Find length of line 300* slower
First of I have read the answer to Why is my WebAssembly function slower than the JavaScript equivalent?
But it has shed little light on the problem, and I have invested a lot of time that may well be that yellow stuff against the wall.
I do not use globals, I do not use any memory. I have two simple functions that find the length of a line segment and compare them to the same thing in plain old Javascript. I have 4 params 3 more locals and returns a float or double.
On Chrome the Javascript is 40 times faster than the webAssembly and on firefox the wasm is almost 300 times slower than the Javascript.
jsPref test case.
I have added a test case to jsPref WebAssembly V Javascript math
What am I doing wrong?
Either
- I have missed an obvious bug, bad practice, or I am suffering coder stupidity.
- WebAssembly is not for 32bit OS (win 10 laptop i7CPU)
- WebAssembly is far from a ready technology.
Please please be option 1.
I have read the webAssembly use case
Re-use existing code by targeting WebAssembly, embedded in a larger
JavaScript / HTML application. This could be anything from simple
helper libraries, to compute-oriented task offload.
I was hoping I could replace some geometry libs with webAssembly to get some extra performance. I was hoping that it would be awesome, like 10 or more times faster. BUT 300 times slower WTF.
UPDATE
This is not a JS optimisation issues.
To ensure that optimisation has as little as possible effect I have tested using the following methods to reduce or eliminate any optimisation bias..
- counter
c += length(...to ensure all code is executed. bigCount += cto ensure whole function is executed. Not needed- 4 lines for each function to reduce a inlining skew. Not Needed
- all values are randomly generated doubles
- each function call returns a different result.
- add slower length calculation in JS using
Math.hypotto prove code is being run. - added empty call that return first param JS to see overhead
// setup and associated functions
const setOf = (count, callback) => {var a = [],i = 0; while (i < count) { a.push(callback(i ++)) } return a };
const rand = (min = 1, max = min + (min = 0)) => Math.random() * (max - min) + min;
const a = setOf(100009,i=>rand(-100000,100000));
var bigCount = 0;
function len(x,y,x1,y1){
var nx = x1 - x;
var ny = y1 - y;
return Math.sqrt(nx * nx + ny * ny);
}
function lenSlow(x,y,x1,y1){
var nx = x1 - x;
var ny = y1 - y;
return Math.hypot(nx,ny);
}
function lenEmpty(x,y,x1,y1){
return x;
}
// Test functions in same scope as above. None is in global scope
// Each function is copied 4 time and tests are performed randomly.
// c += length(... to ensure all code is executed.
// bigCount += c to ensure whole function is executed.
// 4 lines for each function to reduce a inlining skew
// all values are randomly generated doubles
// each function call returns a different result.
tests : [{
func : function (){
var i,c=0,a1,a2,a3,a4;
for (i = 0; i < 10000; i += 1) {
a1 = a[i];
a2 = a[i+1];
a3 = a[i+2];
a4 = a[i+3];
c += length(a1,a2,a3,a4);
c += length(a2,a3,a4,a1);
c += length(a3,a4,a1,a2);
c += length(a4,a1,a2,a3);
}
bigCount = (bigCount + c) % 1000;
},
name : length64,
},{
func : function (){
var i,c=0,a1,a2,a3,a4;
for (i = 0; i < 10000; i += 1) {
a1 = a[i];
a2 = a[i+1];
a3 = a[i+2];
a4 = a[i+3];
c += lengthF(a1,a2,a3,a4);
c += lengthF(a2,a3,a4,a1);
c += lengthF(a3,a4,a1,a2);
c += lengthF(a4,a1,a2,a3);
}
bigCount = (bigCount + c) % 1000;
},
name : length32,
},{
func : function (){
var i,c=0,a1,a2,a3,a4;
for (i = 0; i < 10000; i += 1) {
a1 = a[i];
a2 = a[i+1];
a3 = a[i+2];
a4 = a[i+3];
c += len(a1,a2,a3,a4);
c += len(a2,a3,a4,a1);
c += len(a3,a4,a1,a2);
c += len(a4,a1,a2,a3);
}
bigCount = (bigCount + c) % 1000;
},
name : length JS,
},{
func : function (){
var i,c=0,a1,a2,a3,a4;
for (i = 0; i < 10000; i += 1) {
a1 = a[i];
a2 = a[i+1];
a3 = a[i+2];
a4 = a[i+3];
c += lenSlow(a1,a2,a3,a4);
c += lenSlow(a2,a3,a4,a1);
c += lenSlow(a3,a4,a1,a2);
c += lenSlow(a4,a1,a2,a3);
}
bigCount = (bigCount + c) % 1000;
},
name : Length JS Slow,
},{
func : function (){
var i,c=0,a1,a2,a3,a4;
for (i = 0; i < 10000; i += 1) {
a1 = a[i];
a2 = a[i+1];
a3 = a[i+2];
a4 = a[i+3];
c += lenEmpty(a1,a2,a3,a4);
c += lenEmpty(a2,a3,a4,a1);
c += lenEmpty(a3,a4,a1,a2);
c += lenEmpty(a4,a1,a2,a3);
}
bigCount = (bigCount + c) % 1000;
},
name : Empty,
}
],Results from update.
Because there is a lot more overhead in the test the results are closer but the JS code is still two orders of magnitude faster.
Note how slow the function Math.hypot is. If optimisation was in effect that function would be near the faster len function.
- WebAssembly 13389µs
- Javascript 728µs
/*
=======================================
Performance test. : WebAssm V Javascript
Use strict....... : true
Data view........ : false
Duplicates....... : 4
Cycles........... : 147
Samples per cycle : 100
Tests per Sample. : undefined
---------------------------------------------
Test : 'length64'
Mean : 12736µs ±69µs (*) 3013 samples
---------------------------------------------
Test : 'length32'
Mean : 13389µs ±94µs (*) 2914 samples
---------------------------------------------
Test : 'length JS'
Mean : 728µs ±6µs (*) 2906 samples
---------------------------------------------
Test : 'Length JS Slow'
Mean : 23374µs ±191µs (*) 2939 samples << This function use Math.hypot
rather than Math.sqrt
---------------------------------------------
Test : 'Empty'
Mean : 79µs ±2µs (*) 2928 samples
-All ----------------------------------------
Mean : 10.097ms Totals time : 148431.200ms 14700 samples
(*) Error rate approximation does not represent the variance.
*/Whats the point of WebAssambly if it does not optimise
End of update
All the stuff related to the problem.
Find length of a line.
Original source in custom language
// declare func the < indicates export name, the param with types and return type
func <lengthF(float x, float y, float x1, float y1) float {
float nx, ny, dist; // declare locals float is f32
nx = x1 - x;
ny = y1 - y;
dist = sqrt(ny * ny + nx * nx);
return dist;
}
// and as double
func <length(double x, double y, double x1, double y1) double {
double nx, ny, dist;
nx = x1 - x;
ny = y1 - y;
dist = sqrt(ny * ny + nx * nx);
return dist;
}Code compiles to Wat for proof read
(module
(func
(export lengthF)
(param f32 f32 f32 f32)
(result f32)
(local f32 f32 f32)
get_local 2
get_local 0
f32.sub
set_local 4
get_local 3
get_local 1
f32.sub
tee_local 5
get_local 5
f32.mul
get_local 4
get_local 4
f32.mul
f32.add
f32.sqrt
)
(func
(export length)
(param f64 f64 f64 f64)
(result f64)
(local f64 f64 f64)
get_local 2
get_local 0
f64.sub
set_local 4
get_local 3
get_local 1
f64.sub
tee_local 5
get_local 5
f64.mul
get_local 4
get_local 4
f64.mul
f64.add
f64.sqrt
)
)As compiled wasm in hex string (Note does not include name section) and loaded using WebAssembly.compile. Exported functions then run against Javascript function len (in below snippet)
// hex of above without the name section
const asm = `0061736d0100000001110260047d7d7d7d017d60047c7c7c7c017c0303020001071402076c656e677468460000066c656e67746800010a3b021c01037d2002200093210420032001932205200594200420049492910b1c01037c20022000a1210420032001a122052005a220042004a2a09f0b`
const bin = new Uint8Array(asm.length >> 1);
for(var i = 0; i < asm.length; i+= 2){ bin[i>>1] = parseInt(asm.substr(i,2),16) }
var length,lengthF;
WebAssembly.compile(bin).then(module => {
const wasmInstance = new WebAssembly.Instance(module, {});
lengthF = wasmInstance.exports.lengthF;
length = wasmInstance.exports.length;
});
// test values are const (same result if from array or literals)
const a1 = rand(-100000,100000);
const a2 = rand(-100000,100000);
const a3 = rand(-100000,100000);
const a4 = rand(-100000,100000);
// javascript version of function
function len(x,y,x1,y1){
var nx = x1 - x;
var ny = y1 - y;
return Math.sqrt(nx * nx + ny * ny);
}And the test code is the same for all 3 functions and run in strict mode.
tests : [{
func : function (){
var i;
for (i = 0; i < 100000; i += 1) {
length(a1,a2,a3,a4);
}
},
name : length64,
},{
func : function (){
var i;
for (i = 0; i < 100000; i += 1) {
lengthF(a1,a2,a3,a4);
}
},
name : length32,
},{
func : function (){
var i;
for (i = 0; i < 100000; i += 1) {
len(a1,a2,a3,a4);
}
},
name : lengthNative,
}
]The test results on FireFox are
/*
=======================================
Performance test. : WebAssm V Javascript
Use strict....... : true
Data view........ : false
Duplicates....... : 4
Cycles........... : 34
Samples per cycle : 100
Tests per Sample. : undefined
---------------------------------------------
Test : 'length64'
Mean : 26359µs ±128µs (*) 1128 samples
---------------------------------------------
Test : 'length32'
Mean : 27456µs ±109µs (*) 1144 samples
---------------------------------------------
Test : 'lengthNative'
Mean : 106µs ±2µs (*) 1128 samples
-All ----------------------------------------
Mean : 18.018ms Totals time : 61262.240ms 3400 samples
(*) Error rate approximation does not represent the variance.
*/
