Jump to content
HWBOT Community Forums


  • Posts

  • Joined

  • Last visited

Everything posted by denvys5

  1. Looking at Intel information on new thread scheduling rules (Intel Thread Director), it makes most sense to do one single ranking for each cpu, by adding up cores. My previous point was based on expectation that cores have different instruction sets. With confirmation that 8E cores are running same instruction set (AVX2 enabled), just as other guys above suggested, 8P+8E = 16C makes the most sense.
  2. Same for me. I see res while logged in, but cant look at it from incognito. Pushing button "Hide this result" doesnt do anything.
  3. Question: do we have verification from Intel that P and E cores can do same workload in parallel? Or do they move workload, like on ARM bigLITTLE? #4 sounds reasonable. I would also add 0P+8E core configuration to that list. Why? Coz we might see 8P+64E cpus in near future, if this architecture succeeds. And that means little cores become competitive in MT benchmarks on their own. But, this all ranking split is possible only if core configuration can be verified for each individual submission. So 2D only benchmate subs, as far as I understand.
  4. So what ARE the rules on memory stages? Hardware sharing allowed, but RAM sharing no-no? Or no hardware sharing at all, like all other stages?
  5. Gj beating my 1T score. Looking at clocks, you were really desperate. But smth with your "Effective clock" is not right.
  6. HCI Memtest keeps looping, yes. None of the functionality I have described earlier is present in HCI Memtest itself. It only provides API for this stuff. This allows to design a software solution that would be an actual benchmark (by configuring its setup, performing time-tracking and stopping the process at a defined progress target). I am sorry if I have confused you. There are custom benchmark launchers present on hwbot (e.g. 7zip or y-cruncher), that is why I suggested such idea.
  7. We can define rules, e.g. 6Gb memory for a target of 240% memtest completion with number of threads equal to number of CPU threads. And rank results on the completion time of set target, differentiating them by DIMM type (e.g. DDR4) and, maybe for competitive purposes, number of memory channels that platform supports. As a result, we would get a competition system, there certain memory configurations pass this memtest faster, by being actually faster in reading, writing and latency-wise (the idea comes from existing one in RyzenDramCalc) We already have CPU benchmarks, that depend a lot on mem size and/or rank configuration (e.g. GeekBench, y-cruncher). There is some impact from CPU cores/clocks and cache size/clocks, but it is unknown how much does it matter and it can be tested (clearly, memtest is memory bound by default, so going from 9900K 5.0 Ghz to 7.0 Ghz may make little to no difference).
  8. What about integrating HCI Memtest as a memory benchmark? Like there is one in RyzenDramCalc. It counts time to perform predefined amount of memtest % with predefined memory-size and with predefined amount of threads
  9. And I also have attached screenshot with actual BenchMate window (with saved submission) So what is this about?
  • Create New...