Have you have used a browser with a dual-core?
Web browsing is heavily multi-threaded.
It's easy to sit on the 16-thread Ryzen 7 5800X and discuss without knowing what the dual-core APUs can
-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
*** AMD "Zen 4" thread (inc AM5/APU discussion) ***
Have you have used a browser with a dual-core?
Web browsing is heavily multi-threaded.
It's easy to sit on the 16-thread Ryzen 7 5800X and discuss without knowing what the dual-core APUs can
No.
"Chrome has a multi-process architecture and each process is heavily multi-threaded. The main goal is to keep the main thread (“UI” thread in the browser process) and IO thread (each process' thread for handling IPC) responsive. This means offloading any blocking I/O or other expensive operations to other threads."
https://levelup.gitconnected.com/how-web-browsers-use-processes-and-threads-9f8f8fa23371
Facebook is heavy, I remember with my old Core 2 Duo T6600 it was simply impossible to run it without waiting half a minute to load a single video - Facebook has many of them and when you scroll, you see how fast your CPU actually is.
2-core CPUs are terrible no matter the IPC.
2-core CPUs are terrible no matter the IPC.
"The company didn't confirm exactly when Zen 4 will be released, but sometime in 2022 looks the most likely. That would follow AMD's usual update cycle for its CPU architecture:
Despite being so far ahead of its expected release, we already have a few concrete rumours on what to expect from Zen 4.
The first one isn't a rumour at all - AMD itself has confirmed that it will move to a 5nm process, down from the current 7nm you'll find on Zen 3. This could be a significant move, with the ability to provide the same amount of power within a smaller footprint.
A subsequent post on tech blog Chips and Cheese suggests this could be as much as 40%, while IPC (instructions per clock) could increase by 25%. The article goes on to say that early samples of AMD's less EPYC processors show a 29% speed improvement over the current generation, despite having the same number of cores and clocks."
https://www.techadvisor.co.uk/news/pc-components/amd-zen-4-3801795/
- Zen - March 2017
- Zen 2 - August 2019
- Zen 3 - November 2020
Despite being so far ahead of its expected release, we already have a few concrete rumours on what to expect from Zen 4.
The first one isn't a rumour at all - AMD itself has confirmed that it will move to a 5nm process, down from the current 7nm you'll find on Zen 3. This could be a significant move, with the ability to provide the same amount of power within a smaller footprint.
A subsequent post on tech blog Chips and Cheese suggests this could be as much as 40%, while IPC (instructions per clock) could increase by 25%. The article goes on to say that early samples of AMD's less EPYC processors show a 29% speed improvement over the current generation, despite having the same number of cores and clocks."
https://www.techadvisor.co.uk/news/pc-components/amd-zen-4-3801795/
A bad news.
Genoa with Zen 4 will have only 96 cores, which is half way to doubling the core count, with alleged configuration of 12+1 chiplets, and not 8+1.
Which means the core count per chiplet will remain the same miserable 8 cores.
https://www.techpowerup.com/279116/amd-genoa-expected-to-cram-up-to-96-cores-mcm-imagined
Genoa with Zen 4 will have only 96 cores, which is half way to doubling the core count, with alleged configuration of 12+1 chiplets, and not 8+1.
Which means the core count per chiplet will remain the same miserable 8 cores.
https://www.techpowerup.com/279116/amd-genoa-expected-to-cram-up-to-96-cores-mcm-imagined
If the images in the link are aligned to scale, then the new cIOd looks smaller, so it must be something newer than the GloFo's old 12nm process.
128 is better
No progress, we cannot rely only on IPC improvement.
Keep in mid this will directly compete with the 24-thread Alder Lake or even later iterations.
AMD has no good track record of selling processors with more chiplets - 8-core Ryzen 7 5800X is plenty in supply, while the 12-core Ryzen 9 5900X doesn't exist in the supply chain.
My personal forecast is that AMD already shows signs of wrong decisions - Bulldozer 2 can come at any time now.
You can't buy the 5950X, it is vapourware.
And second - you contradict yourself - the server stations can have millions of cores, if the Threadripper has 64 cores, why can't the desktop have 32?
Zen 4 desktop will be limited to 8 cores and integrated graphics.
And another mismanagement - they shift the production to units which they cannot sell, when at the same time they desperately need real wafers for products which no one can buy - Ryzen 9 5900X, Ryzen 9 5950X and Radeon RX 6800, 6800 XT and 6900 XT.
Exactly. They chose to invest in fatter cores instead of more cores.
Which means lower system responsiveness in the future.
Future systems will behave better with higher core count, not with fat cores.
"Like I said many times, wide SIMD is kind of stupid in CPUs, I just hope AVX512 doesn't ruin the power consumption of these chips."
https://www.techpowerup.com/279129/amd-zen-4-microarchitecture-to-support-avx-512
Bulldozer 2 is coming.
https://www.techpowerup.com/279129/amd-zen-4-microarchitecture-to-support-avx-512
Bulldozer 2 is coming.
Wrong.
In order to Bulldozer 2 to happen you need Intel to have a very strong lineup which it will in the next couple of years, together with slow and power hungry processors from AMD.
Bulldozer didn't have more cores - it actually had up to 4 modules and 8 threads, and Intel had 4 cores and 8 threads at the same time.
There were applications in which the Bulldozer at launch was faster than Phenom 2, the software needed adjustments.
And there is always something after Alder Lake. This is why I said - in a couple of years, not later this year.
edit: lol Intel had a 6-core 12-thread Core i7-980X as early as Q1 2010, while the original Bulldozer FX-8150 was released in Q4 2011 !
Maybe it's Intel's plan to sabotage AMD's progress by introducing bad instructions which will mislead AMD to join, and then Intel will find a way either to have it with less power or to drop it altogether.
Look at how Nvidia is much better in the ray-tracing technology, while AMD cannot compete.
AMD's Next-Generation Van Gogh APU Shows Up with Quad-Channel DDR5 Memory Support
"AMD is slowly preparing to launch its next-generation client-oriented accelerated processing unit (APU), which is AMD's way of denoting a CPU+GPU combination. The future design is codenamed after Van Gogh, showing AMD's continuous use of historic names for their products. The APU is believed to be a design similar to the one found in the SoC of the latest PlayStation 5 and Xbox Series X/S consoles. That means that there are Zen 2 cores present along with the latest RDNA 2 graphics, side by side in the same processor. Today, one of AMD's engineers posted a boot log of the quad-core Van Gogh APU engineering sample, showing some very interesting information.
The boot log contains information about the memory type used in the APU. In the logs, we see a part that says "[drm] RAM width 256bits DDR5", which means that the APU has an interface for the DDR5 memory and it is 256-bit wide, which represents a quad-channel memory configuration. Such a wide memory bus is typically used for applications that need lots of bandwidth. Given that Van Gogh uses RDNA 2 graphics, the company needs a sufficient memory bandwidth to keep the GPU from starving for data. While we don't have much more information about it, we can expect to hear greater details soon."
"AMD is slowly preparing to launch its next-generation client-oriented accelerated processing unit (APU), which is AMD's way of denoting a CPU+GPU combination. The future design is codenamed after Van Gogh, showing AMD's continuous use of historic names for their products. The APU is believed to be a design similar to the one found in the SoC of the latest PlayStation 5 and Xbox Series X/S consoles. That means that there are Zen 2 cores present along with the latest RDNA 2 graphics, side by side in the same processor. Today, one of AMD's engineers posted a boot log of the quad-core Van Gogh APU engineering sample, showing some very interesting information.
The boot log contains information about the memory type used in the APU. In the logs, we see a part that says "[drm] RAM width 256bits DDR5", which means that the APU has an interface for the DDR5 memory and it is 256-bit wide, which represents a quad-channel memory configuration. Such a wide memory bus is typically used for applications that need lots of bandwidth. Given that Van Gogh uses RDNA 2 graphics, the company needs a sufficient memory bandwidth to keep the GPU from starving for data. While we don't have much more information about it, we can expect to hear greater details soon."
Product segmentation - Van Gogh will be positioned lower than Cezanne.
No, Van Gogh will be very low, ultra portable, within 3-5-7 watt TDP, while Cezanne will be up to >45 watt TDP.
AMD Ryzen 7000 Series ‘Raphael’ CPUs Leaked In New Roadmap – 5nm, Zen4, PCIe 5.0, DDR5 And Navi 2 Graphics Coming In 2022
AMD Ryzen 7000 Series 'Raphael' CPUs Leaked In New Roadmap - 5nm, Zen4, PCIe 5.0, DDR5 And Navi 2 Graphics Coming In 2022 (wccftech.com)
Including an iGPU that no one needs?
AMD will be in a trouble. A serious one.
AMD Ryzen 7000 Series 'Raphael' CPUs Leaked In New Roadmap - 5nm, Zen4, PCIe 5.0, DDR5 And Navi 2 Graphics Coming In 2022 (wccftech.com)
Including an iGPU that no one needs?
AMD will be in a trouble. A serious one.
What's the point of two identical APUs - Raphael and Phoenix? 
If Phoenix is enough with its iGPU for the intended market tiers, why would AMD want to lose its performance advantage against the Intel counterparts by wasting the precious die area for a weak GPU that no high-end or enthusiast buyer would want, instead of cramming the much needed more cores?
If Phoenix is enough with its iGPU for the intended market tiers, why would AMD want to lose its performance advantage against the Intel counterparts by wasting the precious die area for a weak GPU that no high-end or enthusiast buyer would want, instead of cramming the much needed more cores?