News Apples New M1 Processor Demolishes the 2019 iMac with 8th Gen Core i5 6-core CPU

Joseph_138

Reputable
Nov 22, 2016
115
17
4,585
0
Being faster than a chip that is almost three generations old and no longer in production is a meaningless comparison. 8th generation i5's also didn't have hyperthreading, yet, so comparing it to a processor that presumably does use some form of multi-threading is not a balanced test. The testing also targets a mid range i5, not a top of the line i9, making it even more meaningless because power users, whether they be using a computer for business or for gaming, will gravitate closer to the higher end of the CPU stack. I would like to see this chip tested against a 10th gen i9, then it will show how weak this processor really is.
 
Nov 13, 2020
1
1
15
0
Like the first commenter, let's not compare this to a 2 generation old CPU. This should be compared to 10th/11th generation. We are hardware enthusiasts here not apple fanboys. Also let's point out the obvious, every new piece hardware is going to demolish its predecessor; that's a given
 
Reactions: thisisaname

nofanneeded

Respectable
Sep 29, 2019
1,562
250
2,090
15
I have the feeling that Apple is cheating using hardware codes inside their chip that can fool specific benchmarking tools..

Also , there is no way to to test their chip with neutral software yet ...
 

spongiemaster

Commendable
Dec 12, 2019
796
362
1,260
0
i9-10900, 32GB RAM, GeForce RTX 2070 Super
vector single cpu 301
vector multi cpu 1878
raster multi cpu 775
raster single gpu 8950



more info here - affinity photo benchmark results page
According to the article, an i5-8500 with a single core boost of 4.1Ghz scored 310 in the Vector Single CPU test. Your post shows a 10900 that has a single core boost of 5.2Ghz scored a 301 in the same test which is 3% slower than the 8500. i5 -8500 is a 6 core/6 thread 3.9Ghz all core turbo (1515 multi cpu score). 10900 is a 10 core/ 20 thread 4.6Ghz all core boost (1878 multi cpu score). Either the 8500 tested too fast, or the 10900 tested slow, but they can't both be right.
 
Nov 14, 2020
2
3
15
0
Comparing what is most likely a dedicated coprocessor inside their new silicon (heavily optimized for one particular task) to a general purpose CPU is not exactly an apples to apples comparison, not even if it is Apple vs Apple :p

This reminds me a lot to the hype around "GPU accelerated" software which AMD promoted in the past around their APUs. There was a real potential for superior performance but it was totally linked to software being written specifically for it, which ultimately nobody did. As soon as they have been able, AMD has proudly gone back to promoting a high performance CPU design.

In this case, however, Apple controls the SW development on iOS so I admit they could be able to generate some superior tools combining their HW & SW skills. Be sure that they will command a price premium for that, maybe this time they are entitled to it.

Apple marketing department at its best. It seems that the reality distortion field has been activated again.
 
Comparing what is most likely a dedicated coprocessor inside their new silicon (heavily optimized for one particular task) to a general purpose CPU is not exactly an apples to apples comparison, not even if it is Apple vs Apple :p
And it doesn't need to be.
Photo Editing is a major market for apple sales and how fast a new apple product is in this specialized field will determine how desirable it will be for that market,they don't care how the computer does it as long as it does it, if this is a software suit that people use on mac that is.
 
Nov 14, 2020
2
3
15
0
True, it is only the sensationalistic title of the article which pisses me off a bit.
I agree that the product development strategy likely makes sense.
 

Spanky Deluxe

Distinguished
Mar 24, 2009
508
0
18,980
0
These results and the Geekbench comparisons are incredibly exciting. That a passively cooled ultraportable laptop can outperform a desktop cpu from two generations ago (where there’s been very little per generation improvements) is really impressive. The Geekbench results appear to show the M1 to be faster than all other current macs in single threaded stuff. That’s insane. I can’t wait to see what Apple come up with when they release actual desktop chips.

This whole thing reminds me a lot of the Pentium-M days, where a new mobile CPU ended up completely changing the CPU market. It was a really exciting time.
 
And it doesn't need to be.
Photo Editing is a major market for apple sales and how fast a new apple product is in this specialized field will determine how desirable it will be for that market,they don't care how the computer does it as long as it does it, if this is a software suit that people use on mac that is.
And linux features put linux where it is. But niche features, it kept it niche. Apple will be nothing more than niche, even behind linux. (Which i love for internet devices and security)
 

nofanneeded

Respectable
Sep 29, 2019
1,562
250
2,090
15
These results and the Geekbench comparisons are incredibly exciting. That a passively cooled ultraportable laptop can outperform a desktop cpu from two generations ago (where there’s been very little per generation improvements) is really impressive. The Geekbench results appear to show the M1 to be faster than all other current macs in single threaded stuff. That’s insane. I can’t wait to see what Apple come up with when they release actual desktop chips.

This whole thing reminds me a lot of the Pentium-M days, where a new mobile CPU ended up completely changing the CPU market. It was a really exciting time.
I doubt it is faster in other applications.
 

JarredWaltonGPU

Senior GPU Editor
Editor
Feb 21, 2020
694
563
1,270
1
According to the article, an i5-8500 with a single core boost of 4.1Ghz scored 310 in the Vector Single CPU test. Your post shows a 10900 that has a single core boost of 5.2Ghz scored a 301 in the same test which is 3% slower than the 8500. i5 -8500 is a 6 core/6 thread 3.9Ghz all core turbo (1515 multi cpu score). 10900 is a 10 core/ 20 thread 4.6Ghz all core boost (1878 multi cpu score). Either the 8500 tested too fast, or the 10900 tested slow, but they can't both be right.
Sure they can, because one of them (the i5 iMac) was tested under OSX. There's a reason we have the caveat paragraph at the end. Tons of unknowns, lots of potential for "fake benchmarks". On the other hand, a desktop iMac against a laptop is a pretty generous comparison for Intel. 8th Gen desktop vs. M1 laptop. One is a 65W chip, one is a 15W (?) chip. And we all know Intel's desktop architecture for 6th, 7th, 8th, 9th, and 10th Gen chips hasn't changed -- it just got a few more cores and some higher clocks over time, with higher power draw.

The real comparisons will be in apps people actually run on the new MacBook, which will probably do quite well overall after optimizations and such come into play. That's one area where Apple's control over both the hardware and OS stack really helps.
 

spongiemaster

Commendable
Dec 12, 2019
796
362
1,260
0
Sure they can, because one of them (the i5 iMac) was tested under OSX. There's a reason we have the caveat paragraph at the end. Tons of unknowns, lots of potential for "fake benchmarks".
You can get a 10900 (or maybe a 10910) in a Mac. What would be the point of trying to compare the performance of CPU's that can run under the same OS, but aren't test under those conditions? Adding over a GHz to the clock speed to basically the same architecture should not result in slower performance.
On the other hand, a desktop iMac against a laptop is a pretty generous comparison for Intel. 8th Gen desktop vs. M1 laptop. One is a 65W chip, one is a 15W (?) chip. And we all know Intel's desktop architecture for 6th, 7th, 8th, 9th, and 10th Gen chips hasn't changed -- it just got a few more cores and some higher clocks over time, with higher power draw.
Is it really that generous? Intel's own 15w Tiger Lake will handily beat a 2 1/2 year old i5-8500 in single core performance.
The real comparisons will be in apps people actually run on the new MacBook, which will probably do quite well overall after optimizations and such come into play. That's one area where Apple's control over both the hardware and OS stack really helps.
Absolutely. The only results that matter are how the new Macs compare to the old Macs running the same software. Apple is really trying to lock in the ecosystem and that will certainly pay dividends for fine grained platform optimizations. It's almost like Apple is building their own console.
 

ASK THE COMMUNITY

TRENDING THREADS