diff --git a/Makefile b/Makefile
index f05fda21..693c9dcb 100644
--- a/Makefile
+++ b/Makefile
@@ -6,20 +6,21 @@
 
 .PHONY: clean cleandist
 
-CXXFLAGS =  -std=c++11 -O2 -march=native -Wall -Wextra -Wshadow -Idependencies/double-conversion -Ldependencies/double-conversion/release/libdouble-conversion.a
+CXXFLAGS =  -std=c++11 -O2 -march=native -Wall -Wextra -Wshadow -Idependencies/double-conversion -Ldependencies/double-conversion/release -ldouble-conversion
 #CXXFLAGS =  -std=c++11 -O2 -march=native -Wall -Wextra -Wshadow -Wno-implicit-function-declaration
 
 EXECUTABLES=parse
 
 EXTRA_EXECUTABLES=parsenocheesy parsenodep8
 
+LIDDOUBLE:=dependencies/double-conversion/release/libdouble-conversion.a
 
-LIBS=dependencies/double-conversion/release/libdouble-conversion.a
+LIBS=$(LIDDOUBLE)
 
-all: $(LIBS) $(EXECUTABLES) 
+all: $(LIBS) $(EXECUTABLES)
 	-./parse
 
-dependencies/double-conversion/release/libdouble-conversion.a : dependencies/double-conversion/README.md
+$(LIDDOUBLE) : dependencies/double-conversion/README.md
 	cd dependencies/double-conversion/ && mkdir -p release && cd release && cmake .. && make
 
 parse: main.cpp common_defs.h linux-perf-events.h
diff --git a/main.cpp b/main.cpp
index 60a092d1..ed165010 100644
--- a/main.cpp
+++ b/main.cpp
@@ -22,6 +22,15 @@
 #include "common_defs.h"
 #include "linux-perf-events.h"
 
+/// Fixme: enable doube conv
+// #define DOUBLECONV
+#ifdef DOUBLECONV
+#include "double-conversion/double-conversion.h"
+#include "double-conversion/ieee.h"
+
+using namespace double_conversion;
+#endif
+
 using namespace std;
 
 //#define DEBUG
@@ -865,6 +874,11 @@ really_inline bool parse_string(const u8 * buf, UNUSED size_t len, UNUSED Parsed
     return true;
 }
 
+#ifdef DOUBLECONV
+static StringToDoubleConverter converter(StringToDoubleConverter::ALLOW_TRAILING_JUNK, 2000000.0, Double::NaN(), NULL, NULL);
+#endif
+
+
 // put a parsed version of number (either as a double or a signed long) into the number buffer,
 // put a 'tag' indicating which type and where it is back onto the tape at that location
 // return false if we can't parse the number which means either
@@ -877,6 +891,17 @@ really_inline bool parse_string(const u8 * buf, UNUSED size_t len, UNUSED Parsed
 //       have a generic scratch - would need to align before using for this
 really_inline bool parse_number(const u8 * buf, UNUSED size_t len, UNUSED ParsedJson & pj, u32 tape_loc, UNUSED bool found_zero, bool found_minus) {
     u32 offset = tape[tape_loc] & 0xffffff;
+////////////////
+// This is temporary... but it illustrates how one could use Google's double conv.
+///
+#ifdef DOUBLECONV
+    int processed_characters_count;
+    double result = converter.StringToDouble((const char*)( buf+offset), 10, &processed_characters_count);
+    printf("number is %f and used %d chars \n", result, processed_characters_count);
+#endif
+////////////////
+// end of double conv temporary stuff.
+////////////////
     if (found_minus) {
         offset++;
     }