Info 64MB V-Cache on 5XXX Zen3 Average +15% in Games

Page 135 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Kedas

Senior member
Dec 6, 2018
355
339
136
Well we know now how they will bridge the long wait to Zen4 on AM5 Q4 2022.
Production start for V-cache is end this year so too early for Zen4 so this is certainly coming to AM4.
+15% Lisa said is "like an entire architectural generation"
 
Last edited:
  • Like
Reactions: Tlh97 and Gideon

gdansk

Golden Member
Feb 8, 2011
1,974
2,354
136
Beyond all this fiddle faddle.

AMD requires a picture of the CPU in socket to get RMA. Glad I took one randomly because I really don't want to dissemble and put it in the motherboard for a sad vanity shot.

So take pictures of your CPUs when commissioning them.
Good to know. I'll keep that in mind next time.
 

Schmide

Diamond Member
Mar 7, 2002
5,581
712
126
Ugggg. I didn't fully read.

A photo of your processor installed in the motherboard socket clearly showing the model and serial number. Please also write your service request number on a piece of paper and include it in the picture such that both CPU serial number and service request number are clearly legible.

So tedious...
 

Schmide

Diamond Member
Mar 7, 2002
5,581
712
126
I was just going to take a picture on top of the waterblock on the taichi, that I don't want to disassemble, and one in the aorus socket with all the numbers in the picture. Even though the taichi was the board it failed on.
 

Det0x

Golden Member
Sep 11, 2014
1,027
2,953
136
Not sure if i should post here or in the 5000 builders thread, but have done a full comparison between my 5800x3d and my 5950x in all the different 3dmarks at max clocks :)
Pretty happy with the results as i got multiple rank#1 with Nvidia+5800x3d combo :cool: (eventho i'm limited to 100mhz baseclock = 4450mhz max multithread)

Night Raid score = 72331 points
  • Graphics Score 171771
  • CPU Score 16898
Wild Life score = 124195 points

Wild life Extreme = 52837 points

Fire Strike = 41882 points
  • Graphics Score 55490
  • Physics Score 30370
  • Combined Score 18446
Fire Strike Extreme = 26505 points
  • Graphics Score 28705
  • Physics Score 30422
  • Combined Score 14995
Fire Strike Ultra = 14864 points
  • Graphics Score 14992
  • Physics Score 30318
  • Combined Score 8130
Time Spy = 20891 points
  • Graphics Score 23182
  • CPU Score 13393
Time Spy Extreme = 10322 points
  • Graphics Score 12056
  • CPU Score 5687
Port Royal = 15879 points


As a comparison, here are my 3090 numbers with the 5950x:


Port Royal = 16 050 @ I scored 16 050 in Port Royal
  • Graphics Score = 16050
TIME SPY = 22 666 @ I scored 22 666 in Time Spy
  • Graphics Score = 23 449
  • CPU Score = 19 062
TIME SPY EXTREME = 12 180 @ I scored 12 180 in Time Spy Extreme
  • Graphics Score = 12 258
  • CPU Score = 11 760
FIRE STRIKE = 43 513 @ I scored 43 513 in Fire Strike
  • Graphics Score = 49 613
  • Physics Score = 44 674
  • Combined Score = 22 188
FIRE STRIKE extreme = 27 138 @ I scored 27 138 in Fire Strike Extreme
  • Graphics Score = 27 940
  • Physics Score = 44 267
  • Combined Score = 15 113
FIRE STRIKE ULTRA = 15 072 @ I scored 15 072 in Fire Strike Ultra
  • Graphics Score = 14 796
  • Physics Score = 44 514
  • Combined Score = 8 140
5800x3d is much stronger in real games than 3dmark would lead you to believe as seen here:
(the "CPU benchmarks" in 3dmark are pretty much render tests with little correlation to a real gaming workloads)
. Shadow of the Tomb Raider: 1080p lowest
  • 5950x @ ~5100/5000mhz = 353fps average cpu game
  • 12900k @ 5750mhz 4300MT/s CL14 = 373fps average cpu game
  • 5800x3d @ 4450mhz = 402fps average cpu game

Horizon Zero Dawn: 1080p performance preset, lowest res scale:
  • 5950x @ ~5100mhz = 301fps average cpu game
  • 12900k @ 5580mhz 7160MT/s CL30 = 321fps average cpu game
  • 5800x3d @ 4450mhz = 313fps average cpu game

F1 2020 1080p low dx11: Australia benchmark location and dry weather:
  • 5950x @ ~5100mhz = 490 average fps
  • 5800x3d @ 4450mhz = 555 average fps

Farcry6 1080p ultra, HD texture enabled, FSR QTY:
  • 5950x @ ~5100mhz = 163 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 203 average fps
  • 5800x3d @ 4450mhz = 176 average fps

Cyberpunk 2077: 1080p low
  • 5950x @ ~5100mhz = 252 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 304 average fps
  • 5800x3d @ 4450mhz = 268 average fps

Final Fantasy XV 1080p low : (game engine limited, results with grain of salt)
  • 5950x @ ~5100mhz = 23426 scores
  • 12900k @ ~5700mhz(?) = 23585 scores
  • 5800x3d @ 4450mhz = 23489 scores

Final Fantasy XIV: Endwalker 1440p maximum : (game engine limited, results with grain of salt)
  • 5950x @ ~5100mhz = 30553 scores
  • 12900k @ ~5700mhz(?) = 33891 scores
  • 5800x3d @ 4450mhz = 33764 scores

HardwareLux Counter-Strike: Global Offensive benchmark settings : (only scale with clockspeed it seems)
  • 12900k @ 5500mhz 4133MT/s CL16 = 954fps
  • 5800x3d @ 4450mhz = 716 fps
Metro Exodus benchmark: 1080p low:
  • 5950x @ ~5100mhz = 322 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 408 average fps
  • 5800x3d @ 4450mhz = 338 average fps
  • 5800x3d @ 4450mhz, dx11 = 524 average fps
Metro Exodus Enhanced Benchmark: 1080p low:
  • 12900k @ 5580mhz 7160MT/s CL30 = 250 average fps
  • 5800x3d @ 4450mhz = 237 average fps
 
Last edited:

szrpx

Member
Jan 12, 2022
34
66
51
Not sure if i should post here or in the 5000 builders thread, but have done a full comparison between my 5800x3d and my 5950x in all the different 3dmarks at max clocks :)
Pretty happy with the results as i got multiple rank#1 with Nvidia+5800x3d combo :cool: (eventho i'm limited to 100mhz baseclock = 4450mhz max multithread)

Night Raid score = 72331 points
  • Graphics Score 171771
  • CPU Score 16898
Wild Life score = 124195 points

Wild life Extreme = 52837 points

Fire Strike = 41882 points
  • Graphics Score 55490
  • Physics Score 30370
  • Combined Score 18446
Fire Strike Extreme = 26505 points
  • Graphics Score 28705
  • Physics Score 30422
  • Combined Score 14995
Fire Strike Ultra = 14864 points
  • Graphics Score 14992
  • Physics Score 30318
  • Combined Score 8130
Time Spy = 20891 points
  • Graphics Score 23182
  • CPU Score 13393
Time Spy Extreme = 10322 points
  • Graphics Score 12056
  • CPU Score 5687
Port Royal = 15879 points


As a comparison, here are my 3090 numbers with the 5950x:


Port Royal = 16 050 @ I scored 16 050 in Port Royal
  • Graphics Score = 16050
TIME SPY = 22 666 @ I scored 22 666 in Time Spy
  • Graphics Score = 23 449
  • CPU Score = 19 062
TIME SPY EXTREME = 12 180 @ I scored 12 180 in Time Spy Extreme
  • Graphics Score = 12 258
  • CPU Score = 11 760
FIRE STRIKE = 43 513 @ I scored 43 513 in Fire Strike
  • Graphics Score = 49 613
  • Physics Score = 44 674
  • Combined Score = 22 188
FIRE STRIKE extreme = 27 138 @ I scored 27 138 in Fire Strike Extreme
  • Graphics Score = 27 940
  • Physics Score = 44 267
  • Combined Score = 15 113
FIRE STRIKE ULTRA = 15 072 @ I scored 15 072 in Fire Strike Ultra
  • Graphics Score = 14 796
  • Physics Score = 44 514
  • Combined Score = 8 140
5800x3d is much stronger in real games than 3dmark would lead you to believe as seen here:
(the "CPU benchmarks" in 3dmark are pretty much render tests with little correlation to a real gaming workloads)
. Shadow of the Tomb Raider: 1080p lowest
  • 5950x @ ~5100/5000mhz = 353fps average cpu game
  • 12900k @ 5750mhz 4300MT/s CL14 = 373fps average cpu game
  • 5800x3d @ 4450mhz = 402fps average cpu game

Horizon Zero Dawn: 1080p performance preset, lowest res scale:
  • 5950x @ ~5100mhz = 301fps average cpu game
  • 12900k @ 5580mhz 7160MT/s CL30 = 321fps average cpu game
  • 5800x3d @ 4450mhz = 313fps average cpu game

F1 2020 1080p low dx11: Australia benchmark location and dry weather:
  • 5950x @ ~5100mhz = 490 average fps
  • 5800x3d @ 4450mhz = 555 average fps

Farcry6 1080p ultra, HD texture enabled, FSR QTY:
  • 5950x @ ~5100mhz = 163 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 203 average fps
  • 5800x3d @ 4450mhz = 176 average fps

Cyberpunk 2077: 1080p low
  • 5950x @ ~5100mhz = 252 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 304 average fps
  • 5800x3d @ 4450mhz = 268 average fps

Final Fantasy XV 1080p low : (game engine limited, results with grain of salt)
  • 5950x @ ~5100mhz = 23426 scores
  • 12900k @ ~5700mhz(?) = 23585 scores
  • 5800x3d @ 4450mhz = 23489 scores

Final Fantasy XIV: Endwalker 1440p maximum : (game engine limited, results with grain of salt)
  • 5950x @ ~5100mhz = 30553 scores
  • 12900k @ ~5700mhz(?) = 33891 scores
  • 5800x3d @ 4450mhz = 33764 scores

HardwareLux Counter-Strike: Global Offensive benchmark settings : (only scale with clockspeed it seems)
  • 12900k @ 5500mhz 4133MT/s CL16 = 954fps
  • 5800x3d @ 4450mhz = 716 fps
Metro Exodus benchmark: 1080p low:
  • 5950x @ ~5100mhz = 322 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 408 average fps
  • 5800x3d @ 4450mhz = 338 average fps
  • 5800x3d @ 4450mhz, dx11 = 524 average fps
Metro Exodus Enhanced Benchmark: 1080p low:
  • 12900k @ 5580mhz 7160MT/s CL30 = 250 average fps
  • 5800x3d @ 4450mhz = 237 average fps

Jesus, what a difference DX11 makes in Metro Exodus
 

Dave3000

Golden Member
Jan 10, 2011
1,343
91
91
I was wondering if comparing a Ryzen 5800X to a Ryzen 5800X3D is similar to comparing a Pentium 133 system without L2 cache to a Pentium 120 system with 512KB L2 PB cache? If we went back to late 1995 and the two top pre-built systems selling at the electronics store either had a Pentium 120 or a Pentium 133 but the Pentium 120 system had 512KB L2 PB cache and the Pentium 133 system did not have any L2 cache, would the Pentium 120 system in this case be better at gaming than that particular Pentium 133 system but a little worse than that particular Pentium 133 system in productivity? Let's assume these two systems are from the same manufacturer and have the same hardware except for the CPU and L2 cache configuration.
 
Last edited:

Dave3000

Golden Member
Jan 10, 2011
1,343
91
91
More like Pentium MMX 200 versus mobile Pentium II 233.

I disagree because the Pentium II 233 had a higher clock speed than the Pentium 200 MMX and they were both completely different architectures and the Pentium II 233 was better at productivity as well as gaming than the Pentium 200 MMX. I'd say if I was going to compare it a Pentium II 233 it's more like a Pentium II 233 compared to a Celeron 266 since the Celeron 266 had higher clock speed than the Pentium II 233, same architecture but without the L2 cache, and the Pentium II 233 outperformed the Celeron 266 in gaming.
 
Last edited:

Dave3000

Golden Member
Jan 10, 2011
1,343
91
91
Just out of curiosity, has anyone here upgraded from a 5600X or 5800X to a 5800X3D and tested the performance in DOSBox-X in DOSBench, specifically the Quake 640x480 timedemo with cycles set to max, CPUtype set to auto, and core set to dynamic_x86 in the DOSBox-X configuration file? If so, how does it comprare with the 5600X or 5800X in this aspect?
 
Last edited:

Det0x

Golden Member
Sep 11, 2014
1,027
2,953
136
Not sure if i should post here or in the 5000 builders thread, but have done a full comparison between my 5800x3d and my 5950x in all the different 3dmarks at max clocks :)
Pretty happy with the results as i got multiple rank#1 with Nvidia+5800x3d combo :cool: (eventho i'm limited to 100mhz baseclock = 4450mhz max multithread)

Night Raid score = 72331 points
  • Graphics Score 171771
  • CPU Score 16898
Wild Life score = 124195 points

Wild life Extreme = 52837 points

Fire Strike = 41882 points
  • Graphics Score 55490
  • Physics Score 30370
  • Combined Score 18446
Fire Strike Extreme = 26505 points
  • Graphics Score 28705
  • Physics Score 30422
  • Combined Score 14995
Fire Strike Ultra = 14864 points
  • Graphics Score 14992
  • Physics Score 30318
  • Combined Score 8130
Time Spy = 20891 points
  • Graphics Score 23182
  • CPU Score 13393
Time Spy Extreme = 10322 points
  • Graphics Score 12056
  • CPU Score 5687
Port Royal = 15879 points


As a comparison, here are my 3090 numbers with the 5950x:


Port Royal = 16 050 @ I scored 16 050 in Port Royal
  • Graphics Score = 16050
TIME SPY = 22 666 @ I scored 22 666 in Time Spy
  • Graphics Score = 23 449
  • CPU Score = 19 062
TIME SPY EXTREME = 12 180 @ I scored 12 180 in Time Spy Extreme
  • Graphics Score = 12 258
  • CPU Score = 11 760
FIRE STRIKE = 43 513 @ I scored 43 513 in Fire Strike
  • Graphics Score = 49 613
  • Physics Score = 44 674
  • Combined Score = 22 188
FIRE STRIKE extreme = 27 138 @ I scored 27 138 in Fire Strike Extreme
  • Graphics Score = 27 940
  • Physics Score = 44 267
  • Combined Score = 15 113
FIRE STRIKE ULTRA = 15 072 @ I scored 15 072 in Fire Strike Ultra
  • Graphics Score = 14 796
  • Physics Score = 44 514
  • Combined Score = 8 140
5800x3d is much stronger in real games than 3dmark would lead you to believe as seen here:
(the "CPU benchmarks" in 3dmark are pretty much render tests with little correlation to a real gaming workloads)
. Shadow of the Tomb Raider: 1080p lowest
  • 5950x @ ~5100/5000mhz = 353fps average cpu game
  • 12900k @ 5750mhz 4300MT/s CL14 = 373fps average cpu game
  • 5800x3d @ 4450mhz = 402fps average cpu game

Horizon Zero Dawn: 1080p performance preset, lowest res scale:
  • 5950x @ ~5100mhz = 301fps average cpu game
  • 12900k @ 5580mhz 7160MT/s CL30 = 321fps average cpu game
  • 5800x3d @ 4450mhz = 313fps average cpu game

F1 2020 1080p low dx11: Australia benchmark location and dry weather:
  • 5950x @ ~5100mhz = 490 average fps
  • 5800x3d @ 4450mhz = 555 average fps

Farcry6 1080p ultra, HD texture enabled, FSR QTY:
  • 5950x @ ~5100mhz = 163 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 203 average fps
  • 5800x3d @ 4450mhz = 176 average fps

Cyberpunk 2077: 1080p low
  • 5950x @ ~5100mhz = 252 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 304 average fps
  • 5800x3d @ 4450mhz = 268 average fps

Final Fantasy XV 1080p low : (game engine limited, results with grain of salt)
  • 5950x @ ~5100mhz = 23426 scores
  • 12900k @ ~5700mhz(?) = 23585 scores
  • 5800x3d @ 4450mhz = 23489 scores

Final Fantasy XIV: Endwalker 1440p maximum : (game engine limited, results with grain of salt)
  • 5950x @ ~5100mhz = 30553 scores
  • 12900k @ ~5700mhz(?) = 33891 scores
  • 5800x3d @ 4450mhz = 33764 scores

HardwareLux Counter-Strike: Global Offensive benchmark settings : (only scale with clockspeed it seems)
  • 12900k @ 5500mhz 4133MT/s CL16 = 954fps
  • 5800x3d @ 4450mhz = 716 fps
Metro Exodus benchmark: 1080p low:
  • 5950x @ ~5100mhz = 322 average fps
  • 12900k @ 5580mhz 7160MT/s CL30 = 408 average fps
  • 5800x3d @ 4450mhz = 338 average fps
  • 5800x3d @ 4450mhz, dx11 = 524 average fps
Metro Exodus Enhanced Benchmark: 1080p low:
  • 12900k @ 5580mhz 7160MT/s CL30 = 250 average fps
  • 5800x3d @ 4450mhz = 237 average fps
I'm back with my 5950x :)
Following is a comparison between my 5800x3d and the 5950x on the same OS with ~same temps / ~same GPU clocks on the same Nvida 3090:

Night Raid score = 81118 points
  • Graphics Score 182507
  • CPU Score 19556
Wild Life score = 125997 points

Wild life Extreme = 53260 points

Fire Strike = 45477 points
  • Graphics Score 52091
  • Physics Score 45410
  • Combined Score 23323
Fire Strike Extreme = 27550 points
  • Graphics Score 28494
  • Physics Score 45922
  • Combined Score 14904
Fire Strike Ultra = 15153 points
  • Graphics Score 14907
  • Physics Score 45585
  • Combined Score 8072
Time Spy = 22866 points
  • Graphics Score 23519
  • CPU Score 19761
Time Spy Extreme = 12247 points
  • Graphics Score 12311
  • CPU Score 11900
Port Royal = 16023 points

Pretty much limited by summertime temps atm, but its ~even between the two cpus.
And like i said above, the 5800x3d is much stronger in real games than 3dmark would lead you to believe.
 

DAPUNISHER

Super Moderator CPU Forum Mod and Elite Member
Super Moderator
Aug 22, 2001
28,274
19,921
146
Props to Wendell for providing the kind of gaming experience that some of us have been opining about. We were discussing how games like Planet Coaster were vastly different late game for CPU performance. My reaction to him having late game saves that demonstrate how intense things get.

antonio-banderas-dissatisfied.gif


Most of the reviewers remind me of the Bruce Lee quote from Enter the Dragon -The art of fighting without fighting. Only they have mastered the art of reviewing CPU gaming performance without gaming.