Bookmark and Share


Specifications of the first wave of next-generation Intel Atom system-on-chips for various “Bay Trail” platforms have been published in China. As expected, the new products will cut down power consumption of chips for low-cost/low-power notebooks. Many of the consumer-oriented Bay Trail products will be marketed under Pentium and Celeron brands. Finally, in addition to tablets, notebooks and desktops, the new SoCs will also target industrial applications.

As previously announced, various versions of desktop-oriented Celeron and Pentium processors with four or two cores will feature high clock-speeds, high-performance graphics engine as well as 10W thermal design power (TDP). By contrast, Pentium and Celeron chips for low-cost/low-power notebooks and convertibles will offer different levels of performance and will have 4.5W – 7.5W thermal design power; some of such products will even support 2.5W scenario design power. Finally, there will be Atom-branded system-on-chips for industrial applications with one to four cores and 5W – 10W TDP.

The new Intel Atom, Celeron and Pentium processors for desktops, mobile and industrial applications based on Silvermont micro-architecture are expected to be formally introduced later this year.

Silvermont: Next-Generation Microarchitecture

Silvermont will serve as the foundation for a breadth of 22nm products expected in market later this year. The performance-per-watt improvements with the new microarchitecture will enable a significant difference in performance and responsiveness for the compute devices built around these products. Intel's Silvermont microarchitecture was designed and co-optimized with Intel's 22nm SoC process with tri-gate transistors. By taking advantage of this industry-leading technology, Intel is able to provide a significant performance increase and improved energy efficiency.

Highlights of the Silvermont microarchitecture include:

  • A new out-of-order execution engine enables best-in-class, single-threaded performance.
  • A new multi-core and system fabric architecture scalable up to eight cores and enabling greater performance for higher bandwidth, lower latency and more efficient out-of-order support for a more balanced and responsive system.
  • New IA instructions and technologies bringing enhanced performance, virtualization and security management capabilities to support a wide range of products. These instructions build on Intel's existing support for 64-bit and the breadth of the IA software installed base.
  • Enhanced power management capabilities including a new intelligent burst technology, low- power C states and a wider dynamic range of operation taking advantage of Intel's 3D transistors. Intel Burst technology 2.0 support for single- and multi-core offers great responsiveness scaled for power efficiency. 

Tags: Intel, Bay Trail, ValleyView, 22nm, Silvermont, Atom


Comments currently: 6
Discussion started: 07/05/13 08:23:01 AM
Latest comment: 07/09/13 02:08:00 PM
Expand all threads | Collapse all threads


looks pretty nice, good jump from current atoms performance level, it is going to give very hard competition to AMD jaguar but time will see what these atome will do against AMD's groundbreaking GCN architechure and HSA....
currently intel has the biggest advantages i.e. 22nm 3D trinsistor while AMD is still on 28nm 2D so surely intel have lead in TDP segment, but this not means intel won...coz-

1.when it comes to gpu intel is on knees in front of AMD GCN, jaguar already showed 1080P torchlite gaming on windows8 pro tablet which is completly impossible for intel atom upcoming SoC.
2.AMD is jaguar is very cost effective product while upcoming atom is not going to cheap coz costlier process.
3.pure x86 is becoming obsolete, this is world of openCL,CUDA,HSA and intel is all about pure x86.
4. AMD already said jaguar+ will come in early 2014, actually AMD is very serious about jaguar and with GCN its complete package.
5.AMD HSA is gaining momentum ,,this is really red signal for intel's monopoly.
3 3 [Posted by: mudi1  | Date: 07/05/13 08:23:01 AM]
- collapse thread

Jeez, stop sucking AMD's dick. I have nothing against AMD but seriously, you sound fucking stupid when you post comments like this.
4 2 [Posted by: dinosore  | Date: 07/05/13 02:40:27 PM]
look frnd i m not a fanboy i also uses intel cpu's but nowadays i found amd is making practical things with opencl like new photoshop etc. while intel is not showing unified design i want to say intel should make it fast before too late
0 2 [Posted by: mudi1  | Date: 07/05/13 05:50:27 PM]
1) Intel already demonstrated Torchlight 2 running at 1080P on Bay Trail!

AMD GPU will likely still be better overall but GCN is not a magical performance technology...

Actual Performance is still in the low range with even the Quad Core Temash barely rating much better than a HD3000 for graphical performance and anything less the HD4000 is below entry level gaming graphics!

2) AMD has yet to show its pricing go to where it can compete with ARM SoCs, which is where Intel ATOM SoC pricing goes in order to compete in the mobile market!

3) No, pure x86 isn't becoming obsolete. Just because AMD can't make it compete in the mobile space doesn't mean Intel can't. Besides, the latest leaked AnTuTu benchmark for Bay Trail T indicates it's 30% better than Qualcomm's Snapdragon 800 and that isn't even the most powerful version of Bay Trail they were testing!

4) If Jaguar+ is anything like Brazos 2.0 was then it will be really minor update... we'll have to wait and see but given AMD's track record it is unlikely to really impress.

5) HSA is mainly software... to take advantage of their APU but besides ARM there isn't any momentum yet to making it a industry standard, which it needs to become in order to have any real effect. Otherwise it'll become just another curiosity like Nvidia's CUDA!

AMD won't even really push it until Kaveri comes out anyway and support for discrete graphic cards won't be added till well into next year anyway... So it's not even finalized and perfected yet!
3 1 [Posted by: James Alan Diaz  | Date: 07/05/13 04:42:53 PM]
look frnd i m not a fanboy i also uses intel cpu's but nowadays i found amd is making practical things with opencl like new photoshop etc. while intel is not showing unified design i want to say intel should make it fast before too late

and for ur objections one by one -

1. both jaguar and atom are low power designs PLZ don't compare them to notebook or PC version chips.

2.when pricing yes it will be nice to see.

3.if u r thinking pure x86 dominates then i don't want to waste my time arguing with u, just use windows 8,internet explorer,large office tools with GPU acceleration on and off. do this on ur own.

4.Jaguar+ have many rumors from considerable modifications to 20nm node but they r rumors.

5.if u think HSA is just software than how can i explain, its like hitting my head in wall but ok i want to try - if HSA is just software use that or similar tool to unify intel ivybridge core and HD 4000 igp is it possible-NO,unify AMD phenomII core and HD 4870 is it possible-NO,,,, look frnd HSA is not just software bundle in very short understand like this- HSA is like intel Hyper-Threading which is actually a software to enable HT enabled intel core cpu's if u have cor2quad HT software will not work it requires specified design

And u said AMD GCN is not magical this sentence proves that u know nothing about architecture,, take this in very short-
1.GCN is actually running in huge bottleneck. HD 7970 requires atleast 1.5TB/sec. of bandwidth to unleash its full performance but it have 260-270GB/sec.,,do u know that.while intel's tiny igp is designed for 40-50GB/sec.(Iris-Pro is different)

2.GCN(launched in 2012) supports unified memory same as nvidia maxwell(sheduled in 2014-15) this a joke?

3. HD 7970 has 3,789 GFLOPS,,GTX 680 has 3,090 GFLOPS while GTX 680 came 2-3 months after hd 7970....

4.with TressFX on HD7970 gives 60+ FPS in tomb raider and GTX 680 gives 26-29FPS............why? both supports TressFX ..this is the secret.

5.and biggest secret of GCN is it architechure is capable to do something we not imagined before 2012 for a gpu,, everyone said that's impossible GCN made that possible,, but i dont disclose that ,its a research work.
2 2 [Posted by: mudi1  | Date: 07/05/13 06:06:33 PM]
someones working hard for a paycheck on this horribly pro-amd pro-stupid site ...
0 0 [Posted by: amdzorz  | Date: 07/09/13 02:08:00 PM]


Add your Comment

Related news

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture