While I'm sure control and performance comes into it, I think much of the switch comes down to preserving their design aesthetic. Apple have regularly designed machines that require their components to operate in temperatures most PC users would consider insane, reaching a nadir with the appalling CPU throttling situation on the recent Macbook Pros that meant the i7 and i9 variants performed near-identically. They will absolutely, demonstrably compromise performance on desktop class machines before they compromise on aesthetic. I've always believed Apple to be a design company as much as anything else, and a low power (as in TDP) architecture will let them keep making beautiful objects without seeing $500 worth of throttling when they're stressed for 20 seconds.Tronam wrote: Thu Jun 25, 2020 8:27 pmI don’t follow this logic. In nearly every device category where they’re using their own custom A-series processors, they have consistently led the industry in both performance and power efficiency. To assume that these upcoming desktop CPUs won’t emphasize performance is inconsistent with how their silicon team has operated over the past decade. They introduced the industry’s first 64-bit smartphone processor in the iPhone 5S and have aggressively released increasingly faster SoCs every single year like clockwork, always ahead of the competition and often dramatically so. Being free of Intel’s rocky and inconsistent roadmap will allow them to ramp up Mac processors at their own pace and incorporate any custom architecture blocks they choose. Just look at how powerful the iPad Pro is at H.265 hardware encoding. This will also allow Apple to sidestep all the security vulnerabilities and zero-day exploits that have been plaguing Intel over the past 5 years.Burillo wrote: Thu Jun 25, 2020 11:43 am i don't think performance is what they're going for. their goal is control. performance has always been secondary on macs, which is perfectly illustrated by the underpowered mac pro's (underpowered for the amount of money you pay for them).
Apple Mac computers make jump to its own chips
-
- KVRAF
- 3511 posts since 27 Dec, 2002 from North East England
Last edited by cron on Fri Jun 26, 2020 1:30 am, edited 1 time in total.
-
- KVRian
- 906 posts since 25 Jan, 2014
So that's the beginning of the end of Hackintosh ? 
- KVRAF
- 4469 posts since 15 Nov, 2006 from Hell
over other ARM vendors? sure. but this is Intel/AMD we're talking about. this is a whole different ball game, because those processors have been geared towards high performance for decades. macbooks and mac minis? they'll probably be alright, since Intel has never been able to produce a low power chip that's actually worth anything, and no one cares about performance on those. mac pros or servers? those will suck.Tronam wrote: Thu Jun 25, 2020 8:27 pmI don’t follow this logic. In nearly every device category where they’re using their own custom A-series processors, they have consistently led the industry in both performance and power efficiency.Burillo wrote: Thu Jun 25, 2020 11:43 am i don't think performance is what they're going for. their goal is control. performance has always been secondary on macs, which is perfectly illustrated by the underpowered mac pro's (underpowered for the amount of money you pay for them).
the minute these chips come out, people will start poking in them, and most likely find those too. nobody's perfect. granted, no one has been hit quite as hard as Intel - but there are a handful of AMD and ARM vulnerabilities out there as well.Tronam wrote: Thu Jun 25, 2020 8:27 pm This will also allow Apple to sidestep all the security vulnerabilities and zero-day exploits that have been plaguing Intel over the past 5 years.
I don't know what to write here that won't be censored, as I can only speak in profanity.
-
Obsolete317542 Obsolete317542 https://www.kvraudio.com/forum/memberlist.php?mode=viewprofile&u=317542
- KVRist
- 253 posts since 1 Dec, 2013 from Belgium
- KVRist
- 227 posts since 16 Feb, 2010 from Germany
And what about AVX which got used in Massive X for example ?discoDSP wrote: Tue Jun 23, 2020 6:39 am New ARM chips may be more powerful but if assembly SSE x86 optimisations aren't properly translated to NEON it will result in a big performance hit. I can see a lot of work for specialised ARM coders on this switch.
-
- KVRian
- 912 posts since 18 Feb, 2004
So what internal knowledge are you basing this on? *nobody* has any idea what they've got in the pipe. Upcoming high performance chips of their own design could be one of the reasons why the new Mac Pro took so long to deliver. We have no idea on any of this.Burillo wrote: Fri Jun 26, 2020 9:43 am over other ARM vendors? sure. but this is Intel/AMD we're talking about. this is a whole different ball game, because those processors have been geared towards high performance for decades. macbooks and mac minis? they'll probably be alright, since Intel has never been able to produce a low power chip that's actually worth anything, and no one cares about performance on those. mac pros or servers? those will suck.
I can also guarantee that customers aren't going to accept poor performance MacBook Pros. Listen to The Talk Show podcast with John Gruber from this past week where he interviews the two guys from Apple. They were in no uncertain terms talking about giving people what they already get now.
-
- KVRAF
- 5648 posts since 18 Jul, 2002
AFAIK AVX provides more speed than SSE in certain scenarios. Haven't investigated how easy is porting to ARM NEON and how it compares in speed. Time will tell.ansolas wrote: Sun Jun 28, 2020 3:07 pmAnd what about AVX which got used in Massive X for example ?discoDSP wrote: Tue Jun 23, 2020 6:39 am New ARM chips may be more powerful but if assembly SSE x86 optimisations aren't properly translated to NEON it will result in a big performance hit. I can see a lot of work for specialised ARM coders on this switch.
- KVRAF
- 4469 posts since 15 Nov, 2006 from Hell
no inside knowledge, of course, but there's only so much that's possible to do without decades of experience. Apple aren't magicians, they're bound by physics and engineering constraints just like everyone else.rezoneight wrote: Sun Jun 28, 2020 3:19 pmSo what internal knowledge are you basing this on? *nobody* has any idea what they've got in the pipe.Burillo wrote: Fri Jun 26, 2020 9:43 am over other ARM vendors? sure. but this is Intel/AMD we're talking about. this is a whole different ball game, because those processors have been geared towards high performance for decades. macbooks and mac minis? they'll probably be alright, since Intel has never been able to produce a low power chip that's actually worth anything, and no one cares about performance on those. mac pros or servers? those will suck.
Apple has a reality distortion field about them where people would pay gobs of money for a machine that performance twice as slow as a comparably priced PC spec, yet "customers not accepting poor performance" were never there. iPad et al. performance also sucked for a long time, yet people bought those in droves. MacBook Air performance sucks balls still, and people still buy those in droves. MacBook Pros aren't fastest laptops around either, not by a mile and especially not for the price - yet people still buy those. Apple customers are not buying Apple stuff for performance reasons, they buy it for the ecosystem, vertical integration and (let's be honest) good looks.rezoneight wrote: Sun Jun 28, 2020 3:19 pm Upcoming high performance chips of their own design could be one of the reasons why the new Mac Pro took so long to deliver. We have no idea on any of this.
I can also guarantee that customers aren't going to accept poor performance MacBook Pros. Listen to The Talk Show podcast with John Gruber from this past week where he interviews the two guys from Apple. They were in no uncertain terms talking about giving people what they already get now.
so i fully expect that if Apple really does underdeliver with ARM MacBooks, no one among Apple customer base would care, because Apple doesn't target those people.
I don't know what to write here that won't be censored, as I can only speak in profanity.
- KVRAF
- 5394 posts since 25 Jan, 2014 from The End of The World as We Knowit
F E E D
Y O U R
F L O W
Y O U R
F L O W
-
- KVRAF
- 5444 posts since 15 Feb, 2020
MS focus is on SOFT ware, Apple focus on HARD ware. Makes sense to meMichael L wrote: Mon Jun 29, 2020 9:17 amI also agree that I don't use Macs because I need any performance enhancement, or more vertical integration. I have plenty, thank you.
I lost my heart in Cap de Creus
- KVRAF
- 5394 posts since 25 Jan, 2014 from The End of The World as We Knowit
I'm sure Bill Gates had a good reason to name it Micro soft.revvy wrote: Mon Jun 29, 2020 10:11 amMS focus is on SOFT ware, Apple focus on HARD ware. Makes sense to me
Clearly, operating system = manhood
F E E D
Y O U R
F L O W
Y O U R
F L O W
-
- KVRian
- 928 posts since 10 Jan, 2010
- KVRAF
- 4469 posts since 15 Nov, 2006 from Hell
in other words, comparing a 4 core with a 6 core, and a 6 core chip wins in a multithreaded test. the rest of this doesn't make much sense, because i'm not sure how did they manage to have a 2.6GHz core beat a 4.6GHz (turbo) core in single threaded test unless the latter was a Pentium 4 or had severe cooling issues and thus was throttled into oblivion. thermal throttling would make sense because i7 has a 1.8GHz base clock, while Apple's high performance (Lightning) core has base of 2.6GHz.chroma wrote: Mon Jun 29, 2020 2:45 pm sample:
https://gadgetversus.com/processor/inte ... 13-bionic/
I don't know what to write here that won't be censored, as I can only speak in profanity.
-
- KVRist
- 177 posts since 18 Oct, 2019
{"panic_string":"BAD MAGIC!
(flag set in iBoot panic header), no macOS panic log available"} "Apple did not respond to a request for comment."
