AMD Announces Q2 2018 Results

Subject: Editorial | July 25, 2018 - 09:47 PM |
Tagged: Vega, ryzen, Q2 2018, Polaris, Intel, EPYC, amd, 7nm, 12nm

Today AMD has released their Q2 results for 2018 and they have fallen in line with previous estimates. The company reported revenue of $1.76B, up $110M from last quarter’s $1.65B. Their net income is $116M which is again up significantly from last quarter’s $81M. These results dwarf Q2 2017’s $1.15B in revenue and a loss of $42M. AMD has shown steady and solid growth since the release of the Ryzen processors and their continuing evolution of the RX series of graphics cards.

View Full Size

The computing group which includes CPUs and GPUs showed a small drop in revenue due to multiple factors. CPU ASPs are steadily dropping for AMD since the original introduction of the Ryzen processors. The top end R7 1800X was introduced at $499 and has slowly dropped in price as the year wore on. This year AMD released the successor to the 1800X in the R7 2700X, but it was released at a $329 price point. We can see that the pricing mix of these CPUs is not as rich as they were on Ryzen’s initial release. The play here seems to be AMD improving efficiency of production as well as a willingness to sacrifice ASPs to gain any kind of marketshare.

GPUs have suffered as well due to the drop off in mining based purchases due to cryptocurrency dropping in value as well as the continued introduction of specialized ASICs performing better in those particular workloads. AMD claims a fairly palatable drop of only around 4% in sales due to the decrease in mining demand. It is likely that partners are feeling more of a pinch in this instance as the selling prices of these cards are finally reaching introductory MSRP levels as well as seeing reasonable availability. We do not know the specifics of AMD’s GPU sales to partners, but it seems like that price has been stable since introduction with the partners and resellers profiting to a greater degree than AMD.

The bright spot for this quarter was that of Enterprise and Semi-Custom. AMD switched around accounting on how it handles Semi-Custom so that accounted for some of the positive gains this quarter saw. AMD also started its collaboration with the Chinese for their own version of a Zen CPU. AMD continues to provide console makers with SoCs in two of the three major product lines out there. AMD is also likely currently contracted by both Sony and Microsoft for the next generation of consoles which will be released in the next two years, though none of the parties involved in such speculation has verified that information. I have a hard time considering that both Sony and Microsoft would abandon what has been a very beneficial partnership to create cutting edge products for their marketplace.

View Full Size

The Enterprise group has also seen sales increase on the EPYC processors. EPYC was released last year, but it was not until this year that actual sales occured. While AMD did not provide specific numbers or guidance here, reading between the lines it looks as if EPYC is starting to gain traction and is shipping in more significant numbers. AMD was very careful in talking about this, as EPYC still has a long ways to go before it can claim to have gained significant marketshare. Lisa Su mentioned earlier that the real ramp for EPYC should occur in 2H 2018. This makes quite a bit of sense as the hardware and software environment for enterprise level products is tremendously different from when AMD was last competitive there. Validation of parts and platforms takes more time, and there are more complex software components involved that have to be updated to work effectively and efficiently on the new Zen architecture and EPYC chips. In the year since EPYC was launched a lot of work has been going on in the background by AMD, their hardware partners, and the software vendors to make sure that when EPYC hits volume production that most of the kinks will be worked out and it is truly enterprise production ready. This isn’t wishful thinking or excuse making. This is simply how a modern enterprise platform evolves and why product cycles are elongated as compared to what we see on the desktop and mobile spaces.

Guidance for next quarter will be disappointing for some investors and readers. AMD claims it will be flat between Q2 and Q3. This is not entirely surprising. Gaining desktop CPU marketshare has not been a slam dunk for AMD with Ryzen. The product stack has made it competitive with Intel and its offerings, and has in fact provided excellent value in terms of IPC and core count. Ryzen is not an Athlon 64. Ryzen was merely competitive with what Intel currently offers as compared to Athlon 64, which was head and shoulders more advanced than what Intel offered at the time with the Pentium 4. AMD is finding advances in marketshare in both desktop and mobile to be slow, but steady. Each quarter since Ryzen was released and the mobile parts being introduced earlier this year, the results have been trending in a positive direction even though ASPs on desktop parts have dropped (though mobile ASPs have increased).

View Full Size

AMD obviously does not expect big gains this next quarter, and are in fact a little behind the ball when it comes to graphics. NVIDIA is poised to release a new generation of products within the next few months addressing the upper midrange and high end offerings that will erode AMD’s effectiveness with their Vega parts. So while EPYC products will increase in sales, AMD looks like it will be shipping fewer GPUs, at least in the high end. We probably will see Polaris based products have price drops applied to them to keep the meat of the market satisfied with AMD product, but do not expect next generation desktop graphics from AMD until 2019.

This was a productive and solid quarter for AMD. It is hard to argue against that. Their financial house is in far greater order and a solid revenue stream heading towards the company. They are keeping costs under control while aggressively pursuing the markets they have a strong history in. They have continued to leverage their IP with the Semi-Custom group and that provides a steady income from both historical partners and new ones. AMD is not seeing a breakaway quarter or year, but they are building a much more solid foundation and executing on their primary markets while competing effectively with Intel. This is certainly not 2003/2004, but it is a new chapter for AMD as they continue to provide new and interesting products to a market that continues to expand.

 

Source: AMD

July 25, 2018 | 11:30 PM - Posted by MoreSteadyGrowthFromThispointOnForEpycAndProfessionalGPU (not verified)

Epyc and Radeon Pro WX/Instinct are the sales that are most helping move AMD's gross margins increase up to 37%. And Watch those Epyc system sales paired with Vega 20 based Radeon Instinct sales as that becomes a larger share of AMD's total revenues relative to any consumer Ryzen or Gaming GPU sales.

AMD no longer has to worry about any volitility in the consumer/Mining GPU markets as Epyc/Radeon Pro WX/Instinct GPU compute/AI sales will more than make up for any consumer related CPU/GPU non stable revenue swings and low markups/margins. Epyc and Radeon Pro compute/AI revenues are going to continue to increase and that's even before Zen2 based Epyc/Rome at 7nm is to market.

Consumer GPUs and CPUs are where AMD's gross margins are not being helped due to consumer market demand/pricing while the Epyc/Radeon Pro WX/Instinct markups are much higher to more than offset any of those consumer market margin declines. AMD is such a lean operation that profits can be had with gross margins in the 33-37% range while Intel would begin to suffer greatly if its gross margins slipped into the 55%-Below percentage point range.

Watch the Epyc/Radeon Pro WX/Instinct sales over the next 3 quarters begin to become a much larger prencentage of AMD's total revenues, enough so at to outweigh any price fluctions in consumer CPU/GPU market. And AMD's share value will continue to rise because Epyc/Radeon Pro WX/Instinct sales are the future for AMD's overall success.

Just remember that Nvidia's GP100 and GP102 sales are mostly covered by Professional revenues and that IP that is paid for by theose Tasla and Quardo high margins are why Nvidia has the funds to create the GP104, GP106, and GP108 SKUs that are tailored towards gaming only. So once AMD gets the professional GPU compute/AI revenue stream paying for the majority of its GPU R&D then AMD can also afford more of a gaming foucsed GPU line of SKUs, ditto for Epyc and its revenue streams paying for CPU R&D to benifit AMD's consumer market CPU offerings.

It takes many millions/billions for Nvidia to afford those 5 different base GPU die tapeouts but Nvidia's professional GPU sales cover most of that cost. So AMD will be getting more R&D paid for by its professional compute/AI GPU revenues along with Epic CPU sales, and Nvidia can not make the kinds of CPU revenues that AMD will be making with Epyc.

AMD's Enterprise Epyc/Radeon WX/Instinct Compute/AI products will more than offset any Consumer/Gaming GPU price declines or fluxuations going forward owing to those large margins/markups that the professional SKUs command retaltive to any consumer markups that are nowhere near as large. AMD's consumer CPU ASPs should be stabilizing more as the first generation Ryzen products are replaced by 2nd generation sales once the first generation Ryzen inventories dry up. AMD Ryzen Pro Line of business oriented Desktop/Mobile CPUs/APUs also have a higher ASP compared to the consumer oriented Ryzen Desktop/Mobile CPUs/APUs.

Embedded and semi-custom pretty much goes along for the ride along with Enterprise and that Embedded/Semi-Custom part is up and down depending on console sales and other embedded devices like Medical/Slot-Machine/Display/Industral/Etc. So that's more dependent on cyclical Console generational sales to some degree.

July 26, 2018 | 04:49 PM - Posted by pdjblum

thanks for posting a far more insightful view of amd's prospects

i don't think josh gets it at all

i hope he takes the time to read and consider your post

July 26, 2018 | 04:59 PM - Posted by Josh Walrath

What are NVIDIA's margins on their products and then compare them to AMD's? AMD sells both high performance GPUs and CPUs. In theory, one would expect them to see revenues greater than NVIDIA, because that company only has high performance GPUs.  NVIDIA certainly has a different philosophy on how they design, market, and sell their chips.  Is it superior?  Well, they certainly can better diversify their products due to a larger R&D budget than what AMD gives their GPU folks.  Can that more adequately tailor those chips for certain markets?  Absolutely.

If you could be a little bit more clear on what exactly I got wrong with my 10 paragraph analysis, please let me know. Do you think I am not bullish enough on AMD's prospects? Because looking at Intel's latest quarter, we can sorta see that AMD may have actually underperformed in terms of how much the market actually grew YoY and QoQ.

July 26, 2018 | 07:12 PM - Posted by pdjblum

josh, intel is well ensconced in the enterprise market while amd is breaking back in

amd has a huge hurtle to surmount to gain share in that market, and it is going to take some time

the growth in that market will accelerate now that they have the products, the infrastructure, and an incredible roadmap, which they did not have with opteron

yeah, i think you are comparing apples to oranges and you are being unjustly harsh on amd's performance to date

i love you and you do a great job, but i have to completely disagree with your analysis

July 26, 2018 | 09:01 PM - Posted by Josh Walrath

I re-read what I wrote, and I don't really see anything that disagrees with what you have above. I agree that they have an aggressive roadmap for EPYC and they have the potential to really hit their stride in the 9 to 11 month window that Intel is leaving open to achieve a density/performance advantage over Xeon. Though I didn't touch on what the outlook for 2019 was, but rather spoke about guidance for the next quarter.

Data center is growing, as evidenced by Intel's results. I think I mentioned on Twitter that we would find out more today about the market in general. AMD has grown their shipments and is well placed to continue to do that. I am actually somewhat surprised that all markets have grown, but I believe Intel has taken the majority of the share. Once 7nm starts shipping and if AMD can keep on the gas, then we can realistically see AMD start taking marketshare away from Intel at a greater rate. But they have to execute, as Intel is working hard to shut down the opportunity AMD has in 2019.

For the rest of this year Intel still has advantages over AMD, and Q2 results have shown this. Guidance for Q3 remains flat for AMD while Intel is pretty bullish and expects to make an astounding $69B in revenue this year. I do believe if TSMC is able to deliver the wafer starts, as well as GLOBALFOUNDRIES, then AMD has a chance to have a better product than Intel across the board in 2019.

I do appreciate criticism and I don't take it personally. 

July 30, 2018 | 12:10 PM - Posted by TheQuantsAreCrunchingTheNumbers (not verified)

A good part of 2019 will be first generation Epyc products that have already gone through the lengthy server vetting/certification process. So Epyc/Rome will probably not be factoring in until that last quarter of 2019. So it's all the first generation Epyc market growth that will figure in and the Epyc MB Platform, in addition to the Epyc core count, is what is giving AMD an advantage in the majority(1P and 2P Systems) part of the server market that makes use of mostly 1P and 2P server SKUs. The Epyc platforms non-segemented offerings of 128 PCIe 3.0 lanes on both 1P and 2P platforms and 8/16 1P/2P memory channels are also what's making Epyc the better choice relative to what Intel is offering on its 1P and 2P Xeon platform offerings.

So that Price/Features figures into the overall Price/Performance metrics that have made many of the big 8 server makers begin choosing to offer Epyc options. The First Generation 14nm Zen/Epyc Platform for 1P and 2P servers are already better overall on that price/performance and price/feature metrics. If you are financing your servers via loans then that initial up front hardware cost being lower for the Epyc SKUs for that level of performance/features makes the amortized loan costs lower and that figures in to the TCO figures along with power usage and other figures.

AMD made a wise choice to Keep Epyc's AVX untis smaller to save on power becuse the majority of server related workloads do not require heavy FP, and AMD can offer FP via it's Radeon Pro WX/Instinct GPU accelerators to those that need AI/FP number crunching. And Radeon Instinct/WX SKUs will be available on 7nm shortly and are also being sampled. So that's Vega 20 on 7nm and more AI/FP performance with Vega 20 getting more AI related ISA extentions relative to Vega 10. I can see AMD probably making a dual Vega 20 Die on a single PCIe card variant to get more Compute/AI into less cabinet space for any newer inferencing systems starting in late 2018 into 2019.

Intel's is a good few years off from competing with Nvidia and AMD for that high performance GPU Compute/AI market. It's not just Zen/Epyc sales but that new AI market growth potential that has AMD is in a position to capture market share and Intel has not entered that GPU accelerator market and will not be ready until probably 2020 and any new Intel GPU product will have to undergo vetting/certification whereas Nvidia and AMD will be mostly already certified/Vetted ownig to their GPUs already being used.

AMD has re-entered the server CPU market with Epyc and is ahead of Intel for GPU compute and AMD can package price both CPUs and GPUs for compute/AI something that Nvidia and Intel can not currently offer because Nvidia lacks any x86 offerings and Intel is a few years off from even sampling any GPU accelerator products that will have to undergo long term vetting/certification before the Server/HPC market will accept and Intel GPU SKUs for production workloads.

July 25, 2018 | 11:53 PM - Posted by Paul A. Mitchell (not verified)

Josh, excellent analysis: many thanks!

July 26, 2018 | 06:39 AM - Posted by Cooe (not verified)

Umm... The launch price of the 2700X was $330... If you can't even get that right...

July 26, 2018 | 11:00 AM - Posted by Josh Walrath

It was corrected. Thanks for the head's up. Does the $30 difference change the point of that paragraph though?

July 26, 2018 | 11:10 AM - Posted by Isaac Johnson

Nope, one typo invalidates everything you've ever written, rules of the internet. You've officially been disgraced by the council of elders. Go now in shame.

July 26, 2018 | 11:13 AM - Posted by Josh Walrath

So it is written, so it shall be.

July 26, 2018 | 03:24 PM - Posted by Cooe (not verified)

No, just illustates how out of touch you & you're information is (as well as much of your analysis).

Sad really; PCPer is normally high quality content, but this, that was not.

July 26, 2018 | 03:34 PM - Posted by Josh Walrath

Thank you for your critique.

July 26, 2018 | 01:40 PM - Posted by Irbosnind (not verified)

Nah, pcper.com is much better.

Post new comment

The content of this field is kept private and will not be shown publicly.
  • Lines and paragraphs break automatically.
  • Allowed HTML tags: <a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd> <blockquote><p><br>
  • Web page addresses and e-mail addresses turn into links automatically.

More information about formatting options

CAPTCHA
This question is for testing whether you are a human visitor and to prevent automated spam submissions.