from the can-i-still-root-for-them-if-they're-no-longer-underdogs? dept.
AMD Ryzen Improves IPC by 52%, not 40%
AMD Ryzen 7 desktop chips are now available for pre-order, and will be released generally on March 2nd. The cheapest "Ryzen 7" 8-core chip will be $329, but has 16 threads just like the $399 and $499 versions (there had been some concern that it might not have multi-threading). Ryzen 3 and 5 series quad-core and hex-core chips will be released later.
AMD held a "Tech Day" to share details about its new chips. Over the past year or two, AMD has said that their goal was to improve instructions per clock (IPC) by 40% with Zen/Ryzen. Now they are saying that they have achieved that... by improving IPC by 52%. It's an impressive number that would not have been possible had Ryzen's predecessor, the Bulldozer architecture, been competitive with Intel's CPUs (on single-threaded performance). However, keep in mind that comparisons between Ryzen and Bulldozer or certain Intel Core i7 CPUs are still based on information provided by AMD.
The 8-core design features 4.8 billion transistors and "200 meters of wiring".
YouTuber removes footage of Ryzen Overclock World Record
YouTube tech pundit Austin Evans uploaded a video earlier today containing footage of AMD's Ryzen launch event. Shortly afterwards, the video was made private, then replaced with a re-edited version of the piece with a couple of changes. A section in which Austin outed the Vega video card by name was edited and overdubbed with the description "a really cool graphics card".
Another section of the video showed an overclocking competition held at the event with a number of well-known LN2 overclocking experts seeing just how far they could push the new Ryzen chips. This whole section was removed, including footage of "a Ryzen chip" running at just over 5.1GHz, followed by the OCers celebrating as a run on Cinebench's R15 multi-threaded performance test set a new world record.
Comments on the video asking why the video was replaced and uploaded confirm that the Vega mention and OC section were removed. Austin Evans did not explain exactly why these changes were made, merely saying "YOU SAW NOTHING" in the comments section.
The 5.1GHz figure is from my memory. I think it might have been 5.16GHz more exactly, but I'm not completely sure about that and obviously can't verify it from the original video.
Related Stories
AMD Ryzen 7 Launches
Reviews and benchmarks for AMD's Ryzen 7 8-core desktop CPUs flooded out at 9 AM EST/6 AM PST:
Along with the new microarchitecture, Zen is the first CPU from AMD to be launched on GlobalFoundries' 14nm process, which is semi-licenced from Samsung. At a base overview, the process should offer 30% better efficiency over the 28nm HKMG (high-k metal gate) process used at TSMC for previous products. One of the issues facing AMD these past few years has been Intel's prowess in manufacturing, first at 22nm and then at 14nm - both using iterative FinFET generations. This gave an efficiency and die-size deficit to AMD through no real fault of their own: redesigning older Bulldozer-derived products for a smaller process is both difficult and gives a lot of waste, depending on how the microarchitecture as designed. Moving to GloFo' 14nm on FinFET, along with a new microarchitecture designed for this specific node, is one stepping stone to playing the game of high-end CPU performance.
Ryzen 5 chips will be released sometime in "Q2", and are presumed to have 4 to 6 cores with hyperthreading enabled. One of these has been revealed: the Ryzen 5 1600X. It has 6 cores, and equivalent clock (3.6 GHz) and turbo (4.0 GHz) speeds to the $500 8-core flagship Ryzen 7 1800X. Ryzen 3 chips will be released in the second half of the year, and include quad-cores with no hyperthreading.
The Intel Core i7-7700K maintains a lead in single-threaded performance, but the Ryzen 7 chips lead in many multi-threaded benchmarks (sometimes beating the $1089 Intel Core i7-6900K).
(Score: 5, Funny) by Anonymous Coward on Thursday February 23 2017, @05:09PM
*stabs wildly*
*stabs some more to make sure*
*stabs again for good measure*
*additional stabbing here*
*stabs just in case*
*considers not stabbing, stabs instead*
(Score: 0) by Anonymous Coward on Thursday February 23 2017, @05:14PM
Have you been drinking, sir?
(Score: 2) by linkdude64 on Thursday February 23 2017, @06:28PM
Damn Russians and their murderous fanboyism!
(Score: 2) by DannyB on Thursday February 23 2017, @09:59PM
Only if they've been drinking nVodka.
To transfer files: right-click on file, pick Copy. Unplug mouse, plug mouse into other computer. Right-click, paste.
(Score: 3, Insightful) by DeathMonkey on Thursday February 23 2017, @06:47PM
I get the vague impression this guy doesn't prefer nVidia.
(Score: 2) by takyon on Friday February 24 2017, @01:15AM
Just in case you missed it: https://soylentnews.org/article.pl?sid=17/02/22/1249249 [soylentnews.org]
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 2) by bob_super on Thursday February 23 2017, @05:19PM
I haven't found specs on the memory interfaces...
Working on my boss to buy a new box, but we need massive memory bandwidth. I can get quad-channel DDR4 from Intel for just over a grand (CPU+mobo+RAM), will Ryzen match that, pretty pretty pretty please??
(Score: 2) by Scruffy Beard 2 on Thursday February 23 2017, @07:42PM
I tired going to the source [amd.com], and it looks like you are right. They have very little information posted.
I think Linus Tech Tips mentioned DDR4 support.
The focus on hype is concerning though.
(Score: 2) by bob_super on Thursday February 23 2017, @08:00PM
The AM4 socket [wikipedia.org] only has 1331 pins, which doesn't bode well for quad-channel DDR4.
That page says support for four modules, but I assume it's 2 per channel...
Which sucks, because I really need max bandwidth, and I can't see how Ryzen can compensate having half what the "Extreme" Intel have (for my workloads).
(Score: 2, Funny) by Anonymous Coward on Thursday February 23 2017, @09:05PM
only has 1331 pins
That won't do. It obviously needs 6 more pins. I suggest adding JTAG.
(Score: 1) by Scruffy Beard 2 on Thursday February 23 2017, @09:26PM
I figured they were saving it for AM4+
(Score: 2) by bob_super on Thursday February 23 2017, @10:14PM
They only need to add one more, and then cut it in half.
(Score: 0) by Anonymous Coward on Thursday February 23 2017, @11:12PM
Optimizing for Windows 10?
(Score: 2) by LoRdTAW on Thursday February 23 2017, @08:18PM
I doubt this has quad channel memory. The original hype of a 32 core CPU with HBM and quad channel DDR4 was speculation of a hypothetical Zen server CPU which is usually where you find quad channel memory (aside from desktop Xeons re-badged as i7's).
Hopefully at some point AMD will release an opteron based on Zen with quad channel memory. Maybe toss in HBM. Then we might have a shot if someone makes a single socket desktop board.
(Score: 3, Insightful) by Azuma Hazuki on Thursday February 23 2017, @05:28PM
For over a decade I've been waiting for this. My first job involves building custom computers, and we've been watching Ryzen with massive anticipation since it was first announced. Odd thing is, now that 1) Ryzen looks like a world-beater and 2) Intel released sub-$100 2c/4t chips in the form of the Pentium G46xx series (and 4560), we may end up using Intel in the low end builds and AMD in the mid and high ones!
I am "that girl" your mother warned you about...
(Score: -1, Troll) by Anonymous Coward on Thursday February 23 2017, @06:06PM
Ryzen will be a world-heater! If you're looking for a correlation to global warming....
(Score: 3, Informative) by butthurt on Thursday February 23 2017, @06:25PM
[...] Ryzen was able to match Intel's performance with 45 W less TDP - 95 W TDP on Ryzen against the 140 W TDP on Intel's 6900K.
-- https://www.techpowerup.com/228684/amd-ryzen-demo-event-beats-usd-1-100-8-core-i7-6900k-with-lower-tdp [techpowerup.com]
(Score: -1, Troll) by Anonymous Coward on Thursday February 23 2017, @07:21PM
Fake news. Don't believe any of it. There is no way that AMD will ever outperform Intel. It's a mathematical impossibility. The tests are rigged, like always when someone tries to say AMD is better. But... the moderators are on a murderous rampage to stifle the truth.
(Score: 1, Funny) by Anonymous Coward on Thursday February 23 2017, @08:13PM
Post was over 140 chars and didn't end with "Sad!" Sad!
(Score: 0) by Anonymous Coward on Thursday February 23 2017, @07:15PM
From early signs it looks like AMD may have a competitive chip finally. Intel missed on its tick tock strategy and it AMD quickly caught up. Intel will have to up its game.
Just to temper that. A lot of what we have seen looks like intel graphic chips vs AMD boards. That was never a competition. Most gamers do not run that. The CUDA guys are running freestanding cards anyway. The office guys want a graphics chip that lets them have 10+ hours on their ultra thin showoff piece notebook.
Lets wait about 3-4 weeks when all the usual sites have their specs up. Right now it seems to be kind of a hype train feel. But looks good. What will be interesting are the single core and same clock tests. Then we will have a better feel for what AMD did. As most of the comparisons I have seen seem apples and applesauce.
(Score: 3, Informative) by Azuma Hazuki on Thursday February 23 2017, @08:37PM
From what I've seen, Ryzen appears to have Haswell/Broadwell level IPC, lower clocks, FAR better efficiency (seriously...3GHz 8C/16T in 65W, how the hell?!), and the kind of pricing I would never have dared imagine in my wildest dreams.
Intel is still going to be the single-thread performance king; for building a gaming machine right now, I'd still recommend the 7700K over any given Ryzen. For now. In every other respect, Ryzen whups Intel like a step-headed redchild. I want a 1700 for a Gentoo box.
I am "that girl" your mother warned you about...
(Score: 2) by vux984 on Friday February 24 2017, @02:42AM
What about ECC? My issue with intel seems that they've been restricting ECC memory support to the Xeons, but with desktop / gaming rigs hitting 32GB+ RAM and beyond and all the press about memory errors, comic ray induced bit flips, and even rowhammer (which ECC doesn't outright stop but allegedly ups the resistance by quite a bit)... there's a lot of people in my circle of friends who would get ECC if they could. And would even be willing to pay a bit extra and give up a couple percent of performance for it.
(Score: 2) by Azuma Hazuki on Friday February 24 2017, @07:28PM
Ooh, yeah, good point. I remember the FX series all have AMD-IOMMU (AMD's version of Intel's VT-d or directed I/O) enabled, but am not sure about ECC...
I am "that girl" your mother warned you about...
(Score: 2) by takyon on Friday February 24 2017, @01:27AM
I'm not sure if we reported on this, but Intel will miss even the tick-tick-tock or whatever they were calling it. They will be doing 14nm for a fourth generation of chips.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 3, Funny) by TheRaven on Friday February 24 2017, @09:44AM
sudo mod me up
(Score: 1) by higuita on Thursday February 23 2017, @06:57PM
The intel response will be that the day before the release, they will announce 16 and 32 core CPUs... again costing a huge fortune, mostly no one will buy it, but recovering again the top CPU brand
i do hope that this is a new athlon vs pentium4, were intel was kicked in the butt!
(Score: 0) by Anonymous Coward on Thursday February 23 2017, @07:16PM
recovering again the top CPU brand
I'm sure Intel will take a stab at it.
(Score: 3, Funny) by tibman on Thursday February 23 2017, @07:54PM
I've already seen some intel response (maybe?). Got an email from newegg about a bunch of sales. All of them were intel related : D
SN won't survive on lurkers alone. Write comments.
(Score: 2) by Celestial on Thursday February 23 2017, @07:09PM
I'm not one to initially adapt a new processor, but I look forward to buying a new notebook computer in late 2018 with an AMD Ryzen processor and AMD Vega graphics card. I imagine that they'll both have decent Linux drivers by then.
(Score: 2) by takyon on Thursday February 23 2017, @09:27PM
Yes. Too bad they won't go past 4 cores in the laptop, but it should have 8 threads.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 0) by Anonymous Coward on Thursday February 23 2017, @11:17PM
I imagine that they'll both have decent Linux drivers by then.
Only if AMD doesn't write them.
(Score: 3, Interesting) by requerdanos on Friday February 24 2017, @02:01AM
I'm not one to initially adapt a new processor, but I imagine that [AMD Ryzen and Vega will] have decent Linux drivers by [2018].
I am not normally one to initially adopt a new processor or technology for many reasons:
I have for years made a point of running technology a generation or two behind "cutting edge" for these reasons, with much success.
BUT
Right now, my main workstation has an AMD FX-8300 chip which is not the slowest chip by any means, but lags for important things I do like media encoding, data crunching, and compiling software. And it looks to me like an AMD Ryzen CPU with appropriate motherboard and RAM can not help but be immensely better than any FX/AM3+ no matter how tuned and polished the FX and no matter how fresh and untested/unmatured the Ryzen/AM4. It just looks like no contest to me.
Of course, my FX-8300 + Motherboard + RAM was as I recall about US$300 altogether, a year ago. For a Ryzen 7 1700X + comparable Motherboard & RAM it looks like I'll be out more like US$700.
What the heck, it's only money. I can use the old FX chip/board to build another decently fast system for someone. Looks like the chips and boards will be available from Newegg on March the 2nd. I already ordered the DDR4 RAM.
Just this one time I will be on the leading instead of trailing edge of something.
(Score: 3, Interesting) by RamiK on Thursday February 23 2017, @09:39PM
With most of the southbridge getting baked into the SoC die there's lots of fast connections even in the mid\low-end so the OEM boxes should start sucking less now.
compiling...
(Score: 3, Interesting) by tibman on Thursday February 23 2017, @09:45PM
Soo, i actually blew up my mobo some months ago while folding for SN. Knew that the little nano-itx was running too hot. But it was stable so i shrugged and ran it until the magic smoke came out. Put a new cheapo mobo in but the cpu socket was turned 90 degrees. Bumped out half the ram and the graphics card : / All it can do now is play little indie games.
Anyways. Just pre-ordered the Ryzen 7 1800x [newegg.com] : ) Should have a new computer together soon. Looking forward to climbing back up the team ladder! Will probably never beat those retired bitcoin miners at the top though : P
SN won't survive on lurkers alone. Write comments.
(Score: 3, Insightful) by bob_super on Friday February 24 2017, @01:17AM
I like how cmn has about a third of the overall points, runaway over a fifth, malloc_free over a tenth, leaving the rest of us far behind in the dust.
Anybody after the 14th is sub-1%...
(Score: 1, Insightful) by Anonymous Coward on Thursday February 23 2017, @11:10PM
Its my understanding that all future AMD chips will have AMD's PSP technology in them. This is their equivilent of Intels AMT/MT/vPro remote control tech. If this is correct, I find it quite disheartening, as now pretty much all new mainstream CPUs are backdoored from the factory. :(
I wonder if CPU manufactures are even allowed to make CPUs without this tech anymore ... There certainly seems to be a niche market for it.
Another option would be to open source the firmware that controls the co-processor (master processor??) and/or allow a user to upload their own keys to it, so that alternative firmware could be loaded by it. It would open the door for a more secure system, and a lot of different alternative uses for that chip.
(Score: 0) by Anonymous Coward on Friday February 24 2017, @02:58AM
There is no reason they couldn't make the X models unkeyed and just use writelocking of the BIOS to ensure security, except for 3rd party DRM implementations. Which is really what it comes down to. It isn't remote management capabilities that are causing the signed firmware fiasco. It is DRM sidechannel concerns from the lame duck media content producers who want to bring us into 1984 just so they can chase these supposed larger profits from preventing piracy.
Given the restrictions on Ryzen, and the new VBIOS signing on the 5k/6k Intel processors, I will probably be buying old G34 or Xeon hardware that either doesn't contain ME provisions, or at least can have it disabled to the maximum extent possible.
Pricing for Ryzen already puts it in the realm of just buying G34 chips, even if they will be much lower performance both IPC and max clock. Honestly though 16-64 threads is far beyond what I really need even today though.
(Score: 2) by RamiK on Friday February 24 2017, @04:20PM
Or just buy a network card along with a new PC so the packets won't go through the micro-controller.
Of course, that's only secure if everything you're running blob-less FOSS without enabling any DRM features.
compiling...