*Official Benchmark Thread* - Post it here or it didn't happen :D

[jaybee83]

38 minutes ago, johnksss said:

Didn't know that I was suppose to?

lol no one said u were "supposed to" bud 😄 

just curious, i expected the 12900K(S) to beat the 5950X when both are maxxed out. same cooling methods on both?

[johnksss]

3 minutes ago, jaybee83 said:

lol no one said u were "supposed to" bud 😄 

just curious, i expected the 12900K(S) to beat the 5950X when both are maxxed out. same cooling methods on both?

You kind of have me at a loss. Just how is the 12900K suppose to beat the 5950X in Cinebench without using  LN2/Dice/or Cascade? Im using my SS at the moment just testing the waters to see what it can do.

[jaybee83]

47 minutes ago, johnksss said:

You kind of have me at a loss. Just how is the 12900K suppose to beat the 5950X in Cinebench without using  LN2/Dice/or Cascade? Im using my SS at the moment just testing the waters to see what it can do.

um... so out of the box theyre basically on par in CB, but the 12900K i could imagine reach overall higher clocks with subambient cooling vs the 5950x. soooo i would expect the former to beat the latter. thats why i was asking.

but if ure just doing initial testing on the chip then ok, still at the beginning, more to come.

hope this is more clear now 😄 

[johnksss]

3 hours ago, jaybee83 said:

um... so out of the box theyre basically on par in CB, but the 12900K i could imagine reach overall higher clocks with subambient cooling vs the 5950x. soooo i would expect the former to beat the latter. thats why i was asking.

but if ure just doing initial testing on the chip then ok, still at the beginning, more to come.

hope this is more clear now 😄 

Hummm, I must have missed where you pointed that out to @Mr. Fox when he didn't beat his 5950x @ 32.6k with his 12900K/KS at 31.5k. Or where @Papusan didn't beat it either with his 31.7k score with his 12900k.

That's what had me confused.

 

[Papusan]

7 hours ago, jaybee83 said:

um... so out of the box theyre basically on par in CB, but the 12900K i could imagine reach overall higher clocks with subambient cooling vs the 5950x. soooo i would expect the former to beat the latter. thats why i was asking.

but if ure just doing initial testing on the chip then ok, still at the beginning, more to come.

hope this is more clear now 😄 

 

3 hours ago, johnksss said:

Hummm, I must have missed where you pointed that out to @Mr. Fox when he didn't beat his 5950x @ 32.6k with his 12900K/KS at 31.5k. Or where @Papusan didn't beat it either with his 31.7k score with his 12900k.

That's what had me confused.

 

You normally don't need exotic cooling for a good binned 5950X and proper tuned mem running 5.0GHz. This means a score above 33.500 in CBR-23. And from what I know, none of the Intel 16 cores chips is able to do +33K on ordinary cooling. Even an 12900K/KS  with SS will struggle  come above 33K in the menioned benchmark. So spot on bro Johnkss in the post above

 

https://hwbot.org/submission/5069674_papusan_3dmark06_geforce_gtx_980_77546_marks

 

Edit. A better score.

https://hwbot.org/submission/5069713_papusan_3dmark_vantage___performance_geforce_gtx_980_78991_marks?recalculate=true

 

[Mr. Fox]

7 hours ago, jaybee83 said:

um... so out of the box theyre basically on par in CB, but the 12900K i could imagine reach overall higher clocks with subambient cooling vs the 5950x. soooo i would expect the former to beat the latter. thats why i was asking.

but if ure just doing initial testing on the chip then ok, still at the beginning, more to come.

hope this is more clear now 😄 

 

3 hours ago, johnksss said:

Hummm, I must have missed where you pointed that out to @Mr. Fox when he didn't beat his 5950x @ 32.6k with his 12900K/KS at 31.5k. Or where @Papusan didn't beat it either with his 31.7k score with his 12900k.

That's what had me confused.

 

 

2 hours ago, Papusan said:

 

You normally don't need exotic cooling for a good binned 5950X and proper tuned mem running 5.0GHz. This means a score above 33.500 in CBR-23. And from what I know, none of the Intel 16 cores chips is able to do +33K on ordinary cooling. Even an 12900K/KS  with SS will struggle  come above 33K in the menioned benchmark. So spot on bro Johnkss in the post above

 

https://hwbot.org/submission/5069674_papusan_3dmark06_geforce_gtx_980_77546_marks

 

https://hwbot.org/submission/5069692_papusan_3dmark_vantage___performance_geforce_gtx_980_78177_marks

This is an apples-to-oranges comparison. 5950X is 16 cores / 32 threads. 12900K/KF/KS are 8 cores/ 16 threads, plus 8 Atom cores for a total of 24 threads. The Intel CPU outperforms the 5950X by a huge margin on a per thread basis, but it is 8 threads fewer than the 5950X. It is erroneous to put them in the same class due to the difference in total usable threads. If you were to disable 4 cores and force the 5950X to run with a maximum of 24 threads it would get its ass kicked really bad by an overclock 12900K/KF/KS.

 

The more appropriate comparison would by a Ryzen 3900X or 5900X, which are 12 core, 24 thread. The highest Cinebench scores on HWBOT for 5900X are lower than the 12900K* scores that I, @Papusan or @johnksss have posted. And, the Cinebench R23 record is with a 5900X running 6.0GHz on LN2.

 

https://hwbot.org/submission/4673735_oclockdoc_cinebench___r23_multi_core_with_benchmate_ryzen_9_5900x_30202_cb

 

https://hwbot.org/hardware/processors#key=ryzen_9_5900x

[Papusan]

10 hours ago, Mr. Fox said:

 

 

This is an apples-to-oranges comparison. 5950X is 16 cores / 32 threads. 12900K/KF/KS are 8 cores/ 16 threads, plus 8 Atom cores for a total of 24 threads. The Intel CPU outperforms the 5950X by a huge margin on a per thread basis, but it is 8 threads fewer than the 5950X. It is erroneous to put them in the same class due to the difference in total usable threads. If you were to disable 4 cores and force the 5950X to run with a maximum of 24 threads it would get its ass kicked really bad by an overclock 12900K/KF/KS.

 

The more appropriate comparison would by a Ryzen 3900X or 5900X, which are 12 core, 24 thread. The highest Cinebench scores on HWBOT for 5900X are lower than the 12900K* scores that I, @Papusan or @johnksss have posted. And, the Cinebench R23 record is with a 5900X running 6.0GHz on LN2.

 

https://hwbot.org/submission/4673735_oclockdoc_cinebench___r23_multi_core_with_benchmate_ryzen_9_5900x_30202_cb

 

https://hwbot.org/hardware/processors#key=ryzen_9_5900x

Or just test with 8 cores/16 threads as you are allowed to on the bot for 12th gen because of the small wimpy small Baby cores (Hybrid arch). Just disable 8 cores on the 5950X and there will be apples vs apples. Look at the top 20, 50 or top 100 https://hwbot.org/benchmark/cinebench_-_r20/rankings?cores=8#start=0#interval=20

 

GTX 980... improved to 11th place🙂

https://hwbot.org/submission/5069714_papusan_3dmark_vantage___performance_geforce_gtx_980_79465_marks?recalculate=true

[jaybee83]

10 hours ago, johnksss said:

Hummm, I must have missed where you pointed that out to @Mr. Fox when he didn't beat his 5950x @ 32.6k with his 12900K/KS at 31.5k. Or where @Papusan didn't beat it either with his 31.7k score with his 12900k.

That's what had me confused.

 

dude, im not trying to attack u here, so no need to get so defensive! 😄 simple reason why i didnt point it out to @Mr. Fox or @Papusan, namely that I didnt read this whole thread and didnt check every single screenshot posted here. so chillax, i just got curious when i saw ur screenshot and wanted to know more, thats it 🙂 im just taking an interest here!

 

9 hours ago, Papusan said:

You normally don't need exotic cooling for a good binned 5950X and proper tuned mem running 5.0GHz. This means a score above 33.500 in CBR-23. And from what I know, none of the Intel 16 cores chips is able to do +33K on ordinary cooling. Even an 12900K/KS  with SS will struggle  come above 33K in the menioned benchmark. So spot on bro Johnkss in the post above

 

good info, i didnt think 5.0+ ghz all core was doable on an 5950x without subambient cooling. what ive mostly seen is maybe up to 4.7-4.8 all core. but maybe that is benchstable vs. everyday stable.

 

7 hours ago, Mr. Fox said:

This is an apples-to-oranges comparison. 5950X is 16 cores / 32 threads. 12900K/KF/KS are 8 cores/ 16 threads, plus 8 Atom cores for a total of 24 threads. The Intel CPU outperforms the 5950X by a huge margin on a per thread basis, but it is 8 threads fewer than the 5950X. It is erroneous to put them in the same class due to the difference in total usable threads. If you were to disable 4 cores and force the 5950X to run with a maximum of 24 threads it would get its ass kicked really bad by an overclock 12900K/KF/KS.

 

The more appropriate comparison would by a Ryzen 3900X or 5900X, which are 12 core, 24 thread. The highest Cinebench scores on HWBOT for 5900X are lower than the 12900K* scores that I, @Papusan or @johnksss have posted. And, the Cinebench R23 record is with a 5900X running 6.0GHz on LN2.

 

https://hwbot.org/submission/4673735_oclockdoc_cinebench___r23_multi_core_with_benchmate_ryzen_9_5900x_30202_cb

 

https://hwbot.org/hardware/processors#key=ryzen_9_5900x

i guess it depends on the perspective. if you compare based on thread count then ure absolutely right, of course. and that also makes the most sense in the hwbot context, since the categories are based on core or thread numbers.

i was looking at it from a pricing and generational tier perspective, i.e. highest tier intel vs. highest tier AMD in the current gen. 12900K has less threads but an advantage regarding reachable clocks, so i actually expected it to be able and beat the 5950X going head to head in CB. i didnt expect the amd chip to be able and clock that high on all core, so thats cool to see!

[Mr. Fox]

58 minutes ago, jaybee83 said:

I guess it depends on the perspective. if you compare based on thread count then ure absolutely right, of course. and that also makes the most sense in the hwbot context, since the categories are based on core or thread numbers.

i was looking at it from a pricing and generational tier perspective, i.e. highest tier intel vs. highest tier AMD in the current gen. 12900K has less threads but an advantage regarding reachable clocks, so i actually expected it to be able and beat the 5950X going head to head in CB. i didnt expect the amd chip to be able and clock that high on all core, so thats cool to see!

If 5950X and X570 were any good I would still be running that. The platform was buggy to the point of frustration and the CPU and memory overclocking capabilities were pathetic. There are not very many that can run 50x on all cores without sub-zero cooling. Nice Cinebench scores is what attracted me to it in the first place. Little did I know that it would ultimately turn out to be about the only thing that I thought it was actually good for... and even then, only when my mouse and keyboard worked. I'd rank it in my top 10 most regrettable purchases of all time.

[jaybee83]

19 minutes ago, Mr. Fox said:

If 5950X and X570 were any good I would still be running that. The platform was buggy to the point of frustration and the CPU and memory overclocking capabilities were pathetic. There are not very many that can run 50x on all cores without sub-zero cooling. Nice Cinebench scores is what attracted me to it in the first place. Little did I know that it would ultimately turn out to be about the only thing that I thought it was actually good for... and even then, only when my mouse and keyboard worked. I'd rank it in my top 10 most regrettable purchases of all time.

phew that sounds tough... lets hope 7000 series will be improved in this regard. maybe AMD's new "XMP" equivalent RAMP standard will help a bit here 

[johnksss]

3 hours ago, jaybee83 said:

dude, im not trying to attack u here, so no need to get so defensive! 😄 simple reason why i didnt point it out to @Mr. Fox or @Papusan, namely that I didnt read this whole thread and didnt check every single screenshot posted here. so chillax, i just got curious when i saw ur screenshot and wanted to know more, thats it 🙂 im just taking an interest here!

 

ummm, ok.

 

[Papusan]

7 hours ago, Mr. Fox said:

If 5950X and X570 were any good I would still be running that. The platform was buggy to the point of frustration and the CPU and memory overclocking capabilities were pathetic. There are not very many that can run 50x on all cores without sub-zero cooling. Nice Cinebench scores is what attracted me to it in the first place. Little did I know that it would ultimately turn out to be about the only thing that I thought it was actually good for... and even then, only when my mouse and keyboard worked. I'd rank it in my top 10 most regrettable purchases of all time.

Enjoy.... 

 

https://forums.guru3d.com/threads/ryzen-9-7950x-allegedly-40-faster-than-5950x-in-cpu-z-multi-threaded.444366/page-4#post-6046405

 

See also... https://forums.guru3d.com/threads/ryzen-9-7950x-allegedly-40-faster-than-5950x-in-cpu-z-multi-threaded.444366/page-4#post-6046477

 

A sneeak peek.... Only rumors but if true 800$ will be too much.

[jaybee83]

4 hours ago, Papusan said:

Enjoy.... 

 

https://forums.guru3d.com/threads/ryzen-9-7950x-allegedly-40-faster-than-5950x-in-cpu-z-multi-threaded.444366/page-4#post-6046405

 

See also... https://forums.guru3d.com/threads/ryzen-9-7950x-allegedly-40-faster-than-5950x-in-cpu-z-multi-threaded.444366/page-4#post-6046477

 

A sneeak peek.... Only rumors but if true 800$ will be too much.

 

hmmm Intel isnt in full control of their own pricing though. shareholders demand a certain margin, since Intel has never been the "budget option" for cpus. so if AMD offers comparable / better performance for a lower price, Intel will be under pressure to either ignore that or make their shareholders mad...

also, can only put that 800 dollar price tag into perspective once 13900K pricing is known. if the 13900K ends up being 900 dollars, then 800 aint that bad 😄 

[Papusan]

15 minutes ago, jaybee83 said:

 

hmmm Intel isnt in full control of their own pricing though. shareholders demand a certain margin, since Intel has never been the "budget option" for cpus. so if AMD offers comparable / better performance for a lower price, Intel will be under pressure to either ignore that or make their shareholders mad...

also, can only put that 800 dollar price tag into perspective once 13900K pricing is known. if the 13900K ends up being 900 dollars, then 800 aint that bad 😄 

Intel have talked about 10% price hike for their chips this fall. 800$ means 33% premium above 12900K for a few extra added baby cores. Remember they now have the goolden chance to grab market shares from AMD. You don't do that easly with exactly same awful price point. And people have less money in their hands nowadays due the increased inflation/worse times. + the desktop sales have never been so low as now the last 30 years. Want more sales.... Just increase the prices, LOOL

[jaybee83]

2 hours ago, Papusan said:

Intel have talked about 10% price hike for their chips this fall. 800$ means 33% premium above 12900K for a few extra added baby cores. Remember they now have the goolden chance to grab market shares from AMD. You don't do that easly with exactly same awful price point. And people have less money in their hands nowadays due the increased inflation/worse times. + the desktop sales have never been so low as now the last 30 years. Want more sales.... Just increase the prices, LOOL

yes asbolutely agreed on the overall abysmal situation with regards to no money in pocket + inflation. however, both intel and amd are still gonna try high prices before they come to their senses. i mean, look at how long it took Nvidia and their partners to react. price in europe are STILL way too high for 3000 series. dont expect too much empathy or understanding from those companies 🤔

 

sooo according to AMD's livestream right now the 7950x is about 48% faster than 5950x in CB23 multi. damn thats gonna be a very tight race vs. the 13900k. i figure intel is just gonna bin it until the last second to just barely beat the 7950x 😄

[Papusan]

19 minutes ago, jaybee83 said:

sooo according to AMD's livestream right now the 7950x is about 48% faster than 5950x in CB23 multi. damn thats gonna be a very tight race vs. the 13900k. i figure intel is just gonna bin it until the last second to just barely beat the 7950x 😄

Too late bin 13900K now 🙂 And AMD couldn't charge huge premium over it's competitors product this time beacuse they can't offer a huge lead in performance as they did with 16 cores 5950X. Neither do they offer more threads than what Intel will offer with 13th gen processors. Hence we now see AMD changed price target down for 7950X. A huge win for the consumers. Just hope Nvidia is forced to do the same. And same for Intel.

 

LOOL

[Reciever]

Too rich for me, though I hope the 5800x3d drops in price, maybe in 6-8 months I'll look for one second hand.

[Talon]

13 minutes ago, Papusan said:

Too late bin 13900K now 🙂 And AMD couldn't charge huge premium over it's competitors product this time beacuse they can't offer a huge lead in performance as they did with 16 cores 5950X. Neither do they offer more threads than what Intel will offer with 13th gen processors. Hence we now see AMD changed price target down for 7950X. A huge win for the consumers. Just hope Nvidia is forced to do the same. And same for Intel.

 

LOOL

 

Definitely a huge win for consumers. Even in times of inflation, lower margins due to 5nm price, AMD knows they had to drop prices to remain competitive at the top end. Curious why they didn't drop low and mid range to really remain competitive where I think Intel is going to smack AMD around a bit. $299 for a 6 core in 2022 is just bad. 

[Papusan]

54 minutes ago, Talon said:

 

Definitely a huge win for consumers. Even in times of inflation, lower margins due to 5nm price, AMD knows they had to drop prices to remain competitive at the top end. Curious why they didn't drop low and mid range to really remain competitive where I think Intel is going to smack AMD around a bit. $299 for a 6 core in 2022 is just bad. 

Isn't the 7600X comparable to the 12600K? Intel charges MSRP at 289$ and is on the way to increase the prices for the whole stack with 10%. But not so sure they will do that for 13600K due the competition. 289$+10% will really be bad value🙂 Even the added baby cores can't make up for a in worst case 320$ deal (6+4 or whatever Intel will add of babies).

[Ashtrix]

The biggest thing out of all was, 2025+ AM5 support. That's a massive win for AMD again. They will saturate the market a lot again due to that move, that is the only reason why AM4 was super popular and high saturation for the past 2 CPU refreshes since Zen 2+ era.

 

 

 

EXPO is looking interesting too, 63ns DDR5 latency and now no more fiddling with their crappy IMC likes on pre Zen 4 which had higher latency on DDR4 standard, this is a proper refined CPU design from AMD of the Zen design no doubt.

 

 

AVX512 is confirmed. No wonder they are getting a huge ST performance too with that wide register support, same for Golden Cove P core too, 30% of the silicon which Intel decided to axe off for 12900KS. Claps !

 

 

5.7GHz boost on 7950X, that is a big move too, huge clock speed boost, I wonder how they will hold it. 230W is the max I think for the top end performance which I think is good. I think RPL will blow the roof off with extended TDP mode (350W+) from factory.

 

 

The main aspect is AMD's AGESA BIOS engineering dept. AND the IO Die on the new Zen 4 processors, I do not care about that iGPU but waiting to see how the new BIOS will hold also the reliability of the most important part of a PC - I/O. I really hope AMD improved their R&D and QC on this on HW and SW sides.

 

Oh I wonder how much Voltage AMD is pumping through this ? Zen 3 had 1.4v on all Processors no wonder the IOD crapping out and on top no room to OC and etc. Only X3D has 1,3v binned chips. If AMD pumps more than 1.4v then if they lock out of voltage control then I won't be really surprised but if that happens then it's going to be a DUD for Enthusiasts and Tinkerers.

 

Intel is already ready with more E cores nonsense to have higher MT performance and they are loading the P core with more L2 Cache and probably improvements to IMC and Ring Bus with added Clocks again.

AMD however is sticking with their no small BGA friendly cores at all, only big powerful beast cores, their CTO mentioned what is Zen 4c, it is a lower frequency Zen 4 with more compactness, I assume they will cut off SMT off it to reduce the die space and thus add more core to compete with ARM Neoverse N2 and V1 as they also lack SMT. Intel has delayed their SPR now to 2023+, it's a bad sign for them tbh, XEON is losing the ground to EPYC and ARMjunk. Anyways Zen 5 is also on track with a brand new design too.

 

True that, unlike Zen 3 AMD blowing the roof off with pricing, this round no such thing thankfully.

 

EDIT - AMD's AVX512 is not like Intel's implementation, so I think the AVX512 won't be on the level of Golden Cove / XEON SPR and maybe not even the old SKL-X, RKL class since it's using 2 SIMD pipelines apparently to make it AVX512 unlike Intel's full width, I hope Intel goes with AVX512 on their new Raptor Cove and not step back like ADL.  So if RPL has AVX512 that will be top CPU for RPCS3 again.

 

Quote

Critically, however, AMD is diverging from Intel in one important aspect: whereas Intel built a true, 512-bit wide SIMD machine for executing AVX-512 instructions, AMD did not. Instead, AMD will be executing these instructions over two cycles. This means AMD’s implementation still benefits from all of the additional instructions, register file space, and other technical improvements that came as part of AVX-512, but they won’t gain the innate doubling in SIMD throughput.

Quote

In discussing the rationale for AMD’s decision, Papermaster cited the extreme power requirements for a true 512-bit SIMD block as the biggest impetus for keeping AMD’s SIMD design at 256-bits. As we’ve already seen in Intel chips with AVX-512 support, the massive throughput of a 512-bit SIMD combined with its high density results in a hard spike in power consumption when using it, requiring Intel’s chips to downclock on AVX-512 workloads (sometimes severely) in order to keep power and thermals in check. Using a narrower 256-bit SIMD means that AMD won’t need to light up nearly as many transistors at once, which will in turn make it easier to keep clockspeeds and power consumption more consistent. At the same time, I don’t think AMD minds that the die space requirements for a 256-bit SIMD are significantly less than a 512-bit SIMD; a full 512-bit SIMD is a lot of transistors to build, and a lot of transistors to fire up during heavy workloads.

 

[Reciever]

I want to see similar strides made in the mobile arena, was there anything of that nature during the presentation?

[Talon]

2 hours ago, Papusan said:

Isn't the 7600X comparable to the 12600K? Intel charges MSRP at 289$ and is on the way to increase the prices for the whole stack with 10%. But not so sure they will do that for 13600K due the competition. 289$+10% will really be bad value🙂 Even the added baby cores can't make up for a in worst case 320$ deal (6+4 or whatever Intel will add of babies).

 

Even the 7700X can't deliver a real beating to the 12600K. It's faster, but not by anything to write home about. And that is last gen and the 7600X will face off against a 13600K within 2 weeks of AMD launch.

 

 

13600K is going to be 6 + 8 and there is no amount of IPC increase AMD can do to beat that. Add in the higher clocks, cache improvements, IMC improvements and AMD won't be able to compete at low-mid end is my guess. 

[Mr. Fox]

It is very difficult to find anything nice to say about anything that has to do with electronics technology. The hardware and the software that runs on it mostly trash, and what little doesn't suck is priced for people that have frivolous spending habits, or more money than intelligence. I hope Intel, AMD and NVIDIA experience record-setting losses and have to sell their next gen garbage for less than they are currently dumping their excess last Gen GPU inventory. It would also be nice to see Apple go out of business and Micro$lop stop working on new versions of Windows and Office and offer nothing but basic function-essential bug fixes for the next 5 or 6 years. The world doesn't need a next gen of anything. What we need is for them to stop pushing overpriced, unreliable, buggy, trash and "digitally signed" PUPs and data-stealing malware gimmicks. They don't deserve anything nice or good, and we don't owe them anything more than a hard reset.

[Reciever]

I chuckled a little when I got the Latitude 5430's in recently.

 

IIRC 2 P-cores and 8 E cores, 12 threads 

 

For some reason I read it as dual core quad threaded in my head. I went for more coffee after that. 

[Papusan]

20 minutes ago, Mr. Fox said:

It is very difficult to find anything nice to say about anything that has to do with electronics technology.

Same can be said about some buyers/fanboys. They defend the brand over anything else. They just can't see there is several ways to heaven😁 God bless you bro @Prema 🙂

 

https://www.techpowerup.com/forums/threads/amd-ryzen-7000-desktop-processors-launched-zen4-leadership-performance.298317/post-4823615