Sidebar Sidebar
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.

Apple's A14 Chip Rumored to Become First Arm-Based Mobile Processor to Exceed 3GHz

still wont get me to buy a ARM based MacBook Pro or Mac Pro
I'm not guessing , I am quit certain AMD thread ripper chips doing graphics work and 3D animation will still be the choice for Hollywood and all the Pro Studios running on Windows 10. It already is. Most studios have gotten rid of Macs in favor of high end Windows workstations
And to Ask the studios to buy ARM based Macs and pay for all those software upgrades in the economic fallout we have going on today, NO WAY.
 
  • Like
Reactions: Val-kyrie and etios
Freeangel1 said:
still wont get me to buy a ARM based MacBook Pro or Mac Pro
I'm not guessing , I am quit certain AMD thread ripper chips doing graphics work and 3D animation will still be the choice for Hollywood and all the Pro Studios running on Windows 10. It already is. Most studios have gotten rid of Macs in favor of high end Windows workstations
And to Ask the studios to buy ARM based Macs and pay for all those software upgrades in the economic fallout we have going on today, NO WAY.
Click to expand...

Agreed. That's one of the reasons ARM-Based MBP is not going to bode well.
 
acconda81 said:
Why would I need so much power on an IPhone? So I can open Facebook 0.05 seconds faster ?
Click to expand...
VR and AR, and processing ever more advanced photo algorithms/ adjustments faster are the two use cases that spring immediately to mind.
 
Kal-037 said:
Meh... Unless they start talking about A14X for a new iPad coming (that will have greater power due to 3Ghz+)... I say meh. 😂😉
Click to expand...

It makes sense to increase the speed with newer A14X so Apple can introduce a 15” iPad Pro start at just $1099
[automerge]1584353543[/automerge]
Falhófnir said:
VR and AR, and processing ever more advanced photo algorithms/ adjustments faster are the two use cases that spring immediately to mind.
Click to expand...

Agreed. The A14X prowess will be suitable for Apple iGlass running AR-Alternate Reality Applications.
 
Last edited:
If those benchmarks are true, ( Look at the current top of the line Single Core Benchmarks in the link below ). I want an Apple ARM MacBook NOW.


[automerge]1584356569[/automerge]
CarlJ said:
I'm sorta wondering when Apple starts building their own lightweight high-performance low-power ARM-based servers for their server farms. They could literally make one that works exactly how they want. And be increasingly less beholden to Azure/Amazon for services.
Click to expand...

Well the recent lawsuit with Nuvia suggest they aren't interested in the Server Market. And wants to focus on the consumer market.
 
citysnaps said:
Nothing wrong with that if it keeps your phone healthy and reliable.
Click to expand...

Healthy, reliable and SLOW. There is a problem when a new product is throttling after only 6-12 months of use.


Woochoo said:
There's a video of an iPad Pro 2018 exporting a video faster than in a MBP 15" 2018, both on same quality. The only downside there was the OS and file management that was unefficient but since you are actually critisizing the comment of the fellow talking about an ARM in a Mac (hence a desktop OS to do those tasks) my point stands still. If that was already happening in an iPad with a reduced thermal envelope and battery compared to a laptop, now imagine a MBP without those limitations and a chip specially designed for higher TDP and performance. Yes, Macs will eventually carry ARM and by the time it happens when they see the performance people will stop laughing at that
Click to expand...

I would say that downside is a huge issue for a primary OS. Good hardware without good software is not worth the expense.

The loss of x86 compatibility may very well mark Apple’s regression into irrelevance for general computing, like it was during the PPC era.
 
Val-kyrie said:
The loss of x86 compatibility may very well mark Apple’s regression into irrelevance for general computing, like it was during the PPC era.
Click to expand...

Not so sure about that. x86 is already much relevant for "general computing" than it was before ARM became popular. It's also possible Apple will be smart about when to make a full changeover re: becoming instantly "irrelevant". I dont think anyone is expecting their "Pro" machines to go ARM only by 2021 or something.
 
DNichter said:
Very impressive. It’s only a matter of time for Intel. Looking forward to iPadOS updates in the fall.
Click to expand...
Intel as a company not so much, they could well start making Arm CPUs alongside x86 ones for the thin and light Windows/ Chromebook market. I think that could well be the beginning of the end for x86 (over a very long timescale) though.
 
Val-kyrie said:
The loss of x86 compatibility may very well mark Apple’s regression into irrelevance for general computing, like it was during the PPC era.
Click to expand...

Said this 6 months ago I would have agree in some form. But Amazon is moving most of their AWS to ARM. This is the start of ARM on Server. It is only a matter of time before ARM repeat what x86 did in the 90s, taking over the Server market.

I just thought Mac Pro introduction was a little unfortunate if Apple is moving to ARM Mac as soon as this year.
 
  • Like
Reactions: Val-kyrie
Val-kyrie said:
Healthy, reliable and SLOW. There is a problem when a new product is throttling after only 6-12 months of use.
Click to expand...

it depends on what that new product (in this case a mobile phone) is doing and how it is used.

You may not understand good system engineering and product hardware design is about managing a set of goals, requirements, and engineering trades that often conflict with each other. A simple example of that, just off the top my head at 5:30am in the morning, would be desired product size/volume vs. battery size vs. battery capacity and charge life vs. desired processor performance vs. the ability to efficiently and safely remove generated heat vs. cost. There is no free lunch.

My 3 year old iPhone X is not slow. On the other hand my expectations are reasonable for a mobile device that easily fits in my pocket and works reliably. I'm not trying to compute pi to 3 trillion digits, or trying to image process 100 MB RAW files with multiple layers, mine bit-coin, or render a Pixar-level animation. I suspect my phone usage is similar to the bulk of the users who purchase roughly 200+ million phones a year (around 600,000 phones a day, on the average).

The good news is, if you find Apple's iPhone performance "SLOW," there are a ton of other choices out there to consider and choose from. Simply find one that meets your requirements and reward that manufacturer with your currency.

For me...Apple's iPhones hit the sweet spot managing all of the conflicting engineering trades, for what I want in a phone and how it is used.
 
  • Like
Reactions: mech986, ericwn, PickUrPoison and 1 other person
Falhófnir said:
Intel as a company not so much, they could well start making Arm CPUs alongside x86 ones for the thin and light Windows/ Chromebook market. I think that could well be the beginning of the end for x86 (over a very long timescale) though.
Click to expand...

Yes, they obviously have a future as a company, but not necessarily with Apple. Maybe Apple continues to use them on the high end, but I think the writing is on the wall.
 
chucker23n1 said:
I wouldn't put too much faith into this report.



The writing sounds like that of a giddy teenage boy.



Geekbench doesn't actually know the frequency on unreleased iOS devices, though. It takes reasonably guesses.



Sounds good. The highest recorded Intel chip is 1412, so this would be a 17% lead compared to that. Which isn't entirely impossible, but given the limited thermal headroom of the Apple chip, seems fairly optimistic.
[automerge]1584345397[/automerge]


Maybe if Swift actually got its concurrency story going…
Click to expand...
Concurrency works ok now through dispatch queues. These proposals are nice to make it easier, but not necessary to take full advantage of all those cores.
 
CarlJ said:
I'm sorta wondering when Apple starts building their own lightweight high-performance low-power ARM-based servers for their server farms. They could literally make one that works exactly how they want. And be increasingly less beholden to Azure/Amazon for services.
Click to expand...

Apple uses Azure/Amazon because they've done the math and its more economical than building & maintaining more of their own server farms and easier to scale to meet demand. Apple make their own hardware to sell as part of a MacOS/iOS/Services package - and there's no market for a Mac server (beyond a handful of XServe nostalgics) because there's no advantage to using MacOS on a server (a major selling point of the XServe was low licensing costs c.f. Windows Server, NetWare etc. which all charged per-user licenses - Linux and the rise of web-related server tech killed that).

Not that ARM servers don't make sense - and most server-side software doesn't care about what CPU it is running on - but Amazon and others are already looking at ARM servers, and is further down that road than Apple - if Apple want ARM-bases servers they can just hire them.

mistasopz said:
Apple sacrifices performance for thinness and aesthetics, so getting hyped for >3GHz capabilities is pointless because they are going to be running far less than that (even if you run something that needs it).
Click to expand...

ARM can deliver more performance (whether it's more GHz or more cores) for the same power consumption/heat output as Intel. Put an Intel chip in an iPhone with a tiny, passive cooling system and try and run it at full turbo boost and it will overheat and throttle far sooner. Put an A-series chip in a MBP, that has fans and much better cooling, and it will be in thermal heaven and run for far longer at full boost than a comparable Intel chip.

Now, Apple get to decide where to strike the balance by designing faster A-series chips for the MBP or designing ever-thinner MBPs to put them in. We'll see which way they go - but the 16" MBP looks like something of a back-track from the "thinner is better" ethos so, maybe, they've got their fingers burned (literally) and have learnt the lesson.

Val-kyrie said:
The loss of x86 compatibility may very well mark Apple’s regression into irrelevance for general computing, like it was during the PPC era.
Click to expand...

Let's fix that for you:
The loss of x86 Windows compatibility may very well mark Apple’s regression into irrelevance for general computing be an inconvenience to some users, like it was not during the PPC era.
Click to expand...

Jobs had already turned the Mac around with the iMac, OS X and the iPod "halo effect" long before the Intel switch. Interoperability was improving with the demise of things like Netware and proprietary email systems in favour of more open standards. Heck, Macs were now running industry standard Unix!

The switch happened because Motorola/IBM were too slow coming through with the new chips that Apple needed (...a successor to the G5 for the PowerMac, a mobile G5 for the PowerBook) whereas Intel had just done a major U-turn in dropping the power-guzzling Pentium 4 space heater in favour of the new, relatively low-power Core chips.... and, boy, did the Interwebs think that the switch to Intel was gouing to be the end of the Mac...

Let's run through that again: existing CPU maker not delivering the chips Apple needed on time, rival CPU maker offering a new, low-power alternative... sound familiar?

Except, this time, the rival CPU maker isn't a "maker" but licenses designs on a pick'n'mix basis and Apple already have experience of using this to make their own bespoke systems-on-a-chip...

Not that the ability to virtualise or dual-boot x86 operating systems wasn't an advantage that undoubtedly helped shift Macs, but it wasn't the master plan - with Bootcamp only added after hackers showed it was possible and virtualisation a third-party option that showed up a year or so after the switch...

Thing is, if by (say) 2022 when it becomes a real issue, the Mac market is still reliant on the ability to run Windows (...and its perfectly feasible that running ARM Windows, which in turn can run x86-32 apps under emulation will be possible) then, frankly, MacOS is irrelevant for general computing.
 
  • Like
Reactions: gnomeisland and Lazy
WoodpeckerBaby said:
First, I hate the Geekbench 5 scale... like mixing F with C.

Second, my main concern is RAM. iPhone 8 has 2GB of RAM, now that larger and more performant apps can benefit from increased RAM now. Limiting it hinders performance and causes unnecessary paging and cache miss.

I hope Apple can remove the concept of RAM altogether. Replacing RAM with enhanced L3 and distributed L4 cache on the chip, that is, on the processor die, inside A-series SoC. This can drastically improve battery life, memory throughput and bus delay. This will also be cheaper as it shrinks the PCB, eliminates RAM supplier premium, and it increases the die size, but that is actually a good thing because as CPU-cores become more performant, clocks higher, and contain more cores, thermal limit (TDP) kicks-in a lot faster. If we increase the die size (less thermal density for better colling action), while shrinking the lithography (7nm->5nm, consume less power, smaller size), we would end up with a lot of unused silicon real estate, which is a waste of space, lowers yield (as bigger die means more likely to get a dust particle, fewer chips per silicon wafers/disks), and massively increases material cost. But if you think about it, RAM is also silicon, specifically, they are just MOSFET logic gates, built on exactly the same material as the CPU die. If we use the extra space and scatter L3 and L4 cache on the processor die among the compute cores, that can not only shorten the memory bus length, and therefore, delay, but also equalize the thermal distribution in the processor die. RAM is nowhere as hot as the cores and each cache block can be run at variable clock frequency based on load and they don't have to match the clock speed of the cores they work with, which saves power dynamically. This is not possible on external RAM modules even if they are soldered on the PCB.
Click to expand...
You can never get enough memory on the die. And the bigger the memory, the slower it is (because the address lines get bigger, etc). And you don’t necessarily want to make the ram from the same process as the cpu. To get sufficient density you want DRAM, and processes for DRAM are optimized quite differently than processes for logic and SRAM.
 
  • Like
Reactions: Lazy
firewood said:
Maybe. But you can put your iPhone on top of a high airflow fan if you want or need the sustained performance.

I’ve actually done that when doing extended testing and benchmarking of a prototype of a math intensive iPhone app. Made the test numbers a bit more consistent.
Click to expand...
Bingo! That’s it! Combo fan and wireless charger.
 
You must log in or register to reply here.
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.
Top Bottom
Back