Jump to content

9000X3D leaks and Cinebench R23

https://www.techpowerup.com/327613/msi-oclab-reveals-ryzen-9000x3d-11-13-faster-than-7000x3d-amd-set-to-dominate-arrow-lake-in-gaming

It's all over the internet but if you haven't seen it already, someone leaked slides apparently from MSI event which covered 9000X3D parts.

 

Gaming: 8 core vs 7800X3D 1080p 4090: +2% each on SOTTR and BMW. +13% on Far Cry 6. 3 games is not a wide selection so we'd ideally need more to see how it goes.

 

Cinebench R23: No change from 9000 (non-3D) at same clock, which is to be expected as R23 doesn't seem to scale with cache/ram, and is near ideal core scaling load. Working backwards from the given scores, I have two estimates on clock:

A: 5.1+ GHz for 8 core, 4.6+ GHz for 16 core

B: 5.3+ GHz for 8 core, 4.8+ GHz for 16 core

 

Scenario A is by using data from HWBOT 9700X results. Leading overclockers there will optimise their systems so this is what you'd see if MSI did same. 

Scenario B is by using MSI same-clock data. It works out about 4% worse than HWBOT scores, but this has the effect of inflating the estimated running clock by the same amount.

 

For comparison, my stock 7800X3D (apart from EXPO), runs at 4.7+ GHz during that test. My score is about 5% lower than MSI's but I'm running on a live system with monitoring that is not optimised for maximum score potential.

 

For a better perspective I'm after typical R23 running clocks of stock AM5 CPUs. Scores are easy to find, clocks less so. Anyone point me towards some, or could supply own data?

Gaming system: R7 7800X3D, Asus ROG Strix B650E-F Gaming Wifi, Thermalright Phantom Spirit 120 SE ARGB, Corsair Vengeance 2x 32GB 6000C30, RTX 4070, MSI MPG A850G, Fractal Design North, Samsung 990 Pro 2TB, Alienware AW3225QF (32" 240 Hz OLED)
Productivity system: i9-7980XE, Asus X299 TUF mark 2, Noctua D15, 64GB ram (mixed), RTX 3070, NZXT E850, GameMax Abyss, Samsung 980 Pro 2TB, iiyama ProLite XU2793QSU-B6 (27" 1440p 100 Hz)
Gaming laptop: Lenovo Legion 5, 5800H, RTX 3070, Kingston DDR4 3200C22 2x16GB 2Rx8, Kingston Fury Renegade 1TB + Crucial P1 1TB SSD, 165 Hz IPS 1080p G-Sync Compatible

Link to comment
Share on other sites

Link to post
Share on other sites

Seems like they've been GPU limited most of the time in those games. Any idea what settings have they used? They've been definitely GPU bound in BMW and SOTTR though.

Link to comment
Share on other sites

Link to post
Share on other sites

3 minutes ago, WereCat said:

Any idea what settings have they used?

It only says 1080p.

Gaming system: R7 7800X3D, Asus ROG Strix B650E-F Gaming Wifi, Thermalright Phantom Spirit 120 SE ARGB, Corsair Vengeance 2x 32GB 6000C30, RTX 4070, MSI MPG A850G, Fractal Design North, Samsung 990 Pro 2TB, Alienware AW3225QF (32" 240 Hz OLED)
Productivity system: i9-7980XE, Asus X299 TUF mark 2, Noctua D15, 64GB ram (mixed), RTX 3070, NZXT E850, GameMax Abyss, Samsung 980 Pro 2TB, iiyama ProLite XU2793QSU-B6 (27" 1440p 100 Hz)
Gaming laptop: Lenovo Legion 5, 5800H, RTX 3070, Kingston DDR4 3200C22 2x16GB 2Rx8, Kingston Fury Renegade 1TB + Crucial P1 1TB SSD, 165 Hz IPS 1080p G-Sync Compatible

Link to comment
Share on other sites

Link to post
Share on other sites

Just now, porina said:

It only says 1080p.

Well, we will have to wait for reviews then as this tells us nothing.

 

BMW can definitely run well above 60FPS before I hit CPU limit with my 5800X3D (without RT) so this looks like they've maxed everything and RT as well so it's more like a GPU benchmark even though RT can be CPU heavy in many games but BMW tends to tax the 4090 quite well for it to be a CPU limitation at only around 60FPS.

 

I looked at SOTTR benches and seems like they've again fell in the ballpark of the maxed out settings with RT which also puts it more toward a GPU limit rather than pushing the CPU.

 

Haven't looked at FC6 as I have no experience with FC games so can't comment on that I just know that these games liked X3D a lot so it's possible they are more CPU heavy but since we don't know the settings I have no idea if the benching they've done was more GPU or CPU heavy.

Link to comment
Share on other sites

Link to post
Share on other sites

3 hours ago, WereCat said:

Seems like they've been GPU limited most of the time in those games. Any idea what settings have they used? They've been definitely GPU bound in BMW and SOTTR though.

being GPU bound doesn't skew the comparison between CPU performance, at least not by a considerable amount

 

maybe when comparing GPUs, because don't the AMD GPUs perform better when bound? or is that when they're CPU bound?

Note: Users receive notifications after Mentions & Quotes. 

Feel free: To ask any question, no matter what question it is, I will try to answer. I know a lot about PCs but not everything.

current PC:

Ryzen 5 5600 |16GB DDR4 3200Mhz | B450 | GTX 1080 ti [further details on my profile]

PCs I used before:

  1. Pentium G4500 | 4GB/8GB DDR4 2133Mhz | H110 | GTX 1050
  2. Ryzen 3 1200 3,5Ghz / OC:4Ghz | 8GB DDR4 2133Mhz / 16GB 3200Mhz | B450 | GTX 1050
  3. Ryzen 3 1200 3,5Ghz | 16GB 3200Mhz | B450 | GTX 1080 ti
Link to comment
Share on other sites

Link to post
Share on other sites

2 hours ago, podkall said:

being GPU bound doesn't skew the comparison between CPU performance, at least not by a considerable amount

It does when the CPU is hardly doing anything because it has to wait for GPU

 

2 hours ago, podkall said:

 

 

maybe when comparing GPUs, because don't the AMD GPUs perform better when bound? or is that when they're CPU bound?

driver overhead on NVIDIA cards make them perform worse in some CPU limited scenarios vs AMD in some cases

Link to comment
Share on other sites

Link to post
Share on other sites

11 minutes ago, WereCat said:

It does when the CPU is hardly doing anything because it has to wait for GPU

Yes, but it is the CPU that reacts faster once it's "done waiting" that counts, which can be a noticeable difference.

 

4K benchmarks vary in performance, and usually follow through on a similar if not exact same trend in performance difference compared to 1080p

Note: Users receive notifications after Mentions & Quotes. 

Feel free: To ask any question, no matter what question it is, I will try to answer. I know a lot about PCs but not everything.

current PC:

Ryzen 5 5600 |16GB DDR4 3200Mhz | B450 | GTX 1080 ti [further details on my profile]

PCs I used before:

  1. Pentium G4500 | 4GB/8GB DDR4 2133Mhz | H110 | GTX 1050
  2. Ryzen 3 1200 3,5Ghz / OC:4Ghz | 8GB DDR4 2133Mhz / 16GB 3200Mhz | B450 | GTX 1050
  3. Ryzen 3 1200 3,5Ghz | 16GB 3200Mhz | B450 | GTX 1080 ti
Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×