It's no different from trying to figure out how the whole Intel platform would work out just from one of these.
Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
RIP OS X/macOS 10
- Thread starter timidpimpin
- Start date
- Sort by reaction score
It's no different from trying to figure out how the whole Intel platform would work out just from one of these.
Not a single Mac shipped with anything close to this. And the Core Duo and later Core 2 Duo Macs blew this thing out of the water. Everyone needs to calm down and stop saying the Mac is doomed and it’s the end of the world because a piece of test hardware isn’t performing as good as a finalized product.
Correct. My 3,1 mini scored about 2600 in geekbench 4, but in 5 I only get about 550. MUCH different score.
This is actually why I'll only use Geekbench 2 when benching something (given that this was the last release compatible on PowerPC).
That way, I've got a solid idea of any given machine's real performance ability directly relative to a whole range of different hardware.
Last edited:
That's probably like asking whether Xbench scores are reliable full stop. It's a fun thing to look at but I wouldn't stake my life on them.
Version 2 is. Any system that can run it is running the same code and instructions. But I would say Cinebench has always been the best and most consistent CPU benchmark, but only very outdated versions run on PowerPC.
When and if I trade up my 2015 Macbook Pro for an ARM macbook pro - going to get a sticker saying: PowerPC inside.
You seem very emphatic on this point.
You might be interested to know that the usual PowerPC logo + stickers from the time period usually only said 'PowerPC'. The 'inside' slogan was an Intel thing.
(As far as extra identifiers go, I always felt the Apple logo spoke for itself. It was helpful when 68k machines were still in circulation, though.)
Last edited:
You think of something like this ...?
[automerge]1593558595[/automerge]
"Increase Contrast" in addition to "Reduce Transparency" are also my favorite settings for MojavePatch in DarkMode - especially in daylight conditions.
Last edited:
You seem very empathic on this point.
You might be interested to know that the usual PowerPC logo + stickers from the time period usually only said 'PowerPC'. The 'inside' slogan was an Intel thing.
(As far as extra identifiers go, I always felt the Apple logo spoke for itself. It was helpful when 68k machines were still in circulation, though.)
ok, maybe without the inside, as I vehemently hate intel, esp Otellini.
You think of something like this ...?
"Proudly Powered by PowerPC"
[automerge]1593592555[/automerge]
Ah yeah, Dark Mode is actually still decent with these two enabled. Still enjoying the 17-incher I see.
Getting back to the complexity of synthetic benchmarking, I decided to do a little apple to apple, and apple to orange comparison.
Yeah, in Geekbench 2, my rather nice Rizen system just walks all over that poor old G5, though surprisingly not all the single core scores are by as high as I was expecting.
Where as:
The same Ryzen system doesn't score so well in Geekbench 5. Doing some looking around, an iPad Pro can score something in that ballpark, as seen here:
I don't have one of these, but they've been tested all the same.
My takeaway is that ARM Macs, especially with native code, should be quite quick, assuming they can scale this up, and I have no reason to think they won't be able to. It's also a little humbling to see the single core score of an Ipad Pro beat that of my new desktop pc. So, there definitely are things we can learn from all of this.
Yeah, in Geekbench 2, my rather nice Rizen system just walks all over that poor old G5, though surprisingly not all the single core scores are by as high as I was expecting.
Where as:
The same Ryzen system doesn't score so well in Geekbench 5. Doing some looking around, an iPad Pro can score something in that ballpark, as seen here:
I don't have one of these, but they've been tested all the same.
So, when we look at these scores, we have to remember that we are comparing a lot of things that are and are not the same. The Geekbench 2 scores are at least somewhat meaningfully similar, and so are the Geekbench 5 scores. Given that we know that the ARM dev hardware basically is an iPad Pro, that's where things get interesting. We can, in fact, get a vague idea of how Geekbench 5 does when put through Rosetta 2, at the very least.
While the terms and conditions for Apple's new "Developer Transition Kit" forbid developers from running benchmarks on the modified Mac mini with an A12Z chip, it appears that results are beginning to surface anyhow.
Geekbench results uploaded so far suggest that the A12Z-based Mac mini has average single-core and multi-core scores of 811 and 2,781 respectively. Keep in mind that Geekbench is running through Apple's translation layer Rosetta 2, so an impact on performance is to be expected. Apple also appears to be slightly underclocking the A12Z chip in the Mac mini to 2.4GHz versus nearly 2.5GHz in the latest iPad Pro models.
It's also worth noting that Rosetta 2 appears to only use the A12Z chip's four "performance" cores and not its four "efficiency" cores.
By comparison, iPad Pro models with the A12Z chip have average single-core and multi-core scores of 1,118 and 4,625 respectively. This is native performance, of course, based on Arm architecture.
Article Link: Rosetta 2 Benchmarks Surface From Mac Mini With A12Z Chip
My takeaway is that ARM Macs, especially with native code, should be quite quick, assuming they can scale this up, and I have no reason to think they won't be able to. It's also a little humbling to see the single core score of an Ipad Pro beat that of my new desktop pc. So, there definitely are things we can learn from all of this.
The iPad pro has a pretty much identical chip to the developer mini, but the mini is only using half the cores (4 of 8). Taking that into account, the iPad only has about a 50% higher score using all 8 cores, and native ARM code. But I imagine that could have something to do with power conservation, since it's a tablet.
Yes, all else being equal, I expect even a Mini sized case for an A12 can handle a LOT more heat than the iPad.
And unlike the iPad, the mini could use a cooling fan. Unless Apple are going for a fanless design...
I could see that one going either way.
On one hand, we've seen what the A12 series is capable of in a passively cooled case. In addition to that, we know how Apple is(and Steve Jobs) was about fanless computers, from the original Macintosh, to the iMac G3, G4 Cube, and most recently the MacBook. Of course, of those the iMac G3 is the only one I'd consider being overly successful. The Macintosh had a reputation for cooking analog boards, and there were a lot of aftermarket internal fans as well as externals like the Kensington System Saver. The Cube was okay-ish in stock form, but ran out of cooling capacity over 500mhz and/or anything beyond the Rage 128(the Cube optional Geforce 2MX had a massive heatsink, but I've never handled a real "Cube edition" of that). All of my Cubes-even the stock-ish ones-have base fans in the fan brackets that Apple put there but never used. My high clocked aftermarket upgrades(1.5ghz and 1.8ghz) have fans that were included in the kit. The MacBook would throttle pretty seriously under even moderate use.
On the other hand, putting a fan in could theoretically unlock a LOT of potential.
What I could see happening is the lower end laptops-the Air and maybe a resurrected MacBook-going fanless and maybe also the Mini(it would be interesting to know if the DTK has one). The iMac, whatever the MacBook Pro ends up being called, and the eventual Mac Pro, having fans. They may be set with an even milder temperature profile than current Intel models, such that they only kick on(or spin fast) if you really start beating on them. It could end up being something like the eMac or iMac G4, where the fan basically doesn't run in normal operation, but when they do kick on you think an airplane is about to land in your front yard.
Both the eMac and iMac G4 case fans remain at one speed throughout operation.
Too loud in the case of the iLamp. Probably why Apple added the Apple Pro speaker port to those. Gotta drown out that background drone.