Samsung's ATIV Smart PC 500T: An Atom-Based Windows 8 Tablet

[Brazilian Joe]

I miss sRGB Gamut and color accuracy tests.

While Adobe RGB is a wider color space, it is also only fully covered on very high-end, very expensive hardware.

sRGB on the other hand, despite being a smaller gamut, is still a great target, widely used by a large amount of amateurs, enthusiasts, prosumers, entry and mid-level professionals, because it is much easier to achieve consitency across screen and print, and across different computers as well.

Summarizing, sRGB has much more value for the average user, and the target audience of this device than Adobe RGB.

Adobe RGB is more of a 'bling bling' spec to draw audience to this review, but people who actually need it for work would quickly dismiss this device. Not that it is bad to have it in the review, much on the contrary. Bur bring back the sRGB numbers please.

 

[keither5150]

Almost there, I need a windows 8 tablet that has at least 256GB.

 

[Guest]

I slapped Win8 Pro on a Acer W500 (with an AMD C-50 processor) and the performance is considerably better than the Atom in this article. I get 4-5 hours batterylife with wifi enabled, browsing internet, playing games , and watching videos (youtube and mkv). Honestly, all Win8 haters have never used the OS on a touch device; because it is awesome on a touch device! I really wish Acer had made a follow up to the W500 with another AMD processor (with a higher resolution screen and an E series processor or better) cuz that would be my uber sweet spot right there.

 

[ojas]

@Alan: Also, Anand has shown Medfield's power consumption and Clover Trail's too, much before Intel's tour, so they had sort of validated those findings before hand as well. Plus AT usually has normalized battery benchmarks as well.

Anyway, they've posted a review of Samsung's ATIV Tab, which runs WindowsRT and uses a Snapdragon processor:
http://www.anandtech.com/show/6528/samsung-ativ-tab-review-qualcomms-first-windows-rt-tablet

 

[AlanDang]

@Ojas,

I guess it is a question of synthetics vs. real-world benchmarks.

Let's look at integer performance on Geekbench. Geekbench runs some blowfish cipher tests. Blowfish is public domain, which makes it easy to implement and has a fixed 64-bit block size. In real life, blowfish really isn't use. It's all AES (Rijndael). But they're using Blowfish, so we're stuck with that.

Then there's compression using bzip2. It's a lot more computationally intensive than regular zip, and it's also open source. That makes sense for a benchmark. But in real-life, most people are still using regular ZIP. So it's not entirely applicable to real-world performance even though it's a legit test.

Then there's image with libjpeg. That's actually pretty good since JPEGs are still the dominant graphics format and libjpeg is a pretty reasonable library. In real-life, we're using libjpeg-turbo which adds SIMD support. It's one of the tricks that made Firefox and Chrome really fast.

Last there's a prime number sieve done in Lua. People aren't finding prime numbers on a day to day basis, and people aren't writing in Lua routinely, so this one is sort of artificial.

Run these tests, and you'll get a magic number describing "integer performance"

With SiSoft Sandra, it's running a multithreaded 64-bit version of dhrystones. The Dhrystone benchmark started in 1984 one smart individual took a look at "a broad range of software, including programs written in FORTRAN, PL/1, SAL, ALGOL 68, and Pascal" and then "characterized these programs in terms of various common constructs: procedure calls, pointer indirections, assignments, etc." From that, he wrote the Dhrystone benchmark to correspond to a representative mix.

So Sandra tells you how the programs of 1984 would run on today's CPUs if multithreaded and done in 64-bit.

So you tell me which is better? The answer is neither. It all depends on what you're looking for and what you want to measure. The important part is CONTEXT and understanding that when things are "unbelievable" it just means that the test scenario isn't reflecting the real-world experience for some reason.

I'm not saying that Anand did anything wrong. I just thought it was interesting to point out that, as a scientist, I spend more time thinking about methods and potential errors in methodology than just results. It's not power consumption based upon previous publications but test runs.

We work with companies regularly. Sometimes a company has a product that's awesome, and with an awesome product, the company would obviously like to help drum up publicity on it by doing a head-to-head comparison. Sometimes a company has a product that isn't awesome and they need to drum up publicity, so they'll do a skewed head-to-head comparison.

The trick isn't figuring out *when* or *if* results are skewed. They always are. The trick is figuring out *how* the tests are skewed and thinking about what that means for real-life use patterns.

With synthetic benchmarks, it's important to understand what's going under the hood. Qualcomm's Vellamo benchmark uses a single thread Linpack -- great for dual core Snapdragons and bad for quad core Tegra 3. Is it a bad benchmark with fishy results? No, it tells you a lot about single-threaded floating point apps. But not all of your apps are going to be single-threaded FP apps.

 

[ojas]

@Alan

Thanks for the breakdown on Geekbench's component benchmarks, i didn't know what they really tested or how they're used, beyond geekbench's short desctiption.

I wish this discussion on Dhrystone/Whetstone had happened a month ago, i randomly ended up reading about it, but i don't remember much now, but yeah it's an old benchmark. IIRC, for some reason, it's still deemed relevent, and i'm not sure but i think Sandra's implementaion is not the original algorithim, but slightly tweaked, i might be completely wrong here. And, the EMBC (folks who made Browser Bench, +1 on using that BTW, i was going to suggest it sooner or later to Chris or Andrew) have a modern implementation of Dhrystone, again if memory serves me correctly (They have CoreMark, MultiBench, and Energy Bench, how are those?).

Oh, and, what's this they're using? (You guys probably shouldn't bother running this, after all Anand's already run it):

We have one last web-based benchmark: WebXPRT by Principled Technologies (PT). WebXPRT measures performance in four HTML5/js workloads:

Photo Effects: Measures the time to apply effects to a set of six photos. The filters are Sharpen, Emboss, and Glow. WebXPRT applies each filter to two photos. This test uses HTML5 Canvas 2D and JavaScript.

Face Detect: Measures the average time to check for human faces in a photo. WebXPRT runs this test on five photos and uses the average time to calculate the final result. This test uses HTML5 Canvas 2D to get access to photo data. The detection algorithm is implemented in JavaScript.

Stocks Dashboard: Measures the time to calculate financial indicators of a stock based on historical data and display the result in a dashboard. The calculations are done in JavaScript, and the calculated stocks data is displayed using HTML tables and Canvas 2D.

Offline Notes: Measures the time to store notes securely in the browser's HTML5 local storage and display recent entries. This test uses using AES for security.

This is from the 2nd page of the Samsung Tab review.

Also on Vellamo...there's been a new version out, does it use single-threaded Linpack too? I've always seen Tegra 3 based devices score relatively higher on Vellamo (and AnTuTu)...

I've run it on a Xolo X900, and even with the separate Linpack download, the difference between one thread and two is minimal on Medfield, Anand found similar results back in May.

Also what about AnTuTu? They had a bug with x86 stuff (another example of why it might be a good idea to use more than one synthetic), and performance jumped quite a bit after they patched it.

Again, i'll bring up PassMark, as it's Windows/Android/iOS...it thinks my CPU (Core 2 Quad Q8400) does 4.4 MB/s per core in the encryption test, and my fourth generation ipod does 5.394 MB/s. the 200 MHz slower ZTE blade does 512 KB/s according to it. It just took one version update for the ipod's score to go from a few hundred KB/s to that insane figure. So yeah. Probably why Andrew doesn't trust this either. Of course, it may be single threaded, and the 16.6 MB/s it claims for my CPU might be for one thread, but in the config it specifically states it's using a multi-threaded benchmark.

Finally: Why not make your (as in, TH's) own benchmark?

P.S. Try and include the Xolo X900/Orange San Diego/Motorola Razar i as well, wouldn't hurt to compare Medfield to Clover Trail going forward. At least, wouldn't be a bad idea to keep it on the charts.

 

[ojas]

It's showing me 21 MB/s for my ipod now :lol:

 

[Squall321]

stop with this windows rt stuff.. y u no make "smart-ultra-tablet-laptop"-pc's with plain ol' windows

 

[cangelini]

[citation][nom]Squall321[/nom]stop with this windows rt stuff.. y u no make "smart-ultra-tablet-laptop"-pc's with plain ol' windows[/citation]
Did you read the story?

 

[ojas]

[citation][nom]AlanDang[/nom]Anandtech and Tom's HW both recently did articles looking at granular power consumption on Atom vs. Tegra3 on WinRT using Intel's test equipment. Anand went with Intel's HW and focused on getting out benchmarks for boot-up, etc. (with pretty looking graphs). Our article published granular data for the memory subsystem, screen, etc. and then spent a lot of time with thinking about ways to independently validate those results and how just the mindset of thinking about watts being drawn for specific tasks lets us make some good predictions for A15, Krait, etc. It's almost like movie reviews. If everyone agrees that something is great, you know you have a winner. If there's a lot of debate, you know that no single solution is perfect, otherwise there wouldn't be a debate.[/citation]
lol looks like Anand's read this comment of yours.
The ARM vs x86 Wars Have Begun: In-Depth Power Analysis of Atom, Krait & Cortex A15

The previous article focused on an admittedly not too interesting comparison: Intel's Atom Z2760 (Clover Trail) versus NVIDIA's Tegra 3. After much pleading, Intel returned with two more tablets: a Dell XPS 10 using Qualcomm's APQ8060A SoC (dual-core 28nm Krait) and a Nexus 10 using Samsung's Exynos 5 Dual (dual-core 32nm Cortex A15). What was a walk in the park for Atom all of the sudden became much more challenging. Both of these SoCs are built on very modern, low power manufacturing processes and Intel no longer has a performance advantage compared to Exynos 5.

 

[ojas]

I think i liked this page ("Final Words") the most, have a read:
http://www.anandtech.com/show/6536/arm-vs-x86-the-real-showdown/14

 

[Bloob]

I'll just shamelessly advertise this AMD tablet here too: http://microsoft-news.com/vizio-announce-first-amd-powered-windows-8-tablet-with-1080p-screen/

 

[madjimms]

In our hands, the Surface's chassis feels much better-built, although its matte finish shows fingerprints very readily. Samsung employs tons of gloss, so you see nothing but shine when you look at the device itself. However, the more slippery body also feels cheaper.

I think someone got matte & gloss confused because gloss gets fingerprints & matte usually doesn't.

 

[jn77]

Samsung can't seem to get the 1 thing right that apple did...... 2048x1536.......... give me at least that much screen rez or 4K rez and I will consider purchasing it. And maybe 256gb SSD with 4 micro SDXC card slots.

 

[jeromesan1]

Can i use samsung ativ smart pc while charging? Just like an ordinary laptop that you remove the battery and connect to the power source(or sometimes called outlet) then you can use for a longer time.

 

[jeromesan1]

There's a USIM CARD slot in this device. how can i use it?.

 

[uselessness123]

Why would you bench the ATIV Smart PC against other price brackets and obviously superiour hardware. This benchmark told me absolutely nothing.

 

[Bron]

You can easily add in a 64GB Micro SD card to address the storage space issues, that gives you over 100 GB free and apps can be installed on the micro-SD card, too. Not to mention that you can add USB HDD's to the dock and have tons of storage that way (terabytes if you want). But for walking around, 100 GB is not bad. And I have a 320 GB wifi drive that can be used as well and is OK for media consumption and similar tasks (not perfect, but usable).