12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290 |
- From 2258cdd072fa32063a7a66fef68808cd597afb9d Mon Sep 17 00:00:00 2001
- From: Frank Chang <frank.chang@sifive.com>
- Date: Thu, 30 Jul 2020 20:42:19 +0800
- Subject: [PATCH 021/107] target/riscv: rvv-1.0: add VMA and VTA
- Introduce vma and vta fields in vtype register.
- According to RVV 1.0 spec (section 3.3.3):
- When a set is marked agnostic, the corresponding set of destination
- elements in any vector or mask destination operand can either retain
- the value they previously held, or are overwritten with 1s.
- So, either vta/vma is set to undisturbed or agnostic, it's legal to
- retain the inactive masked-off elements and tail elements' original
- values unchanged. Therefore, besides declaring vta/vma fields in vtype
- register, also remove all the tail elements clean functions in this
- commit.
- Signed-off-by: Frank Chang <frank.chang@sifive.com>
- Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
- Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
- ---
- target/riscv/cpu.h | 2 +
- target/riscv/vector_helper.c | 1927 ++++++++++++++++------------------
- 2 files changed, 891 insertions(+), 1038 deletions(-)
- diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
- index 33cb265304..3835d22ca1 100644
- --- a/target/riscv/cpu.h
- +++ b/target/riscv/cpu.h
- @@ -107,6 +107,8 @@ typedef struct CPURISCVState CPURISCVState;
-
- FIELD(VTYPE, VLMUL, 0, 3)
- FIELD(VTYPE, VSEW, 3, 3)
- +FIELD(VTYPE, VTA, 6, 1)
- +FIELD(VTYPE, VMA, 7, 1)
- FIELD(VTYPE, VEDIV, 8, 2)
- FIELD(VTYPE, RESERVED, 10, sizeof(target_ulong) * 8 - 11)
- FIELD(VTYPE, VILL, sizeof(target_ulong) * 8 - 1, 1)
- diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
- index f28d20a97d..5a142a1f4b 100644
- --- a/target/riscv/vector_helper.c
- +++ b/target/riscv/vector_helper.c
- @@ -146,55 +146,6 @@ static void probe_pages(CPURISCVState *env, target_ulong addr,
- }
- }
-
- -#ifdef HOST_WORDS_BIGENDIAN
- -static void vext_clear(void *tail, uint32_t cnt, uint32_t tot)
- -{
- - /*
- - * Split the remaining range to two parts.
- - * The first part is in the last uint64_t unit.
- - * The second part start from the next uint64_t unit.
- - */
- - int part1 = 0, part2 = tot - cnt;
- - if (cnt % 8) {
- - part1 = 8 - (cnt % 8);
- - part2 = tot - cnt - part1;
- - memset(QEMU_ALIGN_PTR_DOWN(tail, 8), 0, part1);
- - memset(QEMU_ALIGN_PTR_UP(tail, 8), 0, part2);
- - } else {
- - memset(tail, 0, part2);
- - }
- -}
- -#else
- -static void vext_clear(void *tail, uint32_t cnt, uint32_t tot)
- -{
- - memset(tail, 0, tot - cnt);
- -}
- -#endif
- -
- -static void clearb(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot)
- -{
- - int8_t *cur = ((int8_t *)vd + H1(idx));
- - vext_clear(cur, cnt, tot);
- -}
- -
- -static void clearh(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot)
- -{
- - int16_t *cur = ((int16_t *)vd + H2(idx));
- - vext_clear(cur, cnt, tot);
- -}
- -
- -static void clearl(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot)
- -{
- - int32_t *cur = ((int32_t *)vd + H4(idx));
- - vext_clear(cur, cnt, tot);
- -}
- -
- -static void clearq(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot)
- -{
- - int64_t *cur = (int64_t *)vd + idx;
- - vext_clear(cur, cnt, tot);
- -}
- -
- static inline void vext_set_elem_mask(void *v0, int index,
- uint8_t value)
- {
- @@ -219,7 +170,6 @@ static inline int vext_elem_mask(void *v0, int index)
- /* elements operations for load and store */
- typedef void vext_ldst_elem_fn(CPURISCVState *env, target_ulong addr,
- uint32_t idx, void *vd, uintptr_t retaddr);
- -typedef void clear_fn(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot);
-
- #define GEN_VEXT_LD_ELEM(NAME, MTYPE, ETYPE, H, LDSUF) \
- static void NAME(CPURISCVState *env, abi_ptr addr, \
- @@ -283,7 +233,7 @@ static void
- vext_ldst_stride(void *vd, void *v0, target_ulong base,
- target_ulong stride, CPURISCVState *env,
- uint32_t desc, uint32_t vm,
- - vext_ldst_elem_fn *ldst_elem, clear_fn *clear_elem,
- + vext_ldst_elem_fn *ldst_elem,
- uint32_t esz, uint32_t msz, uintptr_t ra,
- MMUAccessType access_type)
- {
- @@ -310,47 +260,41 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
- k++;
- }
- }
- - /* clear tail elements */
- - if (clear_elem) {
- - for (k = 0; k < nf; k++) {
- - clear_elem(vd, env->vl + k * vlmax, env->vl * esz, vlmax * esz);
- - }
- - }
- }
-
- -#define GEN_VEXT_LD_STRIDE(NAME, MTYPE, ETYPE, LOAD_FN, CLEAR_FN) \
- +#define GEN_VEXT_LD_STRIDE(NAME, MTYPE, ETYPE, LOAD_FN) \
- void HELPER(NAME)(void *vd, void * v0, target_ulong base, \
- target_ulong stride, CPURISCVState *env, \
- uint32_t desc) \
- { \
- uint32_t vm = vext_vm(desc); \
- vext_ldst_stride(vd, v0, base, stride, env, desc, vm, LOAD_FN, \
- - CLEAR_FN, sizeof(ETYPE), sizeof(MTYPE), \
- + sizeof(ETYPE), sizeof(MTYPE), \
- GETPC(), MMU_DATA_LOAD); \
- }
-
- -GEN_VEXT_LD_STRIDE(vlsb_v_b, int8_t, int8_t, ldb_b, clearb)
- -GEN_VEXT_LD_STRIDE(vlsb_v_h, int8_t, int16_t, ldb_h, clearh)
- -GEN_VEXT_LD_STRIDE(vlsb_v_w, int8_t, int32_t, ldb_w, clearl)
- -GEN_VEXT_LD_STRIDE(vlsb_v_d, int8_t, int64_t, ldb_d, clearq)
- -GEN_VEXT_LD_STRIDE(vlsh_v_h, int16_t, int16_t, ldh_h, clearh)
- -GEN_VEXT_LD_STRIDE(vlsh_v_w, int16_t, int32_t, ldh_w, clearl)
- -GEN_VEXT_LD_STRIDE(vlsh_v_d, int16_t, int64_t, ldh_d, clearq)
- -GEN_VEXT_LD_STRIDE(vlsw_v_w, int32_t, int32_t, ldw_w, clearl)
- -GEN_VEXT_LD_STRIDE(vlsw_v_d, int32_t, int64_t, ldw_d, clearq)
- -GEN_VEXT_LD_STRIDE(vlse_v_b, int8_t, int8_t, lde_b, clearb)
- -GEN_VEXT_LD_STRIDE(vlse_v_h, int16_t, int16_t, lde_h, clearh)
- -GEN_VEXT_LD_STRIDE(vlse_v_w, int32_t, int32_t, lde_w, clearl)
- -GEN_VEXT_LD_STRIDE(vlse_v_d, int64_t, int64_t, lde_d, clearq)
- -GEN_VEXT_LD_STRIDE(vlsbu_v_b, uint8_t, uint8_t, ldbu_b, clearb)
- -GEN_VEXT_LD_STRIDE(vlsbu_v_h, uint8_t, uint16_t, ldbu_h, clearh)
- -GEN_VEXT_LD_STRIDE(vlsbu_v_w, uint8_t, uint32_t, ldbu_w, clearl)
- -GEN_VEXT_LD_STRIDE(vlsbu_v_d, uint8_t, uint64_t, ldbu_d, clearq)
- -GEN_VEXT_LD_STRIDE(vlshu_v_h, uint16_t, uint16_t, ldhu_h, clearh)
- -GEN_VEXT_LD_STRIDE(vlshu_v_w, uint16_t, uint32_t, ldhu_w, clearl)
- -GEN_VEXT_LD_STRIDE(vlshu_v_d, uint16_t, uint64_t, ldhu_d, clearq)
- -GEN_VEXT_LD_STRIDE(vlswu_v_w, uint32_t, uint32_t, ldwu_w, clearl)
- -GEN_VEXT_LD_STRIDE(vlswu_v_d, uint32_t, uint64_t, ldwu_d, clearq)
- +GEN_VEXT_LD_STRIDE(vlsb_v_b, int8_t, int8_t, ldb_b)
- +GEN_VEXT_LD_STRIDE(vlsb_v_h, int8_t, int16_t, ldb_h)
- +GEN_VEXT_LD_STRIDE(vlsb_v_w, int8_t, int32_t, ldb_w)
- +GEN_VEXT_LD_STRIDE(vlsb_v_d, int8_t, int64_t, ldb_d)
- +GEN_VEXT_LD_STRIDE(vlsh_v_h, int16_t, int16_t, ldh_h)
- +GEN_VEXT_LD_STRIDE(vlsh_v_w, int16_t, int32_t, ldh_w)
- +GEN_VEXT_LD_STRIDE(vlsh_v_d, int16_t, int64_t, ldh_d)
- +GEN_VEXT_LD_STRIDE(vlsw_v_w, int32_t, int32_t, ldw_w)
- +GEN_VEXT_LD_STRIDE(vlsw_v_d, int32_t, int64_t, ldw_d)
- +GEN_VEXT_LD_STRIDE(vlse_v_b, int8_t, int8_t, lde_b)
- +GEN_VEXT_LD_STRIDE(vlse_v_h, int16_t, int16_t, lde_h)
- +GEN_VEXT_LD_STRIDE(vlse_v_w, int32_t, int32_t, lde_w)
- +GEN_VEXT_LD_STRIDE(vlse_v_d, int64_t, int64_t, lde_d)
- +GEN_VEXT_LD_STRIDE(vlsbu_v_b, uint8_t, uint8_t, ldbu_b)
- +GEN_VEXT_LD_STRIDE(vlsbu_v_h, uint8_t, uint16_t, ldbu_h)
- +GEN_VEXT_LD_STRIDE(vlsbu_v_w, uint8_t, uint32_t, ldbu_w)
- +GEN_VEXT_LD_STRIDE(vlsbu_v_d, uint8_t, uint64_t, ldbu_d)
- +GEN_VEXT_LD_STRIDE(vlshu_v_h, uint16_t, uint16_t, ldhu_h)
- +GEN_VEXT_LD_STRIDE(vlshu_v_w, uint16_t, uint32_t, ldhu_w)
- +GEN_VEXT_LD_STRIDE(vlshu_v_d, uint16_t, uint64_t, ldhu_d)
- +GEN_VEXT_LD_STRIDE(vlswu_v_w, uint32_t, uint32_t, ldwu_w)
- +GEN_VEXT_LD_STRIDE(vlswu_v_d, uint32_t, uint64_t, ldwu_d)
-
- #define GEN_VEXT_ST_STRIDE(NAME, MTYPE, ETYPE, STORE_FN) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
- @@ -359,7 +303,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
- { \
- uint32_t vm = vext_vm(desc); \
- vext_ldst_stride(vd, v0, base, stride, env, desc, vm, STORE_FN, \
- - NULL, sizeof(ETYPE), sizeof(MTYPE), \
- + sizeof(ETYPE), sizeof(MTYPE), \
- GETPC(), MMU_DATA_STORE); \
- }
-
- @@ -384,9 +328,8 @@ GEN_VEXT_ST_STRIDE(vsse_v_d, int64_t, int64_t, ste_d)
- /* unmasked unit-stride load and store operation*/
- static void
- vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
- - vext_ldst_elem_fn *ldst_elem, clear_fn *clear_elem,
- - uint32_t esz, uint32_t msz, uintptr_t ra,
- - MMUAccessType access_type)
- + vext_ldst_elem_fn *ldst_elem, uint32_t esz, uint32_t msz,
- + uintptr_t ra, MMUAccessType access_type)
- {
- uint32_t i, k;
- uint32_t nf = vext_nf(desc);
- @@ -403,12 +346,6 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
- k++;
- }
- }
- - /* clear tail elements */
- - if (clear_elem) {
- - for (k = 0; k < nf; k++) {
- - clear_elem(vd, env->vl + k * vlmax, env->vl * esz, vlmax * esz);
- - }
- - }
- }
-
- /*
- @@ -416,45 +353,45 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
- * stride = NF * sizeof (MTYPE)
- */
-
- -#define GEN_VEXT_LD_US(NAME, MTYPE, ETYPE, LOAD_FN, CLEAR_FN) \
- +#define GEN_VEXT_LD_US(NAME, MTYPE, ETYPE, LOAD_FN) \
- void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \
- CPURISCVState *env, uint32_t desc) \
- { \
- uint32_t stride = vext_nf(desc) * sizeof(MTYPE); \
- vext_ldst_stride(vd, v0, base, stride, env, desc, false, LOAD_FN, \
- - CLEAR_FN, sizeof(ETYPE), sizeof(MTYPE), \
- + sizeof(ETYPE), sizeof(MTYPE), \
- GETPC(), MMU_DATA_LOAD); \
- } \
- \
- void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - vext_ldst_us(vd, base, env, desc, LOAD_FN, CLEAR_FN, \
- + vext_ldst_us(vd, base, env, desc, LOAD_FN, \
- sizeof(ETYPE), sizeof(MTYPE), GETPC(), MMU_DATA_LOAD); \
- }
-
- -GEN_VEXT_LD_US(vlb_v_b, int8_t, int8_t, ldb_b, clearb)
- -GEN_VEXT_LD_US(vlb_v_h, int8_t, int16_t, ldb_h, clearh)
- -GEN_VEXT_LD_US(vlb_v_w, int8_t, int32_t, ldb_w, clearl)
- -GEN_VEXT_LD_US(vlb_v_d, int8_t, int64_t, ldb_d, clearq)
- -GEN_VEXT_LD_US(vlh_v_h, int16_t, int16_t, ldh_h, clearh)
- -GEN_VEXT_LD_US(vlh_v_w, int16_t, int32_t, ldh_w, clearl)
- -GEN_VEXT_LD_US(vlh_v_d, int16_t, int64_t, ldh_d, clearq)
- -GEN_VEXT_LD_US(vlw_v_w, int32_t, int32_t, ldw_w, clearl)
- -GEN_VEXT_LD_US(vlw_v_d, int32_t, int64_t, ldw_d, clearq)
- -GEN_VEXT_LD_US(vle_v_b, int8_t, int8_t, lde_b, clearb)
- -GEN_VEXT_LD_US(vle_v_h, int16_t, int16_t, lde_h, clearh)
- -GEN_VEXT_LD_US(vle_v_w, int32_t, int32_t, lde_w, clearl)
- -GEN_VEXT_LD_US(vle_v_d, int64_t, int64_t, lde_d, clearq)
- -GEN_VEXT_LD_US(vlbu_v_b, uint8_t, uint8_t, ldbu_b, clearb)
- -GEN_VEXT_LD_US(vlbu_v_h, uint8_t, uint16_t, ldbu_h, clearh)
- -GEN_VEXT_LD_US(vlbu_v_w, uint8_t, uint32_t, ldbu_w, clearl)
- -GEN_VEXT_LD_US(vlbu_v_d, uint8_t, uint64_t, ldbu_d, clearq)
- -GEN_VEXT_LD_US(vlhu_v_h, uint16_t, uint16_t, ldhu_h, clearh)
- -GEN_VEXT_LD_US(vlhu_v_w, uint16_t, uint32_t, ldhu_w, clearl)
- -GEN_VEXT_LD_US(vlhu_v_d, uint16_t, uint64_t, ldhu_d, clearq)
- -GEN_VEXT_LD_US(vlwu_v_w, uint32_t, uint32_t, ldwu_w, clearl)
- -GEN_VEXT_LD_US(vlwu_v_d, uint32_t, uint64_t, ldwu_d, clearq)
- +GEN_VEXT_LD_US(vlb_v_b, int8_t, int8_t, ldb_b)
- +GEN_VEXT_LD_US(vlb_v_h, int8_t, int16_t, ldb_h)
- +GEN_VEXT_LD_US(vlb_v_w, int8_t, int32_t, ldb_w)
- +GEN_VEXT_LD_US(vlb_v_d, int8_t, int64_t, ldb_d)
- +GEN_VEXT_LD_US(vlh_v_h, int16_t, int16_t, ldh_h)
- +GEN_VEXT_LD_US(vlh_v_w, int16_t, int32_t, ldh_w)
- +GEN_VEXT_LD_US(vlh_v_d, int16_t, int64_t, ldh_d)
- +GEN_VEXT_LD_US(vlw_v_w, int32_t, int32_t, ldw_w)
- +GEN_VEXT_LD_US(vlw_v_d, int32_t, int64_t, ldw_d)
- +GEN_VEXT_LD_US(vle_v_b, int8_t, int8_t, lde_b)
- +GEN_VEXT_LD_US(vle_v_h, int16_t, int16_t, lde_h)
- +GEN_VEXT_LD_US(vle_v_w, int32_t, int32_t, lde_w)
- +GEN_VEXT_LD_US(vle_v_d, int64_t, int64_t, lde_d)
- +GEN_VEXT_LD_US(vlbu_v_b, uint8_t, uint8_t, ldbu_b)
- +GEN_VEXT_LD_US(vlbu_v_h, uint8_t, uint16_t, ldbu_h)
- +GEN_VEXT_LD_US(vlbu_v_w, uint8_t, uint32_t, ldbu_w)
- +GEN_VEXT_LD_US(vlbu_v_d, uint8_t, uint64_t, ldbu_d)
- +GEN_VEXT_LD_US(vlhu_v_h, uint16_t, uint16_t, ldhu_h)
- +GEN_VEXT_LD_US(vlhu_v_w, uint16_t, uint32_t, ldhu_w)
- +GEN_VEXT_LD_US(vlhu_v_d, uint16_t, uint64_t, ldhu_d)
- +GEN_VEXT_LD_US(vlwu_v_w, uint32_t, uint32_t, ldwu_w)
- +GEN_VEXT_LD_US(vlwu_v_d, uint32_t, uint64_t, ldwu_d)
-
- #define GEN_VEXT_ST_US(NAME, MTYPE, ETYPE, STORE_FN) \
- void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \
- @@ -462,14 +399,14 @@ void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base, \
- { \
- uint32_t stride = vext_nf(desc) * sizeof(MTYPE); \
- vext_ldst_stride(vd, v0, base, stride, env, desc, false, STORE_FN, \
- - NULL, sizeof(ETYPE), sizeof(MTYPE), \
- + sizeof(ETYPE), sizeof(MTYPE), \
- GETPC(), MMU_DATA_STORE); \
- } \
- \
- void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - vext_ldst_us(vd, base, env, desc, STORE_FN, NULL, \
- + vext_ldst_us(vd, base, env, desc, STORE_FN, \
- sizeof(ETYPE), sizeof(MTYPE), GETPC(), MMU_DATA_STORE);\
- }
-
- @@ -510,7 +447,6 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
- void *vs2, CPURISCVState *env, uint32_t desc,
- vext_get_index_addr get_index_addr,
- vext_ldst_elem_fn *ldst_elem,
- - clear_fn *clear_elem,
- uint32_t esz, uint32_t msz, uintptr_t ra,
- MMUAccessType access_type)
- {
- @@ -539,52 +475,46 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
- k++;
- }
- }
- - /* clear tail elements */
- - if (clear_elem) {
- - for (k = 0; k < nf; k++) {
- - clear_elem(vd, env->vl + k * vlmax, env->vl * esz, vlmax * esz);
- - }
- - }
- }
-
- -#define GEN_VEXT_LD_INDEX(NAME, MTYPE, ETYPE, INDEX_FN, LOAD_FN, CLEAR_FN) \
- +#define GEN_VEXT_LD_INDEX(NAME, MTYPE, ETYPE, INDEX_FN, LOAD_FN) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
- void *vs2, CPURISCVState *env, uint32_t desc) \
- { \
- vext_ldst_index(vd, v0, base, vs2, env, desc, INDEX_FN, \
- - LOAD_FN, CLEAR_FN, sizeof(ETYPE), sizeof(MTYPE), \
- + LOAD_FN, sizeof(ETYPE), sizeof(MTYPE), \
- GETPC(), MMU_DATA_LOAD); \
- }
-
- -GEN_VEXT_LD_INDEX(vlxb_v_b, int8_t, int8_t, idx_b, ldb_b, clearb)
- -GEN_VEXT_LD_INDEX(vlxb_v_h, int8_t, int16_t, idx_h, ldb_h, clearh)
- -GEN_VEXT_LD_INDEX(vlxb_v_w, int8_t, int32_t, idx_w, ldb_w, clearl)
- -GEN_VEXT_LD_INDEX(vlxb_v_d, int8_t, int64_t, idx_d, ldb_d, clearq)
- -GEN_VEXT_LD_INDEX(vlxh_v_h, int16_t, int16_t, idx_h, ldh_h, clearh)
- -GEN_VEXT_LD_INDEX(vlxh_v_w, int16_t, int32_t, idx_w, ldh_w, clearl)
- -GEN_VEXT_LD_INDEX(vlxh_v_d, int16_t, int64_t, idx_d, ldh_d, clearq)
- -GEN_VEXT_LD_INDEX(vlxw_v_w, int32_t, int32_t, idx_w, ldw_w, clearl)
- -GEN_VEXT_LD_INDEX(vlxw_v_d, int32_t, int64_t, idx_d, ldw_d, clearq)
- -GEN_VEXT_LD_INDEX(vlxe_v_b, int8_t, int8_t, idx_b, lde_b, clearb)
- -GEN_VEXT_LD_INDEX(vlxe_v_h, int16_t, int16_t, idx_h, lde_h, clearh)
- -GEN_VEXT_LD_INDEX(vlxe_v_w, int32_t, int32_t, idx_w, lde_w, clearl)
- -GEN_VEXT_LD_INDEX(vlxe_v_d, int64_t, int64_t, idx_d, lde_d, clearq)
- -GEN_VEXT_LD_INDEX(vlxbu_v_b, uint8_t, uint8_t, idx_b, ldbu_b, clearb)
- -GEN_VEXT_LD_INDEX(vlxbu_v_h, uint8_t, uint16_t, idx_h, ldbu_h, clearh)
- -GEN_VEXT_LD_INDEX(vlxbu_v_w, uint8_t, uint32_t, idx_w, ldbu_w, clearl)
- -GEN_VEXT_LD_INDEX(vlxbu_v_d, uint8_t, uint64_t, idx_d, ldbu_d, clearq)
- -GEN_VEXT_LD_INDEX(vlxhu_v_h, uint16_t, uint16_t, idx_h, ldhu_h, clearh)
- -GEN_VEXT_LD_INDEX(vlxhu_v_w, uint16_t, uint32_t, idx_w, ldhu_w, clearl)
- -GEN_VEXT_LD_INDEX(vlxhu_v_d, uint16_t, uint64_t, idx_d, ldhu_d, clearq)
- -GEN_VEXT_LD_INDEX(vlxwu_v_w, uint32_t, uint32_t, idx_w, ldwu_w, clearl)
- -GEN_VEXT_LD_INDEX(vlxwu_v_d, uint32_t, uint64_t, idx_d, ldwu_d, clearq)
- +GEN_VEXT_LD_INDEX(vlxb_v_b, int8_t, int8_t, idx_b, ldb_b)
- +GEN_VEXT_LD_INDEX(vlxb_v_h, int8_t, int16_t, idx_h, ldb_h)
- +GEN_VEXT_LD_INDEX(vlxb_v_w, int8_t, int32_t, idx_w, ldb_w)
- +GEN_VEXT_LD_INDEX(vlxb_v_d, int8_t, int64_t, idx_d, ldb_d)
- +GEN_VEXT_LD_INDEX(vlxh_v_h, int16_t, int16_t, idx_h, ldh_h)
- +GEN_VEXT_LD_INDEX(vlxh_v_w, int16_t, int32_t, idx_w, ldh_w)
- +GEN_VEXT_LD_INDEX(vlxh_v_d, int16_t, int64_t, idx_d, ldh_d)
- +GEN_VEXT_LD_INDEX(vlxw_v_w, int32_t, int32_t, idx_w, ldw_w)
- +GEN_VEXT_LD_INDEX(vlxw_v_d, int32_t, int64_t, idx_d, ldw_d)
- +GEN_VEXT_LD_INDEX(vlxe_v_b, int8_t, int8_t, idx_b, lde_b)
- +GEN_VEXT_LD_INDEX(vlxe_v_h, int16_t, int16_t, idx_h, lde_h)
- +GEN_VEXT_LD_INDEX(vlxe_v_w, int32_t, int32_t, idx_w, lde_w)
- +GEN_VEXT_LD_INDEX(vlxe_v_d, int64_t, int64_t, idx_d, lde_d)
- +GEN_VEXT_LD_INDEX(vlxbu_v_b, uint8_t, uint8_t, idx_b, ldbu_b)
- +GEN_VEXT_LD_INDEX(vlxbu_v_h, uint8_t, uint16_t, idx_h, ldbu_h)
- +GEN_VEXT_LD_INDEX(vlxbu_v_w, uint8_t, uint32_t, idx_w, ldbu_w)
- +GEN_VEXT_LD_INDEX(vlxbu_v_d, uint8_t, uint64_t, idx_d, ldbu_d)
- +GEN_VEXT_LD_INDEX(vlxhu_v_h, uint16_t, uint16_t, idx_h, ldhu_h)
- +GEN_VEXT_LD_INDEX(vlxhu_v_w, uint16_t, uint32_t, idx_w, ldhu_w)
- +GEN_VEXT_LD_INDEX(vlxhu_v_d, uint16_t, uint64_t, idx_d, ldhu_d)
- +GEN_VEXT_LD_INDEX(vlxwu_v_w, uint32_t, uint32_t, idx_w, ldwu_w)
- +GEN_VEXT_LD_INDEX(vlxwu_v_d, uint32_t, uint64_t, idx_d, ldwu_d)
-
- #define GEN_VEXT_ST_INDEX(NAME, MTYPE, ETYPE, INDEX_FN, STORE_FN)\
- void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
- void *vs2, CPURISCVState *env, uint32_t desc) \
- { \
- vext_ldst_index(vd, v0, base, vs2, env, desc, INDEX_FN, \
- - STORE_FN, NULL, sizeof(ETYPE), sizeof(MTYPE),\
- + STORE_FN, sizeof(ETYPE), sizeof(MTYPE), \
- GETPC(), MMU_DATA_STORE); \
- }
-
- @@ -609,7 +539,6 @@ static inline void
- vext_ldff(void *vd, void *v0, target_ulong base,
- CPURISCVState *env, uint32_t desc,
- vext_ldst_elem_fn *ldst_elem,
- - clear_fn *clear_elem,
- uint32_t esz, uint32_t msz, uintptr_t ra)
- {
- void *host;
- @@ -671,45 +600,38 @@ ProbeSuccess:
- k++;
- }
- }
- - /* clear tail elements */
- - if (vl != 0) {
- - return;
- - }
- - for (k = 0; k < nf; k++) {
- - clear_elem(vd, env->vl + k * vlmax, env->vl * esz, vlmax * esz);
- - }
- }
-
- -#define GEN_VEXT_LDFF(NAME, MTYPE, ETYPE, LOAD_FN, CLEAR_FN) \
- +#define GEN_VEXT_LDFF(NAME, MTYPE, ETYPE, LOAD_FN) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - vext_ldff(vd, v0, base, env, desc, LOAD_FN, CLEAR_FN, \
- + vext_ldff(vd, v0, base, env, desc, LOAD_FN, \
- sizeof(ETYPE), sizeof(MTYPE), GETPC()); \
- }
-
- -GEN_VEXT_LDFF(vlbff_v_b, int8_t, int8_t, ldb_b, clearb)
- -GEN_VEXT_LDFF(vlbff_v_h, int8_t, int16_t, ldb_h, clearh)
- -GEN_VEXT_LDFF(vlbff_v_w, int8_t, int32_t, ldb_w, clearl)
- -GEN_VEXT_LDFF(vlbff_v_d, int8_t, int64_t, ldb_d, clearq)
- -GEN_VEXT_LDFF(vlhff_v_h, int16_t, int16_t, ldh_h, clearh)
- -GEN_VEXT_LDFF(vlhff_v_w, int16_t, int32_t, ldh_w, clearl)
- -GEN_VEXT_LDFF(vlhff_v_d, int16_t, int64_t, ldh_d, clearq)
- -GEN_VEXT_LDFF(vlwff_v_w, int32_t, int32_t, ldw_w, clearl)
- -GEN_VEXT_LDFF(vlwff_v_d, int32_t, int64_t, ldw_d, clearq)
- -GEN_VEXT_LDFF(vleff_v_b, int8_t, int8_t, lde_b, clearb)
- -GEN_VEXT_LDFF(vleff_v_h, int16_t, int16_t, lde_h, clearh)
- -GEN_VEXT_LDFF(vleff_v_w, int32_t, int32_t, lde_w, clearl)
- -GEN_VEXT_LDFF(vleff_v_d, int64_t, int64_t, lde_d, clearq)
- -GEN_VEXT_LDFF(vlbuff_v_b, uint8_t, uint8_t, ldbu_b, clearb)
- -GEN_VEXT_LDFF(vlbuff_v_h, uint8_t, uint16_t, ldbu_h, clearh)
- -GEN_VEXT_LDFF(vlbuff_v_w, uint8_t, uint32_t, ldbu_w, clearl)
- -GEN_VEXT_LDFF(vlbuff_v_d, uint8_t, uint64_t, ldbu_d, clearq)
- -GEN_VEXT_LDFF(vlhuff_v_h, uint16_t, uint16_t, ldhu_h, clearh)
- -GEN_VEXT_LDFF(vlhuff_v_w, uint16_t, uint32_t, ldhu_w, clearl)
- -GEN_VEXT_LDFF(vlhuff_v_d, uint16_t, uint64_t, ldhu_d, clearq)
- -GEN_VEXT_LDFF(vlwuff_v_w, uint32_t, uint32_t, ldwu_w, clearl)
- -GEN_VEXT_LDFF(vlwuff_v_d, uint32_t, uint64_t, ldwu_d, clearq)
- +GEN_VEXT_LDFF(vlbff_v_b, int8_t, int8_t, ldb_b)
- +GEN_VEXT_LDFF(vlbff_v_h, int8_t, int16_t, ldb_h)
- +GEN_VEXT_LDFF(vlbff_v_w, int8_t, int32_t, ldb_w)
- +GEN_VEXT_LDFF(vlbff_v_d, int8_t, int64_t, ldb_d)
- +GEN_VEXT_LDFF(vlhff_v_h, int16_t, int16_t, ldh_h)
- +GEN_VEXT_LDFF(vlhff_v_w, int16_t, int32_t, ldh_w)
- +GEN_VEXT_LDFF(vlhff_v_d, int16_t, int64_t, ldh_d)
- +GEN_VEXT_LDFF(vlwff_v_w, int32_t, int32_t, ldw_w)
- +GEN_VEXT_LDFF(vlwff_v_d, int32_t, int64_t, ldw_d)
- +GEN_VEXT_LDFF(vleff_v_b, int8_t, int8_t, lde_b)
- +GEN_VEXT_LDFF(vleff_v_h, int16_t, int16_t, lde_h)
- +GEN_VEXT_LDFF(vleff_v_w, int32_t, int32_t, lde_w)
- +GEN_VEXT_LDFF(vleff_v_d, int64_t, int64_t, lde_d)
- +GEN_VEXT_LDFF(vlbuff_v_b, uint8_t, uint8_t, ldbu_b)
- +GEN_VEXT_LDFF(vlbuff_v_h, uint8_t, uint16_t, ldbu_h)
- +GEN_VEXT_LDFF(vlbuff_v_w, uint8_t, uint32_t, ldbu_w)
- +GEN_VEXT_LDFF(vlbuff_v_d, uint8_t, uint64_t, ldbu_d)
- +GEN_VEXT_LDFF(vlhuff_v_h, uint16_t, uint16_t, ldhu_h)
- +GEN_VEXT_LDFF(vlhuff_v_w, uint16_t, uint32_t, ldhu_w)
- +GEN_VEXT_LDFF(vlhuff_v_d, uint16_t, uint64_t, ldhu_d)
- +GEN_VEXT_LDFF(vlwuff_v_w, uint32_t, uint32_t, ldwu_w)
- +GEN_VEXT_LDFF(vlwuff_v_d, uint32_t, uint64_t, ldwu_d)
-
- /*
- *** Vector AMO Operations (Zvamo)
- @@ -786,14 +708,12 @@ vext_amo_noatomic(void *vs3, void *v0, target_ulong base,
- void *vs2, CPURISCVState *env, uint32_t desc,
- vext_get_index_addr get_index_addr,
- vext_amo_noatomic_fn *noatomic_op,
- - clear_fn *clear_elem,
- uint32_t esz, uint32_t msz, uintptr_t ra)
- {
- uint32_t i;
- target_long addr;
- uint32_t wd = vext_wd(desc);
- uint32_t vm = vext_vm(desc);
- - uint32_t vlmax = vext_maxsz(desc) / esz;
-
- for (i = 0; i < env->vl; i++) {
- if (!vm && !vext_elem_mask(v0, i)) {
- @@ -809,48 +729,47 @@ vext_amo_noatomic(void *vs3, void *v0, target_ulong base,
- addr = get_index_addr(base, i, vs2);
- noatomic_op(vs3, addr, wd, i, env, ra);
- }
- - clear_elem(vs3, env->vl, env->vl * esz, vlmax * esz);
- }
-
- -#define GEN_VEXT_AMO(NAME, MTYPE, ETYPE, INDEX_FN, CLEAR_FN) \
- +#define GEN_VEXT_AMO(NAME, MTYPE, ETYPE, INDEX_FN) \
- void HELPER(NAME)(void *vs3, void *v0, target_ulong base, \
- void *vs2, CPURISCVState *env, uint32_t desc) \
- { \
- vext_amo_noatomic(vs3, v0, base, vs2, env, desc, \
- INDEX_FN, vext_##NAME##_noatomic_op, \
- - CLEAR_FN, sizeof(ETYPE), sizeof(MTYPE), \
- + sizeof(ETYPE), sizeof(MTYPE), \
- GETPC()); \
- }
-
- #ifdef TARGET_RISCV64
- -GEN_VEXT_AMO(vamoswapw_v_d, int32_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoswapd_v_d, int64_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoaddw_v_d, int32_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoaddd_v_d, int64_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoxorw_v_d, int32_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoxord_v_d, int64_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoandw_v_d, int32_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoandd_v_d, int64_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoorw_v_d, int32_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamoord_v_d, int64_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamominw_v_d, int32_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamomind_v_d, int64_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamomaxw_v_d, int32_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamomaxd_v_d, int64_t, int64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamominuw_v_d, uint32_t, uint64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamominud_v_d, uint64_t, uint64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamomaxuw_v_d, uint32_t, uint64_t, idx_d, clearq)
- -GEN_VEXT_AMO(vamomaxud_v_d, uint64_t, uint64_t, idx_d, clearq)
- +GEN_VEXT_AMO(vamoswapw_v_d, int32_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoswapd_v_d, int64_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoaddw_v_d, int32_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoaddd_v_d, int64_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoxorw_v_d, int32_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoxord_v_d, int64_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoandw_v_d, int32_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoandd_v_d, int64_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoorw_v_d, int32_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamoord_v_d, int64_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamominw_v_d, int32_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamomind_v_d, int64_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamomaxw_v_d, int32_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamomaxd_v_d, int64_t, int64_t, idx_d)
- +GEN_VEXT_AMO(vamominuw_v_d, uint32_t, uint64_t, idx_d)
- +GEN_VEXT_AMO(vamominud_v_d, uint64_t, uint64_t, idx_d)
- +GEN_VEXT_AMO(vamomaxuw_v_d, uint32_t, uint64_t, idx_d)
- +GEN_VEXT_AMO(vamomaxud_v_d, uint64_t, uint64_t, idx_d)
- #endif
- -GEN_VEXT_AMO(vamoswapw_v_w, int32_t, int32_t, idx_w, clearl)
- -GEN_VEXT_AMO(vamoaddw_v_w, int32_t, int32_t, idx_w, clearl)
- -GEN_VEXT_AMO(vamoxorw_v_w, int32_t, int32_t, idx_w, clearl)
- -GEN_VEXT_AMO(vamoandw_v_w, int32_t, int32_t, idx_w, clearl)
- -GEN_VEXT_AMO(vamoorw_v_w, int32_t, int32_t, idx_w, clearl)
- -GEN_VEXT_AMO(vamominw_v_w, int32_t, int32_t, idx_w, clearl)
- -GEN_VEXT_AMO(vamomaxw_v_w, int32_t, int32_t, idx_w, clearl)
- -GEN_VEXT_AMO(vamominuw_v_w, uint32_t, uint32_t, idx_w, clearl)
- -GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl)
- +GEN_VEXT_AMO(vamoswapw_v_w, int32_t, int32_t, idx_w)
- +GEN_VEXT_AMO(vamoaddw_v_w, int32_t, int32_t, idx_w)
- +GEN_VEXT_AMO(vamoxorw_v_w, int32_t, int32_t, idx_w)
- +GEN_VEXT_AMO(vamoandw_v_w, int32_t, int32_t, idx_w)
- +GEN_VEXT_AMO(vamoorw_v_w, int32_t, int32_t, idx_w)
- +GEN_VEXT_AMO(vamominw_v_w, int32_t, int32_t, idx_w)
- +GEN_VEXT_AMO(vamomaxw_v_w, int32_t, int32_t, idx_w)
- +GEN_VEXT_AMO(vamominuw_v_w, uint32_t, uint32_t, idx_w)
- +GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w)
-
- /*
- *** Vector Integer Arithmetic Instructions
- @@ -916,9 +835,8 @@ RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
- static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
- CPURISCVState *env, uint32_t desc,
- uint32_t esz, uint32_t dsz,
- - opivv2_fn *fn, clear_fn *clearfn)
- + opivv2_fn *fn)
- {
- - uint32_t vlmax = vext_maxsz(desc) / esz;
- uint32_t vm = vext_vm(desc);
- uint32_t vl = env->vl;
- uint32_t i;
- @@ -929,27 +847,26 @@ static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
- }
- fn(vd, vs1, vs2, i);
- }
- - clearfn(vd, vl, vl * dsz, vlmax * dsz);
- }
-
- /* generate the helpers for OPIVV */
- -#define GEN_VEXT_VV(NAME, ESZ, DSZ, CLEAR_FN) \
- +#define GEN_VEXT_VV(NAME, ESZ, DSZ) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- void *vs2, CPURISCVState *env, \
- uint32_t desc) \
- { \
- do_vext_vv(vd, v0, vs1, vs2, env, desc, ESZ, DSZ, \
- - do_##NAME, CLEAR_FN); \
- + do_##NAME); \
- }
-
- -GEN_VEXT_VV(vadd_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vadd_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vadd_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vadd_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vsub_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vsub_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vsub_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vsub_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV(vadd_vv_b, 1, 1)
- +GEN_VEXT_VV(vadd_vv_h, 2, 2)
- +GEN_VEXT_VV(vadd_vv_w, 4, 4)
- +GEN_VEXT_VV(vadd_vv_d, 8, 8)
- +GEN_VEXT_VV(vsub_vv_b, 1, 1)
- +GEN_VEXT_VV(vsub_vv_h, 2, 2)
- +GEN_VEXT_VV(vsub_vv_w, 4, 4)
- +GEN_VEXT_VV(vsub_vv_d, 8, 8)
-
- typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
-
- @@ -980,9 +897,8 @@ RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
- static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
- CPURISCVState *env, uint32_t desc,
- uint32_t esz, uint32_t dsz,
- - opivx2_fn fn, clear_fn *clearfn)
- + opivx2_fn fn)
- {
- - uint32_t vlmax = vext_maxsz(desc) / esz;
- uint32_t vm = vext_vm(desc);
- uint32_t vl = env->vl;
- uint32_t i;
- @@ -993,31 +909,30 @@ static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
- }
- fn(vd, s1, vs2, i);
- }
- - clearfn(vd, vl, vl * dsz, vlmax * dsz);
- }
-
- /* generate the helpers for OPIVX */
- -#define GEN_VEXT_VX(NAME, ESZ, DSZ, CLEAR_FN) \
- +#define GEN_VEXT_VX(NAME, ESZ, DSZ) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
- void *vs2, CPURISCVState *env, \
- uint32_t desc) \
- { \
- do_vext_vx(vd, v0, s1, vs2, env, desc, ESZ, DSZ, \
- - do_##NAME, CLEAR_FN); \
- -}
- -
- -GEN_VEXT_VX(vadd_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vadd_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vadd_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vadd_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vsub_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vsub_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vsub_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vsub_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vrsub_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vrsub_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vrsub_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vrsub_vx_d, 8, 8, clearq)
- + do_##NAME); \
- +}
- +
- +GEN_VEXT_VX(vadd_vx_b, 1, 1)
- +GEN_VEXT_VX(vadd_vx_h, 2, 2)
- +GEN_VEXT_VX(vadd_vx_w, 4, 4)
- +GEN_VEXT_VX(vadd_vx_d, 8, 8)
- +GEN_VEXT_VX(vsub_vx_b, 1, 1)
- +GEN_VEXT_VX(vsub_vx_h, 2, 2)
- +GEN_VEXT_VX(vsub_vx_w, 4, 4)
- +GEN_VEXT_VX(vsub_vx_d, 8, 8)
- +GEN_VEXT_VX(vrsub_vx_b, 1, 1)
- +GEN_VEXT_VX(vrsub_vx_h, 2, 2)
- +GEN_VEXT_VX(vrsub_vx_w, 4, 4)
- +GEN_VEXT_VX(vrsub_vx_d, 8, 8)
-
- void HELPER(vec_rsubs8)(void *d, void *a, uint64_t b, uint32_t desc)
- {
- @@ -1096,30 +1011,30 @@ RVVCALL(OPIVV2, vwadd_wv_w, WOP_WSSS_W, H8, H4, H4, DO_ADD)
- RVVCALL(OPIVV2, vwsub_wv_b, WOP_WSSS_B, H2, H1, H1, DO_SUB)
- RVVCALL(OPIVV2, vwsub_wv_h, WOP_WSSS_H, H4, H2, H2, DO_SUB)
- RVVCALL(OPIVV2, vwsub_wv_w, WOP_WSSS_W, H8, H4, H4, DO_SUB)
- -GEN_VEXT_VV(vwaddu_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwaddu_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwaddu_vv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwsubu_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwsubu_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwsubu_vv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwadd_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwadd_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwadd_vv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwsub_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwsub_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwsub_vv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwaddu_wv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwaddu_wv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwaddu_wv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwsubu_wv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwsubu_wv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwsubu_wv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwadd_wv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwadd_wv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwadd_wv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwsub_wv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwsub_wv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwsub_wv_w, 4, 8, clearq)
- +GEN_VEXT_VV(vwaddu_vv_b, 1, 2)
- +GEN_VEXT_VV(vwaddu_vv_h, 2, 4)
- +GEN_VEXT_VV(vwaddu_vv_w, 4, 8)
- +GEN_VEXT_VV(vwsubu_vv_b, 1, 2)
- +GEN_VEXT_VV(vwsubu_vv_h, 2, 4)
- +GEN_VEXT_VV(vwsubu_vv_w, 4, 8)
- +GEN_VEXT_VV(vwadd_vv_b, 1, 2)
- +GEN_VEXT_VV(vwadd_vv_h, 2, 4)
- +GEN_VEXT_VV(vwadd_vv_w, 4, 8)
- +GEN_VEXT_VV(vwsub_vv_b, 1, 2)
- +GEN_VEXT_VV(vwsub_vv_h, 2, 4)
- +GEN_VEXT_VV(vwsub_vv_w, 4, 8)
- +GEN_VEXT_VV(vwaddu_wv_b, 1, 2)
- +GEN_VEXT_VV(vwaddu_wv_h, 2, 4)
- +GEN_VEXT_VV(vwaddu_wv_w, 4, 8)
- +GEN_VEXT_VV(vwsubu_wv_b, 1, 2)
- +GEN_VEXT_VV(vwsubu_wv_h, 2, 4)
- +GEN_VEXT_VV(vwsubu_wv_w, 4, 8)
- +GEN_VEXT_VV(vwadd_wv_b, 1, 2)
- +GEN_VEXT_VV(vwadd_wv_h, 2, 4)
- +GEN_VEXT_VV(vwadd_wv_w, 4, 8)
- +GEN_VEXT_VV(vwsub_wv_b, 1, 2)
- +GEN_VEXT_VV(vwsub_wv_h, 2, 4)
- +GEN_VEXT_VV(vwsub_wv_w, 4, 8)
-
- RVVCALL(OPIVX2, vwaddu_vx_b, WOP_UUU_B, H2, H1, DO_ADD)
- RVVCALL(OPIVX2, vwaddu_vx_h, WOP_UUU_H, H4, H2, DO_ADD)
- @@ -1145,42 +1060,40 @@ RVVCALL(OPIVX2, vwadd_wx_w, WOP_WSSS_W, H8, H4, DO_ADD)
- RVVCALL(OPIVX2, vwsub_wx_b, WOP_WSSS_B, H2, H1, DO_SUB)
- RVVCALL(OPIVX2, vwsub_wx_h, WOP_WSSS_H, H4, H2, DO_SUB)
- RVVCALL(OPIVX2, vwsub_wx_w, WOP_WSSS_W, H8, H4, DO_SUB)
- -GEN_VEXT_VX(vwaddu_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwaddu_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwaddu_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwsubu_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwsubu_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwsubu_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwadd_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwadd_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwadd_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwsub_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwsub_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwsub_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwaddu_wx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwaddu_wx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwaddu_wx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwsubu_wx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwsubu_wx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwsubu_wx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwadd_wx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwadd_wx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwadd_wx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwsub_wx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwsub_wx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwsub_wx_w, 4, 8, clearq)
- +GEN_VEXT_VX(vwaddu_vx_b, 1, 2)
- +GEN_VEXT_VX(vwaddu_vx_h, 2, 4)
- +GEN_VEXT_VX(vwaddu_vx_w, 4, 8)
- +GEN_VEXT_VX(vwsubu_vx_b, 1, 2)
- +GEN_VEXT_VX(vwsubu_vx_h, 2, 4)
- +GEN_VEXT_VX(vwsubu_vx_w, 4, 8)
- +GEN_VEXT_VX(vwadd_vx_b, 1, 2)
- +GEN_VEXT_VX(vwadd_vx_h, 2, 4)
- +GEN_VEXT_VX(vwadd_vx_w, 4, 8)
- +GEN_VEXT_VX(vwsub_vx_b, 1, 2)
- +GEN_VEXT_VX(vwsub_vx_h, 2, 4)
- +GEN_VEXT_VX(vwsub_vx_w, 4, 8)
- +GEN_VEXT_VX(vwaddu_wx_b, 1, 2)
- +GEN_VEXT_VX(vwaddu_wx_h, 2, 4)
- +GEN_VEXT_VX(vwaddu_wx_w, 4, 8)
- +GEN_VEXT_VX(vwsubu_wx_b, 1, 2)
- +GEN_VEXT_VX(vwsubu_wx_h, 2, 4)
- +GEN_VEXT_VX(vwsubu_wx_w, 4, 8)
- +GEN_VEXT_VX(vwadd_wx_b, 1, 2)
- +GEN_VEXT_VX(vwadd_wx_h, 2, 4)
- +GEN_VEXT_VX(vwadd_wx_w, 4, 8)
- +GEN_VEXT_VX(vwsub_wx_b, 1, 2)
- +GEN_VEXT_VX(vwsub_wx_h, 2, 4)
- +GEN_VEXT_VX(vwsub_wx_w, 4, 8)
-
- /* Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions */
- #define DO_VADC(N, M, C) (N + M + C)
- #define DO_VSBC(N, M, C) (N - M - C)
-
- -#define GEN_VEXT_VADC_VVM(NAME, ETYPE, H, DO_OP, CLEAR_FN) \
- +#define GEN_VEXT_VADC_VVM(NAME, ETYPE, H, DO_OP) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(ETYPE); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- uint32_t i; \
- \
- for (i = 0; i < vl; i++) { \
- @@ -1190,26 +1103,23 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
- \
- *((ETYPE *)vd + H(i)) = DO_OP(s2, s1, carry); \
- } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- }
-
- -GEN_VEXT_VADC_VVM(vadc_vvm_b, uint8_t, H1, DO_VADC, clearb)
- -GEN_VEXT_VADC_VVM(vadc_vvm_h, uint16_t, H2, DO_VADC, clearh)
- -GEN_VEXT_VADC_VVM(vadc_vvm_w, uint32_t, H4, DO_VADC, clearl)
- -GEN_VEXT_VADC_VVM(vadc_vvm_d, uint64_t, H8, DO_VADC, clearq)
- +GEN_VEXT_VADC_VVM(vadc_vvm_b, uint8_t, H1, DO_VADC)
- +GEN_VEXT_VADC_VVM(vadc_vvm_h, uint16_t, H2, DO_VADC)
- +GEN_VEXT_VADC_VVM(vadc_vvm_w, uint32_t, H4, DO_VADC)
- +GEN_VEXT_VADC_VVM(vadc_vvm_d, uint64_t, H8, DO_VADC)
-
- -GEN_VEXT_VADC_VVM(vsbc_vvm_b, uint8_t, H1, DO_VSBC, clearb)
- -GEN_VEXT_VADC_VVM(vsbc_vvm_h, uint16_t, H2, DO_VSBC, clearh)
- -GEN_VEXT_VADC_VVM(vsbc_vvm_w, uint32_t, H4, DO_VSBC, clearl)
- -GEN_VEXT_VADC_VVM(vsbc_vvm_d, uint64_t, H8, DO_VSBC, clearq)
- +GEN_VEXT_VADC_VVM(vsbc_vvm_b, uint8_t, H1, DO_VSBC)
- +GEN_VEXT_VADC_VVM(vsbc_vvm_h, uint16_t, H2, DO_VSBC)
- +GEN_VEXT_VADC_VVM(vsbc_vvm_w, uint32_t, H4, DO_VSBC)
- +GEN_VEXT_VADC_VVM(vsbc_vvm_d, uint64_t, H8, DO_VSBC)
-
- -#define GEN_VEXT_VADC_VXM(NAME, ETYPE, H, DO_OP, CLEAR_FN) \
- +#define GEN_VEXT_VADC_VXM(NAME, ETYPE, H, DO_OP) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(ETYPE); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- uint32_t i; \
- \
- for (i = 0; i < vl; i++) { \
- @@ -1218,18 +1128,17 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- \
- *((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\
- } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- }
-
- -GEN_VEXT_VADC_VXM(vadc_vxm_b, uint8_t, H1, DO_VADC, clearb)
- -GEN_VEXT_VADC_VXM(vadc_vxm_h, uint16_t, H2, DO_VADC, clearh)
- -GEN_VEXT_VADC_VXM(vadc_vxm_w, uint32_t, H4, DO_VADC, clearl)
- -GEN_VEXT_VADC_VXM(vadc_vxm_d, uint64_t, H8, DO_VADC, clearq)
- +GEN_VEXT_VADC_VXM(vadc_vxm_b, uint8_t, H1, DO_VADC)
- +GEN_VEXT_VADC_VXM(vadc_vxm_h, uint16_t, H2, DO_VADC)
- +GEN_VEXT_VADC_VXM(vadc_vxm_w, uint32_t, H4, DO_VADC)
- +GEN_VEXT_VADC_VXM(vadc_vxm_d, uint64_t, H8, DO_VADC)
-
- -GEN_VEXT_VADC_VXM(vsbc_vxm_b, uint8_t, H1, DO_VSBC, clearb)
- -GEN_VEXT_VADC_VXM(vsbc_vxm_h, uint16_t, H2, DO_VSBC, clearh)
- -GEN_VEXT_VADC_VXM(vsbc_vxm_w, uint32_t, H4, DO_VSBC, clearl)
- -GEN_VEXT_VADC_VXM(vsbc_vxm_d, uint64_t, H8, DO_VSBC, clearq)
- +GEN_VEXT_VADC_VXM(vsbc_vxm_b, uint8_t, H1, DO_VSBC)
- +GEN_VEXT_VADC_VXM(vsbc_vxm_h, uint16_t, H2, DO_VSBC)
- +GEN_VEXT_VADC_VXM(vsbc_vxm_w, uint32_t, H4, DO_VSBC)
- +GEN_VEXT_VADC_VXM(vsbc_vxm_d, uint64_t, H8, DO_VSBC)
-
- #define DO_MADC(N, M, C) (C ? (__typeof(N))(N + M + 1) <= N : \
- (__typeof(N))(N + M) < N)
- @@ -1308,18 +1217,18 @@ RVVCALL(OPIVV2, vxor_vv_b, OP_SSS_B, H1, H1, H1, DO_XOR)
- RVVCALL(OPIVV2, vxor_vv_h, OP_SSS_H, H2, H2, H2, DO_XOR)
- RVVCALL(OPIVV2, vxor_vv_w, OP_SSS_W, H4, H4, H4, DO_XOR)
- RVVCALL(OPIVV2, vxor_vv_d, OP_SSS_D, H8, H8, H8, DO_XOR)
- -GEN_VEXT_VV(vand_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vand_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vand_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vand_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vor_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vor_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vor_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vor_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vxor_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vxor_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vxor_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vxor_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV(vand_vv_b, 1, 1)
- +GEN_VEXT_VV(vand_vv_h, 2, 2)
- +GEN_VEXT_VV(vand_vv_w, 4, 4)
- +GEN_VEXT_VV(vand_vv_d, 8, 8)
- +GEN_VEXT_VV(vor_vv_b, 1, 1)
- +GEN_VEXT_VV(vor_vv_h, 2, 2)
- +GEN_VEXT_VV(vor_vv_w, 4, 4)
- +GEN_VEXT_VV(vor_vv_d, 8, 8)
- +GEN_VEXT_VV(vxor_vv_b, 1, 1)
- +GEN_VEXT_VV(vxor_vv_h, 2, 2)
- +GEN_VEXT_VV(vxor_vv_w, 4, 4)
- +GEN_VEXT_VV(vxor_vv_d, 8, 8)
-
- RVVCALL(OPIVX2, vand_vx_b, OP_SSS_B, H1, H1, DO_AND)
- RVVCALL(OPIVX2, vand_vx_h, OP_SSS_H, H2, H2, DO_AND)
- @@ -1333,32 +1242,30 @@ RVVCALL(OPIVX2, vxor_vx_b, OP_SSS_B, H1, H1, DO_XOR)
- RVVCALL(OPIVX2, vxor_vx_h, OP_SSS_H, H2, H2, DO_XOR)
- RVVCALL(OPIVX2, vxor_vx_w, OP_SSS_W, H4, H4, DO_XOR)
- RVVCALL(OPIVX2, vxor_vx_d, OP_SSS_D, H8, H8, DO_XOR)
- -GEN_VEXT_VX(vand_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vand_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vand_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vand_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vor_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vor_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vor_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vor_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vxor_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vxor_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vxor_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vxor_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX(vand_vx_b, 1, 1)
- +GEN_VEXT_VX(vand_vx_h, 2, 2)
- +GEN_VEXT_VX(vand_vx_w, 4, 4)
- +GEN_VEXT_VX(vand_vx_d, 8, 8)
- +GEN_VEXT_VX(vor_vx_b, 1, 1)
- +GEN_VEXT_VX(vor_vx_h, 2, 2)
- +GEN_VEXT_VX(vor_vx_w, 4, 4)
- +GEN_VEXT_VX(vor_vx_d, 8, 8)
- +GEN_VEXT_VX(vxor_vx_b, 1, 1)
- +GEN_VEXT_VX(vxor_vx_h, 2, 2)
- +GEN_VEXT_VX(vxor_vx_w, 4, 4)
- +GEN_VEXT_VX(vxor_vx_d, 8, 8)
-
- /* Vector Single-Width Bit Shift Instructions */
- #define DO_SLL(N, M) (N << (M))
- #define DO_SRL(N, M) (N >> (M))
-
- /* generate the helpers for shift instructions with two vector operators */
- -#define GEN_VEXT_SHIFT_VV(NAME, TS1, TS2, HS1, HS2, OP, MASK, CLEAR_FN) \
- +#define GEN_VEXT_SHIFT_VV(NAME, TS1, TS2, HS1, HS2, OP, MASK) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- void *vs2, CPURISCVState *env, uint32_t desc) \
- { \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(TS1); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- uint32_t i; \
- \
- for (i = 0; i < vl; i++) { \
- @@ -1369,73 +1276,69 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- TS2 s2 = *((TS2 *)vs2 + HS2(i)); \
- *((TS1 *)vd + HS1(i)) = OP(s2, s1 & MASK); \
- } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- }
-
- -GEN_VEXT_SHIFT_VV(vsll_vv_b, uint8_t, uint8_t, H1, H1, DO_SLL, 0x7, clearb)
- -GEN_VEXT_SHIFT_VV(vsll_vv_h, uint16_t, uint16_t, H2, H2, DO_SLL, 0xf, clearh)
- -GEN_VEXT_SHIFT_VV(vsll_vv_w, uint32_t, uint32_t, H4, H4, DO_SLL, 0x1f, clearl)
- -GEN_VEXT_SHIFT_VV(vsll_vv_d, uint64_t, uint64_t, H8, H8, DO_SLL, 0x3f, clearq)
- +GEN_VEXT_SHIFT_VV(vsll_vv_b, uint8_t, uint8_t, H1, H1, DO_SLL, 0x7)
- +GEN_VEXT_SHIFT_VV(vsll_vv_h, uint16_t, uint16_t, H2, H2, DO_SLL, 0xf)
- +GEN_VEXT_SHIFT_VV(vsll_vv_w, uint32_t, uint32_t, H4, H4, DO_SLL, 0x1f)
- +GEN_VEXT_SHIFT_VV(vsll_vv_d, uint64_t, uint64_t, H8, H8, DO_SLL, 0x3f)
-
- -GEN_VEXT_SHIFT_VV(vsrl_vv_b, uint8_t, uint8_t, H1, H1, DO_SRL, 0x7, clearb)
- -GEN_VEXT_SHIFT_VV(vsrl_vv_h, uint16_t, uint16_t, H2, H2, DO_SRL, 0xf, clearh)
- -GEN_VEXT_SHIFT_VV(vsrl_vv_w, uint32_t, uint32_t, H4, H4, DO_SRL, 0x1f, clearl)
- -GEN_VEXT_SHIFT_VV(vsrl_vv_d, uint64_t, uint64_t, H8, H8, DO_SRL, 0x3f, clearq)
- +GEN_VEXT_SHIFT_VV(vsrl_vv_b, uint8_t, uint8_t, H1, H1, DO_SRL, 0x7)
- +GEN_VEXT_SHIFT_VV(vsrl_vv_h, uint16_t, uint16_t, H2, H2, DO_SRL, 0xf)
- +GEN_VEXT_SHIFT_VV(vsrl_vv_w, uint32_t, uint32_t, H4, H4, DO_SRL, 0x1f)
- +GEN_VEXT_SHIFT_VV(vsrl_vv_d, uint64_t, uint64_t, H8, H8, DO_SRL, 0x3f)
-
- -GEN_VEXT_SHIFT_VV(vsra_vv_b, uint8_t, int8_t, H1, H1, DO_SRL, 0x7, clearb)
- -GEN_VEXT_SHIFT_VV(vsra_vv_h, uint16_t, int16_t, H2, H2, DO_SRL, 0xf, clearh)
- -GEN_VEXT_SHIFT_VV(vsra_vv_w, uint32_t, int32_t, H4, H4, DO_SRL, 0x1f, clearl)
- -GEN_VEXT_SHIFT_VV(vsra_vv_d, uint64_t, int64_t, H8, H8, DO_SRL, 0x3f, clearq)
- +GEN_VEXT_SHIFT_VV(vsra_vv_b, uint8_t, int8_t, H1, H1, DO_SRL, 0x7)
- +GEN_VEXT_SHIFT_VV(vsra_vv_h, uint16_t, int16_t, H2, H2, DO_SRL, 0xf)
- +GEN_VEXT_SHIFT_VV(vsra_vv_w, uint32_t, int32_t, H4, H4, DO_SRL, 0x1f)
- +GEN_VEXT_SHIFT_VV(vsra_vv_d, uint64_t, int64_t, H8, H8, DO_SRL, 0x3f)
-
- /* generate the helpers for shift instructions with one vector and one scalar */
- -#define GEN_VEXT_SHIFT_VX(NAME, TD, TS2, HD, HS2, OP, MASK, CLEAR_FN) \
- -void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
- - void *vs2, CPURISCVState *env, uint32_t desc) \
- -{ \
- - uint32_t vm = vext_vm(desc); \
- - uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(TD); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- - uint32_t i; \
- - \
- - for (i = 0; i < vl; i++) { \
- - if (!vm && !vext_elem_mask(v0, i)) { \
- - continue; \
- - } \
- - TS2 s2 = *((TS2 *)vs2 + HS2(i)); \
- - *((TD *)vd + HD(i)) = OP(s2, s1 & MASK); \
- - } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- -}
- -
- -GEN_VEXT_SHIFT_VX(vsll_vx_b, uint8_t, int8_t, H1, H1, DO_SLL, 0x7, clearb)
- -GEN_VEXT_SHIFT_VX(vsll_vx_h, uint16_t, int16_t, H2, H2, DO_SLL, 0xf, clearh)
- -GEN_VEXT_SHIFT_VX(vsll_vx_w, uint32_t, int32_t, H4, H4, DO_SLL, 0x1f, clearl)
- -GEN_VEXT_SHIFT_VX(vsll_vx_d, uint64_t, int64_t, H8, H8, DO_SLL, 0x3f, clearq)
- -
- -GEN_VEXT_SHIFT_VX(vsrl_vx_b, uint8_t, uint8_t, H1, H1, DO_SRL, 0x7, clearb)
- -GEN_VEXT_SHIFT_VX(vsrl_vx_h, uint16_t, uint16_t, H2, H2, DO_SRL, 0xf, clearh)
- -GEN_VEXT_SHIFT_VX(vsrl_vx_w, uint32_t, uint32_t, H4, H4, DO_SRL, 0x1f, clearl)
- -GEN_VEXT_SHIFT_VX(vsrl_vx_d, uint64_t, uint64_t, H8, H8, DO_SRL, 0x3f, clearq)
- -
- -GEN_VEXT_SHIFT_VX(vsra_vx_b, int8_t, int8_t, H1, H1, DO_SRL, 0x7, clearb)
- -GEN_VEXT_SHIFT_VX(vsra_vx_h, int16_t, int16_t, H2, H2, DO_SRL, 0xf, clearh)
- -GEN_VEXT_SHIFT_VX(vsra_vx_w, int32_t, int32_t, H4, H4, DO_SRL, 0x1f, clearl)
- -GEN_VEXT_SHIFT_VX(vsra_vx_d, int64_t, int64_t, H8, H8, DO_SRL, 0x3f, clearq)
- +#define GEN_VEXT_SHIFT_VX(NAME, TD, TS2, HD, HS2, OP, MASK) \
- +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
- + void *vs2, CPURISCVState *env, uint32_t desc) \
- +{ \
- + uint32_t vm = vext_vm(desc); \
- + uint32_t vl = env->vl; \
- + uint32_t i; \
- + \
- + for (i = 0; i < vl; i++) { \
- + if (!vm && !vext_elem_mask(v0, i)) { \
- + continue; \
- + } \
- + TS2 s2 = *((TS2 *)vs2 + HS2(i)); \
- + *((TD *)vd + HD(i)) = OP(s2, s1 & MASK); \
- + } \
- +}
- +
- +GEN_VEXT_SHIFT_VX(vsll_vx_b, uint8_t, int8_t, H1, H1, DO_SLL, 0x7)
- +GEN_VEXT_SHIFT_VX(vsll_vx_h, uint16_t, int16_t, H2, H2, DO_SLL, 0xf)
- +GEN_VEXT_SHIFT_VX(vsll_vx_w, uint32_t, int32_t, H4, H4, DO_SLL, 0x1f)
- +GEN_VEXT_SHIFT_VX(vsll_vx_d, uint64_t, int64_t, H8, H8, DO_SLL, 0x3f)
- +
- +GEN_VEXT_SHIFT_VX(vsrl_vx_b, uint8_t, uint8_t, H1, H1, DO_SRL, 0x7)
- +GEN_VEXT_SHIFT_VX(vsrl_vx_h, uint16_t, uint16_t, H2, H2, DO_SRL, 0xf)
- +GEN_VEXT_SHIFT_VX(vsrl_vx_w, uint32_t, uint32_t, H4, H4, DO_SRL, 0x1f)
- +GEN_VEXT_SHIFT_VX(vsrl_vx_d, uint64_t, uint64_t, H8, H8, DO_SRL, 0x3f)
- +
- +GEN_VEXT_SHIFT_VX(vsra_vx_b, int8_t, int8_t, H1, H1, DO_SRL, 0x7)
- +GEN_VEXT_SHIFT_VX(vsra_vx_h, int16_t, int16_t, H2, H2, DO_SRL, 0xf)
- +GEN_VEXT_SHIFT_VX(vsra_vx_w, int32_t, int32_t, H4, H4, DO_SRL, 0x1f)
- +GEN_VEXT_SHIFT_VX(vsra_vx_d, int64_t, int64_t, H8, H8, DO_SRL, 0x3f)
-
- /* Vector Narrowing Integer Right Shift Instructions */
- -GEN_VEXT_SHIFT_VV(vnsrl_vv_b, uint8_t, uint16_t, H1, H2, DO_SRL, 0xf, clearb)
- -GEN_VEXT_SHIFT_VV(vnsrl_vv_h, uint16_t, uint32_t, H2, H4, DO_SRL, 0x1f, clearh)
- -GEN_VEXT_SHIFT_VV(vnsrl_vv_w, uint32_t, uint64_t, H4, H8, DO_SRL, 0x3f, clearl)
- -GEN_VEXT_SHIFT_VV(vnsra_vv_b, uint8_t, int16_t, H1, H2, DO_SRL, 0xf, clearb)
- -GEN_VEXT_SHIFT_VV(vnsra_vv_h, uint16_t, int32_t, H2, H4, DO_SRL, 0x1f, clearh)
- -GEN_VEXT_SHIFT_VV(vnsra_vv_w, uint32_t, int64_t, H4, H8, DO_SRL, 0x3f, clearl)
- -GEN_VEXT_SHIFT_VX(vnsrl_vx_b, uint8_t, uint16_t, H1, H2, DO_SRL, 0xf, clearb)
- -GEN_VEXT_SHIFT_VX(vnsrl_vx_h, uint16_t, uint32_t, H2, H4, DO_SRL, 0x1f, clearh)
- -GEN_VEXT_SHIFT_VX(vnsrl_vx_w, uint32_t, uint64_t, H4, H8, DO_SRL, 0x3f, clearl)
- -GEN_VEXT_SHIFT_VX(vnsra_vx_b, int8_t, int16_t, H1, H2, DO_SRL, 0xf, clearb)
- -GEN_VEXT_SHIFT_VX(vnsra_vx_h, int16_t, int32_t, H2, H4, DO_SRL, 0x1f, clearh)
- -GEN_VEXT_SHIFT_VX(vnsra_vx_w, int32_t, int64_t, H4, H8, DO_SRL, 0x3f, clearl)
- +GEN_VEXT_SHIFT_VV(vnsrl_vv_b, uint8_t, uint16_t, H1, H2, DO_SRL, 0xf)
- +GEN_VEXT_SHIFT_VV(vnsrl_vv_h, uint16_t, uint32_t, H2, H4, DO_SRL, 0x1f)
- +GEN_VEXT_SHIFT_VV(vnsrl_vv_w, uint32_t, uint64_t, H4, H8, DO_SRL, 0x3f)
- +GEN_VEXT_SHIFT_VV(vnsra_vv_b, uint8_t, int16_t, H1, H2, DO_SRL, 0xf)
- +GEN_VEXT_SHIFT_VV(vnsra_vv_h, uint16_t, int32_t, H2, H4, DO_SRL, 0x1f)
- +GEN_VEXT_SHIFT_VV(vnsra_vv_w, uint32_t, int64_t, H4, H8, DO_SRL, 0x3f)
- +GEN_VEXT_SHIFT_VX(vnsrl_vx_b, uint8_t, uint16_t, H1, H2, DO_SRL, 0xf)
- +GEN_VEXT_SHIFT_VX(vnsrl_vx_h, uint16_t, uint32_t, H2, H4, DO_SRL, 0x1f)
- +GEN_VEXT_SHIFT_VX(vnsrl_vx_w, uint32_t, uint64_t, H4, H8, DO_SRL, 0x3f)
- +GEN_VEXT_SHIFT_VX(vnsra_vx_b, int8_t, int16_t, H1, H2, DO_SRL, 0xf)
- +GEN_VEXT_SHIFT_VX(vnsra_vx_h, int16_t, int32_t, H2, H4, DO_SRL, 0x1f)
- +GEN_VEXT_SHIFT_VX(vnsra_vx_w, int32_t, int64_t, H4, H8, DO_SRL, 0x3f)
-
- /* Vector Integer Comparison Instructions */
- #define DO_MSEQ(N, M) (N == M)
- @@ -1575,22 +1478,22 @@ RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX)
- RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX)
- RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX)
- RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX)
- -GEN_VEXT_VV(vminu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vminu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vminu_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vminu_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vmin_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmin_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmin_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmin_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vmaxu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmaxu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmaxu_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmaxu_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vmax_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmax_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmax_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmax_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV(vminu_vv_b, 1, 1)
- +GEN_VEXT_VV(vminu_vv_h, 2, 2)
- +GEN_VEXT_VV(vminu_vv_w, 4, 4)
- +GEN_VEXT_VV(vminu_vv_d, 8, 8)
- +GEN_VEXT_VV(vmin_vv_b, 1, 1)
- +GEN_VEXT_VV(vmin_vv_h, 2, 2)
- +GEN_VEXT_VV(vmin_vv_w, 4, 4)
- +GEN_VEXT_VV(vmin_vv_d, 8, 8)
- +GEN_VEXT_VV(vmaxu_vv_b, 1, 1)
- +GEN_VEXT_VV(vmaxu_vv_h, 2, 2)
- +GEN_VEXT_VV(vmaxu_vv_w, 4, 4)
- +GEN_VEXT_VV(vmaxu_vv_d, 8, 8)
- +GEN_VEXT_VV(vmax_vv_b, 1, 1)
- +GEN_VEXT_VV(vmax_vv_h, 2, 2)
- +GEN_VEXT_VV(vmax_vv_w, 4, 4)
- +GEN_VEXT_VV(vmax_vv_d, 8, 8)
-
- RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN)
- RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN)
- @@ -1608,22 +1511,22 @@ RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
- RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
- RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
- RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
- -GEN_VEXT_VX(vminu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vminu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vminu_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vminu_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vmin_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmin_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmin_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmin_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vmaxu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmaxu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmaxu_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmaxu_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vmax_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmax_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmax_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmax_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX(vminu_vx_b, 1, 1)
- +GEN_VEXT_VX(vminu_vx_h, 2, 2)
- +GEN_VEXT_VX(vminu_vx_w, 4, 4)
- +GEN_VEXT_VX(vminu_vx_d, 8, 8)
- +GEN_VEXT_VX(vmin_vx_b, 1, 1)
- +GEN_VEXT_VX(vmin_vx_h, 2, 2)
- +GEN_VEXT_VX(vmin_vx_w, 4, 4)
- +GEN_VEXT_VX(vmin_vx_d, 8, 8)
- +GEN_VEXT_VX(vmaxu_vx_b, 1, 1)
- +GEN_VEXT_VX(vmaxu_vx_h, 2, 2)
- +GEN_VEXT_VX(vmaxu_vx_w, 4, 4)
- +GEN_VEXT_VX(vmaxu_vx_d, 8, 8)
- +GEN_VEXT_VX(vmax_vx_b, 1, 1)
- +GEN_VEXT_VX(vmax_vx_h, 2, 2)
- +GEN_VEXT_VX(vmax_vx_w, 4, 4)
- +GEN_VEXT_VX(vmax_vx_d, 8, 8)
-
- /* Vector Single-Width Integer Multiply Instructions */
- #define DO_MUL(N, M) (N * M)
- @@ -1631,10 +1534,10 @@ RVVCALL(OPIVV2, vmul_vv_b, OP_SSS_B, H1, H1, H1, DO_MUL)
- RVVCALL(OPIVV2, vmul_vv_h, OP_SSS_H, H2, H2, H2, DO_MUL)
- RVVCALL(OPIVV2, vmul_vv_w, OP_SSS_W, H4, H4, H4, DO_MUL)
- RVVCALL(OPIVV2, vmul_vv_d, OP_SSS_D, H8, H8, H8, DO_MUL)
- -GEN_VEXT_VV(vmul_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmul_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmul_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmul_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV(vmul_vv_b, 1, 1)
- +GEN_VEXT_VV(vmul_vv_h, 2, 2)
- +GEN_VEXT_VV(vmul_vv_w, 4, 4)
- +GEN_VEXT_VV(vmul_vv_d, 8, 8)
-
- static int8_t do_mulh_b(int8_t s2, int8_t s1)
- {
- @@ -1738,18 +1641,18 @@ RVVCALL(OPIVV2, vmulhsu_vv_b, OP_SUS_B, H1, H1, H1, do_mulhsu_b)
- RVVCALL(OPIVV2, vmulhsu_vv_h, OP_SUS_H, H2, H2, H2, do_mulhsu_h)
- RVVCALL(OPIVV2, vmulhsu_vv_w, OP_SUS_W, H4, H4, H4, do_mulhsu_w)
- RVVCALL(OPIVV2, vmulhsu_vv_d, OP_SUS_D, H8, H8, H8, do_mulhsu_d)
- -GEN_VEXT_VV(vmulh_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmulh_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmulh_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmulh_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vmulhu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmulhu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmulhu_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmulhu_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vmulhsu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmulhsu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmulhsu_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmulhsu_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV(vmulh_vv_b, 1, 1)
- +GEN_VEXT_VV(vmulh_vv_h, 2, 2)
- +GEN_VEXT_VV(vmulh_vv_w, 4, 4)
- +GEN_VEXT_VV(vmulh_vv_d, 8, 8)
- +GEN_VEXT_VV(vmulhu_vv_b, 1, 1)
- +GEN_VEXT_VV(vmulhu_vv_h, 2, 2)
- +GEN_VEXT_VV(vmulhu_vv_w, 4, 4)
- +GEN_VEXT_VV(vmulhu_vv_d, 8, 8)
- +GEN_VEXT_VV(vmulhsu_vv_b, 1, 1)
- +GEN_VEXT_VV(vmulhsu_vv_h, 2, 2)
- +GEN_VEXT_VV(vmulhsu_vv_w, 4, 4)
- +GEN_VEXT_VV(vmulhsu_vv_d, 8, 8)
-
- RVVCALL(OPIVX2, vmul_vx_b, OP_SSS_B, H1, H1, DO_MUL)
- RVVCALL(OPIVX2, vmul_vx_h, OP_SSS_H, H2, H2, DO_MUL)
- @@ -1767,22 +1670,22 @@ RVVCALL(OPIVX2, vmulhsu_vx_b, OP_SUS_B, H1, H1, do_mulhsu_b)
- RVVCALL(OPIVX2, vmulhsu_vx_h, OP_SUS_H, H2, H2, do_mulhsu_h)
- RVVCALL(OPIVX2, vmulhsu_vx_w, OP_SUS_W, H4, H4, do_mulhsu_w)
- RVVCALL(OPIVX2, vmulhsu_vx_d, OP_SUS_D, H8, H8, do_mulhsu_d)
- -GEN_VEXT_VX(vmul_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmul_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmul_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmul_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vmulh_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmulh_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmulh_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmulh_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vmulhu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmulhu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmulhu_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmulhu_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vmulhsu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmulhsu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmulhsu_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmulhsu_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX(vmul_vx_b, 1, 1)
- +GEN_VEXT_VX(vmul_vx_h, 2, 2)
- +GEN_VEXT_VX(vmul_vx_w, 4, 4)
- +GEN_VEXT_VX(vmul_vx_d, 8, 8)
- +GEN_VEXT_VX(vmulh_vx_b, 1, 1)
- +GEN_VEXT_VX(vmulh_vx_h, 2, 2)
- +GEN_VEXT_VX(vmulh_vx_w, 4, 4)
- +GEN_VEXT_VX(vmulh_vx_d, 8, 8)
- +GEN_VEXT_VX(vmulhu_vx_b, 1, 1)
- +GEN_VEXT_VX(vmulhu_vx_h, 2, 2)
- +GEN_VEXT_VX(vmulhu_vx_w, 4, 4)
- +GEN_VEXT_VX(vmulhu_vx_d, 8, 8)
- +GEN_VEXT_VX(vmulhsu_vx_b, 1, 1)
- +GEN_VEXT_VX(vmulhsu_vx_h, 2, 2)
- +GEN_VEXT_VX(vmulhsu_vx_w, 4, 4)
- +GEN_VEXT_VX(vmulhsu_vx_d, 8, 8)
-
- /* Vector Integer Divide Instructions */
- #define DO_DIVU(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) : N / M)
- @@ -1808,22 +1711,22 @@ RVVCALL(OPIVV2, vrem_vv_b, OP_SSS_B, H1, H1, H1, DO_REM)
- RVVCALL(OPIVV2, vrem_vv_h, OP_SSS_H, H2, H2, H2, DO_REM)
- RVVCALL(OPIVV2, vrem_vv_w, OP_SSS_W, H4, H4, H4, DO_REM)
- RVVCALL(OPIVV2, vrem_vv_d, OP_SSS_D, H8, H8, H8, DO_REM)
- -GEN_VEXT_VV(vdivu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vdivu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vdivu_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vdivu_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vdiv_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vdiv_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vdiv_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vdiv_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vremu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vremu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vremu_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vremu_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vrem_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vrem_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vrem_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vrem_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV(vdivu_vv_b, 1, 1)
- +GEN_VEXT_VV(vdivu_vv_h, 2, 2)
- +GEN_VEXT_VV(vdivu_vv_w, 4, 4)
- +GEN_VEXT_VV(vdivu_vv_d, 8, 8)
- +GEN_VEXT_VV(vdiv_vv_b, 1, 1)
- +GEN_VEXT_VV(vdiv_vv_h, 2, 2)
- +GEN_VEXT_VV(vdiv_vv_w, 4, 4)
- +GEN_VEXT_VV(vdiv_vv_d, 8, 8)
- +GEN_VEXT_VV(vremu_vv_b, 1, 1)
- +GEN_VEXT_VV(vremu_vv_h, 2, 2)
- +GEN_VEXT_VV(vremu_vv_w, 4, 4)
- +GEN_VEXT_VV(vremu_vv_d, 8, 8)
- +GEN_VEXT_VV(vrem_vv_b, 1, 1)
- +GEN_VEXT_VV(vrem_vv_h, 2, 2)
- +GEN_VEXT_VV(vrem_vv_w, 4, 4)
- +GEN_VEXT_VV(vrem_vv_d, 8, 8)
-
- RVVCALL(OPIVX2, vdivu_vx_b, OP_UUU_B, H1, H1, DO_DIVU)
- RVVCALL(OPIVX2, vdivu_vx_h, OP_UUU_H, H2, H2, DO_DIVU)
- @@ -1841,22 +1744,22 @@ RVVCALL(OPIVX2, vrem_vx_b, OP_SSS_B, H1, H1, DO_REM)
- RVVCALL(OPIVX2, vrem_vx_h, OP_SSS_H, H2, H2, DO_REM)
- RVVCALL(OPIVX2, vrem_vx_w, OP_SSS_W, H4, H4, DO_REM)
- RVVCALL(OPIVX2, vrem_vx_d, OP_SSS_D, H8, H8, DO_REM)
- -GEN_VEXT_VX(vdivu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vdivu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vdivu_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vdivu_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vdiv_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vdiv_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vdiv_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vdiv_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vremu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vremu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vremu_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vremu_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vrem_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vrem_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vrem_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vrem_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX(vdivu_vx_b, 1, 1)
- +GEN_VEXT_VX(vdivu_vx_h, 2, 2)
- +GEN_VEXT_VX(vdivu_vx_w, 4, 4)
- +GEN_VEXT_VX(vdivu_vx_d, 8, 8)
- +GEN_VEXT_VX(vdiv_vx_b, 1, 1)
- +GEN_VEXT_VX(vdiv_vx_h, 2, 2)
- +GEN_VEXT_VX(vdiv_vx_w, 4, 4)
- +GEN_VEXT_VX(vdiv_vx_d, 8, 8)
- +GEN_VEXT_VX(vremu_vx_b, 1, 1)
- +GEN_VEXT_VX(vremu_vx_h, 2, 2)
- +GEN_VEXT_VX(vremu_vx_w, 4, 4)
- +GEN_VEXT_VX(vremu_vx_d, 8, 8)
- +GEN_VEXT_VX(vrem_vx_b, 1, 1)
- +GEN_VEXT_VX(vrem_vx_h, 2, 2)
- +GEN_VEXT_VX(vrem_vx_w, 4, 4)
- +GEN_VEXT_VX(vrem_vx_d, 8, 8)
-
- /* Vector Widening Integer Multiply Instructions */
- RVVCALL(OPIVV2, vwmul_vv_b, WOP_SSS_B, H2, H1, H1, DO_MUL)
- @@ -1868,15 +1771,15 @@ RVVCALL(OPIVV2, vwmulu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MUL)
- RVVCALL(OPIVV2, vwmulsu_vv_b, WOP_SUS_B, H2, H1, H1, DO_MUL)
- RVVCALL(OPIVV2, vwmulsu_vv_h, WOP_SUS_H, H4, H2, H2, DO_MUL)
- RVVCALL(OPIVV2, vwmulsu_vv_w, WOP_SUS_W, H8, H4, H4, DO_MUL)
- -GEN_VEXT_VV(vwmul_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwmul_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwmul_vv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwmulu_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwmulu_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwmulu_vv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwmulsu_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwmulsu_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwmulsu_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV(vwmul_vv_b, 1, 2)
- +GEN_VEXT_VV(vwmul_vv_h, 2, 4)
- +GEN_VEXT_VV(vwmul_vv_w, 4, 8)
- +GEN_VEXT_VV(vwmulu_vv_b, 1, 2)
- +GEN_VEXT_VV(vwmulu_vv_h, 2, 4)
- +GEN_VEXT_VV(vwmulu_vv_w, 4, 8)
- +GEN_VEXT_VV(vwmulsu_vv_b, 1, 2)
- +GEN_VEXT_VV(vwmulsu_vv_h, 2, 4)
- +GEN_VEXT_VV(vwmulsu_vv_w, 4, 8)
-
- RVVCALL(OPIVX2, vwmul_vx_b, WOP_SSS_B, H2, H1, DO_MUL)
- RVVCALL(OPIVX2, vwmul_vx_h, WOP_SSS_H, H4, H2, DO_MUL)
- @@ -1887,15 +1790,15 @@ RVVCALL(OPIVX2, vwmulu_vx_w, WOP_UUU_W, H8, H4, DO_MUL)
- RVVCALL(OPIVX2, vwmulsu_vx_b, WOP_SUS_B, H2, H1, DO_MUL)
- RVVCALL(OPIVX2, vwmulsu_vx_h, WOP_SUS_H, H4, H2, DO_MUL)
- RVVCALL(OPIVX2, vwmulsu_vx_w, WOP_SUS_W, H8, H4, DO_MUL)
- -GEN_VEXT_VX(vwmul_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwmul_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwmul_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwmulu_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwmulu_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwmulu_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwmulsu_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwmulsu_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwmulsu_vx_w, 4, 8, clearq)
- +GEN_VEXT_VX(vwmul_vx_b, 1, 2)
- +GEN_VEXT_VX(vwmul_vx_h, 2, 4)
- +GEN_VEXT_VX(vwmul_vx_w, 4, 8)
- +GEN_VEXT_VX(vwmulu_vx_b, 1, 2)
- +GEN_VEXT_VX(vwmulu_vx_h, 2, 4)
- +GEN_VEXT_VX(vwmulu_vx_w, 4, 8)
- +GEN_VEXT_VX(vwmulsu_vx_b, 1, 2)
- +GEN_VEXT_VX(vwmulsu_vx_h, 2, 4)
- +GEN_VEXT_VX(vwmulsu_vx_w, 4, 8)
-
- /* Vector Single-Width Integer Multiply-Add Instructions */
- #define OPIVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
- @@ -1927,22 +1830,22 @@ RVVCALL(OPIVV3, vnmsub_vv_b, OP_SSS_B, H1, H1, H1, DO_NMSUB)
- RVVCALL(OPIVV3, vnmsub_vv_h, OP_SSS_H, H2, H2, H2, DO_NMSUB)
- RVVCALL(OPIVV3, vnmsub_vv_w, OP_SSS_W, H4, H4, H4, DO_NMSUB)
- RVVCALL(OPIVV3, vnmsub_vv_d, OP_SSS_D, H8, H8, H8, DO_NMSUB)
- -GEN_VEXT_VV(vmacc_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmacc_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmacc_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmacc_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vnmsac_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vnmsac_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vnmsac_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vnmsac_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vmadd_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vmadd_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vmadd_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vmadd_vv_d, 8, 8, clearq)
- -GEN_VEXT_VV(vnmsub_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV(vnmsub_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV(vnmsub_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV(vnmsub_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV(vmacc_vv_b, 1, 1)
- +GEN_VEXT_VV(vmacc_vv_h, 2, 2)
- +GEN_VEXT_VV(vmacc_vv_w, 4, 4)
- +GEN_VEXT_VV(vmacc_vv_d, 8, 8)
- +GEN_VEXT_VV(vnmsac_vv_b, 1, 1)
- +GEN_VEXT_VV(vnmsac_vv_h, 2, 2)
- +GEN_VEXT_VV(vnmsac_vv_w, 4, 4)
- +GEN_VEXT_VV(vnmsac_vv_d, 8, 8)
- +GEN_VEXT_VV(vmadd_vv_b, 1, 1)
- +GEN_VEXT_VV(vmadd_vv_h, 2, 2)
- +GEN_VEXT_VV(vmadd_vv_w, 4, 4)
- +GEN_VEXT_VV(vmadd_vv_d, 8, 8)
- +GEN_VEXT_VV(vnmsub_vv_b, 1, 1)
- +GEN_VEXT_VV(vnmsub_vv_h, 2, 2)
- +GEN_VEXT_VV(vnmsub_vv_w, 4, 4)
- +GEN_VEXT_VV(vnmsub_vv_d, 8, 8)
-
- #define OPIVX3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
- static void do_##NAME(void *vd, target_long s1, void *vs2, int i) \
- @@ -1968,22 +1871,22 @@ RVVCALL(OPIVX3, vnmsub_vx_b, OP_SSS_B, H1, H1, DO_NMSUB)
- RVVCALL(OPIVX3, vnmsub_vx_h, OP_SSS_H, H2, H2, DO_NMSUB)
- RVVCALL(OPIVX3, vnmsub_vx_w, OP_SSS_W, H4, H4, DO_NMSUB)
- RVVCALL(OPIVX3, vnmsub_vx_d, OP_SSS_D, H8, H8, DO_NMSUB)
- -GEN_VEXT_VX(vmacc_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmacc_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmacc_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmacc_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vnmsac_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vnmsac_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vnmsac_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vnmsac_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vmadd_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vmadd_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vmadd_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vmadd_vx_d, 8, 8, clearq)
- -GEN_VEXT_VX(vnmsub_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX(vnmsub_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX(vnmsub_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX(vnmsub_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX(vmacc_vx_b, 1, 1)
- +GEN_VEXT_VX(vmacc_vx_h, 2, 2)
- +GEN_VEXT_VX(vmacc_vx_w, 4, 4)
- +GEN_VEXT_VX(vmacc_vx_d, 8, 8)
- +GEN_VEXT_VX(vnmsac_vx_b, 1, 1)
- +GEN_VEXT_VX(vnmsac_vx_h, 2, 2)
- +GEN_VEXT_VX(vnmsac_vx_w, 4, 4)
- +GEN_VEXT_VX(vnmsac_vx_d, 8, 8)
- +GEN_VEXT_VX(vmadd_vx_b, 1, 1)
- +GEN_VEXT_VX(vmadd_vx_h, 2, 2)
- +GEN_VEXT_VX(vmadd_vx_w, 4, 4)
- +GEN_VEXT_VX(vmadd_vx_d, 8, 8)
- +GEN_VEXT_VX(vnmsub_vx_b, 1, 1)
- +GEN_VEXT_VX(vnmsub_vx_h, 2, 2)
- +GEN_VEXT_VX(vnmsub_vx_w, 4, 4)
- +GEN_VEXT_VX(vnmsub_vx_d, 8, 8)
-
- /* Vector Widening Integer Multiply-Add Instructions */
- RVVCALL(OPIVV3, vwmaccu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MACC)
- @@ -1995,15 +1898,15 @@ RVVCALL(OPIVV3, vwmacc_vv_w, WOP_SSS_W, H8, H4, H4, DO_MACC)
- RVVCALL(OPIVV3, vwmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, DO_MACC)
- RVVCALL(OPIVV3, vwmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, DO_MACC)
- RVVCALL(OPIVV3, vwmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, DO_MACC)
- -GEN_VEXT_VV(vwmaccu_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwmaccu_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwmaccu_vv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwmacc_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwmacc_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwmacc_vv_w, 4, 8, clearq)
- -GEN_VEXT_VV(vwmaccsu_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV(vwmaccsu_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV(vwmaccsu_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV(vwmaccu_vv_b, 1, 2)
- +GEN_VEXT_VV(vwmaccu_vv_h, 2, 4)
- +GEN_VEXT_VV(vwmaccu_vv_w, 4, 8)
- +GEN_VEXT_VV(vwmacc_vv_b, 1, 2)
- +GEN_VEXT_VV(vwmacc_vv_h, 2, 4)
- +GEN_VEXT_VV(vwmacc_vv_w, 4, 8)
- +GEN_VEXT_VV(vwmaccsu_vv_b, 1, 2)
- +GEN_VEXT_VV(vwmaccsu_vv_h, 2, 4)
- +GEN_VEXT_VV(vwmaccsu_vv_w, 4, 8)
-
- RVVCALL(OPIVX3, vwmaccu_vx_b, WOP_UUU_B, H2, H1, DO_MACC)
- RVVCALL(OPIVX3, vwmaccu_vx_h, WOP_UUU_H, H4, H2, DO_MACC)
- @@ -2017,89 +1920,78 @@ RVVCALL(OPIVX3, vwmaccsu_vx_w, WOP_SSU_W, H8, H4, DO_MACC)
- RVVCALL(OPIVX3, vwmaccus_vx_b, WOP_SUS_B, H2, H1, DO_MACC)
- RVVCALL(OPIVX3, vwmaccus_vx_h, WOP_SUS_H, H4, H2, DO_MACC)
- RVVCALL(OPIVX3, vwmaccus_vx_w, WOP_SUS_W, H8, H4, DO_MACC)
- -GEN_VEXT_VX(vwmaccu_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwmaccu_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwmaccu_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwmacc_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwmacc_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwmacc_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwmaccsu_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwmaccsu_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwmaccsu_vx_w, 4, 8, clearq)
- -GEN_VEXT_VX(vwmaccus_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX(vwmaccus_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX(vwmaccus_vx_w, 4, 8, clearq)
- +GEN_VEXT_VX(vwmaccu_vx_b, 1, 2)
- +GEN_VEXT_VX(vwmaccu_vx_h, 2, 4)
- +GEN_VEXT_VX(vwmaccu_vx_w, 4, 8)
- +GEN_VEXT_VX(vwmacc_vx_b, 1, 2)
- +GEN_VEXT_VX(vwmacc_vx_h, 2, 4)
- +GEN_VEXT_VX(vwmacc_vx_w, 4, 8)
- +GEN_VEXT_VX(vwmaccsu_vx_b, 1, 2)
- +GEN_VEXT_VX(vwmaccsu_vx_h, 2, 4)
- +GEN_VEXT_VX(vwmaccsu_vx_w, 4, 8)
- +GEN_VEXT_VX(vwmaccus_vx_b, 1, 2)
- +GEN_VEXT_VX(vwmaccus_vx_h, 2, 4)
- +GEN_VEXT_VX(vwmaccus_vx_w, 4, 8)
-
- /* Vector Integer Merge and Move Instructions */
- -#define GEN_VEXT_VMV_VV(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VMV_VV(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \
- uint32_t desc) \
- { \
- uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(ETYPE); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- uint32_t i; \
- \
- for (i = 0; i < vl; i++) { \
- ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
- *((ETYPE *)vd + H(i)) = s1; \
- } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- }
-
- -GEN_VEXT_VMV_VV(vmv_v_v_b, int8_t, H1, clearb)
- -GEN_VEXT_VMV_VV(vmv_v_v_h, int16_t, H2, clearh)
- -GEN_VEXT_VMV_VV(vmv_v_v_w, int32_t, H4, clearl)
- -GEN_VEXT_VMV_VV(vmv_v_v_d, int64_t, H8, clearq)
- +GEN_VEXT_VMV_VV(vmv_v_v_b, int8_t, H1)
- +GEN_VEXT_VMV_VV(vmv_v_v_h, int16_t, H2)
- +GEN_VEXT_VMV_VV(vmv_v_v_w, int32_t, H4)
- +GEN_VEXT_VMV_VV(vmv_v_v_d, int64_t, H8)
-
- -#define GEN_VEXT_VMV_VX(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VMV_VX(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \
- uint32_t desc) \
- { \
- uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(ETYPE); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- uint32_t i; \
- \
- for (i = 0; i < vl; i++) { \
- *((ETYPE *)vd + H(i)) = (ETYPE)s1; \
- } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- }
-
- -GEN_VEXT_VMV_VX(vmv_v_x_b, int8_t, H1, clearb)
- -GEN_VEXT_VMV_VX(vmv_v_x_h, int16_t, H2, clearh)
- -GEN_VEXT_VMV_VX(vmv_v_x_w, int32_t, H4, clearl)
- -GEN_VEXT_VMV_VX(vmv_v_x_d, int64_t, H8, clearq)
- +GEN_VEXT_VMV_VX(vmv_v_x_b, int8_t, H1)
- +GEN_VEXT_VMV_VX(vmv_v_x_h, int16_t, H2)
- +GEN_VEXT_VMV_VX(vmv_v_x_w, int32_t, H4)
- +GEN_VEXT_VMV_VX(vmv_v_x_d, int64_t, H8)
-
- -#define GEN_VEXT_VMERGE_VV(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VMERGE_VV(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(ETYPE); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- uint32_t i; \
- \
- for (i = 0; i < vl; i++) { \
- ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \
- *((ETYPE *)vd + H(i)) = *(vt + H(i)); \
- } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- }
-
- -GEN_VEXT_VMERGE_VV(vmerge_vvm_b, int8_t, H1, clearb)
- -GEN_VEXT_VMERGE_VV(vmerge_vvm_h, int16_t, H2, clearh)
- -GEN_VEXT_VMERGE_VV(vmerge_vvm_w, int32_t, H4, clearl)
- -GEN_VEXT_VMERGE_VV(vmerge_vvm_d, int64_t, H8, clearq)
- +GEN_VEXT_VMERGE_VV(vmerge_vvm_b, int8_t, H1)
- +GEN_VEXT_VMERGE_VV(vmerge_vvm_h, int16_t, H2)
- +GEN_VEXT_VMERGE_VV(vmerge_vvm_w, int32_t, H4)
- +GEN_VEXT_VMERGE_VV(vmerge_vvm_d, int64_t, H8)
-
- -#define GEN_VEXT_VMERGE_VX(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VMERGE_VX(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
- void *vs2, CPURISCVState *env, uint32_t desc) \
- { \
- uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(ETYPE); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- uint32_t i; \
- \
- for (i = 0; i < vl; i++) { \
- @@ -2108,13 +2000,12 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
- (ETYPE)(target_long)s1); \
- *((ETYPE *)vd + H(i)) = d; \
- } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- }
-
- -GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t, H1, clearb)
- -GEN_VEXT_VMERGE_VX(vmerge_vxm_h, int16_t, H2, clearh)
- -GEN_VEXT_VMERGE_VX(vmerge_vxm_w, int32_t, H4, clearl)
- -GEN_VEXT_VMERGE_VX(vmerge_vxm_d, int64_t, H8, clearq)
- +GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t, H1)
- +GEN_VEXT_VMERGE_VX(vmerge_vxm_h, int16_t, H2)
- +GEN_VEXT_VMERGE_VX(vmerge_vxm_w, int32_t, H4)
- +GEN_VEXT_VMERGE_VX(vmerge_vxm_d, int64_t, H8)
-
- /*
- *** Vector Fixed-Point Arithmetic Instructions
- @@ -2157,9 +2048,8 @@ static inline void
- vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
- CPURISCVState *env,
- uint32_t desc, uint32_t esz, uint32_t dsz,
- - opivv2_rm_fn *fn, clear_fn *clearfn)
- + opivv2_rm_fn *fn)
- {
- - uint32_t vlmax = vext_maxsz(desc) / esz;
- uint32_t vm = vext_vm(desc);
- uint32_t vl = env->vl;
-
- @@ -2181,17 +2071,15 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
- env, vl, vm, 3, fn);
- break;
- }
- -
- - clearfn(vd, vl, vl * dsz, vlmax * dsz);
- }
-
- /* generate helpers for fixed point instructions with OPIVV format */
- -#define GEN_VEXT_VV_RM(NAME, ESZ, DSZ, CLEAR_FN) \
- +#define GEN_VEXT_VV_RM(NAME, ESZ, DSZ) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, ESZ, DSZ, \
- - do_##NAME, CLEAR_FN); \
- + do_##NAME); \
- }
-
- static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
- @@ -2241,10 +2129,10 @@ RVVCALL(OPIVV2_RM, vsaddu_vv_b, OP_UUU_B, H1, H1, H1, saddu8)
- RVVCALL(OPIVV2_RM, vsaddu_vv_h, OP_UUU_H, H2, H2, H2, saddu16)
- RVVCALL(OPIVV2_RM, vsaddu_vv_w, OP_UUU_W, H4, H4, H4, saddu32)
- RVVCALL(OPIVV2_RM, vsaddu_vv_d, OP_UUU_D, H8, H8, H8, saddu64)
- -GEN_VEXT_VV_RM(vsaddu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vsaddu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vsaddu_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vsaddu_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vsaddu_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vsaddu_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vsaddu_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vsaddu_vv_d, 8, 8)
-
- typedef void opivx2_rm_fn(void *vd, target_long s1, void *vs2, int i,
- CPURISCVState *env, int vxrm);
- @@ -2276,9 +2164,8 @@ static inline void
- vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
- CPURISCVState *env,
- uint32_t desc, uint32_t esz, uint32_t dsz,
- - opivx2_rm_fn *fn, clear_fn *clearfn)
- + opivx2_rm_fn *fn)
- {
- - uint32_t vlmax = vext_maxsz(desc) / esz;
- uint32_t vm = vext_vm(desc);
- uint32_t vl = env->vl;
-
- @@ -2300,27 +2187,25 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
- env, vl, vm, 3, fn);
- break;
- }
- -
- - clearfn(vd, vl, vl * dsz, vlmax * dsz);
- }
-
- /* generate helpers for fixed point instructions with OPIVX format */
- -#define GEN_VEXT_VX_RM(NAME, ESZ, DSZ, CLEAR_FN) \
- +#define GEN_VEXT_VX_RM(NAME, ESZ, DSZ) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \
- void *vs2, CPURISCVState *env, uint32_t desc) \
- { \
- vext_vx_rm_2(vd, v0, s1, vs2, env, desc, ESZ, DSZ, \
- - do_##NAME, CLEAR_FN); \
- + do_##NAME); \
- }
-
- RVVCALL(OPIVX2_RM, vsaddu_vx_b, OP_UUU_B, H1, H1, saddu8)
- RVVCALL(OPIVX2_RM, vsaddu_vx_h, OP_UUU_H, H2, H2, saddu16)
- RVVCALL(OPIVX2_RM, vsaddu_vx_w, OP_UUU_W, H4, H4, saddu32)
- RVVCALL(OPIVX2_RM, vsaddu_vx_d, OP_UUU_D, H8, H8, saddu64)
- -GEN_VEXT_VX_RM(vsaddu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vsaddu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vsaddu_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vsaddu_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vsaddu_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vsaddu_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vsaddu_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vsaddu_vx_d, 8, 8)
-
- static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
- {
- @@ -2366,19 +2251,19 @@ RVVCALL(OPIVV2_RM, vsadd_vv_b, OP_SSS_B, H1, H1, H1, sadd8)
- RVVCALL(OPIVV2_RM, vsadd_vv_h, OP_SSS_H, H2, H2, H2, sadd16)
- RVVCALL(OPIVV2_RM, vsadd_vv_w, OP_SSS_W, H4, H4, H4, sadd32)
- RVVCALL(OPIVV2_RM, vsadd_vv_d, OP_SSS_D, H8, H8, H8, sadd64)
- -GEN_VEXT_VV_RM(vsadd_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vsadd_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vsadd_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vsadd_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vsadd_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vsadd_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vsadd_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vsadd_vv_d, 8, 8)
-
- RVVCALL(OPIVX2_RM, vsadd_vx_b, OP_SSS_B, H1, H1, sadd8)
- RVVCALL(OPIVX2_RM, vsadd_vx_h, OP_SSS_H, H2, H2, sadd16)
- RVVCALL(OPIVX2_RM, vsadd_vx_w, OP_SSS_W, H4, H4, sadd32)
- RVVCALL(OPIVX2_RM, vsadd_vx_d, OP_SSS_D, H8, H8, sadd64)
- -GEN_VEXT_VX_RM(vsadd_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vsadd_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vsadd_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vsadd_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vsadd_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vsadd_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vsadd_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vsadd_vx_d, 8, 8)
-
- static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
- {
- @@ -2427,19 +2312,19 @@ RVVCALL(OPIVV2_RM, vssubu_vv_b, OP_UUU_B, H1, H1, H1, ssubu8)
- RVVCALL(OPIVV2_RM, vssubu_vv_h, OP_UUU_H, H2, H2, H2, ssubu16)
- RVVCALL(OPIVV2_RM, vssubu_vv_w, OP_UUU_W, H4, H4, H4, ssubu32)
- RVVCALL(OPIVV2_RM, vssubu_vv_d, OP_UUU_D, H8, H8, H8, ssubu64)
- -GEN_VEXT_VV_RM(vssubu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vssubu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vssubu_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vssubu_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vssubu_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vssubu_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vssubu_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vssubu_vv_d, 8, 8)
-
- RVVCALL(OPIVX2_RM, vssubu_vx_b, OP_UUU_B, H1, H1, ssubu8)
- RVVCALL(OPIVX2_RM, vssubu_vx_h, OP_UUU_H, H2, H2, ssubu16)
- RVVCALL(OPIVX2_RM, vssubu_vx_w, OP_UUU_W, H4, H4, ssubu32)
- RVVCALL(OPIVX2_RM, vssubu_vx_d, OP_UUU_D, H8, H8, ssubu64)
- -GEN_VEXT_VX_RM(vssubu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vssubu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vssubu_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vssubu_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vssubu_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vssubu_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vssubu_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vssubu_vx_d, 8, 8)
-
- static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
- {
- @@ -2485,19 +2370,19 @@ RVVCALL(OPIVV2_RM, vssub_vv_b, OP_SSS_B, H1, H1, H1, ssub8)
- RVVCALL(OPIVV2_RM, vssub_vv_h, OP_SSS_H, H2, H2, H2, ssub16)
- RVVCALL(OPIVV2_RM, vssub_vv_w, OP_SSS_W, H4, H4, H4, ssub32)
- RVVCALL(OPIVV2_RM, vssub_vv_d, OP_SSS_D, H8, H8, H8, ssub64)
- -GEN_VEXT_VV_RM(vssub_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vssub_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vssub_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vssub_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vssub_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vssub_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vssub_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vssub_vv_d, 8, 8)
-
- RVVCALL(OPIVX2_RM, vssub_vx_b, OP_SSS_B, H1, H1, ssub8)
- RVVCALL(OPIVX2_RM, vssub_vx_h, OP_SSS_H, H2, H2, ssub16)
- RVVCALL(OPIVX2_RM, vssub_vx_w, OP_SSS_W, H4, H4, ssub32)
- RVVCALL(OPIVX2_RM, vssub_vx_d, OP_SSS_D, H8, H8, ssub64)
- -GEN_VEXT_VX_RM(vssub_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vssub_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vssub_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vssub_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vssub_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vssub_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vssub_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vssub_vx_d, 8, 8)
-
- /* Vector Single-Width Averaging Add and Subtract */
- static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
- @@ -2549,19 +2434,19 @@ RVVCALL(OPIVV2_RM, vaadd_vv_b, OP_SSS_B, H1, H1, H1, aadd32)
- RVVCALL(OPIVV2_RM, vaadd_vv_h, OP_SSS_H, H2, H2, H2, aadd32)
- RVVCALL(OPIVV2_RM, vaadd_vv_w, OP_SSS_W, H4, H4, H4, aadd32)
- RVVCALL(OPIVV2_RM, vaadd_vv_d, OP_SSS_D, H8, H8, H8, aadd64)
- -GEN_VEXT_VV_RM(vaadd_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vaadd_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vaadd_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vaadd_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vaadd_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vaadd_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vaadd_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vaadd_vv_d, 8, 8)
-
- RVVCALL(OPIVX2_RM, vaadd_vx_b, OP_SSS_B, H1, H1, aadd32)
- RVVCALL(OPIVX2_RM, vaadd_vx_h, OP_SSS_H, H2, H2, aadd32)
- RVVCALL(OPIVX2_RM, vaadd_vx_w, OP_SSS_W, H4, H4, aadd32)
- RVVCALL(OPIVX2_RM, vaadd_vx_d, OP_SSS_D, H8, H8, aadd64)
- -GEN_VEXT_VX_RM(vaadd_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vaadd_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vaadd_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vaadd_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vaadd_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vaadd_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vaadd_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vaadd_vx_d, 8, 8)
-
- static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
- {
- @@ -2585,19 +2470,19 @@ RVVCALL(OPIVV2_RM, vasub_vv_b, OP_SSS_B, H1, H1, H1, asub32)
- RVVCALL(OPIVV2_RM, vasub_vv_h, OP_SSS_H, H2, H2, H2, asub32)
- RVVCALL(OPIVV2_RM, vasub_vv_w, OP_SSS_W, H4, H4, H4, asub32)
- RVVCALL(OPIVV2_RM, vasub_vv_d, OP_SSS_D, H8, H8, H8, asub64)
- -GEN_VEXT_VV_RM(vasub_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vasub_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vasub_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vasub_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vasub_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vasub_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vasub_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vasub_vv_d, 8, 8)
-
- RVVCALL(OPIVX2_RM, vasub_vx_b, OP_SSS_B, H1, H1, asub32)
- RVVCALL(OPIVX2_RM, vasub_vx_h, OP_SSS_H, H2, H2, asub32)
- RVVCALL(OPIVX2_RM, vasub_vx_w, OP_SSS_W, H4, H4, asub32)
- RVVCALL(OPIVX2_RM, vasub_vx_d, OP_SSS_D, H8, H8, asub64)
- -GEN_VEXT_VX_RM(vasub_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vasub_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vasub_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vasub_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vasub_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vasub_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vasub_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vasub_vx_d, 8, 8)
-
- /* Vector Single-Width Fractional Multiply with Rounding and Saturation */
- static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
- @@ -2692,19 +2577,19 @@ RVVCALL(OPIVV2_RM, vsmul_vv_b, OP_SSS_B, H1, H1, H1, vsmul8)
- RVVCALL(OPIVV2_RM, vsmul_vv_h, OP_SSS_H, H2, H2, H2, vsmul16)
- RVVCALL(OPIVV2_RM, vsmul_vv_w, OP_SSS_W, H4, H4, H4, vsmul32)
- RVVCALL(OPIVV2_RM, vsmul_vv_d, OP_SSS_D, H8, H8, H8, vsmul64)
- -GEN_VEXT_VV_RM(vsmul_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vsmul_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vsmul_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vsmul_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vsmul_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vsmul_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vsmul_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vsmul_vv_d, 8, 8)
-
- RVVCALL(OPIVX2_RM, vsmul_vx_b, OP_SSS_B, H1, H1, vsmul8)
- RVVCALL(OPIVX2_RM, vsmul_vx_h, OP_SSS_H, H2, H2, vsmul16)
- RVVCALL(OPIVX2_RM, vsmul_vx_w, OP_SSS_W, H4, H4, vsmul32)
- RVVCALL(OPIVX2_RM, vsmul_vx_d, OP_SSS_D, H8, H8, vsmul64)
- -GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8)
-
- /* Vector Widening Saturating Scaled Multiply-Add */
- static inline uint16_t
- @@ -2757,9 +2642,9 @@ do_##NAME(void *vd, void *vs1, void *vs2, int i, \
- RVVCALL(OPIVV3_RM, vwsmaccu_vv_b, WOP_UUU_B, H2, H1, H1, vwsmaccu8)
- RVVCALL(OPIVV3_RM, vwsmaccu_vv_h, WOP_UUU_H, H4, H2, H2, vwsmaccu16)
- RVVCALL(OPIVV3_RM, vwsmaccu_vv_w, WOP_UUU_W, H8, H4, H4, vwsmaccu32)
- -GEN_VEXT_VV_RM(vwsmaccu_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV_RM(vwsmaccu_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_RM(vwsmaccu_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_RM(vwsmaccu_vv_b, 1, 2)
- +GEN_VEXT_VV_RM(vwsmaccu_vv_h, 2, 4)
- +GEN_VEXT_VV_RM(vwsmaccu_vv_w, 4, 8)
-
- #define OPIVX3_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
- static inline void \
- @@ -2774,9 +2659,9 @@ do_##NAME(void *vd, target_long s1, void *vs2, int i, \
- RVVCALL(OPIVX3_RM, vwsmaccu_vx_b, WOP_UUU_B, H2, H1, vwsmaccu8)
- RVVCALL(OPIVX3_RM, vwsmaccu_vx_h, WOP_UUU_H, H4, H2, vwsmaccu16)
- RVVCALL(OPIVX3_RM, vwsmaccu_vx_w, WOP_UUU_W, H8, H4, vwsmaccu32)
- -GEN_VEXT_VX_RM(vwsmaccu_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX_RM(vwsmaccu_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX_RM(vwsmaccu_vx_w, 4, 8, clearq)
- +GEN_VEXT_VX_RM(vwsmaccu_vx_b, 1, 2)
- +GEN_VEXT_VX_RM(vwsmaccu_vx_h, 2, 4)
- +GEN_VEXT_VX_RM(vwsmaccu_vx_w, 4, 8)
-
- static inline int16_t
- vwsmacc8(CPURISCVState *env, int vxrm, int8_t a, int8_t b, int16_t c)
- @@ -2815,15 +2700,15 @@ vwsmacc32(CPURISCVState *env, int vxrm, int32_t a, int32_t b, int64_t c)
- RVVCALL(OPIVV3_RM, vwsmacc_vv_b, WOP_SSS_B, H2, H1, H1, vwsmacc8)
- RVVCALL(OPIVV3_RM, vwsmacc_vv_h, WOP_SSS_H, H4, H2, H2, vwsmacc16)
- RVVCALL(OPIVV3_RM, vwsmacc_vv_w, WOP_SSS_W, H8, H4, H4, vwsmacc32)
- -GEN_VEXT_VV_RM(vwsmacc_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV_RM(vwsmacc_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_RM(vwsmacc_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_RM(vwsmacc_vv_b, 1, 2)
- +GEN_VEXT_VV_RM(vwsmacc_vv_h, 2, 4)
- +GEN_VEXT_VV_RM(vwsmacc_vv_w, 4, 8)
- RVVCALL(OPIVX3_RM, vwsmacc_vx_b, WOP_SSS_B, H2, H1, vwsmacc8)
- RVVCALL(OPIVX3_RM, vwsmacc_vx_h, WOP_SSS_H, H4, H2, vwsmacc16)
- RVVCALL(OPIVX3_RM, vwsmacc_vx_w, WOP_SSS_W, H8, H4, vwsmacc32)
- -GEN_VEXT_VX_RM(vwsmacc_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX_RM(vwsmacc_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX_RM(vwsmacc_vx_w, 4, 8, clearq)
- +GEN_VEXT_VX_RM(vwsmacc_vx_b, 1, 2)
- +GEN_VEXT_VX_RM(vwsmacc_vx_h, 2, 4)
- +GEN_VEXT_VX_RM(vwsmacc_vx_w, 4, 8)
-
- static inline int16_t
- vwsmaccsu8(CPURISCVState *env, int vxrm, uint8_t a, int8_t b, int16_t c)
- @@ -2861,15 +2746,15 @@ vwsmaccsu32(CPURISCVState *env, int vxrm, uint32_t a, int32_t b, int64_t c)
- RVVCALL(OPIVV3_RM, vwsmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, vwsmaccsu8)
- RVVCALL(OPIVV3_RM, vwsmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, vwsmaccsu16)
- RVVCALL(OPIVV3_RM, vwsmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, vwsmaccsu32)
- -GEN_VEXT_VV_RM(vwsmaccsu_vv_b, 1, 2, clearh)
- -GEN_VEXT_VV_RM(vwsmaccsu_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_RM(vwsmaccsu_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_RM(vwsmaccsu_vv_b, 1, 2)
- +GEN_VEXT_VV_RM(vwsmaccsu_vv_h, 2, 4)
- +GEN_VEXT_VV_RM(vwsmaccsu_vv_w, 4, 8)
- RVVCALL(OPIVX3_RM, vwsmaccsu_vx_b, WOP_SSU_B, H2, H1, vwsmaccsu8)
- RVVCALL(OPIVX3_RM, vwsmaccsu_vx_h, WOP_SSU_H, H4, H2, vwsmaccsu16)
- RVVCALL(OPIVX3_RM, vwsmaccsu_vx_w, WOP_SSU_W, H8, H4, vwsmaccsu32)
- -GEN_VEXT_VX_RM(vwsmaccsu_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX_RM(vwsmaccsu_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX_RM(vwsmaccsu_vx_w, 4, 8, clearq)
- +GEN_VEXT_VX_RM(vwsmaccsu_vx_b, 1, 2)
- +GEN_VEXT_VX_RM(vwsmaccsu_vx_h, 2, 4)
- +GEN_VEXT_VX_RM(vwsmaccsu_vx_w, 4, 8)
-
- static inline int16_t
- vwsmaccus8(CPURISCVState *env, int vxrm, int8_t a, uint8_t b, int16_t c)
- @@ -2907,9 +2792,9 @@ vwsmaccus32(CPURISCVState *env, int vxrm, int32_t a, uint32_t b, int64_t c)
- RVVCALL(OPIVX3_RM, vwsmaccus_vx_b, WOP_SUS_B, H2, H1, vwsmaccus8)
- RVVCALL(OPIVX3_RM, vwsmaccus_vx_h, WOP_SUS_H, H4, H2, vwsmaccus16)
- RVVCALL(OPIVX3_RM, vwsmaccus_vx_w, WOP_SUS_W, H8, H4, vwsmaccus32)
- -GEN_VEXT_VX_RM(vwsmaccus_vx_b, 1, 2, clearh)
- -GEN_VEXT_VX_RM(vwsmaccus_vx_h, 2, 4, clearl)
- -GEN_VEXT_VX_RM(vwsmaccus_vx_w, 4, 8, clearq)
- +GEN_VEXT_VX_RM(vwsmaccus_vx_b, 1, 2)
- +GEN_VEXT_VX_RM(vwsmaccus_vx_h, 2, 4)
- +GEN_VEXT_VX_RM(vwsmaccus_vx_w, 4, 8)
-
- /* Vector Single-Width Scaling Shift Instructions */
- static inline uint8_t
- @@ -2956,19 +2841,19 @@ RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8)
- RVVCALL(OPIVV2_RM, vssrl_vv_h, OP_UUU_H, H2, H2, H2, vssrl16)
- RVVCALL(OPIVV2_RM, vssrl_vv_w, OP_UUU_W, H4, H4, H4, vssrl32)
- RVVCALL(OPIVV2_RM, vssrl_vv_d, OP_UUU_D, H8, H8, H8, vssrl64)
- -GEN_VEXT_VV_RM(vssrl_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vssrl_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vssrl_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vssrl_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vssrl_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vssrl_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vssrl_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vssrl_vv_d, 8, 8)
-
- RVVCALL(OPIVX2_RM, vssrl_vx_b, OP_UUU_B, H1, H1, vssrl8)
- RVVCALL(OPIVX2_RM, vssrl_vx_h, OP_UUU_H, H2, H2, vssrl16)
- RVVCALL(OPIVX2_RM, vssrl_vx_w, OP_UUU_W, H4, H4, vssrl32)
- RVVCALL(OPIVX2_RM, vssrl_vx_d, OP_UUU_D, H8, H8, vssrl64)
- -GEN_VEXT_VX_RM(vssrl_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vssrl_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vssrl_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vssrl_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vssrl_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vssrl_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vssrl_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vssrl_vx_d, 8, 8)
-
- static inline int8_t
- vssra8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
- @@ -3015,19 +2900,19 @@ RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
- RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
- RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
- RVVCALL(OPIVV2_RM, vssra_vv_d, OP_SSS_D, H8, H8, H8, vssra64)
- -GEN_VEXT_VV_RM(vssra_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vssra_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vssra_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_RM(vssra_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_RM(vssra_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vssra_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vssra_vv_w, 4, 4)
- +GEN_VEXT_VV_RM(vssra_vv_d, 8, 8)
-
- RVVCALL(OPIVX2_RM, vssra_vx_b, OP_SSS_B, H1, H1, vssra8)
- RVVCALL(OPIVX2_RM, vssra_vx_h, OP_SSS_H, H2, H2, vssra16)
- RVVCALL(OPIVX2_RM, vssra_vx_w, OP_SSS_W, H4, H4, vssra32)
- RVVCALL(OPIVX2_RM, vssra_vx_d, OP_SSS_D, H8, H8, vssra64)
- -GEN_VEXT_VX_RM(vssra_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vssra_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vssra_vx_w, 4, 4, clearl)
- -GEN_VEXT_VX_RM(vssra_vx_d, 8, 8, clearq)
- +GEN_VEXT_VX_RM(vssra_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vssra_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vssra_vx_w, 4, 4)
- +GEN_VEXT_VX_RM(vssra_vx_d, 8, 8)
-
- /* Vector Narrowing Fixed-Point Clip Instructions */
- static inline int8_t
- @@ -3090,16 +2975,16 @@ vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
- RVVCALL(OPIVV2_RM, vnclip_vv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
- RVVCALL(OPIVV2_RM, vnclip_vv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
- RVVCALL(OPIVV2_RM, vnclip_vv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
- -GEN_VEXT_VV_RM(vnclip_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vnclip_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vnclip_vv_w, 4, 4, clearl)
- +GEN_VEXT_VV_RM(vnclip_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vnclip_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vnclip_vv_w, 4, 4)
-
- RVVCALL(OPIVX2_RM, vnclip_vx_b, NOP_SSS_B, H1, H2, vnclip8)
- RVVCALL(OPIVX2_RM, vnclip_vx_h, NOP_SSS_H, H2, H4, vnclip16)
- RVVCALL(OPIVX2_RM, vnclip_vx_w, NOP_SSS_W, H4, H8, vnclip32)
- -GEN_VEXT_VX_RM(vnclip_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vnclip_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vnclip_vx_w, 4, 4, clearl)
- +GEN_VEXT_VX_RM(vnclip_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vnclip_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vnclip_vx_w, 4, 4)
-
- static inline uint8_t
- vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
- @@ -3152,16 +3037,16 @@ vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
- RVVCALL(OPIVV2_RM, vnclipu_vv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
- RVVCALL(OPIVV2_RM, vnclipu_vv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
- RVVCALL(OPIVV2_RM, vnclipu_vv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
- -GEN_VEXT_VV_RM(vnclipu_vv_b, 1, 1, clearb)
- -GEN_VEXT_VV_RM(vnclipu_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_RM(vnclipu_vv_w, 4, 4, clearl)
- +GEN_VEXT_VV_RM(vnclipu_vv_b, 1, 1)
- +GEN_VEXT_VV_RM(vnclipu_vv_h, 2, 2)
- +GEN_VEXT_VV_RM(vnclipu_vv_w, 4, 4)
-
- RVVCALL(OPIVX2_RM, vnclipu_vx_b, NOP_UUU_B, H1, H2, vnclipu8)
- RVVCALL(OPIVX2_RM, vnclipu_vx_h, NOP_UUU_H, H2, H4, vnclipu16)
- RVVCALL(OPIVX2_RM, vnclipu_vx_w, NOP_UUU_W, H4, H8, vnclipu32)
- -GEN_VEXT_VX_RM(vnclipu_vx_b, 1, 1, clearb)
- -GEN_VEXT_VX_RM(vnclipu_vx_h, 2, 2, clearh)
- -GEN_VEXT_VX_RM(vnclipu_vx_w, 4, 4, clearl)
- +GEN_VEXT_VX_RM(vnclipu_vx_b, 1, 1)
- +GEN_VEXT_VX_RM(vnclipu_vx_h, 2, 2)
- +GEN_VEXT_VX_RM(vnclipu_vx_w, 4, 4)
-
- /*
- *** Vector Float Point Arithmetic Instructions
- @@ -3176,12 +3061,11 @@ static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \
- *((TD *)vd + HD(i)) = OP(s2, s1, &env->fp_status); \
- }
-
- -#define GEN_VEXT_VV_ENV(NAME, ESZ, DSZ, CLEAR_FN) \
- +#define GEN_VEXT_VV_ENV(NAME, ESZ, DSZ) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- void *vs2, CPURISCVState *env, \
- uint32_t desc) \
- { \
- - uint32_t vlmax = vext_maxsz(desc) / ESZ; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t i; \
- @@ -3192,15 +3076,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- } \
- do_##NAME(vd, vs1, vs2, i, env); \
- } \
- - CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \
- }
-
- RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add)
- RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add)
- RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add)
- -GEN_VEXT_VV_ENV(vfadd_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfadd_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfadd_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfadd_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfadd_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfadd_vv_d, 8, 8)
-
- #define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
- static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
- @@ -3210,12 +3093,11 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
- *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, &env->fp_status);\
- }
-
- -#define GEN_VEXT_VF(NAME, ESZ, DSZ, CLEAR_FN) \
- +#define GEN_VEXT_VF(NAME, ESZ, DSZ) \
- void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
- void *vs2, CPURISCVState *env, \
- uint32_t desc) \
- { \
- - uint32_t vlmax = vext_maxsz(desc) / ESZ; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t i; \
- @@ -3226,28 +3108,27 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \
- } \
- do_##NAME(vd, s1, vs2, i, env); \
- } \
- - CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \
- }
-
- RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add)
- RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add)
- RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add)
- -GEN_VEXT_VF(vfadd_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfadd_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfadd_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfadd_vf_h, 2, 2)
- +GEN_VEXT_VF(vfadd_vf_w, 4, 4)
- +GEN_VEXT_VF(vfadd_vf_d, 8, 8)
-
- RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub)
- RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub)
- RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub)
- -GEN_VEXT_VV_ENV(vfsub_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfsub_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfsub_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfsub_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfsub_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfsub_vv_d, 8, 8)
- RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub)
- RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub)
- RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub)
- -GEN_VEXT_VF(vfsub_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfsub_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfsub_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfsub_vf_h, 2, 2)
- +GEN_VEXT_VF(vfsub_vf_w, 4, 4)
- +GEN_VEXT_VF(vfsub_vf_d, 8, 8)
-
- static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s)
- {
- @@ -3267,9 +3148,9 @@ static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s)
- RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub)
- RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub)
- RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub)
- -GEN_VEXT_VF(vfrsub_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfrsub_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfrsub_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfrsub_vf_h, 2, 2)
- +GEN_VEXT_VF(vfrsub_vf_w, 4, 4)
- +GEN_VEXT_VF(vfrsub_vf_d, 8, 8)
-
- /* Vector Widening Floating-Point Add/Subtract Instructions */
- static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
- @@ -3287,12 +3168,12 @@ static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
-
- RVVCALL(OPFVV2, vfwadd_vv_h, WOP_UUU_H, H4, H2, H2, vfwadd16)
- RVVCALL(OPFVV2, vfwadd_vv_w, WOP_UUU_W, H8, H4, H4, vfwadd32)
- -GEN_VEXT_VV_ENV(vfwadd_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwadd_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwadd_vv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwadd_vv_w, 4, 8)
- RVVCALL(OPFVF2, vfwadd_vf_h, WOP_UUU_H, H4, H2, vfwadd16)
- RVVCALL(OPFVF2, vfwadd_vf_w, WOP_UUU_W, H8, H4, vfwadd32)
- -GEN_VEXT_VF(vfwadd_vf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwadd_vf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwadd_vf_h, 2, 4)
- +GEN_VEXT_VF(vfwadd_vf_w, 4, 8)
-
- static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
- {
- @@ -3309,12 +3190,12 @@ static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
-
- RVVCALL(OPFVV2, vfwsub_vv_h, WOP_UUU_H, H4, H2, H2, vfwsub16)
- RVVCALL(OPFVV2, vfwsub_vv_w, WOP_UUU_W, H8, H4, H4, vfwsub32)
- -GEN_VEXT_VV_ENV(vfwsub_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwsub_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwsub_vv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwsub_vv_w, 4, 8)
- RVVCALL(OPFVF2, vfwsub_vf_h, WOP_UUU_H, H4, H2, vfwsub16)
- RVVCALL(OPFVF2, vfwsub_vf_w, WOP_UUU_W, H8, H4, vfwsub32)
- -GEN_VEXT_VF(vfwsub_vf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwsub_vf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwsub_vf_h, 2, 4)
- +GEN_VEXT_VF(vfwsub_vf_w, 4, 8)
-
- static uint32_t vfwaddw16(uint32_t a, uint16_t b, float_status *s)
- {
- @@ -3328,12 +3209,12 @@ static uint64_t vfwaddw32(uint64_t a, uint32_t b, float_status *s)
-
- RVVCALL(OPFVV2, vfwadd_wv_h, WOP_WUUU_H, H4, H2, H2, vfwaddw16)
- RVVCALL(OPFVV2, vfwadd_wv_w, WOP_WUUU_W, H8, H4, H4, vfwaddw32)
- -GEN_VEXT_VV_ENV(vfwadd_wv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwadd_wv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwadd_wv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwadd_wv_w, 4, 8)
- RVVCALL(OPFVF2, vfwadd_wf_h, WOP_WUUU_H, H4, H2, vfwaddw16)
- RVVCALL(OPFVF2, vfwadd_wf_w, WOP_WUUU_W, H8, H4, vfwaddw32)
- -GEN_VEXT_VF(vfwadd_wf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwadd_wf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwadd_wf_h, 2, 4)
- +GEN_VEXT_VF(vfwadd_wf_w, 4, 8)
-
- static uint32_t vfwsubw16(uint32_t a, uint16_t b, float_status *s)
- {
- @@ -3347,39 +3228,39 @@ static uint64_t vfwsubw32(uint64_t a, uint32_t b, float_status *s)
-
- RVVCALL(OPFVV2, vfwsub_wv_h, WOP_WUUU_H, H4, H2, H2, vfwsubw16)
- RVVCALL(OPFVV2, vfwsub_wv_w, WOP_WUUU_W, H8, H4, H4, vfwsubw32)
- -GEN_VEXT_VV_ENV(vfwsub_wv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwsub_wv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwsub_wv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwsub_wv_w, 4, 8)
- RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, vfwsubw16)
- RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
- -GEN_VEXT_VF(vfwsub_wf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwsub_wf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwsub_wf_h, 2, 4)
- +GEN_VEXT_VF(vfwsub_wf_w, 4, 8)
-
- /* Vector Single-Width Floating-Point Multiply/Divide Instructions */
- RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul)
- RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul)
- RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul)
- -GEN_VEXT_VV_ENV(vfmul_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfmul_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfmul_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfmul_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfmul_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfmul_vv_d, 8, 8)
- RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul)
- RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul)
- RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul)
- -GEN_VEXT_VF(vfmul_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfmul_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfmul_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfmul_vf_h, 2, 2)
- +GEN_VEXT_VF(vfmul_vf_w, 4, 4)
- +GEN_VEXT_VF(vfmul_vf_d, 8, 8)
-
- RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div)
- RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div)
- RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div)
- -GEN_VEXT_VV_ENV(vfdiv_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfdiv_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfdiv_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfdiv_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfdiv_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfdiv_vv_d, 8, 8)
- RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div)
- RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div)
- RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div)
- -GEN_VEXT_VF(vfdiv_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfdiv_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfdiv_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfdiv_vf_h, 2, 2)
- +GEN_VEXT_VF(vfdiv_vf_w, 4, 4)
- +GEN_VEXT_VF(vfdiv_vf_d, 8, 8)
-
- static uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s)
- {
- @@ -3399,9 +3280,9 @@ static uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s)
- RVVCALL(OPFVF2, vfrdiv_vf_h, OP_UUU_H, H2, H2, float16_rdiv)
- RVVCALL(OPFVF2, vfrdiv_vf_w, OP_UUU_W, H4, H4, float32_rdiv)
- RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv)
- -GEN_VEXT_VF(vfrdiv_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfrdiv_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfrdiv_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfrdiv_vf_h, 2, 2)
- +GEN_VEXT_VF(vfrdiv_vf_w, 4, 4)
- +GEN_VEXT_VF(vfrdiv_vf_d, 8, 8)
-
- /* Vector Widening Floating-Point Multiply */
- static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
- @@ -3418,12 +3299,12 @@ static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
- }
- RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
- RVVCALL(OPFVV2, vfwmul_vv_w, WOP_UUU_W, H8, H4, H4, vfwmul32)
- -GEN_VEXT_VV_ENV(vfwmul_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwmul_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwmul_vv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwmul_vv_w, 4, 8)
- RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16)
- RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32)
- -GEN_VEXT_VF(vfwmul_vf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwmul_vf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwmul_vf_h, 2, 4)
- +GEN_VEXT_VF(vfwmul_vf_w, 4, 8)
-
- /* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */
- #define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \
- @@ -3454,9 +3335,9 @@ static uint64_t fmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
- RVVCALL(OPFVV3, vfmacc_vv_h, OP_UUU_H, H2, H2, H2, fmacc16)
- RVVCALL(OPFVV3, vfmacc_vv_w, OP_UUU_W, H4, H4, H4, fmacc32)
- RVVCALL(OPFVV3, vfmacc_vv_d, OP_UUU_D, H8, H8, H8, fmacc64)
- -GEN_VEXT_VV_ENV(vfmacc_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfmacc_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfmacc_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfmacc_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfmacc_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfmacc_vv_d, 8, 8)
-
- #define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \
- static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
- @@ -3470,9 +3351,9 @@ static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \
- RVVCALL(OPFVF3, vfmacc_vf_h, OP_UUU_H, H2, H2, fmacc16)
- RVVCALL(OPFVF3, vfmacc_vf_w, OP_UUU_W, H4, H4, fmacc32)
- RVVCALL(OPFVF3, vfmacc_vf_d, OP_UUU_D, H8, H8, fmacc64)
- -GEN_VEXT_VF(vfmacc_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfmacc_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfmacc_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfmacc_vf_h, 2, 2)
- +GEN_VEXT_VF(vfmacc_vf_w, 4, 4)
- +GEN_VEXT_VF(vfmacc_vf_d, 8, 8)
-
- static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
- {
- @@ -3495,15 +3376,15 @@ static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
- RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16)
- RVVCALL(OPFVV3, vfnmacc_vv_w, OP_UUU_W, H4, H4, H4, fnmacc32)
- RVVCALL(OPFVV3, vfnmacc_vv_d, OP_UUU_D, H8, H8, H8, fnmacc64)
- -GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8, 8)
- RVVCALL(OPFVF3, vfnmacc_vf_h, OP_UUU_H, H2, H2, fnmacc16)
- RVVCALL(OPFVF3, vfnmacc_vf_w, OP_UUU_W, H4, H4, fnmacc32)
- RVVCALL(OPFVF3, vfnmacc_vf_d, OP_UUU_D, H8, H8, fnmacc64)
- -GEN_VEXT_VF(vfnmacc_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfnmacc_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfnmacc_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfnmacc_vf_h, 2, 2)
- +GEN_VEXT_VF(vfnmacc_vf_w, 4, 4)
- +GEN_VEXT_VF(vfnmacc_vf_d, 8, 8)
-
- static uint16_t fmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
- {
- @@ -3523,15 +3404,15 @@ static uint64_t fmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
- RVVCALL(OPFVV3, vfmsac_vv_h, OP_UUU_H, H2, H2, H2, fmsac16)
- RVVCALL(OPFVV3, vfmsac_vv_w, OP_UUU_W, H4, H4, H4, fmsac32)
- RVVCALL(OPFVV3, vfmsac_vv_d, OP_UUU_D, H8, H8, H8, fmsac64)
- -GEN_VEXT_VV_ENV(vfmsac_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfmsac_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfmsac_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfmsac_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfmsac_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfmsac_vv_d, 8, 8)
- RVVCALL(OPFVF3, vfmsac_vf_h, OP_UUU_H, H2, H2, fmsac16)
- RVVCALL(OPFVF3, vfmsac_vf_w, OP_UUU_W, H4, H4, fmsac32)
- RVVCALL(OPFVF3, vfmsac_vf_d, OP_UUU_D, H8, H8, fmsac64)
- -GEN_VEXT_VF(vfmsac_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfmsac_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfmsac_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfmsac_vf_h, 2, 2)
- +GEN_VEXT_VF(vfmsac_vf_w, 4, 4)
- +GEN_VEXT_VF(vfmsac_vf_d, 8, 8)
-
- static uint16_t fnmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
- {
- @@ -3551,15 +3432,15 @@ static uint64_t fnmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
- RVVCALL(OPFVV3, vfnmsac_vv_h, OP_UUU_H, H2, H2, H2, fnmsac16)
- RVVCALL(OPFVV3, vfnmsac_vv_w, OP_UUU_W, H4, H4, H4, fnmsac32)
- RVVCALL(OPFVV3, vfnmsac_vv_d, OP_UUU_D, H8, H8, H8, fnmsac64)
- -GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8, 8)
- RVVCALL(OPFVF3, vfnmsac_vf_h, OP_UUU_H, H2, H2, fnmsac16)
- RVVCALL(OPFVF3, vfnmsac_vf_w, OP_UUU_W, H4, H4, fnmsac32)
- RVVCALL(OPFVF3, vfnmsac_vf_d, OP_UUU_D, H8, H8, fnmsac64)
- -GEN_VEXT_VF(vfnmsac_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfnmsac_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfnmsac_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfnmsac_vf_h, 2, 2)
- +GEN_VEXT_VF(vfnmsac_vf_w, 4, 4)
- +GEN_VEXT_VF(vfnmsac_vf_d, 8, 8)
-
- static uint16_t fmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
- {
- @@ -3579,15 +3460,15 @@ static uint64_t fmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
- RVVCALL(OPFVV3, vfmadd_vv_h, OP_UUU_H, H2, H2, H2, fmadd16)
- RVVCALL(OPFVV3, vfmadd_vv_w, OP_UUU_W, H4, H4, H4, fmadd32)
- RVVCALL(OPFVV3, vfmadd_vv_d, OP_UUU_D, H8, H8, H8, fmadd64)
- -GEN_VEXT_VV_ENV(vfmadd_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfmadd_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfmadd_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfmadd_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfmadd_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfmadd_vv_d, 8, 8)
- RVVCALL(OPFVF3, vfmadd_vf_h, OP_UUU_H, H2, H2, fmadd16)
- RVVCALL(OPFVF3, vfmadd_vf_w, OP_UUU_W, H4, H4, fmadd32)
- RVVCALL(OPFVF3, vfmadd_vf_d, OP_UUU_D, H8, H8, fmadd64)
- -GEN_VEXT_VF(vfmadd_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfmadd_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfmadd_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfmadd_vf_h, 2, 2)
- +GEN_VEXT_VF(vfmadd_vf_w, 4, 4)
- +GEN_VEXT_VF(vfmadd_vf_d, 8, 8)
-
- static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
- {
- @@ -3610,15 +3491,15 @@ static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
- RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16)
- RVVCALL(OPFVV3, vfnmadd_vv_w, OP_UUU_W, H4, H4, H4, fnmadd32)
- RVVCALL(OPFVV3, vfnmadd_vv_d, OP_UUU_D, H8, H8, H8, fnmadd64)
- -GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8, 8)
- RVVCALL(OPFVF3, vfnmadd_vf_h, OP_UUU_H, H2, H2, fnmadd16)
- RVVCALL(OPFVF3, vfnmadd_vf_w, OP_UUU_W, H4, H4, fnmadd32)
- RVVCALL(OPFVF3, vfnmadd_vf_d, OP_UUU_D, H8, H8, fnmadd64)
- -GEN_VEXT_VF(vfnmadd_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfnmadd_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfnmadd_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfnmadd_vf_h, 2, 2)
- +GEN_VEXT_VF(vfnmadd_vf_w, 4, 4)
- +GEN_VEXT_VF(vfnmadd_vf_d, 8, 8)
-
- static uint16_t fmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
- {
- @@ -3638,15 +3519,15 @@ static uint64_t fmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
- RVVCALL(OPFVV3, vfmsub_vv_h, OP_UUU_H, H2, H2, H2, fmsub16)
- RVVCALL(OPFVV3, vfmsub_vv_w, OP_UUU_W, H4, H4, H4, fmsub32)
- RVVCALL(OPFVV3, vfmsub_vv_d, OP_UUU_D, H8, H8, H8, fmsub64)
- -GEN_VEXT_VV_ENV(vfmsub_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfmsub_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfmsub_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfmsub_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfmsub_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfmsub_vv_d, 8, 8)
- RVVCALL(OPFVF3, vfmsub_vf_h, OP_UUU_H, H2, H2, fmsub16)
- RVVCALL(OPFVF3, vfmsub_vf_w, OP_UUU_W, H4, H4, fmsub32)
- RVVCALL(OPFVF3, vfmsub_vf_d, OP_UUU_D, H8, H8, fmsub64)
- -GEN_VEXT_VF(vfmsub_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfmsub_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfmsub_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfmsub_vf_h, 2, 2)
- +GEN_VEXT_VF(vfmsub_vf_w, 4, 4)
- +GEN_VEXT_VF(vfmsub_vf_d, 8, 8)
-
- static uint16_t fnmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
- {
- @@ -3666,15 +3547,15 @@ static uint64_t fnmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
- RVVCALL(OPFVV3, vfnmsub_vv_h, OP_UUU_H, H2, H2, H2, fnmsub16)
- RVVCALL(OPFVV3, vfnmsub_vv_w, OP_UUU_W, H4, H4, H4, fnmsub32)
- RVVCALL(OPFVV3, vfnmsub_vv_d, OP_UUU_D, H8, H8, H8, fnmsub64)
- -GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8, 8)
- RVVCALL(OPFVF3, vfnmsub_vf_h, OP_UUU_H, H2, H2, fnmsub16)
- RVVCALL(OPFVF3, vfnmsub_vf_w, OP_UUU_W, H4, H4, fnmsub32)
- RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
- -GEN_VEXT_VF(vfnmsub_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfnmsub_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfnmsub_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfnmsub_vf_h, 2, 2)
- +GEN_VEXT_VF(vfnmsub_vf_w, 4, 4)
- +GEN_VEXT_VF(vfnmsub_vf_d, 8, 8)
-
- /* Vector Widening Floating-Point Fused Multiply-Add Instructions */
- static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
- @@ -3691,12 +3572,12 @@ static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
-
- RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
- RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
- -GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8)
- RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
- RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
- -GEN_VEXT_VF(vfwmacc_vf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwmacc_vf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwmacc_vf_h, 2, 4)
- +GEN_VEXT_VF(vfwmacc_vf_w, 4, 8)
-
- static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
- {
- @@ -3714,12 +3595,12 @@ static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
-
- RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
- RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32)
- -GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 4, 8)
- RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16)
- RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32)
- -GEN_VEXT_VF(vfwnmacc_vf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwnmacc_vf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwnmacc_vf_h, 2, 4)
- +GEN_VEXT_VF(vfwnmacc_vf_w, 4, 8)
-
- static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
- {
- @@ -3737,12 +3618,12 @@ static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
-
- RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
- RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32)
- -GEN_VEXT_VV_ENV(vfwmsac_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwmsac_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwmsac_vv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwmsac_vv_w, 4, 8)
- RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16)
- RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32)
- -GEN_VEXT_VF(vfwmsac_vf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwmsac_vf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwmsac_vf_h, 2, 4)
- +GEN_VEXT_VF(vfwmsac_vf_w, 4, 8)
-
- static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
- {
- @@ -3760,12 +3641,12 @@ static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
-
- RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
- RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32)
- -GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 2, 4, clearl)
- -GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 4, 8, clearq)
- +GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 2, 4)
- +GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 4, 8)
- RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
- RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
- -GEN_VEXT_VF(vfwnmsac_vf_h, 2, 4, clearl)
- -GEN_VEXT_VF(vfwnmsac_vf_w, 4, 8, clearq)
- +GEN_VEXT_VF(vfwnmsac_vf_h, 2, 4)
- +GEN_VEXT_VF(vfwnmsac_vf_w, 4, 8)
-
- /* Vector Floating-Point Square-Root Instruction */
- /* (TD, T2, TX2) */
- @@ -3781,11 +3662,10 @@ static void do_##NAME(void *vd, void *vs2, int i, \
- *((TD *)vd + HD(i)) = OP(s2, &env->fp_status); \
- }
-
- -#define GEN_VEXT_V_ENV(NAME, ESZ, DSZ, CLEAR_FN) \
- +#define GEN_VEXT_V_ENV(NAME, ESZ, DSZ) \
- void HELPER(NAME)(void *vd, void *v0, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - uint32_t vlmax = vext_maxsz(desc) / ESZ; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t i; \
- @@ -3799,42 +3679,41 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
- } \
- do_##NAME(vd, vs2, i, env); \
- } \
- - CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \
- }
-
- RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt)
- RVVCALL(OPFVV1, vfsqrt_v_w, OP_UU_W, H4, H4, float32_sqrt)
- RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt)
- -GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4, clearl)
- -GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8, clearq)
- +GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4)
- +GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8)
-
- /* Vector Floating-Point MIN/MAX Instructions */
- RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minnum)
- RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minnum)
- RVVCALL(OPFVV2, vfmin_vv_d, OP_UUU_D, H8, H8, H8, float64_minnum)
- -GEN_VEXT_VV_ENV(vfmin_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfmin_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfmin_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfmin_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfmin_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfmin_vv_d, 8, 8)
- RVVCALL(OPFVF2, vfmin_vf_h, OP_UUU_H, H2, H2, float16_minnum)
- RVVCALL(OPFVF2, vfmin_vf_w, OP_UUU_W, H4, H4, float32_minnum)
- RVVCALL(OPFVF2, vfmin_vf_d, OP_UUU_D, H8, H8, float64_minnum)
- -GEN_VEXT_VF(vfmin_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfmin_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfmin_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfmin_vf_h, 2, 2)
- +GEN_VEXT_VF(vfmin_vf_w, 4, 4)
- +GEN_VEXT_VF(vfmin_vf_d, 8, 8)
-
- RVVCALL(OPFVV2, vfmax_vv_h, OP_UUU_H, H2, H2, H2, float16_maxnum)
- RVVCALL(OPFVV2, vfmax_vv_w, OP_UUU_W, H4, H4, H4, float32_maxnum)
- RVVCALL(OPFVV2, vfmax_vv_d, OP_UUU_D, H8, H8, H8, float64_maxnum)
- -GEN_VEXT_VV_ENV(vfmax_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfmax_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfmax_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfmax_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfmax_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfmax_vv_d, 8, 8)
- RVVCALL(OPFVF2, vfmax_vf_h, OP_UUU_H, H2, H2, float16_maxnum)
- RVVCALL(OPFVF2, vfmax_vf_w, OP_UUU_W, H4, H4, float32_maxnum)
- RVVCALL(OPFVF2, vfmax_vf_d, OP_UUU_D, H8, H8, float64_maxnum)
- -GEN_VEXT_VF(vfmax_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfmax_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfmax_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfmax_vf_h, 2, 2)
- +GEN_VEXT_VF(vfmax_vf_w, 4, 4)
- +GEN_VEXT_VF(vfmax_vf_d, 8, 8)
-
- /* Vector Floating-Point Sign-Injection Instructions */
- static uint16_t fsgnj16(uint16_t a, uint16_t b, float_status *s)
- @@ -3855,15 +3734,15 @@ static uint64_t fsgnj64(uint64_t a, uint64_t b, float_status *s)
- RVVCALL(OPFVV2, vfsgnj_vv_h, OP_UUU_H, H2, H2, H2, fsgnj16)
- RVVCALL(OPFVV2, vfsgnj_vv_w, OP_UUU_W, H4, H4, H4, fsgnj32)
- RVVCALL(OPFVV2, vfsgnj_vv_d, OP_UUU_D, H8, H8, H8, fsgnj64)
- -GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfsgnj_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfsgnj_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfsgnj_vv_d, 8, 8)
- RVVCALL(OPFVF2, vfsgnj_vf_h, OP_UUU_H, H2, H2, fsgnj16)
- RVVCALL(OPFVF2, vfsgnj_vf_w, OP_UUU_W, H4, H4, fsgnj32)
- RVVCALL(OPFVF2, vfsgnj_vf_d, OP_UUU_D, H8, H8, fsgnj64)
- -GEN_VEXT_VF(vfsgnj_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfsgnj_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfsgnj_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfsgnj_vf_h, 2, 2)
- +GEN_VEXT_VF(vfsgnj_vf_w, 4, 4)
- +GEN_VEXT_VF(vfsgnj_vf_d, 8, 8)
-
- static uint16_t fsgnjn16(uint16_t a, uint16_t b, float_status *s)
- {
- @@ -3883,15 +3762,15 @@ static uint64_t fsgnjn64(uint64_t a, uint64_t b, float_status *s)
- RVVCALL(OPFVV2, vfsgnjn_vv_h, OP_UUU_H, H2, H2, H2, fsgnjn16)
- RVVCALL(OPFVV2, vfsgnjn_vv_w, OP_UUU_W, H4, H4, H4, fsgnjn32)
- RVVCALL(OPFVV2, vfsgnjn_vv_d, OP_UUU_D, H8, H8, H8, fsgnjn64)
- -GEN_VEXT_VV_ENV(vfsgnjn_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfsgnjn_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfsgnjn_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfsgnjn_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfsgnjn_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfsgnjn_vv_d, 8, 8)
- RVVCALL(OPFVF2, vfsgnjn_vf_h, OP_UUU_H, H2, H2, fsgnjn16)
- RVVCALL(OPFVF2, vfsgnjn_vf_w, OP_UUU_W, H4, H4, fsgnjn32)
- RVVCALL(OPFVF2, vfsgnjn_vf_d, OP_UUU_D, H8, H8, fsgnjn64)
- -GEN_VEXT_VF(vfsgnjn_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfsgnjn_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfsgnjn_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfsgnjn_vf_h, 2, 2)
- +GEN_VEXT_VF(vfsgnjn_vf_w, 4, 4)
- +GEN_VEXT_VF(vfsgnjn_vf_d, 8, 8)
-
- static uint16_t fsgnjx16(uint16_t a, uint16_t b, float_status *s)
- {
- @@ -3911,15 +3790,15 @@ static uint64_t fsgnjx64(uint64_t a, uint64_t b, float_status *s)
- RVVCALL(OPFVV2, vfsgnjx_vv_h, OP_UUU_H, H2, H2, H2, fsgnjx16)
- RVVCALL(OPFVV2, vfsgnjx_vv_w, OP_UUU_W, H4, H4, H4, fsgnjx32)
- RVVCALL(OPFVV2, vfsgnjx_vv_d, OP_UUU_D, H8, H8, H8, fsgnjx64)
- -GEN_VEXT_VV_ENV(vfsgnjx_vv_h, 2, 2, clearh)
- -GEN_VEXT_VV_ENV(vfsgnjx_vv_w, 4, 4, clearl)
- -GEN_VEXT_VV_ENV(vfsgnjx_vv_d, 8, 8, clearq)
- +GEN_VEXT_VV_ENV(vfsgnjx_vv_h, 2, 2)
- +GEN_VEXT_VV_ENV(vfsgnjx_vv_w, 4, 4)
- +GEN_VEXT_VV_ENV(vfsgnjx_vv_d, 8, 8)
- RVVCALL(OPFVF2, vfsgnjx_vf_h, OP_UUU_H, H2, H2, fsgnjx16)
- RVVCALL(OPFVF2, vfsgnjx_vf_w, OP_UUU_W, H4, H4, fsgnjx32)
- RVVCALL(OPFVF2, vfsgnjx_vf_d, OP_UUU_D, H8, H8, fsgnjx64)
- -GEN_VEXT_VF(vfsgnjx_vf_h, 2, 2, clearh)
- -GEN_VEXT_VF(vfsgnjx_vf_w, 4, 4, clearl)
- -GEN_VEXT_VF(vfsgnjx_vf_d, 8, 8, clearq)
- +GEN_VEXT_VF(vfsgnjx_vf_h, 2, 2)
- +GEN_VEXT_VF(vfsgnjx_vf_w, 4, 4)
- +GEN_VEXT_VF(vfsgnjx_vf_d, 8, 8)
-
- /* Vector Floating-Point Compare Instructions */
- #define GEN_VEXT_CMP_VV_ENV(NAME, ETYPE, H, DO_OP) \
- @@ -4076,11 +3955,10 @@ static void do_##NAME(void *vd, void *vs2, int i) \
- *((TD *)vd + HD(i)) = OP(s2); \
- }
-
- -#define GEN_VEXT_V(NAME, ESZ, DSZ, CLEAR_FN) \
- +#define GEN_VEXT_V(NAME, ESZ, DSZ) \
- void HELPER(NAME)(void *vd, void *v0, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - uint32_t vlmax = vext_maxsz(desc) / ESZ; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t i; \
- @@ -4091,7 +3969,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \
- } \
- do_##NAME(vd, vs2, i); \
- } \
- - CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \
- }
-
- target_ulong fclass_h(uint64_t frs1)
- @@ -4154,19 +4031,17 @@ target_ulong fclass_d(uint64_t frs1)
- RVVCALL(OPIVV1, vfclass_v_h, OP_UU_H, H2, H2, fclass_h)
- RVVCALL(OPIVV1, vfclass_v_w, OP_UU_W, H4, H4, fclass_s)
- RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d)
- -GEN_VEXT_V(vfclass_v_h, 2, 2, clearh)
- -GEN_VEXT_V(vfclass_v_w, 4, 4, clearl)
- -GEN_VEXT_V(vfclass_v_d, 8, 8, clearq)
- +GEN_VEXT_V(vfclass_v_h, 2, 2)
- +GEN_VEXT_V(vfclass_v_w, 4, 4)
- +GEN_VEXT_V(vfclass_v_d, 8, 8)
-
- /* Vector Floating-Point Merge Instruction */
- -#define GEN_VFMERGE_VF(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VFMERGE_VF(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- - uint32_t esz = sizeof(ETYPE); \
- - uint32_t vlmax = vext_maxsz(desc) / esz; \
- uint32_t i; \
- \
- for (i = 0; i < vl; i++) { \
- @@ -4174,45 +4049,44 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
- *((ETYPE *)vd + H(i)) \
- = (!vm && !vext_elem_mask(v0, i) ? s2 : s1); \
- } \
- - CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \
- }
-
- -GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2, clearh)
- -GEN_VFMERGE_VF(vfmerge_vfm_w, int32_t, H4, clearl)
- -GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8, clearq)
- +GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2)
- +GEN_VFMERGE_VF(vfmerge_vfm_w, int32_t, H4)
- +GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8)
-
- /* Single-Width Floating-Point/Integer Type-Convert Instructions */
- /* vfcvt.xu.f.v vd, vs2, vm # Convert float to unsigned integer. */
- RVVCALL(OPFVV1, vfcvt_xu_f_v_h, OP_UU_H, H2, H2, float16_to_uint16)
- RVVCALL(OPFVV1, vfcvt_xu_f_v_w, OP_UU_W, H4, H4, float32_to_uint32)
- RVVCALL(OPFVV1, vfcvt_xu_f_v_d, OP_UU_D, H8, H8, float64_to_uint64)
- -GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4, 4, clearl)
- -GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8, 8, clearq)
- +GEN_VEXT_V_ENV(vfcvt_xu_f_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfcvt_xu_f_v_w, 4, 4)
- +GEN_VEXT_V_ENV(vfcvt_xu_f_v_d, 8, 8)
-
- /* vfcvt.x.f.v vd, vs2, vm # Convert float to signed integer. */
- RVVCALL(OPFVV1, vfcvt_x_f_v_h, OP_UU_H, H2, H2, float16_to_int16)
- RVVCALL(OPFVV1, vfcvt_x_f_v_w, OP_UU_W, H4, H4, float32_to_int32)
- RVVCALL(OPFVV1, vfcvt_x_f_v_d, OP_UU_D, H8, H8, float64_to_int64)
- -GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4, 4, clearl)
- -GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8, 8, clearq)
- +GEN_VEXT_V_ENV(vfcvt_x_f_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfcvt_x_f_v_w, 4, 4)
- +GEN_VEXT_V_ENV(vfcvt_x_f_v_d, 8, 8)
-
- /* vfcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to float. */
- RVVCALL(OPFVV1, vfcvt_f_xu_v_h, OP_UU_H, H2, H2, uint16_to_float16)
- RVVCALL(OPFVV1, vfcvt_f_xu_v_w, OP_UU_W, H4, H4, uint32_to_float32)
- RVVCALL(OPFVV1, vfcvt_f_xu_v_d, OP_UU_D, H8, H8, uint64_to_float64)
- -GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4, 4, clearl)
- -GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8, 8, clearq)
- +GEN_VEXT_V_ENV(vfcvt_f_xu_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfcvt_f_xu_v_w, 4, 4)
- +GEN_VEXT_V_ENV(vfcvt_f_xu_v_d, 8, 8)
-
- /* vfcvt.f.x.v vd, vs2, vm # Convert integer to float. */
- RVVCALL(OPFVV1, vfcvt_f_x_v_h, OP_UU_H, H2, H2, int16_to_float16)
- RVVCALL(OPFVV1, vfcvt_f_x_v_w, OP_UU_W, H4, H4, int32_to_float32)
- RVVCALL(OPFVV1, vfcvt_f_x_v_d, OP_UU_D, H8, H8, int64_to_float64)
- -GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4, 4, clearl)
- -GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8, clearq)
- +GEN_VEXT_V_ENV(vfcvt_f_x_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfcvt_f_x_v_w, 4, 4)
- +GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8)
-
- /* Widening Floating-Point/Integer Type-Convert Instructions */
- /* (TD, T2, TX2) */
- @@ -4221,26 +4095,26 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8, clearq)
- /* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/
- RVVCALL(OPFVV1, vfwcvt_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32)
- RVVCALL(OPFVV1, vfwcvt_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64)
- -GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 2, 4, clearl)
- -GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w, 4, 8, clearq)
- +GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 2, 4)
- +GEN_VEXT_V_ENV(vfwcvt_xu_f_v_w, 4, 8)
-
- /* vfwcvt.x.f.v vd, vs2, vm # Convert float to double-width signed integer. */
- RVVCALL(OPFVV1, vfwcvt_x_f_v_h, WOP_UU_H, H4, H2, float16_to_int32)
- RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64)
- -GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 2, 4, clearl)
- -GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 4, 8, clearq)
- +GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 2, 4)
- +GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 4, 8)
-
- /* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */
- RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32)
- RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64)
- -GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 2, 4, clearl)
- -GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 4, 8, clearq)
- +GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 2, 4)
- +GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 4, 8)
-
- /* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */
- RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32)
- RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64)
- -GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 2, 4, clearl)
- -GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 4, 8, clearq)
- +GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 2, 4)
- +GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 4, 8)
-
- /*
- * vfwcvt.f.f.v vd, vs2, vm #
- @@ -4253,8 +4127,8 @@ static uint32_t vfwcvtffv16(uint16_t a, float_status *s)
-
- RVVCALL(OPFVV1, vfwcvt_f_f_v_h, WOP_UU_H, H4, H2, vfwcvtffv16)
- RVVCALL(OPFVV1, vfwcvt_f_f_v_w, WOP_UU_W, H8, H4, float32_to_float64)
- -GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 2, 4, clearl)
- -GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 4, 8, clearq)
- +GEN_VEXT_V_ENV(vfwcvt_f_f_v_h, 2, 4)
- +GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 4, 8)
-
- /* Narrowing Floating-Point/Integer Type-Convert Instructions */
- /* (TD, T2, TX2) */
- @@ -4263,26 +4137,26 @@ GEN_VEXT_V_ENV(vfwcvt_f_f_v_w, 4, 8, clearq)
- /* vfncvt.xu.f.v vd, vs2, vm # Convert float to unsigned integer. */
- RVVCALL(OPFVV1, vfncvt_xu_f_v_h, NOP_UU_H, H2, H4, float32_to_uint16)
- RVVCALL(OPFVV1, vfncvt_xu_f_v_w, NOP_UU_W, H4, H8, float64_to_uint32)
- -GEN_VEXT_V_ENV(vfncvt_xu_f_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfncvt_xu_f_v_w, 4, 4, clearl)
- +GEN_VEXT_V_ENV(vfncvt_xu_f_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfncvt_xu_f_v_w, 4, 4)
-
- /* vfncvt.x.f.v vd, vs2, vm # Convert double-width float to signed integer. */
- RVVCALL(OPFVV1, vfncvt_x_f_v_h, NOP_UU_H, H2, H4, float32_to_int16)
- RVVCALL(OPFVV1, vfncvt_x_f_v_w, NOP_UU_W, H4, H8, float64_to_int32)
- -GEN_VEXT_V_ENV(vfncvt_x_f_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfncvt_x_f_v_w, 4, 4, clearl)
- +GEN_VEXT_V_ENV(vfncvt_x_f_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfncvt_x_f_v_w, 4, 4)
-
- /* vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float */
- RVVCALL(OPFVV1, vfncvt_f_xu_v_h, NOP_UU_H, H2, H4, uint32_to_float16)
- RVVCALL(OPFVV1, vfncvt_f_xu_v_w, NOP_UU_W, H4, H8, uint64_to_float32)
- -GEN_VEXT_V_ENV(vfncvt_f_xu_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfncvt_f_xu_v_w, 4, 4, clearl)
- +GEN_VEXT_V_ENV(vfncvt_f_xu_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfncvt_f_xu_v_w, 4, 4)
-
- /* vfncvt.f.x.v vd, vs2, vm # Convert double-width integer to float. */
- RVVCALL(OPFVV1, vfncvt_f_x_v_h, NOP_UU_H, H2, H4, int32_to_float16)
- RVVCALL(OPFVV1, vfncvt_f_x_v_w, NOP_UU_W, H4, H8, int64_to_float32)
- -GEN_VEXT_V_ENV(vfncvt_f_x_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfncvt_f_x_v_w, 4, 4, clearl)
- +GEN_VEXT_V_ENV(vfncvt_f_x_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfncvt_f_x_v_w, 4, 4)
-
- /* vfncvt.f.f.v vd, vs2, vm # Convert double float to single-width float. */
- static uint16_t vfncvtffv16(uint32_t a, float_status *s)
- @@ -4292,21 +4166,20 @@ static uint16_t vfncvtffv16(uint32_t a, float_status *s)
-
- RVVCALL(OPFVV1, vfncvt_f_f_v_h, NOP_UU_H, H2, H4, vfncvtffv16)
- RVVCALL(OPFVV1, vfncvt_f_f_v_w, NOP_UU_W, H4, H8, float64_to_float32)
- -GEN_VEXT_V_ENV(vfncvt_f_f_v_h, 2, 2, clearh)
- -GEN_VEXT_V_ENV(vfncvt_f_f_v_w, 4, 4, clearl)
- +GEN_VEXT_V_ENV(vfncvt_f_f_v_h, 2, 2)
- +GEN_VEXT_V_ENV(vfncvt_f_f_v_w, 4, 4)
-
- /*
- *** Vector Reduction Operations
- */
- /* Vector Single-Width Integer Reduction Instructions */
- -#define GEN_VEXT_RED(NAME, TD, TS2, HD, HS2, OP, CLEAR_FN)\
- +#define GEN_VEXT_RED(NAME, TD, TS2, HD, HS2, OP) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- void *vs2, CPURISCVState *env, uint32_t desc) \
- { \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t i; \
- - uint32_t tot = env_archcpu(env)->cfg.vlen / 8; \
- TD s1 = *((TD *)vs1 + HD(0)); \
- \
- for (i = 0; i < vl; i++) { \
- @@ -4317,70 +4190,69 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- s1 = OP(s1, (TD)s2); \
- } \
- *((TD *)vd + HD(0)) = s1; \
- - CLEAR_FN(vd, 1, sizeof(TD), tot); \
- }
-
- /* vd[0] = sum(vs1[0], vs2[*]) */
- -GEN_VEXT_RED(vredsum_vs_b, int8_t, int8_t, H1, H1, DO_ADD, clearb)
- -GEN_VEXT_RED(vredsum_vs_h, int16_t, int16_t, H2, H2, DO_ADD, clearh)
- -GEN_VEXT_RED(vredsum_vs_w, int32_t, int32_t, H4, H4, DO_ADD, clearl)
- -GEN_VEXT_RED(vredsum_vs_d, int64_t, int64_t, H8, H8, DO_ADD, clearq)
- +GEN_VEXT_RED(vredsum_vs_b, int8_t, int8_t, H1, H1, DO_ADD)
- +GEN_VEXT_RED(vredsum_vs_h, int16_t, int16_t, H2, H2, DO_ADD)
- +GEN_VEXT_RED(vredsum_vs_w, int32_t, int32_t, H4, H4, DO_ADD)
- +GEN_VEXT_RED(vredsum_vs_d, int64_t, int64_t, H8, H8, DO_ADD)
-
- /* vd[0] = maxu(vs1[0], vs2[*]) */
- -GEN_VEXT_RED(vredmaxu_vs_b, uint8_t, uint8_t, H1, H1, DO_MAX, clearb)
- -GEN_VEXT_RED(vredmaxu_vs_h, uint16_t, uint16_t, H2, H2, DO_MAX, clearh)
- -GEN_VEXT_RED(vredmaxu_vs_w, uint32_t, uint32_t, H4, H4, DO_MAX, clearl)
- -GEN_VEXT_RED(vredmaxu_vs_d, uint64_t, uint64_t, H8, H8, DO_MAX, clearq)
- +GEN_VEXT_RED(vredmaxu_vs_b, uint8_t, uint8_t, H1, H1, DO_MAX)
- +GEN_VEXT_RED(vredmaxu_vs_h, uint16_t, uint16_t, H2, H2, DO_MAX)
- +GEN_VEXT_RED(vredmaxu_vs_w, uint32_t, uint32_t, H4, H4, DO_MAX)
- +GEN_VEXT_RED(vredmaxu_vs_d, uint64_t, uint64_t, H8, H8, DO_MAX)
-
- /* vd[0] = max(vs1[0], vs2[*]) */
- -GEN_VEXT_RED(vredmax_vs_b, int8_t, int8_t, H1, H1, DO_MAX, clearb)
- -GEN_VEXT_RED(vredmax_vs_h, int16_t, int16_t, H2, H2, DO_MAX, clearh)
- -GEN_VEXT_RED(vredmax_vs_w, int32_t, int32_t, H4, H4, DO_MAX, clearl)
- -GEN_VEXT_RED(vredmax_vs_d, int64_t, int64_t, H8, H8, DO_MAX, clearq)
- +GEN_VEXT_RED(vredmax_vs_b, int8_t, int8_t, H1, H1, DO_MAX)
- +GEN_VEXT_RED(vredmax_vs_h, int16_t, int16_t, H2, H2, DO_MAX)
- +GEN_VEXT_RED(vredmax_vs_w, int32_t, int32_t, H4, H4, DO_MAX)
- +GEN_VEXT_RED(vredmax_vs_d, int64_t, int64_t, H8, H8, DO_MAX)
-
- /* vd[0] = minu(vs1[0], vs2[*]) */
- -GEN_VEXT_RED(vredminu_vs_b, uint8_t, uint8_t, H1, H1, DO_MIN, clearb)
- -GEN_VEXT_RED(vredminu_vs_h, uint16_t, uint16_t, H2, H2, DO_MIN, clearh)
- -GEN_VEXT_RED(vredminu_vs_w, uint32_t, uint32_t, H4, H4, DO_MIN, clearl)
- -GEN_VEXT_RED(vredminu_vs_d, uint64_t, uint64_t, H8, H8, DO_MIN, clearq)
- +GEN_VEXT_RED(vredminu_vs_b, uint8_t, uint8_t, H1, H1, DO_MIN)
- +GEN_VEXT_RED(vredminu_vs_h, uint16_t, uint16_t, H2, H2, DO_MIN)
- +GEN_VEXT_RED(vredminu_vs_w, uint32_t, uint32_t, H4, H4, DO_MIN)
- +GEN_VEXT_RED(vredminu_vs_d, uint64_t, uint64_t, H8, H8, DO_MIN)
-
- /* vd[0] = min(vs1[0], vs2[*]) */
- -GEN_VEXT_RED(vredmin_vs_b, int8_t, int8_t, H1, H1, DO_MIN, clearb)
- -GEN_VEXT_RED(vredmin_vs_h, int16_t, int16_t, H2, H2, DO_MIN, clearh)
- -GEN_VEXT_RED(vredmin_vs_w, int32_t, int32_t, H4, H4, DO_MIN, clearl)
- -GEN_VEXT_RED(vredmin_vs_d, int64_t, int64_t, H8, H8, DO_MIN, clearq)
- +GEN_VEXT_RED(vredmin_vs_b, int8_t, int8_t, H1, H1, DO_MIN)
- +GEN_VEXT_RED(vredmin_vs_h, int16_t, int16_t, H2, H2, DO_MIN)
- +GEN_VEXT_RED(vredmin_vs_w, int32_t, int32_t, H4, H4, DO_MIN)
- +GEN_VEXT_RED(vredmin_vs_d, int64_t, int64_t, H8, H8, DO_MIN)
-
- /* vd[0] = and(vs1[0], vs2[*]) */
- -GEN_VEXT_RED(vredand_vs_b, int8_t, int8_t, H1, H1, DO_AND, clearb)
- -GEN_VEXT_RED(vredand_vs_h, int16_t, int16_t, H2, H2, DO_AND, clearh)
- -GEN_VEXT_RED(vredand_vs_w, int32_t, int32_t, H4, H4, DO_AND, clearl)
- -GEN_VEXT_RED(vredand_vs_d, int64_t, int64_t, H8, H8, DO_AND, clearq)
- +GEN_VEXT_RED(vredand_vs_b, int8_t, int8_t, H1, H1, DO_AND)
- +GEN_VEXT_RED(vredand_vs_h, int16_t, int16_t, H2, H2, DO_AND)
- +GEN_VEXT_RED(vredand_vs_w, int32_t, int32_t, H4, H4, DO_AND)
- +GEN_VEXT_RED(vredand_vs_d, int64_t, int64_t, H8, H8, DO_AND)
-
- /* vd[0] = or(vs1[0], vs2[*]) */
- -GEN_VEXT_RED(vredor_vs_b, int8_t, int8_t, H1, H1, DO_OR, clearb)
- -GEN_VEXT_RED(vredor_vs_h, int16_t, int16_t, H2, H2, DO_OR, clearh)
- -GEN_VEXT_RED(vredor_vs_w, int32_t, int32_t, H4, H4, DO_OR, clearl)
- -GEN_VEXT_RED(vredor_vs_d, int64_t, int64_t, H8, H8, DO_OR, clearq)
- +GEN_VEXT_RED(vredor_vs_b, int8_t, int8_t, H1, H1, DO_OR)
- +GEN_VEXT_RED(vredor_vs_h, int16_t, int16_t, H2, H2, DO_OR)
- +GEN_VEXT_RED(vredor_vs_w, int32_t, int32_t, H4, H4, DO_OR)
- +GEN_VEXT_RED(vredor_vs_d, int64_t, int64_t, H8, H8, DO_OR)
-
- /* vd[0] = xor(vs1[0], vs2[*]) */
- -GEN_VEXT_RED(vredxor_vs_b, int8_t, int8_t, H1, H1, DO_XOR, clearb)
- -GEN_VEXT_RED(vredxor_vs_h, int16_t, int16_t, H2, H2, DO_XOR, clearh)
- -GEN_VEXT_RED(vredxor_vs_w, int32_t, int32_t, H4, H4, DO_XOR, clearl)
- -GEN_VEXT_RED(vredxor_vs_d, int64_t, int64_t, H8, H8, DO_XOR, clearq)
- +GEN_VEXT_RED(vredxor_vs_b, int8_t, int8_t, H1, H1, DO_XOR)
- +GEN_VEXT_RED(vredxor_vs_h, int16_t, int16_t, H2, H2, DO_XOR)
- +GEN_VEXT_RED(vredxor_vs_w, int32_t, int32_t, H4, H4, DO_XOR)
- +GEN_VEXT_RED(vredxor_vs_d, int64_t, int64_t, H8, H8, DO_XOR)
-
- /* Vector Widening Integer Reduction Instructions */
- /* signed sum reduction into double-width accumulator */
- -GEN_VEXT_RED(vwredsum_vs_b, int16_t, int8_t, H2, H1, DO_ADD, clearh)
- -GEN_VEXT_RED(vwredsum_vs_h, int32_t, int16_t, H4, H2, DO_ADD, clearl)
- -GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4, DO_ADD, clearq)
- +GEN_VEXT_RED(vwredsum_vs_b, int16_t, int8_t, H2, H1, DO_ADD)
- +GEN_VEXT_RED(vwredsum_vs_h, int32_t, int16_t, H4, H2, DO_ADD)
- +GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4, DO_ADD)
-
- /* Unsigned sum reduction into double-width accumulator */
- -GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD, clearh)
- -GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD, clearl)
- -GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD, clearq)
- +GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD)
- +GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD)
- +GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD)
-
- /* Vector Single-Width Floating-Point Reduction Instructions */
- -#define GEN_VEXT_FRED(NAME, TD, TS2, HD, HS2, OP, CLEAR_FN)\
- +#define GEN_VEXT_FRED(NAME, TD, TS2, HD, HS2, OP) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- void *vs2, CPURISCVState *env, \
- uint32_t desc) \
- @@ -4388,7 +4260,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t i; \
- - uint32_t tot = env_archcpu(env)->cfg.vlen / 8; \
- TD s1 = *((TD *)vs1 + HD(0)); \
- \
- for (i = 0; i < vl; i++) { \
- @@ -4399,23 +4270,22 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \
- s1 = OP(s1, (TD)s2, &env->fp_status); \
- } \
- *((TD *)vd + HD(0)) = s1; \
- - CLEAR_FN(vd, 1, sizeof(TD), tot); \
- }
-
- /* Unordered sum */
- -GEN_VEXT_FRED(vfredsum_vs_h, uint16_t, uint16_t, H2, H2, float16_add, clearh)
- -GEN_VEXT_FRED(vfredsum_vs_w, uint32_t, uint32_t, H4, H4, float32_add, clearl)
- -GEN_VEXT_FRED(vfredsum_vs_d, uint64_t, uint64_t, H8, H8, float64_add, clearq)
- +GEN_VEXT_FRED(vfredsum_vs_h, uint16_t, uint16_t, H2, H2, float16_add)
- +GEN_VEXT_FRED(vfredsum_vs_w, uint32_t, uint32_t, H4, H4, float32_add)
- +GEN_VEXT_FRED(vfredsum_vs_d, uint64_t, uint64_t, H8, H8, float64_add)
-
- /* Maximum value */
- -GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2, float16_maxnum, clearh)
- -GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4, float32_maxnum, clearl)
- -GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maxnum, clearq)
- +GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2, float16_maxnum)
- +GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4, float32_maxnum)
- +GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maxnum)
-
- /* Minimum value */
- -GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum, clearh)
- -GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum, clearl)
- -GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, clearq)
- +GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum)
- +GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum)
- +GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum)
-
- /* Vector Widening Floating-Point Reduction Instructions */
- /* Unordered reduce 2*SEW = 2*SEW + sum(promote(SEW)) */
- @@ -4425,7 +4295,6 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
- uint32_t vm = vext_vm(desc);
- uint32_t vl = env->vl;
- uint32_t i;
- - uint32_t tot = env_archcpu(env)->cfg.vlen / 8;
- uint32_t s1 = *((uint32_t *)vs1 + H4(0));
-
- for (i = 0; i < vl; i++) {
- @@ -4437,7 +4306,6 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
- &env->fp_status);
- }
- *((uint32_t *)vd + H4(0)) = s1;
- - clearl(vd, 1, sizeof(uint32_t), tot);
- }
-
- void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
- @@ -4446,7 +4314,6 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
- uint32_t vm = vext_vm(desc);
- uint32_t vl = env->vl;
- uint32_t i;
- - uint32_t tot = env_archcpu(env)->cfg.vlen / 8;
- uint64_t s1 = *((uint64_t *)vs1);
-
- for (i = 0; i < vl; i++) {
- @@ -4458,7 +4325,6 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
- &env->fp_status);
- }
- *((uint64_t *)vd) = s1;
- - clearq(vd, 1, sizeof(uint64_t), tot);
- }
-
- /*
- @@ -4600,11 +4466,10 @@ void HELPER(vmsof_m)(void *vd, void *v0, void *vs2, CPURISCVState *env,
- }
-
- /* Vector Iota Instruction */
- -#define GEN_VEXT_VIOTA_M(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VIOTA_M(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \
- uint32_t desc) \
- { \
- - uint32_t vlmax = env_archcpu(env)->cfg.vlen; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t sum = 0; \
- @@ -4619,19 +4484,17 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \
- sum++; \
- } \
- } \
- - CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- -GEN_VEXT_VIOTA_M(viota_m_b, uint8_t, H1, clearb)
- -GEN_VEXT_VIOTA_M(viota_m_h, uint16_t, H2, clearh)
- -GEN_VEXT_VIOTA_M(viota_m_w, uint32_t, H4, clearl)
- -GEN_VEXT_VIOTA_M(viota_m_d, uint64_t, H8, clearq)
- +GEN_VEXT_VIOTA_M(viota_m_b, uint8_t, H1)
- +GEN_VEXT_VIOTA_M(viota_m_h, uint16_t, H2)
- +GEN_VEXT_VIOTA_M(viota_m_w, uint32_t, H4)
- +GEN_VEXT_VIOTA_M(viota_m_d, uint64_t, H8)
-
- /* Vector Element Index Instruction */
- -#define GEN_VEXT_VID_V(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VID_V(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
- { \
- - uint32_t vlmax = env_archcpu(env)->cfg.vlen; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- int i; \
- @@ -4642,24 +4505,22 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \
- } \
- *((ETYPE *)vd + H(i)) = i; \
- } \
- - CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- -GEN_VEXT_VID_V(vid_v_b, uint8_t, H1, clearb)
- -GEN_VEXT_VID_V(vid_v_h, uint16_t, H2, clearh)
- -GEN_VEXT_VID_V(vid_v_w, uint32_t, H4, clearl)
- -GEN_VEXT_VID_V(vid_v_d, uint64_t, H8, clearq)
- +GEN_VEXT_VID_V(vid_v_b, uint8_t, H1)
- +GEN_VEXT_VID_V(vid_v_h, uint16_t, H2)
- +GEN_VEXT_VID_V(vid_v_w, uint32_t, H4)
- +GEN_VEXT_VID_V(vid_v_d, uint64_t, H8)
-
- /*
- *** Vector Permutation Instructions
- */
-
- /* Vector Slide Instructions */
- -#define GEN_VEXT_VSLIDEUP_VX(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VSLIDEUP_VX(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - uint32_t vlmax = env_archcpu(env)->cfg.vlen; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- target_ulong offset = s1, i; \
- @@ -4670,16 +4531,15 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- } \
- *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \
- } \
- - CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- /* vslideup.vx vd, vs2, rs1, vm # vd[i+rs1] = vs2[i] */
- -GEN_VEXT_VSLIDEUP_VX(vslideup_vx_b, uint8_t, H1, clearb)
- -GEN_VEXT_VSLIDEUP_VX(vslideup_vx_h, uint16_t, H2, clearh)
- -GEN_VEXT_VSLIDEUP_VX(vslideup_vx_w, uint32_t, H4, clearl)
- -GEN_VEXT_VSLIDEUP_VX(vslideup_vx_d, uint64_t, H8, clearq)
- +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_b, uint8_t, H1)
- +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_h, uint16_t, H2)
- +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_w, uint32_t, H4)
- +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_d, uint64_t, H8)
-
- -#define GEN_VEXT_VSLIDEDOWN_VX(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VSLIDEDOWN_VX(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- @@ -4695,20 +4555,18 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- } \
- *((ETYPE *)vd + H(i)) = j >= vlmax ? 0 : *((ETYPE *)vs2 + H(j)); \
- } \
- - CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- /* vslidedown.vx vd, vs2, rs1, vm # vd[i] = vs2[i+rs1] */
- -GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_b, uint8_t, H1, clearb)
- -GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_h, uint16_t, H2, clearh)
- -GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_w, uint32_t, H4, clearl)
- -GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8, clearq)
- +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_b, uint8_t, H1)
- +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_h, uint16_t, H2)
- +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_w, uint32_t, H4)
- +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8)
-
- -#define GEN_VEXT_VSLIDE1UP_VX(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VSLIDE1UP_VX(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - uint32_t vlmax = env_archcpu(env)->cfg.vlen; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t i; \
- @@ -4723,20 +4581,18 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - 1)); \
- } \
- } \
- - CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- /* vslide1up.vx vd, vs2, rs1, vm # vd[0]=x[rs1], vd[i+1] = vs2[i] */
- -GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_b, uint8_t, H1, clearb)
- -GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_h, uint16_t, H2, clearh)
- -GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_w, uint32_t, H4, clearl)
- -GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, uint64_t, H8, clearq)
- +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_b, uint8_t, H1)
- +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_h, uint16_t, H2)
- +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_w, uint32_t, H4)
- +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, uint64_t, H8)
-
- -#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - uint32_t vlmax = env_archcpu(env)->cfg.vlen; \
- uint32_t vm = vext_vm(desc); \
- uint32_t vl = env->vl; \
- uint32_t i; \
- @@ -4751,17 +4607,16 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + 1)); \
- } \
- } \
- - CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- /* vslide1down.vx vd, vs2, rs1, vm # vd[i] = vs2[i+1], vd[vl-1]=x[rs1] */
- -GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_b, uint8_t, H1, clearb)
- -GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_h, uint16_t, H2, clearh)
- -GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, uint32_t, H4, clearl)
- -GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8, clearq)
- +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_b, uint8_t, H1)
- +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_h, uint16_t, H2)
- +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, uint32_t, H4)
- +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8)
-
- /* Vector Register Gather Instruction */
- -#define GEN_VEXT_VRGATHER_VV(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VRGATHER_VV(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- @@ -4782,16 +4637,15 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
- *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index)); \
- } \
- } \
- - CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- /* vd[i] = (vs1[i] >= VLMAX) ? 0 : vs2[vs1[i]]; */
- -GEN_VEXT_VRGATHER_VV(vrgather_vv_b, uint8_t, H1, clearb)
- -GEN_VEXT_VRGATHER_VV(vrgather_vv_h, uint16_t, H2, clearh)
- -GEN_VEXT_VRGATHER_VV(vrgather_vv_w, uint32_t, H4, clearl)
- -GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, H8, clearq)
- +GEN_VEXT_VRGATHER_VV(vrgather_vv_b, uint8_t, H1)
- +GEN_VEXT_VRGATHER_VV(vrgather_vv_h, uint16_t, H2)
- +GEN_VEXT_VRGATHER_VV(vrgather_vv_w, uint32_t, H4)
- +GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, H8)
-
- -#define GEN_VEXT_VRGATHER_VX(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VRGATHER_VX(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- @@ -4811,21 +4665,19 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
- *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index)); \
- } \
- } \
- - CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- /* vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
- -GEN_VEXT_VRGATHER_VX(vrgather_vx_b, uint8_t, H1, clearb)
- -GEN_VEXT_VRGATHER_VX(vrgather_vx_h, uint16_t, H2, clearh)
- -GEN_VEXT_VRGATHER_VX(vrgather_vx_w, uint32_t, H4, clearl)
- -GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq)
- +GEN_VEXT_VRGATHER_VX(vrgather_vx_b, uint8_t, H1)
- +GEN_VEXT_VRGATHER_VX(vrgather_vx_h, uint16_t, H2)
- +GEN_VEXT_VRGATHER_VX(vrgather_vx_w, uint32_t, H4)
- +GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8)
-
- /* Vector Compress Instruction */
- -#define GEN_VEXT_VCOMPRESS_VM(NAME, ETYPE, H, CLEAR_FN) \
- +#define GEN_VEXT_VCOMPRESS_VM(NAME, ETYPE, H) \
- void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
- CPURISCVState *env, uint32_t desc) \
- { \
- - uint32_t vlmax = env_archcpu(env)->cfg.vlen; \
- uint32_t vl = env->vl; \
- uint32_t num = 0, i; \
- \
- @@ -4836,11 +4688,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
- *((ETYPE *)vd + H(num)) = *((ETYPE *)vs2 + H(i)); \
- num++; \
- } \
- - CLEAR_FN(vd, num, num * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \
- }
-
- /* Compress into vd elements of vs2 where vs1 is enabled */
- -GEN_VEXT_VCOMPRESS_VM(vcompress_vm_b, uint8_t, H1, clearb)
- -GEN_VEXT_VCOMPRESS_VM(vcompress_vm_h, uint16_t, H2, clearh)
- -GEN_VEXT_VCOMPRESS_VM(vcompress_vm_w, uint32_t, H4, clearl)
- -GEN_VEXT_VCOMPRESS_VM(vcompress_vm_d, uint64_t, H8, clearq)
- +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_b, uint8_t, H1)
- +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_h, uint16_t, H2)
- +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_w, uint32_t, H4)
- +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_d, uint64_t, H8)
- --
- 2.33.1
|