AMD goes after $15B embedded space with two new embedded processors

Subject: Processors | February 21, 2018 - 11:22 AM |
Tagged: amd, ryzen, EPYC, embedded, ryzen v1000, epyc 3000

Continuing its expansion of bringing modern processor and graphics designs to as many of its targeted market segments as possible, AMD announced today two new families that address the embedded processor space. The company has already seen double-digital YoY sequential growth in revenue from embedded markets, but the release of the Epyc Embedded 3000 and Ryzen Embedded V1000 family create significant additional opportunity for the company.

amdembed1.png

Embedded markets are unique from traditional consumer and enterprise channels as they address areas from military and aerospace applications to networking hardware and storage devices to retail compute and even casino and arcade gaming. These markets tend to be consistent and stable without the frequent or dramatic swings in architectural preference or market share that we often witness in consumer PCs. As AMD continues to grow and look for stable sources of adjacent income, embedded processors are a critical avenue and one that I believe AMD has distinct advantages in.

amdembed2.png

Research firm IDC estimates the market size that AMD can address with this pair of chip families exceeds $14-15B annually. The largest portion of that ($11-12B) includes storage and networking infrastructure systems that the Epyc 3000 line will target. The remaining amount includes IoT gateways, medical systems, and casino gaming hardware and is the purview of the Ryzen V1000.

Competitors in this space include Intel (with its Xeon D-series and Core family of chips) and many Arm-based designs that focus on low power integration. Intel has the most potential for immediate negative impact with AMD’s expansion in the embedded markets as the shared architecture and compatibility mean customers can more easily move between platforms. AMD is positioning both parts directly against Intel with proposed advantages in value and performance, hoping to move embedded customers to the combined AMD solution.

amdembed5.png

The Ryzen V1000 family combines the company’s recent processor and graphics architectures on a single chip, similar in function to the consumer Ryzen design that was released for notebook and desktop PCs. For the embedded customers and devices being targeted, this marks a completely new class of product with two key benefits over competing solutions. First, it allows for smaller and cooler system designs (critical for the cramped working environments of the embedded space) while increasing maximum performance.

amdembed6.png

Second, the V1000 allows integrators to downscale from using a combination of an Intel processor and a separate, discrete graphics chip to a single chip design. This both raises the ASP (average selling price) for AMD, increasing revenue and potential margin, while lowering the price that customers pay in total for system components.

While AMD struggles to find ways to promote the value of higher performance graphics on its new processors, where it has a significant advantage over Intel, for the consumer and business space, in the embedded markets that additional performance value is well understood. Casino gaming often utilizes multiple high-resolution displays for a single device with demand for high-quality rendered 3D graphics, of which the V1000 can now provide in a single chip design. The same is seen with medical imaging hardware, including ultrasound machines for women’s healthcare and cardiovascular diagnostics.

amdembed3.png

The Epyc Embedded 3000 family does not include integrated graphics on-chip and instead offers higher core performance and performance per dollar compared to competing Intel solutions. AMD believes that the Epyc 3000 will double the total addressable market for the company when it comes to networking and storage infrastructure.

amdembed4.png

AMD previously has disclosed its partnership with Cisco that included AMD-built processor options for some families of switches and other networking gear. As the demand for edge computing grows (systems that will exist near the consumer or enterprise side of a network to aid in computational needs of high speed networks), AMD is offering a compelling solution to counter the Intel Xeon family of processors.

Both the Epyc 3000 and Ryzen V1000 chips represent the first time AMD has targeted embedded customers with specific features and capabilities at the hardware level. During the design phase of its Zen CPU and Vega graphics architecture, business unit leaders included capabilities like multiple 10-gigabit network integration, support of four 4K display outputs, ECC memory (error correction capability for mission-critical applications), and unique embedded-based interfaces for external connectivity.

While these were not needed for the consumer segments of the market, and weren’t exposed in those hardware launches, they provide crucial benefits for AMD customers when selecting a chip for embedded markets.

Source: AMD

AMD EPYC "Rome" Rumors: 7nm, 64 Cores, 2 Designs

Subject: Processors | February 19, 2018 - 08:33 PM |
Tagged: amd, Zen, Zen 2

WCCFTech found some rumors (scroll down near the bottom of the linked article) about AMD’s upcoming EPYC “Rome” generation of EPYC server processors. The main point is that users will be able to buy up to 64 cores (128 threads) on a single packaged processor. This increase in core count will likely be due to the process node shrink, from 14nm down to GlobalFoundries’ 7nm. This is not the same as the upcoming second-generation Zen processors, which are built on 12nm and expected to ship in a few months.

Rome is probably not coming until 2019.

amd-2016-zen-video.png

But when it does… up to 128 threads. Also, if I’m understanding WCCFTech’s post correctly, AMD will produce two different dies for this product line. One design will have 12 cores per die (x4 for 48 cores per package) and the other will have 16 cores per die (x4 for 64 cores per package). The reason why this is interesting is because AMD is, apparently, expecting to sell enough volume to warrant multiple chip designs, rather than just making a flagship and filling in SKUs with bin sorting and cutting off the cores that require abnormally high voltage for a given clock rate as parts with lesser core count. (That will happen too, as usual, but from two different intended designs instead of just the flagship.)

If it works out as AMD plans, this could be an opportunity to acquire prime market share away from Intel and their Xeon processors. The second chip might let them get into second-tier servers with an even more cost-efficient part, because a 12-core die will bin better than a 16-core one and, as mentioned, yield more from a wafer anyway.

Again, this is a common practice from a technical standpoint; the interesting part is that it could work out well for AMD from a strategic perspective. The timing and market might be right for EPYC in various classes of high-end servers.

Source: WCCFTech
Author:
Manufacturer: AMD

Memory Matters

Memory speed is not a factor that the average gamer thinks about when building their PC. For the most part, memory performance hasn't had much of an effect on modern processors running high-speed memory such as DDR3 and DDR4.

With the launch of AMD's Ryzen processors, last year emerged a platform that was more sensitive to memory speeds. By running Ryzen processors with higher frequency and lower latency memory, users should see significant performance improvements, especially in 1080p gaming scenarios.

However, the Ryzen processors are not the only ones to exhibit this behavior.

Gaming on integrated GPUs is a perfect example of a memory starved situation. Take for instance the new AMD Ryzen 5 2400G and it's Vega-based GPU cores. In a full Vega 56 or 64 situation, these Vega cores utilize blazingly fast HBM 2.0 memory. However, due to constraints such as die space and cost, this processor does not integrate HBM.

DSC04643.JPG

Instead, both the CPU portion and the graphics portion of the APU must both depend on the same pool of DDR4 system memory. DDR4 is significantly slower than memory traditionally found on graphics cards such as GDDR5 or HBM. As a result, APU performance is usually memory limited to some extent.

In the past, we've done memory speed testing with AMD's older APUs, however with the launch of the new Ryzen and Vega based R3 2200G and R5 2400G, we decided to take another look at this topic.

For our testing, we are running the Ryzen 5 2400G at three different memory speeds, 2400 MHz, 2933 MHz, and 3200 MHz. While the maximum supported JEDEC memory standard for the R5 2400G is 2933, the memory provided by AMD for our processor review will support overclocking to 3200MHz just fine.

Continue reading our look at memory speed scaling with the Ryzen 5 2400G!

Raven Ridge Delidded: der8auer Posts AMD Ryzen 5 2400G Before and After Video

Subject: Processors | February 16, 2018 - 08:52 AM |
Tagged: tim, thermal paste, Ryzen 5 2400G, ryzen, overclocking, der8aur, delidding, APU, amd

Overclocker der8auer has posted a video demonstrating the delidding process of the AMD Ryzen 5 2400G, and his findings on its effect on temperatures and overclocking headroom.

Delidded.png

The delidded Ryzen 5 2400G (image credit der8auer via YouTube)

The full video is embedded below:

The results are interesting, but disappointing from an overclocking standpoint, as he was only able to increase his highest frequency by 25 MHz. Thermals were far more impressive, as the liquid metal used in place of the factory TIM did lower temps considerably.

Here are his temperature results for both the stock and overclocked R5 2400G:

Stock Temps.png

OC Temps.png

The process was actually quite straightforward, and used an existing Intel delidding tool (the Delid Die Mate 2) along with a small piece of acrylic to spread the force against the PCB.

Delidding.png

Delidding the Ryzen 5 2400G (image credit der8auer via YouTube)

The Ryzen 5 2400G is using thermal paste and is not soldered, which enables this process to be reasonably safe - or as safe as delidding a CPU and voiding your warranty ever is. Is it worth it for lower temps and slight overclocking gains? That's up to the user, but integration of an APU like this invites small form-factors that could benefit from the lower temps, especially with low-profile air coolers.

More views from Raven Ridge, Ryzen 3 2200G and Ryzen 5 2400G roundup

Subject: Processors | February 13, 2018 - 03:10 PM |
Tagged: 2200G, 2400G, amd, raven ridge, ryzen, Zen

Ryan covered the launch of AMD's new Ryzen 5 2400G and Ryzen 3 2200G which you should have already checked out.  The current options on the market offer more setup variations and tests than there is time in the day, which is why you should check out the links below to get a full view of how these new APUs function.  For instance, The Tech Report tested using DDR4-3200 CL14 RAM when benchmarking, which AMD's architecture can take advantage of.  As far as productivity and CPU bound tasks perform, Intel's i5-8400 does come out on top, however it is a different story for the Vega APU.  The 11 CUs of the 2400G perform at the same level or slightly better than a GTX 1030 which could make this very attractive for a gamer on a budget. 

 

2400G.jpg

"AMD's Ryzen 5 2400G and Ryzen 3 2200G bring Raven Ridge's marriage of Radeon Vega graphics processors and Zen CPU cores to the desktop. Join us as we see what a wealth of new technology in one chip means for the state of gaming and productivity performance from the same socket."

Here are some more Processor articles from around the web:

Processors

 

Author:
Subject: Processors
Manufacturer: AMD

Raven Ridge Desktop

As we approach the one-year anniversary of the release of the Ryzen family of processors, the full breadth of the releases AMD put forth inside of 12 months is more apparent than ever. Though I feel like I have written summations of 2017 for AMD numerous times, it still feels like an impressive accomplishment as I reflect for today’s review. Starting with the Ryzen 7 family of processors targeting enthusiasts, AMD iterated through Ryzen 5, Ryzen 3, Ryzen Threadripper, Ryzen Pro, EPYC, and Ryzen Mobile.

Today, though its is labeled as a 2000-series of parts, we are completing what most would consider the first full round of the Ryzen family. As the first consumer desktop APU (AMD’s term for a processor with tightly integrated on-die graphics), the Ryzen 5 2400G and the Ryzen 3 2200G look very much like the Ryzen parts before them and like the Ryzen mobile APUs that we previously looked at in notebook form. In fact, from an architectural standpoint, these are the same designs.

DSC04637.JPG

Before diving into the hardware specifications and details, I think it is worth discussing the opportunity that AMD has with the Ryzen with Vega graphics desktop part. By most estimates, more than 30% of the desktop PCs sold around the world ship without a discrete graphics card installed. This means they depend on the integrated graphics from processor to handle the functions of general compute and any/all gaming that might happen locally. Until today, AMD has been unable to address that market with its currently family of Ryzen processors, as they require discrete graphics solutions.

While most of our readers fall into the camp of not just using a discrete solution but requiring one for gaming purposes, there are a lot of locales and situations where the Ryzen APU is going to provide more than enough graphics horsepower. The emerging markets in China and India, for example, are regularly using low-power systems with integrated graphics, often based on Intel HD Graphics or previous generation AMD solutions. These gamers and consumers will see dramatic increases in performance with the Zen + Vega solution that today’s processor releases utilize.

slides-9.jpg

Let’s not forget about secondary systems, small form factor designs, and PCs design for your entertainment centers as possible outlets for and uses for Ryzen APUs even for the most hardcore of enthusiast. Mom or Dad need a new PC for basic tasks on a budget? Again, AMD is hoping to make a case today for those sales.

Continue reading our review of the AMD Ryzen 5 2400G and Ryzen 3 2200G!

The SDM845 Reference Platform and CPU Results

The Snapdragon 845 is Qualcomm’s latest flagship mobile platform, officially announced on December 6 and known officially as the SDM845 (moving from the MSMxxxx nomenclature of previous iterations). At a recent media event we had a chance to go hands-on with a development platform device for a preview of this new Snapdragon's performance, the results of which we can now share. Will the Snapdragon 845 be Qualcomm's Android antidote to Apple's A11? Read on to find out!

SDM845_Platform.jpg

The SDM845 QRD (Qualcomm Reference Design) Device

While this article will focus on CPU and GPU performance with a few known benchmarks, the Snapdragon 845 is of course a full mobile platform which combines 8-core Kryo 385 CPU, Adreno 630 graphics, Hexagon 685 DSP (which includes the Snapdragon Neural Processing Engine), Spectra 280 image processor, X20 LTE modem, etc. The reference device was packaged like a typical 5.5-inch Android smartphone, which can only help to provide a real-world application of thermal management during benchmarking.


Qualcomm Reference Design Specifications:

  • Baseband Chipset: SDM845
  • Memory: 6 GB LPDDR4X (PoP)
  • Display: 5.5-inch 1440x2560
  • Camera:
    • Front: IMX320 12 MP Sensor
    • Rear: IMX386 12 MP Sensor
  • Audio:
    • No 3.5 mm headset jack (Analog over USB-C)
    • 4 Digital Microphones
  • Connector: USB 3.1 Type-C
    • DisplayPort over USB-C

At the heart of the Snapdragon 845 is the octa-core Kryo 385 CPU, configured with 4x performance cores and 4x efficiency cores, and offering clock speeds of up to 2.8 GHz. In comparison the Snapdragon 835 had a similar 8x CPU configuration (Kryo 280) clocked up to 2.45 GHz. The SDM845 is produced on 10 nm LPP process technology, while the SD835 (MSM8998) was the first to be manufactured at 10 nm (LPE). It is not surprising that Qualcomm is getting higher clock speeds from this new chip at the same process node, and increases in efficiency (the new 10nm LPP FinFET process) should theoretically result in similar - or possibly even lower - power draw from these higher clocks.

Continue reading our performance preview of the new Snapdragon 845 mobile platform!!

Intel Pushes Xeon to the Edge With Refreshed Skylake-Based Xeon D SoCs

Subject: Processors | February 7, 2018 - 09:01 AM |
Tagged: Xeon D, xeon, servers, networking, micro server, Intel, edge computing, augmented reality, ai

Intel announced a major refresh of its Xeon D System on a Chip processors aimed at high density servers that bring the power of the datacenter as close to end user devices and sensors as possible to reduce TCO and application latency. The new Xeon D 2100-series SoCs are built on Intel’s 14nm process technology and feature the company’s new mesh architecture (gone are the days of the ring bus). According to Intel the new chips are squarely aimed at “edge computing” and offer up 2.9-times the network performance, 2.8-times the storage performance, and 1.6-times the compute performance of the previous generation Xeon D-1500 series.

Intel New Xeon D-2100.png

Intel has managed to pack up to 18 Skylake-based processing cores, Quick Assist Technology co-processing (for things like hardware accelerated encryption/decryption), four DDR4 memory channels addressing up to 512 GB of DDR4 2666 MHz ECC RDIMMs, four Intel 10 Gigabit Ethernet controllers, 32 lanes of PCI-E 3.0, and 20 lanes of flexible high speed I/O that includes up to 14 lanes of SATA 3.0, four USB 3.0 ports, or 20 lanes of PCI-E. Of course, the SoCs support Intel’s Management Engine, hardware virtualization, HyperThreading, Turbo Boost 2.0, and AVX-512 instructions with 1 FMA (fuse-multiply-add) as well..

xeond2100-14.jpg

Suffice it to say, there is a lot going on here with these new chips which represent a big step up in capabilities (and TDPs) further bridging the gap between the Xeon E3 v5 family and Xeon E5 family and the new Xeon Scalable Processors. Xeon D is aimed at datacenters where power and space are limited and while the soldered SoCs are single socket (1P) setups, high density is achieved by filling racks with as many single processor Mini ITX boards as possible. Xeon D does not quite match the per-core clockspeeds of the “proper” Xeons but has significantly more cores than Xeon E3 and much lower TDPs and cost than Xeon E5. It’s many lower clocked and lower power cores excel at burstable tasks such as serving up websites where many threads may be generated and maintained for long periods of time but not need a lot of processing power and when new page requests do come in the cores are able to turbo boost to meet demand. For example, Facebook is using Xeon D processors to serve up its front end websites in its Yosemite OpenRack servers where each server rack holds 192 Xeon D 1540 SoCs (four Xeon D boards per 1U sleds) for 1,536 Broadwell cores. Other applications include edge routers, network security appliances, self-driving vehicles, and augmented reality processing clusters. The autonomous vehicles use case is perhaps the best example of just what the heck edge computing is. Rather than fighting the laws of physics to transfer sensor data back to a datacenter for processing to be sent back to the car to in time for it to safely act on the processed information, the idea of edge computing is to bring most of the processing, networking, and storage power as close as possible to both the input sensors and the device (and human) that relies on accurate and timely data to make decisions.

xeond2100-15.jpg

As far as specifications, Intel’s new Xeon D lineup includes 14 processor models broken up into three main categories. The Edge Server and Cloud SKUs include eight, twelve, and eighteen core options with TDPs ranging from 65W to 90W. Interestingly, the 18 core Xeon D does not feature the integrated 10 GbE networking the lower end models have though it supports higher DDR4 memory frequencies. The two remaining classes of Xeon D SoCs are “Network Edge and Storage” and “Integrated Intel Quick Assist Technology” SKUs. These are roughly similar with two eight core, one 12 core, and one 16 core processor (the former also has a quad core that isn’t present in the latter category) though there is a big differentiator in clockspeeds. It seems customers will have to choose between core clockspeeds or Quick Assist acceleration (up to 100 Gbps) as the chips that do have QAT are clocked much lower than the chips without the co-processor hardware which makes sense because they have similar TDPs so clocks needed to be sacrificed to maintain the same core count. Thanks to the updated architecture, Intel is encroaching a bit on the per-core clockspeeds of the Xeon E3 and Xeon E5s though when turbo boost comes into play the Xeon Ds can’t compete.

Intel Xeon D-2100 SKU Information.png

The flagship Xeon D 2191 offers up two more cores (four additional threads) versus the previous Broadwell-based flagship Xeon D 1577 as well as higher clockspeeds at 1.6 GHz base versus 1.3 GHz and 2.2 GHz turbo versus 2.1 GHz turbo. The Xeon D 2191 does lack the integrated networking though. Looking at the two 16 core refreshed Xeon Ds compared to the 16 core Xeon D 1577, Intel has managed to increase clocks significantly (up to 2.2 GHz base and 3.0 GHz boost versus 1.3 GHz base and 2.10 GHz boost), double the number of memory channels and network controllers, and increase the maximum amount of memory from 128 GB to 512 GB. All those increases did come at the cost of TDP though which went from 45W to 100W.

xeond2100-6.jpg

Xeon D has always been an interesting platform both for enthusiasts running VM labs and home servers and big data enterprise clients building and serving up the 'next big thing' built on the astonishing amounts of data people create and consume on a daily basis. (Intel estimates a single self driving car would generate as much as 4TB of data per day while the average person in 2020 will generate 1.5 GB of data per day and VR recordings such as NFL True View will generate up to 3TB a minute!) With Intel ramping up both the core count, per-core performance, and I/O the platform is starting to not only bridge the gap between single socket Xeon E3 and dual socket Xeon E5 but to claim a place of its own in the fast-growing server market.

I am looking forward to seeing how Intel's partners and the enthusiast community take advantage of the new chips and what new projects they will enable. It is also going to be interesting to see the responses from AMD (e.g. Snowy Owl and to a lesser extent Great Horned Owl at the low and niche ends as it has fewer CPU cores but a built in GPU) and the various ARM partners (Qualcomm Centriq, X-Gene, Ampere, ect.*) as they vie for this growth market space with higher powered SoC options in 2018 and beyond.

Also read:

*Note that X-Gene and Ampere are both backed by the Carlyle Group now with MACOM having sold X-Gene to Project Denver Holdings and the ex-Intel employee led Ampere being backed by the Carlyle Group.

Source: Intel

It takes a hefty CPU to power a Chocobo

Subject: Processors | February 5, 2018 - 04:28 PM |
Tagged: final fantasy xv, round up

The new iteration of Final Fantasy sports some hefty recommendations, including the need for a Core i7-3770 or FX-8350 powering your system.  TechSpot decided to test out a variety of CPUs to see how they performed in tandem with a GTX 1080 Ti.  With 14 CPUs represented, including several generations of Intel chips and a representative from each of the three Ryzen lines they proceeded to run through a battery of benchmarks.  The tests quickly showed that if you are running a quad core CPU clocked lower than 4GHz, from either vendor, you are not going to have a good time.  Check out the full results to see if your system can handle it or if you should be shopping for a Ryzen 5 or 7, or perhaps a higher end Coffee Lake if Intel is your cup of tea.

2018-02-05-image-5.jpg

"Today we're checking out Final Fantasy XV CPU performance using the new standalone benchmark released ahead of next month's PC launch. The reason we want to look at CPU performance first is because the game is extremely CPU intensive, far more so than we were expecting."

Here are some more Processor articles from around the web:

Processors

 

Source: Techspot

Intel Recommends Waiting to Apply Haswell and Broadwell Spectre and Meltdown Patches

Subject: Processors | January 22, 2018 - 09:40 PM |
Tagged: spectre, meltdown, Intel

A couple of weeks ago, Intel acknowledged reports that firmware updates for Spectre and Meltdown resulted in reboots and other stability issues. At the time, they still suggested that end-users should apply the patch regardless. They have since identified the cause and their recommendation has changed: OEMs, cloud service providers, system manufacturers, software vendors, and end users should stop deploying the firmware until a newer solution is released.

INTEL_XeonE7v3_1_p.jpg

The new blog post also states that an early version of the updated patch has been created. Testing on the updated firmware started over the weekend, and it will be published shortly after that process has finished.

According to their security advisory, another patch that solved both Spectre 1 and Meltdown did not exhibit stability and reboot issues. This suggests that something went wrong with the Spectre 2 mitigation, which could be a fun course of speculation for tea-leaf readers to guess what went wrong in the patch. Ultimately, it doesn’t matter, though, because new code will be available soon.

Source: Intel