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

Jonathan Dönszelmannwebsite start885cc4e

main
16.6 KiB123 linesraw
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>VFMSL (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&amp;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">VFMSL (by scalar)</h2>
4      <p class="aml">Vector Floating-point Multiply-Subtract Long from accumulator (by scalar). This instruction multiplies the negated vector elements in the first source SIMD&amp;FP register by the specified value in the second source SIMD&amp;FP register, and accumulates the product to the corresponding vector element of the destination SIMD&amp;FP register. 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      <p class="aml">In Armv8.2 and Armv8.3, this is an <span class="arm-defined-word">optional</span> instruction. From Armv8.4 it is mandatory for all implementations to support it.</p>
7      <div class="note"><hr class="note"/><h4>Note</h4>
8        <p class="aml"><a class="armarm-xref" title="Reference to Armv8 ARM section" data-linkend="AArch32.id_isar6">ID_ISAR6</a>.FHM indicates whether this instruction is supported.</p>
9      <hr class="note"/></div>
10    
11    <p class="desc">
12      It has encodings from the following instruction sets:
13       A32 (
14      <a href="#iclass_a1">A1</a>
15      )
16       and 
17       T32 (
18      <a href="#iclass_t1">T1</a>
19      )
20      .
21    </p>
22    <h3 class="classheading"><a id="iclass_a1"/>A1<span style="font-size:smaller;"><br/>(FEAT_FHM)
23          </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="lr">0</td><td class="lr">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><tr class="secondrow"><td colspan="8"/><td/><td/><td/><td class="droppedname">S</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="VFMSL_s_A1_D"/><p class="asm-code">VFMSL{<a href="#sa_q" title="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}}">&lt;q&gt;</a>}.F16 <a href="#sa_dd" title="64-bit SIMD&amp;FP destination register (field &quot;D:Vd&quot;)">&lt;Dd&gt;</a>, <a href="#sa_sn" title="First 32-bit SIMD&amp;FP source register (field &quot;Vn:N&quot;)">&lt;Sn&gt;</a>, <a href="#sa_sm" title="Second 32-bit SIMD&amp;FP source register (field &quot;Vm&lt;2:0&gt;:M&quot;)">&lt;Sm&gt;</a>[<a href="#sa_index_1" title="Element index [0-1] (field &quot;Vm&lt;3&gt;&quot;)">&lt;index&gt;</a>]</p></div><div class="encoding"><h4 class="encoding">128-bit SIMD vector<span class="bitdiff"> (Q == 1)</span></h4><a id="VFMSL_s_A1_Q"/><p class="asm-code">VFMSL{<a href="#sa_q" title="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}}">&lt;q&gt;</a>}.F16 <a href="#sa_qd" title="128-bit SIMD&amp;FP destination register (field &quot;D:Vd&quot;)">&lt;Qd&gt;</a>, <a href="#sa_dn" title="First 64-bit SIMD&amp;FP source register (field &quot;N:Vn&quot;)">&lt;Dn&gt;</a>, <a href="#sa_dm" title="Second 64-bit SIMD&amp;FP source register (field &quot;Vm&lt;2:0&gt;&quot;)">&lt;Dm&gt;</a>[<a href="#sa_index" title="Element index [0-3] (field &quot;M:Vm&lt;3&gt;&quot;)">&lt;index&gt;</a>]</p></div><p class="pseudocode">if !IsFeatureImplemented(FEAT_FHM) then UNDEFINED;
24if Q == '1' &amp;&amp; Vd&lt;0&gt; == '1' then UNDEFINED;
25
26constant integer d = <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(D:Vd);
27constant integer n = if Q == '1' 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);
28constant integer m = if Q == '1' then <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(Vm&lt;2:0&gt;) else <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(Vm&lt;2:0&gt;:M);
29
30constant integer index = if Q == '1' then <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(M:Vm&lt;3&gt;) else <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(Vm&lt;3&gt;);
31constant integer esize = 32;
32constant integer datasize = 32 &lt;&lt; <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(Q);
33constant boolean sub_op = S == '1';
34constant integer regs = if Q == '0' then 1 else 2;</p>
35    <h3 class="classheading"><a id="iclass_t1"/>T1<span style="font-size:smaller;"><br/>(FEAT_FHM)
36          </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="lr">0</td><td class="lr">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><tr class="secondrow"><td colspan="8"/><td/><td/><td/><td class="droppedname">S</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="VFMSL_s_T1_D"/><p class="asm-code">VFMSL{<a href="#sa_q" title="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}}">&lt;q&gt;</a>}.F16 <a href="#sa_dd" title="64-bit SIMD&amp;FP destination register (field &quot;D:Vd&quot;)">&lt;Dd&gt;</a>, <a href="#sa_sn" title="First 32-bit SIMD&amp;FP source register (field &quot;Vn:N&quot;)">&lt;Sn&gt;</a>, <a href="#sa_sm" title="Second 32-bit SIMD&amp;FP source register (field &quot;Vm&lt;2:0&gt;:M&quot;)">&lt;Sm&gt;</a>[<a href="#sa_index_1" title="Element index [0-1] (field &quot;Vm&lt;3&gt;&quot;)">&lt;index&gt;</a>]</p></div><div class="encoding"><h4 class="encoding">128-bit SIMD vector<span class="bitdiff"> (Q == 1)</span></h4><a id="VFMSL_s_T1_Q"/><p class="asm-code">VFMSL{<a href="#sa_q" title="See {xref{ARMARM_Babbefhf}{Standard assembler syntax fields}}">&lt;q&gt;</a>}.F16 <a href="#sa_qd" title="128-bit SIMD&amp;FP destination register (field &quot;D:Vd&quot;)">&lt;Qd&gt;</a>, <a href="#sa_dn" title="First 64-bit SIMD&amp;FP source register (field &quot;N:Vn&quot;)">&lt;Dn&gt;</a>, <a href="#sa_dm" title="Second 64-bit SIMD&amp;FP source register (field &quot;Vm&lt;2:0&gt;&quot;)">&lt;Dm&gt;</a>[<a href="#sa_index" title="Element index [0-3] (field &quot;M:Vm&lt;3&gt;&quot;)">&lt;index&gt;</a>]</p></div><p class="pseudocode">if <a href="shared_pseudocode.html#impl-aarch32.InITBlock.0" title="function: boolean InITBlock()">InITBlock</a>() then UNPREDICTABLE;
37if !IsFeatureImplemented(FEAT_FHM) then UNDEFINED;
38if Q == '1' &amp;&amp; Vd&lt;0&gt; == '1' then UNDEFINED;
39
40constant integer d = <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(D:Vd);
41constant integer n = if Q == '1' 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);
42constant integer m = if Q == '1' then <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(Vm&lt;2:0&gt;) else <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(Vm&lt;2:0&gt;:M);
43
44constant integer index = if Q == '1' then <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(M:Vm&lt;3&gt;) else <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(Vm&lt;3&gt;);
45constant integer esize = 32;
46constant integer datasize = 32 &lt;&lt; <a href="shared_pseudocode.html#impl-shared.UInt.1" title="function: integer UInt(bits(N) x)">UInt</a>(Q);
47constant boolean sub_op = S == '1';
48constant integer regs = if Q == '0' then 1 else 2;</p>
49  <div class="encoding-notes"/><h3 class="explanations">Assembler Symbols</h3><div class="explanations"><table><col class="asyn-l"/><col class="asyn-r"/><tr><td>&lt;q&gt;</td><td><a id="sa_q"/>
50        
51          <p class="aml">See <a class="armarm-xref" title="Reference to Armv8 ARM section" data-linkend="Babbefhf">Standard assembler syntax fields</a>.</p>
52        
53      </td></tr></table><table><col class="asyn-l"/><col class="asyn-r"/><tr><td>&lt;Qd&gt;</td><td><a id="sa_qd"/>
54        
55          <p class="aml">Is the 128-bit name of the SIMD&amp;FP destination register, encoded in the "D:Vd" field as &lt;Qd&gt;*2.</p>
56        
57      </td></tr></table><table><col class="asyn-l"/><col class="asyn-r"/><tr><td>&lt;Dn&gt;</td><td><a id="sa_dn"/>
58        
59          <p class="aml">Is the 64-bit name of the first SIMD&amp;FP source register, encoded in the "N:Vn" field.</p>
60        
61      </td></tr></table><table><col class="asyn-l"/><col class="asyn-r"/><tr><td>&lt;Dm&gt;</td><td><a id="sa_dm"/>
62        
63          <p class="aml">Is the 64-bit name of the second SIMD&amp;FP source register, encoded in the "Vm&lt;2:0&gt;" field.</p>
64        
65      </td></tr></table><table><col class="asyn-l"/><col class="asyn-r"/><tr><td>&lt;Dd&gt;</td><td><a id="sa_dd"/>
66        
67          <p class="aml">Is the 64-bit name of the SIMD&amp;FP destination register, encoded in the "D:Vd" field.</p>
68        
69      </td></tr></table><table><col class="asyn-l"/><col class="asyn-r"/><tr><td>&lt;Sn&gt;</td><td><a id="sa_sn"/>
70        
71          <p class="aml">Is the 32-bit name of the first SIMD&amp;FP source register, encoded in the "Vn:N" field.</p>
72        
73      </td></tr></table><table><col class="asyn-l"/><col class="asyn-r"/><tr><td>&lt;Sm&gt;</td><td><a id="sa_sm"/>
74        
75          <p class="aml">Is the 32-bit name of the second SIMD&amp;FP source register, encoded in the "Vm&lt;2:0&gt;:M" field.</p>
76        
77      </td></tr></table><table><col class="asyn-l"/><col class="asyn-r"/><tr><td>&lt;index&gt;</td><td><a id="sa_index_1"/>
78        
79          
80        
81        
82          <p class="aml">For the 64-bit SIMD vector variant: is the element index in the range 0 to 1, encoded in the "Vm&lt;3&gt;" field.</p>
83        
84      </td></tr><tr><td/><td><a id="sa_index"/>
85        
86          
87        
88        
89          <p class="aml">For the 128-bit SIMD vector variant: is the element index in the range 0 to 3, encoded in the "M:Vm&lt;3&gt;" field.</p>
90        
91      </td></tr></table></div><div class="syntax-notes"/>
92    <div class="ps"><a id="execute"/><h3 class="pseudocode">Operation</h3>
93      <p class="pseudocode"><a href="shared_pseudocode.html#impl-aarch32.CheckAdvSIMDEnabled.0" title="function: CheckAdvSIMDEnabled()">CheckAdvSIMDEnabled</a>();
94bits(datasize) operand1 ;
95bits(datasize) operand2 ;
96bits(64) operand3;
97bits(64) result;
98bits(esize DIV 2) element1;
99bits(esize DIV 2) element2;
100constant <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>();
101
102if Q=='0' then
103    operand1 = <a href="shared_pseudocode.html#impl-aarch32.S.read.1" title="accessor: bits(32) S[integer n]">S</a>[n]&lt;datasize-1:0&gt;;
104    operand2 = <a href="shared_pseudocode.html#impl-aarch32.S.read.1" title="accessor: bits(32) S[integer n]">S</a>[m]&lt;datasize-1:0&gt;;
105else
106    operand1 = <a href="shared_pseudocode.html#impl-aarch32.D.read.1" title="accessor: bits(64) D[integer n]">D</a>[n]&lt;datasize-1:0&gt;;
107    operand2 = <a href="shared_pseudocode.html#impl-aarch32.D.read.1" title="accessor: bits(64) D[integer n]">D</a>[m]&lt;datasize-1:0&gt;;
108element2 = <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, index, esize DIV 2];
109for r = 0 to regs-1
110    operand3 = <a href="shared_pseudocode.html#impl-aarch32.D.read.1" title="accessor: bits(64) D[integer n]">D</a>[d+r];
111    for e = 0 to 1
112        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*r+e, esize DIV 2];
113        if sub_op then element1 = <a href="shared_pseudocode.html#impl-shared.FPNeg.2" title="function: bits(N) FPNeg(bits(N) op, FPCR_Type fpcr)">FPNeg</a>(element1, fpcr);
114        <a href="shared_pseudocode.html#impl-shared.Elem.write.3" title="accessor: Elem[bits(N) &amp;vector, integer e, integer size] = bits(size) value">Elem</a>[result, e, esize] = <a href="shared_pseudocode.html#impl-shared.FPMulAddH.4" title="function: bits(N) FPMulAddH(bits(N) addend, bits(N DIV 2) op1, bits(N DIV 2) op2, FPCR_Type fpcr)">FPMulAddH</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>[operand3, e, esize], element1, element2, fpcr);
115    <a href="shared_pseudocode.html#impl-aarch32.D.write.1" title="accessor: D[integer n] = bits(64) value">D</a>[d+r] = result;</p>
116    </div>
117  <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&amp;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">
118      Internal version only: isa v01_31, pseudocode v2024-09_rel
119      ; Build timestamp: 2024-09-26T13:26
120    </p><p class="copyconf">
121      Copyright © 2010-2024 Arm Limited or its affiliates. All rights reserved.
122      This document is Non-Confidential.
123    </p></body></html>