201–210 of 234 posts
I have an M1 Max. If anyone wants me to benchmark any workflows, I'd be glad to help!
Do you have two 4k displays? If yes, then does running them affects performance significantly? On i9 MBP this was causing extremely severe performance issues, to the point where processor was throttled to 30% performance.
I have an M1 Max. If anyone wants me to benchmark any workflows, I'd be glad to help!
I'm having a hard time finding mips/flops for the M1 CPU, can you measure one of them?
Its mathematical prototype is the simple, classic, vivid, and widely used in social production practice, elementary school mathematics "water input/output of the pool", Therefore, it is scientific.
The "von Neumann architecture" used by computers now has no mathematical model support. So it cannot prove its scientificity.
My theory rebuilt the theoretical foundation of the IT industry, The IT industry is fundamentally associated with mathematics. Solved the most fundamental and core major problems in the IT industry.
Therefore, my "warehouse/workshop model" will surely replace the "von Neumann architecture" and become the first architecture in the computer field, and it is the first architecture to achieve a unified software and hardware.
Software and hardware are factories that manufacture data, so they have the same "warehouse/workshop model" and management methods as the manufacturing industry.
In the IT field, only it and binary system fully comply with these 5 aesthetics: Simplicity, Unity, order, symmetry and definiteness.
It has a wide range of applications, from SOC to supercomputer, from software to hardware, from stand-alone to network, from application layer to system layer, from single thread to distributed, from general programming to explainable AI, from manufacturing industry to IT industry, from energy to finance, from the missile's "Fire-and-Forget" technology to Boeing aircraft pulse production line technology, from myth to Transformers.
Link:
The Grand Unified Programming Theory: The Pure Function Pipeline Data Flow with Principle-based Warehouse/Workshop Model
https://github.com/linpengcheng/PurefunctionPipelineDataflow
Why my "warehouse/workshop model" can achieve high performance and low power consumption (take Apple M1 chip, Intel AVX-512, Qualcomm as examples):
https://github.com/linpengcheng/PurefunctionPipelineDataflow...
Earlier quoted context omitted.
Rather than switching hardware, you can also switch out the software to more efficient one. esbuild would make your builds go sub-ms even without needing a M1 CPU, also worth a try if you cannot switch to the newest hardware, so I guess this comment is for poor people.
Why not both? I can honestly say that I didn't know how bad the 2019 MBP Intel CPUs are until I tried a M1. It's streets ahead. I don't think people will be moving away from webpack for awhile, but transpilation is often a very expensive part, and `swc` is very near to stable, and as a transpiler / polyfilling tool it's pretty fast.
Earlier quoted context omitted.
That ram is no longer a commodity ram sticks, can’t compare prices directly
Good point. The ram is cheaper for them because they aren't buying the dimms, just the silicon.
Earlier quoted context omitted.
>a rebirth of the G4 Cube as a “Mac Mini Pro” That will be one of those shut up and take my money moment. Given how they have been going retro or paying tribute to past design in their recent new product lineup I am hoping a G4 Cube revival is actually within a possibility.
Apple has been on a weird spree of ”hey what if we listened to our customers”. Maybe they’ll add in the ”normal” desktop computer. The iMac comes with a screen I don’t want (+weird laptop-like compromises for thinness), the mac mini is too small for actual HP, and the mac pro cost a ton
Replicating the capabilities of the Mac Pro with would require another model of M1 and for the volumes the Mac Pro sells I do not believe developing a dedicated lithography mask makes sense. Besides, most of the unique capabilities of the Mac Pro are divergent with vision of the M1:
- PCIe slots, there are no GPUs compatible with Arm Mac and some of the functionality of the Afterburner card has been integrated into the M1 Max
- Lots of RAM, as seen with the lower RAM models of Mac Book (Air) Apple is increasingly relying on swapping to the fast SSD.
Earlier quoted context omitted.
Can you help me understand what that means? Is it not possible to run it at the "full" resolution? Will it be scaled to what equates to the 1800x1169 that you mention? That would equate to less "real estate" than what I have on my T460s FHD screen? Of course the screen would be light years ahead to look at. But just sounds a little bit strange with regards to actual pixels/space on the screen?
> Can you help me understand what that means? Is it not possible to run it at the "full" resolution? Will it be scaled to what equates to the 1800x1169 that you mention? Yes, Apple doesn't provide for running at the native resolution out of the box (utilities like SwitchResX make those options available, though I don't know if they work with the M1s yet), all the display modes they propose are scaled. Historically th…
Earlier quoted context omitted.
Do you have one of the M1 Pros? Mine very much does gets hot and I can definitely hear the fans when I'm building a project, but both fronts are certainly improved vs the Intel Macs. Honestly, it gets about as hot and as loud as the Intel version, just far less frequently.
Huh, I made a comment about this issue just the other day ( https://news.ycombinator.com/item?id=28988835 ) and had 5 commentators telling me that it has now been fixed, almost made me order a M1. But now you're saying it actually still runs as hot as before?
Earlier quoted context omitted.
~100G fp32 FMA/s per core on my M1 air last I checked.
Is that CPU or GPU? Sounds a bit high when 2Gflops/watt (but I guess at 40W for all cores =2,5Gflops/W it could make sense?!) is the industry standard! Can you turn off the acceleration to get CPU only figures? What is FMA/s? Edit: Ok that is some sort of SIMD/GPU... I need figures for the raw CPU that can also do general purpose calculations and branches! Maybe MIPS is a better "apples to apples" measurement?
I just ran it on CPU, single core (no pinning), just using the aarch64 fmla instruction.
Using pure BLAS (multithreaded, with the MM ISA extension), I get like 1.2TFlops in fp32 on the whole device. Code for the blas test: https://jott.live/code/blas_test.cc
Earlier quoted context omitted.
~100G fp32 FMA/s per core on my M1 air last I checked.
Is that CPU or GPU? Sounds a bit high when 2Gflops/watt (but I guess at 40W for all cores =2,5Gflops/W it could make sense?!) is the industry standard! Can you turn off the acceleration to get CPU only figures? What is FMA/s? Edit: Ok that is some sort of SIMD/GPU... I need figures for the raw CPU that can also do general purpose calculations and branches! Maybe MIPS is a better "apples to apples" measurement?