gallivm: JIT symbol resolution with linux perf.
Details on docs/llvmpipe.html
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
diff --git a/docs/llvmpipe.html b/docs/llvmpipe.html
index be03083..80f8a01 100644
--- a/docs/llvmpipe.html
+++ b/docs/llvmpipe.html
@@ -130,38 +130,38 @@
<h1>Profiling</h1>
-To profile llvmpipe you should pass the options
-
+<p>
+To profile llvmpipe you should build as
+</p>
<pre>
scons build=profile <same-as-before>
</pre>
+<p>
This will ensure that frame pointers are used both in C and JIT functions, and
that no tail call optimizations are done by gcc.
+</p>
-To better profile JIT code you'll need to build LLVM with oprofile integration.
+<h2>Linux perf integration</h2>
+
+<p>
+On Linux, it is possible to have symbol resolution of JIT code with <a href="http://perf.wiki.kernel.org/">Linux perf</a>:
+</p>
<pre>
- ./configure \
- --prefix=$install_dir \
- --enable-optimized \
- --disable-profiling \
- --enable-targets=host-only \
- --with-oprofile
-
- make -C "$build_dir"
- make -C "$build_dir" install
-
- find "$install_dir/lib" -iname '*.a' -print0 | xargs -0 strip --strip-debug
+ perf record -g /my/application
+ perf report
</pre>
-The you should define
+<p>
+When run inside Linux perf, llvmpipe will create a /tmp/perf-XXXXX.map file with
+symbol address table. It also dumps assembly code to /tmp/perf-XXXXX.map.asm,
+which can be used by the bin/perf-annotate-jit script to produce disassembly of
+the generated code annotated with the samples.
+</p>
-<pre>
- export LLVM=/path/to/llvm-2.6-profile
-</pre>
-
-and rebuild.
+<p>You can obtain a call graph via
+<a href="http://code.google.com/p/jrfonseca/wiki/Gprof2Dot#linux_perf">Gprof2Dot</a>.</p>
<h1>Unit testing</h1>