I agree, and it's pretty similar to the view from DF when they reviewed 3700X, ( 24:15 )
Except for some very high fps requirements like in e-sports, you're not as concerned with the CPU performance except for some very rare drops( < 0.01% ) here and there. He calls them hotspots in the video.
These can be highly irritating, especially when you're playing a single player game and have to pass through the same areas again and again. A very good example is Swan's Pond in Fallout 4 where the fps dropped precipitously and you really needed a good CPU to keep it up.
In a typical review, even if you were doing it at 360p, you wouldn't see this issue since most of the time your benchmark run wouldn't stop there and explore the area but most likely tangentially touch it, if at all. But when actually playing the game, you'd tear your hair out.
I remember that guy FrameChasers during 30xx series announcement, he was quick to point out that 2080Ti overclocked rather well and trying out Doom comparison. Glad to see he's putting out this kind of content
I use handbrake all the time to transcode my smartphone videos into a codec that is watchable on my TV, and to transcode older videos on H264 or older into H265 to save storage.To me its like WTF do they always benchmark handbrake etc its like how many ppl are actually using this software in their jobs? they should be benchmark compiling, theres millions of ppl around the world alone who spends hours per week waiting on compiling to finish
My next gaming system will most likely be equipped with a Intel cpu, very impressive what they have achieved after years of trailing behind amd and apple.
https://publish.twitter.com/?query=https://twitter.com/AhsanQu89750398/status/1456982596198576129&widget=Tweet
Intel transitioning to 7 or even 5nm is going to be very intresting. Thanks competition (amd)
In particular, don't use 30W for M1 when it perhaps consumes less when running Geekbench.Interesting. Would be cool to see a site really dig into that. Equalize power and benchmark across multiple applications.
Interesting. Would be cool to see a site really dig into that. Equalize power and benchmark across multiple applications.
Cinebench is really not that great of a benchmark for M1
Not yet. A fine B550 board is $80 ($60 low end) while Z690 > $200 USD.Even with price cuts, the 12600K is cheaper($369 CAD) here than the Ryzen 5800X ($499 CAD down from $619 CAD). I know the motherboards for 12 series are expensive, but wouldn't be surprised if the Intel build came out cheaper with DDR4.
Do some NVENC and QuickSync comparisons against the new hotness CPU cores while they're at it
IIRC most PC gamers play like 8 hours a week on their PCs, yet there's always a lot of videogame benchmarks in CPU reviews.Sure Ive used handbrake as well, but what I mean very few ppl are using it fulltime 40 hours a week like millions of coders around the world are
SPEC CPU is supposed to be representative of several CPU bound workloads. Of course it's lacking in some areas (for instance code size is too small, no JIT, etc.), but it's quite good to get a good idea of CPU performance.Point being: reviewers can't really satisfy everyone. At least for GPUs there's SPECViewPerf but even that is far from an ideal pool of results.
As some have mentioned (LTT i think too), you choose the benchmarks that fits your product and workload. Not just cinebench 'isnt that good' on M1, i have seen other comparisons where the M1 max lost to windows based hardware. One of them was exporting video's (windows laptop hw).
Developer-Ecosystem-Engineering
Have some changes ready, working on reviews and rebasing, will update the PR when completed.