Making the Google Chrome Speed Tests

These speed tests were filmed at actual web page rendering times. If you're interested in the technical details, read on!
Equipment used:
- Computer: MacBook Pro laptop with Windows installed
- Monitor - 24" Asus: We had to replace the standard fluorescent backlight with very large tungsten fixtures to funnel in more light to capture the screen. In addition, we flipped the monitor 180 degrees to eliminate a shadow from the driver board and set the system preferences on the computer to rotate 180 degrees. No special software was used in this process.
- Camera: Phantom v640 High Speed Camera at 1920 x 1080, films up to 2700 fps
"Why does allrecipes.com in the potato gun sequence appear at once, and not the text first and images second? And why does it appear to render from bottom of the screen to the top?"
Chrome sends the rendered page to the video card buffer all at once, which is why allrecipes.com appears at once, and not with the text first and images second. Chrome actually paints the page from top to bottom, but to eliminate a shadow from the driver board, we had to flip the monitor upside down and set the system preferences in Windows to rotate everything 180 degrees, resulting in the page appearing to render from bottom to top.
"Why does the top one third of the page appear first on the weather.com page load?"
Sometimes only half the buffer gets filled before the video card sends its buffer over to the LCD panel. This is because Chrome on Windows uses GDI to draw, which does not do v-sync.
"The screen wipes are so smooth - how was that achieved?"
The screen wipes up in a gradated wipe because LCD pixels take around 10ms to flip and gradually change color.
More filming details below:
Chrome Browser vs. Potato:
We used a version of the web page allrecipes.com that is accessible when logged in. About four hours into the Potato Gun shoot we decided to use a locally loaded version of the web page to enable more precise synchronization with the potato gun. We finally got the shot we were hoping for after 51 takes.
Chrome Browser vs. Sound:
We loaded an artist page from Pandora.com, a streaming internet radio service directly off the web on a 15Mbps internet connection.
Chrome Browser vs. Lightning:
We used a locally loaded version of weather.com that was legally approved for use in this video (and all the standard website permissions procedures that goes into making videos!)
While we had a super fast 15Mbps internet connection in the studio, any live internet connection introduces quite a bit of variability. To run speed tests on page rendering times, saving locally and loading from the local disk can help reduce this variability.
We'll be releasing the results of these speed tests:
chrome.blogspot.com/2010/05/pe...
www.google.com/chrome

[@GoogleChrome]

@maggitrymbill We actually had to flip the monitor upside down to get rid of a shadow, which is why it appears this way. Please check out the FAQ's in the video's description for further details.

[@lisapolous9908]

Pjessieburch

[@oscher88]

Its just another one of those virals, I liked it man, its funny to see things ( anything actually) in super slow-mo

[@StevePirk]

I swear this is even better than the actual commercial. What detail and engineering... Whoot!

[@Rapider10]

i seriously love that little spinning google chrome symbol... its so mesmerizing when it displays it still

[@AssafLavie]

What a brilliant idea for a video

[@dubrox]

They are crazy! I love it!

[@sportmd8243]

Congratulations it´s incredible!

[@EriCSNChang]

The props in this video are so amazing!! How did you think of those ideas? Google's ads are the most interesting ads I've ever seen!

[@DonnieGQ]

You Guys Inspire Me. I Would Love To Work For Anyone That Has The Skills To Create Another Video As Funny And Professional As This Was.

[@singulariter]

Well done.

[@SUNNETCTS]

nice experiment

[@0921702xxx]

it's a cool idea for testing ~ like it ~

[@CloneDVDair]

really awesome :D!! what did they expand above the speaker with the paint?!?!

[@christinaaaaa]

this is sick!!

[@nao921]

madness and i like this!

[@KrzysztofTarnowski]

Seems like a lot of fun :) Go Chrome Team!

[@rasputinaxp]

@LeonhartBA Read the info. Equipment used: - Computer: MacBook Pro laptop with Windows installed

[@szabiakanich]

Amazing stuff. :D

[@johnfranks]

all of this effort and logistics, yet when viewed frame by frame, the browser clearly has a head start in 2 of the 3 sequences. obviously, these aren't meant to be quantitative benchmark demonstrations, but with so much attention to detail and so many professional eyes involved, i'm disappointed to see the lack of attention to the synchronization of the triggers. =/ very cool ads nonetheless! that camera is incredible! -jc

[@ichguckvids]

"hey boss we wanna make a commercial..." " what do you need for it?" "a potato gun... a really nice speaker... and an lightning! oh and a looot of time so we can have fun while doing it" "I see, the usual then"

[@ameer1079]

I love it!

[@zheruixuan]

sounds too good

[@TriCitiesWARealEstate]

Nice!

[@STARTANGELO]

i actually felt that fan

[@MattCutts]

@maggitrymbill read the description FAQ included with the video. They had to flip the monitor upside down to get rid of a shadow.

[@mrmikerhubarb]

This is awesome! Nice work google.

[@fortysixfish]

Yet another reason why I'd want to work for google when I grow up.

[@agvr2]

this is fAmazing!!!!

[@XxKnine]

incognito option is the best!

[@kyruson]

That's cool!

[@CecilVermule]

All I have to say is that this is pretty cool. Using Chrome to watch this.

[@HanLeeBox]

Great!

[@NeroDeamon]

that discovery stuff......... but awesome anyways :D !!! i like it :P

[@52pegasi]

"Speed-Battle" delivers same results without smashing poor potatoes!

[@maggitrymbill]

@MattCutts Yeah, i saw that after I posted :-) Thanks dude!

[@ChristopherHindefjord]

@Klayhamn I can't see a big problem in that.. The test is about rendering not the time it takes to download all the content from the net (which is totally depended on what speed you have on your internet). By loading a local document you eliminate that variable (and I guess it could be hard to get a good internet connection at that location).. So: It's not a "spoof" (or whatever) they tested the rendering and only the rendering!

[@aimanazlan90]

Sweet.

[@GironRandom]

That's the tesla coil i wanted to see, thanks to C&C! LOL!

[@lonemavericks]

awesome

[@homen3]

I love them! wanna work on google too! ^^

[@laurikvo]

Actually they loaded Pandora page from web, other "tests" were stored on PC itself. They mentioned that in actual test video description. Direct quote: "Chrome Browser vs. Sound: We loaded an artist page from Pandora.com, a streaming internet radio service directly off the web on a 15Mbps internet connection." :)

[@dopster00]

cool stuff. chrome user since 08

[@JamesFan16]

lol at 0:28, and 0:32 xD and potato manicure!!!

[@HankyUSA]

@jmacraemorow Could you elaborate on your question(s)? I don't think I can construct a response from so little.

[@JohnnyJackPompolla]

I live in Agrentina. Here it doesn't matter what software you use, the internet will always be slow, as long as you do not own a high-tech company.

[@Arancaytar]

"It's not so much labcoats as more having fun and blowing things up." YAY SCIENCE! :D

[@f00tballfever]

love chrome.. better than any browser.! its so quick! perfect for people wth no patience.

[@stripes1981]

The Chrome is what the Firefox was a couple years back. A light, blazing fast alternative to the slow, bloated and cumbersome IE. A few years on and Firefox has added features and doesn't feel so light anymore. It'll be interesting to see what direction Chrome takes...

[@MCjingle]

If you read the description, they say "15MB/s Internet connection". Internet speed is measured in Bits not Bytes. An upper case B signifies Bytes, therefore that is 8x the speed of 15Mega bits per second, as there are 8 bits in a byte. Making it 120 Mega bits per second which is about 20 times faster than an average internet connection. In fact here in the UK, 50Mb is the fastest you can get. Didn't think anybody would spot that eh?

[@EisenFeuer]

@googlechrome so that wipe was the actual refresh rate of the monitor?

[@ShadowwwLFS]

@MCjingle I have gbit/s atm, and in our country average connection is 100 mbit which costs $20/month.

[@quinnjdq]

God can you please tell me how to make that chrome fan its so cool i want to make it and put it in my room!!!!

[@akmalhamzah]

they should also test how many times and fast that chrome can crash while using it.

[@HALLA717]

can you tell me how to make the potato launcher thing. Im going to use it in a science project to see which fruit shoot farther. Please?

[@legice]

the way commercials should look like=)

[@ilikemyrealname]

@radtwelve I agree, it's fast, but I've yet to see it be THAT fast. I was really excited to get it but when I would show it against other browsers it didn't seem faster.

[@AjayThakur]

Love to use Google Chrome but it always crashes on Mac when 3/4 tabs are opened specially when the sites are using flash .. damn it ..

[@hussainahm1981]

hmm but the mouse pointer is clicking on the Forward button ! meaning it's loading it from cache.

[@billete37]

@NitriXen I found that Chrome doesn't work with Rhapsody's flash player

[@Wreighn]

Opera ftw

[@westnyorai]

@stevensteven327 don't expect a lot from google OS, unless it's used for a netbook I don't see the point.

[@Cheejyg]

cool!

[@ngohienduong]

This is unbelive able

[@ishhanian]

Where can we see the final shots of these tests?

[@SportlLegend]

Can someone help me? I used to be able to use Google Chrome but now there's only a blank page when I use chrome, nothing loads. How do i fix this?

[@GuilhermedeLucas]

@DJ8ED Metalinguistica!

[@jargainjones]

@internetmud Sure you can, but then you look for efficiency, which is why I mentioned those other browsers. Would you rather walk to school in a brand new pair of $500 snow boots, and have it be a 5 mile walk each day, or would you rather live closer and have it be a 1 mile walk? Now you understand the basics of efficiency.

[@samuraixsamurai]

My Google Chrome browser crashed when watching this video lol

[@zosorh]

@xMaster711 I disagree, I think they're quite similar if it comes to security. I use both and I never come across any pop-ups or other malicious scripts, browsing with Chrome that I wouldn't have come across with Firefox.

[@coollord300]

i want a high air pressureized potato gun know

[@Tomm0509]

"Equipment used: Macbook pro with windows installed"

[@aqworldlyman]

@TazG2000 Download speeds are completely different as it has to deal with your connection. However, browsers all have a different configuration, and javascript on speeds; how many requests to send per a page. How quick to access and use cache, and much more. And I've tried just about every browser (luna, FF, IE, Saf, Opera etc.) and Google Chrome takes less than a second on a 25mb connection, and about 15 seconds for 1 minute of video to load. With IE, it take much longer.

[@Darkanii]

@TazG2000 Thats not entirely true, well they can't make downloading of files faster, but Opera for example has a slow connection-mode (opera turbo). What it does is that when you load a page it downloads the files to one of operas servers then compresses the images (and maybe js/css too?) and sends it to the user, thus making browsing faster. Obviously this is for slow connections, on a fast conneciton its faster to get the files directly from the hosting server and you get better image quality.

[@mluu510]

how many FPS was the lcd? it seems like it was refreshing faster than 60hz

[@matthickford]

The original Chrome speed tests video they are talking about has 300 views compared to 160,000 of this making of!

[@ironj221]

@GeorgePresents Chrome is only limited by your network speed. I'm sure these testers were done with the web content on a local network.

[@pmgodfrey]

- @quinnjdq - Looks like a few pieces of wood, probably without knots in them otherwise it would fly apart. Appears to be attached to a 1/2 or 3/4 horsepower motor which looked like it came from a polishing wheel or grinder wheel looking at the frame. Keep in mind that blocks of wood running around at 3400 RPM can become objects that, if broken loose will inflict damage. Use good screws, not drywall screws. As far as color, pickup some paint swatches at the hardware store and go from there.

[@spiceroyer]

@jazzy639 you mean you want to work at 1st avenue machine where they made this commercial?

[@rivkinnator]

@weinerschnitzelboy it kinda like saying would you play an vbox game on a ps3 or a ps3 gmae on an xbox? if they were both hacked yes it can be done but its just not ment nor optimized for that

[@Klayhamn]

@GloriousCow that simply isn't true. two browsers can deal with incoming traffic in very different ways - since usually by the time SOME of the data arrives, it's already possible to start rendering it. A good browser would be able to capitalize on that partial-data to start rendering the page. Also, some browsers might differ in the actual way they go about to retrieve the data to begin with.

[@JackRendar]

How fun it must be to be a Google Employee :D

[@rafalmag]

@almafuertegmailcom - right, but most users will compare to their web browser, which because of "the internet connection they had or the servers they were connecting to, or the speed of your OS's TCP/IP stack" is much slower. There should be clearly pointed that it is only rendering speed of preloaded content!

[@Algiz-n8d]

Im using firefox at the moment coz of the Addons. but also use chrome for fast web surfing

[@Assassination44]

awesome video. google FTW

[@dxyszou]

wonderfuly

[@Shadow14l]

@Ovidiu91 They're not measuring internet speed at all here. It has no affect. I don't even think the computers they were testing even were connected to the internet. If you look at the url's, you can see they are all local files.

[@khm8891]

@tubester4567 other features like what? thats why they have extensions or add ons

[@unvergebeneid]

What was the refresh rate of this monitor?

[@WaiWu]

"we moved to the idaho potato at this point....." LMAO!

[@MJQ-P]

yeah! cool.!

[@RyanONeill13]

1:19 Sonic boom! Wait, no...just salt. False alarm.

[@GloriousCow]

@Klayhamn From the original videos desc: "These speed tests were filmed at actual web page rendering times." Thats it - render time only. Bandwidth issues are irrelevant. A browser can do nothing about how fast the computer it is running on is connected to the internet. It can be smart about how it displays elements as they are downloaded, but thats it. This is a test of page rendering, and nothing more. So to sum it up - no they are not lying.

[@JanMikolajczak]

lol these ppl have the best jobs ever!!! :D

[@wayfarersprayer]

@Klayhamn tru dat

[@threecheerer]

2:33 so the keytar is an SHS-10!

[@wholesum]

Is the tesla coil guy Dr Mega Volt from burning man?

[@IkonikPhoto]

@GuitaristInProgress I've got Verizon FiOS (fiber-optic connection) with a tested, verified 30Mbps download speed, w/Mac OS X 10.6.2/2.8Ghz Core 2 Duo and I *still* have delays on sites that I've never gone to before. Not the browsers fault I think what people are saying is that page rendering speeds are highly dependent on what the browser has in cache (which is where most of your most viewed websites are rendering from, not necessarily a "fresh" download each time you call the page).

[@hgpot]

@AndrewFaulds why is that?

[@KennethHolmDahlin]

What build of Chrome are you using? 5?

[@FelixMaxwell]

the salt looked cool after it fell