigt_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_ucomisdgt ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomige_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_ucomisdge ((__v2df)__A, (__v2df)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomineq_sd (__m128d __A, __m128d __B)
{
  return __builtin_ia32_ucomisdneq ((__v2df)__A, (__v2df)__B);
}

/* Create a vector of Qi, where i is the element number.  */

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_epi64x (long long __q1, long long __q0)
{
  return __extension__ (__m128i)(__v2di){ __q0, __q1 };
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_epi64 (__m64 __q1,  __m64 __q0)
{
  return _mm_set_epi64x ((long long)__q1, (long long)__q0);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_epi32 (int __q3, int __q2, int __q1, int __q0)
{
  return __extension__ (__m128i)(__v4si){ __q0, __q1, __q2, __q3 };
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_epi16 (short __q7, short __q6, short __q5, short __q4,
	       short __q3, short __q2, short __q1, short __q0)
{
  return __extension__ (__m128i)(__v8hi){
    __q0, __q1, __q2, __q3, __q4, __q5, __q6, __q7 };
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_epi8 (char __q15, char __q14, char __q13, char __q12,
	      char __q11, char __q10, char __q09, char __q08,
	      char __q07, char __q06, char __q05, char __q04,
	      char __q03, char __q02, char __q01, char __q00)
{
  return __extension__ (__m128i)(__v16qi){
    __q00, __q01, __q02, __q03, __q04, __q05, __q06, __q07,
    __q08, __q09, __q10, __q11, __q12, __q13, __q14, __q15
  };
}

/* Set all of the elements of the vector to A.  */

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_epi64x (long long __A)
{
  return _mm_set_epi64x (__A, __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_epi64 (__m64 __A)
{
  return _mm_set_epi64 (__A, __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_epi32 (int __A)
{
  return _mm_set_epi32 (__A, __A, __A, __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_epi16 (short __A)
{
  return _mm_set_epi16 (__A, __A, __A, __A, __A, __A, __A, __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_epi8 (char __A)
{
  return _mm_set_epi8 (__A, __A, __A, __A, __A, __A, __A, __A,
		       __A, __A, __A, __A, __A, __A, __A, __A);
}

/* Create a vector of Qi, where i is the element number.
   The parameter order is reversed from the _mm_set_epi* functions.  */

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_epi64 (__m64 __q0, __m64 __q1)
{
  return _mm_set_epi64 (__q1, __q0);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_epi32 (int __q0, int __q1, int __q2, int __q3)
{
  return _mm_set_epi32 (__q3, __q2, __q1, __q0);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_epi16 (short __q0, short __q1, short __q2, short __q3,
	        short __q4, short __q5, short __q6, short __q7)
{
  return _mm_set_epi16 (__q7, __q6, __q5, __q4, __q3, __q2, __q1, __q0);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_epi8 (char __q00, char __q01, char __q02, char __q03,
	       char __q04, char __q05, char __q06, char __q07,
	       char __q08, char __q09, char __q10, char __q11,
	       char __q12, char __q13, char __q14, char __q15)
{
  return _mm_set_epi8 (__q15, __q14, __q13, __q12, __q11, __q10, __q09, __q08,
		       __q07, __q06, __q05, __q04, __q03, __q02, __q01, __q00);
}

/* Create a vector with element 0 as *P and the rest zero.  */

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_load_si128 (__m128i const *__P)
{
  return *__P;
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_loadu_si128 (__m128i_u const *__P)
{
  return *__P;
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_loadl_epi64 (__m128i_u const *__P)
{
  return _mm_set_epi64 ((__m64)0LL, *(__m64_u *)__P);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_loadu_si64 (void const *__P)
{
  return _mm_loadl_epi64 ((__m128i_u *)__P);
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_store_si128 (__m128i *__P, __m128i __B)
{
  *__P = __B;
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_storeu_si128 (__m128i_u *__P, __m128i __B)
{
  *__P = __B;
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_storel_epi64 (__m128i_u *__P, __m128i __B)
{
  *(__m64_u *)__P = (__m64) ((__v2di)__B)[0];
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_storeu_si64 (void *__P, __m128i __B)
{
  _mm_storel_epi64 ((__m128i_u *)__P, __B);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_movepi64_pi64 (__m128i __B)
{
  return (__m64) ((__v2di)__B)[0];
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_movpi64_epi64 (__m64 __A)
{
  return _mm_set_epi64 ((__m64)0LL, __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_move_epi64 (__m128i __A)
{
  return (__m128i)__builtin_ia32_movq128 ((__v2di) __A);
}

/* Create an undefined vector.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_undefined_si128 (void)
{
  __m128i __Y = __Y;
  return __Y;
}

/* Create a vector of zeros.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setzero_si128 (void)
{
  return __extension__ (__m128i)(__v4si){ 0, 0, 0, 0 };
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi32_pd (__m128i __A)
{
  return (__m128d)__builtin_ia32_cvtdq2pd ((__v4si) __A);
}

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi32_ps (__m128i __A)
{
  return (__m128)__builtin_ia32_cvtdq2ps ((__v4si) __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtpd_epi32 (__m128d __A)
{
  return (__m128i)__builtin_ia32_cvtpd2dq ((__v2df) __A);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtpd_pi32 (__m128d __A)
{
  return (__m64)__builtin_ia32_cvtpd2pi ((__v2df) __A);
}

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtpd_ps (__m128d __A)
{
  return (__m128)__builtin_ia32_cvtpd2ps ((__v2df) __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvttpd_epi32 (__m128d __A)
{
  return (__m128i)__builtin_ia32_cvttpd2dq ((__v2df) __A);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvttpd_pi32 (__m128d __A)
{
  return (__m64)__builtin_ia32_cvttpd2pi ((__v2df) __A);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtpi32_pd (__m64 __A)
{
  return (__m128d)__builtin_ia32_cvtpi2pd ((__v2si) __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtps_epi32 (__m128 __A)
{
  return (__m128i)__builtin_ia32_cvtps2dq ((__v4sf) __A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvttps_epi32 (__m128 __A)
{
  return (__m128i)__builtin_ia32_cvttps2dq ((__v4sf) __A);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtps_pd (__m128 __A)
{
  return (__m128d)__builtin_ia32_cvtps2pd ((__v4sf) __A);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsd_si32 (__m128d __A)
{
  return __builtin_ia32_cvtsd2si ((__v2df) __A);
}

#ifdef __x86_64__
/* Intel intrinsic.  */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsd_si64 (__m128d __A)
{
  return __builtin_ia32_cvtsd2si64 ((__v2df) __A);
}

/* Microsoft intrinsic.  */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsd_si64x (__m128d __A)
{
  return __builtin_ia32_cvtsd2si64 ((__v2df) __A);
}
#endif

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvttsd_si32 (__m128d __A)
{
  return __builtin_ia32_cvttsd2si ((__v2df) __A);
}

#ifdef __x86_64__
/* Intel intrinsic.  */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvttsd_si64 (__m128d __A)
{
  return __builtin_ia32_cvttsd2si64 ((__v2df) __A);
}

/* Microsoft intrinsic.  */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvttsd_si64x (__m128d __A)
{
  return __builtin_ia32_cvttsd2si64 ((__v2df) __A);
}
#endif

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsd_ss (__m128 __A, __m128d __B)
{
  return (__m128)__builtin_ia32_cvtsd2ss ((__v4sf) __A, (__v2df) __B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi32_sd (__m128d __A, int __B)
{
  return (__m128d)__builtin_ia32_cvtsi2sd ((__v2df) __A, __B);
}

#ifdef __x86_64__
/* Intel intrinsic.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64_sd (__m128d __A, long long __B)
{
  return (__m128d)__builtin_ia32_cvtsi642sd ((__v2df) __A, __B);
}

/* Microsoft intrinsic.  */
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64x_sd (__m128d __A, long long __B)
{
  return (__m128d)__builtin_ia32_cvtsi642sd ((__v2df) __A, __B);
}
#endif

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtss_sd (__m128d __A, __m128 __B)
{
  return (__m128d)__builtin_ia32_cvtss2sd ((__v2df) __A, (__v4sf)__B);
}

#ifdef __OPTIMIZE__
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_shuffle_pd(__m128d __A, __m128d __B, const int __mask)
{
  return (__m128d)__builtin_ia32_shufpd ((__v2df)__A, (__v2df)__B, __mask);
}
#else
#define _mm_shuffle_pd(A, B, N)						\
  ((__m128d)__builtin_ia32_shufpd ((__v2df)(__m128d)(A),		\
				   (__v2df)(__m128d)(B), (int)(N)))
#endif

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_unpckhpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_pd (__m128d __A, __m128d __B)
{
  return (__m128d)__builtin_ia32_unpcklpd ((__v2df)__A, (__v2df)__B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_loadh_pd (__m128d __A, double const *__B)
{
  return (__m128d)__builtin_ia32_loadhpd ((__v2df)__A, __B);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_loadl_pd (__m128d __A, double const *__B)
{
  return (__m128d)__builtin_ia32_loadlpd ((__v2df)__A, __B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_movemask_pd (__m128d __A)
{
  return __builtin_ia32_movmskpd ((__v2df)__A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packs_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_packsswb128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packs_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_packssdw128 ((__v4si)__A, (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packus_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_packuswb128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_punpckhbw128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_punpckhwd128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_punpckhdq128 ((__v4si)__A, (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_epi64 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_punpckhqdq128 ((__v2di)__A, (__v2di)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_punpcklbw128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_punpcklwd128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_punpckldq128 ((__v4si)__A, (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_epi64 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_punpcklqdq128 ((__v2di)__A, (__v2di)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v16qu)__A + (__v16qu)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v8hu)__A + (__v8hu)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v4su)__A + (__v4su)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_epi64 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v2du)__A + (__v2du)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_paddsb128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_paddsw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_epu8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_paddusb128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_epu16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_paddusw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v16qu)__A - (__v16qu)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v8hu)__A - (__v8hu)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v4su)__A - (__v4su)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_epi64 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v2du)__A - (__v2du)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psubsb128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psubsw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_epu8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psubusb128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_epu16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psubusw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_madd_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pmaddwd128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mulhi_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pmulhw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mullo_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v8hu)__A * (__v8hu)__B);
}

extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mul_su32 (__m64 __A, __m64 __B)
{
  return (__m64)__builtin_ia32_pmuludq ((__v2si)__A, (__v2si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mul_epu32 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pmuludq128 ((__v4si)__A, (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_epi16 (__m128i __A, int __B)
{
  return (__m128i)__builtin_ia32_psllwi128 ((__v8hi)__A, __B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_epi32 (__m128i __A, int __B)
{
  return (__m128i)__builtin_ia32_pslldi128 ((__v4si)__A, __B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_epi64 (__m128i __A, int __B)
{
  return (__m128i)__builtin_ia32_psllqi128 ((__v2di)__A, __B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srai_epi16 (__m128i __A, int __B)
{
  return (__m128i)__builtin_ia32_psrawi128 ((__v8hi)__A, __B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srai_epi32 (__m128i __A, int __B)
{
  return (__m128i)__builtin_ia32_psradi128 ((__v4si)__A, __B);
}

#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_bsrli_si128 (__m128i __A, const int __N)
{
  return (__m128i)__builtin_ia32_psrldqi128 (__A, __N * 8);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_bslli_si128 (__m128i __A, const int __N)
{
  return (__m128i)__builtin_ia32_pslldqi128 (__A, __N * 8);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_si128 (__m128i __A, const int __N)
{
  return (__m128i)__builtin_ia32_psrldqi128 (__A, __N * 8);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_si128 (__m128i __A, const int __N)
{
  return (__m128i)__builtin_ia32_pslldqi128 (__A, __N * 8);
}
#else
#define _mm_bsrli_si128(A, N) \
  ((__m128i)__builtin_ia32_psrldqi128 ((__m128i)(A), (int)(N) * 8))
#define _mm_bslli_si128(A, N) \
  ((__m128i)__builtin_ia32_pslldqi128 ((__m128i)(A), (int)(N) * 8))
#define _mm_srli_si128(A, N) \
  ((__m128i)__builtin_ia32_psrldqi128 ((__m128i)(A), (int)(N) * 8))
#define _mm_slli_si128(A, N) \
  ((__m128i)__builtin_ia32_pslldqi128 ((__m128i)(A), (int)(N) * 8))
#endif

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_epi16 (__m128i __A, int __B)
{
  return (__m128i)__builtin_ia32_psrlwi128 ((__v8hi)__A, __B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_epi32 (__m128i __A, int __B)
{
  return (__m128i)__builtin_ia32_psrldi128 ((__v4si)__A, __B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_epi64 (__m128i __A, int __B)
{
  return (__m128i)__builtin_ia32_psrlqi128 ((__v2di)__A, __B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psllw128((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pslld128((__v4si)__A, (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_epi64 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psllq128((__v2di)__A, (__v2di)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sra_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psraw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sra_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psrad128 ((__v4si)__A, (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psrlw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psrld128 ((__v4si)__A, (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_epi64 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psrlq128 ((__v2di)__A, (__v2di)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_and_si128 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v2du)__A & (__v2du)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_andnot_si128 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pandn128 ((__v2di)__A, (__v2di)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_or_si128 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v2du)__A | (__v2du)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_xor_si128 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v2du)__A ^ (__v2du)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v16qi)__A == (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v8hi)__A == (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v4si)__A == (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmplt_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v16qs)__A < (__v16qs)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmplt_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v8hi)__A < (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmplt_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v4si)__A < (__v4si)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_epi8 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v16qs)__A > (__v16qs)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v8hi)__A > (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_epi32 (__m128i __A, __m128i __B)
{
  return (__m128i) ((__v4si)__A > (__v4si)__B);
}

#ifdef __OPTIMIZE__
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi16 (__m128i const __A, int const __N)
{
  return (unsigned short) __builtin_ia32_vec_ext_v8hi ((__v8hi)__A, __N);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_epi16 (__m128i const __A, int const __D, int const __N)
{
  return (__m128i) __builtin_ia32_vec_set_v8hi ((__v8hi)__A, __D, __N);
}
#else
#define _mm_extract_epi16(A, N) \
  ((int) (unsigned short) __builtin_ia32_vec_ext_v8hi ((__v8hi)(__m128i)(A), (int)(N)))
#define _mm_insert_epi16(A, D, N)				\
  ((__m128i) __builtin_ia32_vec_set_v8hi ((__v8hi)(__m128i)(A),	\
					  (int)(D), (int)(N)))
#endif

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pmaxsw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epu8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pmaxub128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epi16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pminsw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epu8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pminub128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_movemask_epi8 (__m128i __A)
{
  return __builtin_ia32_pmovmskb128 ((__v16qi)__A);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mulhi_epu16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pmulhuw128 ((__v8hi)__A, (__v8hi)__B);
}

#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_shufflehi_epi16 (__m128i __A, const int __mask)
{
  return (__m128i)__builtin_ia32_pshufhw ((__v8hi)__A, __mask);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_shufflelo_epi16 (__m128i __A, const int __mask)
{
  return (__m128i)__builtin_ia32_pshuflw ((__v8hi)__A, __mask);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_shuffle_epi32 (__m128i __A, const int __mask)
{
  return (__m128i)__builtin_ia32_pshufd ((__v4si)__A, __mask);
}
#else
#define _mm_shufflehi_epi16(A, N) \
  ((__m128i)__builtin_ia32_pshufhw ((__v8hi)(__m128i)(A), (int)(N)))
#define _mm_shufflelo_epi16(A, N) \
  ((__m128i)__builtin_ia32_pshuflw ((__v8hi)(__m128i)(A), (int)(N)))
#define _mm_shuffle_epi32(A, N) \
  ((__m128i)__builtin_ia32_pshufd ((__v4si)(__m128i)(A), (int)(N)))
#endif

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskmoveu_si128 (__m128i __A, __m128i __B, char *__C)
{
  __builtin_ia32_maskmovdqu ((__v16qi)__A, (__v16qi)__B, __C);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_avg_epu8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pavgb128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_avg_epu16 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_pavgw128 ((__v8hi)__A, (__v8hi)__B);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sad_epu8 (__m128i __A, __m128i __B)
{
  return (__m128i)__builtin_ia32_psadbw128 ((__v16qi)__A, (__v16qi)__B);
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_stream_si32 (int *__A, int __B)
{
  __builtin_ia32_movnti (__A, __B);
}

#ifdef __x86_64__
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_stream_si64 (long long int *__A, long long int __B)
{
  __builtin_ia32_movnti64 (__A, __B);
}
#endif

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_stream_si128 (__m128i *__A, __m128i __B)
{
  __builtin_ia32_movntdq ((__v2di *)__A, (__v2di)__B);
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_stream_pd (double *__A, __m128d __B)
{
  __builtin_ia32_movntpd (__A, (__v2df)__B);
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_clflush (void const *__A)
{
  __builtin_ia32_clflush (__A);
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_lfence (void)
{
  __builtin_ia32_lfence ();
}

extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mfence (void)
{
  __builtin_ia32_mfence ();
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi32_si128 (int __A)
{
  return _mm_set_epi32 (0, 0, 0, __A);
}

#ifdef __x86_64__
/* Intel intrinsic.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64_si128 (long long __A)
{
  return _mm_set_epi64x (0, __A);
}

/* Microsoft intrinsic.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64x_si128 (long long __A)
{
  return _mm_set_epi64x (0, __A);
}
#endif

/* Casts between various SP, DP, INT vector types.  Note that these do no
   conversion of values, they just change the type.  */
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_castpd_ps(__m128d __A)
{
  return (__m128) __A;
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_castpd_si128(__m128d __A)
{
  return (__m128i) __A;
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_castps_pd(__m128 __A)
{
  return (__m128d) __A;
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_castps_si128(__m128 __A)
{
  return (__m128i) __A;
}

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_castsi128_ps(__m128i __A)
{
  return (__m128) __A;
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_castsi128_pd(__m128i __A)
{
  return (__m128d) __A;
}

#ifdef __DISABLE_SSE2__
#undef __DISABLE_SSE2__
#pragma GCC pop_options
#endif /* __DISABLE_SSE2__ */

#endif /* _EMMINTRIN_H_INCLUDED */