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) 2007-2019 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 10.0.  */

#ifndef _SMMINTRIN_H_INCLUDED
#define _SMMINTRIN_H_INCLUDED

/* We need definitions from the SSSE3, SSE3, SSE2 and SSE header
   files.  */
#include <tmmintrin.h>

#ifndef __SSE4_1__
#pragma GCC push_options
#pragma GCC target("sse4.1")
#define __DISABLE_SSE4_1__
#endif /* __SSE4_1__ */

/* Rounding mode macros. */
#define _MM_FROUND_TO_NEAREST_INT	0x00
#define _MM_FROUND_TO_NEG_INF		0x01
#define _MM_FROUND_TO_POS_INF		0x02
#define _MM_FROUND_TO_ZERO		0x03
#define _MM_FROUND_CUR_DIRECTION	0x04

#define _MM_FROUND_RAISE_EXC		0x00
#define _MM_FROUND_NO_EXC		0x08

#define _MM_FROUND_NINT		\
  (_MM_FROUND_TO_NEAREST_INT | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_FLOOR	\
  (_MM_FROUND_TO_NEG_INF | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_CEIL		\
  (_MM_FROUND_TO_POS_INF | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_TRUNC	\
  (_MM_FROUND_TO_ZERO | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_RINT		\
  (_MM_FROUND_CUR_DIRECTION | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_NEARBYINT	\
  (_MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC)

/* Test Instruction */
/* Packed integer 128-bit bitwise comparison. Return 1 if
   (__V & __M) == 0.  */
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testz_si128 (__m128i __M, __m128i __V)
{
  return __builtin_ia32_ptestz128 ((__v2di)__M, (__v2di)__V);
}

/* Packed integer 128-bit bitwise comparison. Return 1 if
   (__V & ~__M) == 0.  */
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testc_si128 (__m128i __M, __m128i __V)
{
  return __builtin_ia32_ptestc128 ((__v2di)__M, (__v2di)__V);
}

/* Packed integer 128-bit bitwise comparison. Return 1 if
   (__V & __M) != 0 && (__V & ~__M) != 0.  */
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testnzc_si128 (__m128i __M, __m128i __V)
{
  return __builtin_ia32_ptestnzc128 ((__v2di)__M, (__v2di)__V);
}

/* Macros for packed integer 128-bit comparison intrinsics.  */
#define _mm_test_all_zeros(M, V) _mm_testz_si128 ((M), (V))

#define _mm_test_all_ones(V) \
  _mm_testc_si128 ((V), _mm_cmpeq_epi32 ((V), (V)))

#define _mm_test_mix_ones_zeros(M, V) _mm_testnzc_si128 ((M), (V))

/* Packed/scalar double precision floating point rounding.  */

#ifdef __OPTIMIZE__
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_round_pd (__m128d __V, const int __M)
{
  return (__m128d) __builtin_ia32_roundpd ((__v2df)__V, __M);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_round_sd(__m128d __D, __m128d __V, const int __M)
{
  return (__m128d) __builtin_ia32_roundsd ((__v2df)__D,
					   (__v2df)__V,
					   __M);
}
#else
#define _mm_round_pd(V, M) \
  ((__m128d) __builtin_ia32_roundpd ((__v2df)(__m128d)(V), (int)(M)))

#define _mm_round_sd(D, V, M)						\
  ((__m128d) __builtin_ia32_roundsd ((__v2df)(__m128d)(D),		\
				     (__v2df)(__m128d)(V), (int)(M)))
#endif

/* Packed/scalar single precision floating point rounding.  */

#ifdef __OPTIMIZE__
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_round_ps (__m128 __V, const int __M)
{
  return (__m128) __builtin_ia32_roundps ((__v4sf)__V, __M);
}

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_round_ss (__m128 __D, __m128 __V, const int __M)
{
  return (__m128) __builtin_ia32_roundss ((__v4sf)__D,
					  (__v4sf)__V,
					  __M);
}
#else
#define _mm_round_ps(V, M) \
  ((__m128) __builtin_ia32_roundps ((__v4sf)(__m128)(V), (int)(M)))

#define _mm_round_ss(D, V, M)						\
  ((__m128) __builtin_ia32_roundss ((__v4sf)(__m128)(D),		\
				    (__v4sf)(__m128)(V), (int)(M)))
#endif

/* Macros for ceil/floor intrinsics.  */
#define _mm_ceil_pd(V)	   _mm_round_pd ((V), _MM_FROUND_CEIL)
#define _mm_ceil_sd(D, V)  _mm_round_sd ((D), (V), _MM_FROUND_CEIL)

#define _mm_floor_pd(V)	   _mm_round_pd((V), _MM_FROUND_FLOOR)
#define _mm_floor_sd(D, V) _mm_round_sd ((D), (V), _MM_FROUND_FLOOR)

#define _mm_ceil_ps(V)	   _mm_round_ps ((V), _MM_FROUND_CEIL)
#define _mm_ceil_ss(D, V)  _mm_round_ss ((D), (V), _MM_FROUND_CEIL)

#define _mm_floor_ps(V)	   _mm_round_ps ((V), _MM_FROUND_FLOOR)
#define _mm_floor_ss(D, V) _mm_round_ss ((D), (V), _MM_FROUND_FLOOR)

/* SSE4.1 */

/* Integer blend instructions - select data from 2 sources using
   constant/variable mask.  */

#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
{
  return (__m128i) __builtin_ia32_pblendw128 ((__v8hi)__X,
					      (__v8hi)__Y,
					      __M);
}
#else
#define _mm_blend_epi16(X, Y, M)					\
  ((__m128i) __builtin_ia32_pblendw128 ((__v8hi)(__m128i)(X),		\
					(__v8hi)(__m128i)(Y), (int)(M)))
#endif

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blendv_epi8 (__m128i __X, __m128i __Y, __m128i __M)
{
  return (__m128i) __builtin_ia32_pblendvb128 ((__v16qi)__X,
					       (__v16qi)__Y,
					       (__v16qi)__M);
}

/* Single precision floating point blend instructions - select data
   from 2 sources using constant/variable mask.  */

#ifdef __OPTIMIZE__
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blend_ps (__m128 __X, __m128 __Y, const int __M)
{
  return (__m128) __builtin_ia32_blendps ((__v4sf)__X,
					  (__v4sf)__Y,
					  __M);
}
#else
#define _mm_blend_ps(X, Y, M)						\
  ((__m128) __builtin_ia32_blendps ((__v4sf)(__m128)(X),		\
				    (__v4sf)(__m128)(Y), (int)(M)))
#endif

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blendv_ps (__m128 __X, __m128 __Y, __m128 __M)
{
  return (__m128) __builtin_ia32_blendvps ((__v4sf)__X,
					   (__v4sf)__Y,
					   (__v4sf)__M);
}

/* Double precision floating point blend instructions - select data
   from 2 sources using constant/variable mask.  */

#ifdef __OPTIMIZE__
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blend_pd (__m128d __X, __m128d __Y, const int __M)
{
  return (__m128d) __builtin_ia32_blendpd ((__v2df)__X,
					   (__v2df)__Y,
					   __M);
}
#else
#define _mm_blend_pd(X, Y, M)						\
  ((__m128d) __builtin_ia32_blendpd ((__v2df)(__m128d)(X),		\
				     (__v2df)(__m128d)(Y), (int)(M)))
#endif

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blendv_pd (__m128d __X, __m128d __Y, __m128d __M)
{
  return (__m128d) __builtin_ia32_blendvpd ((__v2df)__X,
					    (__v2df)__Y,
					    (__v2df)__M);
}

/* Dot product instructions with mask-defined summing and zeroing parts
   of result.  */

#ifdef __OPTIMIZE__
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_dp_ps (__m128 __X, __m128 __Y, const int __M)
{
  return (__m128) __builtin_ia32_dpps ((__v4sf)__X,
				       (__v4sf)__Y,
				       __M);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_dp_pd (__m128d __X, __m128d __Y, const int __M)
{
  return (__m128d) __builtin_ia32_dppd ((__v2df)__X,
					(__v2df)__Y,
					__M);
}
#else
#define _mm_dp_ps(X, Y, M)						\
  ((__m128) __builtin_ia32_dpps ((__v4sf)(__m128)(X),			\
				 (__v4sf)(__m128)(Y), (int)(M)))

#define _mm_dp_pd(X, Y, M)						\
  ((__m128d) __builtin_ia32_dppd ((__v2df)(__m128d)(X),			\
				  (__v2df)(__m128d)(Y), (int)(M)))
#endif

/* Packed integer 64-bit comparison, zeroing or filling with ones
   corresponding parts of result.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_epi64 (__m128i __X, __m128i __Y)
{
  return (__m128i) ((__v2di)__X == (__v2di)__Y);
}

/*  Min/max packed integer instructions.  */

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epi8 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pminsb128 ((__v16qi)__X, (__v16qi)__Y);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epi8 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pmaxsb128 ((__v16qi)__X, (__v16qi)__Y);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epu16 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pminuw128 ((__v8hi)__X, (__v8hi)__Y);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epu16 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pmaxuw128 ((__v8hi)__X, (__v8hi)__Y);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epi32 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pminsd128 ((__v4si)__X, (__v4si)__Y);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epi32 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pmaxsd128 ((__v4si)__X, (__v4si)__Y);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epu32 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pminud128 ((__v4si)__X, (__v4si)__Y);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epu32 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pmaxud128 ((__v4si)__X, (__v4si)__Y);
}

/* Packed integer 32-bit multiplication with truncation of upper
   halves of results.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mullo_epi32 (__m128i __X, __m128i __Y)
{
  return (__m128i) ((__v4su)__X * (__v4su)__Y);
}

/* Packed integer 32-bit multiplication of 2 pairs of operands
   with two 64-bit results.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mul_epi32 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_pmuldq128 ((__v4si)__X, (__v4si)__Y);
}

/* Insert single precision float into packed single precision array
   element selected by index N.  The bits [7-6] of N define S
   index, the bits [5-4] define D index, and bits [3-0] define
   zeroing mask for D.  */

#ifdef __OPTIMIZE__
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_ps (__m128 __D, __m128 __S, const int __N)
{
  return (__m128) __builtin_ia32_insertps128 ((__v4sf)__D,
					      (__v4sf)__S,
					      __N);
}
#else
#define _mm_insert_ps(D, S, N)						\
  ((__m128) __builtin_ia32_insertps128 ((__v4sf)(__m128)(D),		\
					(__v4sf)(__m128)(S), (int)(N)))
#endif

/* Helper macro to create the N value for _mm_insert_ps.  */
#define _MM_MK_INSERTPS_NDX(S, D, M) (((S) << 6) | ((D) << 4) | (M))

/* Extract binary representation of single precision float from packed
   single precision array element of X selected by index N.  */

#ifdef __OPTIMIZE__
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_ps (__m128 __X, const int __N)
{
  union { int i; float f; } __tmp;
  __tmp.f = __builtin_ia32_vec_ext_v4sf ((__v4sf)__X, __N);
  return __tmp.i;
}
#else
#define _mm_extract_ps(X, N)						\
  (__extension__							\
   ({									\
     union { int i; float f; } __tmp;					\
     __tmp.f = __builtin_ia32_vec_ext_v4sf ((__v4sf)(__m128)(X), (int)(N)); \
     __tmp.i;								\
   }))
#endif

/* Extract binary representation of single precision float into
   D from packed single precision array element of S selected
   by index N.  */
#define _MM_EXTRACT_FLOAT(D, S, N) \
  { (D) = __builtin_ia32_vec_ext_v4sf ((__v4sf)(S), (N)); }
  
/* Extract specified single precision float element into the lower
   part of __m128.  */
#define _MM_PICK_OUT_PS(X, N)				\
  _mm_insert_ps (_mm_setzero_ps (), (X), 		\
		 _MM_MK_INSERTPS_NDX ((N), 0, 0x0e))

/* Insert integer, S, into packed integer array element of D
   selected by index N.  */

#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_epi8 (__m128i __D, int __S, const int __N)
{
  return (__m128i) __builtin_ia32_vec_set_v16qi ((__v16qi)__D,
						 __S, __N);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_epi32 (__m128i __D, int __S, const int __N)
{
  return (__m128i) __builtin_ia32_vec_set_v4si ((__v4si)__D,
						 __S, __N);
}

#ifdef __x86_64__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_epi64 (__m128i __D, long long __S, const int __N)
{
  return (__m128i) __builtin_ia32_vec_set_v2di ((__v2di)__D,
						 __S, __N);
}
#endif
#else
#define _mm_insert_epi8(D, S, N)					\
  ((__m128i) __builtin_ia32_vec_set_v16qi ((__v16qi)(__m128i)(D),	\
					   (int)(S), (int)(N)))

#define _mm_insert_epi32(D, S, N)				\
  ((__m128i) __builtin_ia32_vec_set_v4si ((__v4si)(__m128i)(D),	\
					  (int)(S), (int)(N)))

#ifdef __x86_64__
#define _mm_insert_epi64(D, S, N)					\
  ((__m128i) __builtin_ia32_vec_set_v2di ((__v2di)(__m128i)(D),		\
					  (long long)(S), (int)(N)))
#endif
#endif

/* Extract integer from packed integer array element of X selected by
   index N.  */

#ifdef __OPTIMIZE__
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi8 (__m128i __X, const int __N)
{
   return (unsigned char) __builtin_ia32_vec_ext_v16qi ((__v16qi)__X, __N);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi32 (__m128i __X, const int __N)
{
   return __builtin_ia32_vec_ext_v4si ((__v4si)__X, __N);
}

#ifdef __x86_64__
extern __inline long long  __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi64 (__m128i __X, const int __N)
{
  return __builtin_ia32_vec_ext_v2di ((__v2di)__X, __N);
}
#endif
#else
#define _mm_extract_epi8(X, N) \
  ((int) (unsigned char) __builtin_ia32_vec_ext_v16qi ((__v16qi)(__m128i)(X), (int)(N)))
#define _mm_extract_epi32(X, N) \
  ((int) __builtin_ia32_vec_ext_v4si ((__v4si)(__m128i)(X), (int)(N)))

#ifdef __x86_64__
#define _mm_extract_epi64(X, N) \
  ((long long) __builtin_ia32_vec_ext_v2di ((__v2di)(__m128i)(X), (int)(N)))
#endif
#endif

/* Return horizontal packed word minimum and its index in bits [15:0]
   and bits [18:16] respectively.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_minpos_epu16 (__m128i __X)
{
  return (__m128i) __builtin_ia32_phminposuw128 ((__v8hi)__X);
}

/* Packed integer sign-extension.  */

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi8_epi32 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovsxbd128 ((__v16qi)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi16_epi32 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovsxwd128 ((__v8hi)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi8_epi64 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovsxbq128 ((__v16qi)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi32_epi64 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovsxdq128 ((__v4si)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi16_epi64 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovsxwq128 ((__v8hi)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi8_epi16 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovsxbw128 ((__v16qi)__X);
}

/* Packed integer zero-extension. */

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu8_epi32 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovzxbd128 ((__v16qi)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu16_epi32 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovzxwd128 ((__v8hi)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu8_epi64 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovzxbq128 ((__v16qi)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu32_epi64 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovzxdq128 ((__v4si)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu16_epi64 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovzxwq128 ((__v8hi)__X);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu8_epi16 (__m128i __X)
{
  return (__m128i) __builtin_ia32_pmovzxbw128 ((__v16qi)__X);
}

/* Pack 8 double words from 2 operands into 8 words of result with
   unsigned saturation. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packus_epi32 (__m128i __X, __m128i __Y)
{
  return (__m128i) __builtin_ia32_packusdw128 ((__v4si)__X, (__v4si)__Y);
}

/* Sum absolute 8-bit integer difference of adjacent groups of 4
   byte integers in the first 2 operands.  Starting offsets within
   operands are determined by the 3rd mask operand.  */

#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mpsadbw_epu8 (__m128i __X, __m128i __Y, const int __M)
{
  return (__m128i) __builtin_ia32_mpsadbw128 ((__v16qi)__X,
					      (__v16qi)__Y, __M);
}
#else
#define _mm_mpsadbw_epu8(X, Y, M)					\
  ((__m128i) __builtin_ia32_mpsadbw128 ((__v16qi)(__m128i)(X),		\
					(__v16qi)(__m128i)(Y), (int)(M)))
#endif

/* Load double quadword using non-temporal aligned hint.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_stream_load_si128 (__m128i *__X)
{
  return (__m128i) __builtin_ia32_movntdqa ((__v2di *) __X);
}

#ifndef __SSE4_2__
#pragma GCC push_options
#pragma GCC target("sse4.2")
#define __DISABLE_SSE4_2__
#endif /* __SSE4_2__ */

/* These macros specify the source data format.  */
#define _SIDD_UBYTE_OPS			0x00
#define _SIDD_UWORD_OPS			0x01
#define _SIDD_SBYTE_OPS			0x02
#define _SIDD_SWORD_OPS			0x03

/* These macros specify the comparison operation.  */
#define _SIDD_CMP_EQUAL_ANY		0x00
#define _SIDD_CMP_RANGES		0x04
#define _SIDD_CMP_EQUAL_EACH		0x08
#define _SIDD_CMP_EQUAL_ORDERED		0x0c

/* These macros specify the polarity.  */
#define _SIDD_POSITIVE_POLARITY		0x00
#define _SIDD_NEGATIVE_POLARITY		0x10
#define _SIDD_MASKED_POSITIVE_POLARITY	0x20
#define _SIDD_MASKED_NEGATIVE_POLARITY	0x30

/* These macros specify the output selection in _mm_cmpXstri ().  */
#define _SIDD_LEAST_SIGNIFICANT		0x00
#define _SIDD_MOST_SIGNIFICANT		0x40

/* These macros specify the output selection in _mm_cmpXstrm ().  */
#define _SIDD_BIT_MASK			0x00
#define _SIDD_UNIT_MASK			0x40

/* Intrinsics for text/string processing.  */

#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistrm (__m128i __X, __m128i __Y, const int __M)
{
  return (__m128i) __builtin_ia32_pcmpistrm128 ((__v16qi)__X,
						(__v16qi)__Y,
						__M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistri (__m128i __X, __m128i __Y, const int __M)
{
  return __builtin_ia32_pcmpistri128 ((__v16qi)__X,
				      (__v16qi)__Y,
				      __M);
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestrm (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
  return (__m128i) __builtin_ia32_pcmpestrm128 ((__v16qi)__X, __LX,
						(__v16qi)__Y, __LY,
						__M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestri (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
  return __builtin_ia32_pcmpestri128 ((__v16qi)__X, __LX,
				      (__v16qi)__Y, __LY,
				      __M);
}
#else
#define _mm_cmpistrm(X, Y, M)						\
  ((__m128i) __builtin_ia32_pcmpistrm128 ((__v16qi)(__m128i)(X),	\
					  (__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistri(X, Y, M)						\
  ((int) __builtin_ia32_pcmpistri128 ((__v16qi)(__m128i)(X),		\
				      (__v16qi)(__m128i)(Y), (int)(M)))

#define _mm_cmpestrm(X, LX, Y, LY, M)					\
  ((__m128i) __builtin_ia32_pcmpestrm128 ((__v16qi)(__m128i)(X),	\
					  (int)(LX), (__v16qi)(__m128i)(Y), \
					  (int)(LY), (int)(M)))
#define _mm_cmpestri(X, LX, Y, LY, M)					\
  ((int) __builtin_ia32_pcmpestri128 ((__v16qi)(__m128i)(X), (int)(LX),	\
				      (__v16qi)(__m128i)(Y), (int)(LY),	\
				      (int)(M)))
#endif

/* Intrinsics for text/string processing and reading values of
   EFlags.  */

#ifdef __OPTIMIZE__
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistra (__m128i __X, __m128i __Y, const int __M)
{
  return __builtin_ia32_pcmpistria128 ((__v16qi)__X,
				       (__v16qi)__Y,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistrc (__m128i __X, __m128i __Y, const int __M)
{
  return __builtin_ia32_pcmpistric128 ((__v16qi)__X,
				       (__v16qi)__Y,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistro (__m128i __X, __m128i __Y, const int __M)
{
  return __builtin_ia32_pcmpistrio128 ((__v16qi)__X,
				       (__v16qi)__Y,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistrs (__m128i __X, __m128i __Y, const int __M)
{
  return __builtin_ia32_pcmpistris128 ((__v16qi)__X,
				       (__v16qi)__Y,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistrz (__m128i __X, __m128i __Y, const int __M)
{
  return __builtin_ia32_pcmpistriz128 ((__v16qi)__X,
				       (__v16qi)__Y,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestra (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
  return __builtin_ia32_pcmpestria128 ((__v16qi)__X, __LX,
				       (__v16qi)__Y, __LY,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestrc (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
  return __builtin_ia32_pcmpestric128 ((__v16qi)__X, __LX,
				       (__v16qi)__Y, __LY,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestro (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
  return __builtin_ia32_pcmpestrio128 ((__v16qi)__X, __LX,
				       (__v16qi)__Y, __LY,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestrs (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
  return __builtin_ia32_pcmpestris128 ((__v16qi)__X, __LX,
				       (__v16qi)__Y, __LY,
				       __M);
}

extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestrz (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
  return __builtin_ia32_pcmpestriz128 ((__v16qi)__X, __LX,
				       (__v16qi)__Y, __LY,
				       __M);
}
#else
#define _mm_cmpistra(X, Y, M)						\
  ((int) __builtin_ia32_pcmpistria128 ((__v16qi)(__m128i)(X),		\
				       (__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistrc(X, Y, M)						\
  ((int) __builtin_ia32_pcmpistric128 ((__v16qi)(__m128i)(X),		\
				       (__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistro(X, Y, M)						\
  ((int) __builtin_ia32_pcmpistrio128 ((__v16qi)(__m128i)(X),		\
				       (__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistrs(X, Y, M)						\
  ((int) __builtin_ia32_pcmpistris128 ((__v16qi)(__m128i)(X),		\
				       (__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistrz(X, Y, M)						\
  ((int) __builtin_ia32_pcmpistriz128 ((__v16qi)(__m128i)(X),		\
				       (__v16qi)(__m128i)(Y), (int)(M)))

#define _mm_cmpestra(X, LX, Y, LY, M)					\
  ((int) __builtin_ia32_pcmpestria128 ((__v16qi)(__m128i)(X), (int)(LX), \
				       (__v16qi)(__m128i)(Y), (int)(LY), \
				       (int)(M)))
#define _mm_cmpestrc(X, LX, Y, LY, M)					\
  ((int) __builtin_ia32_pcmpestric128 ((__v16qi)(__m128i)(X), (int)(LX), \
				       (__v16qi)(__m128i)(Y), (int)(LY), \
				       (int)(M)))
#define _mm_cmpestro(X, LX, Y, LY, M)					\
  ((int) __builtin_ia32_pcmpestrio128 ((__v16qi)(__m128i)(X), (int)(LX), \
				       (__v16qi)(__m128i)(Y), (int)(LY), \
				       (int)(M)))
#define _mm_cmpestrs(X, LX, Y, LY, M)					\
  ((int) __builtin_ia32_pcmpestris128 ((__v16qi)(__m128i)(X), (int)(LX), \
				       (__v16qi)(__m128i)(Y), (int)(LY), \
				       (int)(M)))
#define _mm_cmpestrz(X, LX, Y, LY, M)					\
  ((int) __builtin_ia32_pcmpestriz128 ((__v16qi)(__m128i)(X), (int)(LX), \
				       (__v16qi)(__m128i)(Y), (int)(LY), \
				       (int)(M)))
#endif

/* Packed integer 64-bit comparison, zeroing or filling with ones
   corresponding parts of result.  */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_epi64 (__m128i __X, __m128i __Y)
{
  return (__m128i) ((__v2di)__X > (__v2di)__Y);
}

#ifdef __DISABLE_SSE4_2__
#undef __DISABLE_SSE4_2__
#pragma GCC pop_options
#endif /* __DISABLE_SSE4_2__ */

#ifdef __DISABLE_SSE4_1__
#undef __DISABLE_SSE4_1__
#pragma GCC pop_options
#endif /* __DISABLE_SSE4_1__ */

#include <popcntintrin.h>

#ifndef __SSE4_1__
#pragma GCC push_options
#pragma GCC target("sse4.1")
#define __DISABLE_SSE4_1__
#endif /* __SSE4_1__ */

#ifndef __SSE4_2__
#pragma GCC push_options
#pragma GCC target("sse4.2")
#define __DISABLE_SSE4_2__
#endif /* __SSE4_1__ */

/* Accumulate CRC32 (polynomial 0x11EDC6F41) value.  */
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_crc32_u8 (unsigned int __C, unsigned char __V)
{
  return __builtin_ia32_crc32qi (__C, __V);
}

extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_crc32_u16 (unsigned int __C, unsigned short __V)
{
  return __builtin_ia32_crc32hi (__C, __V);
}

extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_crc32_u32 (unsigned int __C, unsigned int __V)
{
  return __builtin_ia32_crc32si (__C, __V);
}

#ifdef __x86_64__
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_crc32_u64 (unsigned long long __C, unsigned long long __V)
{
  return __builtin_ia32_crc32di (__C, __V);
}
#endif

#ifdef __DISABLE_SSE4_2__
#undef __DISABLE_SSE4_2__
#pragma GCC pop_options
#endif /* __DISABLE_SSE4_2__ */

#ifdef __DISABLE_SSE4_1__
#undef __DISABLE_SSE4_1__
#pragma GCC pop_options
#endif /* __DISABLE_SSE4_1__ */

#endif /* _SMMINTRIN_H_INCLUDED */