diff --git a/doc/site/performance.markdown b/doc/site/performance.markdown index 9c2173779..09eb8ddca 100644 --- a/doc/site/performance.markdown +++ b/doc/site/performance.markdown @@ -6,90 +6,80 @@ seem to like them, so here's a few:

Method Call

- + - + - + - + - - - - +
wren
0.12s 
wren0.4
0.079s 
luajit (-joff)
0.16s 
luajit2.1 -joff
0.091s 
ruby
0.20s 
ruby3.0
0.104s 
lua
0.35s 
lua5.4
0.121s 
python3
0.78s 
python
0.85s 
python3.11
0.171s 
-

DeltaBlue

+ +

Delta Blue

- + - - - - +
wren
0.13s 
wren0.4
0.086s 
python3
0.48s 
python
0.57s 
python3.11
0.107s 
+

Binary Trees

- + - + - + - + - - - - +
luajit (-joff)
0.11s 
luajit2.1 -joff
0.074s 
wren
0.22s 
ruby3.0
0.116s 
ruby
0.24s 
python3.11
0.137s 
python
0.37s 
lua5.4
0.139s 
python3
0.38s 
lua
0.52s 
wren0.4
0.141s 
+

Recursive Fibonacci

- + - + - + - + - - - - +
luajit (-joff)
0.10s 
luajit2.1 -joff
0.055s 
wren
0.20s 
lua5.4
0.087s 
ruby
0.22s 
ruby3.0
0.119s 
lua
0.28s 
wren0.4
0.148s 
python
0.51s 
python3
0.57s 
python3.11
0.156s 
-**Shorter bars are better.** Each benchmark is run ten times and the best time -is kept. It only measures the time taken to execute the benchmarked code -itself, not interpreter startup. - -These were run on my MacBook Pro 2.3 GHz Intel Core i7 with 16 GB of 1,600 MHz -DDR3 RAM. Tested against Lua 5.2.3, LuaJIT 2.0.2, Python 2.7.5, Python 3.3.4, -ruby 2.0.0p247. LuaJIT is run with the JIT *disabled* (i.e. in bytecode -interpreter mode) since I want to support platforms where JIT-compilation is -disallowed. LuaJIT with the JIT enabled is *much* faster than all of the other -languages benchmarked, including Wren, because Mike Pall is a robot from the -future. +**Shorter bars are better.** Each benchmark is run ten times and the median +time is calculated. It only measures the time taken to execute the benchmarked +code itself, not interpreter startup. + +These were run on a machine with an AMD Ryzen 9 5950X processor. Tested +against Lua 5.4.4, LuaJIT 2.1.0-beta3, Python 3.11.3, ruby 3.0.5. LuaJIT is +run with the JIT *disabled* (i.e. in bytecode interpreter mode) since I want +to support platforms where JIT-compilation is disallowed. LuaJIT with the JIT +enabled is *much* faster than all of the other languages benchmarked, +including Wren, because Mike Pall is a robot from the future. The benchmark harness and programs are [here](https://github.com/wren-lang/wren/tree/main/test/benchmark).