collab/polyglot-riscv-arm
what if the same machine code was valid riscv and arm asm
git clone https://git.julia.blue/collab/polyglot-riscv-arm
885cc4e
main
1< ?xml version="1.0" encoding="utf-8"?> 2<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd" > 3< html xmlns ="http://www.w3.org/1999/xhtml ">< head >< link rel ="stylesheet "type ="text/css "href ="insn.css "/>< meta name ="generator "content ="iform.xsl "/>< title > VFMA -- AArch32</ title ></ head >< body >< table style ="margin: 0 auto; ">< tr >< td >< div class ="topbar ">< a href ="index.html "> Base Instructions</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="fpsimdindex.html "> SIMD&FP Instructions</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="a32_encindex.html "> A32 Instructions by Encoding</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="t32_encindex.html "> T32 Instructions by Encoding</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="shared_pseudocode.html "> Shared Pseudocode</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="notice.html "> Proprietary Notice</ a ></ div ></ td ></ tr ></ table >< hr />< h2 class ="instruction-section "> VFMA</ h2 > 4< p class ="aml "> Vector Fused Multiply Accumulate multiplies corresponding elements of two vectors, and accumulates the results into the elements of the destination vector. The instruction does not round the result of the multiply before the accumulation.</ p > 5< p class ="aml "> Depending on settings in the< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="AArch32.cpacr "> CPACR</ a > ,< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="AArch32.nsacr "> NSACR</ a > ,< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="AArch32.hcptr "> HCPTR</ a > , and< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="AArch32.fpexc "> FPEXC</ a > registers, and the Security state and PE mode in which the instruction is executed, an attempt to execute the instruction might be< span class ="arm-defined-word "> undefined</ span > , or trapped to Hyp mode. For more information see< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="CIHIDDFF "> Enabling Advanced SIMD and floating-point support</ a > .</ p > 6 7< p class ="desc "> 8 It has encodings from the following instruction sets: 9 A32 ( 10< a href ="#iclass_a1 "> A1</ a > 11 and 12< a href ="#iclass_a2 "> A2</ a > 13 ) 14 and 15 T32 ( 16< a href ="#iclass_t1 "> T1</ a > 17 and 18< a href ="#iclass_t2 "> T2</ a > 19 ) 20 . 21</ p > 22< h3 class ="classheading ">< a id ="iclass_a1 "/> A1</ h3 >< p class ="desc "/>< div class ="regdiagram-32 ">< table class ="regdiagram ">< thead >< tr >< td > 31</ td >< td > 30</ td >< td > 29</ td >< td > 28</ td >< td > 27</ td >< td > 26</ td >< td > 25</ td >< td > 24</ td >< td > 23</ td >< td > 22</ td >< td > 21</ td >< td > 20</ td >< td > 19</ td >< td > 18</ td >< td > 17</ td >< td > 16</ td >< td > 15</ td >< td > 14</ td >< td > 13</ td >< td > 12</ td >< td > 11</ td >< td > 10</ td >< td > 9</ td >< td > 8</ td >< td > 7</ td >< td > 6</ td >< td > 5</ td >< td > 4</ td >< td > 3</ td >< td > 2</ td >< td > 1</ td >< td > 0</ td ></ tr ></ thead >< tbody >< tr class ="firstrow ">< td class ="l "> 1</ td >< td > 1</ td >< td > 1</ td >< td > 1</ td >< td > 0</ td >< td > 0</ td >< td class ="r "> 1</ td >< td class ="lr "> 0</ td >< td class ="lr "> 0</ td >< td class ="lr "> D</ td >< td class ="lr "> 0</ td >< td class ="lr "> sz</ td >< td colspan ="4 "class ="lr "> Vn</ td >< td colspan ="4 "class ="lr "> Vd</ td >< td class ="l "> 1</ td >< td > 1</ td >< td > 0</ td >< td class ="r "> 0</ td >< td class ="lr "> N</ td >< td class ="lr "> Q</ td >< td class ="lr "> M</ td >< td class ="lr "> 1</ td >< td colspan ="4 "class ="lr "> Vm</ td ></ tr >< tr class ="secondrow ">< td colspan ="7 "/>< td />< td />< td />< td class ="droppedname "> op</ td >< td />< td colspan ="4 "/>< td colspan ="4 "/>< td colspan ="4 "/>< td />< td />< td />< td />< td colspan ="4 "/></ tr ></ tbody ></ table ></ div >< div class ="encoding ">< h4 class ="encoding "> 64-bit SIMD vector< span class ="bitdiff "> (Q == 0)</ span ></ h4 >< a id ="VFMA_A1_D "/>< p class ="asm-code "> VFMA{< a href ="#sa_c_1 "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.< a href ="#sa_dt "title ="Data type for elements of vectors (field "sz") [F16,F32] "> <dt></ a > < a href ="#sa_dd "title ="64-bit SIMD&FP destination register (field "D:Vd") "> <Dd></ a > ,< a href ="#sa_dn "title ="First 64-bit SIMD&FP source register (field "N:Vn") "> <Dn></ a > ,< a href ="#sa_dm "title ="Second 64-bit SIMD&FP source register (field "M:Vm") "> <Dm></ a ></ p ></ div >< div class ="encoding ">< h4 class ="encoding "> 128-bit SIMD vector< span class ="bitdiff "> (Q == 1)</ span ></ h4 >< a id ="VFMA_A1_Q "/>< p class ="asm-code "> VFMA{< a href ="#sa_c_1 "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.< a href ="#sa_dt "title ="Data type for elements of vectors (field "sz") [F16,F32] "> <dt></ a > < a href ="#sa_qd "title ="128-bit SIMD&FP destination register (field "D:Vd") "> <Qd></ a > ,< a href ="#sa_qn "title ="First 128-bit SIMD&FP source register (field "N:Vn") "> <Qn></ a > ,< a href ="#sa_qm "title ="Second 128-bit SIMD&FP source register (field "M:Vm") "> <Qm></ a ></ p ></ div >< p class ="pseudocode "> if Q == '1' && (Vd<0> == '1' || Vn<0> == '1' || Vm<0> == '1') then UNDEFINED; 23if sz == '1' && !IsFeatureImplemented(FEAT_FP16) then UNDEFINED; 24constant advsimd = TRUE; constant op1_neg = (op == '1'); 25constant integer esize = 32 >>< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (sz); 26constant integer elements = 64 DIV esize; 27constant d =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (D:Vd); constant n =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (N:Vn); constant m =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (M:Vm); 28constant regs = if Q == '0' then 1 else 2;</ p > 29< h3 class ="classheading ">< a id ="iclass_a2 "/> A2</ h3 >< p class ="desc "/>< div class ="regdiagram-32 ">< table class ="regdiagram ">< thead >< tr >< td > 31</ td >< td > 30</ td >< td > 29</ td >< td > 28</ td >< td > 27</ td >< td > 26</ td >< td > 25</ td >< td > 24</ td >< td > 23</ td >< td > 22</ td >< td > 21</ td >< td > 20</ td >< td > 19</ td >< td > 18</ td >< td > 17</ td >< td > 16</ td >< td > 15</ td >< td > 14</ td >< td > 13</ td >< td > 12</ td >< td > 11</ td >< td > 10</ td >< td > 9</ td >< td > 8</ td >< td > 7</ td >< td > 6</ td >< td > 5</ td >< td > 4</ td >< td > 3</ td >< td > 2</ td >< td > 1</ td >< td > 0</ td ></ tr ></ thead >< tbody >< tr class ="firstrow ">< td colspan ="4 "class ="lr "> != 1111</ td >< td class ="l "> 1</ td >< td > 1</ td >< td > 1</ td >< td class ="r "> 0</ td >< td class ="lr "> 1</ td >< td class ="lr "> D</ td >< td class ="l "> 1</ td >< td class ="r "> 0</ td >< td colspan ="4 "class ="lr "> Vn</ td >< td colspan ="4 "class ="lr "> Vd</ td >< td class ="l "> 1</ td >< td class ="r "> 0</ td >< td colspan ="2 "class ="lr "> size</ td >< td class ="lr "> N</ td >< td class ="lr "> 0</ td >< td class ="lr "> M</ td >< td class ="lr "> 0</ td >< td colspan ="4 "class ="lr "> Vm</ td ></ tr >< tr class ="secondrow ">< td colspan ="4 "class ="droppedname "> cond</ td >< td colspan ="4 "/>< td />< td />< td colspan ="2 "/>< td colspan ="4 "/>< td colspan ="4 "/>< td colspan ="2 "/>< td colspan ="2 "/>< td />< td class ="droppedname "> op</ td >< td />< td />< td colspan ="4 "/></ tr ></ tbody ></ table ></ div >< div class ="encoding ">< h4 class ="encoding "> Half-precision scalar< span class ="bitdiff "> (size == 01)</ span >< span style ="font-size:smaller; ">< br /> (FEAT_FP16) 30</ span ></ h4 >< a id ="VFMA_A2_H "/>< p class ="asm-code "> VFMA{< a href ="#sa_c "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.F16< a href ="#sa_sd "title ="32-bit SIMD&FP destination register (field "Vd:D") "> <Sd></ a > ,< a href ="#sa_sn "title ="First 32-bit SIMD&FP source register (field "Vn:N") "> <Sn></ a > ,< a href ="#sa_sm "title ="Second 32-bit SIMD&FP source register (field "Vm:M") "> <Sm></ a ></ p ></ div >< div class ="encoding ">< h4 class ="encoding "> Single-precision scalar< span class ="bitdiff "> (size == 10)</ span ></ h4 >< a id ="VFMA_A2_S "/>< p class ="asm-code "> VFMA{< a href ="#sa_c "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.F32< a href ="#sa_sd "title ="32-bit SIMD&FP destination register (field "Vd:D") "> <Sd></ a > ,< a href ="#sa_sn "title ="First 32-bit SIMD&FP source register (field "Vn:N") "> <Sn></ a > ,< a href ="#sa_sm "title ="Second 32-bit SIMD&FP source register (field "Vm:M") "> <Sm></ a ></ p ></ div >< div class ="encoding ">< h4 class ="encoding "> Double-precision scalar< span class ="bitdiff "> (size == 11)</ span ></ h4 >< a id ="VFMA_A2_D "/>< p class ="asm-code "> VFMA{< a href ="#sa_c "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.F64< a href ="#sa_dd "title ="64-bit SIMD&FP destination register (field "D:Vd") "> <Dd></ a > ,< a href ="#sa_dn "title ="First 64-bit SIMD&FP source register (field "N:Vn") "> <Dn></ a > ,< a href ="#sa_dm "title ="Second 64-bit SIMD&FP source register (field "M:Vm") "> <Dm></ a ></ p ></ div >< p class ="pseudocode "> if FPSCR.Len != '000' || FPSCR.Stride != '00' then UNDEFINED; 31if size == '00' || (size == '01' && !IsFeatureImplemented(FEAT_FP16)) then UNDEFINED; 32if size == '01' && cond != '1110' then UNPREDICTABLE; 33constant advsimd = FALSE; constant op1_neg = (op == '1'); 34constant integer esize = 8 <<< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (size); 35constant integer d = if size == '11' then< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (D:Vd) else< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vd:D); 36constant integer n = if size == '11' then< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (N:Vn) else< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vn:N); 37constant integer m = if size == '11' then< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (M:Vm) else< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vm:M); 38constant boolean floating_point = boolean UNKNOWN; 39constant integer regs = integer UNKNOWN; constant integer elements = integer UNKNOWN;</ p >< h3 > CONSTRAINED UNPREDICTABLE behavior</ h3 >< p > If< span class ="pseudocode "> size == '01' && cond != '1110'</ span > , then one of the following behaviors must occur:</ p >< ul >< li > The instruction is< span class ="arm-defined-word "> undefined</ span > .</ li >< li > The instruction executes as if it passes the Condition code check.</ li >< li > The instruction executes as NOP. This means it behaves as if it fails the Condition code check.</ li ></ ul > 40< h3 class ="classheading ">< a id ="iclass_t1 "/> T1</ h3 >< p class ="desc "/>< div class ="regdiagram-16x2 ">< table class ="regdiagram ">< thead >< tr >< td > 15</ td >< td > 14</ td >< td > 13</ td >< td > 12</ td >< td > 11</ td >< td > 10</ td >< td > 9</ td >< td > 8</ td >< td > 7</ td >< td > 6</ td >< td > 5</ td >< td > 4</ td >< td > 3</ td >< td > 2</ td >< td > 1</ td >< td > 0</ td >< td > 15</ td >< td > 14</ td >< td > 13</ td >< td > 12</ td >< td > 11</ td >< td > 10</ td >< td > 9</ td >< td > 8</ td >< td > 7</ td >< td > 6</ td >< td > 5</ td >< td > 4</ td >< td > 3</ td >< td > 2</ td >< td > 1</ td >< td > 0</ td ></ tr ></ thead >< tbody >< tr class ="firstrow ">< td class ="l "> 1</ td >< td > 1</ td >< td class ="r "> 1</ td >< td class ="lr "> 0</ td >< td class ="l "> 1</ td >< td > 1</ td >< td > 1</ td >< td > 1</ td >< td class ="r "> 0</ td >< td class ="lr "> D</ td >< td class ="lr "> 0</ td >< td class ="lr "> sz</ td >< td colspan ="4 "class ="lr "> Vn</ td >< td colspan ="4 "class ="lr "> Vd</ td >< td class ="l "> 1</ td >< td > 1</ td >< td > 0</ td >< td class ="r "> 0</ td >< td class ="lr "> N</ td >< td class ="lr "> Q</ td >< td class ="lr "> M</ td >< td class ="lr "> 1</ td >< td colspan ="4 "class ="lr "> Vm</ td ></ tr >< tr class ="secondrow ">< td colspan ="3 "/>< td />< td colspan ="5 "/>< td />< td class ="droppedname "> op</ td >< td />< td colspan ="4 "/>< td colspan ="4 "/>< td colspan ="4 "/>< td />< td />< td />< td />< td colspan ="4 "/></ tr ></ tbody ></ table ></ div >< div class ="encoding ">< h4 class ="encoding "> 64-bit SIMD vector< span class ="bitdiff "> (Q == 0)</ span ></ h4 >< a id ="VFMA_T1_D "/>< p class ="asm-code "> VFMA{< a href ="#sa_c "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.< a href ="#sa_dt "title ="Data type for elements of vectors (field "sz") [F16,F32] "> <dt></ a > < a href ="#sa_dd "title ="64-bit SIMD&FP destination register (field "D:Vd") "> <Dd></ a > ,< a href ="#sa_dn "title ="First 64-bit SIMD&FP source register (field "N:Vn") "> <Dn></ a > ,< a href ="#sa_dm "title ="Second 64-bit SIMD&FP source register (field "M:Vm") "> <Dm></ a ></ p ></ div >< div class ="encoding ">< h4 class ="encoding "> 128-bit SIMD vector< span class ="bitdiff "> (Q == 1)</ span ></ h4 >< a id ="VFMA_T1_Q "/>< p class ="asm-code "> VFMA{< a href ="#sa_c "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.< a href ="#sa_dt "title ="Data type for elements of vectors (field "sz") [F16,F32] "> <dt></ a > < a href ="#sa_qd "title ="128-bit SIMD&FP destination register (field "D:Vd") "> <Qd></ a > ,< a href ="#sa_qn "title ="First 128-bit SIMD&FP source register (field "N:Vn") "> <Qn></ a > ,< a href ="#sa_qm "title ="Second 128-bit SIMD&FP source register (field "M:Vm") "> <Qm></ a ></ p ></ div >< p class ="pseudocode "> if Q == '1' && (Vd<0> == '1' || Vn<0> == '1' || Vm<0> == '1') then UNDEFINED; 41if sz == '1' && !IsFeatureImplemented(FEAT_FP16) then UNDEFINED; 42if sz == '1' &&< a href ="shared_pseudocode.html#impl-aarch32.InITBlock.0 "title ="function: boolean InITBlock() "> InITBlock</ a > () then UNPREDICTABLE; 43constant advsimd = TRUE; constant op1_neg = (op == '1'); 44constant integer esize = 32 >>< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (sz); 45constant integer elements = 64 DIV esize; 46constant d =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (D:Vd); constant n =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (N:Vn); constant m =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (M:Vm); 47constant regs = if Q == '0' then 1 else 2;</ p >< h3 > CONSTRAINED UNPREDICTABLE behavior</ h3 >< p > If< span class ="pseudocode "> sz == '1' && InITBlock()</ span > , then one of the following behaviors must occur:</ p >< ul >< li > The instruction is< span class ="arm-defined-word "> undefined</ span > .</ li >< li > The instruction executes as if it passes the Condition code check.</ li >< li > The instruction executes as NOP. This means it behaves as if it fails the Condition code check.</ li ></ ul > 48< h3 class ="classheading ">< a id ="iclass_t2 "/> T2</ h3 >< p class ="desc "/>< div class ="regdiagram-16x2 ">< table class ="regdiagram ">< thead >< tr >< td > 15</ td >< td > 14</ td >< td > 13</ td >< td > 12</ td >< td > 11</ td >< td > 10</ td >< td > 9</ td >< td > 8</ td >< td > 7</ td >< td > 6</ td >< td > 5</ td >< td > 4</ td >< td > 3</ td >< td > 2</ td >< td > 1</ td >< td > 0</ td >< td > 15</ td >< td > 14</ td >< td > 13</ td >< td > 12</ td >< td > 11</ td >< td > 10</ td >< td > 9</ td >< td > 8</ td >< td > 7</ td >< td > 6</ td >< td > 5</ td >< td > 4</ td >< td > 3</ td >< td > 2</ td >< td > 1</ td >< td > 0</ td ></ tr ></ thead >< tbody >< tr class ="firstrow ">< td class ="l "> 1</ td >< td > 1</ td >< td > 1</ td >< td > 0</ td >< td > 1</ td >< td > 1</ td >< td > 1</ td >< td class ="r "> 0</ td >< td class ="lr "> 1</ td >< td class ="lr "> D</ td >< td class ="l "> 1</ td >< td class ="r "> 0</ td >< td colspan ="4 "class ="lr "> Vn</ td >< td colspan ="4 "class ="lr "> Vd</ td >< td class ="l "> 1</ td >< td class ="r "> 0</ td >< td colspan ="2 "class ="lr "> size</ td >< td class ="lr "> N</ td >< td class ="lr "> 0</ td >< td class ="lr "> M</ td >< td class ="lr "> 0</ td >< td colspan ="4 "class ="lr "> Vm</ td ></ tr >< tr class ="secondrow ">< td colspan ="8 "/>< td />< td />< td colspan ="2 "/>< td colspan ="4 "/>< td colspan ="4 "/>< td colspan ="2 "/>< td colspan ="2 "/>< td />< td class ="droppedname "> op</ td >< td />< td />< td colspan ="4 "/></ tr ></ tbody ></ table ></ div >< div class ="encoding ">< h4 class ="encoding "> Half-precision scalar< span class ="bitdiff "> (size == 01)</ span >< span style ="font-size:smaller; ">< br /> (FEAT_FP16) 49</ span ></ h4 >< a id ="VFMA_T2_H "/>< p class ="asm-code "> VFMA{< a href ="#sa_c "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.F16< a href ="#sa_sd "title ="32-bit SIMD&FP destination register (field "Vd:D") "> <Sd></ a > ,< a href ="#sa_sn "title ="First 32-bit SIMD&FP source register (field "Vn:N") "> <Sn></ a > ,< a href ="#sa_sm "title ="Second 32-bit SIMD&FP source register (field "Vm:M") "> <Sm></ a ></ p ></ div >< div class ="encoding ">< h4 class ="encoding "> Single-precision scalar< span class ="bitdiff "> (size == 10)</ span ></ h4 >< a id ="VFMA_T2_S "/>< p class ="asm-code "> VFMA{< a href ="#sa_c "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.F32< a href ="#sa_sd "title ="32-bit SIMD&FP destination register (field "Vd:D") "> <Sd></ a > ,< a href ="#sa_sn "title ="First 32-bit SIMD&FP source register (field "Vn:N") "> <Sn></ a > ,< a href ="#sa_sm "title ="Second 32-bit SIMD&FP source register (field "Vm:M") "> <Sm></ a ></ p ></ div >< div class ="encoding ">< h4 class ="encoding "> Double-precision scalar< span class ="bitdiff "> (size == 11)</ span ></ h4 >< a id ="VFMA_T2_D "/>< p class ="asm-code "> VFMA{< a href ="#sa_c "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <c></ a > }{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.F64< a href ="#sa_dd "title ="64-bit SIMD&FP destination register (field "D:Vd") "> <Dd></ a > ,< a href ="#sa_dn "title ="First 64-bit SIMD&FP source register (field "N:Vn") "> <Dn></ a > ,< a href ="#sa_dm "title ="Second 64-bit SIMD&FP source register (field "M:Vm") "> <Dm></ a ></ p ></ div >< p class ="pseudocode "> if FPSCR.Len != '000' || FPSCR.Stride != '00' then UNDEFINED; 50if size == '00' || (size == '01' && !IsFeatureImplemented(FEAT_FP16)) then UNDEFINED; 51if size == '01' &&< a href ="shared_pseudocode.html#impl-aarch32.InITBlock.0 "title ="function: boolean InITBlock() "> InITBlock</ a > () then UNPREDICTABLE; 52constant advsimd = FALSE; constant op1_neg = (op == '1'); 53constant integer esize = 8 <<< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (size); 54constant integer d = if size == '11' then< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (D:Vd) else< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vd:D); 55constant integer n = if size == '11' then< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (N:Vn) else< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vn:N); 56constant integer m = if size == '11' then< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (M:Vm) else< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vm:M); 57constant boolean floating_point = boolean UNKNOWN; 58constant integer regs = integer UNKNOWN; constant integer elements = integer UNKNOWN;</ p >< h3 > CONSTRAINED UNPREDICTABLE behavior</ h3 >< p > If< span class ="pseudocode "> size == '01' && InITBlock()</ span > , then one of the following behaviors must occur:</ p >< ul >< li > The instruction is< span class ="arm-defined-word "> undefined</ span > .</ li >< li > The instruction executes as if it passes the Condition code check.</ li >< li > The instruction executes as NOP. This means it behaves as if it fails the Condition code check.</ li ></ ul > 59< div class ="encoding-notes "/>< h3 class ="explanations "> Assembler Symbols</ h3 >< div class ="explanations ">< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <c></ td >< td >< a id ="sa_c_1 "/> 60 61 62 63 64 65 66< p class ="aml "> For encoding A1: see< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="Babbefhf "> Standard assembler syntax fields</ a > . This encoding must be unconditional.</ p > 67 68</ td ></ tr >< tr >< td />< td >< a id ="sa_c "/> 69 70< p class ="aml "> For encoding A2, T1 and T2: see< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="Babbefhf "> Standard assembler syntax fields</ a > .</ p > 71 72</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <q></ td >< td >< a id ="sa_q "/> 73 74< p class ="aml "> See< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="Babbefhf "> Standard assembler syntax fields</ a > .</ p > 75 76</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <dt></ td >< td >< a id ="sa_dt "/> 77< p > Is the data type for the elements of the vectors, 78 encoded in 79< q > sz</ q > : 80</ p > 81< table class ="valuetable "> 82 83< thead > 84< tr > 85< th class ="bitfield "> sz</ th > 86< th class ="symbol "> <dt></ th > 87</ tr > 88</ thead > 89< tbody > 90< tr > 91< td class ="bitfield "> 0</ td > 92< td class ="symbol "> F32</ td > 93</ tr > 94< tr > 95< td class ="bitfield "> 1</ td > 96< td class ="symbol "> F16</ td > 97</ tr > 98</ tbody > 99 100</ table > 101</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Qd></ td >< td >< a id ="sa_qd "/> 102 103< p class ="aml "> Is the 128-bit name of the SIMD&FP destination register, encoded in the "D:Vd" field as <Qd>*2.</ p > 104 105</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Qn></ td >< td >< a id ="sa_qn "/> 106 107< p class ="aml "> Is the 128-bit name of the first SIMD&FP source register, encoded in the "N:Vn" field as <Qn>*2.</ p > 108 109</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Qm></ td >< td >< a id ="sa_qm "/> 110 111< p class ="aml "> Is the 128-bit name of the second SIMD&FP source register, encoded in the "M:Vm" field as <Qm>*2.</ p > 112 113</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Dd></ td >< td >< a id ="sa_dd "/> 114 115< p class ="aml "> Is the 64-bit name of the SIMD&FP destination register, encoded in the "D:Vd" field.</ p > 116 117</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Dn></ td >< td >< a id ="sa_dn "/> 118 119< p class ="aml "> Is the 64-bit name of the first SIMD&FP source register, encoded in the "N:Vn" field.</ p > 120 121</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Dm></ td >< td >< a id ="sa_dm "/> 122 123< p class ="aml "> Is the 64-bit name of the second SIMD&FP source register, encoded in the "M:Vm" field.</ p > 124 125</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Sd></ td >< td >< a id ="sa_sd "/> 126 127< p class ="aml "> Is the 32-bit name of the SIMD&FP destination register, encoded in the "Vd:D" field.</ p > 128 129</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Sn></ td >< td >< a id ="sa_sn "/> 130 131< p class ="aml "> Is the 32-bit name of the first SIMD&FP source register, encoded in the "Vn:N" field.</ p > 132 133</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Sm></ td >< td >< a id ="sa_sm "/> 134 135< p class ="aml "> Is the 32-bit name of the second SIMD&FP source register, encoded in the "Vm:M" field.</ p > 136 137</ td ></ tr ></ table ></ div >< div class ="syntax-notes "/> 138< div class ="ps ">< a id ="execute "/>< h3 class ="pseudocode "> Operation</ h3 > 139< p class ="pseudocode "> if< a href ="shared_pseudocode.html#impl-aarch32.ConditionPassed.0 "title ="function: boolean ConditionPassed() "> ConditionPassed</ a > () then 140 EncodingSpecificOperations();< a href ="shared_pseudocode.html#impl-aarch32.CheckAdvSIMDOrVFPEnabled.2 "title ="function: CheckAdvSIMDOrVFPEnabled(boolean include_fpexc_check, boolean advsimd) "> CheckAdvSIMDOrVFPEnabled</ a > (TRUE, advsimd); 141 if advsimd then // Advanced SIMD instruction 142 constant< a href ="shared_pseudocode.html#FPCR_Type "title ="type FPCR_Type "> FPCR_Type</ a > fpcr =< a href ="shared_pseudocode.html#impl-aarch32.StandardFPCR.0 "title ="function: FPCR_Type StandardFPCR() "> StandardFPCR</ a > (); 143 for r = 0 to regs-1 144 for e = 0 to elements-1 145 bits(esize) op1 =< a href ="shared_pseudocode.html#impl-shared.Elem.read.3 "title ="accessor: bits(size) Elem[bits(N) vector, integer e, integer size] "> Elem</ a > [< a href ="shared_pseudocode.html#impl-aarch32.D.read.1 "title ="accessor: bits(64) D[integer n] "> D</ a > [n+r],e,esize]; 146 if op1_neg then op1 =< a href ="shared_pseudocode.html#impl-shared.FPNeg.2 "title ="function: bits(N) FPNeg(bits(N) op, FPCR_Type fpcr) "> FPNeg</ a > (op1, fpcr); 147< a href ="shared_pseudocode.html#impl-shared.Elem.write.3 "title ="accessor: Elem[bits(N) &vector, integer e, integer size] = bits(size) value "> Elem</ a > [< a href ="shared_pseudocode.html#impl-aarch32.D.write.1 "title ="accessor: D[integer n] = bits(64) value "> D</ a > [d+r],e,esize] =< a href ="shared_pseudocode.html#impl-shared.FPMulAdd.4 "title ="function: bits(N) FPMulAdd(bits(N) addend, bits(N) op1, bits(N) op2, FPCR_Type fpcr) "> FPMulAdd</ a > (< a href ="shared_pseudocode.html#impl-shared.Elem.read.3 "title ="accessor: bits(size) Elem[bits(N) vector, integer e, integer size] "> Elem</ a > [< a href ="shared_pseudocode.html#impl-aarch32.D.read.1 "title ="accessor: bits(64) D[integer n] "> D</ a > [d+r],e,esize], 148 op1,< a href ="shared_pseudocode.html#impl-shared.Elem.read.3 "title ="accessor: bits(size) Elem[bits(N) vector, integer e, integer size] "> Elem</ a > [< a href ="shared_pseudocode.html#impl-aarch32.D.read.1 "title ="accessor: bits(64) D[integer n] "> D</ a > [m+r],e,esize], fpcr); 149 150 else // VFP instruction 151 constant< a href ="shared_pseudocode.html#FPCR_Type "title ="type FPCR_Type "> FPCR_Type</ a > fpcr =< a href ="shared_pseudocode.html#impl-shared.EffectiveFPCR.0 "title ="function: FPCR_Type EffectiveFPCR() "> EffectiveFPCR</ a > (); 152 case esize of 153 when 16 154 constant op16 = if op1_neg then< a href ="shared_pseudocode.html#impl-shared.FPNeg.2 "title ="function: bits(N) FPNeg(bits(N) op, FPCR_Type fpcr) "> FPNeg</ a > (< a href ="shared_pseudocode.html#impl-aarch32.H.read.1 "title ="accessor: bits(16) H[integer n] "> H</ a > [n], fpcr) else< a href ="shared_pseudocode.html#impl-aarch32.H.read.1 "title ="accessor: bits(16) H[integer n] "> H</ a > [n]; 155< a href ="shared_pseudocode.html#impl-aarch32.H.write.1 "title ="accessor: H[integer n] = bits(16) value "> H</ a > [d] =< a href ="shared_pseudocode.html#impl-shared.FPMulAdd.4 "title ="function: bits(N) FPMulAdd(bits(N) addend, bits(N) op1, bits(N) op2, FPCR_Type fpcr) "> FPMulAdd</ a > (< a href ="shared_pseudocode.html#impl-aarch32.H.read.1 "title ="accessor: bits(16) H[integer n] "> H</ a > [d], op16,< a href ="shared_pseudocode.html#impl-aarch32.H.read.1 "title ="accessor: bits(16) H[integer n] "> H</ a > [m], fpcr); 156 when 32 157 constant op32 = if op1_neg then< a href ="shared_pseudocode.html#impl-shared.FPNeg.2 "title ="function: bits(N) FPNeg(bits(N) op, FPCR_Type fpcr) "> FPNeg</ a > (< a href ="shared_pseudocode.html#impl-aarch32.S.read.1 "title ="accessor: bits(32) S[integer n] "> S</ a > [n], fpcr) else< a href ="shared_pseudocode.html#impl-aarch32.S.read.1 "title ="accessor: bits(32) S[integer n] "> S</ a > [n]; 158< a href ="shared_pseudocode.html#impl-aarch32.S.write.1 "title ="accessor: S[integer n] = bits(32) value "> S</ a > [d] =< a href ="shared_pseudocode.html#impl-shared.FPMulAdd.4 "title ="function: bits(N) FPMulAdd(bits(N) addend, bits(N) op1, bits(N) op2, FPCR_Type fpcr) "> FPMulAdd</ a > (< a href ="shared_pseudocode.html#impl-aarch32.S.read.1 "title ="accessor: bits(32) S[integer n] "> S</ a > [d], op32,< a href ="shared_pseudocode.html#impl-aarch32.S.read.1 "title ="accessor: bits(32) S[integer n] "> S</ a > [m], fpcr); 159 when 64 160 constant op64 = if op1_neg then< a href ="shared_pseudocode.html#impl-shared.FPNeg.2 "title ="function: bits(N) FPNeg(bits(N) op, FPCR_Type fpcr) "> FPNeg</ a > (< a href ="shared_pseudocode.html#impl-aarch32.D.read.1 "title ="accessor: bits(64) D[integer n] "> D</ a > [n], fpcr) else< a href ="shared_pseudocode.html#impl-aarch32.D.read.1 "title ="accessor: bits(64) D[integer n] "> D</ a > [n]; 161< a href ="shared_pseudocode.html#impl-aarch32.D.write.1 "title ="accessor: D[integer n] = bits(64) value "> D</ a > [d] =< a href ="shared_pseudocode.html#impl-shared.FPMulAdd.4 "title ="function: bits(N) FPMulAdd(bits(N) addend, bits(N) op1, bits(N) op2, FPCR_Type fpcr) "> FPMulAdd</ a > (< a href ="shared_pseudocode.html#impl-aarch32.D.read.1 "title ="accessor: bits(64) D[integer n] "> D</ a > [d], op64,< a href ="shared_pseudocode.html#impl-aarch32.D.read.1 "title ="accessor: bits(64) D[integer n] "> D</ a > [m], fpcr);</ p > 162</ div > 163< hr />< table style ="margin: 0 auto; ">< tr >< td >< div class ="topbar ">< a href ="index.html "> Base Instructions</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="fpsimdindex.html "> SIMD&FP Instructions</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="a32_encindex.html "> A32 Instructions by Encoding</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="t32_encindex.html "> T32 Instructions by Encoding</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="shared_pseudocode.html "> Shared Pseudocode</ a ></ div ></ td >< td >< div class ="topbar ">< a href ="notice.html "> Proprietary Notice</ a ></ div ></ td ></ tr ></ table >< p class ="versions "> 164 Internal version only: isa v01_31, pseudocode v2024-09_rel 165 ; Build timestamp: 2024-09-26T13:26 166</ p >< p class ="copyconf "> 167 Copyright © 2010-2024 Arm Limited or its affiliates. All rights reserved. 168 This document is Non-Confidential. 169</ p ></ body ></ html >