News for hackers. Stuff that matters.

A comment on System76 Developing “Cosmic” Desktop Environment. Parent comment

Re:System76 Developing “Cosmic” Desktop Environment by coldtea on Tuesday April 13, 2021 @07:48PM (#26801145)
Is it? I see Geenbench gives the M1 as having 1733 (single) and 7652 (multi) GeekBench score, whereas a AMD Ryzen 7 Pro 5850U system has 1414 (single) and 8140 (multi), so the M1 is quite faster in single core than it (22%) and slower but close in multi-core (the AMD being 6% faster).

And that's with the M1 having 4 slow cores for better battery life / consumption (with 8 full speed cores it would obliterate the 5850U).

[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by commoner on Tuesday April 13, 2021 @08:19PM (#26801433)
They're using PassMark instead of Geekbench.

https://www.cpubenchmark.net/compare/Apple-M1-8-Core-3200-MH...

Apple M1 - CPU Mark: 14,872 / Single thread: 3,630

AMD Ryzen 7 Pro 5850U - CPU Mark: 20,659 / Single thread: 3,237

The AMD is 38.9% faster on the multi-core benchmark, and 10.8% slower on the single-core benchmark.

[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by jolux on Wednesday April 14, 2021 @12:11AM (#26802850)
That's not really surprising, is it? The M1's eight cores are in a big.LITTLE configuration, half of them are not as powerful as the other half.
[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by skohan on Wednesday April 14, 2021 @07:45AM (#26805731)
Also the Ryzen has hyperthreading where M1 doesn’t no?
[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by the_lucifer on Wednesday April 14, 2021 @12:41PM (#26809552)
Yes, M1 doesn’t have hyper threading
[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by coldtea on Wednesday April 14, 2021 @02:33AM (#26803678)
OK, so is PassMark more accurate than Geekbench?

(And, still, that's with M1 having 4 cores tied behind its back for better battery life).

[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by devwastaken on Wednesday April 14, 2021 @02:53AM (#26803816)
Neither bench reflects real world performance. Run cinebench, 7zip, h265 encode, blender render, etc.
[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by sjwright on Wednesday April 14, 2021 @06:19AM (#26805079)
Unless your primary workload is media encoding or rendering in Blender, those benchmarks are just as artificial as the truly artificial ones.

Most people’s performance workload is dominated by media consumption—not media creation. But the latter sure does make for good benchmarks.

[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by kllrnohj on Wednesday April 14, 2021 @08:18AM (#26806048)
> And that's with the M1 having 4 slow cores for better battery life / consumption (with 8 full speed cores it would obliterate the 5850U).

It's not really that simple. An M1 with 8 full speed cores would also consume significantly more power and would no longer work in something like the MacBook Air. On paper these CPUs are both targeting the same power budget, so if AMD can put 8 full-speed CPUs in the same power budget that Apple can "only" put 4 full-speed and 4 low-power then why shouldn't AMD get a win from that?

[ Parent | on HN ]
Re:System76 Developing “Cosmic” Desktop Environment by mushufasa on Wednesday April 14, 2021 @06:17PM (#26813783)
The M1 laptops get much longer battery life than the AMD laptops, and the difference is not due to the size of the battery.
[ Parent | on HN ]