Bondrewd
Veteran
Not quite, but yeah, it works.
Just not on client parts (APUs in particular) which is the ~issue~.
AMD Execution Thread [2023]
- Thread starter Kaotik
- Start date
- Status
Just not on client parts (APUs in particular) which is the ~issue~.
DavidGraham
Veteran
One of their employees clarified the statement.
D
Deleted member 2197
Guest
Blender 3.6: AMD Ray Tracing Performance
Blender expands AMD GPU support with HIP-RT integration. What is HIP-RT, and how much does it impreove rendering times?
www.pugetsystems.com
DaVinci Resolve Studio 18.6 Neural Engine Performance Optimizations
In DaVinci Resolve 18.6, Blackmagic is claiming up to a 4x improvement in Neural Engine performance for AMD GPUs, and a 2x improvement for NVIDIA. Is this a true claim, or a matter of cherry-picked results that won't impact most users?
www.pugetsystems.com
Latest drivers are crashing on me whenever I start fiddling with the performance controls. It seems specific to the voltage control. Every time I try and undervolt it the screen goes black and I need to reboot.
8GB RX 580, and lots of annoyance.
8GB RX 580, and lots of annoyance.
https://videocardz.com/newz/amd-x86...ana-zen6-morpheus-microarchitectures-detailed
IPC figure is rather conservative for ZEN5, far form this 25%-30% IPC "leaks" from RGT/AdoredTV
finally 6 ALU´s
new 16 core complex
IPC figure is rather conservative for ZEN5, far form this 25%-30% IPC "leaks" from RGT/AdoredTV
finally 6 ALU´s
new 16 core complex
Last edited:
D
Deleted member 2197
Guest
AMD released a driver, allowing you to enable Fluid Motion Frames in Starfield, Star Wars Jedi: Survivor, Hogwarts Legacy and more
AMD has just released a new preview driver for its graphics cards, allowing owners of the AMD Radeon RX 7000 series to enable frame generation in games like Starfield, Star Wars Jedi: Survivor, Hogwarts Legacy and Red Dead Redemption 2.
www.dsogaming.com
10-15% would be healthy. Something like 19% for Zen 3 was unusual and was done by chasing a pretty low hanging fruit with the unified L3. I think without doing V-cache as standard(which AMD have made clear they aren't doing, at least not with Zen 5), there's not really any such low hanging fruit again to boost IPC like that in a single gen. Any talk of like 25%+ should just be laughed out of the room(as I did when MLID tried to claim this for Zen 4 early on).https://videocardz.com/newz/amd-x86...ana-zen6-morpheus-microarchitectures-detailed
IPC figure is rather conservative for ZEN5, far form this 25%-30% IPC "leaks" from RGT/AdoredTV
finally 6 ALU´s
new 16 core complex
Low power core is interesting, if true. Given that 'dense option' was pointed out with Zen 4 here, it suggests a potential 3rd design apart from the main and 'c' variants.
Latest drivers are crashing on me whenever I start fiddling with the performance controls. It seems specific to the voltage control. Every time I try and undervolt it the screen goes black and I need to reboot.
8GB RX 580, and lots of annoyance.
I have a 7900XTX and when I try to undervolt it fails the first time, if I retry it succeeds. I guess someone forgot to run regression tests in this area with the latest drives.
Bondrewd
Veteran
Oh there is.
They are making an actual LITTLE but it's not due for Zen5.
Lol did the verge really use the word bullshit in a question to a CEO?
The moat thing is a non issue. The question immediately after that one addressed it.
“PyTorch is a big deal, right? This is the language that all these models are actually coded in. I talk to a bunch of cloud CEOs. They don’t love their dependency on Nvidia as much as anybody doesn’t love being dependent on any one vendor. Is this a place where you can go work with those cloud providers and say, “We’re going to optimize our chips for PyTorch and not CUDA,” and developers can just run on PyTorch and pick whichever is best optimized?”
Great interview overall.
The moat thing is a non issue. The question immediately after that one addressed it.
“PyTorch is a big deal, right? This is the language that all these models are actually coded in. I talk to a bunch of cloud CEOs. They don’t love their dependency on Nvidia as much as anybody doesn’t love being dependent on any one vendor. Is this a place where you can go work with those cloud providers and say, “We’re going to optimize our chips for PyTorch and not CUDA,” and developers can just run on PyTorch and pick whichever is best optimized?”
Great interview overall.
You have been consistently wrong about most everything regarding AMD for the past few years, but you talk so confidently about things that you still manage to get people buying into your rhetoric anyways. There's genuinely no reason to believe you actually know anything
EDIT: unless you actually give us some information.
Last edited:
"and neither in AI."
AMD has been done nothing for AI in the last 10 years. So such statements are absolut rubbish.
It's an interesting "hybrid" approach with the Zen4 and Zen4C cores going in the Phoenix 2.
So they don't "believe" in the big and little core solution done by others but instead offer two cores sharing the same register-transfer level (RTL) template. The result being that both cores are exactly the same but Zen4C has a higher cell density (which makes it 35% smaller) and sacrifices clock speed potential compared to the less dense Zen4 core.
This makes a lot of sense in devices that are thermal limited like laptops, gamepads etc. In these cases having Zen4 cores would just be a waste of silicon area as they would be limited in speed due to the thermal design power.
It also makes sense in high core count products where not all cores can boost to full speed because of thermal and power constraints while offering good multi-core performance.
So they don't "believe" in the big and little core solution done by others but instead offer two cores sharing the same register-transfer level (RTL) template. The result being that both cores are exactly the same but Zen4C has a higher cell density (which makes it 35% smaller) and sacrifices clock speed potential compared to the less dense Zen4 core.
This makes a lot of sense in devices that are thermal limited like laptops, gamepads etc. In these cases having Zen4 cores would just be a waste of silicon area as they would be limited in speed due to the thermal design power.
It also makes sense in high core count products where not all cores can boost to full speed because of thermal and power constraints while offering good multi-core performance.
Bondrewd
Veteran
Oooh someone's upset.
Yes, RDNA3 missed.
Nothing else did.
They do, just that the real LITTLE shouldn't be an infra throughput core like Cortex-A or Atom.
This is not constructive conversation. You need to add details. What are the low hanging fruit to improve IPC and why hasn't it been used so far? What's the source on the new 'LITTLE' cores for Zen5? Give people something to actually talk about.
Last edited:
I just wish you'd qualify your comments with more appropriate language, unless you actually KNOW something is true, in which case you should be telling us more about it, which you almost never do. You just continually talk as if you're some insider with secret knowledge, yet rarely ever substantiate anything you say, not to mention that you've been wrong many times in things you've talked so confidently about. It's even worse when you're replying to others trying to say they're wrong, without ever really detailing why. You just make it sound like you know we're wrong and we just have to trust you for some reason.
I dont have any skin in the game here, I simply care about having better quality discussion and ensuring that people are being transparent about whether their discussion points are speculation or knowledge.
Last edited:
Samsung Showcases Groundbreaking Logic Innovations at System LSI Tech Day 2023
Samsung emphasizes its vision to propel the Fourth Industrial Revolution forward through a comprehensive System LSI humanoid platform; Inaugural event offers an early glimpse of next-gen logic portfolio encompassing Exynos 2400 mobile processor, Zoom Anyplace camera sensor technology, vision...
Samsung said marketing things about their upcoming Exynos 2400 which has an RDNA3 GPU:
Comparisons to the Exynos 2200 (2022 SoC) instead of the current Snapdragon 8 gen 2, expecting it to be competitive with SD8G2 but less so 8G3. Samsung and AMD announced an extension of their IP licensing agreement earlier this year but more info and confirmation isn't bad
Desktop Phoenix with two type of Zen4 cores
wccftech.com
AMD Phoenix Desktop APUs For AM5 Might Utilize Phoenix 2 Dies With Zen 4 & Zen 4C Cores
AMD's upcoming Ryzen 7000 "Phoenix" APUs for the AM5 platform might be utilizing the Zen 4 and Zen 4C hybrid architecture configuration.
wccftech.com
- Status