It's Not Qualcomm's Fault: Dispelling TouchPad Myths
by Anand Lal Shimpi & Brian Klug on August 19, 2011 6:40 PM EST- Posted in
- Tablets
- HP
- Snapdragon
- OMAP
- Qualcomm
- Smartphones
- touchpad
- Mobile
It's Really Not Qualcomm's Fault
We've established that webOS has been and could be ported to different SoCs from different vendors – there's nothing tying it irrevocably to Qualcomm. The next is a discussion of the performance delta that existed because of differing hardware between tablet vendors. The Next Web wrote a story today claiming that webOS could run over 2x as fast on an iPad 2 than on an HP TouchPad. The claim gets even more interesting:
"With a focus on web technologies, webOS could be deployed in the iPad’s Mobile Safari browser as a web-app; this produced similar results, with it running many times faster in the browser than it did on the TouchPad."
I'm going to ignore the whole "because it's webOS it can run in a web browser" argument but let's get to the performance discussion. While webOS and Mojo do make substantial use of JavaScript, CSS, and HTML5, that doesn't necessarily mean the entire OS itself can be a web application. Don't forget the Palm PDK as well, which runs much closer to metal than the Mojo SDK.
Anyhow, the TouchPad uses Qualcomm's Snapdragon S3 APQ8060. It has two Scorpion cores running at 1.2GHz, a shared 512KB L2 cache and a dual-channel memory controller. In the TouchPad there's only a single 1GB DRAM on board. It's unclear if there are two DRAM die on that package or not, so whether or not the SoC is actually given full access to 2 x 32-bit LPDDR2 devices is unclear. The CPU cores are in-order and feature a pipelined FPU and NEON unit. On the GPU side the APQ8060 uses Qualcomm's Adreno 220.
If this hardware sounds familiar to you it's because it's the modem-less version of the MSM8x60, the same SoC used in the HTC Sensation and the EVO 3D.
The iPad 2 uses Apple's A5 SoC manufactured by Samsung. It has two ARM Cortex A9 cores, a 1MB shared L2 cache and a dual-channel memory controller. The A5 in the iPad 2 comes in a PoP (Package-on-Package) configuration with the DRAM stacked on the SoC die. Although it's physically unclear whether both channels are populated, the Samsung DRAM part number on the A5 indicates a PoP stack with two DRAM devices. In other words, the A5 is running in dual-channel mode. The CPU cores are out-of-order, feature a pipelined FPU and NEON unit. Imagination Technologies supplies the PowerVR SGX 543MP2 GPU in the A5.
From a CPU standpoint, Apple has a performance advantage at the same clock speed, but Qualcomm runs its cores at a higher clock. NVIDIA claimed that the move to an out-of-order architecture in the A9 was good for a 20% increase in IPC. Qualcomm has a 20% clock speed advantage. In most situations I think it's safe to say that the A5 and the APQ8060 have equally performing CPUs.
Apple does potentially have a memory bandwidth advantage as it's unclear the memory configuration of the TouchPad. I did wonder if this might be a reason why UI transitions were so slow on the TouchPad. In order to deliver a smooth UI you need good GPU acceleration built into your OS and you need sufficient memory bandwidth for the screen. At 1024 x 768 you need 180MB/s of memory bandwidth to render a UI at 60 fps. That's assuming no overdraw or multi-pass blending effects. With only a single LPDDR2-667 channel there's only 2.7GB/s of theoretical memory bandwidth. In practice you generally get 80% of peak theoretical memory bandwidth, that takes us down to 2.1GB/s. If we assume webOS was really inefficient in drawing its UI and needed 7x the bandwidth per frame, that still leaves us with 840MB/s of bandwidth available for the rest of the SoC. Assuming the CPU cores aren't doing anything, that's enough to provide a smooth, 60 fps UI. Start taxing those CPU cores and their bandwidth demands could go up to a few hundred MB/s, perhaps even more. Let's not even mention what happens if the GPU starts cranking away.
Now if we assume that webOS is super efficient, then even a single LPDDR2 channel is more than enough to deliver a high speed UI. In my calculations above I assumed a 7x increase in memory bandwidth requirements per frame. If we knock that down to 4x we nearly double the amount of memory bandwidth available to the rest of the SoC.
My point here is that the Qualcomm hardware is technically fast enough to deliver a smooth UI in webOS. The problem wasn't the hardware.
As far as CPU performance goes, here's a graph comparing the Tegra 2 based Galaxy Tab 10.1 to the A5 based iPad 2 in Sunspider 0.9:
Granted this test measures the entire hardware and software stack (browser, OS) and does show a ~2x performance delta between the TouchPad and iPad 2, but it shows that it's physically possible to build a tablet that has performance similar to the iPad 2. Furthermore, we've already shown that NVIDIA's Tegra 2 performs similarly to Qualcomm's dual-core SoC in other situations. Completing the circle it's safe to assume that at least from a CPU standpoint, Qualcomm's APQ8060 wasn't the factor holding back the TouchPad, it was software.
The only area where the iPad 2 could conceivably be 2x the speed of the TouchPad due to SoC hardware alone is in GPU performance. However the claims above say the performance advantage was demonstrated in a browser window and not in a cross-platform OpenGL ES 2.0 game.
These days Qualcomm's high end dual-core SoC is comparable to TI's and NVIDIA's. Each platform has its advantages but I find it very difficult to believe that Qualcomm was somehow responsible for the poor performance of the TouchPad.
79 Comments
View All Comments
g1011999 - Saturday, August 20, 2011 - link
If this hardware sounds familiar to you it's because it's the modem-less version of the MSM8x60, the same SoC used in the "HTC Thunderbolt" and the EVO 3D.I think HTC Thunderbolt didn't use the processor but HTC Sensation.
fteoath64 - Saturday, August 20, 2011 - link
Well, HP is expecting too much in terms of sales when the product does not really measure up in terms of price or performance. It has not even given sufficient time to move the product much less the marketing effort being put into it.If you look at the Android tablets, they took about 2 years to get to market, then it started moving but not as fast due to the higher price points. If HP were to position the price at $350 initially, it would have moved volumes compared to their initial prices. They did not learn from Xoom pricing which had to be slashed to move the product. The market is more elastic than it seems, so the marketing people are not doing their jobs.
How could Qualcomm be at fault for their SoCs ?. There are plenty of QualComm Soc smartphones that are plenty fast and selling very well in the market.
piiman - Saturday, August 20, 2011 - link
Yeah at 100.00 bucks these things are flying off the shelves! I find it odd no one as figured out that to beat Apple they should sell their pad for less not more or even the same. I want competition not more of the same.DaemonES - Saturday, August 20, 2011 - link
Scorpion core performing in out-of-order. Article mentioned it like in-order.Wilco1 - Saturday, August 20, 2011 - link
No, the Scorpion core is in-order. It is basically a Cortex-A8 clone, with almost identical integer performance. It supports out-of-order completion of instructions which is something entirely different. Instructions are always executed in-order, but memory instructions use a much longer pipeline which means that simpler instructions which execute afterwards may complete earlier.While out-of-order completion improves performance, any cache miss will still stall the whole core. Given that Cortex-A8 does not support out-of-order completion, and is usually a little faster than Scorpion, it is safe to say that out-of-order completion doesn't provide much performance gain.
An out-of-order core executes instructions out-of-order using register renaming but always completes them in-order. This provides substantial performance gains (20-50%) as the core can continue executing independent instructions after a cache miss. This explains why Scorpion cores have a hard time keeping up with the Cortex-A9, as evidenced by the benchmark results.
Wilco
vshah - Saturday, August 20, 2011 - link
"the same SoC used in the HTC Thunderbolt and the EVO 3D "Should be HTC Sensation, no?
jed22281 - Saturday, August 20, 2011 - link
"The TouchPad needed more work, and webOS as a whole needs more work. You can either scale a project out by taking more time to get it done, or you can scale its width by committing more resources to it. The latter (and more efficient development) is what Palm has needed since day one, what HP promised to bring to it, and sadly exactly what it ultimately failed to receive at HP."Sigh, the parallels with what happened to MeeGo inside Nokia are uncanny.
Symbian kept winning the departmental funding wars until far too late.
As a result Maemo had much less resources, was scaled-out, & need more time.
It didn't get the focus it deserved/needed until Jan 2010, the rest is history.
Despite popular misconception, the merging with Moblin into Meego had little impact on Harmattan's progress compared to the aforementioned.
Penti - Sunday, August 21, 2011 - link
Symbian and MeeGo uses the exact same framework for the applications so there never really was any war, Symbian was carrying QtMobility forward. All the APIs are implemented on Harmattan too. It is a cross-platform runtime/framework and it is a mature runtime/framework/ecosystem/SDK/platform you need. Mango simply isn't getting up to date either it is just trying to catch up technically. It's just a case of killing things too early/before market entry. WebOS was never really launched in a major product by HP as they never got the Pre3 out. Nokia on the other hand had a production used SDK that it ported to run on both Symbian and Linux so it hardly looked hopeless there, however you do have to cancel products some times even before market entry this just wasn't clear that it was the right products that got canceled.Also such things like making it run on the platforms/SoC's is also up to the hardware vendors, and of course platforms like Symbian, Android and even MeeGo which was getting drivers and whole board support packages for several SoCs when Nokia didn't want it any longer as well as the Linux Kernel in general. It's far easier for WebOS to work for a large range of devices then say WP7. MeeGo was essentially put of the map before they got the bits put together with Nokia's regard. Switching from Clutter to Qt was a good move though if they really would have went through with it fully. It wasn't a question of the OS itself there rather the platform on top of it which isn't OS-bound.
It also kinda is like if they would have given up at RIM with the Blackberry Playbook after 45 days. It's ridiculous and no tablet really other then Apple's which wasn't a finished product itself when released, is gonna take off the first minute it is released. If so it would really only be Apple and Samsung on the market. Here in Sweden they never got to release either the TouchPad or the Veer here for that matter. I don't think you can really judge a platform within 30 days as HP management did, it wasn't even a world release, third party software was of course lagging and would of course be lacking as long as they only had the touchpad and veer on the market. It might been out on the selfs in the US but still just as Palm failed wasn't a world release and wasn't given time for the software to be worked out. It would be quite odd if you could create a software platform and framework which would work on tablets alone today. Not many would be familiar with such a platform.
ssnova - Saturday, August 20, 2011 - link
To all those "haters" and paranoid people about Anand selling out to qualcomm, they should find better things to waste their time on, rather than pointing fingers and being useless witchhunters.I found the article to be as fair as possible and technically "enlightening", if one would see other articles out there that say, "oh webOS runs 2x faster on the ipad2", then most would come to the strict conclusion that hp's touchpad's hardware was the sole thing to blame. But when one examine's the touchpad's hardware the whole story doesn't make sense. Anand basically broke it down for us and shed some light on the subject matter, which I thought was cool and appreciated it as a reader.
From what I get, certain aspects would run faster on different hardware, again, not because the hardware is "that much more superior", but because the old code was optimized for other hardware as well.
Any how, here's to hoping that webOS will either: a.) improve...or b.) someone does a good port of android OS to the touchpad's hardware...as I keep my eye out for a low priced touchdpad, :P
Keep on keeping on Anand, you the man!
BillBear - Saturday, August 20, 2011 - link
If we're into clearing up mistaken information on the web, why are you ignoring this?Mojo based WebOS apps can run in Safari.
Palm's very first webcast introducing the WebOS app environment to potential developers featured writing demo app code in Textmate on a Macintosh and then running that demo app on top of Safari.
You can still catch that webcast here: http://www.youtube.com/watch?v=YXS3SQauwPE