• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.
  • The forums have been upgraded with support for dark mode. By default it will follow the setting on your system/browser. You may override it by scrolling to the end of the page and clicking the gears icon.

WebAssembly Fibonacci benchmarking

Result (average [ms])
JavaScript: 401.8000
WebAssembly: 178.7900
JavaScript/WebAssembly: 2.2473

CPU = Ryzen 7900 5.4 GHz
Browser = Edge
RAM = 4800 MHz 64 GB 2xChannels DDR5 CL40
 
How well does this work with NoScript...
 
P4-630 said:
How well does this work with NoScript...
Click to expand...
The NoScript browser extension allows JavaScript and other potentially harmful content to be executed only by trusted web sites of your choice (e.g. your online bank).
You can enable JavaScript and other dynamic capabilities for sites you trust with a simple click.

I have uploaded the source code of this web page here: https://pastebin.com/82rni7mB
As you can see it does not contain any suspicious code.

In Brave and most other browsers, you can press ctrl + u to view the source code of the page.
This is the HTML code.

To view the JavaScript code, press ctrl+shift+I while on the page.
 
Epiphany browser 44.3 (WebKit version 605.1)
Capture d’écran du 2023-06-08 10-13-29.png


The new version scores 1.2 ms better than the previous version in this test and seems to have become narrowly faster in WebAssembly.
 
Didn't realize Firefox was so much slower than Chromium in JS.
Linux 6.3.6-zen1-1-zen #1 ZEN SMP PREEMPT_DYNAMIC Mon, 05 Jun 2023 15:12:42 +0000 x86_64 GNU/Linux
R9 5900X with 32GB@3600MHz RAM
Screenshot from 2023-06-08 11-00-16.png
 

Attachments

  • Screenshot from 2023-06-08 11-01-54.png
    Screenshot from 2023-06-08 11-01-54.png
    470.5 KB · Views: 70
kacperoo29 said:
Didn't realize Firefox was so much slower than Chromium in JS.
Click to expand...
It is possible that developers mainly target Chrome and Safari and optimize specifically for these two browsers. You can often achieve a given result in JS with more than 4 different methods, and thus you can achieve the same result with vastly different code. What is optimal for Chrome is not necessarily optimal for Firefox. Suppose everything would be perfectly optimized for Firefox then it could (in theory) be that Firefox is faster in JS than Chrome.

There are benchmarks that seem to show that Firefox can be faster in JS than Chrome:
1. https://testdrive-archive.azurewebsites.net/Performance/RoboHornetPro/Default.html
2. https://www.principledtechnologies.com/benchmarkxprt/webxprt/
3. https://jsbench.me/
4. http://jsben.ch/9DaxR
5. http://jsben.ch/wnaZC
Etc.

You see that (many) popular websites with a lot of JS code often run faster on Firefox than on Chrome:
Firefox isn't slower than Chrome. It's faster.
by in firefox
 
Result (average [ms])
JavaScript: 1569.6000
WebAssembly: 382.7000
JavaScript/WebAssembly: 4.1014

i7-3770 , 2 x 8GB RAM @1600MHz DDR3 , GTX1060
Windows 10 22H2 , Firefox 114
 
Last edited:
i9 12900k + 32gb DDR4 @3600MHz + Chrome version 114.0.5735.110 (Official Build) (64-bit)

1686229061627.png
 
AMD 3800x + 32GB DDR4 @3600MHz + Brave Version 1.52.122 Chromium: 114.0.5735.110 (Offizieller Build) (64-Bit)

fib.jpg
 
Jacky_BEL said:
Result (average [ms])
JavaScript: 1569.6000
WebAssembly: 382.7000
JavaScript/WebAssembly: 4.1014

i7-3770 , 2 x 8GB RAM @1600MHz DDR3 , GTX1060
Windows 10 22H2 , Firefox 114
Click to expand...
Out of curiosity I ran it in Windows-Sandbox , which uses Edge , with following results:

Result (average [ms])
JavaScript: 973.5200
WebAssembly: 368.2300
JavaScript/WebAssembly: 2.6438
 
AMD

brave

Result (average [ms])
JavaScript: 538.1000
WebAssembly: 229.3000
JavaScript/WebAssembly: 2.3467

firefox

Result (average [ms])
JavaScript: 1179.5000
WebAssembly: 203.7000
JavaScript/WebAssembly: 5.7904

INTEL

brave

Result (average [ms])
JavaScript: 484.7000
WebAssembly: 203.9000
JavaScript/WebAssembly: 2.3771

firefox

Result (average [ms])
JavaScript: 1050.7000
WebAssembly: 201.9000
JavaScript/WebAssembly: 5.2041

great! another useless test...
 

Attachments

  • fibonacciAMD.jpg
    fibonacciAMD.jpg
    767.7 KB · Views: 82
  • fibonacciINTEL.jpg
    fibonacciINTEL.jpg
    1.2 MB · Views: 85
Result (average [ms])
JavaScript: 343.8100
WebAssembly: 164.8500
JavaScript/WebAssembly: 2.0856

CPU = Intel i9-13900k
Ram = Corsair 500MT/s 32gb DDR5
Browser = Edge Stable 114.0.1823.43
 
Capture d’écran du 2023-06-20 08-39-38.png

Nyxt browser - I think it has similar speed to Epiphany because both use WebKitGTK

Capture d’écran du 2023-06-20 19-08-35.png

After updating my system, I noticed that a much newer version of Nyxt was installed. (version 3.1.0)
It seems that Nyxt again became several percent faster in this test.
 
Screenshot from 2023-07-23 10-28-14.png

I score 348.4 ms

Hardware: Intel i3-3240 + 8GB DDR3 @1600MHz dual-channel + NVIDIA GTX 650 1GB + EVO 850 500GB
Software: Clear Linux + i3-wm + Epiphany 44.4 browser + nouveau open-source GPU driver
 
2023-08-02-155248_1920x1080_scrot.png

Hardware: AMD R5 PRO 3400G + dual-channel DDR4 @2666MHz + integrated graphics
Software: Void Linux + XFCE + Nyxt browser 3.3.0 + Mesa open-source GPU driver
 
7800x3d, 6400DDR5, Firefox 116, Win10

Result (average [ms])
JavaScript: 971.0000
WebAssembly: 173.9000
JavaScript/WebAssembly: 5.5837
 
xrpi7TK.png


Result (average [ms])
JavaScript: 243.5000
WebAssembly: 124.1000
JavaScript/WebAssembly: 1.9621

Software: Clear Linux -- Nyxt 3.9.1 -- GNOME Shell -- nouveau GPU driver
Hardware: Intel 12600KF -- Kingston 6000 MHz CL40 -- GTX 650 1GB -- BIOSTAR B760MZ-E PRO -- Antec P6 -- Xilence XP550 -- ARCTIC i35 -- EVO 850 500GB
 
dfGPlK3.png


Result: 124.0000

Hardware: Intel 12600KF (stock) -- Kingston 6200 MHz CL36 -- Sapphire RX 7600 -- BIOSTAR B760MZ-E PRO -- Antec P6 -- Xilence XP550 -- ARCTIC i35 -- 980 PRO 500GB
Software: OpenBSD, bspwm, open-source GPU driver, UFS file system, Epiphany 46

According to top, the total RAM usage of this system (when epiphany is open) is only 471 MB.
This would mean that you could still browse relatively well with this setup even if your system only has 1 GB of RAM.

To be clear, I'm talking specifically about active RAM usage.
 
9700x
6200MT/s


Edge:
1746997974416.png

LibreWolf:
1746998031447.png
 
You must log in or register to reply here.
Back
Top