SherbyNet - /page/wikibook/entry.mu

Micron Document

<!DOCTYPE html>

<title>Transactional Synchronization Extensions</title>

</head>

<span id="openzim-page-title" class="mw-page-title-main"><span class="mw-page-title-main">Transactional Synchronization Extensions</span></span>

</h1>

</header>

<p><b>Transactional Synchronization Extensions</b> (<b>TSX</b>), also called <b>Transactional Synchronization Extensions New Instructions</b> (<b>TSX-NI</b>), is an extension to the <a href="X86" title="X86">x86</a> <a href="Instruction_set_architecture" title="Instruction set architecture">instruction set architecture</a> (ISA) that adds hardware <a href="Transactional_memory" title="Transactional memory">transactional memory</a> support, speeding up execution of multi-threaded software through lock elision. According to different benchmarks, TSX/TSX-NI can provide around 40% faster applications execution in specific workloads, and 4–5 times more database <a href="Transactions_per_second" title="Transactions per second">transactions per second</a> (TPS).<sup id="cite_ref-1" class="reference"><a href="#cite_note-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-2" class="reference"><a href="#cite_note-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-3" class="reference"><a href="#cite_note-3"><span class="cite-bracket">[</span>3<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-4" class="reference"><a href="#cite_note-4"><span class="cite-bracket">[</span>4<span class="cite-bracket">]</span></a></sup>

</p><p>TSX/TSX-NI was documented by <a href="Intel" title="Intel">Intel</a> in February 2012, and debuted in June 2013 on selected Intel <a href="Microprocessor" title="Microprocessor">microprocessors</a> based on the <a href="Haswell_(microarchitecture)" title="Haswell (microarchitecture)">Haswell</a> microarchitecture.<sup id="cite_ref-5" class="reference"><a href="#cite_note-5"><span class="cite-bracket">[</span>5<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-6" class="reference"><a href="#cite_note-6"><span class="cite-bracket">[</span>6<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-7" class="reference"><a href="#cite_note-7"><span class="cite-bracket">[</span>7<span class="cite-bracket">]</span></a></sup> Haswell processors below 45xx as well as R-series and K-series (with unlocked multiplier) <a href="Stock_keeping_unit" title="Stock keeping unit">SKUs</a> do not support TSX/TSX-NI.<sup id="cite_ref-comparison_8-0" class="reference"><a href="#cite_note-comparison-8"><span class="cite-bracket">[</span>8<span class="cite-bracket">]</span></a></sup> In August 2014, Intel announced a bug in the TSX/TSX-NI implementation on current steppings of Haswell, Haswell-E, Haswell-EP and early <a href="Broadwell_(microarchitecture)" title="Broadwell (microarchitecture)">Broadwell</a> CPUs, which resulted in disabling the TSX/TSX-NI feature on affected CPUs via a <a href="Microcode" title="Microcode">microcode</a> update.<sup id="cite_ref-techreport-26911_9-0" class="reference"><a href="#cite_note-techreport-26911-9"><span class="cite-bracket">[</span>9<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-intel-spec-update_10-0" class="reference"><a href="#cite_note-intel-spec-update-10"><span class="cite-bracket">[</span>10<span class="cite-bracket">]</span></a></sup>

</p><p>In 2016, a <a href="Side-channel_attack" title="Side-channel attack">side-channel</a> <a href="Timing_attack" title="Timing attack">timing attack</a> was found by abusing the way TSX/TSX-NI handles transactional faults (i.e. <a href="Page_fault" title="Page fault">page faults</a>) in order to break <a href="KASLR" class="mw-redirect" title="KASLR">kernel address space layout randomization</a> (KASLR) on all major operating systems.<sup id="cite_ref-Breaking_Kernel_Address_Space_Layout_Randomization_with_Intel_TSX_11-0" class="reference"><a href="#cite_note-Breaking_Kernel_Address_Space_Layout_Randomization_with_Intel_TSX-11"><span class="cite-bracket">[</span>11<span class="cite-bracket">]</span></a></sup> In 2021, Intel released a microcode update that disabled the TSX/TSX-NI feature on CPU generations from <a href="Skylake_(microarchitecture)" title="Skylake (microarchitecture)">Skylake</a> to <a href="Coffee_Lake" title="Coffee Lake">Coffee Lake</a>, as a mitigation for discovered security issues.<sup id="cite_ref-12" class="reference"><a href="#cite_note-12"><span class="cite-bracket">[</span>12<span class="cite-bracket">]</span></a></sup>

</p><p>While TSX/TSX-NI is not supported anymore in desktop-class processors, it remains supported in the <a href="Xeon" title="Xeon">Xeon</a> line of processors (at least on specific models, as of the 6th generation).<sup id="cite_ref-13" class="reference"><a href="#cite_note-13"><span class="cite-bracket">[</span>13<span class="cite-bracket">]</span></a></sup>

</p><p>Support for TSX/TSX-NI emulation is provided as part of the Intel Software Development Emulator.<sup id="cite_ref-14" class="reference"><a href="#cite_note-14"><span class="cite-bracket">[</span>14<span class="cite-bracket">]</span></a></sup> There is also experimental support for TSX/TSX-NI emulation in a <a href="QEMU" title="QEMU">QEMU</a> fork.<sup id="cite_ref-15" class="reference"><a href="#cite_note-15"><span class="cite-bracket">[</span>15<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading2"><h2 id="Features">Features</h2></div>

<p>TSX/TSX-NI provides two software interfaces for designating code regions for transactional execution. <b>Hardware Lock Elision</b> (HLE) is an instruction prefix-based interface designed to be backward compatible with processors without TSX/TSX-NI support. <b>Restricted Transactional Memory</b> (RTM) is a new instruction set interface that provides greater flexibility for programmers.<sup id="cite_ref-anandtech-tsx_16-0" class="reference"><a href="#cite_note-anandtech-tsx-16"><span class="cite-bracket">[</span>16<span class="cite-bracket">]</span></a></sup>

</p><p>TSX/TSX-NI enables <a href="Speculative_execution" title="Speculative execution">optimistic execution</a> of transactional code regions. The hardware monitors multiple threads for conflicting memory accesses, while aborting and rolling back transactions that cannot be successfully completed. Mechanisms are provided for software to detect and handle failed transactions.<sup id="cite_ref-anandtech-tsx_16-1" class="reference"><a href="#cite_note-anandtech-tsx-16"><span class="cite-bracket">[</span>16<span class="cite-bracket">]</span></a></sup>

</p><p>In other words, lock elision through transactional execution uses memory transactions as a fast path where possible, while the slow (fallback) path is still a normal lock.

</p>

<div class="mw-heading mw-heading3"><h3 id="Hardware_Lock_Elision">Hardware Lock Elision</h3></div>

<p>Hardware Lock Elision (HLE) adds two new instruction prefixes, <code>XACQUIRE</code> and <code>XRELEASE</code>. These two prefixes reuse the <a href="Opcodes" class="mw-redirect" title="Opcodes">opcodes</a> of the existing <code>REPNE</code> / <code>REPE</code> prefixes (<code>F2H</code> / <code>F3H</code>). On processors that do not support HLE, <code>REPNE</code> / <code>REPE</code> prefixes are ignored on instructions for which the <code>XACQUIRE</code> / <code>XRELEASE</code> are valid, thus enabling backward compatibility.<sup id="cite_ref-17" class="reference"><a href="#cite_note-17"><span class="cite-bracket">[</span>17<span class="cite-bracket">]</span></a></sup>

</p><p>The <code>XACQUIRE</code> prefix hint can only be used with the following instructions with an explicit <code>LOCK</code> prefix: <code>ADD</code>, <code>ADC</code>, <code>AND</code>, <code>BTC</code>, <code>BTR</code>, <code>BTS</code>, <code>CMPXCHG</code>, <code>CMPXCHG8B</code>, <code>DEC</code>, <code>INC</code>, <code>NEG</code>, <code>NOT</code>, <code>OR</code>, <code>SBB</code>, <code>SUB</code>, <code>XOR</code>, <code>XADD</code>, and <code>XCHG</code>. The <code>XCHG</code> instruction can be used without the <code>LOCK</code> prefix as well.

</p><p>The <code>XRELEASE</code> prefix hint can be used both with the instructions listed above, and with the <code>MOV mem, reg</code> and <code>MOV mem, imm</code> instructions.

</p><p>HLE allows optimistic execution of a critical section by skipping the write to a lock, so that the lock appears to be free to other threads. A failed transaction results in execution restarting from the <code>XACQUIRE</code>-prefixed instruction, but treating the instruction as if the <code>XACQUIRE</code> prefix were not present.

</p>

<div class="mw-heading mw-heading3"><h3 id="Restricted_Transactional_Memory">Restricted Transactional Memory</h3></div>

<p>Restricted Transactional Memory (RTM) is an alternative implementation to HLE which gives the programmer the flexibility to specify a fallback code path that is executed when a transaction cannot be successfully executed. Unlike HLE, RTM is not backward compatible with processors that do not support it. For backward compatibility, programs are required to detect support for RTM in the CPU before using the new instructions.

</p><p>RTM adds three new instructions: <code>XBEGIN</code>, <code>XEND</code> and <code>XABORT</code>. The <code>XBEGIN</code> and <code>XEND</code> instructions mark the start and the end of a transactional code region; the <code>XABORT</code> instruction explicitly aborts a transaction. Transaction failure redirects the processor to the fallback code path specified by the <code>XBEGIN</code> instruction, with the abort status returned in the <code>EAX</code> register.

</p>

<th>EAX register<br>bit position</th>

<th>Meaning

</th></tr>

<tr>

<td>Set if abort caused by <code>XABORT</code> instruction.

</td></tr>

<tr>

<td>If set, the transaction may succeed on a retry. This bit is always clear if bit 0 is set.

</td></tr>

<tr>

<td>Set if another logical processor conflicted with a memory address that was part of the transaction that aborted.

</td></tr>

<tr>

<td>Set if an internal buffer overflowed.

</td></tr>

<tr>

<td>Set if debug breakpoint was hit.

</td></tr>

<tr>

<td>Set if an abort occurred during execution of a nested transaction.

</td></tr>

<tr>

<td>Reserved.

</td></tr>

<tr>

<td><code>XABORT</code> argument (only valid if bit 0 set, otherwise reserved).

</td></tr></tbody></table>

<div class="mw-heading mw-heading3"><h3 id="XTEST_instruction"><code>XTEST</code> instruction</h3></div>

<p>TSX/TSX-NI provides a new <code>XTEST</code> instruction that returns whether the processor is executing a transactional region. This instruction is supported by the processor if it supports HLE or RTM or both.

</p>

<div class="mw-heading mw-heading3"><h3 id="TSX_Suspend_Load_Address_Tracking">TSX Suspend Load Address Tracking</h3></div>

<p>TSX/TSX-NI Suspend Load Address Tracking (TSXLDTRK) is an instruction set extension that allows to temporarily disable tracking loads from memory in a section of code within a transactional region. This feature extends HLE and RTM, and its support in the processor must be detected separately.

</p><p>TSXLDTRK introduces two new instructions, <code>XSUSLDTRK</code> and <code>XRESLDTRK</code>, for suspending and resuming load address tracking, respectively. While the tracking is suspended, any loads from memory will not be added to the transaction read set. This means that, unless these memory locations were added to the transaction read or write sets outside the suspend region, writes at these locations by other threads will not cause transaction abort. Suspending load address tracking for a portion of code within a transactional region allows to reduce the amount of memory that needs to be tracked for read-write conflicts and therefore increase the probability of successful commit of the transaction.

</p>

<div class="mw-heading mw-heading2"><h2 id="Implementation">Implementation</h2></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .hatnote{font-style:italic}.mw-parser-output div.hatnote{padding-left:1.6em;margin-bottom:0.5em}.mw-parser-output .hatnote i{font-style:normal}.mw-parser-output .hatnote+link+.hatnote{margin-top:-0.5em}@media print{body.ns-0 .mw-parser-output .hatnote{display:none!important}}

/* end https://en.wikipedia.org/ */

</style><div role="note" class="hatnote navigation-not-searchable">See also: <a href="Transactional_memory#Available_implementations" title="Transactional memory">Transactional memory § Available implementations</a></div>

<p>Intel's TSX/TSX-NI specification describes how the transactional memory is exposed to programmers, but withholds details on the actual transactional memory implementation.<sup id="cite_ref-haswell-tm_18-0" class="reference"><a href="#cite_note-haswell-tm-18"><span class="cite-bracket">[</span>18<span class="cite-bracket">]</span></a></sup> Intel specifies in its developer's and optimization manuals that Haswell maintains both read-sets and write-sets at the granularity of a cache line, tracking addresses in the L1 data cache of the processor.<sup id="cite_ref-intel-arch-sdm_19-0" class="reference"><a href="#cite_note-intel-arch-sdm-19"><span class="cite-bracket">[</span>19<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-intel-arch-optimization_20-0" class="reference"><a href="#cite_note-intel-arch-optimization-20"><span class="cite-bracket">[</span>20<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-21" class="reference"><a href="#cite_note-21"><span class="cite-bracket">[</span>21<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-22" class="reference"><a href="#cite_note-22"><span class="cite-bracket">[</span>22<span class="cite-bracket">]</span></a></sup> Intel also states that data conflicts are detected through the <a href="Cache_coherence" title="Cache coherence">cache coherence</a> protocol.<sup id="cite_ref-intel-arch-optimization_20-1" class="reference"><a href="#cite_note-intel-arch-optimization-20"><span class="cite-bracket">[</span>20<span class="cite-bracket">]</span></a></sup>

</p><p>Haswell's L1 data cache has an associativity of eight. This means that in this implementation, a transactional execution that writes to nine distinct locations mapping to the same cache set will abort. However, due to micro-architectural implementations, this does not mean that fewer accesses to the same set are guaranteed to never abort. Additionally, in CPU configurations with <a href="Hyper-Threading_Technology" class="mw-redirect" title="Hyper-Threading Technology">Hyper-Threading Technology</a>, the L1 cache is shared between the two threads on the same core, so operations in a sibling logical processor of the same core can cause evictions.<sup id="cite_ref-intel-arch-optimization_20-2" class="reference"><a href="#cite_note-intel-arch-optimization-20"><span class="cite-bracket">[</span>20<span class="cite-bracket">]</span></a></sup>

</p><p>Independent research points into Haswell’s transactional memory most likely being a deferred update system using the per-core caches for transactional data and register checkpoints.<sup id="cite_ref-haswell-tm_18-1" class="reference"><a href="#cite_note-haswell-tm-18"><span class="cite-bracket">[</span>18<span class="cite-bracket">]</span></a></sup> In other words, Haswell is more likely to use the cache-based transactional memory system, as it is a much less risky implementation choice. On the other hand, Intel's <a href="Skylake_(microarchitecture)" title="Skylake (microarchitecture)">Skylake</a> or later may combine this cache-based approach with <i>memory ordering buffer</i> (MOB) for the same purpose, possibly also providing multi-versioned transactional memory that is more amenable to <a href="Speculative_multithreading" title="Speculative multithreading">speculative multithreading</a>.<sup id="cite_ref-23" class="reference"><a href="#cite_note-23"><span class="cite-bracket">[</span>23<span class="cite-bracket">]</span></a></sup>

</p>

<div class="mw-heading mw-heading2"><h2 id="History_and_bugs">History and bugs</h2></div>

<p>In August 2014, Intel announced that a bug exists in the TSX/TSX-NI implementation on Haswell, Haswell-E, Haswell-EP and early Broadwell CPUs, which resulted in disabling the TSX/TSX-NI feature on affected CPUs via a microcode update.<sup id="cite_ref-techreport-26911_9-1" class="reference"><a href="#cite_note-techreport-26911-9"><span class="cite-bracket">[</span>9<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-intel-spec-update_10-1" class="reference"><a href="#cite_note-intel-spec-update-10"><span class="cite-bracket">[</span>10<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-24" class="reference"><a href="#cite_note-24"><span class="cite-bracket">[</span>24<span class="cite-bracket">]</span></a></sup> The bug was fixed in F-0 steppings of the vPro-enabled Core M-5Y70 Broadwell CPU in November 2014.<sup id="cite_ref-intel-330836-003_25-0" class="reference"><a href="#cite_note-intel-330836-003-25"><span class="cite-bracket">[</span>25<span class="cite-bracket">]</span></a></sup>

</p><p>The bug was found and then reported during a diploma thesis in the School of Electrical and Computer Engineering of the <a href="National_Technical_University_of_Athens" title="National Technical University of Athens">National Technical University of Athens</a>.<sup id="cite_ref-26" class="reference"><a href="#cite_note-26"><span class="cite-bracket">[</span>26<span class="cite-bracket">]</span></a></sup>

</p><p>In October 2018, Intel disclosed a TSX/TSX-NI memory ordering issue found in some <a href="Skylake_(microarchitecture)" title="Skylake (microarchitecture)">Skylake</a> processors.<sup id="cite_ref-27" class="reference"><a href="#cite_note-27"><span class="cite-bracket">[</span>27<span class="cite-bracket">]</span></a></sup> As a result of a microcode update, HLE support was disabled in the affected CPUs, and RTM was mitigated by sacrificing one performance counter when used outside of Intel <a href="Software_Guard_Extensions" title="Software Guard Extensions">SGX</a> mode or System Management Mode (<a href="System_Management_Mode" title="System Management Mode">SMM</a>). System software would have to either effectively disable RTM or update performance monitoring tools not to use the affected performance counter.

</p><p>In June 2021, Intel published a microcode update that further disables TSX/TSX-NI on various Xeon and Core processor models from <a href="Skylake_(microarchitecture)" title="Skylake (microarchitecture)">Skylake</a> through <a href="Coffee_Lake" title="Coffee Lake">Coffee Lake</a> and <a href="Whiskey_Lake_(microprocessor)" class="mw-redirect" title="Whiskey Lake (microprocessor)">Whiskey Lake</a> as a mitigation for TSX Asynchronous Abort (TAA) vulnerability. Earlier mitigation for memory ordering issue was removed.<sup id="cite_ref-28" class="reference"><a href="#cite_note-28"><span class="cite-bracket">[</span>28<span class="cite-bracket">]</span></a></sup> By default, with the updated microcode, the processor would still indicate support for RTM but would always abort the transaction. System software is able to detect this mode of operation and mask support for TSX/TSX-NI from the <a href="CPUID#EAX=7,_ECX=0:_Extended_Features" title="CPUID"><code>CPUID</code></a> instruction, preventing detection of TSX/TSX-NI by applications. System software may also enable the "Unsupported Software Development Mode", where RTM is fully active, but in this case RTM usage may be subject to the issues described earlier, and therefore this mode should not be enabled on production systems. On some systems RTM can't be re-enabled when SGX is active. HLE is always disabled.

</p><p>According to Intel 64 and IA-32 Architectures Software Developer's Manual from May 2020, Volume 1, Chapter 2.5 Intel Instruction Set Architecture And Features Removed,<sup id="cite_ref-intel-arch-sdm_19-1" class="reference"><a href="#cite_note-intel-arch-sdm-19"><span class="cite-bracket">[</span>19<span class="cite-bracket">]</span></a></sup> HLE has been removed from Intel products released in 2019 and later. RTM is not documented as removed. However, Intel 10th generation <a href="Comet_Lake_(microprocessor)" class="mw-redirect" title="Comet Lake (microprocessor)">Comet Lake</a> and <a href="Ice_Lake_(microprocessor)" title="Ice Lake (microprocessor)">Ice Lake</a> client processors, which were released in 2020, do not support TSX/TSX-NI,<sup id="cite_ref-29" class="reference"><a href="#cite_note-29"><span class="cite-bracket">[</span>29<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-30" class="reference"><a href="#cite_note-30"><span class="cite-bracket">[</span>30<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-31" class="reference"><a href="#cite_note-31"><span class="cite-bracket">[</span>31<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-32" class="reference"><a href="#cite_note-32"><span class="cite-bracket">[</span>32<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-33" class="reference"><a href="#cite_note-33"><span class="cite-bracket">[</span>33<span class="cite-bracket">]</span></a></sup> including both HLE and RTM. Engineering versions of Comet Lake processors were still retaining TSX/TSX-NI support.

</p><p>In Intel Architecture Instruction Set Extensions Programming Reference revision 41 from October 2020,<sup id="cite_ref-intel-arch-extensions_34-0" class="reference"><a href="#cite_note-intel-arch-extensions-34"><span class="cite-bracket">[</span>34<span class="cite-bracket">]</span></a></sup> a new TSXLDTRK instruction set extension was documented. It was first included in <a href="Sapphire_Rapids_(microprocessor)" class="mw-redirect" title="Sapphire Rapids (microprocessor)">Sapphire Rapids</a> processors released in January 2023.

</p>

<ul><li><a href="Advanced_Synchronization_Facility" title="Advanced Synchronization Facility">Advanced Synchronization Facility</a> – AMD's competing technology</li></ul>

<div class="mw-heading mw-heading2"><h2 id="References">References</h2></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .reflist{margin-bottom:0.5em;list-style-type:decimal}@media screen{.mw-parser-output .reflist{font-size:90%}}.mw-parser-output .reflist .references{font-size:100%;margin-bottom:0;list-style-type:inherit}.mw-parser-output .reflist-columns-2{column-width:30em}.mw-parser-output .reflist-columns-3{column-width:25em}.mw-parser-output .reflist-columns{margin-top:0.3em}.mw-parser-output .reflist-columns ol{margin-top:0}.mw-parser-output .reflist-columns li{page-break-inside:avoid;break-inside:avoid-column}.mw-parser-output .reflist-upper-alpha{list-style-type:upper-alpha}.mw-parser-output .reflist-upper-roman{list-style-type:upper-roman}.mw-parser-output .reflist-lower-alpha{list-style-type:lower-alpha}.mw-parser-output .reflist-lower-greek{list-style-type:lower-greek}.mw-parser-output .reflist-lower-roman{list-style-type:lower-roman}

/* end https://en.wikipedia.org/ */

</style><div class="reflist reflist-columns references-column-width" style="column-width: 30em;">

/* start https://en.wikipedia.org/ */

.mw-parser-output cite.citation{font-style:inherit;word-wrap:break-word}.mw-parser-output .citation q{quotes:"\"""\"""'""'"}.mw-parser-output .citation:target{background-color:rgba(0,127,255,0.133)}.mw-parser-output .id-lock-free.id-lock-free a{background:url("./mw/Lock-green.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-limited.id-lock-limited a,.mw-parser-output .id-lock-registration.id-lock-registration a{background:url("./mw/Lock-gray-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-subscription.id-lock-subscription a{background:url("./mw/Lock-red-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .cs1-ws-icon a{background:url("./mw/Wikisource-logo.svg")right 0.1em center/12px no-repeat}body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-free a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-limited a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-registration a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-subscription a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .cs1-ws-icon a{background-size:contain;padding:0 1em 0 0}.mw-parser-output .cs1-code{color:inherit;background:inherit;border:none;padding:inherit}.mw-parser-output .cs1-hidden-error{display:none;color:var(--color-error,#d33)}.mw-parser-output .cs1-visible-error{color:var(--color-error,#d33)}.mw-parser-output .cs1-maint{display:none;color:#085;margin-left:0.3em}.mw-parser-output .cs1-kern-left{padding-left:0.2em}.mw-parser-output .cs1-kern-right{padding-right:0.2em}.mw-parser-output .citation .mw-selflink{font-weight:inherit}@media screen{.mw-parser-output .cs1-format{font-size:95%}html.skin-theme-clientpref-night .mw-parser-output .cs1-maint{color:#18911f}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .cs1-maint{color:#18911f}}

/* end https://en.wikipedia.org/ */

</style><cite id="CITEREFRichard_M._YooChristopher_J._HughesKonrad_LaiRavi_Rajwar2013" class="citation web cs1">Richard M. Yoo; Christopher J. Hughes; Konrad Lai; Ravi Rajwar (November 2013). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20161024172155/http://pcl.intel-research.net/publications/SC13-TSX.pdf">"Performance Evaluation of Intel Transactional Synchronization Extensions for High-Performance Computing"</a> <span class="cs1-format">(PDF)</span>. <i>intel-research.net</i>. Archived from <a rel="nofollow" class="external text" href="http://pcl.intel-research.net/publications/SC13-TSX.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2016-10-24<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-14</span></span>.</cite></span>

</li>

<li id="cite_note-2"><span class="mw-cite-backlink"><b><a href="#cite_ref-2">^</a></b></span> <span class="reference-text"><cite id="CITEREFTomas_KarnagelRoman_DementievRavi_RajwarKonrad_Lai2014" class="citation web cs1">Tomas Karnagel; Roman Dementiev; Ravi Rajwar; Konrad Lai; Thomas Legler; Benjamin Schlegel; Wolfgang Lehner (February 2014). <a rel="nofollow" class="external text" href="http://software.intel.com/sites/default/files/managed/4d/2a/hpca_TSX.pdf">"Improving In-Memory Database Index Performance with Intel Transactional Synchronization Extensions"</a> <span class="cs1-format">(PDF)</span>. <i>software.intel.com</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2014-03-03</span></span>.</cite></span>

</li>

<li id="cite_note-3"><span class="mw-cite-backlink"><b><a href="#cite_ref-3">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20131029202737/http://sc13.supercomputing.org/schedule/event_detail.php?evid=pap260">"Performance Evaluation of Intel Transactional Synchronization Extensions for High Performance Computing"</a>. <i>supercomputing.org</i>. November 2013. Archived from <a rel="nofollow" class="external text" href="http://sc13.supercomputing.org/schedule/event_detail.php?evid=pap260">the original</a> on 2013-10-29<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-14</span></span>.</cite></span>

</li>

<li id="cite_note-4"><span class="mw-cite-backlink"><b><a href="#cite_ref-4">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.sisoftware.co.uk/?d=qa&f=ben_mem_hle">"Benchmarks: Haswell's TSX and Memory Transaction Throughput (HLE and RTM)"</a>. <i>sisoftware.co.uk</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-14</span></span>.</cite></span>

</li>

<li id="cite_note-5"><span class="mw-cite-backlink"><b><a href="#cite_ref-5">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://software.intel.com/en-us/blogs/2012/02/07/transactional-synchronization-in-haswell">"Transactional Synchronization in Haswell"</a>. Software.intel.com<span class="reference-accessdate">. Retrieved <span class="nowrap">2012-02-07</span></span>.</cite></span>

</li>

<li id="cite_note-6"><span class="mw-cite-backlink"><b><a href="#cite_ref-6">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://arstechnica.com/business/news/2012/02/transactional-memory-going-mainstream-with-intel-haswell.ars">"Transactional memory going mainstream with Intel Haswell"</a>. <i>Ars Technica</i>. 2012-02-08<span class="reference-accessdate">. Retrieved <span class="nowrap">2012-02-09</span></span>.</cite></span>

</li>

<li id="cite_note-7"><span class="mw-cite-backlink"><b><a href="#cite_ref-7">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.tomshardware.com/reviews/core-i7-4770k-haswell-review,3521.html">"The Core i7-4770K Review"</a>. Tom's Hardware. 2013-06-01<span class="reference-accessdate">. Retrieved <span class="nowrap">2012-06-03</span></span>.</cite></span>

</li>

<li id="cite_note-comparison-8"><span class="mw-cite-backlink"><b><a href="#cite_ref-comparison_8-0">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://ark.intel.com/compare/77773,77775,77777,77480,77769,77771,75036,75037,75043,76640,75044,75045,75047,75048,76641,75049,75050,75121,75122,75123,76642,75124,75125">"Intel Comparison Table of Haswell Pentium, i3, i5, and i7 models"</a>. intel.com<span class="reference-accessdate">. Retrieved <span class="nowrap">2014-02-11</span></span>.</cite></span>

</li>

<li id="cite_note-techreport-26911-9"><span class="mw-cite-backlink">^ <a href="#cite_ref-techreport-26911_9-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-techreport-26911_9-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite id="CITEREFScott_Wasson2014" class="citation web cs1">Scott Wasson (2014-08-12). <a rel="nofollow" class="external text" href="http://techreport.com/news/26911/errata-prompts-intel-to-disable-tsx-in-haswell-early-broadwell-cpus">"Errata prompts Intel to disable TSX in Haswell, early Broadwell CPUs"</a>. <i>techreport.com</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2014-08-12</span></span>.</cite></span>

</li>

<li id="cite_note-intel-spec-update-10"><span class="mw-cite-backlink">^ <a href="#cite_ref-intel-spec-update_10-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-intel-spec-update_10-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/4th-gen-core-family-desktop-specification-update.pdf">"Desktop 4th Generation Intel Core Processor Family, Desktop Intel Pentium Processor Family, and Desktop Intel Celeron Processor Family: Specification Update (Revision 014)"</a> <span class="cs1-format">(PDF)</span>. <a href="Intel" title="Intel">Intel</a>. June 2014. p. 46<span class="reference-accessdate">. Retrieved <span class="nowrap">2014-08-13</span></span>. <q>Under a complex set of internal timing conditions and system events, software using the Intel TSX/TSX-NI (Transactional Synchronization Extensions) instructions may observe unpredictable system behavior.</q></cite></span>

</li>

<li id="cite_note-Breaking_Kernel_Address_Space_Layout_Randomization_with_Intel_TSX-11"><span class="mw-cite-backlink"><b><a href="#cite_ref-Breaking_Kernel_Address_Space_Layout_Randomization_with_Intel_TSX_11-0">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.blackhat.com/docs/us-16/materials/us-16-Jang-Breaking-Kernel-Address-Space-Layout-Randomization-KASLR-With-Intel-TSX-wp.pdf">"Breaking Kernel Address Space Layout Randomization with Intel TSX"</a> <span class="cs1-format">(PDF)</span>. 2016.</cite></span>

</li>

<li id="cite_note-12"><span class="mw-cite-backlink"><b><a href="#cite_ref-12">^</a></b></span> <span class="reference-text"><cite id="CITEREFGareth_Halfacree2021" class="citation web cs1">Gareth Halfacree (2021-06-29). <a rel="nofollow" class="external text" href="https://www.theregister.com/2021/06/29/intel_tsx_disabled/">"Intel sticks another nail in the coffin of TSX with feature-disabling microcode update"</a>. <a href="The_Register" title="The Register">The Register</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2012-10-17</span></span>.</cite></span>

</li>

<li id="cite_note-13"><span class="mw-cite-backlink"><b><a href="#cite_ref-13">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.intel.com/content/www/us/en/products/compare.html?productIds=237247,237249,237252,237255,237259,237261,237263,237267,237554,237557,237558,237562,237565,237566,237569,240775,240777,240781,240785,241643,241825,241828,241830,241834,241836,241837,241838,241840,241842,241844,241845,242628,242632,242634,242635,242636,242637,242638,242640,242642,242643,242665,242666,242667,242668,242669,242670,242671,242856,243112">"Compare Products"</a>. <i>Intel</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2025-03-10</span></span>.</cite></span>

</li>

<li id="cite_note-14"><span class="mw-cite-backlink"><b><a href="#cite_ref-14">^</a></b></span> <span class="reference-text"><cite id="CITEREFWooyoung_Kim2013" class="citation web cs1">Wooyoung Kim (2013-07-25). <a rel="nofollow" class="external text" href="http://software.intel.com/en-us/blogs/2013/07/25/fun-with-intel-transactional-synchronization-extensions">"Fun with Intel Transactional Synchronization Extensions"</a>. <a href="Intel" title="Intel">Intel</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-12</span></span>.</cite></span>

</li>

<li id="cite_note-15"><span class="mw-cite-backlink"><b><a href="#cite_ref-15">^</a></b></span> <span class="reference-text"><cite id="CITEREFSebastien_DabdoubStephen_Tu" class="citation web cs1">Sebastien Dabdoub; Stephen Tu. <a rel="nofollow" class="external text" href="http://people.csail.mit.edu/stephentu/papers/tsx.pdf">"Supporting Intel Transactional Synchronization Extensions in QEMU"</a> <span class="cs1-format">(PDF)</span>. <i>mit.edu</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-12</span></span>.</cite></span>

</li>

<li id="cite_note-anandtech-tsx-16"><span class="mw-cite-backlink">^ <a href="#cite_ref-anandtech-tsx_16-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-anandtech-tsx_16-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite id="CITEREFJohan_De_Gelas2012" class="citation web cs1">Johan De Gelas (2012-09-20). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20120922222405/http://www.anandtech.com/show/6290/making-sense-of-intel-haswell-transactional-synchronization-extensions/2">"Making Sense of the Intel Haswell Transactional Synchronization eXtensions"</a>. <a href="AnandTech" title="AnandTech">AnandTech</a>. Archived from <a rel="nofollow" class="external text" href="http://www.anandtech.com/show/6290/making-sense-of-intel-haswell-transactional-synchronization-extensions/2">the original</a> on September 22, 2012<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-10-20</span></span>.</cite></span>

</li>

<li id="cite_note-17"><span class="mw-cite-backlink"><b><a href="#cite_ref-17">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20131029205123/http://software.intel.com/sites/products/documentation/doclib/stdxe/2013/composerxe/compiler/cpp-win/GUID-A462FBC8-37F2-490F-A68B-2FFA8010DEBC.htm">"Hardware Lock Elision Overview"</a>. intel.com. Archived from <a rel="nofollow" class="external text" href="http://software.intel.com/sites/products/documentation/doclib/stdxe/2013/composerxe/compiler/cpp-win/GUID-A462FBC8-37F2-490F-A68B-2FFA8010DEBC.htm">the original</a> on 2013-10-29<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-10-27</span></span>.</cite></span>

</li>

<li id="cite_note-haswell-tm-18"><span class="mw-cite-backlink">^ <a href="#cite_ref-haswell-tm_18-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-haswell-tm_18-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite id="CITEREFDavid_Kanter2012" class="citation web cs1">David Kanter (2012-08-21). <a rel="nofollow" class="external text" href="http://www.realworldtech.com/haswell-tm/">"Analysis of Haswell's Transactional Memory"</a>. Real World Technologies<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-19</span></span>.</cite></span>

</li>

<li id="cite_note-intel-arch-sdm-19"><span class="mw-cite-backlink">^ <a href="#cite_ref-intel-arch-sdm_19-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-intel-arch-sdm_19-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-software-developer-manual-325462.pdf">"Intel 64 and IA-32 Architectures Software Developer's Manual Combined Volumes: 1, 2A, 2B, 2C, 3A, 3B, and 3C"</a> <span class="cs1-format">(PDF)</span>. Intel. September 2013. p. 342<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-19</span></span>.</cite></span>

</li>

<li id="cite_note-intel-arch-optimization-20"><span class="mw-cite-backlink">^ <a href="#cite_ref-intel-arch-optimization_20-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-intel-arch-optimization_20-1"><sup><i><b>b</b></i></sup></a> <a href="#cite_ref-intel-arch-optimization_20-2"><sup><i><b>c</b></i></sup></a></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-optimization-manual.pdf">"Intel 64 and IA-32 Architectures Optimization Reference Manual"</a> <span class="cs1-format">(PDF)</span>. Intel. September 2013. p. 446<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-19</span></span>.</cite></span>

</li>

<li id="cite_note-21"><span class="mw-cite-backlink"><b><a href="#cite_ref-21">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://software.intel.com/en-us/forums/topic/402412">"Intel TSX implementation properties"</a>. Intel. 2013<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-14</span></span>. <q>The processor tracks both the read-set addresses and the write-set addresses in the first level data cache (L1 cache) of the processor.</q></cite></span>

</li>

<li id="cite_note-22"><span class="mw-cite-backlink"><b><a href="#cite_ref-22">^</a></b></span> <span class="reference-text"><cite id="CITEREFDe_Gelas2012" class="citation web cs1">De Gelas, Johan (September 20, 2012). <a rel="nofollow" class="external text" href="https://archive.today/20131223115711/http://www.anandtech.com/show/6290/making-sense-of-intel-haswell-transactional-synchronization-extensions/4">"Making Sense of the Intel Haswell Transactional Synchronization eXtensions"</a>. AnandTech. Archived from <a rel="nofollow" class="external text" href="http://www.anandtech.com/show/6290/making-sense-of-intel-haswell-transactional-synchronization-extensions/4">the original</a> on December 23, 2013<span class="reference-accessdate">. Retrieved <span class="nowrap">23 December</span> 2013</span>. <q>The whole "CPU does the fine grained locks" is based upon tagging the L1 (64 B) cachelines and there are 512 of them to be specific (64 x 512 = 32 KB). There is only one "lock tag" per cacheline.</q></cite></span>

</li>

<li id="cite_note-23"><span class="mw-cite-backlink"><b><a href="#cite_ref-23">^</a></b></span> <span class="reference-text"><cite id="CITEREFDavid_Kanter2012" class="citation web cs1">David Kanter (2012-08-21). <a rel="nofollow" class="external text" href="http://www.realworldtech.com/haswell-tm-alt/">"Haswell Transactional Memory Alternatives"</a>. Real World Technologies<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-11-14</span></span>.</cite></span>

</li>

<li id="cite_note-24"><span class="mw-cite-backlink"><b><a href="#cite_ref-24">^</a></b></span> <span class="reference-text"><cite id="CITEREFIan_Cutress2014" class="citation web cs1">Ian Cutress (2014-08-12). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20140814022515/http://anandtech.com/show/8376/intel-disables-tsx-instructions-erratum-found-in-haswell-haswelleep-broadwelly">"Intel Disables TSX Instructions: Erratum Found in Haswell, Haswell-E/EP, Broadwell-Y"</a>. <a href="AnandTech" title="AnandTech">AnandTech</a>. Archived from <a rel="nofollow" class="external text" href="http://www.anandtech.com/show/8376/intel-disables-tsx-instructions-erratum-found-in-haswell-haswelleep-broadwelly">the original</a> on August 14, 2014<span class="reference-accessdate">. Retrieved <span class="nowrap">2014-08-30</span></span>.</cite></span>

</li>

<li id="cite_note-intel-330836-003-25"><span class="mw-cite-backlink"><b><a href="#cite_ref-intel-330836-003_25-0">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/core-m-processor-family-spec-update.pdf">"Intel Core M Processor Family. Specification Update. December 2014. Revision 003. 330836-003"</a> <span class="cs1-format">(PDF)</span>. <a href="Intel" title="Intel">Intel</a>. December 2014. p. 10<span class="reference-accessdate">. Retrieved <span class="nowrap">2014-12-28</span></span>. <q>BDM53 <sup>1</sup> E-0: X, F-0:, Status: Fixed ERRATA: Intel TSX Instructions Not Available. 1. Applies to Intel Core M-5Y70 processor. Intel TSX is supported on Intel Core M-5Y70 processor with Intel vPro Technology. Intel TSX is not supported on other processor SKUs.</q></cite></span>

</li>

<li id="cite_note-26"><span class="mw-cite-backlink"><b><a href="#cite_ref-26">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20170305013511/https://www.hipeac.net/assets/public/publications/newsletter/hipeacinfo45.pdf">"HiPEAC info"</a> <span class="cs1-format">(PDF)</span>. p. 12. Archived from <a rel="nofollow" class="external text" href="https://www.hipeac.net/assets/public/publications/newsletter/hipeacinfo45.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2017-03-05.</cite></span>

</li>

<li id="cite_note-27"><span class="mw-cite-backlink"><b><a href="#cite_ref-27">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.intel.com/content/dam/support/us/en/documents/processors/Performance-Monitoring-Impact-of-TSX-Memory-Ordering-Issue-604224.pdf">"Performance Monitoring Impact of Intel® Transactional Synchronization Extension Memory Ordering Issue White Paper, June 2021, Revision 1.4"</a> <span class="cs1-format">(PDF)</span>. Intel. 2021-06-12. p. 5. <q>The October 2018 microcode update also disabled the HLE instruction prefix of Intel TSX and force all RTM transactions to abort when operating in Intel SGX mode or System Management Mode (SMM).</q></cite></span>

</li>

<li id="cite_note-28"><span class="mw-cite-backlink"><b><a href="#cite_ref-28">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.intel.com/content/www/us/en/support/articles/000059422/processors.html">"Intel® Transactional Synchronization Extensions (Intel® TSX) Memory and Performance Monitoring Update for Intel® Processors"</a>. Intel. 2021-06-12.</cite></span>

</li>

<li id="cite_note-29"><span class="mw-cite-backlink"><b><a href="#cite_ref-29">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://ark.intel.com/content/www/us/en/ark/products/199332/intel-core-i9-10900k-processor-20m-cache-up-to-5-30-ghz.html">"Intel® Core™ i9-10900K Processor specifications"</a>. Intel. 2020<span class="reference-accessdate">. Retrieved <span class="nowrap">2020-10-10</span></span>.</cite></span>

</li>

<li id="cite_note-30"><span class="mw-cite-backlink"><b><a href="#cite_ref-30">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://ark.intel.com/content/www/us/en/ark/products/201838/intel-core-i9-10980hk-processor-16m-cache-up-to-5-30-ghz.html">"Intel® Core™ i9-10980HK Processor specifications"</a>. Intel. 2020<span class="reference-accessdate">. Retrieved <span class="nowrap">2020-10-10</span></span>.</cite></span>

</li>

<li id="cite_note-31"><span class="mw-cite-backlink"><b><a href="#cite_ref-31">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://ark.intel.com/content/www/us/en/ark/products/201888/intel-core-i7-10810u-processor-12m-cache-up-to-4-90-ghz.html">"Intel® Core™ i7-10810U Processor specifications"</a>. Intel. 2020<span class="reference-accessdate">. Retrieved <span class="nowrap">2020-10-10</span></span>.</cite></span>

</li>

<li id="cite_note-32"><span class="mw-cite-backlink"><b><a href="#cite_ref-32">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://ark.intel.com/content/www/us/en/ark/products/199336/intel-xeon-w-1290p-processor-20m-cache-3-70-ghz.html">"Intel® Xeon® W-1290P Processor specifications"</a>. Intel. 2020<span class="reference-accessdate">. Retrieved <span class="nowrap">2020-10-10</span></span>.</cite></span>

</li>

<li id="cite_note-33"><span class="mw-cite-backlink"><b><a href="#cite_ref-33">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://ark.intel.com/content/www/us/en/ark/products/196593/intel-core-i7-1068ng7-processor-8m-cache-up-to-4-10-ghz.html">"Intel® Core™ i7-1068NG7 Processor specifications"</a>. Intel. 2020<span class="reference-accessdate">. Retrieved <span class="nowrap">2020-10-10</span></span>.</cite></span>

</li>

<li id="cite_note-intel-arch-extensions-34"><span class="mw-cite-backlink"><b><a href="#cite_ref-intel-arch-extensions_34-0">^</a></b></span> <span class="reference-text"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://software.intel.com/content/dam/develop/external/us/en/documents/architecture-instruction-set-extensions-programming-reference.pdf">"Intel® Architecture Instruction Set Extensions Programming Reference"</a> <span class="cs1-format">(PDF)</span>. Intel. 2020<span class="reference-accessdate">. Retrieved <span class="nowrap">2020-10-21</span></span>.</cite></span>

</li>

</ol></div>

<div class="mw-heading mw-heading2"><h2 id="Further_reading">Further reading</h2></div>

<ul><li><cite id="CITEREFAfekLevyMorrison2014" class="citation book cs1">Afek, Y.; Levy, A.; Morrison, A. (2014). <i>Proceedings of the 2014 ACM symposium on Principles of distributed computing - PODC '14</i>. Software-improved hardware lock elision, p. 212. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1145%2F2611462.2611482">10.1145/2611462.2611482</a>. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9781450329446</bdi>. <a href="S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:16645370">16645370</a>.</cite>. Software-based improvements to hardware lock-elision in Intel TSX.</li></ul>

<div class="mw-heading mw-heading2"><h2 id="External_links">External links</h2></div>

<ul><li><a rel="nofollow" class="external text" href="http://software.intel.com/sites/default/files/blog/393551/sf12-arcs004-100.pdf">Presentation from IDF 2012</a> (PDF)</li>

<li><a rel="nofollow" class="external text" href="http://halobates.de/adding-lock-elision-to-linux.pdf">Adding lock elision to Linux</a>, Linux Plumbers Conference 2012 (PDF)</li>

<li><a rel="nofollow" class="external text" href="https://lwn.net/Articles/534758/">Lock elision in the GNU C library</a>, <a href="LWN.net" title="LWN.net">LWN.net</a>, January 30, 2013, by Andi Kleen</li>

<li><a rel="nofollow" class="external text" href="http://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-optimization-manual.pdf">TSX Optimization Guide</a>, Chapter 12 (PDF)</li>

<li><a rel="nofollow" class="external text" href="https://software.intel.com/content/dam/develop/public/us/en/documents/325462-sdm-vol-1-2abcd-3abcd.pdf">Software Developers Manual</a>, Volume 1, Chapter 2.5 (PDF)</li>

<li><a rel="nofollow" class="external text" href="http://www.intel.com/software/tsx">Web Resources about Intel Transactional Synchronization Extensions</a></li>

<li><a rel="nofollow" class="external text" href="https://lkml.org/lkml/2014/9/18/218">x86, microcode: BUG: microcode update that changes x86_capability</a>, <a href="LKML" class="mw-redirect" title="LKML">LKML</a>, September 2014 (there is also another <a rel="nofollow" class="external text" href="https://bugs.gentoo.org/show_bug.cgi?id=528712">similar bug report</a>)</li>

<li><a rel="nofollow" class="external text" href="https://wiki.gentoo.org/wiki/Intel_microcode">Intel microcode</a>, Gentoo, September 19, 2015</li></ul>

/* start https://en.wikipedia.org/ */

.mw-parser-output .hlist dl,.mw-parser-output .hlist ol,.mw-parser-output .hlist ul{margin:0;padding:0}.mw-parser-output .hlist dd,.mw-parser-output .hlist dt,.mw-parser-output .hlist li{margin:0;display:inline}.mw-parser-output .hlist.inline,.mw-parser-output .hlist.inline dl,.mw-parser-output .hlist.inline ol,.mw-parser-output .hlist.inline ul,.mw-parser-output .hlist dl dl,.mw-parser-output .hlist dl ol,.mw-parser-output .hlist dl ul,.mw-parser-output .hlist ol dl,.mw-parser-output .hlist ol ol,.mw-parser-output .hlist ol ul,.mw-parser-output .hlist ul dl,.mw-parser-output .hlist ul ol,.mw-parser-output .hlist ul ul{display:inline}.mw-parser-output .hlist .mw-empty-li{display:none}.mw-parser-output .hlist dt::after{content:": "}.mw-parser-output .hlist dd::after,.mw-parser-output .hlist li::after{content:" · ";font-weight:bold}.mw-parser-output .hlist dd:last-child::after,.mw-parser-output .hlist dt:last-child::after,.mw-parser-output .hlist li:last-child::after{content:none}.mw-parser-output .hlist dd dd:first-child::before,.mw-parser-output .hlist dd dt:first-child::before,.mw-parser-output .hlist dd li:first-child::before,.mw-parser-output .hlist dt dd:first-child::before,.mw-parser-output .hlist dt dt:first-child::before,.mw-parser-output .hlist dt li:first-child::before,.mw-parser-output .hlist li dd:first-child::before,.mw-parser-output .hlist li dt:first-child::before,.mw-parser-output .hlist li li:first-child::before{content:" (";font-weight:normal}.mw-parser-output .hlist dd dd:last-child::after,.mw-parser-output .hlist dd dt:last-child::after,.mw-parser-output .hlist dd li:last-child::after,.mw-parser-output .hlist dt dd:last-child::after,.mw-parser-output .hlist dt dt:last-child::after,.mw-parser-output .hlist dt li:last-child::after,.mw-parser-output .hlist li dd:last-child::after,.mw-parser-output .hlist li dt:last-child::after,.mw-parser-output .hlist li li:last-child::after{content:")";font-weight:normal}.mw-parser-output .hlist ol{counter-reset:listitem}.mw-parser-output .hlist ol>li{counter-increment:listitem}.mw-parser-output .hlist ol>li::before{content:" "counter(listitem)"\a0 "}.mw-parser-output .hlist dd ol>li:first-child::before,.mw-parser-output .hlist dt ol>li:first-child::before,.mw-parser-output .hlist li ol>li:first-child::before{content:" ("counter(listitem)"\a0 "}

/* end https://en.wikipedia.org/ */

</style><style data-mw-deduplicate="TemplateStyles:r1236075235">

/* start https://en.wikipedia.org/ */

.mw-parser-output .navbox{box-sizing:border-box;border:1px solid #a2a9b1;width:100%;clear:both;font-size:88%;text-align:center;padding:1px;margin:1em auto 0}.mw-parser-output .navbox .navbox{margin-top:0}.mw-parser-output .navbox+.navbox,.mw-parser-output .navbox+.navbox-styles+.navbox{margin-top:-1px}.mw-parser-output .navbox-inner,.mw-parser-output .navbox-subgroup{width:100%}.mw-parser-output .navbox-group,.mw-parser-output .navbox-title,.mw-parser-output .navbox-abovebelow{padding:0.25em 1em;line-height:1.5em;text-align:center}.mw-parser-output .navbox-group{white-space:nowrap;text-align:right}.mw-parser-output .navbox,.mw-parser-output .navbox-subgroup{background-color:#fdfdfd}.mw-parser-output .navbox-list{line-height:1.5em;border-color:#fdfdfd}.mw-parser-output .navbox-list-with-group{text-align:left;border-left-width:2px;border-left-style:solid}.mw-parser-output tr+tr>.navbox-abovebelow,.mw-parser-output tr+tr>.navbox-group,.mw-parser-output tr+tr>.navbox-image,.mw-parser-output tr+tr>.navbox-list{border-top:2px solid #fdfdfd}.mw-parser-output .navbox-title{background-color:#ccf}.mw-parser-output .navbox-abovebelow,.mw-parser-output .navbox-group,.mw-parser-output .navbox-subgroup .navbox-title{background-color:#ddf}.mw-parser-output .navbox-subgroup .navbox-group,.mw-parser-output .navbox-subgroup .navbox-abovebelow{background-color:#e6e6ff}.mw-parser-output .navbox-even{background-color:#f7f7f7}.mw-parser-output .navbox-odd{background-color:transparent}.mw-parser-output .navbox .hlist td dl,.mw-parser-output .navbox .hlist td ol,.mw-parser-output .navbox .hlist td ul,.mw-parser-output .navbox td.hlist dl,.mw-parser-output .navbox td.hlist ol,.mw-parser-output .navbox td.hlist ul{padding:0.125em 0}.mw-parser-output .navbox .navbar{display:block;font-size:100%}.mw-parser-output .navbox-title .navbar{float:left;text-align:left;margin-right:0.5em}body.skin--responsive .mw-parser-output .navbox-image img{max-width:none!important}@media print{body.ns-0 .mw-parser-output .navbox{display:none!important}}

/* end https://en.wikipedia.org/ */

</style></div><div role="navigation" class="navbox" aria-labelledby="AMD_technology57" style="padding:3px"><table class="nowraplinks mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><style data-mw-deduplicate="TemplateStyles:r1239400231">

/* start https://en.wikipedia.org/ */

.mw-parser-output .navbar{display:inline;font-size:88%;font-weight:normal}.mw-parser-output .navbar-collapse{float:left;text-align:left}.mw-parser-output .navbar-boxtext{word-spacing:0}.mw-parser-output .navbar ul{display:inline-block;white-space:nowrap;line-height:inherit}.mw-parser-output .navbar-brackets::before{margin-right:-0.125em;content:"[ "}.mw-parser-output .navbar-brackets::after{margin-left:-0.125em;content:" ]"}.mw-parser-output .navbar li{word-spacing:-0.125em}.mw-parser-output .navbar a>span,.mw-parser-output .navbar a>abbr{text-decoration:inherit}.mw-parser-output .navbar-mini abbr{font-variant:small-caps;border-bottom:none;text-decoration:none;cursor:inherit}.mw-parser-output .navbar-ct-full{font-size:114%;margin:0 7em}.mw-parser-output .navbar-ct-mini{font-size:114%;margin:0 4em}html.skin-theme-clientpref-night .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}@media(prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}}@media print{.mw-parser-output .navbar{display:none!important}}

/* end https://en.wikipedia.org/ */

</style><div id="AMD_technology57" style="font-size:114%;margin:0 4em"><a href="AMD" title="AMD">AMD</a> technology</div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%">Software</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="AGESA" title="AGESA">AGESA</a></li>

<li><a href="AMDgpu_(Linux_kernel_module)" title="AMDgpu (Linux kernel module)">AMDgpu</a></li>

<li><a href="AMD_Software" title="AMD Software">AMD Software</a></li>

<li><a href="Vivado" title="Vivado">Vivado</a></li>

<li><a href="Xilinx_ISE" title="Xilinx ISE">Xilinx ISE</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Platforms</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">Current</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em">

<li><a href="GPUOpen" title="GPUOpen">GPUOpen</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Obsolete</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="AMD_Spider" title="AMD Spider">Spider</a></li>

<li><a href="AMD_Dragon" title="AMD Dragon">Dragon</a></li>

<li><a href="AMD_Horus" title="AMD Horus">Horus</a></li></ul>

</div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Technology</th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Cool'n'Quiet" title="Cool'n'Quiet">Cool'n'Quiet</a></li>

<li><a href="High_Bandwidth_Memory" title="High Bandwidth Memory">High Bandwidth Memory</a></li>

<li><a href="PowerNow!" title="PowerNow!">PowerNow!</a></li>

<li><a href="AMD_PowerPlay" title="AMD PowerPlay">PowerPlay</a></li>

<li><a href="AMD_PowerTune" title="AMD PowerTune">PowerTune</a></li>

<li><a href="AMD_Turbo_Core" title="AMD Turbo Core">Turbo Core</a></li>

<li><a href="AMD_Wraith" title="AMD Wraith">AMD Wraith</a></li>

<li><a href="Virtex_(FPGA)" title="Virtex (FPGA)">Virtex</a></li>

<ul><li><a href="Ryzen_AI" class="mw-redirect" title="Ryzen AI">Ryzen AI</a></li></ul></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Instructions</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

</div></td></tr></tbody></table></div>

<div class="navbox-styles"></div><div role="navigation" class="navbox" aria-labelledby="Intel_technology56" style="padding:3px"><table class="nowraplinks mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><div id="Intel_technology56" style="font-size:114%;margin:0 4em"><a href="Intel" title="Intel">Intel</a> technology</div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%">Platforms</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Centrino" title="Centrino">Centrino</a></li>

<li><a href="Centrino#Montevina_platform_(2008)" title="Centrino">Centrino 2</a></li>

<li><a href="Tablet_computer#Intel_tablet_platforms" title="Tablet computer">Tablet</a></li>

<li><a href="Ultrabook" title="Ultrabook">Ultrabook</a></li>

<li><a href="Intel_Skulltrail" title="Intel Skulltrail">Skulltrail</a></li>

<li><a href="Intel_Galileo" title="Intel Galileo">Galileo</a></li>

<li><a href="Intel_Edison" title="Intel Edison">Edison</a></li>

<li><a href="Intel_Curie" class="mw-redirect" title="Intel Curie">Curie</a></li>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Discontinued</th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Common_Building_Block" title="Common Building Block">Common Building Block</a></li>

<li><a href="MultiProcessor_Specification" title="MultiProcessor Specification">MultiProcessor Specification</a></li>

<li><a href="Intel_Communication_Streaming_Architecture" title="Intel Communication Streaming Architecture">Intel Communication Streaming Architecture</a></li>

<li><a href="Intel_Inboard_386" title="Intel Inboard 386">Intel Inboard 386</a></li>

<li><a href="Intel_Play" title="Intel Play">Intel Play</a></li>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Current</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Advanced_Programmable_Interrupt_Controller" title="Advanced Programmable Interrupt Controller">Advanced Programmable Interrupt Controller</a></li>

<li><a href="Intel_Turbo_Boost" title="Intel Turbo Boost">Intel Turbo Boost</a></li>

<li><a href="Intel_Secure_Key" class="mw-redirect" title="Intel Secure Key">Intel Secure Key</a></li>

<li><a href="Intel_Management_Engine" title="Intel Management Engine">Intel Management Engine</a></li>

<li><a href="Intel_Active_Management_Technology" title="Intel Active Management Technology">Active Management Technology</a>

<ul><li><a href="Intel_AMT_versions" title="Intel AMT versions">AMT versions</a></li></ul></li>

<li><a href="High-bandwidth_Digital_Content_Protection" title="High-bandwidth Digital Content Protection">High-bandwidth Digital Content Protection</a></li>

<li><a href="Intel_High_Definition_Audio" title="Intel High Definition Audio">High Definition Audio</a></li>

<li><a href="Intel_Hub_Architecture" title="Intel Hub Architecture">Hub Architecture</a></li>

<li><a href="Intel_Rapid_Storage_Technology" title="Intel Rapid Storage Technology">Rapid Storage Technology</a></li>

<li><a href="SpeedStep" title="SpeedStep">SpeedStep</a></li>

<li><a href="Serial_Digital_Video_Out" title="Serial Digital Video Out">Serial Digital Video Out</a></li>

<li><a href="Host_Embedded_Controller_Interface" title="Host Embedded Controller Interface">Host Embedded Controller Interface</a></li>

<li><a href="Hyper-threading" title="Hyper-threading">Hyper-threading</a></li>

<li><a href="Platform_Environment_Control_Interface" title="Platform Environment Control Interface">Platform Environment Control Interface</a></li>

<li><a href="Intel_QuickPath_Interconnect" title="Intel QuickPath Interconnect">QuickPath Interconnect</a></li>

<li><a href="Platform_Controller_Hub" title="Platform Controller Hub">Platform Controller Hub</a></li>

<li><a href="System_Management_Bus" title="System Management Bus">System Management Bus</a></li>

<li><a href="Thunderbolt_(interface)" title="Thunderbolt (interface)">Thunderbolt</a></li>

<li><a href="Intel_Ultra_Path_Interconnect" title="Intel Ultra Path Interconnect">Ultra Path Interconnect</a></li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Upcoming</th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="Silicon_Photonics_Link" title="Silicon Photonics Link">Silicon Photonics Link</a></li></ul>

</div></td></tr></tbody></table></div>

<p><br>

</p>

<div class="navbox-styles"></div><div role="navigation" class="navbox" aria-labelledby="Multimedia_Instruction_set_extensions305" style="padding:3px"><table class="nowraplinks mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><div id="Multimedia_Instruction_set_extensions305" style="font-size:114%;margin:0 4em"><a href="Multimedia" title="Multimedia">Multimedia</a> <a href="Instruction_set_architecture" title="Instruction set architecture">Instruction set</a> <a href="Processor_supplementary_capability" title="Processor supplementary capability">extensions</a></div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Single_instruction%2C_multiple_data" title="Single instruction, multiple data">SIMD</a> (<a href="Reduced_instruction_set_computer" title="Reduced instruction set computer">RISC</a>)</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="DEC_Alpha" title="DEC Alpha">Alpha</a>

<li><a href="Power_ISA" title="Power ISA">Power ISA</a>

<li><a href="SPARC" title="SPARC">SPARC</a>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Single_instruction%2C_multiple_data" title="Single instruction, multiple data">SIMD</a> (<a href="X86" title="X86">x86</a>)</th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

</div></td></tr><tr><td class="navbox-abovebelow" colspan="2"><div>Suspended extensions' dates are <s>struck through</s>.</div></td></tr></tbody></table></div>

<div class="navbox-styles"></div><div role="navigation" class="navbox" aria-labelledby="Instruction_set_extensions506" style="padding:3px"><table class="nowraplinks mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><div id="Instruction_set_extensions506" style="font-size:114%;margin:0 4em"><a href="Instruction_set_architecture" title="Instruction set architecture">Instruction set</a> <a href="Processor_supplementary_capability" title="Processor supplementary capability">extensions</a></div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Single_instruction%2C_multiple_data" title="Single instruction, multiple data">SIMD</a></th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<li><a href="Power_ISA" title="Power ISA">Power ISA</a>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Bit_manipulation_instructions" title="Bit manipulation instructions">Bit manipulation</a> <br> <a href="Find_first_set" title="Find first set">Find first set</a></th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="X86_Bit_manipulation_instruction_set" title="X86 Bit manipulation instruction set">Intel BMI</a> (ABM: 2007, BMI1: 2012, BMI2: 2013, TBM: 2012)</li>

<li><a href="Intel_ADX" title="Intel ADX">Intel ADX</a> (2014)</li></ul>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Instruction_set_architecture#Code_density" title="Instruction set architecture">Compressed<br> instructions</a></th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="ARM_architecture_family#Thumb" title="ARM architecture family">Thumb</a></li>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Security and <br> <a href="Cryptographic_accelerator" title="Cryptographic accelerator">cryptography</a></th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

<ul><li><a href="VIA_PadLock" title="VIA PadLock">PadLock</a> (2003)</li>

<li><a href="AES_instruction_set" title="AES instruction set">AES-NI</a> (2008); ARMv8 also has AES instructions</li>

<li><a href="CLMUL_instruction_set" title="CLMUL instruction set">CLMUL</a> (2010)</li>

<li><a href="RDRAND" title="RDRAND">RDRAND</a> (2012)</li>

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Transactional_memory" title="Transactional memory">Transactional <br> memory</a></th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

</div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="Hardware-assisted_virtualization" class="mw-redirect" title="Hardware-assisted virtualization">Virtualization</a></th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em">

</div></td></tr><tr><td class="navbox-abovebelow" colspan="2"><div>Suspended extensions' dates are <s>struck through</s>.</div></td></tr></tbody></table></div></div><div><div class="zim-footer">

This article is issued from <a class="external text" title="Last edited on 2025-08-06" href="https://en.wikipedia.org/wiki/?title=Transactional_Synchronization_Extensions&oldid=1304464978">Wikipedia</a>. The text is available under <a class="external text" href="https://creativecommons.org/licenses/by-sa/4.0/deed.en">Creative Commons Attribution-Share Alike 4.0</a> unless otherwise noted. Additional terms may apply for the media files.

</div>

</div></div>

</div>

</main>

</div>

</body></html>