-ipsccp, which is run by default at link-time.</li>
<li>LLVM 1.5 is now about 15% faster than LLVM 1.4 and its core data structures
use about 30% less memory.</li>
- <li>LLVM includes new experimental native code generators for SparcV8 and
- Alpha.</li>
+ <li>LLVM includes new experimental native code generators for SparcV8,
+ Alpha, and IA64.</li>
<li>Support for Microsoft Visual Studio is improved, and <a
href="GettingStartedVS.html">now documented</a>.</li>
</ol>
<div class="doc_text">
<ol>
- <li></li>
+ <li>LLVM can now create native shared libraries with '<tt>llvm-gcc ...
+ -shared -Wl,-native</tt>' (or with <tt>-Wl,-native-cbe</tt>).</li>
+ <li>LLVM now supports a new "<a href="LangRef.html#i_prefetch">llvm.prefetch
+ </a>" intrinsic, and llvm-gcc now supports __builtin_prefetch.
</ol>
</div>
be used to step through programs and inspect the stack.</li>
<li>The "iterative scan" register allocator (enabled with -regalloc=iterativescan)
is not stable.</li>
-<li>The SparcV8 and Alpha ports are experimental.</li>
+<li>The SparcV8, Alpha, and IA64 ports are experimental.</li>
</ul>
</div>
<tt>__builtin_types_compatible_p</tt>, <tt>__builtin_choose_expr</tt>,
<tt>__builtin_constant_p</tt>, and <tt>__builtin_expect</tt>
(currently ignored). We also support builtins for ISO C99 floating
- point comparison macros (e.g., <tt>__builtin_islessequal</tt>).</li>
+ point comparison macros (e.g., <tt>__builtin_islessequal</tt>), and
+ <tt>__builtin_prefetch</tt>.</li>
</ol>
<p>The following extensions <b>are</b> known to be supported:</p>