It's that same "Noone gets fired for buying Intel" mediocre mentality...
-
WANTED: Happy members who like to discuss audio and other topics related to our interest. Desire to learn and share knowledge of science required. There are many reviews of audio hardware and expert members to help answer your questions. Click here to have your audio equipment measured for free!
Intel destroyed by AMD, let's talk like audio
- Thread starter renaudrenaud
- Start date
It's that same "Noone gets fired for buying Intel" mediocre mentality...
OP
renaudrenaud
Major Contributor
- Thread Starter
- #22
Macs are on their way for the ARM... At the end of the year Intel will lost this market.
- Joined
- Sep 4, 2019
- Messages
- 1,172
- Likes
- 2,321
Hahahha.
Of course, there shouldn't be absolutely any deny about AMDs leadership when it comes to productivity/rendering performance.
Still,
I long hesitated between AMD and Intel platform for my early 2020 build.
Since my main computer is 80% about gaming, I ended up with a Z390 / 9700K / 32Go 3600Mhz set up. Why? Because Intel CPUs are still ahead when it comes to FPS/pure gaming performance (and only this). Pretty obvious when you look at 1080p benchs. Then, the gap reduces when you go up to 1440p/UHD
For my future build, I could turn around for some X670/AMD 4000 build. But I will only if Gaming performance benchmarked (same as "measured") comes closer to what Intel 10th Gen has to offer.
By the way, the aforementioned build is a very tiny SFF/itx one. Here it is:
Funny, but I just helped my son build a midpriced gaming system. At that pricepoint, the AMD 3600x offered significantly better performance than the Intel option (i5-9600). We went for an Nvidia 2060 Super for video, as it offered better performance and lower power consumption than the AMD choices.
It has always been good to have AMD out there, even when their chips have not been as good as Intel's. A competitor always pushes companies to develop and move forward harder. I am two years into my current workstation (Xeon 4 Core), so not looking for a replacement right now. If I were, I would be going AMD, as their 3950x outperforms the equivalent priced Xeon by a wide margin and produces far less heat and uses less power.
GeorgeWalk
Senior Member
- Joined
- Sep 6, 2019
- Messages
- 471
- Likes
- 792
Yes, that is what I was saying earlier.
AFAIK the Intel 9700K generates less heat than a Ryzen 3800x. This could be the only reason to pick an Intel CPU over AMD when it comes to an SFF build. The gaming performance delta is neglible and within variance imho. When it comes to any other task, AMD is better though. But for this specific scenario, Intel is a legitimate choice.
- Joined
- Feb 28, 2016
- Messages
- 1,279
- Likes
- 1,180
I wonder what the foot print for the D8088 would be if you had to put enough of them together to equal the compute power of that single Epyc?
As a rough estimate, we can suppose the 8088 has a throughput of 1M instructions per second and the EPYC 1 instruction per cycle per core at 3 GHz. A 64-core EPYC (the pictured one is a 16-core) then has about 200,000 times higher instruction throughput. Since each instruction can also accomplish a lot more, it is probably safe to say the EPYC is at least 1 million times faster. The 8088 DIP package measures 53x16 mm. A million of these would have an area of 848 m². Since a little space between the chips is necessary, we can round this up to 1000 m². That's roughly the size of 5 tennis courts. Powering this monstrosity would require about 2 MW while the top EPYC needs 280 W.
Intel absolutely dominates single threaded performance. I am running 3700x and my Jriver with digital EQ (FIR at 262k taps - eat that Chord!) is able to barely play real time without dropouts. Single thread performance of 3700x is good enough for now and when 4900x comes around I will pop that in and get an instant boost. You can't do that with Intel!
Hi, do you mean you can't do that same DSP with an i9-9900K (or faster)?
Senior NEET Engineer
Addicted to Fun and Learning
That's a big brain move. Buy a CPU then change it within a year.
- Joined
- Sep 4, 2019
- Messages
- 1,172
- Likes
- 2,321
I believe he is referring to Intel’s constantly changing motherboard chipset and sockets making newer generation chips incompatible. The new 10th generation pentium chips are nothing more than a mild update to the 9th generation, but require a new bios chipset and in turn motherboard. Conversely, AMD has pledged and followed through that their motherboards will be compatible for several generations of cpus. I believe the current 3rd gen Ryzen cpus will operate on first gen boards and AMD says 4th gen will also.
Yes I agree with that, having an i9-9900K myself (as mentioned earlier) and not being able to just swap it out for an i9-10900K.
But as you mentioned, it's a minor performance increase anyway and actually wouldn't help the kind of DSP (for audio) I'm doing anyway.
Newk Yuler
Active Member
- Joined
- Mar 5, 2019
- Messages
- 155
- Likes
- 252
IIRC, when AMD first started challenging Intel in the CPU market they shipped a lot of bad CPUs that had be replaced. It allowed them to claim the numbers being shipped against Intel. Along with many years of inferior measured performance compared to Intel has always made me want to stay away from AMD. I later gave them some preference for video cards that eventually went away in favor of Nvidia.
I've built and rebuilt a lot of computers over the years and only one had an AMD CPU from scratch. My dad used it for a decade for internet and email. The only reason it was replaced was because I didn't want to deal with him using Win 7 after its retirement and we decided it was time for a new computer. It was a decent machine for that sort of thing but it had weird quirks and failures. If I wanted something for power and dependability it always had an Intel CPU. Including the times I've purchased assembled desktops and laptops. I realize times have changed for both companies and I'm biased, but until I have a very good reason to switch I'll go Intel for a serious build. Partly because AMD started with BS claims of success based on shipping a bunch of faulty CPUs.
I've built and rebuilt a lot of computers over the years and only one had an AMD CPU from scratch. My dad used it for a decade for internet and email. The only reason it was replaced was because I didn't want to deal with him using Win 7 after its retirement and we decided it was time for a new computer. It was a decent machine for that sort of thing but it had weird quirks and failures. If I wanted something for power and dependability it always had an Intel CPU. Including the times I've purchased assembled desktops and laptops. I realize times have changed for both companies and I'm biased, but until I have a very good reason to switch I'll go Intel for a serious build. Partly because AMD started with BS claims of success based on shipping a bunch of faulty CPUs.
How can someone allergic to BS support Intel? The company that still doesn't use ECC for their caches or support ECC RAM on their non Xeon lines, still uses subpar thermal paste under their IHS instead of solder, cheats in benchmarks, does shady deals with OEMs to keep their monopoly and use very bad libel disguised as marketing (e.g. "lol, AMD is gluing chip together. Nevermind that we did too after a few months").
And best of all, pointing to AMD's shipping of faulty CPUs (that they did, and it affected Gentoo users like me the most, but we got free RMAs) but conveniently ignoring the endless stream of vulnerabilities that Intel's shoddy chips continue to exhibit. We even got another this morning: https://www.guru3d.com/news-story/c...rmation-to-be-extracted-from-other-cores.html
Intel is actually used by the audiophiles of the computer world, the ones who don't really know how computers work but "they know their ears and brands". AMD (even Piledriver) is used a lot by libre software/OS devs who actually know what it's all about:
for example, Linus Torvalds (https://lore.kernel.org/lkml/CAHk-=whan1CiRtcgBt-5SkW-ga_GeLH5+AO26RmK7vOA5yw9ng@mail.gmail.com/T/#u) and Matthew Dillon (http://lists.dragonflybsd.org/pipermail/users/2018-August/357852.html).
It doesn't though. Here's a non synthetic open-source single-threaded benchmark that souldn't be only about SIMD unit performance:
https://www.guru3d.com/articles-pages/intel-core-i9-10900k-processor-review,14.html
It doesn't really show a "domination". And most "real-world" software like browsers (or anything doing networking) will be a lot worse due to the syscall overhead of Intel's combined vulnerabilities.
Really, you should consider that Windows has a poor scheduler that doesn't deal well with the "internal NUMA" setup of Ryzen, that benchmarks could be (are often) compiled using ICC with Intel's math libraries and other stuff that doesn't allow you to really gauge hardware performance.
Now, I may come off as a fanboy, but I just really know about this and don't want people to be the audiophiles/living jokes of other crowds while they laugh at the original ones.
Intel only has the edge in two domains, right now: SIMD performance and (slightly) clock speeds. Still, you'd be buying from crooks selling half backed designs with more holes than Swiss cheese.
Last edited:
I meant single threaded gaming performance, which takes advantage of the Intel's ring bus and the lowered memory latency - this shortcoming of AMD (way less than 10% in real terms if you know how to tweak your b-die memory) compared to Intel should be fixed completely in Zen 3. I hear rumors of 30%+ improvements in singled threaded performance from improvements in memory, IPC, clock and core packaging.
Let's not get started on "audiophile" computers and "audiophile" network routers and switches. At one time some idiot was trying to argue that I need an "audiophile" computer because my 3700x would cause jitter when serving data to my DLNA network digital player - even though there is no clock information in the data packets
Last edited:
Promit
Active Member
- Joined
- Apr 1, 2020
- Messages
- 197
- Likes
- 523
Curiously, this was the same argument deployed by NVIDIA against AMD in the GPU battle. Of course they actually brought the receipts and micro-stutter turned out to be a real thing that eventually expanded the range of measurements that serious reviewers use to evaluate new hardware. I'm not holding out hope for Intel to back up the talk.
Personally I've been in the pro game dev world a long time and I'm hearing solid praise for AMD pretty much across the board. There are a few workloads and use cases where the Ryzen stuff still has driver problems or scheduling problems or something else wonky going on, but not many.
If you want best of the best gaming performance, you still would buy Intel, however, you are going to pay out the wazoo and are better off putting that money towards a better graphics card (although you are probably running a 2080 or better if you are one of these people).
I built my gaming computer during Amazon Prime Day last year, which was around the same time AMD released their new 3000 series. I went with Intel because there were some amazing deals on the 9700k and Z390 mobos, and the AMD cpus all sold out immediately. If I had to do it again now, AMD is a no-brainer since prices have come down on AMD CPUs and AM4 will be compatible with Zen 3.
L5730
Addicted to Fun and Learning
Benchmarks are benchmarks.
Without a (fairly) standardised set of testing methods, one simply cannot reliably compare the performance of something.
A car does 0-30 mph in x seconds on a hot sandy beach, and another does 0-62 mph in y seconds, on rainy day on grass. What use would x and y be to anyone, when comparing the two vehicles are for very similar purposes???
Intel have always had an instructions per clock advantage, so MHz for MHz, on a single thread, the Intel chip would complete a task quicker than an AMD chip with the same clock speed. The waters all got muddied with boost clocks, turbo, throttling etc. All well and good have x GHz single core speed, but when it tails off after a few minutes, that sucks.
I was looking to build a new PC to replace my old Intel Core 2 Duo E6750 machine. I started at Intel i7 4770k and kept looking at every new release and many things put me off. I didn't like the motherboard layouts, and I didn't like the shoddy putty being used to conduct heat from the chip die to the heat spreader.
AMD Ryzen and X370 chipset came along, and these seemed to offer everything I wanted in a platform. The heat spreader is soldered to the die, so I'm happy about that. The ASrock Tai-Chi X370 motherboard layout ticked all of the boxes. There are a couple of small teething issues, some BIOS tweaks are a bit odd, temperature reporting using an offset (really, still doing that?), a difficulty in getting exactly what the core voltage is supposed to be and how to read it without physically probing the board. Sure, the equivalent Intel i7 chip would be a little quicker in single threaded workloads, but I doubt I'd notice in real world use.
...and here is the thing - real world use.
I've read a couple of reviews, and one site did a huge comparison of performance on similarly spec'd machines AMD vs. Intel with the then current Adobe suite.
Benchmarks and stop watches showed which was faster in what areas and specific tasks (different filters in Photoshop maybe multi-threaded, despite a generally single threaded environment). But, the differences were not that huge really. A few seconds when a task took a few minutes - I doubt that anyone would really notice that on their home machine if they didn't have a stop watch.
The article mentions laptops as an example where benchmark performance stats. aren't everything. I agree, you are buying a product where usability, form factor, battery life, weight and other factors are important. It's like having the cleanest, most perfect DAC on the planet, but it's a stupid shape, weighs so much that four beefy fellas need to move it around, lights up like Blackpool tower as soon as you turn in on and the remote control randomises it's buttons every time you press a button. It'd be utterly unusable to the vast majority of people, but it measures soo well.
When it's about desktop PC components though, nah, benchmarks are important.
Without a (fairly) standardised set of testing methods, one simply cannot reliably compare the performance of something.
A car does 0-30 mph in x seconds on a hot sandy beach, and another does 0-62 mph in y seconds, on rainy day on grass. What use would x and y be to anyone, when comparing the two vehicles are for very similar purposes???
Intel have always had an instructions per clock advantage, so MHz for MHz, on a single thread, the Intel chip would complete a task quicker than an AMD chip with the same clock speed. The waters all got muddied with boost clocks, turbo, throttling etc. All well and good have x GHz single core speed, but when it tails off after a few minutes, that sucks.
I was looking to build a new PC to replace my old Intel Core 2 Duo E6750 machine. I started at Intel i7 4770k and kept looking at every new release and many things put me off. I didn't like the motherboard layouts, and I didn't like the shoddy putty being used to conduct heat from the chip die to the heat spreader.
AMD Ryzen and X370 chipset came along, and these seemed to offer everything I wanted in a platform. The heat spreader is soldered to the die, so I'm happy about that. The ASrock Tai-Chi X370 motherboard layout ticked all of the boxes. There are a couple of small teething issues, some BIOS tweaks are a bit odd, temperature reporting using an offset (really, still doing that?), a difficulty in getting exactly what the core voltage is supposed to be and how to read it without physically probing the board. Sure, the equivalent Intel i7 chip would be a little quicker in single threaded workloads, but I doubt I'd notice in real world use.
...and here is the thing - real world use.
I've read a couple of reviews, and one site did a huge comparison of performance on similarly spec'd machines AMD vs. Intel with the then current Adobe suite.
Benchmarks and stop watches showed which was faster in what areas and specific tasks (different filters in Photoshop maybe multi-threaded, despite a generally single threaded environment). But, the differences were not that huge really. A few seconds when a task took a few minutes - I doubt that anyone would really notice that on their home machine if they didn't have a stop watch.
The article mentions laptops as an example where benchmark performance stats. aren't everything. I agree, you are buying a product where usability, form factor, battery life, weight and other factors are important. It's like having the cleanest, most perfect DAC on the planet, but it's a stupid shape, weighs so much that four beefy fellas need to move it around, lights up like Blackpool tower as soon as you turn in on and the remote control randomises it's buttons every time you press a button. It'd be utterly unusable to the vast majority of people, but it measures soo well.
When it's about desktop PC components though, nah, benchmarks are important.
Senior NEET Engineer
Addicted to Fun and Learning
No advantage in cache and memory latency?
Similar threads
- Poll
