Apple's Redesigned Mac Pro is Coming in 2019 (theverge.com) 183
Apple's long-awaited update to the 2013 Mac Pro won't be released until sometime next year, the company told TechCrunch. From a report: We've known since a press roundtable in April 2017 that Apple was "completely rethinking" the Mac Pro, in the words of marketing chief Phil Schiller. Now, we have confirmation that the product is arriving next year after some speculation that it could make an appearance this year at a fall hardware event typically reserved for MacBook announcements.
"We want to be transparent and communicate openly with our pro community so we want them to know that the Mac Pro is a 2019 product. It's not something for this year," Tom Boger, Apple's senior director of Mac hardware product marketing, told TechCrunch. "In addition to transparency for pro customers on an individual basis, there's also a larger fiscal reasoning behind it."
"We want to be transparent and communicate openly with our pro community so we want them to know that the Mac Pro is a 2019 product. It's not something for this year," Tom Boger, Apple's senior director of Mac hardware product marketing, told TechCrunch. "In addition to transparency for pro customers on an individual basis, there's also a larger fiscal reasoning behind it."
My Mac Pro is faster than Apple's Mac Pro (Score:5, Informative)
My 2009 2x 6 core Xeon 3.4ghz system is faster than Apple's 2013 tubular 6 core Mac Pro that sells for $3000. Apple won't repair my Mac Pro's heat sensors but I'll be damned if I'll buy a new computer that costs a ton of money and runs slower. So I'm stuck with loud fans for the time being. It's frustrating as hell.
Re: (Score:3)
There's an easy solution for the fans. Connect the 12V fans to 5V.
I've been using that trick for years since we have a bunch of Dell servers that after a BIOS update broke the software that based the fan speed on a reading from a temperature sensor. Also, I unplugged half of the fans since they run cool enough without them.
Re: (Score:2, Flamebait)
There's an easy solution for the fans. Connect the 12V fans to 5V.
There's an even easier solution. Buy a quality product from a company who's motto is "It just works". Shame that no longer exists.
Re:My Mac Pro is faster than Apple's Mac Pro (Score:5, Informative)
There are great apps for fan control on the Mac that bypass the normal sensor info. I would be a lot more helpful if I could remember any of them. It might be Fan Control, but I'm not sure: https://www.lifewire.com/macs-... [lifewire.com]
Re: (Score:2)
There are great apps for fan control on the Mac that bypass the normal sensor info.
So buy a premium quality fancy machine just so you have to bypass and screw around with something that shouldn't be broken in the first place?
Re:My Mac Pro is faster than Apple's Mac Pro (Score:5, Interesting)
Considering they're just dealing with loud fans, it's a better situation already. The fact is, you can buy heat sensors on eBay for under $5 if it's really worth it to you.
you have to bypass and screw around with something that shouldn't be broken in the first place?
Because other brands of computer never have failing components out of warranty? Because this computer has heat sensors beyond what typical PCs have, so there's more to fail? I'm not a huge Mac fan, but that's a bit of a stretch of an argument.
Re: My Mac Pro is faster than Apple's Mac Pro (Score:2)
I've just started up my 1986 ZX Spectrum after 20 years and loaded a couple of games. It's still working fine as far as I can tell and it's had a hard life in the past.
Re: (Score:2)
Re: My Mac Pro is faster than Apple's Mac Pro (Score:2)
No but then my Spectrum was relatively cheap and from a company notorious for poor build quality and yet it still works fine. I don't think it's unreasonable to expect a very expensive computer from a supposed high-quality manufacturer to still be working perfectly after a mere 9 years.
Re: (Score:2)
Re: (Score:2)
I too am running an equivalent era factory water-cooled HP z800 with 2x X5687 quad 3.6ghz.
I have a stack of dead power supplies I will eventually repair myself... the gods of planned obsolescence will have to wait.
Re:My Mac Pro is faster than Apple's Mac Pro (Score:4, Interesting)
I'm still using my 2008 Mac Pro as my main game system (dual boot Windows 7), with a 1070 Ti it still runs the games I play pretty nicely (MMOs mainly) and doesn't have nearly as much fan noise of my wife's Dell.
I think the era where your computer was obsolete every 2 years is over.
Translation (Score:5, Informative)
We want to be transparent and communicate openly with our pro community so we want them to know that the Mac Pro is a 2019 product. It's not something for this year,
Translation: We couldn't be bothered to get off our ass and work on this before now because we make all our money from iPhones these days.
In addition to transparency for pro customers on an individual basis, there's also a larger fiscal reasoning behind it.
If Apple wants to be transparent it might help if they didn't say things that only have meaning if you work at Apple. "Larger fiscal reasoning" could mean almost anything.
Re: (Score:2)
Translation: We couldn't be bothered to get off our ass and work on this before now because we make all our money from iPhones these days.
Not only that but they are still selling the 2013 model at full price despite the fact that it is 5 years old. Jobs' reality distortion field still seems to live on even though Jobs himself is no longer with us.
Re: (Score:2)
Translation: We couldn't be bothered to get off our ass and work on this before now because we make all our money from iPhones these days.
The Mac Pro is just a computer to build iPhone apps with.
Re: (Score:3)
It means "We couldn't be bothered to get off our ass and work on this before now because we make all our money from iPhones these days"
That doesn't make any sense. Apple has one of the (or is it "the") biggest cash reserves of any public company in history. They can buy Dell with pocket change.
If they gave the money to the Federal Reserve and had them print up special $0.99 bills, they could power San Francisco for a year by burning them.
To me, the only thing that makes any sense is that it has something to do with taxes and a 2019 deadline of some sort. (That or they want to build a factory in a tax-favored location, and it won't be comp
Funding isn't the issue (Score:2)
That doesn't make any sense. Apple has one of the (or is it "the") biggest cash reserves of any public company in history. They can buy Dell with pocket change.
Exactly my point. The only reason to not update the Mac Pro is because either (A) it isn't profitable or (B) your attention is elsewhere or (C) gross incompetence. Funding the project is obviously not a problem for Apple so it's something of a mystery why they only can be bothered to update the Mac desktop lines once per presidential term. My guess is that management attention is largely on the iPhone and iOS and the Mac gets the sloppy seconds.
To me, the only thing that makes any sense is that it has something to do with taxes and a 2019 deadline of some sort. (That or they want to build a factory in a tax-favored location, and it won't be complete until 2019).
Might be a factor but taxes really aren't as big a conside
Re: (Score:3)
My guess is that management attention is largely on the iPhone and iOS and the Mac gets the sloppy seconds.
That and the new HQ. Apple's chief designer Johnathan Ive has been working on designing the new HQ for the last several years which has taken his primary attention. He handed off his managerial duties to two deputies in the interim and only recently returned to the role [9to5mac.com]. While Ive's work is on overall design and not necessarily the technical details, his design choices have influenced Apple's look and engineering. My guess is that his lieutenants did not have his managerial skills to take over adequately as
Fiscal Reasoning? (Score:5, Insightful)
Seriously... "Fiscal Reasoning?!?" That's like saying Bill Gates needs to save for a few days to buy himself a Big Mac.
Apple has been lost for a while, hardware-wise. (Score:5, Interesting)
I doubt they could do much better than simply going back to the 2012 cheesegrater hardware, with a new motherboard that offers the same expansion capabilities but newer, faster/more CPU and RAM and so forth. Pluggable gfx cards, hard drives, absolutely no non-replaceable flash storage, optical drives, lots of standard USB I/O, ethernet, optical and analog audio, etc.
I also highly doubt they'll do it. They'll almost certainly just screw up again. Look at the mini and so on; just one more screwup after another last few iterations. There's no sign of sanity over there at all. And the iMac "Pro" is outright ridiculous.
That's okay, though. The cheesegraters will probably last for many years yet. I feel no burning need to give them money for yet another design fail.
OTOH, I'd be happy to give them money if they actually improved the mac pro beyond the cheesegrater. Or went back to the cheesegrater. Or actually improved the mini beyond its peak (which is not the current mini.) Or put out a decent mid-tower.
But again... breath-holding is not called for here. The evidence shows they're thoroughly lost in stupidland.
Re: (Score:2)
https://www.asus.com/us/Motherboards/X99PROUSB_31/
Older Model, probably $300 new when it came out...
Or this http://www.asrockrack.com/general/productdetail.asp?Model=EP2C602
$350 from Newegg. Convert one of the PCI x16 slots into a Thunderbolt port... Update to DDR4, maybe.
XEONs pack a hell of a wallop in cores.
Do that, at half the price you're charging for the Current ash-can.
And give me an upgrad
Re: (Score:3)
You realzie OEM’ing to Asus is the root cause of the whole “AMD Secure Processor” bug from a couple weeks back, right? (AMD OEM’d that “non-critical” part of the design to an Asus Subsidiary)
I’d think twice about partnering with Asus.
Re: (Score:2)
But contract with someone with volume - get them to make you a mostly identical version of a wide-production motherboard that apple can put their special license ROMs on (or a special TPM the add in a seperate step).
Pick any manufcaturer who has decent volume - Supermicro would probably be a good choice for the Mac Pro. ASrock, ASUS, both make great home user motherboards.
Walk back away from the 2 year upgrade cycle - give people something they can get 10 years out of, because at this point YOU CAN. I
Re: (Score:3)
I agree 100% that Apple has completely lost their way W.R.T. computer hardware.
When they:
* put out a new computer that is slower the previous model (the Mac Mini fiasco)
* make it impossible to upgrade RAM and SSD because they are soldered in (WTF!?), etc.
you quickly realize Apple is all about streamlining their products at the expense of versatility.
Seriously, who the fuck would buy an Mac Pro [apple.com] -- when the hardware is so over-priced and out-dated it isn't even funny -- so why even continue selling it?
They ar
Re: (Score:2)
They are out of touch with what geeks want.
Probably due to lack of desire/effort. A business can get by just fine without targeting a specific audience in order to have strategic focus on their core customers.
This is like saying that Budweiser is out of touch with craft beer consumers, even though microbrew is clearly better than mass produced.
Re: (Score:2)
The difference is that Budweiser knows they're being outmoded which is how and why they're part of the single largest brewer in the world [wikipedia.org]. Craft beer has eaten so much of their market, the most regulators didn't blink at the purchase since they've been losing market share for years. Budweiser reacted to the changes in their market in order to stay in business.
Apple actively tries to keep the market from changing instead of adapting. The MacPro is evidence of that. Once the darling of the graphics and music
Re: (Score:2)
Re: (Score:2)
Not twice the price, 3 times the price, but 10-20% premium.
I'd replace almost all my Linux boxes in a heartbeat. Bring back the MBP 17, or at
Re: (Score:2)
Pretty much. High-end systems like the Pro should be thought of as tools and not fashion.
A nice sized case with slots, sata, m2 and space for lots of drives.
They could do a reference design and add an advanced heatsink and fans to keep the noise down.
Evolution prediction of mac hardware by use case (Score:2)
If the remaining good older/affordable apple hardware dies, this is my prediction
"Server"
xserve -> mac pro -> mac mini -> linux pc
Photo/Video content creators
mac pro -> mac pro -> imac/pc
"home users"
imac -> imac -> mac book air -> ipad
students
macbook air -> ipad/chrome book
programmers/mobile content creators
mackbook pro -> macbook pro -> macbook air like macbook
Iphone users
iphone -> iphone -> iphone
iPod touch users
ipod -> iphone
Apple used to have software manufactur
Based on the A12 (Score:2)
I predict a 12-core A12 based Mac Pro. Why else would it take so long to release?
Apple still has pro users? (Score:2)
The way they've been neglecting the Mac for years, you'd expect all their pro users to have jumped ship. But then again, the alternatives are all flawed.
Re: (Score:2)
Re: (Score:3)
Re: (Score:2)
The way they've been neglecting the Mac for years, you'd expect all their pro users to have jumped ship. But then again, the alternatives are all flawed.
I suspect they have plenty of pro users. Just understand that by "Pro" these days, they mean people catching planes to give some Powerpoint show in a nice suit. That's why we still get laptops while desktops flounder.
Re: (Score:2)
Re: (Score:2)
Yes, I know Colorsync was a big deal back then, but Windows includes an equivalent solution now, right?
Re: (Score:2)
Apple has the OS and other apps able to all use the same color details in much better way.
Apple gave the pros a great system LAST year (Score:3)
The way they've been neglecting the Mac for years, you'd expect all their pro users to have jumped ship.
Not after the iMac Pro. That is a seriously good system and really takes the pressure off Apple to deliver a Mac Pro, which is why they are pushing back the schedule to make it better.
With new innovations like... (Score:5, Funny)
They will Solder the Mouse and Keyboard in directly.
Too prevent counterfeit Mice and Keyboards, or something.
This will be called 'Courage".
Re:With new innovations like... (Score:5, Informative)
Re: (Score:2)
Funny enough, my coworker just got the iMac as her work computer. The most recent version of the mouse that comes with it has a rechargeable battery instead of using AAs. Okay cool... except Apple didn't want to blemish the sleek design of the mouse, so the charge port is ON THE BOTTOM. I.e. if your mouse battery dies, you can't use it at the same time you're charging it up.
Well,let's be serious. I'm much more of a Mac addict than most of you lot, and one of the first things I'll admit is that Apple hasn't had a usable mouse since before the puck style appeared in '98.
Re: (Score:2)
I don't think it was a matter of blemish, it was a matter of making sure the battery life isn't unnecessarily shortened by keeping the mouse plugged in all the time.
THAT SAID
I'm not a big fan of wireless keyboards and mice in general except in specific circumstances. The keyboard that's at my desk day in and day out doesn't need to be wireless. I'm not lounging on the couch with it. Same with my trackball. Apple doesn't want you to use the mouse like a wired mouse, so they came up with a weirdo design to en
Re: (Score:2)
Wireless keyboards are major issue if you work in an industry where security compliance is a requirement. Wireless keyboards are a security fail for PCI-DSS and HIPAA.
Re: (Score:3)
I hate two things about the new version of the mouse. It wouldn't be so bad to have the port on the bottom except that you don't get the warning to charge the mouse until it's almost dead (as in it doesn't make it through the rest of the day for me). If the warning came with 25% charge left or something higher than what it currently does then I'd have more time to charge it. I'm terrible at checking how much charge is remaining. The older version with two AA batteries wasn't that bad because I used recharge
Why!? (Score:4, Informative)
Apple, come on! Just give us a tower with good cooling and standard expansion slots. That's what the pros want. This shouldn't take long to design, even if you want to make it all shiny.
If you can't handle designing a tower anymore, just give us a "blessed" motherboard that we can assemble our own computer out of. No support, etc. For pros only.
Re: (Score:2)
TB with it's need to route video over it is why the mac pro has been MIA and that 2013 has shit.
Apple Dell / HP and others looked at the past and PUT IN A LOOP BACK CABLE like the old voodoo cards.
Re: (Score:3)
I predict it will be shaped like a fireplug.
Buy one today (Score:2)
Apple, come on! Just give us a tower with good cooling and standard expansion slots
Congrats, you can by one today. It's called the iMac Pro. It has amazing cooling and really quiet fans.
For the nostalgic that still need "standard expansion slots", just get an external chassis for that connected via thunderbolt 3. You could wind up with way more slots than any PC if you so desired.
Go back to the CheeseGrater, but with ARM (Score:2)
But smaller, with datacenter specs, so lots of 2.5" SAS drives, no optical, lots of GFX cards, with datacenter sizes (half height, half length, 2 slots).
Put a couple Cavium (Marvell) ThunderX2 chips inside (instead of intel) so that you start the transition to ARM in earnest, and with a Bang.
https://en.wikipedia.org/wiki/... [wikipedia.org]
If is Good enough for a FUCKING CRAY XC50 SUPERCOMPUTES, shall be good enough for Mac "Pro" users.
For the tiem being, leave the Apple designed ARM stuff for low end laptops.
More Apple screw-ups. (Score:2)
Sounds to me like they want to force people waiting on the sidelines to consider the shitty iMac Pro or the eve
Mac Pro 2019. Now with more and heavier welds (Score:3)
It will be an additional $500 more expensive and the case will be sealed shut to absolutely prevent anyone from even attempting to see if any part can be pried off the motherboard to be replaced.
If something goes bad, oh well. You'll have to buy another one. That's the fiscal reasoning behind the delay.
Re: (Score:2)
there's also a larger fiscal reasoning behind it.
It will be an additional $500 more expensive and the case will be sealed shut to absolutely prevent anyone from even attempting to see if any part can be pried off the motherboard to be replaced.
If something goes bad, oh well. You'll have to buy another one. That's the fiscal reasoning behind the delay.
Joking aside, this is exactly what Apple will do.
6 years... (Score:2)
Yes, Apple very clearly cares about professional users.
Re: (Score:2)
* With nothing else: The MacBook Pro was touted as the ideal laptop
Re: (Score:2)
It will still be overpriced an inflexible (Score:2)
Whatever the revamped Mac Pro will be you can guarantee that it will still be massively overpriced (more so than Apple's usual pricing) and won't go anywhere near having the upgradeability that one would usually expect from a "pro" machine.
Re: (Score:2)
It will be like they epoxied two mac-minis together.
No, they said modular. They'll use Velcro.
Re:My prediction: (Score:5, Funny)
Velcro is not exotic or proprietary enough. They will use a patented, 3D printed, titanium, sintered, anodized clip with a custom bluetooth chip.
Re: (Score:3)
They're going for dual A10X - two iPads glued back to back. Maybe they'll curve the screens into a complete 360.
Re:My prediction: (Score:5, Funny)
Pyramid
Pyramid
Pyramid
iPyramid
iPyramid Pro
Re: (Score:2)
Re: (Score:2)
If you could watch the cooling liquid percolate through the little impossible do-dad, that would sell it for me.
By the way, if you haven't seen Cliff Stoll get excited about Klein bottles [youtube.com], this is your chance.
Re: (Score:3)
Nope, going to be fireplug. Its the only logical shape for the next mac pro.
Re: (Score:2)
Keep it away from your dog then.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Wait, but isn't that because more complex instruction sets...
I mean, it's in the name of the architecture dude...
Re: (Score:2)
First step, find a prominent RISC platform that doesn't just have RISC in the name for historical reasons. At this point, everything with any performance is CISC (whether by the inaccurate concept of count of available instructions, or in terms of how many instructions per memory cycle as was the original intent).
Re: (Score:2)
Looks like the POWER8 is RISC based https://www.ibm.com/developerw... [ibm.com]
Re: (Score:3)
The issue being that RISC was a technical feature that became a marketing bullet point. As the original bet of RISC architecture was lost (that complex hardware could not scale up, and that compiler optimization would close the gap of CISC), surviving high performance "RISC" families started embracing instruction set extensions to include multi-cycle instructions.
However, marketing material continued to beat the old dead horse of how RISC was better, despite their own designs seemingly saying otherwise.
RIS
Re: (Score:2)
Care to point some out?
Actually *all* modern architectures are RISC ... CISC no longer exists, except as "compatibly mode" for x86.
Re: (Score:2)
Well, pretty much all modern SIMD instructions are not RISC.
For specifics, here's an ARM document about instructions in the pipeline and how many cycles the different instructions are:
http://infocenter.arm.com/help... [arm.com]
RISC was supposed to be that any given instruction was simplistic and would use no more than a single cycle, and that the processing units would be utterly generic. Now we have something of a hybrid of that philosophy and CISC philosophy, with people 'rooting' for the relatively meaningless 'C
Re: (Score:2)
Hasty Instruction Set Computing (Score:5, Interesting)
add segment_register:[disp + r32_A + r32_B*n], r32_C
That's no-one's idea of a classic RISC instruction.
And even though this gets decoded into micro-ops, the complex address generation is computed only once, and the memory order checks take advantage of this having been a single, fused instruction, so the semantic nuances are carried deep through the OOO pipeline.
There's so much crap on the Internet about RISC, it blows my mind.
50% of the RISC hype was about being able to compete against the legacy vendors with smaller, cheaper design teams.
You can call x86 RISC, but it never got cheaper to design. The cost of the design is almost a superset of its CISC and RISC elements (I'm pretty sure its hybrid nature creates headaches above and beyond the sum of its parts).
The RISC hype bubble had some validity for roughly a five-year period before Intel launched the Pentium Pro in 1995 (RISC hype persisted outside the clue nucleus for another five years after that for largely political reasons). The Pentium Pro is where the complexity of the CPU core and the complexity of the memory subsystem (and latency hiding) began to cross over. There is no possible way to design a processor with a deep, concurrent queue of in-flight cache and memory transactions (with SMP coherence), and extensive latency hiding in the execution engine using a small design team.
Wikipedia's article on the Pentium Pro makes it sounds like its performance sucked, but it held up amazingly well on mixed Windows NT server workloads compared to any RISC architecture at anywhere near the price (it's deep OOO latency-hiding was a huge boon to memory thrashing compared to in-order RISC with wider dispatch.)
Wide dispatch = straight line speed (American car).
OOO latency absorbers = cornering speed (German car).
Of course, most benchmarks are biased to the salt-flat quarter mile.
Another thing, the majority of CISC junk-in-the-trunk (e.g. 286 call gates) is subject to exponential shrinkage; barely a third decimal point by the time you reach a billion transistors.
On the matter of superscalar execution, this naturally prioritizes the quick and the fleeting (only these instructions could pair up in the P5). Superscalar under OOO is a different beast: now the killer dimension becomes instruction flight time. This for the macro-ops at the level of the retirement order buffer, the micro-ops at the level of the dispatch buffer, and the outstanding memory operations at the level of the memory order buffer.
Intel's x86 architecture is more HISC than RISC: Hasty Instruction Set Computing. The faster you retire the operations (at any level), the sooner you free up precious reservation buffers. (x86 never inched one step closer to a conventional load/store architecture, the cardinal 'R' in RISC; most especially, transient addresses off the stack frame do not retire to the register model in x86—what a waste of reservation stations—because they are never register-assigned in the first place.)
Micro-operation [wikipedia.org]
If some traditional RISC architecture adds macro-op fusion to its internal implementation, do I get to declare that "modern MIPS is nothing more than a MIPS translation layer around a CISC chip, anyway"?
Since the early 1990s, this debate has been my #1 personal case study in technological propaganda, herd following, and revisionist misinformation.
I originally got onto this file asking myself a hard question: just who is this messianic charlatan named Steve Jobs?
Re:Hasty Instruction Set Computing (Score:4, Insightful)
add segment_register:[disp + r32_A + r32_B*n], r32_C
That's no-one's idea of a classic RISC instruction.
You're right. It's not. That, sir, is an x86 instruction, which the x86 translation layer takes as input and passes to a RISC core. Intel, at least, has been doing this since the Core series was released.
Your comment jumps the rails right there, with your first remark, and only gets farther and farther off course from there.
Re: (Score:3)
Even if you strip off the microcode and the instruction decode (which is intrinsic to the platform an dI would argue you cannot strip away), you'd still be left with a behemoth that most would not call RISC, except for religious adherents to the hype of RISC as a way to claim victory.
Of course, everything has dramatically changed since the m68k CISC v. Berkeley RISC days, and this whole debate is silly. Just because something is CISC, it doesn't vindicate the m68k design that spawned the architectural expl
Re: (Score:2)
The base conditions of the argument has changed too. It used to be about what you could do with a fixed number of transistors or fixed cost. But as prices of everything went down, the rules changed. So Intel decided they could keep their PC market share by just shoving in more and more transistors. Make this chip do instruction decoding and translating, then pair with another compute engine chip with modern super-scalar designs, add in some chips for caches, and shove it all in a CPU bundle the size of
botanist vs engineer (Score:4, Interesting)
No, since the Pentium Pro in 1995, which already employed microcode translation; not with the Pentium IV, which was deliberately brain damaged to win the MHz war (I don't even know how to classify the trace cache, except ungodly hot); again with the Core Duo, after that (god bless Israel).
How Israel saved Intel [seattletimes.com]
What you are calling a RISC core has more proprietary CISC-world abstraction violations than you could shake a stick at (these are primarily performance hacks, but nonetheless).
Explain to me why micro-op fission gets more air time in your lexicon than macro-op fusion? Because modern x86 processors use both tricks to obtain a working representation which minimizes in-flight resource consumption (which is similar to RISC, but is not directly motivated by either "simple" or "reduced"—hasty is a better proxy—and none of this is reflected in the instruction set, as is patently obvious). And even then, the micro-op fission remains semantically distinct from an actual RISC instruction stream deep into the pipeline in small yet critical details (internal modern x86 micro-ops are fuzzy creatures, but these implementation tricks aren't publicly documented).
There's actually a more basic level underneath RISC: readers and writers attached to separate busses. But this is so low level is tends to make your ISA non-portable to the next iteration, so no-one sane goes here (I'm looking at you, Itanium, even though after you started here, you went another 100 miles downstream).
write_assert rA to register_bus_1
read rB from register bus_1
read rC from register bus_1
write_deassert rA to register_bus_1
Register files tend to be multiple ported, so there would be other register busses available concurrently. That's all one clock cycle if your macro-op fusion puts Humpty back together again (and not analogous to any RISC instruction).
mov ebx, eax
mov ecx, eax
In a transport triggered architecture [wikipedia.org]-like world, these two instructions could be fused into a single assertion of eax, and a simultaneous read by register file ebx and register file ecx off the same bus.
But you'd still call it a RISC core, wouldn't you, so long as the internal representation was granulated into some kind of small, vaguely uniform ops? (Macro or micro, who cares?)
Between 1985 and 1995, I must have read many dozen articles in computer magazines about how x86 CISC could never grow up to compete against the Big Boys (where RISC was the prototypical Big Boy). This was a potent brew of aesthetic disgust (with which I largely concurred), competitive ambition, and mentally defective bullshit—as history now records. In order to advance this kind of claim in a falsifiable way, RISC has to actually mean something.
Back when I wrote a fair amount of 486 code, I mainly worked in a RISC subset (most of which dated back to the 8086 or were simple extensions), heavily augmented with non-RISC ModR/M sib addressing modes. There was no OOO, so there was no need for an intermediate micro-op representation: the complex read/modify/write instruction were decomposed into RISC primitives (load,operation,store) by an execution-engine state machine (which I suppose you could call a micro-op sequencer on the understanding that the machine supported exactly one in-flight macro-op. A non-distinction without a difference?) Compared to 386, 486 felt a bit RISCy because many of your core operations had a single-cycle execution time (and you tended to ignore program fetch delays, because of the concurrent internal i-cache).
Once you get into OOO, you need track multiple i
Re: (Score:2)
Re: (Score:2)
At the time of RISC, the instruction decoding and micro engine was often one of the largest and most complex parts of a computer. The design of so many computers and chips in those days was all about the instruction decoding and microengine, if they wanted to speed up their processing then they worked on faster clock speeds (work harder, not smarter). So the idea of RISC is to minimize those parts of the chip and replace them with components that can speed up the processing. Ie, more registers, concurrent
Re: (Score:2)
A highly clocked x86 is literally the opposite of what RISC designers actually thought was possible.
I thought CISC processors were essentially RISC processors, using microcode to execute the complex statement.
Re: (Score:2)
Your RISC/CISC processor isn't really what people used to call "RISC".
(And neither are modern ARM processors, they've gone over to the dark side in order to compete with CISC on performance...)
Re: (Score:2)
Internally, sure. They still expose a complex ISA like AMD64 and ultimately implement it. But the black box you buy is CISC.
Re: (Score:3)
Re: (Score:2)
AMD EPYC gen 2 system? (Score:2)
AMD EPYC gen 2 system?
Re: (Score:2)
That was their new feature last time. They need to innovate if they want to stay ahead.
Innovation (Score:2)
1/4 as good, 4x the price.
Re: (Score:3)
1/4 as good, 4x the price.
Just like kosher food!
Re: (Score:2)
Nathan's hotdogs are tasteless trash!
Pretty much this. (Score:3)
I own two Macbook Pros for mobile work, but for desktop work I rely on a self-built that runs MacOS and actually has the hardware that I need in it. Too bad Apple won't sell me one, I'd buy it instead and not have to worry about dealing with the vagaries and annoyances of maintaining my own white box hardware.
Re: (Score:2)
Re: (Score:2)
Yeah, that's bollocks,
The alleged "we will use our own chips" thing is slated for 2020. They just said the Mac Pro is a 2019 product.
Furthermore, if there is one Mac that really needs to stay on x86_64 architecture, it is the Mac Pro where power consumption is not an issue but absolute performance is.
Also, I find it quite amusing that people are assuming that the new Apple chip for PCs will use the ARM architecture. Is there any reason why Apple couldn't do their own x8664 compatible?
Re: (Score:2)
They'd need intel and AMD's blessing and to pay them royalties to do AMD64.
Re: (Score:2)
No more VMware fusion or Bootcamp. No more performance. All new drivers for everything.
I guarantee it. Switching to ARM will be the end of Mac OS. You will lose the developers. Though Ballmer was a fucking monkey, he was right.
https://www.youtube.com/watch?v=Vhh_GeBPOhs
Re: (Score:2)
Re: (Score:2)
To host an other OS, obviously.
You are not a pro?
Re: (Score:2)
More likely the dead end has already happened. Just look at the specs of the current model. Next one is probably the first of its kind with A-series. One brand new high-end A-series core paired with a lower power core to switch to when idle.
Re: (Score:2)
External GPU has 40 Gbit/s, versus that same GPU getting 128 gbit/s of throughput internally. In the 2019 timeframe, that PCIe number will jump to 256 gbit/s with PCIe gen 4. There has been very little information on Thunderbolt 4, but even the most optimistic speculation has it at 80 gpbs and after pcie gen 4.
One can argue that a fair number of applications settle for x8 PCIe (64 gbit/s) to get to SLI, but even then you are ahead of thunderbolt 3 and you also have a second GPU.
Additionally, serdes and en