Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.sys.mac.system > #133073 > unrolled thread

First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon")

Back to article view | Back to comp.sys.mac.system

Contents

  First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Arlen Holder <arlenholder@newmachine.com> - 2020-06-30 04:42 +0000
    Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Arlen Holder <arlenholder@newmachine.com> - 2020-06-30 04:50 +0000
      Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Arlen Holder <arlenholder@newmachine.com> - 2020-06-30 05:02 +0000
    Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Alan Baker <notonyourlife@no.no.no.no> - 2020-06-30 00:38 -0700
    Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") joe <none@domain.invalid> - 2020-06-30 08:07 -0500
      Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") nospam <nospam@nospam.invalid> - 2020-06-30 09:42 -0400
        Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") joe <none@domain.invalid> - 2020-06-30 09:39 -0500
        Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Arlen Holder <arlenholder@newmachine.com> - 2020-06-30 17:16 +0000
        Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Lewis <g.kreme@gmail.com.dontsendmecopies> - 2020-06-30 18:08 +0000
          Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") nospam <nospam@nospam.invalid> - 2020-06-30 14:26 -0400
            Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Alan Baker <notonyourlife@no.no.no.no> - 2020-06-30 12:25 -0700
              Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Lewis <g.kreme@gmail.com.dontsendmecopies> - 2020-06-30 22:38 +0000
            Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Arlen Holder <arlenholder@newmachine.com> - 2020-06-30 23:58 +0000
      Re: First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon") Arlen Holder <arlenholder@newmachine.com> - 2020-06-30 16:56 +0000

#133073 — First leaked reputed benchmarks for Apple ARM (aka what MARKETING is desperate for you to term "Apple Silicon")

All verbatim (since Apologists _hate_ all facts about Apple products):

  "The _top_ score for Apple's new silicon at the time of this writing 
   is 844 for single-core and 2958 for multi-core, whereas a 4th-gen 
   iPad Pro scored 1118 for single-core and 4726 for multi-core."

o *A Wild Apple ARM Benchmark Appears*
<https://gizmodo.com/a-wild-apple-arm-benchmark-appears-1844204355>

  "Beyond the iPad, the closest thing we have to compare to the alleged 
   dev kits at the moment are Intel cores... from mid-2020 MacBook Pro. 
   According Geekbench 5, one of the highest single-core scores is 1244,
   and one of the highest multi-core scores is 4526. That Intel core is
   running 400 MHz less per core than the Apple ARM dev kits, and has the 
   same number of cores, yet its performance is leaps and bounds ahead."

More details in the article... 
-- 
Apple is all MARKETING & the lowest R&D % spend in the tech industry.

[toc] | [next] | [standalone]

#133076

UPDATE (verbatim since Apologists hate facts about Apple products).

  "the Apple silicon-equipped developer kits average 811 for 
   single-threaded Geekbench and 2781 for multi-threaded. 
   *That's about 20 percent slower than the entry-level i3-1000ng4* 
   powered Macbook Air's single-core results"

o *Developers leak benchmarks from the Apple silicon Mac transition kit*
<https://arstechnica.com/gadgets/2020/06/developers-leak-benchmarks-from-the-apple-silicon-mac-transition-kit/>
  
  "These tell us what emulation of legacy apps might look like on Apple 
   silicon Macs"

More details in the cited article... 
-- 
Never forget that Apple is all MARKETING & at the same time, Apple has the
absolute lowest R&D % spend in the entire high-tech industry, bar none.

[toc] | [prev] | [next] | [standalone]

#133078

UPDATED... (all verbatim since Apologists love to dispute facts)...

  "The machines seem to be achieving around *800* on the Geekbench v5 
   single core test, and around *2600* on multi-core.

   For comparison, the entry-level $999 2020 MacBook Air achieves a
   Geekbench score of *1005* on single core and *~2000* on multi-core.

o *First benchmarks surface for Apple's ARM-based Developer Transition Kit*
<https://9to5mac.com/2020/06/29/first-benchmarks-surface-for-apples-arm-based-developer-transition-kit/>

  "Developers estimate the performance penalty could be around 25-40%."

Plenty more details in the cited article.
-- 
Ever wonder why Apple MARKETING is so high & yet Apple R&D is so very low?

[toc] | [prev] | [next] | [standalone]

#133080

On 2020-06-29 9:42 p.m., Arlen Holder wrote:
> All verbatim (since Apologists _hate_ all facts about Apple products):
> 
>    "The _top_ score for Apple's new silicon at the time of this writing
>     is 844 for single-core and 2958 for multi-core, whereas a 4th-gen
>     iPad Pro scored 1118 for single-core and 4726 for multi-core."
> 
> o *A Wild Apple ARM Benchmark Appears*
> <https://gizmodo.com/a-wild-apple-arm-benchmark-appears-1844204355>
> 
>    "Beyond the iPad, the closest thing we have to compare to the alleged
>     dev kits at the moment are Intel cores... from mid-2020 MacBook Pro.
>     According Geekbench 5, one of the highest single-core scores is 1244,
>     and one of the highest multi-core scores is 4526. That Intel core is
>     running 400 MHz less per core than the Apple ARM dev kits, and has the
>     same number of cores, yet its performance is leaps and bounds ahead."
> 
> More details in the article...
> 

Wow. You have discovered the AMAZING fact that non-native software will 
be slower than native software.

[toc] | [prev] | [next] | [standalone]

#133081

On 6/29/2020 11:42 PM, Arlen Holder wrote:
> All verbatim (since Apologists _hate_ all facts about Apple products):
> 
>    "The _top_ score for Apple's new silicon at the time of this writing
>     is 844 for single-core and 2958 for multi-core, whereas a 4th-gen
>     iPad Pro scored 1118 for single-core and 4726 for multi-core."
> 
> o *A Wild Apple ARM Benchmark Appears*
> <https://gizmodo.com/a-wild-apple-arm-benchmark-appears-1844204355>
> 
>    "Beyond the iPad, the closest thing we have to compare to the alleged
>     dev kits at the moment are Intel cores... from mid-2020 MacBook Pro.
>     According Geekbench 5, one of the highest single-core scores is 1244,
>     and one of the highest multi-core scores is 4526. That Intel core is
>     running 400 MHz less per core than the Apple ARM dev kits, and has the
>     same number of cores, yet its performance is leaps and bounds ahead."
> 
> More details in the article...
> 

Breaking News:

AH points out that a low cost development platform is slower than a 
computer that costs 4 times as much.

AH has failed to show any performance claims for the transition kits 
that this data refutes.

AH ignores the fact that the A12z used in the transition kit is 2 years 
old and not the A14 that will be in Apple Silicon based Macs..

AH neglects to point out the slower results were obtained using x86 
tests translated to run on ARM; not native ARM code.

So, while he does post some 'facts', he makes no valid point.

The linked article uses "supposedly", "rumors ", and "If true,". It also 
indicates "Future Apple ARM processors are supposed to be souped-up 
versions of the A12Z, allegedly 12-cores with eight 
performance-dedicated cores". Given that, I fail to see how this article 
can provide a meaningful view of what to expect for the product to be 
released at the end of the year.

[toc] | [prev] | [next] | [standalone]

#133083

In article <rdfdev$m6h$1@gioia.aioe.org>, joe <none@domain.invalid>
wrote:

> AH ignores the fact that the A12z used in the transition kit is 2 years 
> old and not the A14 that will be in Apple Silicon based Macs..

the a14 will not be used in apple silicon macs.

the a* series were designed for mobile devices, namely iphone and ipad.

what will go into apple silicon macs will be an entirely new chip
category, optimized for laptop/desktop use which have very different
design constraints.

[toc] | [prev] | [next] | [standalone]

#133084

On 6/30/2020 8:42 AM, nospam wrote:
> In article <rdfdev$m6h$1@gioia.aioe.org>, joe <none@domain.invalid>
> wrote:
> 
>> AH ignores the fact that the A12z used in the transition kit is 2 years
>> old and not the A14 that will be in Apple Silicon based Macs..
> 
> the a14 will not be used in apple silicon macs.
> 
> the a* series were designed for mobile devices, namely iphone and ipad.
> 
> what will go into apple silicon macs will be an entirely new chip
> category, optimized for laptop/desktop use which have very different
> design constraints.
> 
Thanks for the info.

[toc] | [prev] | [next] | [standalone]

#133088

On Tue, 30 Jun 2020 09:42:32 -0400, nospam wrote:

> what will go into apple silicon macs will be an entirely new chip
> category, optimized for laptop/desktop use which have very different
> design constraints.

Hi nospam,

  "The eight results found and uploaded on June 20 are all listed as having
   VirtualApple 2,400MHz (4 cores) as the processor, referencing the *A12Z*
   being used inside the DTK. A full breakdown of the results indicates the
   device uses "macOS 11.0" as its operating system, and has 16 gigabytes
   of memory."

I'm not bamboozled by bullshit MARKETING like you apologists are,
where it's clear Apple is _desperate_ to distance itself from what it 
actually is.

Each time you use that idiotic MARKETING term, "Apple Silicon", I'll simply 
point out what it really is, which is NOT Apple Silicon - it's licensed ARM 
technology - which Apple is desperate to distance itself from.

Moving forward, here's what Apple Insider had to say about speed:
o *First Apple Silicon Developer Transition Kit benchmarks show Rosetta performance impact*
<https://appleinsider.com/articles/20/06/29/first-apple-silicon-developer-transition-kit-benchmarks-show-rosetta-performance-impact>

 "In terms of performance, the single-core tests resulted in a range of 
  between 736 and 844 points and an average of *811*. For multi-core 
  benchmarks, the range is from 2,582 to 2,962, with an average score of
  2,781.

  These results are considerably lower than the *1,118* single-core and
  4,625 multi-core benchmarks of the 12.9-inch iPad Pro which also uses
  the A12Z Bionic"

More details in the article cited.
-- 
There's good reason Apple is desperate to distance itself from what it is.

[toc] | [prev] | [next] | [standalone]

#133092

In message <300620200942326341%nospam@nospam.invalid> nospam <nospam@nospam.invalid> wrote:
> In article <rdfdev$m6h$1@gioia.aioe.org>, joe <none@domain.invalid>
> wrote:

>> AH ignores the fact that the A12z used in the transition kit is 2 years 
>> old and not the A14 that will be in Apple Silicon based Macs..

> the a14 will not be used in apple silicon macs.

Almost certainly so, but we do not know at all what the chips in the new
Macs will be.

> the a* series were designed for mobile devices, namely iphone and ipad.

It will almost certainly have more cores than the A12Z

> what will go into apple silicon macs will be an entirely new chip
> category, optimized for laptop/desktop use which have very different
> design constraints.

That would be my guess, yes.

The "benchmarks" on the DTK are entirely meaningless. The DTK is not a
product.

-- 
What if there were no hypothetical questions?

[toc] | [prev] | [next] | [standalone]

#133096

In article <slrnrfmvsr.1t4r.g.kreme@ProMini.lan>, Lewis
<g.kreme@gmail.com.dontsendmecopies> wrote:

> >> AH ignores the fact that the A12z used in the transition kit is 2 years 
> >> old and not the A14 that will be in Apple Silicon based Macs..
> 
> > the a14 will not be used in apple silicon macs.
> 
> Almost certainly so, but we do not know at all what the chips in the new
> Macs will be.

nor do we know what the a14 will be.

however, we do know that the macs won't be using an a* series.

> > the a* series were designed for mobile devices, namely iphone and ipad.
> 
> It will almost certainly have more cores than the A12Z

yep, given that a phone has very tight power, thermal and size
constraints, whereas a laptop and desktop do not. 

> > what will go into apple silicon macs will be an entirely new chip
> > category, optimized for laptop/desktop use which have very different
> > design constraints.
> 
> That would be my guess, yes.

not just a guess, but it's been confirmed.

> The "benchmarks" on the DTK are entirely meaningless. The DTK is not a
> product.

not entirely meaningless.

it's a lower bound which the actual products will greatly surpass.

[toc] | [prev] | [next] | [standalone]

#133098

On 2020-06-30 11:26 a.m., nospam wrote:
> In article <slrnrfmvsr.1t4r.g.kreme@ProMini.lan>, Lewis
> <g.kreme@gmail.com.dontsendmecopies> wrote:
> 
>>>> AH ignores the fact that the A12z used in the transition kit is 2 years
>>>> old and not the A14 that will be in Apple Silicon based Macs..
>>
>>> the a14 will not be used in apple silicon macs.
>>
>> Almost certainly so, but we do not know at all what the chips in the new
>> Macs will be.
> 
> nor do we know what the a14 will be.
> 
> however, we do know that the macs won't be using an a* series.
> 
>>> the a* series were designed for mobile devices, namely iphone and ipad.
>>
>> It will almost certainly have more cores than the A12Z
> 
> yep, given that a phone has very tight power, thermal and size
> constraints, whereas a laptop and desktop do not.
> 
>>> what will go into apple silicon macs will be an entirely new chip
>>> category, optimized for laptop/desktop use which have very different
>>> design constraints.
>>
>> That would be my guess, yes.
> 
> not just a guess, but it's been confirmed.
> 
>> The "benchmarks" on the DTK are entirely meaningless. The DTK is not a
>> product.
> 
> not entirely meaningless.
> 
> it's a lower bound which the actual products will greatly surpass.
> 

And as AppleInsider points out, the benchmarks are pretty good when 
compared to existing Mac Minis.

'In terms of performance, the Geekbench 5 benchmark lists the Core i3 at 
949 for single-core tests and 3,197 for multi-core, and the Core i7 at 
1,205 and 6,024 for single and multi-core scores respectively. 
Benchmarks for the A12Z Bionic in the iPad Pro put it at 1,118 points 
for single-core tests, and 4,625 for multi-core, again putting it 
between the two extremes of the Mac mini's processors.'

<https://appleinsider.com/articles/20/06/23/compared-apples-developer-transition-kit-versus-mac-mini>

And as they also point out, that's how the A12Z scores when it is 
constrained by thermal limits in a tablet enclosure with no fan.

[toc] | [prev] | [next] | [standalone]

#133104

In message <rdg3js$oq2$1@dont-email.me> Alan Baker <notonyourlife@no.no.no.no> wrote:
> And as they also point out, that's how the A12Z scores when it is 
> constrained by thermal limits in a tablet enclosure with no fan.

And the A12Z is to years old.

-- 
I leave symbols to the symbol-minded - George Carlin

[toc] | [prev] | [next] | [standalone]

#133105

On Tue, 30 Jun 2020 14:26:40 -0400, nospam wrote:

> it's a lower bound which the actual products will greatly surpass.

Hi nospam,

That's an understatement, in that it had better not be worse.

As you know, nospam, I treat you differently than the other types:
o Type I apologist = knows the truth like Bill Clinton didn't inhale
o Type II apologist = not malicious but filters out fact so is ignorant
o Type III apologist = actually _believes_ the strange things they claim

In general, you often claim the opposite of what you know to be the truth,
but you always have extreme faith in Apple, no matter what Apple does.

Knowing that, I would expect nothing less than supreme faith in Apple, 
such as when you apologists claimed, oh, about a year or so ago that...
o "Apple wasn't worried" (about 5G)

Which told me, instantly, that I needed to delve deeper...
o Where, as you know by now, Apple was literally _desperate_ for 5G...

Such that, only months later, Apple surrendered billions to Qualcomm
o In one of the most expensive abject surrenders in corporate history

Which, as you're aware, you'll pay for in that Kuo tells us Apple is
attempting to recoup those horrendously huge payments to Qualcomm from its
customers by not supplying basic accessories in the 2020 iPhone 12 box.

It's a testament to you, if I actually believed a word you said, that you
are so very, um, shall we say, _confident_ that Apple will, for the first
time in its entire history, create a decent chip that isn't full of
non-patchable holes and that doesn't need to be throttled to half speed
just so the system is stable.

For example, these Axx scores need to be about halved to be realistic:
o <https://browser.geekbench.com/ios-benchmarks>

Of course, the new ARM-based chip will be a PC chip, and not a smartphone
chip, which you recognize is vastly different in terms of complexity &
power delivery.

But the good news, so far anyway, is that the speed is "only" 10 percent to
about 30 percent slower, which, at this stage of the game, let's hope, is
the bottom rung (time will tell):
  "Here, we see only about a 10.7% performance deficit in multi-core and
   about 28.6% in single-core. This implies that Apple's A12Z under
   emulation is not too far away from a mainstream MacBook Air"
  <https://www.notebookcheck.net/First-A12Z-Bionic-DTK-Geekbench-5-benchmarks-show-Apple-s-transition-holds-immense-promise-only-a-28-in-drop-seen-in-single-core-score-compared-to-the-MacBook-Air-2020.477595.0.html>
-- 
Apple is disingenuous for people to associate Mac ARM as "Apple Silicon".

[toc] | [prev] | [next] | [standalone]

#133086

On Tue, 30 Jun 2020 08:07:42 -0500, joe wrote:

> So, while he does post some 'facts', he makes no valid point.

Hi "joe",

I realize you're a well-known troll, so I'll speak in simple sentences.
o Is your point simply that you hate all actual facts about Apple?

1. I simply posted basic facts as reported in the news (verbatim).
2. You don't appear to ever _like_ facts about Apple products (even these).

What else is your point, "joe" (other than you hate all facts about Apple)?
-- 
Apple apologists believe only in what MARKETING cleverly feeds them.

[toc] | [prev] | [standalone]

Back to top | Article view | comp.sys.mac.system

csiph-web