Author: njn
Date: 2007-10-11 07:00:18 +0100 (Thu, 11 Oct 2007)
New Revision: 6976
Log:
- remove an out-of-date comment
- add first performance figures
Modified:
branches/MASSIF2/massif/ms_main.c
Modified: branches/MASSIF2/massif/ms_main.c
===================================================================
--- branches/MASSIF2/massif/ms_main.c 2007-10-10 07:08:27 UTC (rev 6975)
+++ branches/MASSIF2/massif/ms_main.c 2007-10-11 06:00:18 UTC (rev 6976)
@@ -44,7 +44,6 @@
// - do a graph-drawing test
// - write a good basic test that shows how the tool works, suitable for
// documentation
-// - with --heap=no, --heap-admin still counts. should it?
//
// Possible ideas for the future:
// - Consider 'instructions executed' as a time unit -- more regular than
@@ -144,6 +143,19 @@
// Tests:
// - tests/overloaded_new.cpp is there
//
+// Performance:
+//
+// perl perf/vg_perf --tools=massif --reps=3 perf/{bz2,heap,tinycc}
+//
+// The other benchmarks don't do much allocation, and so give similar speeds
+// to Nulgrind.
+//
+// Initial slowdown:
+// bz2 massif1 :1.18s ma: 5.3s ( 4.5x, -----)
+// heap massif1 :0.24s ma:26.7s (111.4x, -----)
+// tinycc massif1 :0.44s ma:10.7s (24.4x, -----)
+//
+//
//---------------------------------------------------------------------------
#include "pub_tool_basics.h"
-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems? Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
Valgrind-developers mailing list
Valgrind-developers@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/valgrind-developers
