diff --git a/README.html b/README.html index 80a58bc7..13dfcd27 100644 --- a/README.html +++ b/README.html @@ -79,48 +79,99 @@ The following table provides measured execution times on a subset of benchmarks in comparison with the standard C distribution.
- - - - + + + + + - + + + - + - - - - - - - - - - - - - - - - - - - + + + + - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Language Project Version  Execution time (sec)  Mode  Benchmark execution time (sec)  Language Sample command
binarytrees 15nsieve 9 fannkuch 10 nbody 1e6nsieve 9
Clua5.1.417.6375.47716.04415.201lua fannkuch.lua 10
Javaluaj (interpreted)2.018.35518.33933.95348.088java -cp luaj-jse-2.0.jar lua fannkuch.lua 10
luaj -j (lua2java)2.04.46313.7895.88416.701java -cp luaj-jse-2.0.jar lua -j fannkuch.lua 10
luaj -b (luajc)2.0
luaj2.0-b (luajc) 2.98011.274 5.073 16.79411.274Java java -cp luaj-jse-2.0.jar;bcel-5.2.jar lua -b fannkuch.lua 10
-j (lua2java)4.4635.88416.70113.789java -cp luaj-jse-2.0.jar lua -j fannkuch.lua 10
(interpreted)18.35533.95348.08818.339java -cp luaj-jse-2.0.jar lua fannkuch.lua 10
lua5.1.417.63716.04415.2015.477Clua fannkuch.lua 10
jill1.0.144.51254.63072.17220.779Java
kahlua1.0jse22.96363.27768.22321.529Java
mochalua1.050.45770.36882.86841.262Java
+ Luaj in interpreted mode performs well for the benchmarks, and even better when source-to-source (lua2java) -or bytecode-to-bytecode (luajc) compilers are used, and actually executes faster than -C-based lua in some cases. +or bytecode-to-bytecode (luajc) compilers are used, +and actually executes faster than C-based lua in some cases. +It is also faster than Java-lua implementations Jill, Kahlua, and Mochalua for all benchmarks tested.

2 - Simple Examples

diff --git a/build-perf.xml b/build-perf.xml index f28ab919..39466737 100644 --- a/build-perf.xml +++ b/build-perf.xml @@ -61,9 +61,9 @@ - +