Jump to content
HWBOT Community Forums

Team Cup 2022 Planning Thread


Recommended Posts

okay so next round of comments/questions

amd gpu catzilla 576p ddr2 - use amd cpu, is ddr2 required for cpu as well or just gpu?n

nvidia gpu gb5 compute pcie 3.0 - this one goes to the audience, ban titans? Titan v might be a compute monster and I shudder to think of the cost to have both of them and then also an rtx titan

ddr4 igp - can we have similar restrictions to cc 2021? Otherwise I got at least 80 eu laptop I can bring to bare or 6770hq nuc etc

igp potential ddr stage - people asked for a stage that bans ati, intel, and nvidia igp so you have to run sis etc. Could create a ddr igp stage for these guys, or a second ddr2 igp stage I guess

pyprime ddr5 - do we have to use 3 different cpu models or just 3 different individual cpus?

gpupi 1b amd ddr4 - 5 different cpu cores, this means 5 different models or also 5 different core counts? Assuming all ddr4

x265 1080p ddr3 - can we ban s1151 and 2011-3, possibly 2011-1 as well. Alternatively no restrictions and allow xeons for maximum chaos

gb3 ddr2 single core - ban l3014 plz. Could also be fun to ban semprons as well and make the whole stage alternate cpus if others think that's fun

superpi 16m ddr 3 sockets - ban core 2 arch, it's just one score but still. Could ban s775/771 but kinda wanna see netburst s775

 

I think some of these I mentioned to leeg before some not, but this way the community can comment and tell me where I'm wrong or where I didn't go far enough etc

 

 

Link to comment
Share on other sites

  • Crew
55 minutes ago, yosarianilives said:

okay so next round of comments/questions

amd gpu catzilla 576p ddr2 - use amd cpu, is ddr2 required for cpu as well or just gpu?  ONLY GPU

nvidia gpu gb5 compute pcie 3.0 - this one goes to the audience, ban titans? Titan v might be a compute monster and I shudder to think of the cost to have both of them and then also an rtx titan: ADDED NO TITAN RULE

ddr4 igp - can we have similar restrictions to cc 2021? Otherwise I got at least 80 eu laptop I can bring to bare or 6770hq nuc etc

igp potential ddr stage - people asked for a stage that bans ati, intel, and nvidia igp so you have to run sis etc. Could create a ddr igp stage for these guys, or a second ddr2 igp stage I guess: 

pyprime ddr5 - do we have to use 3 different cpu models or just 3 different individual cpus? ITS BASED ON CORECOUNT

gpupi 1b amd ddr4 - 5 different cpu cores, this means 5 different models or also 5 different core counts? Assuming all ddr4:  ITS BASED ON CPU CORE (VERMEER, MATTISSE,...)

x265 1080p ddr3 - can we ban s1151 and 2011-3, possibly 2011-1 as well. Alternatively no restrictions and allow xeons for maximum chaos: 3 DIFFERENT SOCKETS, NO XEONS

gb3 ddr2 single core - ban l3014 plz. Could also be fun to ban semprons as well and make the whole stage alternate cpus if others think that's fun:  IT'S GEEKBENCH SINGLE CORE TEST FOR 2 CORE CPUS

superpi 16m ddr 3 sockets - ban core 2 arch, it's just one score but still. Could ban s775/771 but kinda wanna see netburst s775: DDR Platform

 

I think some of these I mentioned to leeg before some not, but this way the community can comment and tell me where I'm wrong or where I didn't go far enough etc

 

 

 

Link to comment
Share on other sites

9 minutes ago, Leeghoofd said:

x265 1080p ddr3 - can we ban s1151 and 2011-3, possibly 2011-1 as well. Alternatively no restrictions and allow xeons for maximum chaos: 3 DIFFERENT SOCKETS, NO XEONS

The no xeons part makes me sad, can we do like in the past where it was no xeons with more than 6 cores? (i assume the ruling is to exclude 1680v2 and 2011-3 shenanigans)

Link to comment
Share on other sites

Cen we get 775 completely removed from the AMD GPU AGP stage? cause right now it's just epowered i865G boards instad of epowered VIA P880 boards pretty much :(  Or just ban Core2 architecture CPUs and allow any board if you want us to run 775 :D

Edited by TAGG
  • Like 3
Link to comment
Share on other sites

  • Crew
2 hours ago, TAGG said:

Or just ban Core2 architecture CPUs and allow any board if you want us to run 775

Yep, banning VIA PT880 changes nothing (865G boards). Banning all Core2 would be nice.

4 hours ago, Leeghoofd said:

igp potential ddr stage - people asked for a stage that bans ati, intel, and nvidia igp so you have to run sis etc. Could create a ddr igp stage for these guys, or a second ddr2 igp stage I guess: 

3rd party IGP, I'm all in ?

  • Like 2
Link to comment
Share on other sites

On 7/12/2022 at 3:45 PM, TAGG said:

The no xeons part makes me sad, can we do like in the past where it was no xeons with more than 6 cores? (i assume the ruling is to exclude 1680v2 and 2011-3 shenanigans)

Yeah, my original suggestion about this sort of stage was to try to get people to use 1, 2, 4, 6 as the core counts for some benchmark on DDR3 (i.e. needing to use X58 or X79 to get the 6-core option via an i7), but reduce the weird cheesing of the "optimal" configuration just being like a 9900K on a ddr3 board, e5-2696 v3 on one of those weird "X99" boards that supports DDR3, and some 2011-1 15-core Xeon or something. I guess Sky/Kaby/Coffee Lake with DDR3 is still on the table, though, so a 9900K on DDR3 will probably be the top score, which might be a little harder to acquire/do than most teams/people getting their hands on a 1680v2.

 

On 7/12/2022 at 3:49 PM, Leeghoofd said:

No Xeons above 6 cores allowed

Just kind of related, but would it make sense to limit it to maximum of 8GB of memory, rather than it needing to *be* 8GB? Not that I think it would necessarily be an optimal  submission, but someone using X58 might prefer to use 3x2GB rather than some weird monstrosity of a ram configuration to get 8GB.

Could the stage just be limited to being 6-core max, rather than only limiting it on Xeons, or just excluding 1151/1151v2? As the stage is, I think it's still potentially requiring a 9900K on DDR3 in order for a team to be competitive in the stage. Just looking up some of the CPUs I'd imagine will be "competitive" in this stage and their approximate peak performance on X265 1080p, but like a 4790K looks like it might be able to do about 40fps on LN2, a 3770K at just under 30fps, a 6-core SB/IB on X79 about 35fps on LN2, a 6-core Westmere on LN2 about 30fps, and a Skylake/Kaby Lake i7 probably about 50-55fps. While I don't think we've seen any 9900K/KFs on DDR3 for this bench yet, it looks like upwards of 5.5GHz is possible on a 9900K on DDR3 (e.g. Dim0n527's R23 at 5800MHz (https://hwbot.org/submission/4823752)), which could potentially put it it up at 80+fps, or at least in the 70+fps range (since I'm not sure how much the extra bandwidth of DDR4 benefits over DDR3 for X265), or heck, even just 60-65fps at "stock". 8-core on X79 seems to only be around 40-45fps, so, it seems like a 1680v2 would at least be less of an advantage than just a team just having a 9900K (or potentially even an 8700K/8086K) on DDR3.

Sorry of that was kind of incoherent rambling, but was just trying to convey how it seems like allowing 1151/1151v2 on DDR3 on this stage (because hwbot will recognize them as being different sockets, right?) effectively means a team needs to have one of the few compatible boards with the BIOS mod to even have a chance on the stage, since it seems like having that board means that a team with that one board could run both a 9900K and a 7700K to potentially just have 20% more combined fps from those two scores as a team with a 4790k, 4930K/4960X, and Westmere 6-core, which is more of the "spirit" of what I think I was originally trying to have the stage be. Just feels like a 9900K tips the balance far more than allowing 8-core Xeons.

Link to comment
Share on other sites

11 hours ago, TASOS said:

Single cpu socket boards please.

I dont want to see "Mail Servers" benching again.

 

Yeah, might be a little more ideal to just limit to 6 cores maximum. If someone wants to take a dual socket board with dual dual-core CPUs (e.g. dual E5-2637s) and try to beat the various overclockable native 6-core options, I'd be fine with that, but if it's just limited to 6-core CPUs, I feel like Yos is going to just go source some E7-4809 v2s and/or some E7-8893 v2s or something and triple-socket or quad-socket them to compete with like 18c36t and 24c48t. While I'd kind of enjoy seeing something fun like that, I feel like that also is not in the spirit of "fair" competition with 6-core processors. Could be interesting, though, seeing some SR-2s competing though, even if they were allowed to go dual 6-core. Just throwing in my two cents.

Link to comment
Share on other sites

4 hours ago, yosarianilives said:

Idea that should make everyone happy, no mp in tc. But @mr.pacoif you would like pick a bench and I'll see what I can do with my 2011-1 box and you can bring whatever you've got

Careful what you wish for...........Paco has everything and then some. lol

Edited by Mr.Scott
  • Like 4
  • Haha 1
Link to comment
Share on other sites

Brace for a long one.

Comments about the AMD AGP stage, which needs it own section:

  • The AMD AGP stage is currently set up to exclude AGP 8x.  I'm not sure if this is intentional, but it's interesting.  Top AGP 8x cards are obviously a bit rare and expensive, but I'm concerned the top AMD AGP 4x cards - eg Radeon 9100 and 8500 - aren't any easier to get hold of.  Call me sentimental but they're also collectors items that it might be a shame to mod to death, whereas for top AGP 8x people already have super modded cards.
  • AMD AGP Stage has a lot of other 'loophole' boards/platforms not currently banned.  There are a couple of ASRock 775Dual series boards, but also AM2/AM2+ AGP options that even enable Deneb+AGP (this is afaik 'optimal' for 3DMark2001SE AGP).  As it stands only the relatively common stuff is banned, which would just hand an even greater advantage to people like me who have non-listed 'loophole' hardware.
  • The mobo restrictions should either be made much more comprehensive, or relaxed entirely.
  • If AGP 8x is really not allowed, then IMO the restrictions might as well be relaxed entirely as CPU won't make much difference.  If AGP 8x is allowed, it's probably a good idea to either restrict by CPU core and accept people running 4CoreDual+P4, or to restrict by CPU socket eg to 462/478/754.  Restricting to older sockets and allowing AGP 8x would push the bottleneck to the CPU, which would at least nerf the unobtainium cards.
  • An alternative might be to specify certain relatively widely available cards, eg Radeon 9200
  • IMO the best thing to do is to allow AGP 8x and restrict CPU socket rather than specific boards.
  • It would also be viable to just make the stage 'full out', if that's done I think we've had 01se relatively recently so maybe 05 or 06 would be better?  But full out 01se on AMD AGP is fine.

Comments about benchmark/hardware selection:

  • Requiring 4 scores seems really excessive for the Intel LGA1156 stage, it's a relatively niche platform, I'd suggest 2 in line with eg AMD DDR2 GPU.
  • Is Intel 3DMark Vantage CPU score DDR4 intended to be one score per gen, or just i5s only?  One score per gen would be good.
  • Is DDR5 iGPU really intended to be x1 score?  3 scores are needed in other DDR5 categories.  I suppose many people will have -KF or non-iGPU boards but you'd expect at least 2?
  • Is GPUPI 1B on AMD CPUs for the DDR4 stage even memory bound?  Conventionally GPUPI isn't.  If a benchmate-based memory sensitive benchmark is desired there's always good old ycruncher.  This could be swapped with the Intel CPU DDR5 stage.
  • I'm slightly disappointed there's no max mem clock stage on any platform  but the current stages look fun so I wouldn't want to suggest scrapping any of them.
  • GPUPI 3.3 32B on geforce 900 series is a 15+ minute benchmark.  I'm not complaining, but just as long as you're aware.
  • I'm a big fan of the use of unique video card cores, rather than unique specific models, for the iGPU section.  Had to get at least one positive comment in there!
  • AMD AM3 HWBOT x265 seems like a missed opportunity to give people a reason to bench 1 core per CU FX by allowing all 4-core AMD DDR3 ?

Comments about loopholes:

  • Noticed the Intel DDR5 CPU stage specifies "Use 1 processor(s)" - isn't this redundant as server stuff is conventionally banned by default?  If it needs to be specified many other stages might be lacking it.
  • DDR1 SuperPi 16M is going to get 4CoreDual'd unless core 2 arch is explicitly banned.
  • DDR3 x265 per socket is at real risk from chinese DDR3 "X99" boards, Z170, and CFL modded Z170.  Probably laptop stuff too?  It might be best to just have a socket whitelist.
  • Is it intended to allow TR4 Threadripper for the DDR4 AMD GPUPI 1B stage?  What about TRX40 threadripper, and WRX80 threadripper pro?  Might make sense to restrict to dual channel.
  • Geforce 900 series (Nvidia GPUPI 3.3 32B) as configured on HWBOT includes the Titan X.  Is this intended?  I don't think it's too bad by modern GPU standards...
  • Currently the DDR4 AMD GPUPI 1B stage would include mobile-only "Zen 3+" as optimal hardware.  If that's banned, it'll require Bristol Ridge which afaik is locked to 2400 max mem mult and a bit of a compatibility minefield.  Might be a good idea to ban mobile and reduce to 4 subs (zen 1/+/2/3).  Although I supposed it would be funny to see people benching mem on bristol ridge, so I won't complain if it's kept at 5 ?

Things I suspect are mistakes:

  • Many stages don't explicitly list what you'd assume are standard restrictions (eg use only 1 GPU core), but presumably this is to be added?
  • AMD GPU stages all say "unique processors" rather than "unique videocards", except GDDR6
  • Nvidia 3DMark03 GT215 says "unique processors"
  • DDR2 iGPU says "unique processors"
  • Some of the memory stages say "unique processors", some say "unique hardware", despite having the same restrictions written

I haven't looked too carefully for loopholes based on mobile, socket adapters and 'consumer' multi-CPU, so there might be some that I haven't flagged up.

Link to comment
Share on other sites

1 hour ago, denvys5 said:

 Suggestion:

IGPU DDR5 - ban Steamdeck/other custom handheld consoles. Steamdeck in particular is stronk in igpu, and is kinda rare (due to high demand).

afaik steam deck is LPDDR5 not DDR5 so would be excluded by default (same as how GDDR5 is excluded)

  • Thanks 1
Link to comment
Share on other sites

6 minutes ago, mickulty said:
  • Currently the DDR4 AMD GPUPI 1B stage would include mobile-only "Zen 3+" as optimal hardware.  If that's banned, it'll require Bristol Ridge which afaik is locked to 2400 max mem mult and a bit of a compatibility minefield.  Might be a good idea to ban mobile and reduce to 4 subs (zen 1/+/2/3).  Although I supposed it would be funny to see people benching mem on bristol ridge, so I won't complain if it's kept at 5 ?

.

If restriction is done by core lineup (like in the description), not generation, then we can do Cezanne+Vermeer+Matisse+Renoir+ for example Summit Ridge.

That way, nobody needs to use BristolRidge

  • Like 1
Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...