Explore the new system architectire of Apple Silicon Macs

On 2020-07-03 9:06 p.m., Arlen Holder wrote:
UPDATE:

"When hardware needs to be replaced, it becomes a natural time to
consider alternatives. That, in turn, opens the door to the question
of upgrading -- not to a Mac, but to Windows."

o *When Apple moves Mac to Arm, is it time for Mac users to move to Windows?*
https://www.zdnet.com/article/when-apple-moves-mac-to-arm-is-it-time-for-mac-users-to-move-to-windows/

"the entire installed base of Macs will become obsolete within 2-5 years.
There will come a time, probably in 2024 or 2025, but possibly as early
as 2023, when Intel Macs will no longer get operating system updates.

At that time, owners of Intel-based Macs will face the same question
I mentioned above: Replace them with what?

As with year-by-year obsolescence, cost will be an issue. The Mac mini
I bought in 2018 was a bit over $2,000... I did price out a roughly
equivalent PC and it came to about *half the price*.

Within the next three to four years, all Mac users will have to face the
decision of whether to upgrade their hardware with new Macs,
or with non-Apple PCs."


As usual, you aren't very careful to choose sources that support your
biases:

'That pretty much sums it up. Even though the prospect of buying new,
expensive Macs is scary, the total cost of ownership is aggressively
less than Windows ownership. Beyond that, Mac users are Mac users for a
reason (or, more accurately, many individual reasons). They, like I,
will migrate to the new hardware when it becomes necessary.

For most Mac users, the move to Apple Silicon will not only be something
of a non-event given Apple's skill in architecture migrations, most of
us will simply move when it's time to buy a new Mac.'

Alan Baker wrote:
On 2020-07-03 9:06 p.m., Arlen Holder wrote:
UPDATE:

"When hardware needs to be replaced, it becomes a natural time to
consider alternatives. That, in turn, opens the door to the question
of upgrading -- not to a Mac, but to Windows."

o *When Apple moves Mac to Arm, is it time for Mac users to move to
Windows?*
https://www.zdnet.com/article/when-apple-moves-mac-to-arm-is-it-time-for-mac-users-to-move-to-windows/


"the entire installed base of Macs will become obsolete within 2-5
years.
There will come a time, probably in 2024 or 2025, but possibly as
early
as 2023, when Intel Macs will no longer get operating system updates.

At that time, owners of Intel-based Macs will face the same question
I mentioned above: Replace them with what?

As with year-by-year obsolescence, cost will be an issue. The Mac
mini
I bought in 2018 was a bit over $2,000... I did price out a roughly
equivalent PC and it came to about *half the price*.

Within the next three to four years, all Mac users will have to
face the
decision of whether to upgrade their hardware with new Macs,
or with non-Apple PCs."


As usual, you aren't very careful to choose sources that support your
biases:

'That pretty much sums it up. Even though the prospect of buying new,
expensive Macs is scary, the total cost of ownership is aggressively
less than Windows ownership. Beyond that, Mac users are Mac users for a
reason (or, more accurately, many individual reasons). They, like I,
will migrate to the new hardware when it becomes necessary.

For most Mac users, the move to Apple Silicon will not only be something
of a non-event given Apple's skill in architecture migrations, most of
us will simply move when it's time to buy a new Mac.'

In the article here, at the bottom, the commentators at the bottom
of the article, try to escape in a hype-mobile :-)

https://www.theverge.com/2020/6/23/2...peed-wwdc-2020

By having an indeterminate planning cycle, you leave the door open
to... just about anything.

The computing industry has been chock-full of vaporous goodness
in the past. I don't see a reason for that to stop. Even Intel is
riding their rocket powered "inertia machine" right now, overclocking
processors to make it seem like, um, "progress".

Maybe Apple is only making these announcements, to get free advertising ?

https://www.extremetech.com/computin...uting-monopoly

"Apple has very good reason to want the highest level
of single-threaded performance it can get."

[But that's not the plan though, is it. We know what the
plan is, and it's just as silly now as when others
announced it and failed in the past.]

"Since actual Apple hardware isn’t expected to be available soon,
I’m not going to try to speculate about how the products from
all three companies will stack up"

[Can't argue with that]

What Apple can't afford, is for the homegrown ARM project to turn into a
"PowerPC fiasco". Now, how could such a thing happen... Hmmm.

My bag of popcorn is ready.

I'm digging into the photo album for that picture
of the Exponential ECL CPU.

https://en.wikipedia.org/wiki/Exponential_Technology

Paul

On 2020-07-03 10:56 p.m., Paul wrote:
Alan Baker wrote:
On 2020-07-03 9:06 p.m., Arlen Holder wrote:
UPDATE:

Â*Â* "When hardware needs to be replaced, it becomes a natural time to
Â*Â*Â* consider alternatives. That, in turn, opens the door to the question
Â*Â*Â* of upgrading -- not to a Mac, but to Windows."

o *When Apple moves Mac to Arm, is it time for Mac users to move to
Windows?*
https://www.zdnet.com/article/when-apple-moves-mac-to-arm-is-it-time-for-mac-users-to-move-to-windows/


Â*Â* "the entire installed base of Macs will become obsolete within 2-5
years.
Â*Â*Â* There will come a time, probably in 2024 or 2025, but possibly as
early
Â*Â*Â* as 2023, when Intel Macs will no longer get operating system
updates.

Â*Â*Â* At that time, owners of Intel-based Macs will face the same question
Â*Â*Â* I mentioned above: Replace them with what?

Â*Â*Â* As with year-by-year obsolescence, cost will be an issue. The Mac
mini
Â*Â*Â* I bought in 2018 was a bit over $2,000... I did price out a roughly
Â*Â*Â* equivalent PC and it came to about *half the price*.

Â*Â*Â* Within the next three to four years, all Mac users will have to
face the
Â*Â*Â* decision of whether to upgrade their hardware with new Macs,
Â*Â*Â* or with non-Apple PCs."


As usual, you aren't very careful to choose sources that support your
biases:

'That pretty much sums it up. Even though the prospect of buying new,
expensive Macs is scary, the total cost of ownership is aggressively
less than Windows ownership. Beyond that, Mac users are Mac users for
a reason (or, more accurately, many individual reasons). They, like I,
will migrate to the new hardware when it becomes necessary.

For most Mac users, the move to Apple Silicon will not only be
something of a non-event given Apple's skill in architecture
migrations, most of us will simply move when it's time to buy a new Mac.'

In the article here, at the bottom, the commentators at the bottom
of the article, try to escape in a hype-mobile :-)

https://www.theverge.com/2020/6/23/2...peed-wwdc-2020


By having an indeterminate planning cycle, you leave the door open
to... just about anything.

The computing industry has been chock-full of vaporous goodness
in the past. I don't see a reason for that to stop. Even Intel is
riding their rocket powered "inertia machine" right now, overclocking
processors to make it seem like, um, "progress".

Maybe Apple is only making these announcements, to get free advertising ?

https://www.extremetech.com/computin...uting-monopoly


Â*Â* "Apple has very good reason to want the highest level
Â*Â*Â* of single-threaded performance it can get."

Â*Â*Â* [But that's not the plan though, is it. We know what the
Â*Â*Â*Â* plan is, and it's just as silly now as when others
Â*Â*Â*Â* announced it and failed in the past.]

Â*Â* "Since actual Apple hardware isn’t expected to be available soon,
Â*Â*Â* I’m not going to try to speculate about how the products from
Â*Â*Â* all three companies will stack up"

Â*Â*Â* [Can't argue with that]

What Apple can't afford, is for the homegrown ARM project to turn into a
"PowerPC fiasco". Now, how could such a thing happen... Hmmm.

My bag of popcorn is ready.

I'm digging into the photo album for that picture
of the Exponential ECL CPU.

https://en.wikipedia.org/wiki/Exponential_Technology

You get that Apple's homegrown chips are what they've been using in
iPhone since 2012, right?

Alan Baker wrote:
On 2020-07-03 10:56 p.m., Paul wrote:
Alan Baker wrote:
On 2020-07-03 9:06 p.m., Arlen Holder wrote:
UPDATE:

"When hardware needs to be replaced, it becomes a natural time to
consider alternatives. That, in turn, opens the door to the
question
of upgrading -- not to a Mac, but to Windows."

o *When Apple moves Mac to Arm, is it time for Mac users to move to
Windows?*
https://www.zdnet.com/article/when-apple-moves-mac-to-arm-is-it-time-for-mac-users-to-move-to-windows/


"the entire installed base of Macs will become obsolete within
2-5 years.
There will come a time, probably in 2024 or 2025, but possibly
as early
as 2023, when Intel Macs will no longer get operating system
updates.

At that time, owners of Intel-based Macs will face the same
question
I mentioned above: Replace them with what?

As with year-by-year obsolescence, cost will be an issue. The
Mac mini
I bought in 2018 was a bit over $2,000... I did price out a roughly
equivalent PC and it came to about *half the price*.

Within the next three to four years, all Mac users will have to
face the
decision of whether to upgrade their hardware with new Macs,
or with non-Apple PCs."


As usual, you aren't very careful to choose sources that support your
biases:

'That pretty much sums it up. Even though the prospect of buying new,
expensive Macs is scary, the total cost of ownership is aggressively
less than Windows ownership. Beyond that, Mac users are Mac users for
a reason (or, more accurately, many individual reasons). They, like
I, will migrate to the new hardware when it becomes necessary.

For most Mac users, the move to Apple Silicon will not only be
something of a non-event given Apple's skill in architecture
migrations, most of us will simply move when it's time to buy a new
Mac.'

In the article here, at the bottom, the commentators at the bottom
of the article, try to escape in a hype-mobile :-)

https://www.theverge.com/2020/6/23/2...peed-wwdc-2020


By having an indeterminate planning cycle, you leave the door open
to... just about anything.

The computing industry has been chock-full of vaporous goodness
in the past. I don't see a reason for that to stop. Even Intel is
riding their rocket powered "inertia machine" right now, overclocking
processors to make it seem like, um, "progress".

Maybe Apple is only making these announcements, to get free advertising ?

https://www.extremetech.com/computin...uting-monopoly


"Apple has very good reason to want the highest level
of single-threaded performance it can get."

[But that's not the plan though, is it. We know what the
plan is, and it's just as silly now as when others
announced it and failed in the past.]

"Since actual Apple hardware isn’t expected to be available soon,
I’m not going to try to speculate about how the products from
all three companies will stack up"

[Can't argue with that]

What Apple can't afford, is for the homegrown ARM project to turn into a
"PowerPC fiasco". Now, how could such a thing happen... Hmmm.

My bag of popcorn is ready.

I'm digging into the photo album for that picture
of the Exponential ECL CPU.

https://en.wikipedia.org/wiki/Exponential_Technology

You get that Apple's homegrown chips are what they've been using in
iPhone since 2012, right?

And what class are they ???

If I run SuperPI 32M on it, how many seconds does it take ???

If ARM was intended (by ARM Holdings) to be a rocket powered
car, it would already be a rocket powered car. I don't think
the ARM staff had any intention of going "head to head with Intel".

I fail to see how this can end well. Sorry.

To be successful in that business, you have to add some
value, and do it without patent overhang. And patents
are a major impediment to anyone running the gauntlet.
Is the Apple patent portfolio "Intel-proof" ?

Intel doesn't always play nice.

Now, if we assign reasonable expectations to the
outcome, what is the resulting chip worth ?

Paul

On 2020-07-04 12:49 a.m., Paul wrote:
Alan Baker wrote:
On 2020-07-03 10:56 p.m., Paul wrote:
Alan Baker wrote:
On 2020-07-03 9:06 p.m., Arlen Holder wrote:
UPDATE:

Â*Â* "When hardware needs to be replaced, it becomes a natural time to
Â*Â*Â* consider alternatives. That, in turn, opens the door to the
question
Â*Â*Â* of upgrading -- not to a Mac, but to Windows."

o *When Apple moves Mac to Arm, is it time for Mac users to move to
Windows?*
https://www.zdnet.com/article/when-apple-moves-mac-to-arm-is-it-time-for-mac-users-to-move-to-windows/


Â*Â* "the entire installed base of Macs will become obsolete within
2-5 years.
Â*Â*Â* There will come a time, probably in 2024 or 2025, but possibly
as early
Â*Â*Â* as 2023, when Intel Macs will no longer get operating system
updates.

Â*Â*Â* At that time, owners of Intel-based Macs will face the same
question
Â*Â*Â* I mentioned above: Replace them with what?

Â*Â*Â* As with year-by-year obsolescence, cost will be an issue. The
Mac mini
Â*Â*Â* I bought in 2018 was a bit over $2,000... I did price out a
roughly
Â*Â*Â* equivalent PC and it came to about *half the price*.

Â*Â*Â* Within the next three to four years, all Mac users will have to
face the
Â*Â*Â* decision of whether to upgrade their hardware with new Macs,
Â*Â*Â* or with non-Apple PCs."


As usual, you aren't very careful to choose sources that support
your biases:

'That pretty much sums it up. Even though the prospect of buying
new, expensive Macs is scary, the total cost of ownership is
aggressively less than Windows ownership. Beyond that, Mac users are
Mac users for a reason (or, more accurately, many individual
reasons). They, like I, will migrate to the new hardware when it
becomes necessary.

For most Mac users, the move to Apple Silicon will not only be
something of a non-event given Apple's skill in architecture
migrations, most of us will simply move when it's time to buy a new
Mac.'

In the article here, at the bottom, the commentators at the bottom
of the article, try to escape in a hype-mobile :-)

https://www.theverge.com/2020/6/23/2...peed-wwdc-2020


By having an indeterminate planning cycle, you leave the door open
to... just about anything.

The computing industry has been chock-full of vaporous goodness
in the past. I don't see a reason for that to stop. Even Intel is
riding their rocket powered "inertia machine" right now, overclocking
processors to make it seem like, um, "progress".

Maybe Apple is only making these announcements, to get free
advertising ?

https://www.extremetech.com/computin...uting-monopoly


Â*Â*Â* "Apple has very good reason to want the highest level
Â*Â*Â*Â* of single-threaded performance it can get."

Â*Â*Â*Â* [But that's not the plan though, is it. We know what the
Â*Â*Â*Â*Â* plan is, and it's just as silly now as when others
Â*Â*Â*Â*Â* announced it and failed in the past.]

Â*Â*Â* "Since actual Apple hardware isn’t expected to be available soon,
Â*Â*Â*Â* I’m not going to try to speculate about how the products from
Â*Â*Â*Â* all three companies will stack up"

Â*Â*Â*Â* [Can't argue with that]

What Apple can't afford, is for the homegrown ARM project to turn into a
"PowerPC fiasco". Now, how could such a thing happen... Hmmm.

My bag of popcorn is ready.

I'm digging into the photo album for that picture
of the Exponential ECL CPU.

https://en.wikipedia.org/wiki/Exponential_Technology

You get that Apple's homegrown chips are what they've been using in
iPhone since 2012, right?

And what class are they ???

Don't know.

But the benchmark scores that have been run using Intel versions of the
benchmark software aren't bad.


If I run SuperPI 32M on it, how many seconds does it take ???

If ARM was intended (by ARM Holdings) to be a rocket powered
car, it would already be a rocket powered car. I don't think
the ARM staff had any intention of going "head to head with Intel".

ARM isn't designing the chips:

Apple is.


I fail to see how this can end well. Sorry.

To be successful in that business, you have to add some
value, and do it without patent overhang. And patents
are a major impediment to anyone running the gauntlet.
Is the Apple patent portfolio "Intel-proof" ?

Intel doesn't always play nice.

Now, if we assign reasonable expectations to the
outcome, what is the resulting chip worth ?

You need to educate yourself as to what Apple has already done designing
CPUs for the ARM ISA...

In message Paul wrote:
Alan Baker wrote:
You get that Apple's homegrown chips are what they've been using in
iPhone since 2012, right?

If ARM was intended (by ARM Holdings) to be a rocket powered
car, it would already be a rocket powered car. I don't think
the ARM staff had any intention of going "head to head with Intel".

The world's faster super computer is an ARM based machine.

It is about 3 times faster than the #2 machine.

https://top500.org/
The new top system, Fugaku, turned in a High Performance Linpack (HPL)
result of 415.5 petaflops, besting the now second-place Summit system by
a factor of 2.8x. Fugaku, is powered by Fujitsu’s 48-core A64FX SoC,
becoming the first number one system on the list to be powered by ARM
processors.

--
"Master, what is the difference between a humanistic, monastic system
of belief in which wisdom is sought by means of an apparently
nonsensical system of questions and answers, and a lot of mystic
gibberish made up on the spur of the moment?" Wen considered this
for some time, and a last said: "A fish!"

On 7/4/2020 12:49 AM, Paul wrote:

snip

If ARM was intended (by ARM Holdings) to be a rocket powered
car, it would already be a rocket powered car. I don't think
the ARM staff had any intention of going "head to head with Intel".

I fail to see how this can end well. Sorry.

To be successful in that business, you have to add some
value, and do it without patent overhang. And patents
are a major impediment to anyone running the gauntlet.
Is the Apple patent portfolio "Intel-proof" ?

Intel doesn't always play nice.

Now, if we assign reasonable expectations to the
outcome, what is the resulting chip worth ?

You have to believe that Apple made some sort of a licensing and royalty
arrangement with Intel before going down this road.

It also could be that there are still going to be a couple of x86 Mac
machines manufactured, like a Xeon Mac Pro, and maybe one Core i9
Macbook Pro, for power users.

For most users Apple probably figures that the potential battery life
improvements by using a CPU with a much lower TDP, as well as the cost
savings, outweighs the loss of the subset of customers that are using
x86 applications that would suffer a significant performance hit by
requiring both virtualization and emulation.

While some OS-X x86 applications may be re-written to run natively on
the A15 (or whatever the CPU is called), some companies may just not
bother and tell their users that there will be no future OS-X releases.

In article , sms
wrote:


You have to believe that Apple made some sort of a licensing and royalty
arrangement with Intel before going down this road.

no, because intel has nothing to do with apple's chip design.

It also could be that there are still going to be a couple of x86 Mac
machines manufactured, like a Xeon Mac Pro, and maybe one Core i9
Macbook Pro, for power users.

apple stated that there are more intel macs in the pipeline, although
probably not very many, since demand for them is going to be much
lower.

For most users Apple probably figures that the potential battery life
improvements by using a CPU with a much lower TDP, as well as the cost
savings, outweighs the loss of the subset of customers that are using
x86 applications that would suffer a significant performance hit by
requiring both virtualization and emulation.

desktop macs do not have batteries and there will not be a 'significant
performance hit', especially for virtualization, which is effectively
zero.

based on existing devices using apple designed processors, it's *very*
likely that apple silicon macs running intel apps will be comparable to
or even faster than on a similar intel mac in most tasks.

this already happened once before, where 68k apps ran faster on a
powerpc mac than natively on a 68k mac.

While some OS-X x86 applications may be re-written to run natively on
the A15 (or whatever the CPU is called), some companies may just not
bother and tell their users that there will be no future OS-X releases.

an opportunity their competitors will gladly seize.

On Sat, 04 Jul 2020 11:03:02 -0400, nospam wrote:

based on existing devices using apple designed processors, it's *very*
likely that apple silicon macs running intel apps will be comparable to
or even faster than on a similar intel mac in most tasks.

*nospam proves, yet again, he's completely bamboozled by Apple MARKETING!*

Anyone using the idiotic phrase "Apple Silicon" for what is, was, and has
always been "ARM Silicon", in this case, fab'd by TSMC, is already proven
to be completely bamboozled by MARKETING bull****.

Fact is, when nospam uses that idiotic term, "Apple Silicon", it _proves_
he's bamboozled by MARKETING because it means he _believes_ the bull****.

For more details where people called it "ARM Silicon" for years, until
basically this week, when Apple MARKETING became _desperate_ for people to
NOT think of it as what it is (think "product differentiation), see this:
https://groups.google.com/d/msg/comp.sys.mac.system/ElvAtPCgr6I/5DDVwYz_AgAJ
--
People using idiotic purely MARKETING-bull**** terms like "Apple Silicon"
for what has always been called "ARM Silicon" are simply proving that they
are incapable of thinking any other way than what Apple MARKETING wants
them to believe.

https://appleinsider.com/articles/20/06/12/ten-years-of-apple-technology-shifts-made-the-arm-mac-possible
Notice in _that_ article, written prior to Apple's ridiculously desperate
attempt to have the ignorati focus NOT on the ARM technology they're
licensing, they repeatedly call it "ARM Silicon" & "ARM chips", etc.

"Apple's transition to Macs with *proprietary ARM chips* may soon be
officially acknowledged, but there have been clear and definite signs
of the switch for years."

"Laying the groundwork for *ARM Macs*"

"The actual start of the *transition to ARM Macs*"

"with the first of the *ARM-based Macs* due to potentially debut in
2021."

"Apple is already an *ARM chipmaking expert*, with A-series chips
powering the company's iPhones, iPads and Apple TVs."

"paving the way for an *ARM Mac* in general."

"Apple has laid the groundwork for *ARM Macs* for longer than a decade."

"Rumors of an *ARM Mac* are fairly recent*

"With a switch to *ARM-based CPUs*, there are opportunities for
even further integration"

"Apple made... the first publicly visible step toward an *ARM Mac*"

"Apple may not have specifically had an *ARM Mac* in mind when it
released Xcode"

"tentative signs that Apple may bring the IDE to *ARM-based chips*

"For *Apple-designed hardware like ARM chips*, it's... integral"

"although not a heralding of *ARM-based Mac* devices"

"Apple will apply the lessons... *to ARM Macs*."

"could also play a larger role in the transition to *ARM-based Macs*"

"There's a high possibility that Apple will market the *switch to ARM*
as a security upgrade"

"bake its features directly into an *ARM system-on-chip* (SoC)."

"One of the more major changes that *paved the way for ARM Macs* was
the death of 32-bit apps"

"For a transition to *ARM-based Macs, that's going to be an important
point"

"Apple has a clear goal and path in mind for the *switch to ARM*"

"the overall transition to *ARM-based Macs* isn't going to be a short
one."

"For eagle-eyed technologists and enthusiasts, it also hinted at the
potential of *Apple's first-party _ARM silicon_*."
--
Apple Silicon is a frantically desperate ploy ignoring it's ARM Silicon.

On 2020-07-04 9:08 a.m., Arlen Holder wrote:
On Sat, 04 Jul 2020 11:03:02 -0400, nospam wrote:

based on existing devices using apple designed processors, it's *very*
likely that apple silicon macs running intel apps will be comparable to
or even faster than on a similar intel mac in most tasks.

*nospam proves, yet again, he's completely bamboozled by Apple MARKETING!*

Anyone using the idiotic phrase "Apple Silicon" for what is, was, and has
always been "ARM Silicon", in this case, fab'd by TSMC, is already proven
to be completely bamboozled by MARKETING bull****.

You're an idiot.

It has now been shown over and over that Apple designs its own chips.


Fact is, when nospam uses that idiotic term, "Apple Silicon", it _proves_
he's bamboozled by MARKETING because it means he _believes_ the bull****.

For more details where people called it "ARM Silicon" for years, until
basically this week, when Apple MARKETING became _desperate_ for people to
NOT think of it as what it is (think "product differentiation), see this:
https://groups.google.com/d/msg/comp.sys.mac.system/ElvAtPCgr6I/5DDVwYz_AgAJ

On Sat, 4 Jul 2020 12:50:08 -0000 (UTC), Lewis wrote:

The world's faster super computer is an ARM based machine.
It is about 3 times faster than the #2 machine.

The Type III apologists like Lewis feel that because a super fast machine
can be created out of almost any CPU (if you have enough of them), that,
magically, it translates to Apple making a fast machine out of one of them.

It's just not logically feasible what Lewis is constantly arguing.
o It simply proves, yet again, Lewis is awed by MARKETING bull****.

The fact is that Apple has _never_ even once in its entire history ever
made a best-in-class smartphone CPU, so what makes Apple think they can
make a best-in-class PC CPU?

HINT: They likely can't. (it's all marketing bull****)
DOUBLEHINT: It's called "product differentiation").

I repeat the fact which nobody has ever refuted with actual facts!:

... *Apple has _never_ even made a best-in-class smartphone cpu* ...
So what makes Lewis think Apple can make a best-in-class PC CPU?

HINT: Nothing. It's imaginary. And lots (and lots) of MARKETING.
--
Before anyone claims Apple smartphone chips are "best in class", don't
ignore the fact that almost every single one of them is not only fatally
flawed where those compromises are unpatchable, but almost every one of
them is throttled by Apple, with Apple adding _more_ of them to throttling
in iOS 10, then more in iOS 11, then more in iOS 12, and then even more in
iOS 13, such that almost all Apple smartphone CPUs are to be throttled.

On 2020-07-04 9:24 a.m., Arlen Holder wrote:
On Sat, 4 Jul 2020 12:50:08 -0000 (UTC), Lewis wrote:

The world's faster super computer is an ARM based machine.
It is about 3 times faster than the #2 machine.
The Type III apologists like Lewis feel that because a super fast machine
can be created out of almost any CPU (if you have enough of them), that,
magically, it translates to Apple making a fast machine out of one of them.

It's just not logically feasible what Lewis is constantly arguing.
o It simply proves, yet again, Lewis is awed by MARKETING bull****.

The fact is that Apple has_never_ even once in its entire history ever
made a best-in-class smartphone CPU, so what makes Apple think they can
make a best-in-class PC CPU?

HINT: They likely can't. (it's all marketing bull****)
DOUBLEHINT: It's called "product differentiation").

I repeat the fact which nobody has ever refuted with actual facts!:

...*Apple has _never_ even made a best-in-class smartphone cpu* ...
So what makes Lewis think Apple can make a best-in-class PC CPU?

HINT: Nothing. It's imaginary. And lots (and lots) of MARKETING.
Before anyone claims Apple smartphone chips are "best in class",
don't ignore the fact that almost every single one of them is not only
fatally flawed where those compromises are unpatchable, but almost every
one of them is throttled by Apple, with Apple adding _more_ of them to
throttling in iOS 10, then more in iOS 11, then more in iOS 12, and then
even more in iOS 13, such that almost all Apple smartphone CPUs are to
be throttled.

And yet even allegedly "throttled", they outperform every other
smartphone CPU...

....and you've never explained what these alleged "fatal flaws" are.

On Sat, 04 Jul 2020 01:56:16 -0400, Paul wrote:

The computing industry has been chock-full of vaporous goodness
in the past. I don't see a reason for that to stop.

Hi Paul,

I agree with you on the "vaporous goodness" MARKETING feeds apologists.

The problem here is, what Mayayana calls "AppleSeeds", are true believers.
o They're a cult that believes in imaginary functionality by MARKETING.

They know Apple has _never_ created even a best-in-class smartphone CPU
o And yet, they believe that Apple will create a best-in-class PC CPU.

On what basis?
o Pure MARKETING bull****

There are both obvious & subtle ways they _believe_ the MARKETING bull****.
o Lewis, for example, claims that since there's a super expensive computer
that is super powerful, that uses ARM technology, then, by gawd, of
course anything that Apple makes will be powerful - especially if it's
called "Apple Silicon" (in a desperate ploy to get people like Lewis
to think it's not what it really is, which is ARM Silicon,
fab'd by TSMC).

We already proved, many many many (many) times, Apple smartphone CPUs
aren't even close to "best in class" given almost all of them have multiple
huge unpatchable holes that the apologists love to completely ignore!
(notice MARKETING ignores those holes too - apologists cue MARKETING)
o *Hackers release a new jailbreak that unlocks every iPhone*
https://groups.google.com/forum/#!topic/misc.phone.mobile.iphone/r66f4aYm5oI

There are so many unpatchable flaws in Apple smartphone CPUs, it's crazy:
o *The FBI was easily able to penetrate Apple's most secure iPhones*
https://groups.google.com/forum/#!topic/misc.phone.mobile.iphone/fe_26eulOaw

The holes in Apple CPUs has been discusssed umpteen times on the Apple
newsgroups, and yet, it's no coincidence that MARKETING doesn't speak of
the huge holes in their smartphone CPUs (and neither do the Apologists!)
o *The 'Checkm8' exploit* (kills almost all iPhone CPUs ever made!)
https://groups.google.com/forum/misc.phone.mobile.iphone/cwlXKVyQfT4

Notice these don't even cover the incessant huge holes in Apple iOS either:
o *A critical iPhone and iPad bug that lurked for 8 years*
https://groups.google.com/forum/misc.phone.mobile.iphone/P5b1Ujau6iU

It never ends for the Mac either, with the bugs galore, even in the kernel:
o *Every Apple operating system, MacOS, iOS, iPadOS, watchOS, and tvOS*
*were seriously vulnerable*
*(and Apple wasn't who found it, yet again - it never ends)*
https://groups.google.com/forum/#!topic/misc.phone.mobile.iphone/SPzqnW7L65w/

it never ends... where all these huge holes in all Apple products are
_ignored_ by MARKETING, so the apologists are completely immune to them.

Not to mention that almost all of them are throttled, one by one, to _half_
speed (so basically all benchmarks that aren't about halved, are bogus):
o *Apple throttled your iPhone by cutting its speed almost in HALF!*
https://groups.google.com/forum/#!topic/misc.phone.mobile.iphone/l79Xb6qx8Fs

What we have to agree on are the facts, which is that in _every_ iOS
release since iOS 10, Apple added more and more of the latest phones to
their throttling regimen (more in iOS 10, more still in iOS 11, even more
still in iOS 12, and even more still in iOS 13).
o *Every iPhone CPU from the iPhone 6 to iPhone 7 were throttled*
*then iPhone 8 to iPhone X were throttled*
*& now the iPhone XS, iPhone XS Max & iPhone XR get throttling software*
https://groups.google.com/forum/#!topic/misc.phone.mobile.iphone/Mzh1IvniDr8

At least now it's no longer secret (once benchmarks plummeted, which is how
they found it out in the first place), where now, the poor sad iPhone user,
if they don't keep replacing their batteries forever, are faced with the
stark unenviable choice of:
o *MANDATORY - either choose _unacceptable_ performance*
o *MANDATORY - or choose _unacceptable_ stability*
... ... ... /YOU MUST CHOOSE ONE NOW!/ ... ... ...

o nospam is a bit more logical, where he too falls for the desperate ploy
by Apple MARKETING to get him to think it's NOT ARM Silicon, but some
kind of "special" silicon, that only Apple can make (where all Apple has
to do is tweak one resistor and then they can claim they "designed" it).

We already showed proof that it has been called ARM silicon for ages, until
now, when suddenly, only now... *Apple cares what you call ARM silicon*.
https://groups.google.com/d/msg/comp.sys.mac.system/ElvAtPCgr6I/5DDVwYz_AgAJ

In summary, the logical questions to ask a

Q1: Given Apple has _never_ even made a best-in-class smartphone CPU...
What makes apologists like Lewis so confident they can make a
best-in-class PC CPU?

Q2: Given almost all Apple CPUs are throttled to about half performance,
and, given that even at peak performance, they're full of unpatchable
fatal flaws...
What makes apologists like nospam believe that they'll be best in class
PC CPUs?
--
Apologists believe anything Apple MARKETING feeds them to believe;
but Apple MARKETING doesn't tell them the truth about their product.

Lewis wrote:
In message Paul wrote:
Alan Baker wrote:
You get that Apple's homegrown chips are what they've been using in
iPhone since 2012, right?

If ARM was intended (by ARM Holdings) to be a rocket powered
car, it would already be a rocket powered car. I don't think
the ARM staff had any intention of going "head to head with Intel".

The world's faster super computer is an ARM based machine.

It is about 3 times faster than the #2 machine.

https://top500.org/
The new top system, Fugaku, turned in a High Performance Linpack (HPL)
result of 415.5 petaflops, besting the now second-place Summit system by
a factor of 2.8x. Fugaku, is powered by Fujitsu’s 48-core A64FX SoC,
becoming the first number one system on the list to be powered by ARM
processors.


FFS Lewis, will you stop with that nonsense!

TOP500 computers run parallelized "perfect scaling" applications.

There are very few things you can do on a TOP500 computer,
that have the necessary scaling properties. Not even Cinebench
would scale on there.

The majority of desktop code that matters, does not parallelize.
It's serialized.

A desktop computer needs at least one computer core that runs at "top clock".

This is why, a desktop processor that Intel made that turbos on
two cores to top clock, was such a win. It provided a core for
interrupt handling and various background activity, plus a core
that could run straight-line code at top speed. But even turboing
on one core is handy. (That's because Intel improved on the time
interval needed to change power states. It no longer takes 100us.)

Is that what ARM Holdings designed the ISA for ?
Can they turbo on one core ? To 5GHz ? And retire four
instructions per clock tick (IPC) ?

On my high-core-count machine, most of the time the
excess of cores are idle. The only time I get good usage
of the machine, is doing 7ZIP compression. Some
compression runs last for 24 hours.

Adobe Photoshop, half of the filters are parallelized,
half of the filters are single threaded. When the new
hardware comes out, a Mac enthusiast site will run PSBench
and they'll be noting how well the serialized filters
run on the new hardware. That's how the new hardware
will get its rating of "winner or loser".

Photoshop was one of the first applications to popularize
the notion of parallelism. Including the usage of
accelerator cards (card with dual DSP on it), to help
before CPUs had the cores necessary. The new hardware
though, has to prove its stuff, by making "Rotate" run faster.
("Rotate" is single threaded, and according to the article
written by Adobe long ago, it's done single threaded so
you can rotate 72 times by 5 degrees and "get back your
original photo"). There are other filters, where excess
error accumulation is not considered a problem.

If all of the code in the ecosystem could be converted
to perfect-scaling parallelized code, then this exercise
has a hope of succeeding. I've not heard of any
breakthroughs in this regard.

If I'd seen any sign that ARM is a "top clock" kind of
arch, there'd really be nothing to say. It's good on
mobile platforms. It's good at saving power. Now, we
wait for someone to make a 300W chip that runs at... ???
At a speed suitable for serialized code, able to beat
Intel on serialized.

Apple will simply try to bury the issue. And everyone
will leave the scene in a hype-mobile. As it should be.

I've got three Apple computers on the table I'm sitting at.
I've lived it. I know what it's like to run Unreal at 20FPS
and pretend I'm enjoying myself. Apple fixed that when
they moved to Intel. I would have no right to complain
about the platform today. But now what ? Well, I
guess we'll find out some day.

Paul

In article , Paul
wrote:


I've got three Apple computers on the table I'm sitting at.
I've lived it. I know what it's like to run Unreal at 20FPS
and pretend I'm enjoying myself. Apple fixed that when
they moved to Intel. I would have no right to complain
about the platform today.

what you have are 20 years old and your complaints are not relevant.

But now what ? Well, I
guess we'll find out some day.

that day will be in a few months.

it's quite obvious what's about to happen, at least to those without
blinders.