"The Ryzen 8000G series of APUs is based on AMD's Phoenix silicon, which is already in use in their Ryzen Mobile 7040/8040 chips."
And Ryzen 6000 series APUs that were Zen-3+/RDNA2 but had DDR5 Memory Controllers and yet there was no Ryzen 6000G for AM5 and no Ryzen 7000G for AM5 as well that's since been rebranded as Ryzen 8000G and too late to be attractive in pricing at its current MSRP versus a $100 dollar CPU paired with a low cost dGPU.
Had AMD released a Ryzen 7000G back then when dGPU prices where higher then it would have made more sense at a higher price point but not today and rebranded as 8000G at the 8700G's current MSRP. So now to wait for the retail pricing for the 8700G to drop below $200 and that will make more sense versus a $100 CPU paired with a low cost dGPU.
At current costs this certainly won't happen, but APUs will still be very popular for compact PCs. Mainly the 8600G which, once at the same clock rate, should have almost the same performance as the 8700G.
No not with the 760M iGPU on the 8600G only having half the number of Raster Back Ends(RBE) enabled and only 16 ROPs to the 780M's 32 ROPs and the reviewers just need to take it up to 1080P from 720P to make the ROPs more of a factor there 760M(16 ROPs) vs 780M(32 ROPs)!
And Strangely enough the 660M was only 6 CUs and only one Shader Array active for that RDNA2 iGPU while the 760M got 8CUs and so both Shader Arrays had to be activated for that on the 8600G and each shader array supports 2 RBEs and there are 4 RBE's total across the 2 Shader arrays that make up the full tape-out. So to make the 760M 2CUs/1WGP on each shader shader array is disabled and so are 1 RBR on each Shader array to net only 16ROPs there for the 760M Bin!
So any reviewer testing at only 720P is not going to stress the raster performance that much on any 760M vs 780M comparison and I would test the scaling of both from 720P to 1080P and even 1440p(even if the frame rates drop below 30 FPS) to get some scaling with resolution numbers for the iGPUs.
P.S. Raster Back End(RBE) and Render Back End(RBE) are pretty much synonymous but I get that it's used to mean the same thing and on Radeon iGPUs and each RBE has 8 ROPs. And I'm Using Techpowerup's GPU database for my Render Configuration numbers and the iGPU Block Diagrams that AMD provided for the Radeon 600M and 700M series iGPUs' full tape-outs that are binned for hardware units to create the various iGPU SKUs.
ETA Prime adjusts settings across his runs to target 60 FPS minimum Frame rates and when he can not get that then he'll target 30FPS to 60FPS with settings not maintained between runs because he's just tying to show the way to get a setting mix that targets playable frame rates while retaining Image Quality as best as possible.
So for that his testing is good for that and his very small for factor builds that no others in the tech press rally focus on building! But That's not good for actual iGPU reviewing where some of the settings need to be turned off and other settings equalized across runs to properly stress the Raster Performance of the 760M iGPU vs the 780M(Twice as many ROPs enabled). So turn off all the up-scaling and frame generation and run some Raster Intensive games at high settings and at different Resolutions there to get at actual Raster Scaling of the iGPUs! And so do that 720p and 1080P up to 1440P(even if the frame rates fall below 30FPS) to look at actual Raster performance only and that scaling there for the 760M vs 780M.
And folks Like Gamers Nexus and Hardware Unboxed do the actual hardware oriented benchmarks that take a few days to complete and use more gaming titles there for that and at different resolutions for Raster Gaming tests and then other non Raster only but Ray Traced and Up-scaled or frame generated tests that are separate from the raster testing.
And did you note on ETA Prime's recent InWin Chopin Max Build video that the included AMD Spire cooler was too tall to fit in that Inwin Chopin Build so some other proper Low Profile cooler was utilized. And AMD's clueless about very small form factor builds that utilize AMD's G series Desktop APUs like the ASRock Desk Mini and Inwin Chopin that need true low profile coolers to fit those form factors!
it would not have made sense to have diy apus a year ago with expensive motherboards and ddr5, especially while zen3 ddr4 was so cheap and readily available (and selling well)
people test, but nobody watches the clockspeeds and wattage the whole time
on a related note, a lot of my personal benchmarking is not an average or a 'run', but actually i choose a demanding spot to stand still and do my single fps temp/watt/fan logging over time and hardware comparisons there, because the demanding parts are what really matter when choosing settings or parts (and i'm 60 vsync anyway)
i dont get it, my asrock deskmeet with 5600g has all the STAPM options to tweak or disable it, so is this simply a matter of zen4 desktop mobos not having the user facing options?
I'm waiting for the ASRock X600 Desk Mini and its STX/AM5 MB to show up at ASRock's web site so I can look at the manual for that and the Memory QVL and even the SSD compatibility listings. And I sure hope there's some USB4 there. But really I want ASRock to Provide an OCuLink Knockout on the steel case with mounting holes for some M.2 to OCuLink Adapter that ASRock can provide as an extra cost option! Now My X300 desk Mini has a USB Knockout and mounting points for an optional extra USB port in the x300 Desk Mini But I'm looking at maybe getting some M.2 to OCUlink adapter and getting out the Dremel Tool there for that to get some OCuLink Port retrofitted there! The X300 does not even have USB4 so even if the 4 PCIe lanes to the bottom M.2 slot on the STX MB are PCIe 3.0 that's still similar bandwidth to USB4.
What sensor is the APU actually pulling from on desktop? I get the problem conceptually but do desktop motherboards have a skin sensor somewhere?!? Or is there actually no sensor and instead there’s just an algorithm at work?
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
23 Comments
Back to Article
Samus - Friday, February 2, 2024 - link
Oops. :)drw392772 - Friday, February 2, 2024 - link
Thanks Steve!ballsystemlord - Friday, February 2, 2024 - link
Where is that quote that he likes to play from, anyway?kn00tcn - Saturday, February 3, 2024 - link
an apple or intel keynotethexile - Sunday, February 4, 2024 - link
Intel 2021 Keynote.https://www.youtube.com/watch?v=OnNZ3hCjIvs
ballsystemlord - Monday, February 5, 2024 - link
Thanks, thexile.thomasjkenney - Friday, February 2, 2024 - link
Good article, interesting find. Thanks."...problems from which the Ryzen 8000G APUs suffer from."
Avoids dangling participle, then swerves back for the hit! :)
mode_13h - Friday, February 2, 2024 - link
lol!FWhitTrampoline - Saturday, February 3, 2024 - link
"The Ryzen 8000G series of APUs is based on AMD's Phoenix silicon, which is already in use in their Ryzen Mobile 7040/8040 chips."And Ryzen 6000 series APUs that were Zen-3+/RDNA2 but had DDR5 Memory Controllers and yet there was no Ryzen 6000G for AM5 and no Ryzen 7000G for AM5 as well that's since been rebranded as Ryzen 8000G and too late to be attractive in pricing at its current MSRP versus a $100 dollar CPU paired with a low cost dGPU.
Had AMD released a Ryzen 7000G back then when dGPU prices where higher then it would have made more sense at a higher price point but not today and rebranded as 8000G at the 8700G's current MSRP. So now to wait for the retail pricing for the 8700G to drop below $200 and that will make more sense versus a $100 CPU paired with a low cost dGPU.
Dante Verizon - Saturday, February 3, 2024 - link
At current costs this certainly won't happen, but APUs will still be very popular for compact PCs. Mainly the 8600G which, once at the same clock rate, should have almost the same performance as the 8700G.FWhitTrampoline - Saturday, February 3, 2024 - link
No not with the 760M iGPU on the 8600G only having half the number of Raster Back Ends(RBE) enabled and only 16 ROPs to the 780M's 32 ROPs and the reviewers just need to take it up to 1080P from 720P to make the ROPs more of a factor there 760M(16 ROPs) vs 780M(32 ROPs)!And Strangely enough the 660M was only 6 CUs and only one Shader Array active for that RDNA2 iGPU while the 760M got 8CUs and so both Shader Arrays had to be activated for that on the 8600G and each shader array supports 2 RBEs and there are 4 RBE's total across the 2 Shader arrays that make up the full tape-out. So to make the 760M 2CUs/1WGP on each shader shader array is disabled and so are 1 RBR on each Shader array to net only 16ROPs there for the 760M Bin!
So any reviewer testing at only 720P is not going to stress the raster performance that much on any 760M vs 780M comparison and I would test the scaling of both from 720P to 1080P and even 1440p(even if the frame rates drop below 30 FPS) to get some scaling with resolution numbers for the iGPUs.
FWhitTrampoline - Saturday, February 3, 2024 - link
P.S. Raster Back End(RBE) and Render Back End(RBE) are pretty much synonymous but I get that it's used to mean the same thing and on Radeon iGPUs and each RBE has 8 ROPs. And I'm Using Techpowerup's GPU database for my Render Configuration numbers and the iGPU Block Diagrams that AMD provided for the Radeon 600M and 700M series iGPUs' full tape-outs that are binned for hardware units to create the various iGPU SKUs.Terry_Craig - Saturday, February 3, 2024 - link
I think they are very close in any res: https://youtu.be/puKstrlDLOI?t=425FWhitTrampoline - Saturday, February 3, 2024 - link
ETA Prime adjusts settings across his runs to target 60 FPS minimum Frame rates and when he can not get that then he'll target 30FPS to 60FPS with settings not maintained between runs because he's just tying to show the way to get a setting mix that targets playable frame rates while retaining Image Quality as best as possible.So for that his testing is good for that and his very small for factor builds that no others in the tech press rally focus on building! But That's not good for actual iGPU reviewing where some of the settings need to be turned off and other settings equalized across runs to properly stress the Raster Performance of the 760M iGPU vs the 780M(Twice as many ROPs enabled). So turn off all the up-scaling and frame generation and run some Raster Intensive games at high settings and at different Resolutions there to get at actual Raster Scaling of the iGPUs! And so do that 720p and 1080P up to 1440P(even if the frame rates fall below 30FPS) to look at actual Raster performance only and that scaling there for the 760M vs 780M.
And folks Like Gamers Nexus and Hardware Unboxed do the actual hardware oriented benchmarks that take a few days to complete and use more gaming titles there for that and at different resolutions for Raster Gaming tests and then other non Raster only but Ray Traced and Up-scaled or frame generated tests that are separate from the raster testing.
And did you note on ETA Prime's recent InWin Chopin Max Build video that the included AMD Spire cooler was too tall to fit in that Inwin Chopin Build so some other proper Low Profile cooler was utilized. And AMD's clueless about very small form factor builds that utilize AMD's G series Desktop APUs like the ASRock Desk Mini and Inwin Chopin that need true low profile coolers to fit those form factors!
kn00tcn - Saturday, February 3, 2024 - link
it would not have made sense to have diy apus a year ago with expensive motherboards and ddr5, especially while zen3 ddr4 was so cheap and readily available (and selling well)MDD1963 - Saturday, February 3, 2024 - link
I mean, how could *anyone* have anticipated or even thought of testing for gaming workloads exceeding 190 seconds?kn00tcn - Saturday, February 3, 2024 - link
people test, but nobody watches the clockspeeds and wattage the whole timeon a related note, a lot of my personal benchmarking is not an average or a 'run', but actually i choose a demanding spot to stand still and do my single fps temp/watt/fan logging over time and hardware comparisons there, because the demanding parts are what really matter when choosing settings or parts (and i'm 60 vsync anyway)
kn00tcn - Saturday, February 3, 2024 - link
i dont get it, my asrock deskmeet with 5600g has all the STAPM options to tweak or disable it, so is this simply a matter of zen4 desktop mobos not having the user facing options?https://github.com/FlyGoat/RyzenAdj there's always this
FWhitTrampoline - Saturday, February 3, 2024 - link
I'm waiting for the ASRock X600 Desk Mini and its STX/AM5 MB to show up at ASRock's web site so I can look at the manual for that and the Memory QVL and even the SSD compatibility listings. And I sure hope there's some USB4 there. But really I want ASRock to Provide an OCuLink Knockout on the steel case with mounting holes for some M.2 to OCuLink Adapter that ASRock can provide as an extra cost option! Now My X300 desk Mini has a USB Knockout and mounting points for an optional extra USB port in the x300 Desk Mini But I'm looking at maybe getting some M.2 to OCUlink adapter and getting out the Dremel Tool there for that to get some OCuLink Port retrofitted there! The X300 does not even have USB4 so even if the 4 PCIe lanes to the bottom M.2 slot on the STX MB are PCIe 3.0 that's still similar bandwidth to USB4.kn00tcn - Thursday, February 8, 2024 - link
memory qvl is almost useless, what matters is the chips used, speed, timings, and mobo/agesa generated subtimingsSunrise089 - Saturday, February 3, 2024 - link
What sensor is the APU actually pulling from on desktop? I get the problem conceptually but do desktop motherboards have a skin sensor somewhere?!? Or is there actually no sensor and instead there’s just an algorithm at work?FunBunny2 - Saturday, February 3, 2024 - link
that gets a Bingo.kn00tcn - Thursday, February 8, 2024 - link
GN's charts make it seem like an algorithm, a cumulative value goes up over time, and the result is mild throttling