Unified memory. Specialized processing cores. That's two. Do you or do you not agree that moving the memory controller from the motherboard to the processor increased performance?What factors? You just keep throwing these statements out without any details. What are the factors, why are they more important, and what background do you have that suggests that your opinion is meaningful?
Those two cannot both be true. Changing the name of something does not change that something. It is the same thing under another name.I said “It’s a change of name. Same fundamental architecture. Like Xeon vs. Celeron.”
Isn't Tiger Lake the answer to the M1? It is in the Dell XPS 13" right now.
https://www.forbes.com/sites/brooke...nchmarks-13-inch-macbook-pro/?sh=66aa32c967e1
Also if you look at the US market (which is where Apple tends to be somewhat more focused) the Mac market share is more like 25% than 8%. Considering that they have no low end machines (even the MBA price and fit and finish wise is not low end) they are a major player in their market.The Mac is not having a hard time surviving. Apple sold $9 billion worth in the last quarter alone. Does that sound like a "struggling" product? The Mac user base is currently at 140 million and continues to grow as half of Macs sold today are to people new to the Mac.
The fact is, Apple only makes a handful of computers in a few form factors at the higher end of the market. This naturally limits broader appeal.
Whaaa??? You mean there were other factors? I wish I had known: That there are other factors at play other than RISC versus CISC.Had nothing to do with RISC vs. CISC. It had everything to do with business interests. IBM was pretty much only interested in developing high-performance variants that consumed more and more power. And not long after that, Motorola lost interest and spun off their semiconductor business to form Freescale Semiconductor. This left the PPC roadmap headed towards a cliff.
Apple didn't have much choice. And since they already had Mac OS X on Intel from its OpenStep lineage, Intel was an easy fit. And Intel happened to be developing the more "efficient" Core design.
This exactly. ^^^^^^Motorola couldn’t deliver chips that didn’t suck even for desktops. They were bad at chip design.
And IBM had no interest in doing so because, as I said before, they were focussed on chips for their own RS/6000 workstations, which made them a ton more money than selling chips to Apple.
Your entire argument is based on a flawed hypothesis. Just because an architecture is good doesn’t mean that a DESIGN will be good. Intel and AMD both use x86-64, but that doesn’t mean that their designs are equally successful.
I don't think they lost interest, they were leaking money like a sieve. BTW I also know a designer at Motorola (then moved to Freescale) that worked on PPC along with us. They wanted to keep it going as it was an oppertunity for them with Apple.Whaaa??? You mean there were other factors? I wish I had known: That there are other factors at play other than RISC versus CISC.
If only I had known we could have avoided all of this. Oh, wait.
So, IBM was only interested in high-performance variants that consumed more and more power? Really? You mean they wouldn't be interested in developing higher-performance processors that used equal or less power? They were solely focused on higher-performance at more and more power?
Motorola lost interest in capturing a market with higher-performing processor designs? Seems like a very poor business decision to ignore such a huge market.
Why were they leaking money like a sieve? After all they were producing a RISC processor. I've read so much about how producing RISC processors is the way to go.I don't think they lost interest, they were leaking money like a sieve. BTW I also know a designer at Motorola (then moved to Freescale) that worked on PPC along with us. They wanted to keep it going as it was an oppertunity for them with Apple.
Full circle. 68k to ARM. RISC baby.RISC has been "the future" since at least 1985 when ARM started, and a bit before that with MIPS.
It looks like it is finally reality now in more than quite narrow markets.
Typical response for this site. I didn't expect anything more./snarky
Had nothing to do with that. It was largely related to how the cell phone market was going. Plus the culture and mismanagment played a role. I didn't work there, getting that last from my friend.Why were they leaking money like a sieve? After all they were producing a RISC processor. I've read so much about how producing RISC processors is the way to go.
Maybe I could have: Unified memory. Specialized processing cores. That's two.As far as the CPU cores are concerned, there are no other factors (other than on package RAM to feed the CPU faster) that could or would have any impact on CPU performance, so it is mainly because of Apple's CPU core designs. It's neither a CISC nor RISC issue, it really comes down to Apple's implementation of the armv8 ISA.
I've no background in this stuff, but couldn't you argue that since everything shares the unified memory on the package, other PU's can quickly finish a task allowing a dependent CPU thread to continue sooner, thus speeding up the CPU performance? Now obviously, that's a bit of crappy programming, but it could happen.
How can they call this RISC when they now have a more complex instruction set? Adding instructions for encryption, graphics, signal processing, etc. This is more the definition of CISC.
As far as the CPU cores are concerned, there are no other factors (other than on package RAM to feed the CPU faster) that could or would have any impact on CPU performance, so it is mainly because of Apple's CPU core designs. It's neither a CISC nor RISC issue, it really comes down to Apple's implementation of the armv8 ISA.
I've no background in this stuff, but couldn't you argue that since everything shares the unified memory on the package, other PU's can quickly finish a task allowing a dependent CPU thread to continue sooner, thus speeding up the CPU performance? Now obviously, that's a bit of crappy programming, but it could happen.
In latest test online the M1 Macbook Pro takes 36 minutes to compile Mozilla Firefox. While it's no bad for a thin and light notebook (and even very good), it's nothing exceptional.
RISC instruction set on ARM has been growing for years. However, the instructions are still fixed in length and they are not run in parallel as in CISC. Fundamentally - it is still RISC.
I know that some version of the Amiga still exists. I also know Apple had little or nothing to do with its Commodore version failing. I owned an Amiga 1000, 2000, and 3000 between approximately 1985 and 1993. What killed it was that everyone wanted IBM compatibility (so if someone says Windows Compatibility they obviously weren’t there) and the fact that it was labeled a “game machine “. Today that’s a compliment, back then it was an insult. It didn’t help that Commodore really had no idea what they had or how to market it and what they needed software wise to compete. You could do video editing by the late 1980’s, the computer had built software for mixing pictures and video and sound. it was multi tasking years before other home computers. But it wasn’t IBM Compatible. I don’t know if it ever got out of prototype but there was an add-on called “Side-Car” that was supposed to give you the ability to run MS Dos programs. I don’t remember hearing if it would run Windows 1.0 to 3.11. By that time it’s sales were dwindling and when Windows 95 came out with all sorts of features that the Amiga had 10 years earlier every tech magazine was proclaiming what geniuses MicroSoft were.You both need to watch the Amiga videos out there.
I don’t know cmaier from jack but it’s obvious that he has designed chips and worked with both x86 and RISC designs, something other posters here on MacRumors have verified. What are your credentials?I love how people on this site always qualify their insults with "nothing personal" or some such nonsense.
I'm not going to try and convince you of anything as it's obvious your mind is closed.
My understanding was that CISC was chosen because its faster, it can run multiple operations at one time while the RISC could run just 1 operation at one time. RISC was used mainly on devices that were more of an appliance mainly due to their low power usage. I mean, even on the *nix side of things they mainly use AMD and Intel which are CISC, no Windows needed there. It doesn't help that Apple abandoned IBM POWER PC(RISC) and switched architectures to Intel(CISC) just because PowerPC was not delivering as much performance.
ARM seems to be doing well.PowerPC - Dead
SPARC - Essentially dead
MIPS - Dead
Great resume