- Mar 3, 2017
- 1,747
- 6,598
- 136
It’s was 3200ish. Strix may score around 3300-3400 at 5.1GHzHamoa published 1t GB6 was like 3k+ so yea? Not far off.
That was Linux but yeah, that's where it should sit.It’s was 3200ish. Strix may score around 3300-3400 at 5.1GHz
Since they indicated responsiveness it would be 1t and the end note is a typo.No need to bet, we have AMD on the record showing us just a 5% lead over X Elite in Surface 15". A pity they messed up the end note so we don't know if it's ST or MT score.
View attachment 100710
View attachment 100711
This is a good score, ~3.5K@5.1G, on Linux it will be good, add ~5% on top.Comparison between 3.65Ghz avg Strix and ~5Ghz avg Hawk Point.
Both 6.3 and W11. Make of it what you will.
Why you want em, if you are talking about normal TS, its CPU test is artificially capped at 16 threads and it's long a test of RAM performance rather than CPUNow, onto the timespy scores.
No, the graphics score.Why you want em, if you are talking about normal TS, its CPU test is artificially capped at 16 threads and it's long a test of RAM performance rather than CPU
Hot damn, right where I thought it would be (well, 3.5).Strix matches Phoenix/Hawk at 3.6G
16% is fine for nT IPC.When people need to remember is zen4 to zen5 is two coves worth of additional resources 16 points of IPC would be bad.....
If I had to guess I would agree. Still, accurate labeling would be reassuring.Since they indicated responsiveness it would be 1t and the end note is a typo.
Agree , with no power increase and in some cases decrease , but I'm a gamer16% is fine for nT IPC.
Yea, this seems like a good take. Family 1Ah frequency reporting was reporting nonsense and it was recently patched for Linux. Hybrid designs are tough.Now I wonder what would it means if GB detect StrixPoint as 3.6-4.2Ghz CPU with those leaked score.
I will not comment on the how optimistic or not the scores are, but Zen4c/Zen5c is not really a hybrid core as far as the OS is concerned. It is fully ISA equivalent to the non compact core.Yea, this seems like a good take. Family 1Ah frequency reporting was reporting nonsense and it was recently patched for Linux. Hybrid designs are tough.
There’s 33% more cores and 100MHz clock increase in the 890M.
Is it being choked by the limited cache?There’s 33% more cores and 100MHz clock increase in the 890M.
I'm not sure I understand any of these points. Let's go through them and sort of see where we stand.Price determines how many cores someone buys compared to absolute specs. If it cost as much to buy a brand new 8c cpu vs a 16c one, a lot of people would indeed prefer core count over a small amount of 1t gain.
This is literally a myth and for 99% of people running multi-core workloads or just trying to multi-task, the already high bandwidth of DDR5 is more than enough.
Its not like we see crazy performance gains with hyper-tuned memory outside of a few workloads. Reducing pressure on memory doesn't do that much. As such we see that customers would much rather buy V-cache CPUs that negate memory bottlenecks instead of spending 3x more than they would otherwise on super fancy ram that might not even be perfectly stable at desired speeds and timings.
Ultra high end ram tuning is even more niche than overclocking CPU/GPU. More cores would give significant gains across many workloads meanwhile ram tuning is basically only good for gaming and very niche and uncommon workloads.
I think it's even worse than that, they're not even a tiny minority that "wants it", they're a tiny minority that knows that AMD grew big when they offered more cores for cheap and just stupidly assume that "if they kept doing it they'd win again".It's a vey vocal and very, very tiny minority who wants the increase in core counts on the consumer platform.
It's wrong.(frequency)
ASUSTeK COMPUTER INC. ASUS TUF Gaming A14 FA401WV - Geekbench
Benchmark results for an ASUSTeK COMPUTER INC. ASUS TUF Gaming A14 FA401WV with an AMD Eng Sample: 100-000000994-37_Y processor.browser.geekbench.com
View attachment 100723
Yeah. It’s just fanobyism. Same thing happened with Intel, people for years said 4 cores is all you need. Then Zen came out and suddenly 8, 12, 16 cores became desired.
After 16 and Zen 2, the only higher core parts are thousands of dollars, nevermind more expensive mobos.
Same thing for higher bandwidth. We’ve been stuck on dual channel forever.
AMD, it turns out, likes to make money just as much as Intel and Nvidia
It's a compute test, IIRC it should not be BW limited and theoretically it matches with the +33% units and max boost increaseIs it being choked by the limited cache?
I think it's even worse than that, they're not even a tiny minority that "wants it", they're a tiny minority that knows that AMD grew big when they offered more cores for cheap and just stupidly assume that "if they kept doing it they'd win again".
Dividing your total workload in chunks smaller than 6.25% is already done by almost no programs. Including games. Already with 8 cores your ideal breakdown should have your biggest workload be smaller than 12.5% of your total workload, and almost no games manage this. If any at all.
Honestly, I am thinking that at this point, before we get any meaning to extra cores, we'll need a new pattern/language/compiler/profiler that allows automated or greatly simplified threading.
Luckily for AMD, I always have specific bottlenecks I want addressing.