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 > VDOT (by element) -- 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 "> VDOT (by element)</ h2 > 4< p class ="aml "> BFloat16 floating-point indexed dot product (vector, by element). This instruction delimits the source vectors into pairs of 16-bit BF16 elements. Each pair of elements in the first source vector is multiplied by the indexed pair of elements in the second source vector. The resulting single-precision products are then summed and added destructively to the single-precision element in the destination vector which aligns with the pair of BFloat16 values in the first source vector. The instruction does not update the< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="AArch32.fpscr "> FPSCR</ a > exception status.</ p > 5 6< p class ="desc "> 7 It has encodings from the following instruction sets: 8 A32 ( 9< a href ="#iclass_a1 "> A1</ a > 10 ) 11 and 12 T32 ( 13< a href ="#iclass_t1 "> T1</ a > 14 ) 15 . 16</ p > 17< h3 class ="classheading ">< a id ="iclass_a1 "/> A1< span style ="font-size:smaller; ">< br /> (FEAT_AA32BF16) 18</ span ></ 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 > 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 "> 0</ 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 > 1</ td >< td class ="r "> 0</ td >< td class ="lr "> 1</ td >< td class ="lr "> N</ td >< td class ="lr "> Q</ td >< td class ="lr "> M</ td >< td class ="lr "> 0</ td >< td colspan ="4 "class ="lr "> Vm</ td ></ tr ></ tbody ></ table ></ div >< div class ="encoding ">< h4 class ="encoding "> 64-bit SIMD vector< span class ="bitdiff "> (Q == 0)</ span ></ h4 >< a id ="VDOT_s_A1_D "/>< p class ="asm-code "> VDOT{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.BF16< 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 "Vm") "> <Dm></ a > [< a href ="#sa_index "title ="Element index [0-1] (field "M") "> <index></ a > ]</ p ></ div >< div class ="encoding ">< h4 class ="encoding "> 128-bit SIMD vector< span class ="bitdiff "> (Q == 1)</ span ></ h4 >< a id ="VDOT_s_A1_Q "/>< p class ="asm-code "> VDOT{< 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") "> <Dm></ a > [< a href ="#sa_index "title ="Element index [0-1] (field "M") "> <index></ a > ]</ p ></ div >< p class ="pseudocode "> if !IsFeatureImplemented(FEAT_AA32BF16) then UNDEFINED; 19if Q == '1' && (Vd<0> == '1' || Vn<0> == '1') then UNDEFINED; 20constant integer d =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (D:Vd); 21constant integer n =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (N:Vn); 22constant integer m =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vm); 23constant integer i =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (M); 24constant integer regs = if Q == '1' then 2 else 1;</ p > 25< h3 class ="classheading ">< a id ="iclass_t1 "/> T1< span style ="font-size:smaller; ">< br /> (FEAT_AA32BF16) 26</ span ></ 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 > 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 "> 0</ 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 > 1</ td >< td class ="r "> 0</ td >< td class ="lr "> 1</ td >< td class ="lr "> N</ td >< td class ="lr "> Q</ td >< td class ="lr "> M</ td >< td class ="lr "> 0</ td >< td colspan ="4 "class ="lr "> Vm</ td ></ tr ></ tbody ></ table ></ div >< div class ="encoding ">< h4 class ="encoding "> 64-bit SIMD vector< span class ="bitdiff "> (Q == 0)</ span ></ h4 >< a id ="VDOT_s_T1_D "/>< p class ="asm-code "> VDOT{< a href ="#sa_q "title ="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}} "> <q></ a > }.BF16< 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 "Vm") "> <Dm></ a > [< a href ="#sa_index "title ="Element index [0-1] (field "M") "> <index></ a > ]</ p ></ div >< div class ="encoding ">< h4 class ="encoding "> 128-bit SIMD vector< span class ="bitdiff "> (Q == 1)</ span ></ h4 >< a id ="VDOT_s_T1_Q "/>< p class ="asm-code "> VDOT{< 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") "> <Dm></ a > [< a href ="#sa_index "title ="Element index [0-1] (field "M") "> <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; 27if !IsFeatureImplemented(FEAT_AA32BF16) then UNDEFINED; 28if Q == '1' && (Vd<0> == '1' || Vn<0> == '1') then UNDEFINED; 29constant integer d =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (D:Vd); 30constant integer n =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (N:Vn); 31constant integer m =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (Vm); 32constant integer i =< a href ="shared_pseudocode.html#impl-shared.UInt.1 "title ="function: integer UInt(bits(N) x) "> UInt</ a > (M); 33constant integer regs = if Q == '1' then 2 else 1;</ p > 34< div class ="encoding-notes "/>< h3 class ="explanations "> Assembler Symbols</ h3 >< div class ="explanations ">< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <q></ td >< td >< a id ="sa_q "/> 35 36< p class ="aml "> See< a class ="armarm-xref "title ="Reference to Armv8 ARM section "data-linkend ="Babbefhf "> Standard assembler syntax fields</ a > .</ p > 37 38</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Qd></ td >< td >< a id ="sa_qd "/> 39 40< p class ="aml "> Is the 128-bit name of the SIMD&FP destination register, encoded in the "D:Vd" field as <Qd>*2.</ p > 41 42</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Qn></ td >< td >< a id ="sa_qn "/> 43 44< 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 > 45 46</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Dd></ td >< td >< a id ="sa_dd "/> 47 48< p class ="aml "> Is the 64-bit name of the SIMD&FP destination register, encoded in the "D:Vd" field.</ p > 49 50</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Dn></ td >< td >< a id ="sa_dn "/> 51 52< p class ="aml "> Is the 64-bit name of the first SIMD&FP source register, encoded in the "N:Vn" field.</ p > 53 54</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <Dm></ td >< td >< a id ="sa_dm "/> 55 56< p class ="aml "> Is the 64-bit name of the second SIMD&FP source register, encoded in the "Vm" field.</ p > 57 58</ td ></ tr ></ table >< table >< col class ="asyn-l "/>< col class ="asyn-r "/>< tr >< td > <index></ td >< td >< a id ="sa_index "/> 59 60< p class ="aml "> Is the element index in the range 0 to 1, encoded in the "M" field.</ p > 61 62</ td ></ tr ></ table ></ div >< div class ="syntax-notes "/> 63< div class ="ps ">< a id ="execute "/>< h3 class ="pseudocode "> Operation</ h3 > 64< p class ="pseudocode ">< a href ="shared_pseudocode.html#impl-aarch32.CheckAdvSIMDEnabled.0 "title ="function: CheckAdvSIMDEnabled() "> CheckAdvSIMDEnabled</ a > (); 65constant< 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 > (); 66 67bits(64) operand1; 68bits(64) operand2; 69bits(64) result; 70 71operand2 =< a href ="shared_pseudocode.html#impl-aarch32.Din.read.1 "title ="accessor: bits(64) Din[integer n] "> Din</ a > [m]; 72for r = 0 to regs-1 73 operand1 =< a href ="shared_pseudocode.html#impl-aarch32.Din.read.1 "title ="accessor: bits(64) Din[integer n] "> Din</ a > [n+r]; 74 result =< a href ="shared_pseudocode.html#impl-aarch32.Din.read.1 "title ="accessor: bits(64) Din[integer n] "> Din</ a > [d+r]; 75 for e = 0 to 1 76 constant bits(16) elt1_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 > [operand1, 2 * e + 0, 16]; 77 constant bits(16) elt1_b =< 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 + 1, 16]; 78 constant bits(16) elt2_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 > [operand2, 2 * i + 0, 16]; 79 constant bits(16) elt2_b =< 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, 2 * i + 1, 16]; 80 constant bits(32) sum =< a href ="shared_pseudocode.html#impl-shared.FPAdd_BF16.3 "title ="function: bits(N) FPAdd_BF16(bits(N) op1, bits(N) op2, FPCR_Type fpcr) "> FPAdd_BF16</ a > (< a href ="shared_pseudocode.html#impl-shared.BFMulH.3 "title ="function: bits(2*N) BFMulH(bits(N) op1, bits(N) op2, FPCR_Type fpcr) "> BFMulH</ a > (elt1_a, elt2_a, fpcr), 81< a href ="shared_pseudocode.html#impl-shared.BFMulH.3 "title ="function: bits(2*N) BFMulH(bits(N) op1, bits(N) op2, FPCR_Type fpcr) "> BFMulH</ a > (elt1_b, elt2_b, fpcr), fpcr); 82< 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.FPAdd_BF16.3 "title ="function: bits(N) FPAdd_BF16(bits(N) op1, bits(N) op2, FPCR_Type fpcr) "> FPAdd_BF16</ 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 > [result, e, 32], sum, fpcr); 83< a href ="shared_pseudocode.html#impl-aarch32.D.write.1 "title ="accessor: D[integer n] = bits(64) value "> D</ a > [d+r] = result;</ p > 84</ div > 85< 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 "> 86 Internal version only: isa v01_31, pseudocode v2024-09_rel 87 ; Build timestamp: 2024-09-26T13:26 88</ p >< p class ="copyconf "> 89 Copyright © 2010-2024 Arm Limited or its affiliates. All rights reserved. 90 This document is Non-Confidential. 91</ p ></ body ></ html >