Wednesday, May 13th 2020

OPNs for At Least Twelve Desktop AMD "Renoir" APUs Decoded

Igor's Lab discovered that AMD may be working on as many as twelve desktop Ryzen G "Renoir" processors with integrated graphics. These include six SKUs each covering the 65 W and 35 W TDP categories, and include two each of 8-core/16-thread, 6-core/12-thread, and 4-core/8-thread SKUs per TDP category. All twelve chips feature increased power limits from their mobile siblings, and a reference memory frequency of DDR4-3200. The parts also feature iGPU maximum engine clock boost frequency as high as 2.10 GHz, to overcome the compute unit deficit "Renoir" has against its predecessor, "Picasso/Raven Ridge," with their up to 11 CUs.

The series appears to be led by an 8-core/16-thread SKU with CPU boost frequency as high as 4.45 GHz, iGPU engine clock as high as 2.10 GHz, and various power-state clock speeds detailed in the table below. The 6-core/12-thread part boosts up to 4.30 GHz, with iGPU engine clock up to 1.90 GHz. The 4-core/8-thread part boosts up to 4.10 GHz, with up to 1.70 GHz iGPU engine clocks. The 35 W TDP parts have, on average, 200-300 MHz lower max CPU core boost- and nominal clock speeds, but more aggressive power-management as defined in the various P-states. Half of these OPNs point to chips with identical clock speeds and core configurations. These are probably differentiated from each other with some of them being Ryzen PRO SKUs.
It stands to reason that all SKUs will be launched under the upcoming Ryzen 4000G-series branding. We already know that the 8-core parts will get a Ryzen 7 brand extension from the Ryzen 7 4700G leak. It's possible that the Ryzen 5 parts will be 6-core/12-thread, and Ryzen 3 4-core/8-thread. For the Ryzen 5 desktop APU series in particular, this would amount to a 50% increase in core- and thread-counts (from the 3400G), while it would see the introduction of SMT for Ryzen 3 desktop APU series (from the 3200G). Find some technical commentary in the Igor's Lab report at the source link below.
Source: Igor's Lab
Add your own comment

32 Comments on OPNs for At Least Twelve Desktop AMD "Renoir" APUs Decoded

#1
Dante Uchiha
The only thing impressive is the clock of the iGPU 2100Mhz. I think these APUs will be much less attractive in the desktop market, where TDP and refrigeration are not as limited, it will offer a very small upgrade on the GPU part or even a downgrade, at a very high cost... totally breaking the proposal of an APU.

AMD could take it easy with the increase of cores (4200G 6C/6T and 4400G 6C/12T) and put another 1~2CU or at least keep the 11CU of the previous generation.
Posted on Reply
#2
nBagasW
An athlon with 4c/4t, 35W TDP for 60 bucks is what I've been waiting for, even if it only clocked at 3,2 Ghz without turbo.
Posted on Reply
#3
mtcn77
Dante Uchiha
The only thing impressive is the clock of the iGPU 2100Mhz. I think these APUs will be much less attractive in the desktop market,
Don't expect much. These apus don't come with any special antialiasing modes, so don't expect the exclusivity. The gpu clock isn't the inhibitor, shader clocks are quite the norm, it is the bandwidth that is deficient. You need 4x bandwidth for full rate filtering. Not to be expected in an apu.
Posted on Reply
#4
GoldenX
So, 7nm process, and we only got a 10% bump in raw compute power. Vega is already old news for APUs, AMD, bring something better.
Posted on Reply
#5
JAB Creations
Zen 2 APUs for desktop should be branded as 3000 series.
Posted on Reply
#6
Darmok N Jalad
Dante Uchiha
The only thing impressive is the clock of the iGPU 2100Mhz. I think these APUs will be much less attractive in the desktop market, where TDP and refrigeration are not as limited, it will offer a very small upgrade on the GPU part or even a downgrade, at a very high cost... totally breaking the proposal of an APU.

AMD could take it easy with the increase of cores (4200G 6C/6T and 4400G 6C/12T) and put another 1~2CU or at least keep the 11CU of the previous generation.
I would think it would be more attractive in the desktop market, where they can be used by OEMs in thin-boxes and AIOs and not need a dGPU. Maybe they won’t have much value in the DIY market, unless you want to skip the dGPU and still want 8C/16T. If you’re a non-gamer, or a casual gamer, these might be very attractive.
Posted on Reply
#7
Apocalypsee
I hope RAM speed supports improve too. Even at 1.4-1.6GHz clock, memory bandwidth is the limitation for iGPU.
Posted on Reply
#8
evernessince
GoldenX
So, 7nm process, and we only got a 10% bump in raw compute power. Vega is already old news for APUs, AMD, bring something better.
I'm pretty sure you commented the same thing in another thread but it has been pointed out to you before that the Vega going into these APUs has had significant enhancements.
Posted on Reply
#9
GoldenX
evernessince
I'm pretty sure you commented the same thing in another thread but it has been pointed out to you before that the Vega going into these APUs has had significant enhancements.
If it did, it would not be a Vega, GCN5.0.
Posted on Reply
#10
medi01
This is a great product for SFFs and office PCs, too bad OEMs are in "special relationships with Intel" mode.
GoldenX
Vega is already old news
That's a 1.6 times faster per clock Vega (per AMD's estimates) if it's the same GPU as in Renoir mobile chips.
Posted on Reply
#11
3rold
JAB Creations
Zen 2 APUs for desktop should be branded as 3000 series.
I agree with you. I find the naming convention very confusing. No idea why they ever did that.
Posted on Reply
#12
T1beriu
Decoded? There's no hidden code in OPNs. It's just a name.
Posted on Reply
#13
Mats
Dante Uchiha
The only thing impressive is the clock of the iGPU 2100Mhz. I think these APUs will be much less attractive in the desktop market, where TDP and refrigeration are not as limited, it will offer a very small upgrade on the GPU part or even a downgrade, at a very high cost... totally breaking the proposal of an APU.

AMD could take it easy with the increase of cores (4200G 6C/6T and 4400G 6C/12T) and put another 1~2CU or at least keep the 11CU of the previous generation.
You don't know that this one is faster than the previous one, despite fewer CU's, right? :rolleyes: That's like comparing two CPU's just by looking at the number of cores alone..
This is not the same graphics as in Picasso (3000G/H/U).

Also, lowering the CPU core count is a very stupid idea. Gaming laptops are a MUCH larger market than laptops with fastest iGP ever. AMD needs 8 cores to be able to compete with Intel.
Posted on Reply
#14
las
JAB Creations
Zen 2 APUs for desktop should be branded as 3000 series.
Yes. But..

Mobile 3000 series = Zen+
Mobile 4000 = Zen 2

This is really missleading.
Many people bought mobile 3000 series because they thought it was like 3000 desktop series / Zen 2.
Posted on Reply
#15
R0H1T
las
Yes. But..

Mobile 3000 series = Zen+
Mobile 4000 = Zen 2

This is really missleading.
Many people bought mobile 3000 series because they thought it was like 3000 desktop series / Zen 2.
No they didn't, where are you getting this from :rolleyes:
Posted on Reply
#16
Melvis
The real question is will they be supported on older B450/X470 motherboards or older.
Posted on Reply
#17
las
R0H1T
No they didn't, where are you getting this from :rolleyes:
Yes they did. I know 3 people that bought a Thinkpad T595 with a 3000 series mobile Ryzen thinking it was like Desktop 3000 series.

AMD only does this to trick people. It's obvious.
Posted on Reply
#18
nBagasW
Melvis
The real question is will they be supported on older B450/X470 motherboards or older.
I think it doesn't matter anymore as people with sane mind would surely only interested in buying 500 series mobo from now on. Thanks to AMD for killing their own product sales (the 400 series chipset)
Posted on Reply
#19
Mats
nBagasW
I think it doesn't matter anymore as people with sane mind would surely only interested in buying 500 series mobo from now on.
That doesn't help people with a sane mind who wants to upgrade the CPU.
Posted on Reply
#20
YAYgee
According to AMD the higher graphics clock, a 25% increase (from 1400MHz to 1750MHz), helped to reach those "59%" gains.
It's a 50% increase (from 1400MHz to 2100MHz) for desktop Renoir. So even bigger gains? New Vega 8 = old Vega 14 (a decent improvement on Picasso's Vega 11).
Posted on Reply
#21
Dante Uchiha
YAYgee
According to AMD the higher graphics clock, a 25% increase (from 1400MHz to 1750MHz), helped to reach those "59%" gains.
It's a 50% increase (from 1400MHz to 2100MHz) for desktop Renoir. So even bigger gains? New Vega 8 = old Vega 14 (a decent improvement on Picasso's Vega 11).
Yeah... It's easy to OC Vega 11 up to 1600~1800mhz on 12nm. Renoir may have considerable gains on iGPU side if the memory controller manages to break the 4000Mhz barrier.
Posted on Reply
#22
mtcn77
GoldenX
If it did, it would not be a Vega, GCN5.0.
Vega has mobile tiled rasterizing mode, present on nvidia since maxwell. It is all there needs to be.
The problem is memory bandwidth causing the shader cores to idle. What normally needs to happen for full texturing is 8x bandwidth. Z culling reduces that to 4x. However it still is an inordinate amount of memory for a simple pixel operation, so better pixels or better rasterization saving on concurrent writes is pretty important.
RDNA on the other hand is for directx 12 and extending scalarization support to two cycle operations. I wonder if Nvidia has the same extension since warp arrays can be rearranged which is what scalarization is about in the end. It is about not wasting registers for vector operations and having all for a single atomic operation, so the effort is towards running maximum instances of a single shader.
Posted on Reply
#23
Apocalypsee
Melvis
The real question is will they be supported on older B450/X470 motherboards or older.
I think it should, it based on Zen 2 which is supported on B450/X470 it should have no reason why it wont be supported. But if AMD tied this new APU with new Zen 3 AGESA which was meant for B550/X570 it could mean otherwise.
Posted on Reply
#24
GoldenX
mtcn77
Vega has mobile tiled rasterizing mode, present on nvidia since maxwell. It is all there needs to be.
The problem is memory bandwidth causing the shader cores to idle. What normally needs to happen for full texturing is 8x bandwidth. Z culling reduces that to 4x. However it still is an inordinate amount of memory for a simple pixel operation, so better pixels or better rasterization saving on concurrent writes is pretty important.
RDNA on the other hand is for directx 12 and extending scalarization support to two cycle operations. I wonder if Nvidia has the same extension since warp arrays can be rearranged which is what scalarization is about in the end. It is about not wasting registers for vector operations and having all for a single atomic operation, so the effort is towards running maximum instances of a single shader.
This is what tilted Nintendo to use the Tegra X1.
Posted on Reply
#25
mtcn77
GoldenX
This is what tilted Nintendo to use the Tegra X1.
I couldn't draw any parallels. Mind sharing if you had pointers between them?
Tegra again, is not a high power chip in my eyes. You only need to go into multicycle register scheduling if you have such lots of shaders that it becomes a losing game to schedule vectors, losing latency to perform the amount of work. Just because you can, doesn't validate you should. Small gpus on the other hand cannot shuffle between so much work simultaneously anyway. Everything is serial by nature, rather than schedule.
Posted on Reply
Add your own comment