diff --git a/doc/index.html b/doc/index.html index 3f5ce30..85a338f 100644 --- a/doc/index.html +++ b/doc/index.html @@ -198,8 +198,7 @@ application concerns.

- 
-big_int32_t x;
+    
big_int32_t x;
 
 ... read into x from a file ...
 
@@ -241,8 +240,7 @@ generate exactly the same code for both.

   
   
     
-    
-big_int32_t x;
+    
big_int32_t x;
 
 ... read into x from a file ...
 
@@ -253,8 +251,7 @@ for (int32_t i = 0; i < 1000000; ++i)
 

     
     
-    
-int32_t x;
+    
int32_t x;
 
 ... read into x from a file ...
 
@@ -290,121 +287,91 @@ stores, multiple instructions are required.

 
These tests were run against release builds on a circa 2012 4-core little endian X64 Intel Core i5-3570K 
 CPU @ 3.40GHz under Windows 7.

 
-
See speed_test.cpp, 
-speed_test_functions.hpp, 
-speed_test_functions.cpp, and 
-Jamfile.v2 for the actual code and build. The timed functions are in a separate 
-compilation unit to prevent being optimized away.

-
-
Because the timings are anomalous, particularly for those high-lighted below 
-in yellow, the generated code from the GNU compiler was studied in detail. 
-Exactly the same code is being generated for by-value conversion functions, 
-in-place conversion functions, and the endian types. Exactly the same code is 
-being generated whether intrinsics are used or not for 32 and 64-bit tests. 
+
See loop_time_test.cpp and 
+Jamfile.v2 for the actual code and build 
+setup. 
 (For GCC 4.7, there are no 16-bit intrinsics, so they are emulated by using 
 32-bit intrinsics.)

 
-
-  
-    
-  
-

-    
Conclusions

-    
The decision to use endian types or endian conversion functions should be 
-    made based on application use cases, not assumptions about generated code 
-    efficiency. Modern optimizers generate the same code for either approach, 
-    and whether or not intrinsics are available.  

-
 
-
-
+
+
-
-
-
-
+
+
-
-  
-
-  
-
-  
-
-  
-
-  
-  
-  
-
-  
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
+
+
-
-  
-
-  
-
-  
-
-  
-
-  
-  
-  
-
-  
+
+
+
+
+
+
+
+
+
+
+
+
GNU g++ version 4.7.0
 Iterations: 1,000,000,000, Intrinsics: __builtin_bswap16, etc.
GNU C++ version 4.7.0
 Iterations: 1000000000, Intrinsics: __builtin_bswap16, etc.

 
Test Caseint
arg		int
value(arg)		int
in place(arg)		Endian
arg		Endian
type		Endian
conversion
function		
 
16-bit aligned big endian2.71 s2.42 s2.42 s2.68 s
16-bit aligned little endian2.42 s2.40 s2.68 s2.45 s
32-bit aligned big endian2.68 s2.70 s2.70 s2.68 s
32-bit aligned little endian2.68 s2.68 s2.65 s2.68 s
64-bit aligned big endian2.96 s2.95 s2.95 s2.95 s
64-bit aligned little endian2.42 s2.40 s2.70 s2.42 s
 Iterations: 1,000,000,000, Intrinsics: no byte swap intrinsics
16-bit aligned big endian1.37 s0.81 s
16-bit aligned little endian0.83 s0.81 s
16-bit unaligned big endian1.09 s0.83 s
16-bit unaligned little endian1.09 s0.81 s
32-bit aligned big endian0.98 s0.27 s
32-bit aligned little endian0.28 s0.27 s
32-bit unaligned big endian3.82 s0.27 s
32-bit unaligned little endian3.82 s0.27 s
64-bit aligned big endian1.65 s0.41 s
64-bit aligned little endian0.41 s0.41 s
64-bit unaligned big endian17.53 s0.41 s
64-bit unaligned little endian17.52 s0.41 s
 Iterations: 1000000000, Intrinsics: no byte swap intrinsics

 
Test Caseint
arg		int
value(arg)		int
in place(arg)		Endian
arg		Endian
type		Endian
conversion
function		
 
16-bit aligned big endian2.71 s2.42 s2.42 s2.68 s
16-bit aligned little endian2.42 s2.40 s2.68 s2.42 s
32-bit aligned big endian2.68 s2.70 s2.67 s2.70 s
32-bit aligned little endian2.68 s2.67 s2.70 s2.67 s
64-bit aligned big endian2.96 s2.95 s2.95 s2.93 s
64-bit aligned little endian2.42 s2.42 s2.67 s2.40 s
16-bit aligned big endian1.95 s0.81 s
16-bit aligned little endian0.83 s0.81 s
16-bit unaligned big endian1.19 s0.81 s
16-bit unaligned little endian1.20 s0.81 s
32-bit aligned big endian0.97 s0.28 s
32-bit aligned little endian0.27 s0.28 s
32-bit unaligned big endian4.10 s0.27 s
32-bit unaligned little endian4.10 s0.27 s
64-bit aligned big endian1.64 s0.42 s
64-bit aligned little endian0.41 s0.41 s
64-bit unaligned big endian17.52 s0.42 s
64-bit unaligned little endian17.52 s0.41 s

 
 

+
 

 
 
-
+
-
-
-
-
+
+
-
-  
-
-  
-
-  
-
-  
-
-  
-
-  
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
+
+
-
-  
-
-  
-
-  
-
-  
-
-  
-  
-  
-
-  
+
+
+
+
+
+
+
+
+
+
+
+

 
Microsoft Visual C++ version 11.0
 Iterations: 1,000,000,000, Intrinsics: cstdlib _byteswap_ushort, etc.
 Iterations: 1000000000, Intrinsics: cstdlib _byteswap_ushort, etc.

 
Test Caseint
arg		int
value(arg)		int
in place(arg)		Endian
arg		Endian
type		Endian
conversion
function		
 
16-bit aligned big endian1.90 s1.87 s1.89 s1.87 s
16-bit aligned little endian1.89 s1.87 s1.89 s1.87 s
32-bit aligned big endian1.89 s1.87 s1.89 s1.87 s
32-bit aligned little endian1.89 s1.87 s1.87 s1.89 s
64-bit aligned big endian1.87 s1.89 s1.87 s1.89 s
64-bit aligned little endian1.87 s1.87 s1.87 s1.89 s
 Iterations: 1,000,000,000, Intrinsics: no byte swap intrinsics
16-bit aligned big endian2.18 s0.83 s
16-bit aligned little endian0.81 s0.83 s
16-bit unaligned big endian1.64 s0.83 s
16-bit unaligned little endian1.64 s0.83 s
32-bit aligned big endian0.83 s0.81 s
32-bit aligned little endian0.83 s0.81 s
32-bit unaligned big endian3.01 s0.83 s
32-bit unaligned little endian3.01 s0.81 s
64-bit aligned big endian1.09 s1.05 s
64-bit aligned little endian0.83 s1.03 s
64-bit unaligned big endian12.64 s1.01 s
64-bit unaligned little endian8.41 s0.83 s
 Iterations: 1000000000, Intrinsics: no byte swap intrinsics

 
Test Caseint
arg		int
value(arg)		int
in place(arg)		Endian
arg		Endian
type		Endian
conversion
function		
 
16-bit aligned big endian1.90 s1.89 s1.87 s1.87 s
16-bit aligned little endian1.89 s1.87 s1.89 s1.87 s
32-bit aligned big endian1.89 s1.87 s1.87 s1.89 s
32-bit aligned little endian1.87 s1.89 s1.87 s1.89 s
64-bit aligned big endian2.32 s2.46 s2.45 s2.34 s
64-bit aligned little endian1.87 s1.87 s1.89 s1.87 s
16-bit aligned big endian0.84 s0.81 s
16-bit aligned little endian0.83 s0.81 s
16-bit unaligned big endian1.65 s0.81 s
16-bit unaligned little endian1.65 s0.83 s
32-bit aligned big endian3.46 s0.83 s
32-bit aligned little endian0.81 s0.83 s
32-bit unaligned big endian3.01 s0.81 s
32-bit unaligned little endian3.01 s0.81 s
64-bit aligned big endian10.50 s0.83 s
64-bit aligned little endian0.83 s0.97 s
64-bit unaligned big endian12.62 s0.81 s
64-bit unaligned little endian8.42 s0.81 s

 
 

 
@@ -458,7 +425,7 @@ Tim Blechmann, Tim Moore, tymofey, Tomas Puverle, Vincente Botet, Yuval Ronen
 and Vitaly Budovski,.

 

 
Last revised:
-26 May, 2013

+28 May, 2013

 
© Copyright Beman Dawes, 2011, 2013

 
Distributed under the Boost Software License, Version 1.0. See
 www.boost.org/ LICENSE_1_0.txt