I thought another benefit to 64-bit was the opportunity to eliminate 32-bit-only cruft, further streamlining iOS when 32-bit apps were officially dropped in iOS11.
Apple is like a marathon runner trying to establish a new world record- they are racing to achieve a personal goal that they have set for themselves. The fact that there are other competitors in the race is incidental.
If Apple was only racing to beat the competition they could get by with only being marginally better than their closest rivals.
Competition is good, but for companies (and people) who are focused on excellence rather than simply winning, competition isn’t a good enough benchmark to get you where you need to be.
Let the Samsung’s and tech pundits of the world focus on the excitement of what they perceive as a race, which is in reality a breathless quest to see who’s going to finish in second place.
Very typically, an article from DED about SoCs, becomes a rant about Samsung. A rant that has nothing to do with the purported subject of the article.
This article is not just about the SOC's, but more about how the entire industry was ill-prepared to compete with what Apple suddenly threw out there, being so caught off-guard, that iKnockoffs like Samsung would put out lies about Apple's 64-bit announcement.
It's a valid article. DED hits it on all points.
The article’s title, if you read it, is very specifically about the A7 vs other chips in the industry. Most of the article doesn’t even deal with that other than in a very brief an simplistic way. The rest is his usual rant about Samsung, and some others.
yes, I know that there are people here who only want to read goody articles about Apple, and so whatever he writes is going to get a thumbs up, and that AI likes this because it generates, both positive and negative comments beyond what an objective article will generate. But that doesn’t mean that I, and some others don’t understand what’s happening, even if you, and some others don’t.
The headline doesn't say what industry, but the article elaborates that it's the mobile computing industry. Who else is making CPUs in that industry? Qualcomm (mentioned), Samsung (mentioned) and ... ?
So, Samsung _has_ to be in the article because it's a CPU competitor. To provide context, other aspects of Samsung's business (and business practices) were mentioned. Same for Nvidia, but oddly not for Qualcomm. I suppose two out of three ain't bad?
I think your characterisation of the article being "his usual rant about Samsung" is a little off-target. Providing facts about mobile CPUs isn't a rant, reminding people of facts about a corporation's behaviour isn't a rant, and revealing a roadmap (that may be obvious in hindsight) isn't a rant. I also think there is very little basis for claiming that the article veers away from the premise in the headline, since the author (as usual) explains not just what happened but what the implications are - opinionated, yes, but hardly grounds for your claim.
As Mr. Dilger has pointed out on numerous occasions there is indeed a coordinated campaign by tech bloggers and competitors to spread FUD about Apple, its software, and its hardware. This continues, in part, because of Apple’s legendary secrecy and its reluctance to respond to the fake news published about it. We should have noticed by now that the spec monkeys have receded into the woodwork from whence they came because the superiority of Apple’s A chips is now indisputable.
Some of this is indeed Apple’s fault. Despite Schiller’s talents in marketing, the top management team, from Jobs onwards, has been very poor at laying out Apple’s philosophy. So the main difference people read about, and this includes from writers in the industry, is that Android is “open” and that iOS is “closed”. even though Apple has, from time to time, given some explanations their as to how, and why they do what they do, there has never been a complete, coherent statement from them as to why they do what they do overall. Their explanations tend to get lost in the noise. They really have needed to just come out and say exactly what they do as compared to their competition.
so as for that open vs closed debate that techies argue over, but which the general public not only doesn’t care about, but isn’t even aware of, it has its basis in the beginnings of how Apple and Google needed (note that word, needed) to enter the cell industry.
apple was turned down by Verizon, because Jobs was so secretive that Verizon didn’t trust that Apple had a product they could sell. Jobs went to AT&T, which was number two, and struggling, and made a deal there. As we know, the iphone became a big hit. But was limited to AT&T for, I think it was, three years. Apple I know, was working on an App Store from the beginning, though it didn’t come out with it the first year, a very good marketing ploy. When it did, the second year, it has almost 14 million users starved for apps, which was a large number of smartphone users at the time, and the store became an instant success.
but in order to not have problems with AT&T and other providers later, given that Apple curated the store from the beginning, they had to walk a fine line in what apps they allowed. So they didn’t allow apps that broke contractural obligations. One of the big ones back then was the fight over hot spots. Cell providers were charging a fairly high fee for that, and of course, a lot of people wanted the service, but didn’t want to pay for it. Apple didn’t allow apps that went around people’s contracts, which angered a bunch of people.
when Android came out, and I’m not going into the whole thing about that now. I’ve done that a few times already. Google didn’t curate the store at all. This was a strategy to get as many apps as fast as possible in the store in order to catch up with the App Store. A quirk in the law regarding corporate responsibility in publishing which these stores do, is that if you oversee the store, and have some responsibility in determining what goes in, and what doesn’t, you are liable for anything that breaks the laws in any way, and can be sued by copyright holders, or anyone whose services something in the store is working around. There are laws about theft of services.
apple would be caught in that, so they didn’t allow anything that violated their rules about illegal activity, either civil or criminal, into the App Store. Google, claiming loudly that they didn’t look at anything in the store and that they therefor weren’t responsible for it, had lots of, let’s say, questionable apps.. People were downloading apps to get free hotspots, for example.
out of this, Apple was said to be closed, and Android, open. The other reason was that in it’s eagerness to get Android quickly adopted, they allowed skinning, which Apple doesn’t. They also allowed side loading of apps from other stores. That these things bypass security and usability didn’t seem to bother Android users, and along with being able, in some cases to even buy, and load software ROMs to bypass Google’s work, gained Android a great reputation in the pirate community, and a bad one for Apple.
Even after Google needed to curate because of huge amounts of malware (99% of mobile malware is on the Android platform), and hot spots became free, they maintained their rep. Somehow, every Android problem was pushed to the various OEMs building the phones instead of Google itself, while Apple is just Apple.
anyway, now I’ve ranted enough.
Some of your points are legitimate, this one ("FUD about Apple's performance is Apple's fault") is not. What I've seen is a consistent unwillingness to accept reality among people who don't want to accept reality, regardless of what Apple does. An especially obvious version of this is with regard to performance. We got people saying that Apple's performance wasn't that great. Then when GB numbers made that untenable it was "well the SPEC performance will suck". When that became untenable I've now seen plenty of twits say with a straight face that SPEC is purely a marketing benchmark with zero real world relevance.
A different version of this has to do with the relationship between IPC, frequency, and performance. To me it seems absolutely obvious that Apple understood, the day they began their designs, that everything about the future (power, smaller but not faster transistors, wire delays starting to dominate transistor delays, 2.5D and then 3D) leaned towards chip designs that prioritized wide and smart over frequency. But if you don't want to believe this, you won't, regardless of what Apple does or doesn't say. If your entire self image is built on the idea that Intel (or maybe AMD) is king, and their kingship is justified by their frequency, you're not interested in arguments for why this is a losing proposition going forward. Has nothing to do with what Apple does or doesn't say publicly (let alone weird side tangents like App Store policies).
Apple is like a marathon runner trying to establish a new world record- they are racing to achieve a personal goal that they have set for themselves. The fact that there are other competitors in the race is incidental.
If Apple was only racing to beat the competition they could get by with only being marginally better than their closest rivals.
Competition is good, but for companies (and people) who are focused on excellence rather than simply winning, competition isn’t a good enough benchmark to get you where you need to be.
Let the Samsung’s and tech pundits of the world focus on the excitement of what they perceive as a race, which is in reality a breathless quest to see who’s going to finish in second place.
This is, I think, a more perceptive comment than most realize. I've frequently talked about the difference between Technical and Financial companies. Technical companies don't fear the future, don't fear change, because they are confident that they can make and direct change, that whatever comes next will be to their benefit. Finance companies are terrified of change because all they feel confident in is the ability to keep doing what they're doing today.
Few companies, even those nominally in "Tech" are Technical companies, companies that aren't scared of change, scared of disrupting themselves. nVidia kinda sorta. AMD right now. Intel back in its glory days, from about the 386 to about Sandy Bridge. When engineers at Apple propose "OK, for the A15 our goal is another 25% performance improvement, and we figure let's add SVE2 to extend our wide vectors to integer support", management is saying "Right on! Make it so!". When engineers at Intel propose "OK, 7nm is so dense, how about we put AVX512 and 4 cores everywhere", immediately the discussion turns into "well how will that affect our Xeon sales? And what if it reduces the prices we can charge for mid-range? How about you cripple the AVX512 support by making the scatter gather really slow? Or how about we give them lots of cores, which sounds good in the ads, but we don't give them enough DRAM controllers to actually run all those cores optimally?"
And so it goes. The Apple engineers (at least for now, who knows how long it will last) have carte blanche to make the best product they can, year after year. The Intel engineers are not allowed to do ANYTHING that might make a product at level n of the 29 step marketing segmentation an acceptable, cheaper, replacement for level n+1.
An especially obvious version of this is with regard to performance. We got people saying that Apple's performance wasn't that great. Then when GB numbers made that untenable it was "well the SPEC performance will suck". When that became untenable I've now seen plenty of twits say with a straight face that SPEC is purely a marketing benchmark with zero real world relevance.
A different version of this has to do with the relationship between IPC, frequency, and performance. To me it seems absolutely obvious that Apple understood, the day they began their designs, that everything about the future (power, smaller but not faster transistors, wire delays starting to dominate transistor delays, 2.5D and then 3D) leaned towards chip designs that prioritized wide and smart over frequency.
Heh, one of my favorite troll, reactionary, thoughtless, stupid anti-Apple ARM comments is that you can’t compare benchmarks that run on different CPU architectures. Your mind is just sitting there, frozen and flabbergasted, thinking about whether you want to go into a discussion over how computers work, where you actually have to go back to the beginning to describe why 1+1=2 is true whether you ask in English or Swahili. For all intents and purposes, when you read a comment like that, you are talking to a person who think what happens inside computers is magic.
That will give you the A6X article and you can work backwards or follow links in there. If you like technical details, the A4 article is probably the best. Unfortunately after that one they degenerate more and more into complaining about Samsung, with fewer and fewer previously unpublished details about the actual chips.
Very typically, an article from DED about SoCs, becomes a rant about Samsung. A rant that has nothing to do with the purported subject of the article.
This article is not just about the SOC's, but more about how the entire industry was ill-prepared to compete with what Apple suddenly threw out there, being so caught off-guard, that iKnockoffs like Samsung would put out lies about Apple's 64-bit announcement.
It's a valid article. DED hits it on all points.
The article’s title, if you read it, is very specifically about the A7 vs other chips in the industry. Most of the article doesn’t even deal with that other than in a very brief an simplistic way. The rest is his usual rant about Samsung, and some others.
yes, I know that there are people here who only want to read goody articles about Apple, and so whatever he writes is going to get a thumbs up, and that AI likes this because it generates, both positive and negative comments beyond what an objective article will generate. But that doesn’t mean that I, and some others don’t understand what’s happening, even if you, and some others don’t.
That’s just a lot of wordy opinion. Many of us agree with DED’s observations on what Apple does, what the industry does, and what tech writers do.
One person even built/builds these chips and confirmed this article in post #11. So, thanks for your opinion, but...
Very typically, an article from DED about SoCs, becomes a rant about Samsung. A rant that has nothing to do with the purported subject of the article.
This article is not just about the SOC's, but more about how the entire industry was ill-prepared to compete with what Apple suddenly threw out there, being so caught off-guard, that iKnockoffs like Samsung would put out lies about Apple's 64-bit announcement.
It's a valid article. DED hits it on all points.
The article’s title, if you read it, is very specifically about the A7 vs other chips in the industry. Most of the article doesn’t even deal with that other than in a very brief an simplistic way. The rest is his usual rant about Samsung, and some others.
yes, I know that there are people here who only want to read goody articles about Apple, and so whatever he writes is going to get a thumbs up, and that AI likes this because it generates, both positive and negative comments beyond what an objective article will generate. But that doesn’t mean that I, and some others don’t understand what’s happening, even if you, and some others don’t.
The headline doesn't say what industry, but the article elaborates that it's the mobile computing industry. Who else is making CPUs in that industry? Qualcomm (mentioned), Samsung (mentioned) and ... ?
So, Samsung _has_ to be in the article because it's a CPU competitor. To provide context, other aspects of Samsung's business (and business practices) were mentioned. Same for Nvidia, but oddly not for Qualcomm. I suppose two out of three ain't bad?
I think your characterisation of the article being "his usual rant about Samsung" is a little off-target. Providing facts about mobile CPUs isn't a rant, reminding people of facts about a corporation's behaviour isn't a rant, and revealing a roadmap (that may be obvious in hindsight) isn't a rant. I also think there is very little basis for claiming that the article veers away from the premise in the headline, since the author (as usual) explains not just what happened but what the implications are - opinionated, yes, but hardly grounds for your claim.
Well, just to be fair, Mediatek, Rockchip, Allwinner and Huawei are also all making mobile chips. (But, honestly, only Huawei is making chips that can even pretend to be in flagship class.) And nVidia, with Denver was, as mentioned, still considered a serious possibility for quite a few years after the A7 shipped.
At this time, of course, Intel was still peddling the fantasy that it was going to be a contender in mobile, so DED could/should probably have included them in his list of Apple competitor wannabe's.
Mel, I think you mischaracterize the article: the one I just read covered the exact subject line quite well IMO.
Then again, as an Apple watcher since the 70s, I find Daniel’s articles to be clear, plainly factual, and very well-written. They also accord very (*very*) closely with my own recollections, personal knowledge and experiences in the industry during the periods in question.
Very typically, an article from DED about SoCs, becomes a rant about Samsung. A rant that has nothing to do with the purported subject of the article.
This article is not just about the SOC's, but more about how the entire industry was ill-prepared to compete with what Apple suddenly threw out there, being so caught off-guard, that iKnockoffs like Samsung would put out lies about Apple's 64-bit announcement.
It's a valid article. DED hits it on all points.
The article’s title, if you read it, is very specifically about the A7 vs other chips in the industry. Most of the article doesn’t even deal with that other than in a very brief an simplistic way. The rest is his usual rant about Samsung, and some others.
yes, I know that there are people here who only want to read goody articles about Apple, and so whatever he writes is going to get a thumbs up, and that AI likes this because it generates, both positive and negative comments beyond what an objective article will generate. But that doesn’t mean that I, and some others don’t understand what’s happening, even if you, and some others don’t.
Tell us what’s happening, Mel. Because in your longer previous comment you mentioned that Apple was at fault for misperceptions, that the company needed to better elucidate its strategies. But that’s a slippery slope. In the same comment you suggested that most consumers don’t know or care, and so it could only be for the techies and (here’s the important bit) Apple’s COMPETITION that you’re suggesting that elucidation would be of value. Now why on Earth would Apple wish to provide its competition more insight and detail on its future plans. The company has, in fact, stated that not doing so is exactly a major reason for its secrecy. Obviously Apple has weighed the benefits it might gain from opening its roadmap to its own developer community against providing that same reveal to competitors and has decided in favor of more secrecy than some would prefer, with all the attendant bashing and naysaying that comes with that stance. Are you suggesting you’ve done the same evaluation and you feel you’re conclusion on the matter, which seems to differ from Apple’s, is more appropriate than the company’s stated position?
Apple is like a marathon runner trying to establish a new world record- they are racing to achieve a personal goal that they have set for themselves. The fact that there are other competitors in the race is incidental.
If Apple was only racing to beat the competition they could get by with only being marginally better than their closest rivals.
Competition is good, but for companies (and people) who are focused on excellence rather than simply winning, competition isn’t a good enough benchmark to get you where you need to be.
Let the Samsung’s and tech pundits of the world focus on the excitement of what they perceive as a race, which is in reality a breathless quest to see who’s going to finish in second place.
To extend the analogy, it’s like a multi-day race where participants need to stop at the end of each leg to sleep and recharge. On some legs the competition does better, by getting an earlier start, making themselves look good all the way through that leg, but then they’ve exhausted themselves and are incapable of sustaining throughout the long haul. Something about a turtle and a bunny springs to mind.
i love apple's gimmicks that EVERYONE joins in the next or second iteration of their devices. funny how these gimmicks actually do a lot to save space, increase speed, and power management.
Journalist and bloggers were right, 64 bit per se isn’t an advantage. They just had the transition to 64 bit of desktops which was promoted by computer companies as ‘huge’ while it turned out to be used largely as marketing to sell more computers with no subsequent speed gain to speak of and lots of incompatible software that had to be bought again.
This time journalist thought they knew there stuff and spotted another marketing campaign promoting 64bit for embedded.
The point is that ARM 32 bit and 64 bit are completely different processors using a different instruction set. So thats the difference.
Apple did this before with Intel processors, when used in 64 bit mode (intel keeps its 32 bit stuf lingering around) the processors can be seen as completely different from 32 bit, exhibiting different register sets and instructions with much more efficient context switching.
While reading this I was thinking about all the people I know who at the time were invested in Android (usually Scamsung) who insisted they did not like Apple stuff and would never buy an iPhone, iPad or a Mac.
Most of them have a variety of Apple devices and the switch happened downstream of what is detailed here. The choices they made in thei period allowed Apple to pull away from Samsung/Android in the minds of the ordinary Joe/Jane.
While reading this I was thinking about all the people I know who at the time were invested in Android (usually Scamsung) who insisted they did not like Apple stuff and would never buy an iPhone, iPad or a Mac.
Most of them have a variety of Apple devices and the switch happened downstream of what is detailed here. The choices they made in thei period allowed Apple to pull away from Samsung/Android in the minds of the ordinary Joe/Jane.
Similar recollection here as well. Almost every single person I knew who sweared back then to not buy/own an iPhone or iPad or MacBook have now all swing back (happened around 6 or 6s). Even the one who bitches the most about how Fup iPhone is or Apple ID, is still sticking to iPhone (and upgrading every year) after all these years of bitching. The last I know is she owns iPhone XS Max, not sure if she upgraded to 11 Pro Mad this year or not.
As Mr. Dilger has pointed out on numerous occasions there is indeed a coordinated campaign by tech bloggers and competitors to spread FUD about Apple, its software, and its hardware. This continues, in part, because of Apple’s legendary secrecy and its reluctance to respond to the fake news published about it. We should have noticed by now that the spec monkeys have receded into the woodwork from whence they came because the superiority of Apple’s A chips is now indisputable.
Some of this is indeed Apple’s fault. Despite Schiller’s talents in marketing, the top management team, from Jobs onwards, has been very poor at laying out Apple’s philosophy. So the main difference people read about, and this includes from writers in the industry, is that Android is “open” and that iOS is “closed”. even though Apple has, from time to time, given some explanations their as to how, and why they do what they do, there has never been a complete, coherent statement from them as to why they do what they do overall. Their explanations tend to get lost in the noise. They really have needed to just come out and say exactly what they do as compared to their competition.
so as for that open vs closed debate that techies argue over, but which the general public not only doesn’t care about, but isn’t even aware of, it has its basis in the beginnings of how Apple and Google needed (note that word, needed) to enter the cell industry.
apple was turned down by Verizon, because Jobs was so secretive that Verizon didn’t trust that Apple had a product they could sell. Jobs went to AT&T, which was number two, and struggling, and made a deal there. As we know, the iphone became a big hit. But was limited to AT&T for, I think it was, three years. Apple I know, was working on an App Store from the beginning, though it didn’t come out with it the first year, a very good marketing ploy. When it did, the second year, it has almost 14 million users starved for apps, which was a large number of smartphone users at the time, and the store became an instant success.
but in order to not have problems with AT&T and other providers later, given that Apple curated the store from the beginning, they had to walk a fine line in what apps they allowed. So they didn’t allow apps that broke contractural obligations. One of the big ones back then was the fight over hot spots. Cell providers were charging a fairly high fee for that, and of course, a lot of people wanted the service, but didn’t want to pay for it. Apple didn’t allow apps that went around people’s contracts, which angered a bunch of people.
when Android came out, and I’m not going into the whole thing about that now. I’ve done that a few times already. Google didn’t curate the store at all. This was a strategy to get as many apps as fast as possible in the store in order to catch up with the App Store. A quirk in the law regarding corporate responsibility in publishing which these stores do, is that if you oversee the store, and have some responsibility in determining what goes in, and what doesn’t, you are liable for anything that breaks the laws in any way, and can be sued by copyright holders, or anyone whose services something in the store is working around. There are laws about theft of services.
apple would be caught in that, so they didn’t allow anything that violated their rules about illegal activity, either civil or criminal, into the App Store. Google, claiming loudly that they didn’t look at anything in the store and that they therefor weren’t responsible for it, had lots of, let’s say, questionable apps.. People were downloading apps to get free hotspots, for example.
out of this, Apple was said to be closed, and Android, open. The other reason was that in it’s eagerness to get Android quickly adopted, they allowed skinning, which Apple doesn’t. They also allowed side loading of apps from other stores. That these things bypass security and usability didn’t seem to bother Android users, and along with being able, in some cases to even buy, and load software ROMs to bypass Google’s work, gained Android a great reputation in the pirate community, and a bad one for Apple.
Even after Google needed to curate because of huge amounts of malware (99% of mobile malware is on the Android platform), and hot spots became free, they maintained their rep. Somehow, every Android problem was pushed to the various OEMs building the phones instead of Google itself, while Apple is just Apple.
anyway, now I’ve ranted enough.
Some of your points are legitimate, this one ("FUD about Apple's performance is Apple's fault") is not. What I've seen is a consistent unwillingness to accept reality among people who don't want to accept reality, regardless of what Apple does. An especially obvious version of this is with regard to performance. We got people saying that Apple's performance wasn't that great. Then when GB numbers made that untenable it was "well the SPEC performance will suck". When that became untenable I've now seen plenty of twits say with a straight face that SPEC is purely a marketing benchmark with zero real world relevance.
A different version of this has to do with the relationship between IPC, frequency, and performance. To me it seems absolutely obvious that Apple understood, the day they began their designs, that everything about the future (power, smaller but not faster transistors, wire delays starting to dominate transistor delays, 2.5D and then 3D) leaned towards chip designs that prioritized wide and smart over frequency. But if you don't want to believe this, you won't, regardless of what Apple does or doesn't say. If your entire self image is built on the idea that Intel (or maybe AMD) is king, and their kingship is justified by their frequency, you're not interested in arguments for why this is a losing proposition going forward. Has nothing to do with what Apple does or doesn't say publicly (let alone weird side tangents like App Store policies).
A lot of Apple’s public image is a direct result of what Apple does and says. For example, Apple has the highest rating of any major company when it involved being green. Apple does the work, but also touts it at every opportunity. Everyone knows that Apple is very serious about it. They also tout privacy heavily. But they don’t really talk about why they’re more “closed” than Android. They pretty much leave that alone. So the public hears the argument (those who care) from the other side. And we should all know that when an argument is one sided, the side that presents their case wins amongst those who care, and write about it. Apple may not want to get involved about that aspect, but it’s been leaving them with a bad reputation in that area. It’s something that Apple could help to fix, but they don’t.
now, you’re talking about SoC performance. I didn’t say there’s FUD about Apple’s performance. I don’t know how you misunderstood that. I was talking about the other areas of Apple’s reputation, not SoC performance. Pretty much everyone knows that Apple’s SoCs are well ahead. Writers know that as well. So we get the grading on a curve sort of thing. There and acknowledgement that in talking about Android SoCs, the tests that can include iOS will, and they’ll show how much ahead Apple is, often without having to say so. Read the Anandtech reviews. The new Huawei Mate 30 Pro is there now. Not a very good phone overall, except for some photography, which for many areas turns out to be pretty good. Though I never pay much attention to the photography part of a review unless it done by a pro photographer or videographer.
so we have the new Kirin 990, which is their state of the art SoC, with a modem built-in. If we take Apple’s chips out of the equation, this is a really good SoC. The best Android SoC so far. Pretty good, right? But it’s not only way behind the current A13, it’s pretty far behind last years A12, and barely coming to the year before’s A11. So, in reality, this is a terrible SoC. But reviewers can’t just come out and say that. So they say that this is the best new SoC out for Android phones, which is true. But at points in the review, mention that Apple’s SoC just wipes out the competition. But Android makers can't get Apple’s’, so it doesn’t matter.
Comments
Thanks! This is great stuff!
So, Samsung _has_ to be in the article because it's a CPU competitor. To provide context, other aspects of Samsung's business (and business practices) were mentioned. Same for Nvidia, but oddly not for Qualcomm. I suppose two out of three ain't bad?
I think your characterisation of the article being "his usual rant about Samsung" is a little off-target. Providing facts about mobile CPUs isn't a rant, reminding people of facts about a corporation's behaviour isn't a rant, and revealing a roadmap (that may be obvious in hindsight) isn't a rant. I also think there is very little basis for claiming that the article veers away from the premise in the headline, since the author (as usual) explains not just what happened but what the implications are - opinionated, yes, but hardly grounds for your claim.
An especially obvious version of this is with regard to performance. We got people saying that Apple's performance wasn't that great. Then when GB numbers made that untenable it was "well the SPEC performance will suck". When that became untenable I've now seen plenty of twits say with a straight face that SPEC is purely a marketing benchmark with zero real world relevance.
A different version of this has to do with the relationship between IPC, frequency, and performance. To me it seems absolutely obvious that Apple understood, the day they began their designs, that everything about the future (power, smaller but not faster transistors, wire delays starting to dominate transistor delays, 2.5D and then 3D) leaned towards chip designs that prioritized wide and smart over frequency. But if you don't want to believe this, you won't, regardless of what Apple does or doesn't say. If your entire self image is built on the idea that Intel (or maybe AMD) is king, and their kingship is justified by their frequency, you're not interested in arguments for why this is a losing proposition going forward.
Has nothing to do with what Apple does or doesn't say publicly (let alone weird side tangents like App Store policies).
I've frequently talked about the difference between Technical and Financial companies. Technical companies don't fear the future, don't fear change, because they are confident that they can make and direct change, that whatever comes next will be to their benefit. Finance companies are terrified of change because all they feel confident in is the ability to keep doing what they're doing today.
Few companies, even those nominally in "Tech" are Technical companies, companies that aren't scared of change, scared of disrupting themselves. nVidia kinda sorta. AMD right now. Intel back in its glory days, from about the 386 to about Sandy Bridge.
When engineers at Apple propose "OK, for the A15 our goal is another 25% performance improvement, and we figure let's add SVE2 to extend our wide vectors to integer support", management is saying "Right on! Make it so!".
When engineers at Intel propose "OK, 7nm is so dense, how about we put AVX512 and 4 cores everywhere", immediately the discussion turns into "well how will that affect our Xeon sales? And what if it reduces the prices we can charge for mid-range? How about you cripple the AVX512 support by making the scatter gather really slow? Or how about we give them lots of cores, which sounds good in the ads, but we don't give them enough DRAM controllers to actually run all those cores optimally?"
And so it goes. The Apple engineers (at least for now, who knows how long it will last) have carte blanche to make the best product they can, year after year. The Intel engineers are not allowed to do ANYTHING that might make a product at level n of the 29 step marketing segmentation an acceptable, cheaper, replacement for level n+1.
That will give you the A6X article and you can work backwards or follow links in there.
If you like technical details, the A4 article is probably the best. Unfortunately after that one they degenerate more and more into complaining about Samsung, with fewer and fewer previously unpublished details about the actual chips.
One person even built/builds these chips and confirmed this article in post #11. So, thanks for your opinion, but...
Well, just to be fair, Mediatek, Rockchip, Allwinner and Huawei are also all making mobile chips.
(But, honestly, only Huawei is making chips that can even pretend to be in flagship class.)
And nVidia, with Denver was, as mentioned, still considered a serious possibility for quite a few years after the A7 shipped.
At this time, of course, Intel was still peddling the fantasy that it was going to be a contender in mobile, so DED could/should probably have included them in his list of Apple competitor wannabe's.
Then again, as an Apple watcher since the 70s, I find Daniel’s articles to be clear, plainly factual, and very well-written. They also accord very (*very*) closely with my own recollections, personal knowledge and experiences in the industry during the periods in question.
So basically, you signed up to the site to register your Butthurt.
They just had the transition to 64 bit of desktops which was promoted by computer companies as ‘huge’ while it turned out to be used largely as marketing to sell more computers with no subsequent speed gain to speak of and lots of incompatible software that had to be bought again.
This time journalist thought they knew there stuff and spotted another marketing campaign promoting 64bit for embedded.
The point is that ARM 32 bit and 64 bit are completely different processors using a different instruction set. So thats the difference.
Apple did this before with Intel processors, when used in 64 bit mode (intel keeps its 32 bit stuf lingering around) the processors can be seen as completely different from 32 bit, exhibiting different register sets and instructions with much more efficient context switching.
Most of them have a variety of Apple devices and the switch happened downstream of what is detailed here. The choices they made in thei period allowed Apple to pull away from Samsung/Android in the minds of the ordinary Joe/Jane.
now, you’re talking about SoC performance. I didn’t say there’s FUD about Apple’s performance. I don’t know how you misunderstood that. I was talking about the other areas of Apple’s reputation, not SoC performance. Pretty much everyone knows that Apple’s SoCs are well ahead. Writers know that as well. So we get the grading on a curve sort of thing. There and acknowledgement that in talking about Android SoCs, the tests that can include iOS will, and they’ll show how much ahead Apple is, often without having to say so. Read the Anandtech reviews. The new Huawei Mate 30 Pro is there now. Not a very good phone overall, except for some photography, which for many areas turns out to be pretty good. Though I never pay much attention to the photography part of a review unless it done by a pro photographer or videographer.
so we have the new Kirin 990, which is their state of the art SoC, with a modem built-in. If we take Apple’s chips out of the equation, this is a really good SoC. The best Android SoC so far. Pretty good, right? But it’s not only way behind the current A13, it’s pretty far behind last years A12, and barely coming to the year before’s A11. So, in reality, this is a terrible SoC. But reviewers can’t just come out and say that. So they say that this is the best new SoC out for Android phones, which is true. But at points in the review, mention that Apple’s SoC just wipes out the competition. But Android makers can't get Apple’s’, so it doesn’t matter.