Server Support Company provides the most flexible and cost effective server support services that can be custom tailored to fit your company’s needs. Basically, you've tried the rest now try the best server support company.
Kiran - I think you are 100% correct. ARM has to demonstrate its viability in these classes of applications to be believed. That has to come from server specific devices and more importantly systems based on those chips entering the market. Not sure what you mean by "A11" - if you mean ARM11, then the A15 is radically different. Ability to cluster more than 4 CPUs together, much deeper pipelines to support processor frequencies in the 2.5GHz etc, new on-chip interconnect bus etc.
A chinese company, Nufront, announced today a dual core Cortex-A9 device running at 2GHz. Marvell has discussed a quadcore device addressing similar frequencies being available this year, so the frequencies are starting to get interesting for a range of non-mobile applications. And getting past the 4GB physical address memory limitation which the A15 does, I would argue, further increases the applicability of ARM.
ARM's approach to enter into the high performance computing market like servers and networking equipment is not really aggressive. Cortex A15 doesn't really look anything different from their current highly used processor architectures such as A9 and A11. Anyways there will be a huge demand for the low power and high performance processors in the server segment since companies could save huge money. We need to wait and see few successful designs with A15 powered processors to know more details.
Weatherhead - you are absolutely correct. Cortex-A15 is a 32-bit processor. Server workloads tend to be quite different by application. Just like SeaMicro, a start-up OEM in the Bay Area, who is pursuing certain server applications with Atom, ARM and its partners see an opportunity to address applications that need modest processing performance. Of course, we are new to the space. You have every right to be skeptical until you see proof. That's what me and my team are working on every day.
I'm assuming from recent context that this is still a 32-bit processor (being a member of the ARMv7 Cortex family) with 40-bit physical addressing (i.e. 1 TB). How can it possibly complete in the "server space" like everyone is implying without a true 64-bit architecture? If this is v7 with physical addressing extensions you are still going to be running 32-bit processes. May be viable for a supercharged smart phone but I don't see it being competitive against existing Intel offerings in the server or even laptop space as those are all capable of running full 64-bit applications and operating systems as far as I know. Now if they extend the instruction set architecture to full 64 bit addressing and integer performance in like a "Cortex" ARMv8 architecture that would be something to talk about. It is interesting though that one of the advantages of ARMv7 is the ability to mix 16-bit ARM thumb 2 opcodes and full 32-bit ARM opcodes, how does that translate to a true 64-bit processor?
Disclosure: I work for ARM
Just to add to Gary's comment above
1) Due to the volumes and cost sensitivity of the phone market, a company will absolutely not use a processor that is over functional for the design. We still have companies licensing ARM11 for this space to address the needs of less functional handsets
2) Even once Cortex-A15 based silicon becomes available, there is quite a period time that elapses before handsets based on the devices are purchasable
3) These transitions take a long period of time. To illustrate, for 1Q2010, Cortex shipments represented 6% of the total ARM shipments. We absolutely expect the performance driven end of phone- and indeed other applications to transition over to the Cortex-A15, but it will take a long period of time
We have been hearing about ARM going into the HPC market for years now, but nothing has materialised yet. ARM is being very conservative for understandable reasons, but I wish them well in the high end uprocessor market segment as we need more competition there.
Three ARM licencees made presentations centered on mobile application of the A15. See the article.
The A15 provides more processing power than the A8/A9, which you will need to get into higher-end applications. The A8 and A9 are in presently shipping devices, while A15 designs probably won't appear until next spring, if not next summer.
For these types of applications, Marvell typically design their own ARM compatible CPUs. Server workloads vary quite substantially from application to application. Some with modest CPU performance requirements...Others that absolutely demand the maximum available CPU processing power available. A range of ARM Powered devices will appear; some Cortex-A9 based, some Cortex-A15 based, etc
Something missing in this picture?. If A15 is less than twice the area of A9, and 5 times performance, why would this not get into all cell phone, even running at half the speed of A9.
ARM is in troube...they have to make sure Apple, Qualcomm, Marvell, Broadcom Samsung, TI suceed with A9/A8 combo, yet need to introduce A15.
Intel always give true claims, however the x86 architecture is screwed up, the claims are never wrong......
A Book For All Reasons Bernard Cole1 Comment Robert Oshana's recent book "Software Engineering for Embedded Systems (Newnes/Elsevier)," written and edited with Mark Kraeling, is a 'book for all reasons.' At almost 1,200 pages, it ...