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 > VFMAB, VFMAT (BFloat16, by scalar) -- 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 "> VFMAB, VFMAT (BFloat16, by scalar)</ h2 > 4< p class ="aml "> The BFloat16 floating-point widening multiply-add long instruction widens the even-numbered (bottom) or odd-numbered (top) 16-bit elements in the first source vector, and an indexed element in the second source vector from Bfloat16 to single-precision format. The instruction then multiplies and adds these values to the overlapping single-precision elements of the destination vector.</ p > 5< p class ="aml "> Unlike other BFloat16 multiplication instructions, this performs a fused multiply-add, without intermediate rounding that uses the Round to Nearest rounding mode and can generate a floating-point exception that causes cumulative exception bits in the< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="AArch32.fpscr "> FPSCR</ a > to be set.</ 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 ) 12 and 13 T32 ( 14< a href ="#iclass_t1 "> T1</ a > 15 ) 16 . 17</ p > 18< h3 class ="classheading ">< a id ="iclass_a1 "/> A1< span style ="font-size:smaller; ">< br /> (FEAT_AA32BF16) 19</ span ></ h3 >< 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 > 1</ td >< td > 1</ td >< td > 1</ td >< td class ="r "> 0</ td >< td class ="lr "> 0</ td >< td class ="lr "> D</ td >< td class ="l "> 1</ td >< td class ="r "> 1</ td >< td colspan ="4 "class ="lr "> Vn</ td >< td colspan ="4 "class ="lr "> Vd</ td >< td class ="l "> 1</ td >< td > 0</ 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 ></ tbody ></ table ></ div >< div class ="encoding ">< h4 class ="encoding "> A1</ h4 >< a id ="VFMA_bfs_A1_Q "/>< p class ="asm-code "> VFMA< a href ="#sa_bt "title ="Bottom or top element specifier (field "Q") "> <bt></ a > {< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.BF16< 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_dm "title ="Second 64-bit SIMD&FP source register (field "Vm<2:0>") "> <Dm></ a > [< a href ="#sa_index "title ="Element index [0-3] (field "M:Vm<3>") "> <index></ a > ]</ p ></ div >< p class ="pseudocode "> if !IsFeatureImplemented(FEAT_AA32BF16) then UNDEFINED; 20if Vd<0> == '1' || Vn<0> == '1' then UNDEFINED; 21constant integer d =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (D:Vd); 22constant integer n =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (N:Vn); 23constant integer m =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vm<2:0>); 24constant integer i =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (M:Vm<3>); 25constant integer elements = 128 DIV 32; 26constant integer sel =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Q);</ p > 27< h3 class ="classheading ">< a id ="iclass_t1 "/> T1< span style ="font-size:smaller; ">< br /> (FEAT_AA32BF16) 28</ span ></ h3 >< 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 > 1</ td >< td > 1</ td >< td > 1</ td >< td > 1</ td >< td class ="r "> 0</ td >< td class ="lr "> 0</ td >< td class ="lr "> D</ td >< td class ="l "> 1</ td >< td class ="r "> 1</ td >< td colspan ="4 "class ="lr "> Vn</ td >< td colspan ="4 "class ="lr "> Vd</ td >< td class ="l "> 1</ td >< td > 0</ 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 ></ tbody ></ table ></ div >< div class ="encoding ">< h4 class ="encoding "> T1</ h4 >< a id ="VFMA_bfs_T1_Q "/>< p class ="asm-code "> VFMA< a href ="#sa_bt "title ="Bottom or top element specifier (field "Q") "> <bt></ a > {< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.BF16< 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_dm "title ="Second 64-bit SIMD&FP source register (field "Vm<2:0>") "> <Dm></ a > [< a href ="#sa_index "title ="Element index [0-3] (field "M:Vm<3>") "> <index></ a > ]</ p ></ div >< p class ="pseudocode "> if< a href ="shared_pseudocode.html#impl-aarch32.InITBlock.0 "title ="function: boolean InITBlock() "> InITBlock</ a > () then UNPREDICTABLE; 29if !IsFeatureImplemented(FEAT_AA32BF16) then UNDEFINED; 30if Vd<0> == '1' || Vn<0> == '1' then UNDEFINED; 31constant integer d =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (D:Vd); 32constant integer n =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (N:Vn); 33constant integer m =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vm<2:0>); 34constant integer i =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (M:Vm<3>); 35constant integer elements = 128 DIV 32; 36constant integer sel =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Q);</ p > 37< div class ="encoding-notes "/>< h3 class ="explanations "> Assembler Symbols</ h3 >< div class ="explanations ">< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <bt></ td >< td >< a id ="sa_bt "/> 38< p > Is the bottom or top element specifier, 39 encoded in 40< q > Q</ q > : 41</ p > 42< table class ="valuetable "> 43 44< thead > 45< tr > 46< th class ="bitfield "> Q</ th > 47< th class ="symbol "> <bt></ th > 48</ tr > 49</ thead > 50< tbody > 51< tr > 52< td class ="bitfield "> 0</ td > 53< td class ="symbol "> B</ td > 54</ tr > 55< tr > 56< td class ="bitfield "> 1</ td > 57< td class ="symbol "> T</ td > 58</ tr > 59</ tbody > 60 61</ table > 62</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <q></ td >< td >< a id ="sa_q "/> 63 64< p class ="aml "> See< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="Babbefhf "> Standard assembler syntax fields</ a > .</ p > 65 66</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Qd></ td >< td >< a id ="sa_qd "/> 67 68< p class ="aml "> Is the 128-bit name of the SIMD&FP destination register, encoded in the "D:Vd" field as <Qd>*2.</ p > 69 70</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Qn></ td >< td >< a id ="sa_qn "/> 71 72< 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 > 73 74</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Dm></ td >< td >< a id ="sa_dm "/> 75 76< p class ="aml "> Is the 64-bit name of the second SIMD&FP source register, encoded in the "Vm<2:0>" field.</ p > 77 78</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <index></ td >< td >< a id ="sa_index "/> 79 80< p class ="aml "> Is the element index in the range 0 to 3, encoded in the "M:Vm<3>" field.</ p > 81 82</ td ></ tr ></ table ></ div >< div class ="syntax-notes "/> 83< div class ="ps ">< a id ="execute "/>< h3 class ="pseudocode "> Operation</ h3 > 84< p class ="pseudocode ">< a href ="shared_pseudocode.html#impl-aarch32.CheckAdvSIMDEnabled.0 "title ="function: CheckAdvSIMDEnabled() "> CheckAdvSIMDEnabled</ a > (); 85constant< 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 > (); 86 87constant bits(128) operand1 =< a href ="shared_pseudocode.html#impl-aarch32.Q.read.1 "title ="accessor: bits(128) Q[integer n] "> Q</ a > [n>>1]; 88constant bits(64) operand2 =< a href ="shared_pseudocode.html#impl-aarch32.D.read.1 "title ="accessor: bits(64) D[integer n] "> D</ a > [m]; 89constant bits(128) operand3 =< a href ="shared_pseudocode.html#impl-aarch32.Q.read.1 "title ="accessor: bits(128) Q[integer n] "> Q</ a > [d>>1]; 90bits(128) result; 91 92constant bits(32) element2 =< a href ="shared_pseudocode.html#impl-shared.Elem.read.3 "title ="accessor: bits(size) Elem[bits(N) vector, integer e, integer size] "> Elem</ a > [operand2, i, 16] :< a href ="shared_pseudocode.html#impl-shared.Zeros.1 "title ="function: bits(N) Zeros(integer N) "> Zeros</ a > (16); 93 94for e = 0 to elements-1 95 constant bits(32) element1 =< a href ="shared_pseudocode.html#impl-shared.Elem.read.3 "title ="accessor: bits(size) Elem[bits(N) vector, integer e, integer size] "> Elem</ a > [operand1, 2 * e + sel, 16] :< a href ="shared_pseudocode.html#impl-shared.Zeros.1 "title ="function: bits(N) Zeros(integer N) "> Zeros</ a > (16); 96 constant bits(32) addend =< a href ="shared_pseudocode.html#impl-shared.Elem.read.3 "title ="accessor: bits(size) Elem[bits(N) vector, integer e, integer size] "> Elem</ a > [operand3, e, 32]; 97< 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 > [result, e, 32] =< 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 > (addend, element1, element2, fpcr); 98 99< a href ="shared_pseudocode.html#impl-aarch32.Q.write.1 "title ="accessor: Q[integer n] = bits(128) value "> Q</ a > [d>>1] = result;</ p > 100</ div > 101< 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 "> 102 Internal version only: isa v01_31, pseudocode v2024-09_rel 103 ; Build timestamp: 2024-09-26T13:26 104</ p >< p class ="copyconf "> 105 Copyright © 2010-2024 Arm Limited or its affiliates. All rights reserved. 106 This document is Non-Confidential. 107</ p ></ body ></ html >