So based on that, it's potentially 73% faster than the old Atom clock for clock, assuming perfect scaling. .25 points per GHz per core compared to .1444 points per GHz for Saltwell.
What I consider important is that this is a FP test and Silvermont improves more on integer side so it's safe to say it will beat the same A4 in integer loads (eg. the stuff that is actually relevant on tablets).
Quick check for single threaded Cinebench 11.5 scores for the Z2760 yields 0.18. So normalizing for frequency (assuming that the Z3770 is actually running at 2.4 GHz) would have Baytrail roughly 53% faster.
Z3770 is not running at 2.4Ghz four cores active here. Likely this 3W soc has only a very little factory fixed turbo with four cores up, so your calculation has not common sense. No, actually you can not calculate the single thread performance. Moreover remember that A4-5000 is 15W TDP so is not competitive at all in tablets, the only feasible Amd soc is clocked at 1Ghz dual core only. This is the reason Kabini actually is very weak in mobile.
Assume that the A4-5000 idles at under 1W (I've heard it's actually 0.77W). This means that the chip uses 8W more in Prime95, for a total of 9W. An extra 6W is consumed if FurMark is thrown into the mix as that large GPU fires up. You would indeed get your 15W usage there... but certainly not when you're running a CineBench test?
Sure, Kabini will use more power, but not drastically so, and it always depends on the usage scenario anyway. Considering the large GPU, higher process node and lack of a dual channel memory controller, Kabini will do quite well in terms of power but is still leaving a little potential performance on the table. In any case, I imagine its GPU will run rings around Bay Trail's.
Same is valid for Intel Soc, Baytrail T 3W TDP is with GPU on die up and running, so very likely under cpu stress the four cpus consume less than 2W at 1.47 Ghz. In my country 9W is MORE than FOUR times 2W. It is a fact that this 3W soc can sport the same throughput of a 15W Kabini. No, you can not try to defend Kabini, he is not born for mobile but for a console instead. Not a chance, in fact nobody use it waiting for Baytrail, this really counts. We'll see next year with the Soc refresh, maybe will be better still i have some doubts because the process is the same and the arc too.
I'm pretty sure that beating an A4 in integer workloads isn't all that relevant on tablets... :P
The more pertinent questions here are what's the price, tdp, performance, and what are the design wins? It's safe to assume we'll see a variety of Win8 x86 devices, but, again, we're talking about what's relevant on tablets :D
Intel's mighty marketing honcho AKA Francois claimed Haswell would be ...hot as hell...and in the area of thermodynamics, he was accurate.
So, if he is involved in dispensing performance tweets you can assume that clock rate was 30-40% more than indicated and real power usage was at minimun 2-3 times Intel's marketing TDP.
Forgive me, but isn't the comparison with a 2010 MBA Core 2 Duo based on the assumption that Baytrail will clock around 2GHz? Do we have anything concrete on clocks or is this an educated guess based on the power savings of FinFET 22nm process?
So performance will come down to the thermal limits of the device. I wonder whether a 2-2.4GHz could be sustained for very long in a passively cooled device. Or are the rumoured 2.4GHz clocks likely only for the Pentium/Celeron branded low end notebooks? I think Dan is on the money for this one.
Turbo boost is such a SCAM, from everyone using it, including Nvidia for their GPU's (and I guess AMD, too).
Turbo-Boost frequency (more relevantly called "burst speed") is almost completely IRRELEVANT, because you'll not be able to use it for too long. The real speed is the base one, so 1.46 Ghz for Atom.
In thermal- and power-constrained devices like tablets, you may have somewhat of a point. Anywhere else? You're very wrong. Turbo is utilized frequently and makes quite a bit of difference.
Why mention Penryn then not include it in the benchmarks?
I have penryn and if this is really faster then well, it's time to upgrade I guess. I'm using penryn 2.2ghz with a 9800MGTS and it still is serving me well. Been waiting for baytrail to see if I can upgrade. Would be funny to get a tablet that performed better than my old laptop all around. I know it's probably not possible to get that type of GPU performance lol but man..... this is ridiculous how intel is moving. I'm loving the dedication to mobile now.
Same here, I have a Conroe-based desktop and a Penryn laptop that get about 1.3 and 1.1 respectively on Cinebench 11.5. When you use a spreadsheet and presentation software for 90% of your non-web browsing time, there's little incentive to upgrade. Both my processors have TDP of 35w and this bad boy is 4.5 or so. Pretty crazy to be 10% faster but use 1/8th the power. If Bay Trail allows for more than 4gb ram and a good 1440p monitor, I'd jump.
Never mind celerons, this stuff is (as you can see from above) logically positioned to take a huge swathe of the consumer market from the Core line. If not in this generation then certainly fairly soon. Much cheaper, passively cooled etc.
It might well considerably improve the quality at the budget end too. Or maybe they'll manage to control it somehow so it won't.....
The problem with Cinebench is, that it's compiled with the Intel compiler which means that all SIMD optimizations are disabled on non Intel CPUs, which skews the benchmark considerably. No wonder Intel was choosing this and only this as a showcase.
The information we need is at what actual clocks was the Baytrail chip running. We know very well that Intel's Turbo is very aggressive. Even when all 4 threads are running the CPU will use the full SOC TDP and because the GPU is not under heavy load all 4 cores could be boosting to 2 Ghz. But when you run a workload like 3DMark or a game the CPU cores and GPU cores will get fully utilized and so the max achievable CPU turbo could be much lower.
Anyway this Baytrail chip should be faster than A6-1450 for CPU performance. but the fact is the A6-1450 GPU should easily be faster. we also need to see the TDP and average power consumption of this Baytrail chip. AMD needs to come out with a slightly better binned SKU than A6-1450 with better turbo clocks. single core turbo can easily go upto 2 Ghz and quad core turbo should atleast hit 1.2 Ghz.
Rag - a6-1450 in Acer v5-122 uses about 4w in cinebench 11.5 and scores 1.02 - google notebookcheck a6-1450. Based on all the leaks I have seen, Bay Trail probably runs at 1.46 GHz with a turbo freq of 2.4 GHz. Look @ geekbench browser, this leak, or the antutu leaks from earlier - all are @ 1.46 GHz (except one of the earliest AnTuTu benchmarks @ 1.1 GHz)
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
33 Comments
Back to Article
Lonyo - Wednesday, September 4, 2013 - link
So based on that, it's potentially 73% faster than the old Atom clock for clock, assuming perfect scaling..25 points per GHz per core compared to .1444 points per GHz for Saltwell.
beginner99 - Wednesday, September 4, 2013 - link
What I consider important is that this is a FP test and Silvermont improves more on integer side so it's safe to say it will beat the same A4 in integer loads (eg. the stuff that is actually relevant on tablets).karasaj - Wednesday, September 4, 2013 - link
Isn't saltwell .26 per core? While Baytrail would be .375 per core? .52/2 (saltwell only has 2 cores) vs ~1.5 / 4 (baytrail has four)?Anand Lal Shimpi - Wednesday, September 4, 2013 - link
Keep in mind that Clovertrail is 2 cores/4 threads, so per core utilization is higher than a standard 2 core/2 thread part.karasaj - Wednesday, September 4, 2013 - link
/oh i forgot about that. Somewhere in between then?Khato - Wednesday, September 4, 2013 - link
Quick check for single threaded Cinebench 11.5 scores for the Z2760 yields 0.18. So normalizing for frequency (assuming that the Z3770 is actually running at 2.4 GHz) would have Baytrail roughly 53% faster.Gondalf - Wednesday, September 4, 2013 - link
Z3770 is not running at 2.4Ghz four cores active here. Likely this 3W soc has only a very little factory fixed turbo with four cores up, so your calculation has not common sense. No, actually you can not calculate the single thread performance.Moreover remember that A4-5000 is 15W TDP so is not competitive at all in tablets, the only feasible Amd soc is clocked at 1Ghz dual core only. This is the reason Kabini actually is very weak in mobile.
silverblue - Thursday, September 5, 2013 - link
Again, TDP rears its ugly head. The A4-5000 may be rated at 15W TDP but that doesn't mean it uses it, especially not in every day scenarios.Consider the following link:
http://www.techspot.com/review/671-amd-a4-5000-kab...
Assume that the A4-5000 idles at under 1W (I've heard it's actually 0.77W). This means that the chip uses 8W more in Prime95, for a total of 9W. An extra 6W is consumed if FurMark is thrown into the mix as that large GPU fires up. You would indeed get your 15W usage there... but certainly not when you're running a CineBench test?
Also, consider this:
http://www.tomshardware.com/reviews/kabini-a4-5000...
Sure, Kabini will use more power, but not drastically so, and it always depends on the usage scenario anyway. Considering the large GPU, higher process node and lack of a dual channel memory controller, Kabini will do quite well in terms of power but is still leaving a little potential performance on the table. In any case, I imagine its GPU will run rings around Bay Trail's.
Gondalf - Thursday, September 5, 2013 - link
Same is valid for Intel Soc, Baytrail T 3W TDP is with GPU on die up and running, so very likely under cpu stress the four cpus consume less than 2W at 1.47 Ghz. In my country 9W is MORE than FOUR times 2W.It is a fact that this 3W soc can sport the same throughput of a 15W Kabini.
No, you can not try to defend Kabini, he is not born for mobile but for a console instead. Not a chance, in fact nobody use it waiting for Baytrail, this really counts.
We'll see next year with the Soc refresh, maybe will be better still i have some doubts because the process is the same and the arc too.
mrdude - Wednesday, September 4, 2013 - link
I'm pretty sure that beating an A4 in integer workloads isn't all that relevant on tablets... :PThe more pertinent questions here are what's the price, tdp, performance, and what are the design wins? It's safe to assume we'll see a variety of Win8 x86 devices, but, again, we're talking about what's relevant on tablets :D
axien86 - Wednesday, September 4, 2013 - link
Intel's mighty marketing honcho AKA Francois claimed Haswell would be ...hot as hell...and in the area of thermodynamics, he was accurate.So, if he is involved in dispensing performance tweets you can assume that clock rate was 30-40% more than indicated and real power usage was at minimun 2-3 times Intel's marketing TDP.
jljaynes - Wednesday, September 4, 2013 - link
* 'SDP' - who knows what the TDP is.Homeles - Wednesday, September 4, 2013 - link
Try reading his comment again, bro.jljaynes - Thursday, September 5, 2013 - link
Intel uses SDP to market a lower number? I'm not disagreeing with what he saidzlatan - Wednesday, September 4, 2013 - link
32 bit OS? :oSo the rumors are true, there won't be 64 bit support this year. It's shame Intel. :(
DanNeely - Wednesday, September 4, 2013 - link
Is this Intel's fault for not having a 64bit driver, or MS's fault for not enabling the feature in their 64 bit builds?Wade_Jensen - Wednesday, September 4, 2013 - link
Forgive me, but isn't the comparison with a 2010 MBA Core 2 Duo based on the assumption that Baytrail will clock around 2GHz? Do we have anything concrete on clocks or is this an educated guess based on the power savings of FinFET 22nm process?DanNeely - Wednesday, September 4, 2013 - link
Previous reporting said Baytrail will be available in up to 2.4 ghz variants.ex:
liliputing.com/2013/07/intel-atom-z3770-bay-trail-chip-specs-performance-leaked.html
jljaynes - Wednesday, September 4, 2013 - link
Dan - based on everything I have seen, I believe 2.4 GHz is the turbo frequency, but the chip is actually a 1.46 GHz part.DanNeely - Thursday, September 5, 2013 - link
In addition to tablets Intel's launching baytrail under the Celeron and Pentium names. I suspect the latter will be the only ones running at 2.4ghz.Wade_Jensen - Thursday, September 5, 2013 - link
So performance will come down to the thermal limits of the device. I wonder whether a 2-2.4GHz could be sustained for very long in a passively cooled device. Or are the rumoured 2.4GHz clocks likely only for the Pentium/Celeron branded low end notebooks? I think Dan is on the money for this one.Krysto - Friday, September 6, 2013 - link
Turbo boost is such a SCAM, from everyone using it, including Nvidia for their GPU's (and I guess AMD, too).Turbo-Boost frequency (more relevantly called "burst speed") is almost completely IRRELEVANT, because you'll not be able to use it for too long. The real speed is the base one, so 1.46 Ghz for Atom.
kyuu - Sunday, September 8, 2013 - link
In thermal- and power-constrained devices like tablets, you may have somewhat of a point. Anywhere else? You're very wrong. Turbo is utilized frequently and makes quite a bit of difference.tential - Wednesday, September 4, 2013 - link
Why mention Penryn then not include it in the benchmarks?I have penryn and if this is really faster then well, it's time to upgrade I guess. I'm using penryn 2.2ghz with a 9800MGTS and it still is serving me well. Been waiting for baytrail to see if I can upgrade. Would be funny to get a tablet that performed better than my old laptop all around. I know it's probably not possible to get that type of GPU performance lol but man..... this is ridiculous how intel is moving. I'm loving the dedication to mobile now.
purerice - Wednesday, September 4, 2013 - link
Same here, I have a Conroe-based desktop and a Penryn laptop that get about 1.3 and 1.1 respectively on Cinebench 11.5. When you use a spreadsheet and presentation software for 90% of your non-web browsing time, there's little incentive to upgrade.Both my processors have TDP of 35w and this bad boy is 4.5 or so. Pretty crazy to be 10% faster but use 1/8th the power.
If Bay Trail allows for more than 4gb ram and a good 1440p monitor, I'd jump.
Boissez - Thursday, September 5, 2013 - link
FWIW I tested an old system I have with a Q9300 quad @2,5 Ghz with 32-bit XP. It yielded a score of 2.84 in CB11.5.Or if one were to extrapolate the clocks Baytrail comes within 10% of Penryn in terms of IPC (or about the same as Kentsfield). Not too shabby.
aousy - Wednesday, September 4, 2013 - link
The question is how much will Intel sell it for. Sell it too cheap and it will cannibalize Celerons, sell it too high and nobody will buy it.Qwertilot - Thursday, September 5, 2013 - link
Never mind celerons, this stuff is (as you can see from above) logically positioned to take a huge swathe of the consumer market from the Core line. If not in this generation then certainly fairly soon. Much cheaper, passively cooled etc.It might well considerably improve the quality at the budget end too. Or maybe they'll manage to control it somehow so it won't.....
Roland00Address - Thursday, September 5, 2013 - link
it is ok for this chip to cannibalize Celerons because it die size is smaller than a Celeron it is a problem if this chip cannibalize the core seriesNovum - Thursday, September 5, 2013 - link
The problem with Cinebench is, that it's compiled with the Intel compiler which means that all SIMD optimizations are disabled on non Intel CPUs, which skews the benchmark considerably. No wonder Intel was choosing this and only this as a showcase.raghu78 - Thursday, September 5, 2013 - link
The information we need is at what actual clocks was the Baytrail chip running. We know very well that Intel's Turbo is very aggressive. Even when all 4 threads are running the CPU will use the full SOC TDP and because the GPU is not under heavy load all 4 cores could be boosting to 2 Ghz. But when you run a workload like 3DMark or a game the CPU cores and GPU cores will get fully utilized and so the max achievable CPU turbo could be much lower.Anyway this Baytrail chip should be faster than A6-1450 for CPU performance. but the fact is the A6-1450 GPU should easily be faster. we also need to see the TDP and average power consumption of this Baytrail chip. AMD needs to come out with a slightly better binned SKU than A6-1450 with better turbo clocks. single core turbo can easily go upto 2 Ghz and quad core turbo should atleast hit 1.2 Ghz.
jljaynes - Thursday, September 5, 2013 - link
Rag - a6-1450 in Acer v5-122 uses about 4w in cinebench 11.5 and scores 1.02 - google notebookcheck a6-1450. Based on all the leaks I have seen, Bay Trail probably runs at 1.46 GHz with a turbo freq of 2.4 GHz. Look @ geekbench browser, this leak, or the antutu leaks from earlier - all are @ 1.46 GHz (except one of the earliest AnTuTu benchmarks @ 1.1 GHz)Valis - Sunday, September 8, 2013 - link
Here's a question, is the z3000-series because of their 2-4 GB RAM limit only x86, or are they x64/ia64 also?