• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Share your AIDA 64 cache and memory benchmark here

tabascosauz

Moderator
Supporter
Staff member
Joined
Jun 24, 2015
Messages
8,153 (2.37/day)
Location
Western Canada
System Name ab┃ob
Processor 7800X3D┃5800X3D
Motherboard B650E PG-ITX┃X570 Impact
Cooling NH-U12A + T30┃AXP120-x67
Memory 64GB 6400CL32┃32GB 3600CL14
Video Card(s) RTX 4070 Ti Eagle┃RTX A2000
Storage 8TB of SSDs┃1TB SN550
Case Caselabs S3┃Lazer3D HT5
Regarding voltages, I'm a bit hesitant going much higher on the VSOC, what would be a decent maximum voltage I could or should try for those sweet 2000MHz+ FCLKs?

I am somewhat scared of running windows repeatedly with unstable hardware, things might get corrupted :O running memtest from a bootable USB device ain't so bad and might be somewhat quicker to boot, will look into those others regardless.

I run 1.2V daily for 4200CL16 with iGPU use. Not actually using (ie. gaming) the iGPU should lower your VSOC requirements a bit; the only reason I run 1.2V is because in iGPU loads VSOC will still drop to 1.11V or so regardless of how extreme I set the LLC, so I literally need extra VSOC to prevent crashing in games. Just don't go over 1.2V daily.

Yes, that's always the risk with OC, but it's a remote risk. Generally you have to be running something blatantly unstable extended periods of time (ie. daily use) to manifest meaningful Windows or data corruption. And knowing Windows, it'll happen anyways with a stable system. Ask me how I know...

MT86 is aight for verifying a new kit you just bought. No one uses it in OC because it's slow, not very good (doesn't work the CPU at all) and a pain in the ass. Use TM5 or HCI (for HCI free verison, you have to open multiple instances and run them simultaneously to fill up the entirety of your mem capacity).

If I had to guess, no iGPU usage 4000-4200 probably needs between 1.125-1.175V.

In my case it might actually make sense to do most or all the tweaking from the CBS menu then, as I suppose that ones the baseline for all other features and should be the least buggy.

A new motherboard isn't really in the picture for me atm, I'd rather save up a bit for a Cezanne chip, if this board will also support it.

That makes sense. The B450 board does have the smaller 16MB BIOS chip, but it does have Vermeer support so I'm optimistic. I'd only recommend the B550I AX for benching/tweaking anyhow, Bluetooth is a little buggy for daily.

After every CMOS reset/BIOS flash you'll be visiting CBS anyways to turn off TSME and PowerDown, so it's good to get acquainted.

I'm still not sure whether the IF is unstable, or actually the memory is. If you say CJR mem's sweetspot is around 3600-3800 then 4133MHz seems quite high on all accounts. Won't stop me from trying though of course :).

Thanks! I still hope i'll be able to use both the iGPU and discrete GPU one day, time will tell. Currently have screens connected to both but windows will only let me switch between GPUs right after a new hardware install. Feels a bit like they're disallowing it on purpose.

Sorry, I meant sweet spot as in tRCD and tRP can do 19 at 3600/3733. On second thought I don't know if they need to relax to 20 at 3800.

Mem stability is easy to rule out if you don't play games on iGPU. Either HCI up to 1000% (personally I say 3000%) coverage, or TM5 through minimum of 3 runs, plus maybe some Prime95 Large FFT if you feel up to it.

IF stability is the hard one to rule out, especially on APUs where the iGPU rail (VDDCR_GFX) also shares the VSOC domain so can introduce substantial droop to VSOC sometimes. There are a few tests that some people say work (GitHub - 00-matt/randomx-stress: Cook your computer.) but generally you'll have to just use the computer for a few weeks.

That's an interesting note on the dual GPUs, I've only had experience mixing Intel iGPUs and dGPUs but in my experience I had to run two separate screens with one connected to each, no switching on the go like Optimus.
 
Last edited:
Joined
Jul 24, 2018
Messages
33 (0.01/day)
Progress on E Die.

3800-1900-8.png
 
Joined
Aug 9, 2019
Messages
1,695 (0.87/day)
Processor 7800X3D 2x16GB CO
Motherboard Asrock B650m HDV
Cooling Peerless Assassin SE
Memory 2x16GB DR A-die@6000c30 tuned
Video Card(s) Asus 4070 dual OC 2610@915mv
Storage WD blue 1TB nvme
Display(s) Lenovo G24-10 144Hz
Case Corsair D4000 Airflow
Power Supply EVGA GQ 650W
Software Windows 10 home 64
Benchmark Scores Superposition 8k 5267 Aida64 58.5ns
Good job. What voltage are you running? With 1.45V you might be able to do cl15 and 1t or 2t. 2t is easiest, grar down mode does not work with cl15. You might have to up trcdrd to 20. tWR might do 10 and tRP might do 5, except for that there is very little you can do.
 
Joined
Jul 24, 2018
Messages
33 (0.01/day)
Good job. What voltage are you running? With 1.45V you might be able to do cl15 and 1t or 2t. 2t is easiest, grar down mode does not work with cl15. You might have to up trcdrd to 20. tWR might do 10 and tRP might do 5, except for that there is very little you can do.

Thanks, your advice helped :)

Still 1.4v. Not looking to push it too much further for 24/7. I'm pretty happy with current speeds at those volts. I tried 2t with cl15 and even loosening up other timings i just couldn't seem to get it stable. 1.45v probably would be possible but doesn't really seem worth it to me.

I was able to drop tWRRD to 2, tWTRS to 2 and tWTRL to 5, seems stable so far.

I also could drop tWR to 10 but then I have to loosen tRDWR and tWRRD for stability, it seemed that having lower tRDWR and tWRRD was a bit faster. tRP won't go any lower right now without stability issues, would probably have to loosen something else, I don't remember which timing has to be loosened now. Lots of numbers. :)
 

freeagent

Moderator
Staff member
Joined
Sep 16, 2018
Messages
8,560 (3.78/day)
Location
Winnipeg, Canada
Processor AMD R7 5800X3D
Motherboard Asus Crosshair VIII Dark Hero
Cooling Thermalright Frozen Edge 360, 3x TL-B12 V2, 2x TL-B12 V1
Memory 2x8 G.Skill Trident Z Royal 3200C14, 2x8GB G.Skill Trident Z Black and White 3200 C14
Video Card(s) Zotac 4070 Ti Trinity OC
Storage WD SN850 1TB, SN850X 2TB, SN770 1TB
Display(s) LG 50UP7100
Case Fractal Torrent Compact
Audio Device(s) JBL Bar 700
Power Supply Seasonic Vertex GX-1000, Monster HDP1800
Mouse Logitech G502 Hero
Keyboard Logitech G213
VR HMD Oculus 3
Software Yes
Benchmark Scores Yes
Its really tough trying to crack that low latency that I could touch with the 5600. Its also tough running over 1900 1:1 without WHEA errors. I haven't had a lot of time to research what safe voltages are for this thing. Old VDDG and VDDP settings that I used on my 5600 have no effect here.. Could barely get 4 sticks to run at 1900 1:1 on my 5600, but on the 5900 it does it no sweat.. Maybe its an AGESA thing.. or I just need to spend some more time getting to know her..

Looks like the moves worked on my old girl don't work with this girl.. I have to tap into my powers of persuasion somehow :laugh:

Capture.JPG
 
Joined
Sep 27, 2019
Messages
1,212 (0.64/day)
Location
Canada
System Name New compy
Processor AMD Ryzen 5800x3D
Motherboard MSI MPG x570S EDGE MAX WiFi
Cooling Noctua NH-D15S w. FHP141 + Xigmatek AOS XAF-F1451
Memory 32gb G.Skill Ripjaws V Samsung B-Die Dual Rank F4-4000C16D-32GVKA
Video Card(s) ASUS TUF GAMING RTX 4070ti
Storage 17tb (8+4tb WD Black HDD's, 2+2+0.5+0.5tb M.2 SSD Drives) + 16tb WD Red Pro backup drive
Display(s) Alienware AW2518H 24" 240hz, Sony X85K 43" 4k 120hz HDR TV
Case Thermaltake Core v71
Audio Device(s) iFi Nano Idsd Le, Creative T20 + T50, Sennheiser HD6Mix
Power Supply EVGA Supernova G2 1000w
Mouse Logitech G502 Hero custom w. G900 scroll wheel mod, Rival 3 + Rival 3 wireless, JLab Epic Mouse
Keyboard Corsair K68 RGB + K70 RGB + K57 RGB Wireless + Logitech G613
Software Win 10 Pro
Benchmark Scores https://valid.x86.fr/s2y7ny
Here's where I'm at stable after setting 2t timing, it reduced my latency.

1zen2t.jpg


And at 1866

1zen2t1866.jpg
 
Last edited:

freeagent

Moderator
Staff member
Joined
Sep 16, 2018
Messages
8,560 (3.78/day)
Location
Winnipeg, Canada
Processor AMD R7 5800X3D
Motherboard Asus Crosshair VIII Dark Hero
Cooling Thermalright Frozen Edge 360, 3x TL-B12 V2, 2x TL-B12 V1
Memory 2x8 G.Skill Trident Z Royal 3200C14, 2x8GB G.Skill Trident Z Black and White 3200 C14
Video Card(s) Zotac 4070 Ti Trinity OC
Storage WD SN850 1TB, SN850X 2TB, SN770 1TB
Display(s) LG 50UP7100
Case Fractal Torrent Compact
Audio Device(s) JBL Bar 700
Power Supply Seasonic Vertex GX-1000, Monster HDP1800
Mouse Logitech G502 Hero
Keyboard Logitech G213
VR HMD Oculus 3
Software Yes
Benchmark Scores Yes
I do like my phat bottoms :toast:

Capture.JPG
 

freeagent

Moderator
Staff member
Joined
Sep 16, 2018
Messages
8,560 (3.78/day)
Location
Winnipeg, Canada
Processor AMD R7 5800X3D
Motherboard Asus Crosshair VIII Dark Hero
Cooling Thermalright Frozen Edge 360, 3x TL-B12 V2, 2x TL-B12 V1
Memory 2x8 G.Skill Trident Z Royal 3200C14, 2x8GB G.Skill Trident Z Black and White 3200 C14
Video Card(s) Zotac 4070 Ti Trinity OC
Storage WD SN850 1TB, SN850X 2TB, SN770 1TB
Display(s) LG 50UP7100
Case Fractal Torrent Compact
Audio Device(s) JBL Bar 700
Power Supply Seasonic Vertex GX-1000, Monster HDP1800
Mouse Logitech G502 Hero
Keyboard Logitech G213
VR HMD Oculus 3
Software Yes
Benchmark Scores Yes
Hell yeah man, now were getting somewhere.. shes got some more left in her, I promise you can get into the 35ns range, maybe even lower.. but you would have to give up some mem clock and trade for tighter timings and 1T in exchange for mucho more vdimm. That CPU is the crown jewel for that gen, she is a ripper and will dump like a truck if you tell her to. This bench loves CPU speed.. as well as memory speed, uncore, and.. pretty much anything to do with speed.
 

AMF

Joined
Apr 28, 2021
Messages
689 (0.53/day)
Location
USA
System Name MR T System price 2280$
Processor Ryzen 9 3900x 325 $4.7Ghz boost pbo +50 +50 enhance - offset auto voltage -.1875 offset soc
Motherboard ROG STRIX X570-E Gaming 125 $ open box
Cooling 280mm ARCTIC FREEZER II idle temps 25c cpu 28c cpu diode 20c vrm 25c motherboard b stock 60$
Memory 2x 16GB Dual rank G Skill Trident Z Neo F4-3600C16-16GTZNC @3800 1.395v 16-19-16-20-38-58-1T $96
Video Card(s) Asrock RX 6950XT Oc formula Oc edition 705$ 2700 2800 boost 1090v 2476 mem 19GB/s
Storage 500 GB WD SN850 PCI-E 4.0x4 85$ pcie16x4
Display(s) V505-J09 Vizio 4k HDR 299$ oc 5hz
Case Cougar Panzer Max G Full Tower Tempered Glass 150$
Audio Device(s) TV junk ewww
Power Supply Seasonic SS-1250XM2 Bought in 2013 350$ 11 y/o hasnt lost any voltage or watts
Mouse Logitech ERGO Trackball 35$
Keyboard Corsair K57 50$
VR HMD Dont give a damn about vr
Software win 11 pro modded by me no ai no remote connections free hehe
Benchmark Scores 8188 multi 540 single cinebench r20
vengence rgb pro ddr4 2666 oc to 3600 1.325v undervolted soc to 1.025 to help with heat works great fully 100% stable...... Note: i have great stability due to my seasonic1250w 104a single rail psu gold .... ull have to pry it from my cold dead hands ...... has been thru 3 bulds over the past 8 years or so
 

Attachments

  • cachemem.png
    cachemem.png
    92.7 KB · Views: 245
  • gpgpu.png
    gpgpu.png
    125.6 KB · Views: 271
Last edited by a moderator:
Joined
May 7, 2011
Messages
1 (0.00/day)
Are these result ok , i feel i have some timings wrong , not finished yet
5900x, B550-F 2x8Gb Corsair Hynix CJR A2 mem
 

Attachments

  • Zt.png
    Zt.png
    32.3 KB · Views: 216
  • aida64score.png
    aida64score.png
    91.3 KB · Views: 211
Joined
Nov 11, 2020
Messages
298 (0.20/day)
  • 5950x @ custom water+TechN block with latest CTR running
  • 4x8GB (gskill 3600 cl16) running flat 14-14-14 timings running on T1 setup-time (no GDM)
  • Minimum required vdimm = 1.54v (maxtemp below 40degress even when gaming with a 3090)
  • Everyday settings = ~290 game cpu fps in SotTR @ 1080p lowest (300fps when pushed)
  • 100% stable as the stresstesting and benchmarking-screens below will show

1623533172489.png


Some of my stability testing: (worse latency because everything running)
1623533702151.png
1623533754927.png
1623534629712.png
1623533810679.png


@FilipM that reminds me, the old GDM vs 2T debate seems to be rather interesting. 2T is *sometimes* faster in membench by half a second or so. But GDM consistently wins in AIDA read/write by about 500MB/s and copy by about 200MB/s. GDM might also be leading to better GPU performance, but I'll need to bench that.
Have been benching the performance difference between "pure T1", T1 GDM and T2 in the Monero miner which is known to scale very well with both speed (bandwidth) and timings (latency).

The goal was to decide once and for all whether T1 GDM actually is slower than T2 due to half speed on mux, in real applications ->not synthetic aida64 .. But this benchmark can also be used to test whether you actually scale with higher flck speeds above 1900mhz (which it seems hardly anyone really does outside running aida64 and thinking they have improved performance, while actually getting lower numbers in "real benchmarks")

Settings:
  • 5950x @ 4700/4600 static OC, SMT enabled
  • 4x8GB memory sticks
  • Hwinfo open for all runs
  • consecutive runs
  • Flat CL 14-14-14-14 timings
T1 setuptime.png
T1 setup-time
19723.4 H/S over 15min run
upto 627 H/S per core

T1 GDM.png
T1 GDM
19151 H/S over 15min run
upto 606 H/S per core

T2.png
T2
19413 H/S over 15min run
upto 616 H/S per core

  • 19413 / 19151 = T2 is ~1.3% faster than T1 GDM in this benchmark
  • 19723 / 19413 = T1 setup-time is ~1.6% faster than T2 in this benchmark
  • 19723 / 19151 = T1 setup-time is ~2.9% faster than T1 GDM in this benchmark
So I come to the conclusion that T2 is faster than T1 GDM .. But this is also a bit dependent on the fact that you actually have stable T2 settings.

T2 is more difficult to stabilize than T1 GDM as the latter "smooths over" / arranges and/or changes timing-mismatches, so if you want to retrieve these last 1.3% memory performance percentages then be prepared to spend many hours fine-tuning your settings .. For the regular user is it rather doubtful that this is worth it, as the time is probably better spent maximizing CPU overclocking in my eyes, as virtually everything scales with higher CPU speed..

I can also say that the degree of difficulty to stabilize "pure T1" is in a another league, especially with dual rank. (32GB or more)

Aida64 screenshot of my fastest T1 setup-time with my new 24/7 settings for CTR. (notice how straight the CPU mhz line is in 3dmark Timespy with this new version of CTR)
1623542877102.png
If anyone else wants to test / bench with the same mining program: Instructions for installing monero can be found here
 
Last edited:

Slammey

New Member
Joined
Jun 17, 2021
Messages
2 (0.00/day)
Hi everyone,

Just got the 3600 neo kit C14 and fiddled a bit. 4x16gb dual channel kits.

Meg Ace x570 - 5950x

What do you think and is there more juice I could pull out.

Temps on Aida64 bench don't go more than 40c

Thanksl

20210617_115614.jpg


Hi everyone,

Just got the 3600 neo kit C14 and fiddled a bit. 4x16gb dual channel kits.

Meg Ace x570 - 5950x

What do you think and is there more juice I could pull out.

Temps on Aida64 bench don't go more than 40c

Thanksl

20210617_115614.jpg

An other one..

20210617_182503.jpg
 

freeagent

Moderator
Staff member
Joined
Sep 16, 2018
Messages
8,560 (3.78/day)
Location
Winnipeg, Canada
Processor AMD R7 5800X3D
Motherboard Asus Crosshair VIII Dark Hero
Cooling Thermalright Frozen Edge 360, 3x TL-B12 V2, 2x TL-B12 V1
Memory 2x8 G.Skill Trident Z Royal 3200C14, 2x8GB G.Skill Trident Z Black and White 3200 C14
Video Card(s) Zotac 4070 Ti Trinity OC
Storage WD SN850 1TB, SN850X 2TB, SN770 1TB
Display(s) LG 50UP7100
Case Fractal Torrent Compact
Audio Device(s) JBL Bar 700
Power Supply Seasonic Vertex GX-1000, Monster HDP1800
Mouse Logitech G502 Hero
Keyboard Logitech G213
VR HMD Oculus 3
Software Yes
Benchmark Scores Yes
That 5950x is pretty fast! Like my 5600x wtf? I can hit 51ns range and lower with it but I have not been below 53ns on my 5900x, and I had to lean on it to do that.. Also gets errors over 1900 fclk.. dagnabbit.
 

Slammey

New Member
Joined
Jun 17, 2021
Messages
2 (0.00/day)
That 5950x is pretty fast! Like my 5600x wtf? I can hit 51ns range and lower with it but I have not been below 53ns on my 5900x, and I had to lean on it to do that.. Also gets errors over 1900 fclk.. dagnabbit.

Gonna do more testing.. Feel like I still have room somewhere loll
 

freeagent

Moderator
Staff member
Joined
Sep 16, 2018
Messages
8,560 (3.78/day)
Location
Winnipeg, Canada
Processor AMD R7 5800X3D
Motherboard Asus Crosshair VIII Dark Hero
Cooling Thermalright Frozen Edge 360, 3x TL-B12 V2, 2x TL-B12 V1
Memory 2x8 G.Skill Trident Z Royal 3200C14, 2x8GB G.Skill Trident Z Black and White 3200 C14
Video Card(s) Zotac 4070 Ti Trinity OC
Storage WD SN850 1TB, SN850X 2TB, SN770 1TB
Display(s) LG 50UP7100
Case Fractal Torrent Compact
Audio Device(s) JBL Bar 700
Power Supply Seasonic Vertex GX-1000, Monster HDP1800
Mouse Logitech G502 Hero
Keyboard Logitech G213
VR HMD Oculus 3
Software Yes
Benchmark Scores Yes
Just messin around..

Capture.PNG
 
Joined
Aug 9, 2019
Messages
1,695 (0.87/day)
Processor 7800X3D 2x16GB CO
Motherboard Asrock B650m HDV
Cooling Peerless Assassin SE
Memory 2x16GB DR A-die@6000c30 tuned
Video Card(s) Asus 4070 dual OC 2610@915mv
Storage WD blue 1TB nvme
Display(s) Lenovo G24-10 144Hz
Case Corsair D4000 Airflow
Power Supply EVGA GQ 650W
Software Windows 10 home 64
Benchmark Scores Superposition 8k 5267 Aida64 58.5ns

tabascosauz

Moderator
Supporter
Staff member
Joined
Jun 24, 2015
Messages
8,153 (2.37/day)
Location
Western Canada
System Name ab┃ob
Processor 7800X3D┃5800X3D
Motherboard B650E PG-ITX┃X570 Impact
Cooling NH-U12A + T30┃AXP120-x67
Memory 64GB 6400CL32┃32GB 3600CL14
Video Card(s) RTX 4070 Ti Eagle┃RTX A2000
Storage 8TB of SSDs┃1TB SN550
Case Caselabs S3┃Lazer3D HT5
Holy shit, is that stable? Latency is high with that speed/timings, I think vsoc and iod voltage is too low. Try 1.2V soc and 1.1V iod, I bet latency will be atleast 5ns lower :)

It's not 1:1, top right corner

That said, I'm surprised Copy is so high at 2:1. Usually Ryzen of all types suffer significantly on Copy once not synced, Write speed is more along the lines of what I was expecting from all 3 R/W/C
 

freeagent

Moderator
Staff member
Joined
Sep 16, 2018
Messages
8,560 (3.78/day)
Location
Winnipeg, Canada
Processor AMD R7 5800X3D
Motherboard Asus Crosshair VIII Dark Hero
Cooling Thermalright Frozen Edge 360, 3x TL-B12 V2, 2x TL-B12 V1
Memory 2x8 G.Skill Trident Z Royal 3200C14, 2x8GB G.Skill Trident Z Black and White 3200 C14
Video Card(s) Zotac 4070 Ti Trinity OC
Storage WD SN850 1TB, SN850X 2TB, SN770 1TB
Display(s) LG 50UP7100
Case Fractal Torrent Compact
Audio Device(s) JBL Bar 700
Power Supply Seasonic Vertex GX-1000, Monster HDP1800
Mouse Logitech G502 Hero
Keyboard Logitech G213
VR HMD Oculus 3
Software Yes
Benchmark Scores Yes
I noticed that too and thought it was Aida being Aida, but it was repeatable.. I have to play with it more to stabilize.. tm5 would run for a minute or so before errors would start..

Edit:

my copies were high like that too with the 5600 come to think of it it’s the writes that surprised me.. first time running un synced..
 

companyja

New Member
Joined
Jun 21, 2021
Messages
1 (0.00/day)
Hey mates, I upgraded my CPU from a 6600k for rather cheap to play a few specific CPU-heavy games and I was trying to extract as much as I could from my very old Kingston 2x8GB 2133 CL14 kit (Micron rev. B). This is as much as I've been able to extract from it while being absolutely stable:

cachemem95.png


That's 3200 on 16-19-19-36 and a tRFC of 438, CR1.. Voltage is on 1.45V, so rather high, and higher than that leads to instability no matter the timings. I can get a few things to run on 3400 16-20-20-38 but it doesn't pass memtest64 for example, so I don't want to run that 24/7. Are there any tertieary timings I can maybe mess with? I see that my "Copy" score is lagging behind quite a bit and my speeds in general are not impressive compared to the ones on here, but my latency is looking okay I think.

I could get 3600 17-21-21-40 to run but with much looser tertiary timings (Gigabyte has a few modes such as Normal/Enhanced Stability/Enhanced Performance, 3600 could only get stable on enhanced stability) and a tRFC of around 500 and CR2T, but scores were way lower with increased latency, in the low 30000s. I'm thinking 3200 is the highest speed that gets me 100% stable but I don't know if there are additional timings to tighten up to extract some more performance. Cheers mates!
 
Joined
Apr 18, 2013
Messages
1,260 (0.30/day)
Location
Artem S. Tashkinov
Stock Ryzen 7 5800X except for a 0.05V undervolt.

16GB x 4 DDR4 3600MHz

cachemem.png
cpuid.png
 

Attachments

  • gpgpu.png
    gpgpu.png
    83.1 KB · Views: 198

HelloHell

New Member
Joined
Jun 27, 2021
Messages
1 (0.00/day)
My result, the ram voltage is 1.42v. Stable and WHEA error free with 2000 FCLK.

latencia1.PNG

hwinfo 7 hours of use without WHEA is actually months

mu41vqp5xyd61.jpg
 
Joined
Nov 11, 2020
Messages
298 (0.20/day)
  • 5950x @ custom water+TechN block with latest CTR running
  • 4x8GB (gskill 3600 cl16) running flat 14-14-14 timings running on T1 setup-time (no GDM)
  • Minimum required vdimm = 1.54v (maxtemp below 40degress even when gaming with a 3090)
  • Everyday settings = ~290 game cpu fps in SotTR @ 1080p lowest (300fps when pushed)
  • 100% stable as the stresstesting and benchmarking-screens below will show

View attachment 203613

Some of my stability testing: (worse latency because everything running)
View attachment 203616
View attachment 203617
View attachment 203624
View attachment 203618


Have been benching the performance difference between "pure T1", T1 GDM and T2 in the Monero miner which is known to scale very well with both speed (bandwidth) and timings (latency).

The goal was to decide once and for all whether T1 GDM actually is slower than T2 due to half speed on mux, in real applications ->not synthetic aida64 .. But this benchmark can also be used to test whether you actually scale with higher flck speeds above 1900mhz (which it seems hardly anyone really does outside running aida64 and thinking they have improved performance, while actually getting lower numbers in "real benchmarks")

Settings:
  • 5950x @ 4700/4600 static OC, SMT enabled
  • 4x8GB memory sticks
  • Hwinfo open for all runs
  • consecutive runs
  • Flat CL 14-14-14-14 timings
View attachment 203651
T1 setup-time
19723.4 H/S over 15min run
upto 627 H/S per core

View attachment 203652
T1 GDM
19151 H/S over 15min run
upto 606 H/S per core

View attachment 203653
T2
19413 H/S over 15min run
upto 616 H/S per core

  • 19413 / 19151 = T2 is ~1.3% faster than T1 GDM in this benchmark
  • 19723 / 19413 = T1 setup-time is ~1.6% faster than T2 in this benchmark
  • 19723 / 19151 = T1 setup-time is ~2.9% faster than T1 GDM in this benchmark
So I come to the conclusion that T2 is faster than T1 GDM .. But this is also a bit dependent on the fact that you actually have stable T2 settings.

T2 is more difficult to stabilize than T1 GDM as the latter "smooths over" / arranges and/or changes timing-mismatches, so if you want to retrieve these last 1.3% memory performance percentages then be prepared to spend many hours fine-tuning your settings .. For the regular user is it rather doubtful that this is worth it, as the time is probably better spent maximizing CPU overclocking in my eyes, as virtually everything scales with higher CPU speed..

I can also say that the degree of difficulty to stabilize "pure T1" is in a another league, especially with dual rank. (32GB or more)

Aida64 screenshot of my fastest T1 setup-time with my new 24/7 settings for CTR. (notice how straight the CPU mhz line is in 3dmark Timespy with this new version of CTR)
View attachment 203654
If anyone else wants to test / bench with the same mining program: Instructions for installing monero can be found here
Some more testing in windows11 :)

Getting some pretty good numbers in dram calc and for Aida64 memory latency.. 51.5ns for a dual ccd 5950x @ 1900:3800 IF aint too shabby :)
There is something wrong with how Aida64 reads the L3 numbers in Windows11... But aida is a synthetic app and its real performance in real programs that should matter
stabil-testing-4.JPG


Intel latency tester
stabil-testing-6.JPG

Sandra inter thread efficiency benchmark
start-sandra-4.JPG
SiSoftware Sandra

Benchmark Results
Aggregate Inter-Thread Bandwidth : 157.91GB/s
Results Interpretation : Higher Scores mean Better Performance.
Binary Numeral System (base 2) : 1GB(/s) = 1024MB(/s), 1MB(/s) = 1024kB(/s), 1kB(/s) = 1024 bytes(/s), etc.

Benchmark Results
Average Inter-Thread Latency : 40.7ns (9.9ns - 63.4ns)
Inter-Thread (same Core) Latency : 10.0ns
Inter-Core (same Module) Latency : 20.9ns
Inter-Module (same Package) Latency : 59.6ns
Results Interpretation : Lower Scores mean Better Performance.
Decimal Numeral System (base 10) : 1s = 1000ms, 1ms = 1000µs, 1µs = 1000ns, etc.

Performance per Thread
Aggregate Inter-Thread Bandwidth : 5GB/s
No. Threads : 32
Results Interpretation : Higher Scores mean Better Performance.
Binary Numeral System (base 2) : 1GB(/s) = 1024MB(/s), 1MB(/s) = 1024kB(/s), 1kB(/s) = 1024 bytes(/s), etc.

Performance vs. Power
Processor(s) Power : 105.00W
Aggregate Inter-Thread Bandwidth : 1540.01MB/s/W
Results Interpretation : Higher Scores mean Better Performance.
Average Inter-Thread Latency : 3.88ns/W
Results Interpretation : Lower Scores mean Better Performance.

Capacity vs. Power
Total Cache Size : 707.05kB/W
Results Interpretation : Higher Scores mean Better Performance.

Performance vs. Speed
Aggregate Inter-Thread Bandwidth : 33.69MB/s/MHz
Results Interpretation : Higher Scores mean Better Performance.
Average Inter-Thread Latency : 0.08ns/MHz
Results Interpretation : Lower Scores mean Better Performance.

Detailed Results
Processor Affinity : U0-U1 U2-U3 U4-U5 U6-U7 U8-U9 U10-U11 U12-U13 U14-U15 U16-U17 U18-U19 U20-U21 U22-U23 U24-U25 U26-U27 U28-U29 U30-U31
U0-M0C0T0 <> U2-M0C1T0 Data Latency : 19.8ns
U0-M0C0T0 <> U4-M0C2T0 Data Latency : 22.0ns
U0-M0C0T0 <> U6-M0C3T0 Data Latency : 19.0ns
U0-M0C0T0 <> U8-M0C4T0 Data Latency : 19.9ns
U0-M0C0T0 <> U10-M0C5T0 Data Latency : 19.7ns
U0-M0C0T0 <> U12-M0C6T0 Data Latency : 20.6ns
U0-M0C0T0 <> U14-M0C7T0 Data Latency : 20.4ns
U0-M0C0T0 <> U16-M1C0T0 Data Latency : 61.8ns
U0-M0C0T0 <> U18-M1C1T0 Data Latency : 62.2ns
U0-M0C0T0 <> U20-M1C2T0 Data Latency : 62.0ns
U0-M0C0T0 <> U22-M1C3T0 Data Latency : 61.9ns
U0-M0C0T0 <> U24-M1C4T0 Data Latency : 61.5ns
U0-M0C0T0 <> U26-M1C5T0 Data Latency : 61.7ns
U0-M0C0T0 <> U28-M1C6T0 Data Latency : 60.9ns
U0-M0C0T0 <> U30-M1C7T0 Data Latency : 58.7ns
U0-M0C0T0 <> U1-M0C0T1 Data Latency : 10.0ns
U0-M0C0T0 <> U3-M0C1T1 Data Latency : 18.5ns
U0-M0C0T0 <> U5-M0C2T1 Data Latency : 19.4ns
U0-M0C0T0 <> U7-M0C3T1 Data Latency : 19.1ns
U0-M0C0T0 <> U9-M0C4T1 Data Latency : 20.1ns
U0-M0C0T0 <> U11-M0C5T1 Data Latency : 19.7ns
U0-M0C0T0 <> U13-M0C6T1 Data Latency : 20.9ns
U0-M0C0T0 <> U15-M0C7T1 Data Latency : 20.5ns
U0-M0C0T0 <> U17-M1C0T1 Data Latency : 56.6ns
U0-M0C0T0 <> U19-M1C1T1 Data Latency : 56.8ns
U0-M0C0T0 <> U21-M1C2T1 Data Latency : 57.6ns
U0-M0C0T0 <> U23-M1C3T1 Data Latency : 57.4ns
U0-M0C0T0 <> U25-M1C4T1 Data Latency : 58.0ns
U0-M0C0T0 <> U27-M1C5T1 Data Latency : 58.1ns
U0-M0C0T0 <> U29-M1C6T1 Data Latency : 58.6ns
U0-M0C0T0 <> U31-M1C7T1 Data Latency : 58.7ns
U2-M0C1T0 <> U4-M0C2T0 Data Latency : 19.1ns
U2-M0C1T0 <> U6-M0C3T0 Data Latency : 19.4ns
U2-M0C1T0 <> U8-M0C4T0 Data Latency : 19.7ns
U2-M0C1T0 <> U10-M0C5T0 Data Latency : 20.1ns
U2-M0C1T0 <> U12-M0C6T0 Data Latency : 20.5ns
U2-M0C1T0 <> U14-M0C7T0 Data Latency : 20.9ns
U2-M0C1T0 <> U16-M1C0T0 Data Latency : 56.7ns
U2-M0C1T0 <> U18-M1C1T0 Data Latency : 56.5ns
U2-M0C1T0 <> U20-M1C2T0 Data Latency : 57.5ns
U2-M0C1T0 <> U22-M1C3T0 Data Latency : 57.5ns
U2-M0C1T0 <> U24-M1C4T0 Data Latency : 58.1ns
U2-M0C1T0 <> U26-M1C5T0 Data Latency : 57.9ns
U2-M0C1T0 <> U28-M1C6T0 Data Latency : 58.7ns
U2-M0C1T0 <> U30-M1C7T0 Data Latency : 58.4ns
U2-M0C1T0 <> U1-M0C0T1 Data Latency : 18.9ns
U2-M0C1T0 <> U3-M0C1T1 Data Latency : 9.9ns
U2-M0C1T0 <> U5-M0C2T1 Data Latency : 19.1ns
U2-M0C1T0 <> U7-M0C3T1 Data Latency : 19.4ns
U2-M0C1T0 <> U9-M0C4T1 Data Latency : 19.7ns
U2-M0C1T0 <> U11-M0C5T1 Data Latency : 20.1ns
U2-M0C1T0 <> U13-M0C6T1 Data Latency : 20.4ns
U2-M0C1T0 <> U15-M0C7T1 Data Latency : 20.9ns
U2-M0C1T0 <> U17-M1C0T1 Data Latency : 56.5ns
U2-M0C1T0 <> U19-M1C1T1 Data Latency : 56.5ns
U2-M0C1T0 <> U21-M1C2T1 Data Latency : 57.5ns
U2-M0C1T0 <> U23-M1C3T1 Data Latency : 57.6ns
U2-M0C1T0 <> U25-M1C4T1 Data Latency : 58.1ns
U2-M0C1T0 <> U27-M1C5T1 Data Latency : 57.9ns
U2-M0C1T0 <> U29-M1C6T1 Data Latency : 58.6ns
U2-M0C1T0 <> U31-M1C7T1 Data Latency : 58.5ns
U4-M0C2T0 <> U6-M0C3T0 Data Latency : 19.8ns
U4-M0C2T0 <> U8-M0C4T0 Data Latency : 20.7ns
U4-M0C2T0 <> U10-M0C5T0 Data Latency : 20.5ns
U4-M0C2T0 <> U12-M0C6T0 Data Latency : 21.6ns
U4-M0C2T0 <> U14-M0C7T0 Data Latency : 21.2ns
U4-M0C2T0 <> U16-M1C0T0 Data Latency : 57.2ns
U4-M0C2T0 <> U18-M1C1T0 Data Latency : 57.2ns
U4-M0C2T0 <> U20-M1C2T0 Data Latency : 58.2ns
U4-M0C2T0 <> U22-M1C3T0 Data Latency : 58.1ns
U4-M0C2T0 <> U24-M1C4T0 Data Latency : 58.7ns
U4-M0C2T0 <> U26-M1C5T0 Data Latency : 58.6ns
U4-M0C2T0 <> U28-M1C6T0 Data Latency : 59.3ns
U4-M0C2T0 <> U30-M1C7T0 Data Latency : 59.4ns
U4-M0C2T0 <> U1-M0C0T1 Data Latency : 19.6ns
U4-M0C2T0 <> U3-M0C1T1 Data Latency : 19.1ns
U4-M0C2T0 <> U5-M0C2T1 Data Latency : 9.9ns
U4-M0C2T0 <> U7-M0C3T1 Data Latency : 19.8ns
U4-M0C2T0 <> U9-M0C4T1 Data Latency : 20.8ns
U4-M0C2T0 <> U11-M0C5T1 Data Latency : 20.5ns
U4-M0C2T0 <> U13-M0C6T1 Data Latency : 21.6ns
U4-M0C2T0 <> U15-M0C7T1 Data Latency : 21.2ns
U4-M0C2T0 <> U17-M1C0T1 Data Latency : 57.2ns
U4-M0C2T0 <> U19-M1C1T1 Data Latency : 58.5ns
U4-M0C2T0 <> U21-M1C2T1 Data Latency : 58.1ns
U4-M0C2T0 <> U23-M1C3T1 Data Latency : 58.2ns
U4-M0C2T0 <> U25-M1C4T1 Data Latency : 58.5ns
U4-M0C2T0 <> U27-M1C5T1 Data Latency : 58.7ns
U4-M0C2T0 <> U29-M1C6T1 Data Latency : 59.2ns
U4-M0C2T0 <> U31-M1C7T1 Data Latency : 59.5ns
U6-M0C3T0 <> U8-M0C4T0 Data Latency : 20.5ns
U6-M0C3T0 <> U10-M0C5T0 Data Latency : 20.8ns
U6-M0C3T0 <> U12-M0C6T0 Data Latency : 21.2ns
U6-M0C3T0 <> U14-M0C7T0 Data Latency : 21.6ns
U6-M0C3T0 <> U16-M1C0T0 Data Latency : 57.3ns
U6-M0C3T0 <> U18-M1C1T0 Data Latency : 57.3ns
U6-M0C3T0 <> U20-M1C2T0 Data Latency : 58.1ns
U6-M0C3T0 <> U22-M1C3T0 Data Latency : 58.2ns
U6-M0C3T0 <> U24-M1C4T0 Data Latency : 58.9ns
U6-M0C3T0 <> U26-M1C5T0 Data Latency : 58.6ns
U6-M0C3T0 <> U28-M1C6T0 Data Latency : 59.6ns
U6-M0C3T0 <> U30-M1C7T0 Data Latency : 59.2ns
U6-M0C3T0 <> U1-M0C0T1 Data Latency : 19.6ns
U6-M0C3T0 <> U3-M0C1T1 Data Latency : 19.4ns
U6-M0C3T0 <> U5-M0C2T1 Data Latency : 19.8ns
U6-M0C3T0 <> U7-M0C3T1 Data Latency : 9.9ns
U6-M0C3T0 <> U9-M0C4T1 Data Latency : 20.5ns
U6-M0C3T0 <> U11-M0C5T1 Data Latency : 20.8ns
U6-M0C3T0 <> U13-M0C6T1 Data Latency : 21.2ns
U6-M0C3T0 <> U15-M0C7T1 Data Latency : 21.6ns
U6-M0C3T0 <> U17-M1C0T1 Data Latency : 57.2ns
U6-M0C3T0 <> U19-M1C1T1 Data Latency : 57.1ns
U6-M0C3T0 <> U21-M1C2T1 Data Latency : 58.0ns
U6-M0C3T0 <> U23-M1C3T1 Data Latency : 58.1ns
U6-M0C3T0 <> U25-M1C4T1 Data Latency : 58.7ns
U6-M0C3T0 <> U27-M1C5T1 Data Latency : 58.4ns
U6-M0C3T0 <> U29-M1C6T1 Data Latency : 59.4ns
U6-M0C3T0 <> U31-M1C7T1 Data Latency : 59.2ns
U8-M0C4T0 <> U10-M0C5T0 Data Latency : 21.2ns
U8-M0C4T0 <> U12-M0C6T0 Data Latency : 22.2ns
U8-M0C4T0 <> U14-M0C7T0 Data Latency : 21.9ns
U8-M0C4T0 <> U16-M1C0T0 Data Latency : 57.7ns
U8-M0C4T0 <> U18-M1C1T0 Data Latency : 58.0ns
U8-M0C4T0 <> U20-M1C2T0 Data Latency : 58.6ns
U8-M0C4T0 <> U22-M1C3T0 Data Latency : 58.7ns
U8-M0C4T0 <> U24-M1C4T0 Data Latency : 59.1ns
U8-M0C4T0 <> U26-M1C5T0 Data Latency : 59.3ns
U8-M0C4T0 <> U28-M1C6T0 Data Latency : 59.7ns
U8-M0C4T0 <> U30-M1C7T0 Data Latency : 59.9ns
U8-M0C4T0 <> U1-M0C0T1 Data Latency : 20.4ns
U8-M0C4T0 <> U3-M0C1T1 Data Latency : 19.7ns
U8-M0C4T0 <> U5-M0C2T1 Data Latency : 20.7ns
U8-M0C4T0 <> U7-M0C3T1 Data Latency : 20.5ns
U8-M0C4T0 <> U9-M0C4T1 Data Latency : 9.9ns
U8-M0C4T0 <> U11-M0C5T1 Data Latency : 21.2ns
U8-M0C4T0 <> U13-M0C6T1 Data Latency : 22.2ns
U8-M0C4T0 <> U15-M0C7T1 Data Latency : 21.9ns
U8-M0C4T0 <> U17-M1C0T1 Data Latency : 57.9ns
U8-M0C4T0 <> U19-M1C1T1 Data Latency : 57.9ns
U8-M0C4T0 <> U21-M1C2T1 Data Latency : 58.5ns
U8-M0C4T0 <> U23-M1C3T1 Data Latency : 58.7ns
U8-M0C4T0 <> U25-M1C4T1 Data Latency : 59.1ns
U8-M0C4T0 <> U27-M1C5T1 Data Latency : 59.2ns
U8-M0C4T0 <> U29-M1C6T1 Data Latency : 59.8ns
U8-M0C4T0 <> U31-M1C7T1 Data Latency : 59.9ns
U10-M0C5T0 <> U12-M0C6T0 Data Latency : 21.9ns
U10-M0C5T0 <> U14-M0C7T0 Data Latency : 22.2ns
U10-M0C5T0 <> U16-M1C0T0 Data Latency : 58.0ns
U10-M0C5T0 <> U18-M1C1T0 Data Latency : 57.7ns
U10-M0C5T0 <> U20-M1C2T0 Data Latency : 58.8ns
U10-M0C5T0 <> U22-M1C3T0 Data Latency : 58.6ns
U10-M0C5T0 <> U24-M1C4T0 Data Latency : 59.2ns
U10-M0C5T0 <> U26-M1C5T0 Data Latency : 59.0ns
U10-M0C5T0 <> U28-M1C6T0 Data Latency : 59.9ns
U10-M0C5T0 <> U30-M1C7T0 Data Latency : 59.7ns
U10-M0C5T0 <> U1-M0C0T1 Data Latency : 20.4ns
U10-M0C5T0 <> U3-M0C1T1 Data Latency : 20.1ns
U10-M0C5T0 <> U5-M0C2T1 Data Latency : 20.5ns
U10-M0C5T0 <> U7-M0C3T1 Data Latency : 20.8ns
U10-M0C5T0 <> U9-M0C4T1 Data Latency : 21.2ns
U10-M0C5T0 <> U11-M0C5T1 Data Latency : 9.9ns
U10-M0C5T0 <> U13-M0C6T1 Data Latency : 21.9ns
U10-M0C5T0 <> U15-M0C7T1 Data Latency : 22.3ns
U10-M0C5T0 <> U17-M1C0T1 Data Latency : 58.3ns
U10-M0C5T0 <> U19-M1C1T1 Data Latency : 57.9ns
U10-M0C5T0 <> U21-M1C2T1 Data Latency : 59.0ns
U10-M0C5T0 <> U23-M1C3T1 Data Latency : 58.8ns
U10-M0C5T0 <> U25-M1C4T1 Data Latency : 59.4ns
U10-M0C5T0 <> U27-M1C5T1 Data Latency : 59.1ns
U10-M0C5T0 <> U29-M1C6T1 Data Latency : 59.9ns
U10-M0C5T0 <> U31-M1C7T1 Data Latency : 59.7ns
U12-M0C6T0 <> U14-M0C7T0 Data Latency : 22.4ns
U12-M0C6T0 <> U16-M1C0T0 Data Latency : 58.5ns
U12-M0C6T0 <> U18-M1C1T0 Data Latency : 58.8ns
U12-M0C6T0 <> U20-M1C2T0 Data Latency : 59.4ns
U12-M0C6T0 <> U22-M1C3T0 Data Latency : 59.5ns
U12-M0C6T0 <> U24-M1C4T0 Data Latency : 60.0ns
U12-M0C6T0 <> U26-M1C5T0 Data Latency : 60.0ns
U12-M0C6T0 <> U28-M1C6T0 Data Latency : 60.5ns
U12-M0C6T0 <> U30-M1C7T0 Data Latency : 60.4ns
U12-M0C6T0 <> U1-M0C0T1 Data Latency : 21.1ns
U12-M0C6T0 <> U3-M0C1T1 Data Latency : 20.6ns
U12-M0C6T0 <> U5-M0C2T1 Data Latency : 20.6ns
U12-M0C6T0 <> U7-M0C3T1 Data Latency : 20.8ns
U12-M0C6T0 <> U9-M0C4T1 Data Latency : 20.6ns
U12-M0C6T0 <> U11-M0C5T1 Data Latency : 21.1ns
U12-M0C6T0 <> U13-M0C6T1 Data Latency : 9.9ns
U12-M0C6T0 <> U15-M0C7T1 Data Latency : 21.7ns
U12-M0C6T0 <> U17-M1C0T1 Data Latency : 60.2ns
U12-M0C6T0 <> U19-M1C1T1 Data Latency : 59.7ns
U12-M0C6T0 <> U21-M1C2T1 Data Latency : 60.2ns
U12-M0C6T0 <> U23-M1C3T1 Data Latency : 60.2ns
U12-M0C6T0 <> U25-M1C4T1 Data Latency : 60.0ns
U12-M0C6T0 <> U27-M1C5T1 Data Latency : 60.4ns
U12-M0C6T0 <> U29-M1C6T1 Data Latency : 60.5ns
U12-M0C6T0 <> U31-M1C7T1 Data Latency : 60.3ns
U14-M0C7T0 <> U16-M1C0T0 Data Latency : 59.9ns
U14-M0C7T0 <> U18-M1C1T0 Data Latency : 59.5ns
U14-M0C7T0 <> U20-M1C2T0 Data Latency : 60.1ns
U14-M0C7T0 <> U22-M1C3T0 Data Latency : 60.4ns
U14-M0C7T0 <> U24-M1C4T0 Data Latency : 60.3ns
U14-M0C7T0 <> U26-M1C5T0 Data Latency : 60.5ns
U14-M0C7T0 <> U28-M1C6T0 Data Latency : 60.7ns
U14-M0C7T0 <> U30-M1C7T0 Data Latency : 60.1ns
U14-M0C7T0 <> U1-M0C0T1 Data Latency : 20.8ns
U14-M0C7T0 <> U3-M0C1T1 Data Latency : 21.1ns
U14-M0C7T0 <> U5-M0C2T1 Data Latency : 20.7ns
U14-M0C7T0 <> U7-M0C3T1 Data Latency : 21.5ns
U14-M0C7T0 <> U9-M0C4T1 Data Latency : 21.2ns
U14-M0C7T0 <> U11-M0C5T1 Data Latency : 22.0ns
U14-M0C7T0 <> U13-M0C6T1 Data Latency : 21.7ns
U14-M0C7T0 <> U15-M0C7T1 Data Latency : 9.9ns
U14-M0C7T0 <> U17-M1C0T1 Data Latency : 60.0ns
U14-M0C7T0 <> U19-M1C1T1 Data Latency : 59.6ns
U14-M0C7T0 <> U21-M1C2T1 Data Latency : 60.0ns
U14-M0C7T0 <> U23-M1C3T1 Data Latency : 60.5ns
U14-M0C7T0 <> U25-M1C4T1 Data Latency : 60.5ns
U14-M0C7T0 <> U27-M1C5T1 Data Latency : 60.6ns
U14-M0C7T0 <> U29-M1C6T1 Data Latency : 60.6ns
U14-M0C7T0 <> U31-M1C7T1 Data Latency : 60.1ns
U16-M1C0T0 <> U18-M1C1T0 Data Latency : 22.2ns
U16-M1C0T0 <> U20-M1C2T0 Data Latency : 22.5ns
U16-M1C0T0 <> U22-M1C3T0 Data Latency : 21.7ns
U16-M1C0T0 <> U24-M1C4T0 Data Latency : 22.0ns
U16-M1C0T0 <> U26-M1C5T0 Data Latency : 21.2ns
U16-M1C0T0 <> U28-M1C6T0 Data Latency : 21.5ns
U16-M1C0T0 <> U30-M1C7T0 Data Latency : 21.1ns
U16-M1C0T0 <> U1-M0C0T1 Data Latency : 61.4ns
U16-M1C0T0 <> U3-M0C1T1 Data Latency : 60.0ns
U16-M1C0T0 <> U5-M0C2T1 Data Latency : 60.7ns
U16-M1C0T0 <> U7-M0C3T1 Data Latency : 59.7ns
U16-M1C0T0 <> U9-M0C4T1 Data Latency : 60.0ns
U16-M1C0T0 <> U11-M0C5T1 Data Latency : 59.9ns
U16-M1C0T0 <> U13-M0C6T1 Data Latency : 60.3ns
U16-M1C0T0 <> U15-M0C7T1 Data Latency : 60.1ns
U16-M1C0T0 <> U17-M1C0T1 Data Latency : 10.1ns
U16-M1C0T0 <> U19-M1C1T1 Data Latency : 22.2ns
U16-M1C0T0 <> U21-M1C2T1 Data Latency : 22.5ns
U16-M1C0T0 <> U23-M1C3T1 Data Latency : 21.7ns
U16-M1C0T0 <> U25-M1C4T1 Data Latency : 22.0ns
U16-M1C0T0 <> U27-M1C5T1 Data Latency : 21.2ns
U16-M1C0T0 <> U29-M1C6T1 Data Latency : 21.5ns
U16-M1C0T0 <> U31-M1C7T1 Data Latency : 21.1ns
U18-M1C1T0 <> U20-M1C2T0 Data Latency : 21.6ns
U18-M1C1T0 <> U22-M1C3T0 Data Latency : 21.1ns
U18-M1C1T0 <> U24-M1C4T0 Data Latency : 21.2ns
U18-M1C1T0 <> U26-M1C5T0 Data Latency : 21.1ns
U18-M1C1T0 <> U28-M1C6T0 Data Latency : 21.0ns
U18-M1C1T0 <> U30-M1C7T0 Data Latency : 21.5ns
U18-M1C1T0 <> U1-M0C0T1 Data Latency : 60.7ns
U18-M1C1T0 <> U3-M0C1T1 Data Latency : 59.5ns
U18-M1C1T0 <> U5-M0C2T1 Data Latency : 59.9ns
U18-M1C1T0 <> U7-M0C3T1 Data Latency : 59.6ns
U18-M1C1T0 <> U9-M0C4T1 Data Latency : 59.8ns
U18-M1C1T0 <> U11-M0C5T1 Data Latency : 59.3ns
U18-M1C1T0 <> U13-M0C6T1 Data Latency : 59.7ns
U18-M1C1T0 <> U15-M0C7T1 Data Latency : 59.6ns
U18-M1C1T0 <> U17-M1C0T1 Data Latency : 22.2ns
U18-M1C1T0 <> U19-M1C1T1 Data Latency : 10.1ns
U18-M1C1T0 <> U21-M1C2T1 Data Latency : 21.6ns
U18-M1C1T0 <> U23-M1C3T1 Data Latency : 21.2ns
U18-M1C1T0 <> U25-M1C4T1 Data Latency : 21.2ns
U18-M1C1T0 <> U27-M1C5T1 Data Latency : 21.0ns
U18-M1C1T0 <> U29-M1C6T1 Data Latency : 21.0ns
U18-M1C1T0 <> U31-M1C7T1 Data Latency : 21.5ns
U20-M1C2T0 <> U22-M1C3T0 Data Latency : 21.3ns
U20-M1C2T0 <> U24-M1C4T0 Data Latency : 21.4ns
U20-M1C2T0 <> U26-M1C5T0 Data Latency : 21.0ns
U20-M1C2T0 <> U28-M1C6T0 Data Latency : 21.0ns
U20-M1C2T0 <> U30-M1C7T0 Data Latency : 21.2ns
U20-M1C2T0 <> U1-M0C0T1 Data Latency : 61.4ns
U20-M1C2T0 <> U3-M0C1T1 Data Latency : 59.9ns
U20-M1C2T0 <> U5-M0C2T1 Data Latency : 60.3ns
U20-M1C2T0 <> U7-M0C3T1 Data Latency : 59.7ns
U20-M1C2T0 <> U9-M0C4T1 Data Latency : 60.0ns
U20-M1C2T0 <> U11-M0C5T1 Data Latency : 59.7ns
U20-M1C2T0 <> U13-M0C6T1 Data Latency : 59.9ns
U20-M1C2T0 <> U15-M0C7T1 Data Latency : 60.0ns
U20-M1C2T0 <> U17-M1C0T1 Data Latency : 22.5ns
U20-M1C2T0 <> U19-M1C1T1 Data Latency : 21.6ns
U20-M1C2T0 <> U21-M1C2T1 Data Latency : 10.1ns
U20-M1C2T0 <> U23-M1C3T1 Data Latency : 21.3ns
U20-M1C2T0 <> U25-M1C4T1 Data Latency : 21.4ns
U20-M1C2T0 <> U27-M1C5T1 Data Latency : 21.0ns
U20-M1C2T0 <> U29-M1C6T1 Data Latency : 21.1ns
U20-M1C2T0 <> U31-M1C7T1 Data Latency : 21.2ns
U22-M1C3T0 <> U24-M1C4T0 Data Latency : 20.9ns
U22-M1C3T0 <> U26-M1C5T0 Data Latency : 21.3ns
U22-M1C3T0 <> U28-M1C6T0 Data Latency : 21.3ns
U22-M1C3T0 <> U30-M1C7T0 Data Latency : 21.9ns
U22-M1C3T0 <> U1-M0C0T1 Data Latency : 60.7ns
U22-M1C3T0 <> U3-M0C1T1 Data Latency : 59.6ns
U22-M1C3T0 <> U5-M0C2T1 Data Latency : 59.8ns
U22-M1C3T0 <> U7-M0C3T1 Data Latency : 59.8ns
U22-M1C3T0 <> U9-M0C4T1 Data Latency : 60.0ns
U22-M1C3T0 <> U11-M0C5T1 Data Latency : 59.8ns
U22-M1C3T0 <> U13-M0C6T1 Data Latency : 60.3ns
U22-M1C3T0 <> U15-M0C7T1 Data Latency : 60.5ns
U22-M1C3T0 <> U17-M1C0T1 Data Latency : 21.7ns
U22-M1C3T0 <> U19-M1C1T1 Data Latency : 21.2ns
U22-M1C3T0 <> U21-M1C2T1 Data Latency : 21.4ns
U22-M1C3T0 <> U23-M1C3T1 Data Latency : 10.1ns
U22-M1C3T0 <> U25-M1C4T1 Data Latency : 21.0ns
U22-M1C3T0 <> U27-M1C5T1 Data Latency : 21.3ns
U22-M1C3T0 <> U29-M1C6T1 Data Latency : 21.1ns
U22-M1C3T0 <> U31-M1C7T1 Data Latency : 21.3ns
U24-M1C4T0 <> U26-M1C5T0 Data Latency : 20.9ns
U24-M1C4T0 <> U28-M1C6T0 Data Latency : 20.9ns
U24-M1C4T0 <> U30-M1C7T0 Data Latency : 21.2ns
U24-M1C4T0 <> U1-M0C0T1 Data Latency : 61.5ns
U24-M1C4T0 <> U3-M0C1T1 Data Latency : 60.1ns
U24-M1C4T0 <> U5-M0C2T1 Data Latency : 61.0ns
U24-M1C4T0 <> U7-M0C3T1 Data Latency : 60.2ns
U24-M1C4T0 <> U9-M0C4T1 Data Latency : 60.5ns
U24-M1C4T0 <> U11-M0C5T1 Data Latency : 60.6ns
U24-M1C4T0 <> U13-M0C6T1 Data Latency : 60.5ns
U24-M1C4T0 <> U15-M0C7T1 Data Latency : 60.9ns
U24-M1C4T0 <> U17-M1C0T1 Data Latency : 22.9ns
U24-M1C4T0 <> U19-M1C1T1 Data Latency : 21.7ns
U24-M1C4T0 <> U21-M1C2T1 Data Latency : 22.1ns
U24-M1C4T0 <> U23-M1C3T1 Data Latency : 20.8ns
U24-M1C4T0 <> U25-M1C4T1 Data Latency : 10.1ns
U24-M1C4T0 <> U27-M1C5T1 Data Latency : 20.9ns
U24-M1C4T0 <> U29-M1C6T1 Data Latency : 21.0ns
U24-M1C4T0 <> U31-M1C7T1 Data Latency : 21.2ns
U26-M1C5T0 <> U28-M1C6T0 Data Latency : 21.1ns
U26-M1C5T0 <> U30-M1C7T0 Data Latency : 21.2ns
U26-M1C5T0 <> U1-M0C0T1 Data Latency : 61.3ns
U26-M1C5T0 <> U3-M0C1T1 Data Latency : 60.2ns
U26-M1C5T0 <> U5-M0C2T1 Data Latency : 60.6ns
U26-M1C5T0 <> U7-M0C3T1 Data Latency : 59.9ns
U26-M1C5T0 <> U9-M0C4T1 Data Latency : 60.7ns
U26-M1C5T0 <> U11-M0C5T1 Data Latency : 60.3ns
U26-M1C5T0 <> U13-M0C6T1 Data Latency : 60.5ns
U26-M1C5T0 <> U15-M0C7T1 Data Latency : 60.0ns
U26-M1C5T0 <> U17-M1C0T1 Data Latency : 21.7ns
U26-M1C5T0 <> U19-M1C1T1 Data Latency : 20.7ns
U26-M1C5T0 <> U21-M1C2T1 Data Latency : 20.8ns
U26-M1C5T0 <> U23-M1C3T1 Data Latency : 20.9ns
U26-M1C5T0 <> U25-M1C4T1 Data Latency : 21.0ns
U26-M1C5T0 <> U27-M1C5T1 Data Latency : 10.1ns
U26-M1C5T0 <> U29-M1C6T1 Data Latency : 21.1ns
U26-M1C5T0 <> U31-M1C7T1 Data Latency : 21.1ns
U28-M1C6T0 <> U30-M1C7T0 Data Latency : 21.2ns
U28-M1C6T0 <> U1-M0C0T1 Data Latency : 61.5ns
U28-M1C6T0 <> U3-M0C1T1 Data Latency : 60.4ns
U28-M1C6T0 <> U5-M0C2T1 Data Latency : 60.7ns
U28-M1C6T0 <> U7-M0C3T1 Data Latency : 60.2ns
U28-M1C6T0 <> U9-M0C4T1 Data Latency : 60.8ns
U28-M1C6T0 <> U11-M0C5T1 Data Latency : 60.3ns
U28-M1C6T0 <> U13-M0C6T1 Data Latency : 60.6ns
U28-M1C6T0 <> U15-M0C7T1 Data Latency : 60.1ns
U28-M1C6T0 <> U17-M1C0T1 Data Latency : 22.1ns
U28-M1C6T0 <> U19-M1C1T1 Data Latency : 20.9ns
U28-M1C6T0 <> U21-M1C2T1 Data Latency : 21.3ns
U28-M1C6T0 <> U23-M1C3T1 Data Latency : 20.9ns
U28-M1C6T0 <> U25-M1C4T1 Data Latency : 20.9ns
U28-M1C6T0 <> U27-M1C5T1 Data Latency : 20.9ns
U28-M1C6T0 <> U29-M1C6T1 Data Latency : 10.1ns
U28-M1C6T0 <> U31-M1C7T1 Data Latency : 21.2ns
U30-M1C7T0 <> U1-M0C0T1 Data Latency : 61.1ns
U30-M1C7T0 <> U3-M0C1T1 Data Latency : 60.1ns
U30-M1C7T0 <> U5-M0C2T1 Data Latency : 60.4ns
U30-M1C7T0 <> U7-M0C3T1 Data Latency : 60.0ns
U30-M1C7T0 <> U9-M0C4T1 Data Latency : 60.3ns
U30-M1C7T0 <> U11-M0C5T1 Data Latency : 60.3ns
U30-M1C7T0 <> U13-M0C6T1 Data Latency : 60.3ns
U30-M1C7T0 <> U15-M0C7T1 Data Latency : 60.1ns
U30-M1C7T0 <> U17-M1C0T1 Data Latency : 21.1ns
U30-M1C7T0 <> U19-M1C1T1 Data Latency : 20.9ns
U30-M1C7T0 <> U21-M1C2T1 Data Latency : 20.8ns
U30-M1C7T0 <> U23-M1C3T1 Data Latency : 21.2ns
U30-M1C7T0 <> U25-M1C4T1 Data Latency : 21.0ns
U30-M1C7T0 <> U27-M1C5T1 Data Latency : 21.1ns
U30-M1C7T0 <> U29-M1C6T1 Data Latency : 21.2ns
U30-M1C7T0 <> U31-M1C7T1 Data Latency : 10.1ns
U1-M0C0T1 <> U3-M0C1T1 Data Latency : 23.0ns
U1-M0C0T1 <> U5-M0C2T1 Data Latency : 23.4ns
U1-M0C0T1 <> U7-M0C3T1 Data Latency : 22.4ns
U1-M0C0T1 <> U9-M0C4T1 Data Latency : 22.8ns
U1-M0C0T1 <> U11-M0C5T1 Data Latency : 21.6ns
U1-M0C0T1 <> U13-M0C6T1 Data Latency : 22.2ns
U1-M0C0T1 <> U15-M0C7T1 Data Latency : 21.0ns
U1-M0C0T1 <> U17-M1C0T1 Data Latency : 63.4ns
U1-M0C0T1 <> U19-M1C1T1 Data Latency : 62.3ns
U1-M0C0T1 <> U21-M1C2T1 Data Latency : 62.9ns
U1-M0C0T1 <> U23-M1C3T1 Data Latency : 62.3ns
U1-M0C0T1 <> U25-M1C4T1 Data Latency : 62.7ns
U1-M0C0T1 <> U27-M1C5T1 Data Latency : 61.8ns
U1-M0C0T1 <> U29-M1C6T1 Data Latency : 62.1ns
U1-M0C0T1 <> U31-M1C7T1 Data Latency : 62.0ns
U3-M0C1T1 <> U5-M0C2T1 Data Latency : 22.2ns
U3-M0C1T1 <> U7-M0C3T1 Data Latency : 20.8ns
U3-M0C1T1 <> U9-M0C4T1 Data Latency : 21.3ns
U3-M0C1T1 <> U11-M0C5T1 Data Latency : 20.4ns
U3-M0C1T1 <> U13-M0C6T1 Data Latency : 20.6ns
U3-M0C1T1 <> U15-M0C7T1 Data Latency : 20.9ns
U3-M0C1T1 <> U17-M1C0T1 Data Latency : 61.3ns
U3-M0C1T1 <> U19-M1C1T1 Data Latency : 60.3ns
U3-M0C1T1 <> U21-M1C2T1 Data Latency : 61.0ns
U3-M0C1T1 <> U23-M1C3T1 Data Latency : 60.5ns
U3-M0C1T1 <> U25-M1C4T1 Data Latency : 60.5ns
U3-M0C1T1 <> U27-M1C5T1 Data Latency : 60.3ns
U3-M0C1T1 <> U29-M1C6T1 Data Latency : 60.5ns
U3-M0C1T1 <> U31-M1C7T1 Data Latency : 60.5ns
U5-M0C2T1 <> U7-M0C3T1 Data Latency : 21.3ns
U5-M0C2T1 <> U9-M0C4T1 Data Latency : 21.8ns
U5-M0C2T1 <> U11-M0C5T1 Data Latency : 20.6ns
U5-M0C2T1 <> U13-M0C6T1 Data Latency : 21.0ns
U5-M0C2T1 <> U15-M0C7T1 Data Latency : 20.7ns
U5-M0C2T1 <> U17-M1C0T1 Data Latency : 61.6ns
U5-M0C2T1 <> U19-M1C1T1 Data Latency : 60.8ns
U5-M0C2T1 <> U21-M1C2T1 Data Latency : 61.2ns
U5-M0C2T1 <> U23-M1C3T1 Data Latency : 61.0ns
U5-M0C2T1 <> U25-M1C4T1 Data Latency : 61.0ns
U5-M0C2T1 <> U27-M1C5T1 Data Latency : 60.9ns
U5-M0C2T1 <> U29-M1C6T1 Data Latency : 60.1ns
U5-M0C2T1 <> U31-M1C7T1 Data Latency : 60.3ns
U7-M0C3T1 <> U9-M0C4T1 Data Latency : 20.5ns
U7-M0C3T1 <> U11-M0C5T1 Data Latency : 20.9ns
U7-M0C3T1 <> U13-M0C6T1 Data Latency : 20.8ns
U7-M0C3T1 <> U15-M0C7T1 Data Latency : 21.5ns
U7-M0C3T1 <> U17-M1C0T1 Data Latency : 59.8ns
U7-M0C3T1 <> U19-M1C1T1 Data Latency : 59.7ns
U7-M0C3T1 <> U21-M1C2T1 Data Latency : 59.9ns
U7-M0C3T1 <> U23-M1C3T1 Data Latency : 59.6ns
U7-M0C3T1 <> U25-M1C4T1 Data Latency : 59.6ns
U7-M0C3T1 <> U27-M1C5T1 Data Latency : 60.0ns
U7-M0C3T1 <> U29-M1C6T1 Data Latency : 60.1ns
U7-M0C3T1 <> U31-M1C7T1 Data Latency : 60.1ns
U9-M0C4T1 <> U11-M0C5T1 Data Latency : 20.8ns
U9-M0C4T1 <> U13-M0C6T1 Data Latency : 20.6ns
U9-M0C4T1 <> U15-M0C7T1 Data Latency : 21.2ns
U9-M0C4T1 <> U17-M1C0T1 Data Latency : 60.3ns
U9-M0C4T1 <> U19-M1C1T1 Data Latency : 59.8ns
U9-M0C4T1 <> U21-M1C2T1 Data Latency : 60.1ns
U9-M0C4T1 <> U23-M1C3T1 Data Latency : 60.0ns
U9-M0C4T1 <> U25-M1C4T1 Data Latency : 59.8ns
U9-M0C4T1 <> U27-M1C5T1 Data Latency : 59.9ns
U9-M0C4T1 <> U29-M1C6T1 Data Latency : 60.3ns
U9-M0C4T1 <> U31-M1C7T1 Data Latency : 60.2ns
U11-M0C5T1 <> U13-M0C6T1 Data Latency : 21.1ns
U11-M0C5T1 <> U15-M0C7T1 Data Latency : 22.0ns
U11-M0C5T1 <> U17-M1C0T1 Data Latency : 59.8ns
U11-M0C5T1 <> U19-M1C1T1 Data Latency : 59.4ns
U11-M0C5T1 <> U21-M1C2T1 Data Latency : 59.8ns
U11-M0C5T1 <> U23-M1C3T1 Data Latency : 59.9ns
U11-M0C5T1 <> U25-M1C4T1 Data Latency : 60.0ns
U11-M0C5T1 <> U27-M1C5T1 Data Latency : 60.3ns
U11-M0C5T1 <> U29-M1C6T1 Data Latency : 60.3ns
U11-M0C5T1 <> U31-M1C7T1 Data Latency : 60.2ns
U13-M0C6T1 <> U15-M0C7T1 Data Latency : 21.7ns
U13-M0C6T1 <> U17-M1C0T1 Data Latency : 60.1ns
U13-M0C6T1 <> U19-M1C1T1 Data Latency : 59.8ns
U13-M0C6T1 <> U21-M1C2T1 Data Latency : 61.4ns
U13-M0C6T1 <> U23-M1C3T1 Data Latency : 60.2ns
U13-M0C6T1 <> U25-M1C4T1 Data Latency : 60.2ns
U13-M0C6T1 <> U27-M1C5T1 Data Latency : 60.7ns
U13-M0C6T1 <> U29-M1C6T1 Data Latency : 60.7ns
U13-M0C6T1 <> U31-M1C7T1 Data Latency : 60.5ns
U15-M0C7T1 <> U17-M1C0T1 Data Latency : 60.2ns
U15-M0C7T1 <> U19-M1C1T1 Data Latency : 59.7ns
U15-M0C7T1 <> U21-M1C2T1 Data Latency : 60.1ns
U15-M0C7T1 <> U23-M1C3T1 Data Latency : 60.4ns
U15-M0C7T1 <> U25-M1C4T1 Data Latency : 60.4ns
U15-M0C7T1 <> U27-M1C5T1 Data Latency : 60.7ns
U15-M0C7T1 <> U29-M1C6T1 Data Latency : 60.7ns
U15-M0C7T1 <> U31-M1C7T1 Data Latency : 60.2ns
U17-M1C0T1 <> U19-M1C1T1 Data Latency : 22.2ns
U17-M1C0T1 <> U21-M1C2T1 Data Latency : 22.5ns
U17-M1C0T1 <> U23-M1C3T1 Data Latency : 21.7ns
U17-M1C0T1 <> U25-M1C4T1 Data Latency : 22.0ns
U17-M1C0T1 <> U27-M1C5T1 Data Latency : 21.2ns
U17-M1C0T1 <> U29-M1C6T1 Data Latency : 21.5ns
U17-M1C0T1 <> U31-M1C7T1 Data Latency : 21.1ns
U19-M1C1T1 <> U21-M1C2T1 Data Latency : 21.6ns
U19-M1C1T1 <> U23-M1C3T1 Data Latency : 21.1ns
U19-M1C1T1 <> U25-M1C4T1 Data Latency : 21.2ns
U19-M1C1T1 <> U27-M1C5T1 Data Latency : 21.0ns
U19-M1C1T1 <> U29-M1C6T1 Data Latency : 21.0ns
U19-M1C1T1 <> U31-M1C7T1 Data Latency : 21.5ns
U21-M1C2T1 <> U23-M1C3T1 Data Latency : 21.3ns
U21-M1C2T1 <> U25-M1C4T1 Data Latency : 21.4ns
U21-M1C2T1 <> U27-M1C5T1 Data Latency : 21.0ns
U21-M1C2T1 <> U29-M1C6T1 Data Latency : 21.0ns
U21-M1C2T1 <> U31-M1C7T1 Data Latency : 21.2ns
U23-M1C3T1 <> U25-M1C4T1 Data Latency : 20.9ns
U23-M1C3T1 <> U27-M1C5T1 Data Latency : 21.4ns
U23-M1C3T1 <> U29-M1C6T1 Data Latency : 21.2ns
U23-M1C3T1 <> U31-M1C7T1 Data Latency : 21.9ns
U25-M1C4T1 <> U27-M1C5T1 Data Latency : 21.3ns
U25-M1C4T1 <> U29-M1C6T1 Data Latency : 21.1ns
U25-M1C4T1 <> U31-M1C7T1 Data Latency : 21.7ns
U27-M1C5T1 <> U29-M1C6T1 Data Latency : 21.5ns
U27-M1C5T1 <> U31-M1C7T1 Data Latency : 22.5ns
U29-M1C6T1 <> U31-M1C7T1 Data Latency : 22.2ns
1x 64bytes Blocks Bandwidth : 25.88GB/s
4x 64bytes Blocks Bandwidth : 27.09GB/s
4x 256bytes Blocks Bandwidth : 108.12GB/s
4x 1kB Blocks Bandwidth : 328.23GB/s
4x 4kB Blocks Bandwidth : 535.84GB/s
16x 4kB Blocks Bandwidth : 765.65GB/s
4x 64kB Blocks Bandwidth : 1TB/s
16x 64kB Blocks Bandwidth : 744.45GB/s
8x 256kB Blocks Bandwidth : 499.46GB/s
4x 1MB Blocks Bandwidth : 131.74GB/s
16x 1MB Blocks Bandwidth : 24.88GB/s
8x 4MB Blocks Bandwidth : 18.44GB/s

Benchmark Status
Result ID : AMD Ryzen 9 5950X 16-Core Processor (2M 16C 32T 4.8GHz, 1.9GHz IMC, 16x 512kB L2, 2x 32MB L3)
Microcode : A20F10-1009
Computer : ASUS System Product Name (ASUS ROG CROSSHAIR VIII HERO (WI-FI))
Platform Compliance : x64
No. Threads : 32
System Timer : 10MHz
Page Size : 4kB

Processor
Model : AMD Ryzen 9 5950X 16-Core Processor
URL : https://www.amd.com
Speed : 4.8GHz
Min/Max/Turbo Speed : 2.2GHz - 3.4GHz - 4.8GHz
Modules per Processor : 2 Unit(s)
Cores per Processor : 8 Unit(s)
Threads per Core : 2 Unit(s)
Front-Side Bus Speed : 100MHz
Revision/Stepping : 21 / 0
Microcode : A20F10-1009
Latest Version : A20F10-16
L1D (1st Level) Data Cache : 16x 32kB, 8-Way, Exclusive, 64bytes Line Size, 2 Thread(s)
L1I (1st Level) Code Cache : 16x 32kB, 8-Way, Exclusive, 64bytes Line Size, 2 Thread(s)
L2 (2nd Level) Data/Unified Cache : 16x 512kB, 8-Way, Fully Inclusive, 64bytes Line Size, 2 Thread(s)
L3 (3rd Level) Data/Unified Cache : 2x 32MB, 16-Way, Exclusive, 64bytes Line Size, 16 Thread(s)
Rated Power (TDP) : 105.00W

Memory Controller
Speed : 1.9GHz (100%)
Min/Max/Turbo Speed : 950MHz - 1.9GHz

Performance Enhancing Tips
Warning 5010 : Cannot use Large Memory Pages due to lack of privileges.
Notice 242 : Dynamic OverClocking/Turbo engaged. Environment conditions may influence performance.
Tip 229 : CPU microcode update available. Check for an updated System BIOS with updated microcode.
Tip 3 : Double-click tip or press Enter while a tip is selected for more information about the tip.

New SotTR cpu game average fps record without even pushing = 306 fps
SotTR 306-2.JPG


  • 5950x @ 4700/4600 static OC, SMT enabled
  • 4x8GB memory sticks
  • Hwinfo open
  • Windows 11
  • Flat CL 14-14-14-14 timings
T1 setup-time
19819.2 H/S over 15min run in Monero miner
upto 629 H/S per core
best-2.JPG
 
Last edited:
Top