Subject: Editorial | July 25, 2018 - 09:47 PM | Josh Walrath
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.
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.
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).
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.
Subject: General Tech | July 3, 2018 - 12:50 PM | Jeremy Hellstrom
Tagged: rumour, Polaris, navi, amd
The rumour around the 'net today concerns AMD's new generation of GPUs, the 12nm Polaris 30 update and the 7nm Navi chip. If these rumours are correct, we will see Polaris before the end of the year and it will come with a performance boost of 20% compared to the current Polaris 20 based cards. It will be very interesting to see how they match up to Vega, both in price as well as performance; not to mention how much they narrow the gap between their cards and NVIDIAs. Navi will initially be for mid-range GPU applications, likely to make AMD some good income from next generation consoles and eventually paired with HBM2 to replace Vega on the high end.
"The post notes that Polaris 30 will be manufactured using the 12-nanometre finFET process and will offer a 20 per cent boost in performance over the Polaris 20-based high-end GPUs that debuted in 2017."
Here is some more Tech News from around the web:
- Download Bomb Trick Returns in Chrome -- Also Affects Firefox, Opera, Vivaldi and Brave @ Slashdot
- Guidemaster: Picking the right Thunderbolt 3 or USB-C dock for your desk @ Ars Technica
- Intel is reportedly planning NUC trio with Coffee Lake U-series CPUs @ The Inquirer
- Rowhammer returns, Spectre fix unfixed, Wireguard makes a new friend, and much more @ The Register
- Things Nvidia Needs to Fix @ Techspot
- And that's now all three LTE protocol layers with annoying security flaws @ The Register
Subject: Processors | April 25, 2018 - 09:45 PM | Josh Walrath
Tagged: Zen+, Vega, TSMC, ryzen, Results, Q1 2018, Polaris, GLOBALFOUNDRIES, financials, amd, 7nm, 12nm
Today AMD announced their latest financial results for Q1 2018. We expected it to be a good quarter with their guidance earlier this year, but I doubt many thought it would be as strong as it turned out to be. AMD posted revenue of $1.65 billion with a net income of $81 million. This is up from the expected $1.57 billion that analysts expected from what is typically a slow quarter. This is up 40% from Q1 2017 and its $1.18 billion and up 23% from Q4 2017.
There are multiple reasons behind this revenue growth. The compute and graphics segment lead the way with $1.12B of revenue. The entire year of 2017 AMD had released parts seemingly nonstop since March and the introduction of Ryzen. Q1 continued this trend with the release of the first Ryzen APUs with Vega Graphics introducing the 2000 series. AMD also ramped up production of the newly released Zen+ Ryzen chips and started shipping those out to retailers and partners alike. Initial mobile Ryzen parts were also introduced and shipped with SKUs being also shipped to partners who have yet to announce and release products based on these chips. Finally the strength of the Radeon graphics chips in both gaming and blockchain applications allowed them a tremendous amount of sellthrough throughout 2017 and into 2018. AMD estimates that 10% of the quarter was due to blockchain demand.
Enterprise, Embedded, and Semi-Custom had a revenue of $532 million, which is lower than most analysts expected. Semi-Custom in particular has seen a decline over the past few quarters with the release and saturation of the market of the latest console platforms utilizing AMD designed chips. It appears as though much of the contract is front loaded in terms of revenue with royalties tapering off over time as sales decrease. AMD did have some significant wins, namely providing Intel with Vega based GPUs to be integrated with Intel’s Kaby Lake-G based units. These declines were offset by the shipment of EPYC based processors that are slowly ramping and being shipped to partners to be integrated into server platforms later this year. We have seen a handful of wins from companies like Dell EMC, but AMD is still slowly re-entering the market that they were forced to abandon with their previous, outdated Opteron products. AMD expects to reach mid-single digit marketshare during 2019, but for now they are just getting off the ground with this platform.
The company is not standing still or resting on their laurels after the successful and heralded launch of the latest Ryzen 2000 series chips based on the Zen+ architecture. It is aggressively ramping their mobile chips featuring the Zen/Vega combination and have some 25 product wins being released throughout late spring and summer. Overall partners have some 60 products either shipping or will ship later this year featuring Ryzen based CPUs.
There is some fear that AMD will see its GPU sales throughput be impacted by the recent drop of cryptocurrency value. Several years back with the Bitcoin crash we saw a tremendous amount of secondhand product being sold and GPU revenues for the company tanked. AMD is a bit more optimistic about the upcoming quarter as they expect the current cryptocurrency/blockchain market is much more robust and people will be holding onto these cards to mine other products/workloads rather than drop them on eBay. My thought here is that we will see a rise in cards available on the secondary/used market, but quite a bit might be offset by latent gaming demand that has been held back due the outrageous prices of GPUs over the past year. People that have been waiting for prices to get back to MSRP or below will then buy. This could be further enhanced if memory prices start to drop, providing more affordable DDR4 and flash for SSDs.
The company is also forging ahead with advanced process technology. They have recently received silicon back from TSMC’s 7nm process and it looks to be a Vega based product. The rumor surrounding this is that it will be more of a compute platform initially rather than gaming oriented. Later this year AMD expects to receive new EPYC silicon, but it looks as though this will be from GLOBALFOUNDRIES 7nm process. AMD wants to be flexible in terms of manufacturing, but they have a long history with GLOBALFOUNDRIES when it comes to CPU production. The two companies work closely together to make sure the process and CPU design match up as cleanly as possible to allow products such as Zen to reach market successfully. The GPU arm is obviously more flexible here as they have a history with multiple foundry partners throughout the past two decades.
AMD has set an aggressive, but achievable, timetable of product releases that is initially focusing on the CPU side but would logically be transitioning to the GPU side. Zen+ is out on time and has met with acclaim from consumers and reviewers alike. The latest GPU products are comparable in performance to what NVIDIA has to offer, though they are less power efficient for that level of performance. The “pipecleaner” Vega on 7nm will pave the way towards Navi based products that look to be introduced next year. AMD could possibly refresh Vega on 12nm, but so far there has been no concrete information that such a product exists. They may very well continue to rely on current Polaris and Vega products throughout the rest of this year while focusing on Navi efforts to have a more competitive part come 2019.
Q2 2018 looks to be another successful quarter for AMD. The company’s outlook calls for revenue in the $1.725 billion range, plus or minus $50 million. AMD expects continued growth in all Ryzen product lines and greater throughput of EPYC based products as companies test and release products based on that platform. The GPU market could remain flat, but will most likely decline. That decline will be more than covered by the sell-through of the Ryzen line from top to bottom.
AMD improved their margin by an impressive 4%. Going from 32% to 36% showed the strength and higher ASPs of both CPU and GPU products. AMD expects another 1% increase over the next quarter. While these are good numbers for AMD, they do not match the 58%+ for NVIDIA and Intel when it comes to their margins. AMD certainly has a lot of room for improvement, and a richer product stack will allow them to achieve greater ASPs and see a rise in their overall margins. If EPYC becomes more successful, then we could see another significant improvement in margins for the company.
AMD is getting back to where they belong in terms of product placement, competitiveness, and financial performance. The company has seen a huge improvement year on year and hopes to continue that with a rich product stack that addresses multiple areas of computing. AI and machine learning is ramping up in the company in terms of software support as they feel their CPUs and GPUs are already good enough to handle the workloads. As more money comes in, they can afford to diversify and create a wider product base to compete in more markets. So far Lisa Su has been very, very successful in helping pull AMD from the ashes to the competitive situation that they currently find themselves in.
Subject: Graphics Cards, Processors | April 9, 2018 - 04:25 PM | Ryan Shrout
Tagged: Vega, Polaris, kaby lake-g, Intel, amd
Over the weekend, some interesting information has surfaced surrounding the new Kaby Lake-G hardware from Intel. A product that is officially called the “8th Generation Intel Core Processors with Radeon RX Vega M Graphics” is now looking like it might be more of a Polaris-based GPU than a Vega-based one. This creates an interesting marketing and technology capability discussion for the community, and both Intel and AMD, that is worth diving into.
PCWorld first posted the question this weekend, using some interesting data points as backup that Kaby Lake-G may in fact be based on Polaris. In Gordon’s story he notes that in AIDA64 the GPU is identified as “Polaris 22” while the Raven Ridge-based APUs from AMD show up as “Raven Ridge.” Obviously the device identification of a third party piece of software is a suspect credential in any situation, but the second point provided is more salient: based on the DXDiag information, the GPU on the Hades Canyon NUC powered by Kaby Lake-G does not support DirectX 12.1.
Image source: PCWorld
AMD clearly stated in its launch of the Vega architecture last year that the new GPUs supported DX 12.1, among other features. The fact that the KBL-G part does NOT include support for it is compelling evidence that the GPU might be more similar to Polaris than Vega.
Tom’s Hardware did some more digging that was posted this morning, using a SiSoft Sandra test that can measure performance of FP16 math and FP32. For both the Radeon RX Vega 64 and 56 discrete graphics cards, running the test with FP16 math results in a score that is 65% faster than the FP32 results. With a Polaris-based graphics card, an RX 470, the scores between FP32 and FP16 were identical as the architecture can support FP16 math functions but doesn’t accelerate it with AMD’s “rapid packed math” feature (that was a part of the Vega launch).
Image source: Tom's Hardware
And you guessed it, the Kaby Lake-G part only runs essentially even in the FP16 mode. (Also note that AMD’s Raven Ridge APU that integrated Vega graphics does get accelerated by 61% using FP16.)
What Kaby Lake-G does have that leans toward Vega is support for HBM2 memory (which none of the Polaris cards have) and “high bandwidth memory cache controller and enhanced compute units with additional ROPs” according to the statement from Intel given to Tom’s Hardware.
It should be noted that just because the benchmarks and games that can support rapid packed math don’t take advantage of that capability today, does not mean they won’t have the capability to do so after a driver or firmware update. That being said, if that’s the plan, and even if it’s not, Intel should come out and tell the consumers and media.
The debate and accusations of conspiracy are running rampant again today with this news. Is Intel trying to pull one over on us by telling the community that this is a Vega-based product when it is in fact based on Polaris? Why would AMD allow and promote the Vega branding with a part that it knows didn’t meet the standards it created to be called a Vega architecture solution?
Another interesting thought comes when analyzing this debate with the Ryzen 7 2400G and Ryzen 5 2200G products, both of which claim to use Vega GPUs as a portion of the APU. However, without support for HBM2 or the high-bandwidth cache controller, does that somehow shortchange the branding for it? Or are the memory features of the GPU considered secondary to its design?
This is the very reason why companies hate labels, hate specifications, and hate having all of this tracked by a competent and technical media. Basically every company in the tech industry is guilty of this practice: Intel has 2-3 architectures running as “8th Generation” in the market, AMD is selling RX 500 cards that were once RX 400 cards, and NVIDIA has changed performance capabilities of the MX 150 at least once or twice.
The nature of semi-custom chips designs is that they are custom. Are the GPUs used in the PS4 and Xbox One or Xbox One X called Polaris, Vega, or something else? It would be safer for AMD and its partners to give each new product its own name, its own brand—but then the enthusiasts would want to know what it was most like, and how did it compare to Polaris, or Vega, etc.? It’s also possible that AMD was only willing to sell this product to Intel if it included some of these feature restrictions. In complicated negotiations like this one surely was, anything is feasible.
These are tough choices for companies to make. AMD loves having the Vega branding in more products as it gives weight to the development cost and time it spent on the design. Having Vega associated with more high-end consumer products, including those sold by Intel, give them leverage for other products down the road. From Intel’s vantage point using the Vega brand makes it looks like it has the very latest technology in its new processor and it can benefit from any cross-promotion that occurs around the Vega brand from AMD or its partners.
Unfortunately, it means that the devil is in the details, and the details are something that no one appears to be willing to share. Does it change the performance we saw in our recent Hades Canyon NUC review or our perspective on it as a product? It does not. But as features like Rapid Packed Math or the new geometry shader accelerate in adoption, the capability for Kaby Lake-G to utilize them is going to be scrutinized more heavily.
Subject: Graphics Cards | March 29, 2018 - 05:45 PM | Tim Verry
Tagged: RX 580, RX 570, RX 560, RX 550, Polaris, mining, asrock, amd
ASRock, a company known mostly for its motherboards that was formerly an Asus sub-brand but is now an independent company owned by Pegatron since 2010 is now getting into the graphics card market with a new Phantom Gaming series. At launch, the Phantom Gaming series is comprised of four AMD Polaris-based graphics cards including the Phantom Gaming RX 550 2G and RX 560 2G on the low end and the Phantom Gaming X RX 570 8G OC and RX 580 8G OC on the mid/high end range.
ASRock is using black shrouds with white accents and silver and red logos. The lower end Phantom Gaming cards utilize a single dual ball bearing fan while the Phantom Gaming X cards use a dual fan configuration. ASRock is using copper baseplates paired with aluminum heatsinks and composite heatpipes. The Phantom Gaming RX 550 and RX 560 cards use only PCI-E slot power while the Phantom Gaming X RX 570 and RX 580 cards get power from both the slot and a single 8-pin PCI-E power connector.
Video outputs include one HDMI 2.0, one DisplayPort 1.4, and one DL-DVI-D on the Phantom Gaming parts and one HDMI 2.0, three DisplayPort 1.4, and one DL-DVI-D on the higher-end Phantom Gaming X graphics cards. All of the graphics card models feature both silent and overclocked modes in addition to their out-of-the-box default clocks depending on whether you value performance or noise. Users can select which mode they want or perform a custom overclock or fan curve using ASRock's Phantom Gaming Tweak utility.
On the performance front, out of the box ASRock is slightly overclocking the Phantom Gaming X OC cards (the RX 570 and RX 580 based ones) and slightly underclocking the lower end Phantom Gaming cards (including the memory which is downclocked to 6 GHz) compared to their AMD reference specifications.
|ASRock RX 580 OC||RX 580||ASRock RX 570 OC||RX 570||ASRock RX 560||RX 560||ASRock RX 550||RX 550|
|GPU Clock (MHz)||1380||1340||1280||1244||1149||1275||1100||1183|
|GPU Clock OC Mode (MHz)||1435||-||1331||-||1194||-||1144||-|
|Memory Clock (GHz)||8GHz||8GHz||7GHz||7GHz||6GHz||7GHz||6GHz||7GHz|
|Memory Clock OC Mode (MHz)||8320||-||7280||-||6240||-||6240||-|
The table above shows the comparisons between the ASRock graphics cards and their AMD reference card counterparts. Note that the Phantom Gaming RX 560 2G is based on the cut-down 14 CU (compute unit) model rather than the launch 16 CU GPU. Also, even in OC Mode, ASRock does not bring the memory up to the 7 GT/s reference spec. On the positive side, turning on OC mode does give a decent factory overclock of the GPU over reference. Also nice to see is that on the higher end "OC Certified" Phantom Gaming X cards, ASRock overclocks both the GPU and memory speeds which is often not the case with factory overclocks.
ASRock did not detail pricing with any of the launch announcement cards, but they should be coming soon with 4GB models of the RX 560 an RX 550 to follow later this year.
It is always nice to have more competition in this space and hopefully a new AIB partner for AMD helps alleviate shortages and demand for gaming cards if only by a bit. I am curious how well the cards will perform as while they look good on paper the company is new to graphics cards and the build quality really needs to be there. I am just hoping that the Phantom Gaming moniker is not an allusion to how hard these cards are going to be to find for gaming! (heh) If the rumored Ethereum ASICs do not kill the demand for AMD GPUs I do expect that ASRock will also be releasing mining specific cards as well at some point.
What are your thoughts on the news of ASRock moving into graphics cards?
Beating AMD and Analyst Estimates
January 30th has rolled around and AMD released their Q4 2017 results. The results were positive and somewhat unexpected. I have been curious how the company fared and was waiting for these results to compare them to the relatively strong quarter that Intel experienced. At the Q3 earnings AMD was not entirely bullish about how Q4 would go. The knew that it was going to be a down quarter as compared to an unexpectedly strong third quarter, but they were unsure how that was going to pan out. The primary reason that Q4 was not going to be as strong was due to the known royalty income that AMD was expecting from their Semi-Custom Group. Q4 has traditionally been bad for that group as all of their buildup for the holiday season came from Q1 and Q2 rampings of the physical products that would be integrated into consoles.
The results exceeded AMD’s and analysts’ expectations. They were expecting in the $1.39B range, but their actual revenue came in at a relatively strong $1.48B. Not only was the quarter stronger than expected, but AMD was able to pull out another positive net income of $61M. It has been a while since AMD was able to post back to back profitable quarters. This allowed AMD to have a net positive year to the tune of $43M where in 2016 AMD had a loss of $497M. 2017 as a whole was $1.06B more in revenue over 2016. AMD has been historically lean in terms of expenses for the past few years, and a massive boost in revenue has allowed them to invest in R&D as well as more aggressively ramp up their money making products to compete more adequately with Intel, who is having their own set of issues right now with manufacturing and security.
Subject: Mobile | January 8, 2018 - 04:46 PM | Tim Verry
Tagged: CES, CES 2018, acer, nitro 5, ryzen mobile, RX 560, Polaris, amd
Acer is showing off a new 15.6" gaming laptop at CES using both AMD's Ryzen Mobile processors and RX 560 discrete graphics cards. The Acer Nitro 5 is a stylized gaming notebook aimed at mainstream and casual gamers that are looking for a mobile platform for LAN parties and portable PC gaming.
The laser etched top cover and stylish chassis holds a large 15.6" 1080p display and webcam up top and a full backlit keyboard and trackpad on the bottom half. A large crimson red hinge accents the slate gray and black angular body. There is support for USB 3.1 with three USB Type-A ports and one USB Type-C, one headset jack, one HDMI output, one SD card reader, and one Gigabit Ethernet jack. Audio is handled by Dobly Audio Premium and Acer TrueHarmony powered speakers. There is a numpad and the trackpad appears fairly large, but the arrow keys are somewhat squished between the standard keys and the numpad. The WASD keys can be outlined with brighter backlighting and CPU and GPU temps can be monitored with NitroSense software though, so there's that (heh).
Acer did not provide exact specifications, but the Nitro 5 will be able to be configured with Zen-based Ryzen Mobile processors and Polaris-based AMD RX 560 graphics. It is not clear which specific Ryzen Mobile chips Acer will use or if the Vega-based onboard GPU will be able to be used with the discrete graphics active (perhaps in DX 12 games). The AMD chips are paired with up to 32 GB of DDR4 RAM and 512GB of PCI-E based SSD storage. In addition to the wired networking, the Nitro 5 also has dual stream 802.11ac Wi-Fi.
The AMD-powered Acer Nitro 5 will be available in North America in April starting at $799. EMEA (countries in Europe, the Middle East, and Africa) availability is also slated for April starting at €1,099. It is nice to see AMD getting some design wins with Ryzen Mobile, though discrete mobile Vega would be a nice thing to see happen sooner than later.
The Expected Unexpected
Last night we first received word that Raja had resigned from AMD (during a sabbatical) after they had launched Vega. The initial statement was that Raja would come back to resume his position at AMD in a December/January timeframe. During this time there was some doubt as to if Raja would in fact come back to AMD, as “sabbaticals” in the tech world would often lead the individual to take stock of their situation and move on to what they would consider to be greener pastures.
Raja has dropped by the PCPer offices in the past.
Initially it was thought that Raja would take the time off and then eventually jump to another company and tackle the issues there. This behavior is quite common in Silicon Valley and Raja is no stranger to this. Raja cut his teeth on 3D graphics at S3, but in 2001 he moved to ATI. While there he worked on a variety of programs including the original Radeon, the industry changing Radeon 9700 series, and finishing up with the strong HD 4000 series of parts. During this time ATI was acquired by AMD and he became one of the top graphics guru at that company. In 2009 he quit AMD and moved on to Apple. He was Director of Graphics Architecture at Apple, but little is known about what he actually did. During that time Apple utilized AMD GPUs and licensed Imagination Technologies graphics technology. Apple could have been working on developing their own architecture at this point, which has recently showed up in the latest iPhone products.
In 2013 Raja rejoined AMD and became a corporate VP of Visual Computing, but in 2015 he was promoted to leading the Radeon Technology Group after Lisu Su became CEO of the company. While there Raja worked to get AMD back on an even footing under pretty strained conditions. AMD had not had the greatest of years and had seen their primary moneymakers start taking on water. AMD had competitive graphics for the most part, and the Radeon technology integrated into AMD’s APUs truly was class leading. On the discrete side AMD was able to compare favorably to NVIDIA with the HD 7000 and later R9 200 series of cards. After NVIDIA released their Maxwell based chips, AMD had a hard time keeping up. The general consensus here is that the RTG group saw its headcount decreased by the company-wide cuts as well as a decrease in R&D funds.
Subject: Processors | November 6, 2017 - 02:00 PM | Josh Walrath
Tagged: radeon, Polaris, mobile, kaby lake, interposer, Intel, HBM2, gaming, EMIB, apple, amd, 8th generation core
In what is probably considered one of the worst kept secrets in the industry, Intel has announced a new CPU line for the mobile market that integrates AMD’s Radeon graphics. For the past year or so rumors of such a partnership were freely flowing, but now we finally get confirmation as to how this will be implemented and marketed.
Intel’s record on designing GPUs has been rather pedestrian. While they have kept up with the competition, a slew of small issues and incompatibilities have plagued each generation. Performance is also an issue when trying to compete with AMD’s APUs as well as discrete mobile graphics offerings from both AMD and NVIDIA. Software and driver support is another area where Intel has been unable to compete due largely to economics and the competitions’ decades of experience in this area.
There are many significant issues that have been solved in one fell swoop. Intel has partnered with AMD’s Semi-Custom Group to develop a modern and competent GPU that can be closely connected to the Intel CPU all the while utilizing HBM2 memory to improve overall performance. The packaging of this product utilizes Intel’s EMIB (Embedded Multi-die Interconnect Bridge) tech.
EMIB is an interposer-like technology that integrates silicon bridges into the PCB instead of relying upon a large interposer. This allows a bit more flexibility in layout of the chips as well as lowers the Z height of the package as there is not a large interposer sitting between the chips and the PCB. Just as interposer technology allows the use of chips from different process technologies to work seamlessly together, EMIB provides that same flexibility.
The GPU looks to be based on the Polaris architecture which is a slight step back from AMD’s cutting edge Vega architecture. Polaris does not implement the Infinity Fabric component that Vega does. It is more conventional in terms of data communication. It is a step beyond what AMD has provided for Sony and Microsoft, who each utilize a semi-custom design for the latest console chips. AMD is able to integrate the HBM2 controller that is featured in Vega. Using HBM2 provides a tremendous amount of bandwidth along with power savings as compared to traditional GDDR-5 memory modules. It also saves dramatically on PCB space allowing for smaller form factors.
EMIB provides nearly all of the advantages of the interposer while keeping the optimal z-height of the standard PCB substrate.
Intel did have to do quite a bit of extra work on the power side of the equation. AMD utilizes their latest Infinity Fabric for fine grained power control in their upcoming Raven Ridge based Ryzen APUs. Intel had to modify their current hardware to be able to do much the same work with 3rd party silicon. This is no easy task as the CPU needs to monitor and continually adjust for GPU usage in a variety of scenarios. This type of work takes time and a lot of testing to fine tune as well as the inevitable hardware revisions to get thing to work correctly. This then needs to be balanced by the GPU driver stack which also tends to take control of power usage in mobile scenarios.
This combination of EMIB, Intel Kaby Lake CPU, HBM2, and a current AMD GPU make this a very interesting combination for the mobile and small form factor markets. The EMIB form factor provides very fast interconnect speeds and a smaller footprint due to the integration of HBM2 memory. The mature AMD Radeon software stack for both Windows and macOS environments provides Intel with another feature in which to sell their parts in areas where previously they were not considered. The 8th Gen Kaby Lake CPU provides the very latest CPU design on the new 14nm++ process for greater performance and better power efficiency.
This is one of those rare instances where such cooperation between intense rivals actually improves the situation for both. AMD gets a financial shot in the arm by signing a large and important customer for their Semi-Custom division. The royalty income from this partnership should be more consistent as compared to the console manufacturers due to the seasonality of the console product. This will have a very material effect on AMD’s bottom line for years to come. Intel gets a solid silicon solution with higher performance than they can offer, as well as aforementioned mature software stack for multiple OS. Finally throw in the HBM2 memory support for better power efficiency and a smaller form factor, and it is a clear win for all parties involved.
The PCB savings plus faster interconnects will allow these chips to power smaller form factors with better performance and battery life.
One of the unknowns here is what process node the GPU portion will be manufactured on. We do not know which foundry Intel will use, or if they will stay in-house. Currently TSMC manufactures the latest console SoCs while GLOBALFOUNDRIES handles the latest GPUS from AMD. Initially one would expect Intel to build the GPU in house, but the current rumor is that AMD will work to produce the chips with one of their traditional foundry partners. Once the chip is manufactured then it is sent to Intel to be integrated into their product.
Apple is one of the obvious candidates for this particular form factor and combination of parts. Apple has a long history with Intel on the CPU side and AMD on the GPU side. This product provides all of the solutions Apple needs to manufacture high performance products in smaller form factors. Gaming laptops also get a boost from such a combination that will offer relatively high performance with minimal power increases as well as the smaller form factor.
The potential (leaked) performance of the 8th Gen Intel CPU with Radeon Graphics.
The data above could very well be wrong about the potential performance of this combination. What we see is pretty compelling though. The Intel/AMD product performs like a higher end CPU with discrete GPU combo. It is faster than a NVIDIA GTX 1050 Ti and trails the GTX 1060. It also is significantly faster than a desktop AMD RX 560 part. We can also see that it is going to be much faster than the flagship 15 watt TDP AMD Ryzen 7 2700U. We do not yet know how it compares to the rumored 65 watt TDP Raven Ridge based APUs from AMD that will likely be released next year. What will be fascinating here is how much power the new Intel combination will draw as compared to the discrete solutions utilizing NVIDIA graphics.
To reiterate, this is Intel as a customer for AMD’s Semi-Custom group rather than a licensing agreement between the two companies. They are working hand in hand in developing this solution and then both profiting from it. AMD getting royalties from every Intel package sold that features this technology will have a very positive effect on earnings. Intel gets a cutting edge and competent graphics solution along with the improved software and driver support such a package includes.
Update: We have been informed that AMD is producing the chips and selling them directly to Intel for integration into these new SKUs. There are no royalties or licensing, but the Semi-Custom division should still receive the revenue for these specialized products made only for Intel.
There has been a lot of news lately about the release of Cryptocurrency-specific graphics cards from both NVIDIA and AMD add-in board partners. While we covered the currently cryptomining phenomenon in an earlier article, today we are taking a look at one of these cards geared towards miners.
It's worth noting that I purchased this card myself from Newegg, and neither AMD or Sapphire are involved in this article. I saw this card pop up on Newegg a few days ago, and my curiosity got the best of me.
There has been a lot of speculation, and little official information from vendors about what these mining cards will actually entail.
From the outward appearance, it is virtually impossible to distinguish this "new" RX 470 from the previous Sapphire Nitro+ RX 470, besides the lack of additional display outputs beyond the DVI connection. Even the branding and labels on the card identify it as a Nitro+ RX 470.
In order to test the hashing rates of this GPU, we are using Claymore's Dual Miner Version 9.6 (mining Ethereum only) against a reference design RX 470, also from Sapphire.
On the reference RX 470 out of the box, we hit rates of about 21.8 MH/s while mining Ethereum.
Once we moved to the Sapphire mining card, we move up to at least 24 MH/s from the start.