AnarchoPrimitivI'm expecting a lot of bad faith arguments to the like of "that's too late, people will just buy Nvidia", when a majority of those people were going to buy Nvidia regardless... At least thats what historical precedent has demonstrated time and time again.... Even when AMD offers a better product and for less, Nvidia still sells more, this was especially the case in the 2000s. It's just a simple fact that thr majority of consumers don't make their purchasing decisions rationally by comparing price to performance as we would like to believe... Nvidia just has this mentia that better specs at a better price seemingly has a very difficult time overcoming. Solely for the sake of competition, I wish it was different, as nothing would be better for consumers than for AMD to grab a big chunk of market share, although I have a small feeling that RDNA2 will be the most competitive generation in years, and I think the commiserate release of the consoles, and the fact that developers will be programming for the consoles first and foremost, will help AMD tremendously this time around.

What's it like to be a victim all the time?

AnarchoPrimitivI'm expecting a lot of bad faith arguments to the like of "that's too late, people will just buy Nvidia", when a majority of those people were going to buy Nvidia regardless... At least thats what historical precedent has demonstrated time and time again.... Even when AMD offers a better product and for less, Nvidia still sells more, this was especially the case in the 2000s. It's just a simple fact that thr majority of consumers don't make their purchasing decisions rationally by comparing price to performance as we would like to believe... Nvidia just has this mentia that better specs at a better price seemingly has a very difficult time overcoming. Solely for the sake of competition, I wish it was different, as nothing would be better for consumers than for AMD to grab a big chunk of market share, although I have a small feeling that RDNA2 will be the most competitive generation in years, and I think the commiserate release of the consoles, and the fact that developers will be programming for the consoles first and foremost, will help AMD tremendously this time around.

If we hear those arguments, they will rest on their own merits.....or lack thereof. Don't let the polarizing continent of fanboys, from either side, skew opinion. I literally have a small handfull of those people on ignore because I'm sick of hearing it... lol

FrickDo you mean the higher clocks? I'm pretty sure AMD caught up with the IPC with Zen2.

Intel has higher clocks, but based on what I'm seeing for Icelake, Intel is taking a big step forward with IPC again.

Remember that Skylake only had a 32kB L1 data-cache and 256kB L2 cache. Zen2 clobbers that with a 64kB L1 dCache and 512kB L2 cache.

Icelake comes back with 64kB L1 cache and 512kB L2 cache. But not only that, its improving the ROB (register renaming buffers or something like that), and other bits that make Icelake look much wider and probably much better from an IPC perspective.

I don't think Zen2 was ever "clearly better" than Skylake with regards to IPC. It was close, but not necessarily an IPC king. Icelake has a bunch of core-enhancements that should improve IPC dramatically. The question is what clocks can Intel get from their 10nm node. Intel's 14nm node clearly is cost-effective and has very high clocks, so the 10nm IceLake may lose a bit of clock speed.

techguymaxcWhat's it like to be a victim all the time?

I think your reading comprehension needs improvement if that's what you got from his post.

dragontamer5788I doubt it. Intel's IPC is very far ahead, and memory-latency is always going to be hampered given AMD's architecture. With Intel's Icelake improving IPC (and finally moving to 10nm), I think Intel is moving faster than AMD can catch up.

Lol wait what? Zen2 actually has higher IPC than intel in most workloads. Gaming is the only exception because of the nature of the workload itself where memory and intercore latency is crucial.

AnarchoPrimitivI'm expecting a lot of bad faith arguments to the like of "that's too late, people will just buy Nvidia", when a majority of those people were going to buy Nvidia regardless... At least thats what historical precedent has demonstrated time and time again.... Even when AMD offers a better product and for less, Nvidia still sells more, this was especially the case in the 2000s. It's just a simple fact that thr majority of consumers don't make their purchasing decisions rationally by comparing price to performance as we would like to believe... Nvidia just has this mentia that better specs at a better price seemingly has a very difficult time overcoming. Solely for the sake of competition, I wish it was different, as nothing would be better for consumers than for AMD to grab a big chunk of market share, although I have a small feeling that RDNA2 will be the most competitive generation in years, and I think the commiserate release of the consoles, and the fact that developers will be programming for the consoles first and foremost, will help AMD tremendously this time around.

At the end of the day, nVidia showed off good stuff, AMD had horrible drivers with the 5700 XT and locked the clock speeds on the 5600 XT (unforgivable). Radeon has been doing a good job killing themselves, even AMD fans like myself know it. Ryzen has been great in comparison. Ryzen 3600 is $250 here in Canada, the 10600k is $400... Ryzen is the obvious choice. The 10400's clock speed is unforgivably low (4ghz) which makes the 4.4ghz Ryzen 3600 also an easy choice in comparison. Motherboards are also cheaper and better (Strix B550-F is $230 here, and the Strix Z490 is $350, and the Strix B550-F actually has better VRMs). I'll probably buy a 3080 if I can, I'm not waiting for November, it is up to AMD to show Radeon early enough to matter.

If the Ryzen 4600 also launches for $250 CAD, that will be another home run. 20 percent better IPC than the 10600k, 1/3 less power consumption, and hopefully finally 4.8ghz clock speeds?

techguymaxcWhat's it like to be a victim all the time?

I don't understand what you're talking about? Who's a victim and what are they a victim of? I'm seriously asking? I don't feel as though hoping for more competition, regardless of who the winners and losers are is a controversial opinion, but I gather that you seemingly do? I may be mistaken but it seems as though you're looking for a fight where none exists

sergionographyLol wait what? Zen2 actually has higher IPC than intel in most workloads. Gaming is the only exception because of the nature of the workload itself where memory and intercore latency is crucial.

lemire.me/blog/2019/12/05/instructions-per-cycle-amd-versus-intel/

Its not very clear cut. Zen2 was much better than Zen or Zen+, but I'm not convinced that Zen2 took the IPC crown from Skylake yet.

Intel's superior performance in video game benchmarks should leave your head scratching too: Intel can't be getting all of that speed just from clocks, video games talk to RAM a lot (and the GPU) and DDR4 (and GPU) doesn't care about the clockspeed of the CPU. There's something to be said about Intel's superior and low-latency memory controller, which is probably what is affecting video game FPS more than anything else. (Especially when you consider that AMD's chips have superior sized caches).

TheLostSwedeI think your reading comprehension needs improvement if that's what you got from his post.

Thank you, I felt like he was looking for a fight where none existed

techguymaxcSo an announcement that there will be an announcement.

Guess AMD doesn't want my money. I sold my 2080 Ti a month ago and I'm ready to buy today.

Maybe AMD are cranking clock speeds as we speak.

Anyway, all I can think of is Sean Connery in a sub.

dragontamer5788lemire.me/blog/2019/12/05/instructions-per-cycle-amd-versus-intel/

Its not very clear cut. Zen2 was much better than Zen or Zen+, but I'm not convinced that Zen2 took the IPC crown from Skylake yet.

Well because IPC is a very generic and broad term. What we do know for sure is that 3000 series beats Intel with much lower clock speeds, or at the very least takes them on head to head. This is on similar core configurations.

dragontamer5788lemire.me/blog/2019/12/05/instructions-per-cycle-amd-versus-intel/

Its not very clear cut. Zen2 was much better than Zen or Zen+, but I'm not convinced that Zen2 took the IPC crown from Skylake yet.

Intel's superior performance in video game benchmarks should leave your head scratching too: Intel can't be getting all of that speed just from clocks, video games talk to RAM a lot and DDR4 doesn't care about the clockspeed of the processor. There's something to be said about Intel's superior and low-latency memory controller.

It isn't that complicated. Ryzen IPC is higher, you can tell by running both CPUs at the same clock speed and voila, Ryzen is faster. Ryzen is lacking clock speed, that is all. If Ryzen also hit 5.3ghz we wouldn't be having this conversation.

Also Intel's memory controller is not superior. There is a difference between a mesh and ring bus. A mesh is better the more cores you have. A ring bus is better with less cores. AMD doesn't see the need make two different sets of CPUs just to get an extra 3 percent in gaming FPS, especially since IPC and clock speed will solve the slight memory latency deficiency. It isn't an AMD vs Intel thing, it is a conscious choice. Intel also has workstation CPUs that don't use a ring bus, and they've died out, killed by AMD's offerings. The 10980XE anyone?

AnarchoPrimitivThank you, I felt like he was looking for a fight where none existed

I really think some people have a hard time understanding what they're reading. It could also be a matter of not having enough insight into the topic they comment on, but they want to sound smart or add their own opinion, without actually understanding the wider picture. Oh well...

SearingIt isn't that complicated. Ryzen IPC is higher, you can tell by running both CPUs at the same clock speed and voila, Ryzen is faster.

Intel absolutely has faster PDEP, PEXT, DIV, and IDIV instructions. I know, because I've measured them personally. In the case of PDEP / PEXT, 1000% faster or more (single-clock PDEP / PEXT on Intel, but over 15 clocks on AMD).

AMD and Intel both have single-clock add / subtract. AMD had the first dual-AES pipeline (supporting two concurrent AES instructions), so AMD's AES IPC was superior to Intel's AES IPC on Skylake.

What instructions, what conditions, what memory? Its actually very complicated. If we're sitting around adding/subtracting numbers inside of registers all day, both processors tie. MAC instructions, I forget from the top of my head... but you get the picture. Its pretty complicated, because all these CPUs have different speeds for every instruction.

dragontamer5788Intel absolutely has faster PDEP, PEXT, DIV, and IDIV instructions. I know, because I've measured them personally.

AMD and Intel both have single-clock add / subtract. AMD had the first dual-AES pipeline (supporting two concurrent AES instructions), so AMD's AES IPC was superior to Intel's AES IPC on Skylake.

What instructions, what conditions, what memory? Its actually very complicated.

Of course, I'm talking about on average real world, that's why I said it doesn't have to be complicated. Run them both at the same clock speed and do your stuff, and generally Ryzen 3000 will beat Skylake.

milewski1015Isn't it likely that these dates are just reveal events?

you may be correct about that, I may have read into the "launch" date a little too much. Hopefully if that is the case we will get an update prior to the event.

Legacy-ZAI love how AMD has been very quiet, it most likely signals something great down the line. I really wanted a juicy tidbit to bite on in the meanwhile though. :laugh:

I like this approach as well. I am not surprised on the cpu side. From a consumer mind share point of view, AMD is in the position of power after riding a wave of great products in the 3xxx series and full momentum going into the Zen 3 launch, while Intel has been the one having to constantly react for quite some time. So no need at all for AMD to play their cards now. On the GPU side I am a little surprised with the silence. I think nVidia's reveal was for the most part very well received and if AMD were fully confident with their original forecasting of price/performance for RDNA2 vs. 30xx that they would have already brought out some sort of counter info to hold off potential 30xx buyers (being that sales start next week). And if they have a grand slam up their sleeves, they would have definitely made it known now to hold off buyers for another month. Perhaps they have had great yields giving them flexibility in pricing, and therefore are holding off to find out real world performance of the 30xx series relative to their lineup (opposed to marketing numbers) so that they can adjust to either match or undercut nVidia right out of the gate. All speculation of course...

I'm excited - it's my birthday month so maybe I'll just say F it and get myself some shiny new computer parts.

I'll be waiting though to see what AMD has to offer for their new GPUs. If they offer something similar and/or better for less than what Nvidia is bring to the table, I'll get a new GPU from AMD and skip Nvidia this time around.

SearingOf course, I'm talking about on average real world, that's why I said it doesn't have to be complicated. Run them both at the same clock speed and do your stuff, and generally Ryzen 3000 will beat Skylake.

I guess what I'm trying to point out, is how much of that is attributable to Ryzen 3xxx series 512kB L2 cache and 64kB L1 cache?

With Icelake hitting 512kB L2 and 64kB L1 dCache, I don't think there's anything AMD can do to keep up with Intel in this next generation on an IPC basis. The main saving grace, is that Icelake probably won't clock as high (given all the issues on the 10nm node).

dragontamer5788I guess what I'm trying to point out, is how much of that is attributable to Ryzen 3xxx series 512kB L2 cache and 64kB L1 cache?

With Icelake hitting 512kB L2 and 64kB L1 dCache, I don't think there's anything AMD can do to keep up with Intel in this next generation on an IPC basis. The main saving grace, is that Icelake probably won't clock as high (given all the issues on the 10nm node).

www.techpowerup.com/248825/intel-increases-l1d-and-l2-cache-sizes-with-ice-lake#:~:text=The%20L1%20instruction%20cache%20is%20still%2032%20KB,L2%20caches%20with%20relatively%20smaller%20shared%20L3%20caches.

I don't think that zen one is fully right, L2 cache is inclusive now.

DemonicRyzen666www.techpowerup.com/248825/intel-increases-l1d-and-l2-cache-sizes-with-ice-lake#:~:text=The%20L1%20instruction%20cache%20is%20still%2032%20KB,L2%20caches%20with%20relatively%20smaller%20shared%20L3%20caches.

I don't think that zen one is fully right, L2 cache is inclusive now.

I stand corrected. Icelake L1 is only 48kB.

Seems like Zen is 64kB combined cache per core according to Wikichip. Which means IceLake actually has the L1 cache advantage. Hmmm.

reminded me the movie , the hunt for red October.....but please don't make it too red...

dragontamer5788Intel has higher clocks, but based on what I'm seeing for Icelake, Intel is taking a big step forward with IPC again.

Remember that Skylake only had a 32kB L1 data-cache and 256kB L2 cache. Zen2 clobbers that with a 64kB L1 dCache and 512kB L2 cache.

Icelake comes back with 64kB L1 cache and 512kB L2 cache. But not only that, its improving the ROB (register renaming buffers or something like that), and other bits that make Icelake look much wider and probably much better from an IPC perspective.

I don't think Zen2 was ever "clearly better" than Skylake with regards to IPC. It was close, but not necessarily an IPC king. Icelake has a bunch of core-enhancements that should improve IPC dramatically. The question is what clocks can Intel get from their 10nm node. Intel's 14nm node clearly is cost-effective and has very high clocks, so the 10nm IceLake may lose a bit of clock speed.

Intel has been shady about their IPC gain claims, they have less than 5 percent advantage in out of order but mostly due to faster caches. Their most recent IPC claim is for a select few benchmarks, that scale with increased cache size. Can you guess what Intel has done differently with new chips?

I'm honestly surprised AMD and TSMC can keep up with the multitude of chips they are pushing, between consoles, CPUs, GPUs, and chipsets......

So AMD will launch a 3070ti competitor, will that's not what i need, my 1080TI needs an Upgrade NOW :)

But i guess that intel is out of the game before they even entered :D

AMD late to the GPU party once again...

Yes! But wait is that when they plan to publish the specs or the units?