Cache callstack results to avoid expensive lookup
This works well as our use-case is to lookup the same addresses multiple
times (loops, helper functions, etc.). With a simple timing of
ReactorUnitTests.exe, with this optimization enabled, total time dropped
from 16.72 seconds to 2.24 seconds (~7.5X faster).
This optimization is especially important for Mac where resolving stack
addresses takes much longer than on other platforms. With this
optimization, running a specific gles-unittests test, it was able to
output the callstack trace in about 30 seconds; without, it was still
emitting jit code after 10 minutes at which point I gave up.
Bug: b/131425026
Change-Id: I97e76256220f73fba0a1fc4099532e833f561551
Reviewed-on: https://swiftshader-review.googlesource.com/c/SwiftShader/+/32369
Kokoro-Presubmit: kokoro <noreply+kokoro@google.com>
Tested-by: Antonio Maiorano <amaiorano@google.com>
Reviewed-by: Nicolas Capens <nicolascapens@google.com>
Reviewed-by: Ben Clayton <bclayton@google.com>
diff --git a/src/Reactor/ReactorDebugInfo.cpp b/src/Reactor/ReactorDebugInfo.cpp
index 246574d..cd7cc44 100644
--- a/src/Reactor/ReactorDebugInfo.cpp
+++ b/src/Reactor/ReactorDebugInfo.cpp
@@ -20,6 +20,7 @@
# include "boost/stacktrace.hpp"
# include <algorithm>
+# include <unordered_map>
namespace rr {
@@ -58,21 +59,35 @@
std::vector<Location> locations;
- // Note that bs::stacktrace() effectively returns a vector of addresses; bs::frame construction is where
- // the heavy lifting is done: resolving the function name, file and line number.
namespace bs = boost::stacktrace;
+
+ // Cache to avoid expensive stacktrace lookups, especially since our use-case results in looking up the
+ // same call stack addresses many times.
+ static std::unordered_map<bs::frame::native_frame_ptr_t, Location> cache;
+
for(bs::frame frame : bs::stacktrace())
{
- if(shouldSkipFile(frame.source_file()))
+ Location location;
+
+ auto iter = cache.find(frame.address());
+ if(iter == cache.end())
+ {
+ location.function.file = frame.source_file();
+ location.function.name = frame.name();
+ location.line = frame.source_line();
+ cache[frame.address()] = location;
+ }
+ else
+ {
+ location = iter->second;
+ }
+
+ if(shouldSkipFile(location.function.file))
{
continue;
}
- Location location;
- location.function.file = frame.source_file();
- location.function.name = frame.name();
- location.line = frame.source_line();
- locations.push_back(location);
+ locations.push_back(std::move(location));
if(limit > 0 && locations.size() >= limit)
{
