To be honest I’m not surprised. The pain in the ass is a quite fairly common human affliction.
And yet the pace of progress in the x86 design has significantly increased since AMD forced Intel to really ramp up on its R&D. Early rumors suggest that Zen4 will be another sizable leap in computing power, even larger than Zen3 compared to Zen2.
I do not see anything that would cause different CPU core types to be an exclusive feature for the Mac (that being if there is enough demand). I do not think Apple could even lock such a potentially broad category behind a patent to make it that way.
What’s interesting about Anandtech’s tests is that they use tasks designed to test high-performance servers. It turns out that claims that ARM can’t compare to x86 in this regard because “ARM isn’t made for heavy workloads” is just plain nonsense. Importantly, Apple co-processors are not used in these tests.
1 Like
Well heat production and power consumption are issues they are dealing with.
I should have written my text better stating also to consider the power consumption.
But still the CPU and GPU are being beefed up to the max yet the highway between them is a remaining bottleneck too.
1 Like
Also : finally
Native photogrammetry that is fine with rotating an object and auto stitching the scans…
2 Likes
So why you contested my negative appreciation of Anandtech untruthful phrase quoted here?
They even base their affirmation only in SPEC2017. It is ridiculous.
In strategic terms Mac has a vast advantage on power drawn that is a big jump, here all glowing articles appear truthful - it is basically ARM energy advantages transported to personal computer size level. But do not have advantage in performance, but i think they might get it in next versions if PC do not take a sizable jump also.
Since the PC line will not go unified memory , they will have to get improvements by their competing different brains. Currently we have different RAM for CPU and another more performing for GPU if they get the same then might be possible for both sides to pool it.
I am afraid you are misinformed, many servers are ARM. Nvidia one for example
The NVIDIA Grace CPU leverages the flexibility of the Arm® architecture to create a CPU and server architecture designed from the ground up for accelerated computing. This innovative design will deliver up to 30X higher aggregate bandwidth compared to today’s fastest servers and up to 10X higher performance for applications running terabytes of data. NVIDIA Grace is designed to enable scientists and researchers to train the world’s largest models to solve the most complex problems.
I’m afraid you didn’t read carefully what I wrote.
Reading through this thread really warms my heart. It feels like the old days, when Mac and PC people would openly fight in the streets.
I was a PC guy back then. Spilled much blood in the fight against our most hated enemy. But I’m older now. Wiser. Some may see my ensuing switch as a betrayal of everything I once stood for.
To them, I say “…nay. PCs are totally lame.”
6 Likes
Hehe same, welcome to the darkside 
1 Like
I don’t think so, you need Mac M1 to prove that ARM can do heavy workload when several companies have ARM in servers - even Microsoft build ARM - the fastest computer in world is ARM+GPU. https://en.wikipedia.org/wiki/Fugaku_(supercomputer)
I only had a rebuttal for your comment against what you quoted. Maybe you only quoted a small portion of what you meant to disprove?
Your Anandtech quote read,
Anandtech:
„The chips here aren’t only able to outclass any competitor laptop design, but also competes against the best desktop systems out there, you’d have to bring out server-class hardware to get ahead of the M1 Max – it’s just generally absurd.”
Which you said was a lie.
I only replied that it is not. These M1 chips are beating high-end desktop machines in certain apps and with certain task.
Nothing more nothing less.
I do say the wording is vague and could lend to non-techies as meaning all task. 
we both are from that time - lets say:
To the non-believers zip it shut 
2 Likes
I found this goodie in the Anandtech article. Please be something that render engines need 
“The performance differences here are just insane, and really showcase just how far ahead Apple’s memory subsystem is in its ability to allow the CPUs to scale to such degree in memory-bound workloads.”
1 Like
The GPU naturally comes to mind, however in my testing, I’ve had extreme trouble to find workloads that would stress the GPU sufficiently to take advantage of the available bandwidth. Granted, this is also an issue of lacking workloads, but for actual 3D rendering and benchmarks, I haven’t seen the GPU use more than 90GB/s (measured via system performance counters). While I’m sure there’s some productivity workload out there where the GPU is able to stretch its legs, we haven’t been able to identify them yet.
1 Like
Do be aware that Optix often halves rendertime for RTX cards, I don’t expect mac to render faster. The addtional vram and ST performance should be relevent in constructing gigantic scenes. Viewport performance is also of interest. Hopefully this will light a fire under the competitors. I don’t see myself moving my entire workflow to mac just for this, however.
2 Likes
Well they not outclass my medium class laptop in 2 of most relevant content creation benchmarks usually presented. So there is no justification for the absolutism in that phrase which i criticized.
Is there any scene in other Blender demos that can push for more memory bandwidth than the BMW27?
Is there anyone here that will get one of these Mac soon?
In Premiere Pro
Another software that i am expecting benchmarks is Blackmagic Resolve.
Metal cycle coming next year?
1 Like
Yes, with Blender 3.1.