Thursday, September 14th 2017

AMD Raven Ridge Ryzen 5 2500U with Vega Graphics APU Geekbench Scores Surface

A Geekbench page has just surfaced for AMD's upcoming Raven Ridge APUs, which bring both Vega graphics and Ryzen CPU cores to AMD's old "the future is Fusion" mantra. The APU in question is being tagged as AMD's Raven Ridge-based Ryzen 5 2500U, which leverages 4 Zen cores and 8 threads (via SMT) running at 2.0 GHz with AMD's Vega graphics.

According to Geekbench, the Ryzen APU scores 3,561 points in the single-core score, and 9,421 points in the multi-core score. Compared to AMD's A12-9800, which also leverages 4 cores (albeit being limited to 4 threads) running at almost double the frequency of this Ryzen 5 2500U (3.8 GHz vs the Ryzen's 2 GHz), that's 36% better single-core performance and 48% better multi-core performance. These results are really fantastic, and just show how much AMD has managed to improve their CPU (and in this case, APU) design over their Bulldozer-based iterations.

Source: Guru3D
Add your own comment

54 Comments on AMD Raven Ridge Ryzen 5 2500U with Vega Graphics APU Geekbench Scores Surface

#1
RejZoR
Still waiting for Ryzen equivalent of E-450 APU. It'll probably come last I'm suspecting... But it'll probably be well worth the waiting.
Posted on Reply
#2
Chaitanya
RejZoR said:
Still waiting for Ryzen equivalent of E-450 APU. It'll probably come last I'm suspecting... But it'll probably be well worth the waiting.
maybe we will see Ryzen 3 APUs at some point filling the niche of E-450 for entry level notebooks.
Posted on Reply
#3
the54thvoid
How does the APU's Vega core compare with past APU's? Can it run demanding 1080p games at 30fps?

If so, that'd be pretty cool.
Posted on Reply
#4
Gasaraki
What about compared to Intel Iris?
Posted on Reply
#5
jabbadap
the54thvoid said:
How does the APU's Vega core compare with past APU's? Can it run demanding 1080p games at 30fps?

If so, that'd be pretty cool.
Which Ryzen APU do you mean? These are mobile apus thus they will be power constrained. GFXBench has some preliminary Opengl numbers, but then again are they from final product or something else.
Posted on Reply
#6
TheinsanegamerN
the54thvoid said:
How does the APU's Vega core compare with past APU's? Can it run demanding 1080p games at 30fps?

If so, that'd be pretty cool.
Considering nobody has seen the core, nobody knows.

What Is known in that bulldozer APUs sucked HARD. Bristol ridge barely gets over 11GB/s bandwidth from 2400MHz memory, which is hypothetically capable of 34GB/s. this had to feed both the CPU and GPU. Their CPU cores were also unable to keep near full boost, meaning CPU performance was pathetic. The current bristol ridge APU is twice as fast as a 620 equipped intel CPU, yet it is also known that the GPU is running at less then half capacity. A 384 core 64 bit GCN chip is 40-60% faster then a 512 core desktop APU right now.

So assuming that AMD keeps the 512 core design, but uses ryzen CPU and memory controller, expect big boosts. Even a 256 core ryzen APU would be faster then AMDs current 512 core parts. Hypothetically, they have a 704 core GPU in the works for APUs.

My guess would be 512 core at 15 watt and 704 core for 35 watt and desktop parts.
Posted on Reply
#7
Steevo
Gasaraki said:
What about compared to Intel Iris?
Intel graphics suck, no matter how hard they try, they suck.

Intel sucks at video rendering, upscaling, enhancements. Intel sucks at 3D graphics, great processors for the longest time, but their graphics suck as well.

http://www.anandtech.com/show/11538/the-microsoft-surface-pro-2017-review-evolution/5

Essentially any 7 year old midrange card or 5 year old entry level discreet card will kick it's ass.
Posted on Reply
#8
MirXD
a mobile soc that beats the current gen Desktop APU. damn.
Posted on Reply
#9
Fouquin
Steevo said:
Intel graphics suck, no matter how hard they try, they suck.

Intel sucks at video rendering, upscaling, enhancements. Intel sucks at 3D graphics, great processors for the longest time, but their graphics suck as well.

http://www.anandtech.com/show/11538/the-microsoft-surface-pro-2017-review-evolution/5

Essentially any 7 year old midrange card or 5 year old entry level discreet card will kick it's ass.
That's also a mobile variant in a 15W ultra low-power dual-core... Not really giving a fair shake to look at a throttled mobile chip and compare it to discrete options with 5x the power envelope.
Posted on Reply
#11
Steevo
Fouquin said:
That's also a mobile variant in a 15W ultra low-power dual-core... Not really giving a fair shake to look at a throttled mobile chip and compare it to discrete options with 5x the power envelope.
The Pro 4 shown with a 930M chip has *somewhat* higher graphical performance with the same normalized battery life and thus close to the same exact power consumption from a two year older setup. Try again?
Posted on Reply
#12
Fouquin
Steevo said:
The Pro 4 shown with a 930M chip has much higher graphical performance with the same normalized battery life and thus close to the same exact power consumption from a two year older setup. Try again?
The 930M is also a 33W (2x the afforded power envelope) chip, thus capable of higher performance flags? Measuring battery life doesn't tell you how much power the GPU is using since it's almost never running into a scenario to turbo, but the higher power envelope reinforces the idea that the 930M is less restricted than the Iris Plus 640.

This would be a more level comparison. With 35-45W to play with Intel can pack a much more potent iGPU.
Posted on Reply
#13
Frick
Fishfaced Nincompoop
Steevo said:
Intel graphics suck, no matter how hard they try, they suck.
Eh, the Iris Pro is the fastest IGP avaliable. The problem is that it's only avaliable in $400 CPUs.

TheinsanegamerN said:
.

What Is known in that bulldozer APUs sucked HARD.
Honestly I don't think they did, depending on the model. The problem was they were almost exclusively used in power starved laptops with gimped memory so everyone has a bad experience from them. Yeah the CPU side was miles behind Intel but there was compelling APUs that would offer good all around performance ... if anyone would base a system around them. You could make decent small machines with some of their FM2+ APUs.

Also there's managing expectations. Obviously a dedicated used GPU will be faster and probably cheaper, but still.
Posted on Reply
#14
jmcslob
I want the 7850k version of Zen and the V.

the54thvoid said:
How does the APU's Vega core compare with past APU's? Can it run demanding 1080p games at 30fps?

If so, that'd be pretty cool.
Exactly...
The best I could do I was 1366x768 on high details on most games 30fps with a 7850k @4.4Ghz core 975Mhz gfx with DDR3 2.4Ghz

I would be extatic if they could do 1080p medium details @30fps.
Posted on Reply
#15
Fouquin
Frick said:

Honestly I don't think they did, depending on the model. The problem was they were almost exclusively used in power starved laptops with gimped memory so everyone has a bad experience from them. Yeah the CPU side was miles behind Intel but there was compelling APUs that would offer good all around performance ... if anyone would base a system around them. You could make decent small machines with some of their FM2+ APUs.
HP's ProBook 645 was one of a few good implementations. It had Richland series APUs and with the top configuration of an A10-5750M it was honestly a damn good 14-inch travel laptop with some gaming chops for older titles. Pulled about 56W from the wall and had between 4-6 hours battery life.

Support for dual-channel DDR3-1866 helped tremendously.
Posted on Reply
#16
Frick
Fishfaced Nincompoop
jmcslob said:
I want the 7850k version of Zen and the V.
95 watts worth of Zen and Vega would be neat.
Posted on Reply
#18
jmcslob
Frick said:
95 watts worth of Zen and Vega would be neat.
That's what my intentions were when I bought my current Mobo...
It's a MSI 350 gaming pro.
At least I hope they use AM4 for those APU's...
I kinda want my Ryzen 5 1400/ Vega APU...
Posted on Reply
#19
Thalles Adorno
Fouquin said:
The 930M is also a 33W (2x the afforded power envelope) chip, thus capable of higher performance flags? Measuring battery life doesn't tell you how much power the GPU is using since it's almost never running into a scenario to turbo, but the higher power envelope reinforces the idea that the 930M is less restricted than the Iris Plus 640.

This would be a more level comparison. With 35-45W to play with Intel can pack a much more potent iGPU.
Well, I can give your answer. I have an i5 5675C with the iGPU Iris pro 6200. The difference is very low when running it at 12W versus running it at 30W (factory setting). I had major problems with temps and had to downclock it, not much of a difference
Posted on Reply
#20
Fouquin
Thalles Adorno said:
Well, I can give your answer. I have an i5 5675C with the iGPU Iris pro 6200. The difference is very low when running it at 12W versus running it at 30W (factory setting). I had major problems with temps and had to downclock it, not much of a difference
For the sake of pedantry, that iGPU is a different process and µarch. The iGPU in Skylake/Kaby is quite a bit better.
Posted on Reply
#21
Steevo
Fouquin said:
The 930M is also a 33W (2x the afforded power envelope) chip, thus capable of higher performance flags? Measuring battery life doesn't tell you how much power the GPU is using since it's almost never running into a scenario to turbo, but the higher power envelope reinforces the idea that the 930M is less restricted than the Iris Plus 640.

This would be a more level comparison. With 35-45W to play with Intel can pack a much more potent iGPU.
While I can't disagree that at very low resolutions and settings it seems to work fine, at 1080 it fell flat on its face consistantly compared to a 40W higher device the Zbox Magnus 970, which offered a minimum of 2X the performance at 1080 and usually much more than that. So are we talking about playing a game on a screen with terrible resolution and only basic settings? I have Iris in my new laptop Im posting this on, tried steam for a few games and hated it so much I went back to my phone.

My phone can play the games at 1080 (GTA3 for example) with HDMI interface to my TV or DLNA and offers the same performance in these light weight games, as do most tablets, again rendering the Intel graphics virtually pointless from a 3D standpoint.

The 640 vs the 930M the normalized power consumption shows very minor difference, and the only real difference was the size of batteries installed in the two devices.
Posted on Reply
#22
Darmok N Jalad
I am looking forward to what AMD can do with this next gen APU. The previous attempt was severely lacking in CPU performance, and even then the architecture liked as much memory bandwidth as you could give it. Between having a Ryzen base and DDR4 to work with, I expect good results at 1080P, especially from a 95W desktop version.
Posted on Reply
#23
Mats
Fouquin said:
For the sake of pedantry, that iGPU is a different process and µarch.
Broadwell, Skylake, Kaby Lake, and Coffee Lake are all 14 nm.
Posted on Reply
#24
Fouquin
Mats said:
Broadwell, Skylake, Kaby Lake, and Coffee Lake are all 14 nm.
Right my mistake. Iris Pro 5200 is still built on 22nm, but Iris Pro 6200 is 14nm. They did update the µarch for Skylake's iGPU still.
Posted on Reply
#25
AnarchoPrimitiv
Alright, now all AMD needs to do is integrate about 1-4GB of HBM(GEN 1 or 2) into this APU to act has both a huge L4 cache/VRAM (they have several patents specific to this type of product). If they could make an APU that'd be able to do 60fps@1080p on high to ultra settings in most games, it'd sell incredibly well. Heck, such an APU would practically launch a new category of ultrabooks and mobile computers....could you imagine something as thin as the HP spectre that could do 60fps @1080p? or even tablets with that APU? it'd even be able to start making fully self-contained VR HMDs. Since the CUs in APUs are so dependent on RAM speed, a 2-4GB HBM package on the same interposer as the APU would do A LOT to strengthen APU performance, especially on the GPU end, and when the Vega CUs aren't using the HBM, it'd double as a huge L3/L4 cache which would probably help the CPU side of things too....maybe when HBM production improves, AMD might finally utilize the patents they possess addressing such technology.
Posted on Reply
Add your own comment