Apple announces new Mac Mini, Air + 13" MBP featuring their own M1 chip.

[Markus Krause]

For VST plugins an AMD Ryzen 5800x or an Intel I9 is at least 10 times faster than the I3

[Etienne1973]

History seems repeating. Intel Pentium IV vs Apple Power PC (Motorola/IBM). Clock Speed vs Altivec.

[RugerioDelStereo]

Looks great, but I'm gonna wait. I have a 2017 Macbook Pro, i5 3.1 Dual Core Intel with 16GB RAM.Logic Pro X works amazing on it. No need for this yet.

[Passing Bye]

Gonna wait for benchmarks, if that Mini scores around 7-8k on Geekbench, it's mine.

[Passing Bye]

How would that i3 from 2018 compare to the i9 10900 or the i5 10600 (if I've got those names right)?

If you want rough numbers from Geekbench, that Mac Mini have around 3k score, i9 10900 ones are around 10k and i5 10600 are around 6k... Ryzen 9 5950X have same score as most expensive 28 core Xeon Mac Pro, which is around 18k... but that's just numbers.

[david.beholder]

How does geekbench translates to real daw/real plugins performance?
I'd like to see less synthetic tests.

Apple is famous for bold unsubstituted claims and meaningless high numbers in presentations

[andi75]

VST performance mainly depends on the floating point performance of the CPU. The Intel I7, the I9 and the Ryzen are very strong with it.
Apples M1 chipset is a RISC processor mainly used for tablets and smartphones. They are optimized for low power consumption.

IIRC, SPECfp is about floating point performance. Does not look too bad for the M1 then: https://www.anandtech.com/show/16226/ap ... eep-dive/4

[Passing Bye]

How does geekbench translates to real daw/real plugins performance. I'd like to see less synthetic tests.

SCAN is the best thing we have for that

http://www.scanproaudio.info/tag/benchmark/
http://www.scanproaudio.info/tag/dawbench/

[Etienne1973]

VST performance mainly depends on the floating point performance of the CPU. The Intel I7, the I9 and the Ryzen are very strong with it.
Apples M1 chipset is a RISC processor mainly used for tablets and smartphones. They are optimized for low power consumption.

IIRC, SPECfp is about floating point performance. Does not look too bad for the M1 then: https://www.anandtech.com/show/16226/ap ... eep-dive/4

... and that's only the A14. Let's see what the M1 architecture can do. On the other hand: Perhaps we have high hopes?

[Passing Bye]

VST performance mainly depends on the floating point performance of the CPU. The Intel I7, the I9 and the Ryzen are very strong with it.
Apples M1 chipset is a RISC processor mainly used for tablets and smartphones. They are optimized for low power consumption.

IIRC, SPECfp is about floating point performance. Does not look too bad for the M1 then: https://www.anandtech.com/show/16226/ap ... eep-dive/4

... and that's only the A14. Let's see what the M1 architecture can do. On the other hand: Perhaps we have high hopes?

I'm hoping it performs close to Ryzen 5 3600, but if it's anywhere like that to 5950x...

[Markus Krause]

VST performance mainly depends on the floating point performance of the CPU. The Intel I7, the I9 and the Ryzen are very strong with it.
Apples M1 chipset is a RISC processor mainly used for tablets and smartphones. They are optimized for low power consumption.

IIRC, SPECfp is about floating point performance. Does not look too bad for the M1 then: https://www.anandtech.com/show/16226/ap ... eep-dive/4

These benchmark results are garbage. They are not based on real measurements of the Mac mini:

We currently do not have Apple Silicon devices and likely won’t get our hands on them for another few weeks, but we do have the A14, and expect the new Mac chips to be strongly based on the microarchitecture we’re seeing employed in the iPhone designs. Of course, we’re still comparing a phone chip versus a high-end laptop and even a high-end desktop chip, but given the performance numbers, that’s also exactly the point we’re trying to make here, setting the stage as the bare minimum of what Apple could achieve with their new Apple Silicon Mac chips.

[andi75]

I cannot see how those results are garbage. They are measuring the A14, which is the baseline of the performance to be expected from the M1

[Markus Krause]

Those measurements were done with a different RAM, a different mainboard-chipset, a different OS and on a different device. That all also has significant impact on how fast a computer is.

[andi75]

You are right. Lets wait for real life benchmarks...

[george]

Not sure if these benchmarks are real but if true then M1 single core performance is way better than the i9 @ 3.6 GHz and slightly superior with multicore i9-9980HK @ 2.4 GHz (8 cores) from MacBook Pro (16-inch Late 2019).

https://www.cpu-monkey.com/en/compare_c ... ionic-1693

If Apple can manage to release M2 in a 1-2 years with another 50% performance bump then we will get massive performance improvements compared to Intel and the processor switch will be justified.