diff options
Diffstat (limited to 'docs/ReleaseNotes.html')
| -rw-r--r-- | docs/ReleaseNotes.html | 63 |
1 files changed, 62 insertions, 1 deletions
diff --git a/docs/ReleaseNotes.html b/docs/ReleaseNotes.html index bcac293..3b5c2e6 100644 --- a/docs/ReleaseNotes.html +++ b/docs/ReleaseNotes.html @@ -206,6 +206,36 @@ Release Notes</a>.</h1> </div> + +<!--=========================================================================--> +<h3> +<a name="Polly">Polly: Polyhedral Optimizer</a> +</h3> + +<div> + + <p><a href="http://polly.llvm.org/">Polly</a> is an <em>experimental</em> + optimizer for data locality and parallelism. It currently provides high-level + loop optimizations and automatic parallelisation (using the OpenMP run time). + Work in the area of automatic SIMD and accelerator code generation was + started. + + <p>Within the LLVM 3.1 time-frame there were the following highlights:</p> + + <ul> + <li>Polly became an official LLVM project</li> + <li>Polly can be loaded directly into clang (Enabled by '-O3 -mllvm -polly' + )</li> + <li>An automatic scheduling optimizer (derived from <a + href="http://pluto-compiler.sourceforge.net/">Pluto</a>) was integrated. It + performs loop transformations to optimize for data-locality and parallelism. + The transformations include, but are not limited to interchange, fusion, + fission, skewing and tiling. + </li> + </ul> + +</div> + </div> <!-- *********************************************************************** --> @@ -269,6 +299,8 @@ Release Notes</a>.</h1> Support to model instruction bundling / packing.</li> <li><a href="#armintegratedassembler">ARM Integrated Assembler</a>, A full featured assembler and direct-to-object support for ARM.</li> + <li><a href="#blockplacement">Basic Block Placement</a> + Probability driven basic block placement.</li> <li>....</li> </ul> @@ -292,6 +324,9 @@ Release Notes</a>.</h1> module as a whole to LLVM subsystems.</li> <li>Loads can now have range metadata attached to them to describe the possible values being loaded.</li> + <li>Inline cost heuristics have been completely overhauled and now closely + model constant propagation through call sites, disregard trivially dead + code costs, and can model C++ STL iterator patterns.</li> <li>....</li> </ul> </div> @@ -308,6 +343,14 @@ Release Notes</a>.</h1> optimizers:</p> <ul> + <li>The loop unroll pass now is able to unroll loops with run-time trip counts. + This feature is turned off by default, and is enabled with the + <code>-unroll-runtime</code> flag.</li> + <li>A new basic-block autovectorization pass is available. Pass + <code>-vectorize</code> to run this pass along with some associated + post-vectorization cleanup passes. For more information, see the EuroLLVM + 2012 slides: <a href="http://llvm.org/devmtg/2012-04-12/Slides/Hal_Finkel.pdf"> + Autovectorization with LLVM</a>.</li> <li>....</li> </ul> @@ -373,6 +416,19 @@ Release Notes</a>.</h1> target's schedule description which can be queried to determine legal groupings of instructions in a bundle.</p> +<p> We have added a new target independent VLIW packetizer based on the + DFA infrastructure to group machine instructions into bundles.</p> + +</div> + +<h4> +<a name="blockplacement">Basic Block Placement</a> +</h4> +<div> +<p>A probability based block placement and code layout algorithm was added to +LLVM's code generator. This layout pass supports probabilities derived from +static heuristics as well as source code annotations such as +<code>__builtin_expect</code>.</p> </div> <!--=========================================================================--> @@ -391,6 +447,7 @@ Release Notes</a>.</h1> times and better support for different calling conventions. The old WINCALL instructions are no longer needed.</li> <li>DW2 Exception Handling is enabled on Cygwin and MinGW.</li> + <li>Support for implicit TLS model used with MS VC runtime</li> </ul> </div> @@ -451,6 +508,8 @@ syntax, there are still significant gaps in that support.</p> <div> +<p>Support for Qualcomm's Hexagon VLIW processor has been added.</p> + <ul> <li>....</li> @@ -524,6 +583,8 @@ syntax, there are still significant gaps in that support.</p> <li><code>llvm::getTrapFunctionName()</code></li> <li><code>llvm::EnableSegmentedStacks</code></li> </ul></li> + <li>The MDBuilder class has been added to simplify the creation of + metadata.</li> <li>....</li> </ul> @@ -621,7 +682,7 @@ syntax, there are still significant gaps in that support.</p> src="http://www.w3.org/Icons/valid-html401-blue" alt="Valid HTML 4.01"></a> <a href="http://llvm.org/">LLVM Compiler Infrastructure</a><br> - Last modified: $Date: 2012-04-12 17:17:35 +0200 (Thu, 12 Apr 2012) $ + Last modified: $Date: 2012-04-17 03:13:53 +0200 (Tue, 17 Apr 2012) $ </address> </body> |
