… so far, as Microsoft was in a “shut-up and ship” mode of operation during 2013 and could deliver its revolutionary Cloud OS with its even more disruptive Big Data solution for x86 only (that is likely to change as 64-bit ARM will be delivered with servers in H2 CY14).
AMD is also in a quite unique market position now as its only real competitor, Calxeda shut down its operation on December 19, 2013 and went into restructuring. The reason for that was lack of further funding by venture capitalists attributed mainly to its initial 32-bit Cortex-A15 based approach and the unwillingness of customers and software partners to port their already 64-bit x86 software back to 32-bit.
With the only remaining competitor in the 64-bit ARM server SoC race so far*, Applied Micro’s X-Gene SoC being built on a purpose built core of its own (see also my Software defined server without Microsoft: HP Moonshot [‘Experiencing the Cloud’, April 10, Dec 6, 2013] post), i.e. with only architecture license taken from ARM Holdings, the volume 64-bit ARM server SoC market starting in 2014 already belongs to AMD. I would base that prediction on the AppliedMicro’s X-Gene: 2013 Year in Review [Dec 20, 2013] post, stating that the first-generation X-Gene product is just nearing volume production, and a pilot X-Gene solution is planned only for early 2014 delivery by Dell.
* There is also Cavium which has too an ARMv8 architecture license only (obtained in August, 2012) but for this the latest information (as of Oct 30, 2013) was that: “In terms of the specific announcement of the product, we want to do it fairly close to silicon. We believe that this is a very differentiated product, and we would like to kind of keep it under the covers as long as we can. Obviously our customers have all the details of the products, and they’re working with them, but on a general basis for competitive reasons, we are kind of keeping this a little bit more quieter than we normally do.”
Meanwhile the 64-bit x86 based SeaMicro solution has been on the market since July 30, 2010, after 3 years in development. At the time of SeaMicro acquisition by AMD (Feb 29, 2012) this already represented a quite well thought-out and engineered solution, as one can easily grasp from the information included below: 
1. IOVT: I/O-Virtualization Technology
2. TIO: Turn It Off
3. Freedom™ Supercomputer Fabric: 3D torus network fabric
- 8 x 8 x 8 Fabric nodes
- Diameter (max hop) 4 + 4 + 4 = 12
- Theor. cross section bandwidth = 2 (periodic) x 8 x 8 (section) x 2(bidir) x 2.0Gbs/link = 512Gb/s
- Compute, storage, mgmt cards are plugged into the network fabric
- Support for hot plugged compute cards
The first three—IOVT, TIO, and the Freedom™ Supercomputer Fabric—live in SeaMicro’s Freedom™ ASIC. Freedom™ ASICs are paired with each CPU and with DRAM, forming the foundational building block of a SeaMicro system.
4. DCAT: Dynamic Computation-Allocation Technology™
- CPU management and load balancing
- Dynamic workload allocation to specific CPUs on the basis of power-usage metrics
- Users can create pools of compute for a given application
- Compute resources can be dynamically added to the pool based on predefined utilization thresholds
The DCAT technology resides in the SeaMicro system software and custom-designed FPGAs/NPUs, which control and direct the I/O traffic.
More information:
- SeaMicro SM10000-64 Server [SeaMicro presentation on Hot Chips 23, Aug 19, 2011] for slides in PDF format while the presentation itself is the first one in the following recorded video (just the first 20 minutes + 7 minutes of—quite valuable—Q&A following that):
Session 7, Hot Chips 23 (2011), Friday, August 19, 2011. SeaMicro SM10000-64 Server: Building Data Center Servers Using “Cell Phone” Chips Ashutosh Dhodapkar, Gary Lauterbach, Sean Lie, Dhiraj Mallick, Jim Bauman, Sundar Kanthadai, Toru Kuzuhara, Gene Shen, Min Xu, and Chris Zhang, SeaMicro Poulson: An 8-Core, 32nm, Next-Generation Intel Itanium Processor Stephen Undy, Intel T4: A Highly Threaded Server-on-a-Chip with Native Support for Heterogenous Computing Robert Golla and Paul Jordan, Oracle
- SeaMicro Technology Overview [Anil Rao from SeaMicro, January 2012]
- System Overview for the SM10000 Family [Anil Rao from SeaMicro, January 2012]
Note that the above is just for the 1st generation as after the AMD acquisition (Feb 29, 2012) a second generation solution came out with the SM15000 enclosure (Sept 10, 2012 with more info in the details section later), and certainly there will be a 3d generation solution with the integrated into the each of x86 and 64-bit ARM based SoCs coming in 2014.
With the “only production ready, production tested supercompute fabric” (as was touted by Rory Read, CEO of AMD more than a year ago), the SeaMicro Freedom™ now will be integrated into the upcoming 64-bit ARM Cortex-A57 based “Seattle” chips from AMD, sampling in the first quarter of 2014. Consequently I would argue that even the high-end market will be captured by the company. Moreover, I think this will not be only in the SoC realm but in enclosures space as well (although that 3d type of enclosure is still to come), to detriment of HP’s highly marketed Moonshot and CloudSystem initiatives.
Then here are two recent quotes from the top executive duo of AMD showing the importance of their upcoming solution as they view it themselves:
Rory Read – AMD’s President and CEO [Oct 17, 2013]:
In the server market, the industry is at the initial stages of a multiyear transition that will fundamentally change the competitive dynamic. Cloud providers are placing a growing importance on how they get better performance from their datacenters while also reducing the physical footprint and power consumption of their server solution.
Lisa Su – AMD’s Senior Vice President and General Manager, Global Business Units [Oct 17, 2013]:
We are fully top to bottom in 28 nanometer now across all of our products, and we are transitioning to both 20 nanometer and to FinFETs over the next couple of quarters in terms of designs. … [Regarding] the SeaMicro business, we are very pleased with the pipeline that we have there. Verizon was the first major datacenter win that we can talk about publicly. We have been working that relationship for the last two years. …
… We’re very excited about the server space. It’s a very good market. It’s a market where there is a lot of innovation and change. In terms of 64-bit ARM, you will see us sampling that product in the first quarter of 2014. That development is on schedule and we’re excited about that. All of the customer discussions have been very positive and then we will combine both the [?x86 and the?]64-bit ARM chip with our SeaMicro servers that will have full solution as well. You will see SeaMicro plus ARM in 2014.
So I think we view this combination of IP as really beneficial to accelerating the dense server market both on the chip side and then also on the solution side with the customer set.
AMD SeaMicro has been extensively working with key platform software vendors, especially in the open source space:
The current state of that collaboration is reflected in the corresponding numbered sections coming after the detailed discussion (given below before the numbered sections):
Verizon (as its first big name cloud customer, actually not using OpenStack)
OpenStack (inc. Rackspace, excl. Red Hat)
Red Hat
Ubuntu
Big Data, Hadoop
So let’s take a detailed look at the major topic:
AMD in the Demo Theater [OpenStack Foundation YouTube channel, May 8, 2013]
AMD presented its demo at the April 2013 OpenStack Summit in Portland, OR. For more summit videos, visit: http://www.openstack.org/summit/portland-2013/session-videos/
Note that the OpenStack Quantum networking project was renamed Neutron after April, 2013. Details on the OpenStack effort will be provided later in the post.
Rory Read – AMD President and CEO [Oct 30, 2012]:
That SeaMicro Freedom™ fabric is ultimately very-very important. It is the only production ready, production tested supercompute fabric on the planet.
Lisa Su – AMD Senior Vice President and General Manager, Global Business Units [Oct 30, 2012]:
The biggest change in the datacenter is that there is no one size fits all. So we will offer ARM-based CPUs with our fabric. We will offer x86-based CPUs with our fabric. And we will also look at opportunities where we can merge the CPU technology together with graphics compute in an APU form-factor that will be very-very good for specific workloads in servers as well. So AMD will be the only company that’s able to offer the full range of compute horsepower with the right workloads in the datacenter.
AMD makes ARM Cortex-A57 64bit Server Processor [Charbax YouTube channel, Oct 30, 2012]
AMD has announced that they are launching a new ARM Cortex-A57 64bit ARMv8 Processor in 2014, targetted for the servers market. This is an interview with Andrew Feldman, VP and GM of Data Center Server Solutions Group at AMD, founder of SeaMicro now acquired by AMD.
From AMD Changes Compute Landscape as the First to Bridge Both x86 and ARM Processors for the Data Center [press release, Oct 29, 2012]
This strategic partnership with ARM represents the next phase of AMD’s strategy to drive ambidextrous solutions in emerging mega data center solutions. In March, AMD announced the acquisition of SeaMicro, the leader in high-density, energy-efficient servers. With this announcement, AMD will integrate the AMD SeaMicro Freedom fabric across its leadership AMD Opteron x86- and ARM technology-based processors that will enable hundreds, or even thousands of processor clusters to be linked together to provide the most energy-efficient solutions.
AMD ARM Oct 29, 2012 Full length presentation [Manny Janny YouTube channel, Oct 30, 2012]
I do not have any affiliation with AMD or ARM. This video is posted to provide the general public with information and provide an area for comments
Rory Read – AMD President and CEO: [3:27] That SeaMicro Freedom™ fabric is ultimately very-very important in this announcement. It is the only production ready, production tested supercompute fabric on the planet. [3:41]
Lisa Su – Senior Vice President and General Manager, Global Business Units: [13:09] The biggest change in the datacenter is that there is no one size fits all. So we will offer ARM-based CPUs with our fabric. We will offer x86-based CPUs with our fabric. And we will also look at opportunities where we can merge the CPU technology together with graphics compute in an APU form-factor that will be very-very good for specific workloads in servers as well. So AMD will be the only company that’s able to offer the full range of compute horsepower with the right workloads in the datacenter [13:41]
From AMD to Acquire SeaMicro: Accelerates Disruptive Server Strategy [press release, Feb 29, 2012]
AMD (NYSE: AMD) today announced it has signed a definitive agreement to acquire SeaMicro, a pioneer in energy-efficient, high-bandwidth microservers, for approximately $334 million, of which approximately $281 million will be paid in cash. Through the acquisition of SeaMicro, AMD will be accelerating its strategy to deliver disruptive server technology to its OEM customers serving cloud-centric data centers. With SeaMicro’s fabric technology and system-level design capabilities, AMD will be uniquely positioned to offer industry-leading server building blocks tuned for the fastest-growing workloads such as dynamic web content, social networking, search and video. …
… “Cloud computing has brought a sea change to the data center–dramatically altering the economics of compute by changing the workload and optimal characteristics of a server,” said Andrew Feldman, SeaMicro CEO, who will become general manager of AMD’s newly created Data Center Server Solutions business. “SeaMicro was founded to dramatically reduce the power consumed by servers, while increasing compute density and bandwidth. By becoming a part of AMD, we will have access to new markets, resources, technology, and scale that will provide us with the opportunity to work tightly with our OEM partners as we fundamentally change the server market.”
ARM TechCon 2012 SoC Partner Panel: Introducing the ARM Cortex-A50 Series [ARMflix YouTube channel, recorded on Oct 30, published on Nov 13, 2012]
Moderator: Simon Segars EVP and GM, Processor and Physical IP Divisions ARM Panelists: Andrew Feldman Corporate VP & GM, Data Center Server Solutions (need to confirm his title with AMD) AMD Martyn Humphries VP & General Manager, Mobile Applications Group Broadcom Karl Freund VP, Marketing Calxeda** John Kalkman VP, Marketing Samsung Semiconductor Bob Krysiak EVP and President of the Americas Region STMicroelectronics
** Note that nearly 14 months later, on Dec 19, 2013 Calxeda ran out of its ~$100M venture capital accumulated earlier. As the company was not able to secure further funding it shut down its operation by dismissing most of its employees (except 12 workers serving existing customers) and went into “restructuring” with just putting on their company website: “We will update you as we conclude our restructuring process”. This is despite of the kind of pioneering role the company had, especially with HP’s Moonshot and CloudSystem initiatives, and the relatively short term promise of delivering its server cartridge to HP’s next-gen Moonshot enclosure as was well reflected in my Software defined server without Microsoft: HP Moonshot [‘Experiencing the Cloud’, April 10, Dec 6, 2013] post. The major problem was that “it tried to get to market with 32-bit chip technology, at a time most x86 servers boast 64-bit technology … [and as] customers and software companies weren’t willing to port their software to run on 32-bit systems” – reported the Wall Street Journal. I would also say that AMD’s “only production ready, production tested supercompute fabric on the planet” (see AMD Rory’s statement already given above) with its upcoming “Seattle” 64-bit ARM SoC to be on track for delivery in H2 CY14 was another major reason for the lack of additional venture funds to Calxeda.
AMD’s 64-bit “Seattle” ARM processor brings best of breed hardware and software to the data center [AMD Business blog, Dec 12, 2013]
Going into 2014, the server market is set to face the biggest disruption since AMD launched the 64-bit x86 AMD Opteron™ processor – the first 64-bit x86 processor – in 2003. Processors based on ARM’s 64-bit ARMv8 architecture will start to appear next year, and just like the x86 AMD Opteron™ processors a decade ago, AMD’s ARM 64-bit processors will offer enterprises a viable option for efficiently handling vast amounts of data.
From: AMD Unveils Server Strategy and Roadmap [press release June 18, 2013]
These forthcoming AMD Opteron™ processors bring important innovations to the rapidly changing compute market, including integrated CPU and GPU compute (APU); high core-count ARM servers for high-density compute in the data center; and substantial improvements in compute per-watt per-dollar and total cost of ownership.
“Our strategy is to differentiate ourselves by using our unique IP to build server processors that are particularly well matched to a target workload and thereby drive down the total cost of owning servers. This strategy unfolds across both the enterprise and data centers and includes leveraging our graphics processing capabilities and embracing both x86 and ARM instruction sets,” said Andrew Feldman, general manager of the Server Business Unit, AMD. “AMD led the world in the transition to multicore processors and 64-bit computing, and we intend to do it again with our next-generation AMD Opteron families.”
In 2014, AMD will set the bar in power-efficient server compute with the industry’s premier ARM server CPU. The 64-bit CPU, code named “Seattle,” is based on ARM Cortex™-A57 cores and is expected to provide category-leading throughput as well as setting the bar in performance-per-watt. AMD will also deliver a best-in-class APU, code named “Berlin.” “Berlin” is an x86 CPU and APU, based on a new generation of cores named “Steamroller.” Designed to double the performance of the recently available “Kyoto” part, “Berlin” will offer extraordinary compute-per-watt that will enable massive rack density. The third processor announced today is code named “Warsaw,” AMD’s next-generation 2P/4P offering. It is optimized to handle the heavily virtualized workloads found in enterprise environments including the more complex compute needs of data analytics, xSQL and traditional databases. “Warsaw” will provide significantly improved performance-per-watt over today’s AMD Opteron™ 6300 family.
Seattle
“Seattle” will be the industry’s only 64-bit ARM-based server SoC from a proven server processor supplier. “Seattle” is an 8- and then 16-core CPU based on the ARM Cortex-A57 core and is expected to run at or greater than 2 GHz. The “Seattle” processor is expected to offer 2-4X the performance of AMD’s recently announced AMD Opteron X-Series processor with significant improvement in compute-per-watt. It will deliver 128GB DRAM support, extensive offload engines for better power efficiency and reduced CPU loading, server caliber encryption, and compression and legacy networking including integrated 10GbE. It will be the first processor from AMD to integrate AMD’s advanced Freedom™ Fabric for dense compute systems directly onto the chip. AMD plans to sample “Seattle” in the first quarter of 2014 with production in the second half of the year.
Berlin
“Berlin” is an x86-based processor that will be available both as a CPU and APU. The processor boasts four next-generation “Steamroller” cores and will offer almost 8X the gigaflops per-watt compared to current AMD Opteron™ 6386SE processor. It will be the first server APU built on AMD’s revolutionary Heterogeneous System Architecture (HSA), which enables uniform memory access for the CPU and GPU and makes programming as easy as C++. “Berlin” will offer extraordinary compute per-watt that enables massive rack density. It is expected to be available in the first half of 2014.
Warsaw
“Warsaw” is an enterprise server CPU optimized to deliver unparalleled performance and total cost of ownership for two- and four-socket servers. Designed for enterprise workloads, it will offer improved performance-per-watt, which drives down the cost of owning a “Warsaw”-based server while enabling seamless migration from the AMD Opteron 6300 Series family. It is a fully compatible socket with identical software certifications, making it ideal for the AMD Open 3.0 Server – the industry’s most cost effective Open Compute platform. It is expected to be available in the first quarter of 2014.
Note that AMD Details Embedded Product Roadmap [press release, Sept, 9, 2013] as well in which there is also a:
“Hierofalcon” CPU SoC
“Hierofalcon” is the first 64-bit ARM-based platform from AMD targeting embedded data center applications, communications infrastructure and industrial solutions. It will include up to eight ARM Cortex™-A57 CPUs expected to run up to 2.0 GHz, and provides high-performance memory with two 64-bit DDR3/4 channels with error correction code (ECC) for high reliability applications. The highly integrated SoC includes 10 Gb KR Ethernet and PCI-Express Gen 3 for high-speed network connectivity, making it ideal for control plane applications. The “Hierofalcon” series also provides enhanced security with support for ARM TrustZone® technology and a dedicated cryptographic security co-processor, aligning to the increased need for networked, secure systems. “Hierofalcon” is expected to be sampling in the second quarter of 2014 with production in the second half of the year.
The AMD Opteron processor came at a time when x86 processors were seen by many as silicon that could only power personal computers, with specialized processors running on architectures such as SPARC™ and Power™ being the ones that were handling server workloads. Back in 2003, the AMD Opteron processor did more than just offer another option, it made the x86 architecture a viable contender in the server market – showing that processors based on x86 architectures could compete effectively against established architectures. Thanks in no small part to the AMD Opteron processor, today the majority of servers shipped run x86 processors.
In 2014, AMD will once again disrupt the datacenter as x86 processors will be joined by those that make use of ARM’s 64-bit architecture. Codenamed “Seattle,” AMD’s first ARM-based Opteron processor will use the ARMv8 architecture, offering low-power processing in the fast growing dense server space.
To appreciate what the first ARM-based AMD Opteron processor is designed to deliver to those wanting to deploy racks of servers, it is important to realize that the ARMv8 architecture offers a clean slate on which to build both hardware and software.
ARM’s ARMv8 architecture is much more than a doubling of word-length from previous generation ARMv7 architecture: it has been designed from the ground-up to provide higher performance while retaining the trademark power efficiencies that everyone has come to expect from the ARM architecture. AMD’s “Seattle” processors will have either four or eight cores, packing server-grade features such as support for up to 128 GB of ECC memory, and integrated 10Gb/sec of Ethernet connectivity with AMD’s revolutionary Freedom™ fabric, designed to cater for dense compute systems.
From: AMD Delivers a New Generation of AMD Opteron and Intel Xeon “Ivy Bridge” Processors in its New SeaMicro SM15000 Micro Server Chassis [press release, Sept 10, 2012]
With the new AMD Opteron processor, AMD’s SeaMicro SM15000 provides 512 cores in a ten rack unit system with more than four terabytes of DRAM and supports up to five petabytes of Freedom Fabric Storage. Since AMD’s SeaMicro SM15000 server is ten rack units tall, a one-rack, four-system cluster provides 2,024 cores, 16 terabytes of DRAM, and is capable of supporting 20 petabytes of storage. The new and previously unannounced AMD Opteron processor is a custom designed octal core 2.3 GHz part based on the new “Piledriver” core, and supports up to 64 gigabytes of DRAM per CPU. The SeaMicro SM15000 system with the new AMD Opteron processor sets the high watermark for core density for micro servers.
… Configurations based on the AMD Opteron processor and Intel Xeon Processor E3-1265Lv2 (“Ivy Bridge” microarchitecture) will be available in November 2012. …
AMD off-chip interconnect fabric IP designed to enable significantly lower TCO
• Links hundreds –> thousands of SoC modules
• Shares hundreds of TBs storage and virtualizes I/O
• 160Gbps Ethernet Uplink
• Instruction Set:
- x86
- ARM (coming in 2014 when the fabric will be integrated into the SoCs as well, including the x86 SoCs)
From: SM15000-OP: 64 Octal Core Servers
with AMD Opteron™ processors (2.0/2.3/2.8 GHz, 8 “Piledriver” cores)
Freedom™ ASIC 2.0 – Industry’s only Second Generation Fabric Technology
The Freedom™ ASIC is the building block of SeaMicro Fabric Compute Systems, enabling interconnection of energy efficient servers in a 3-dimensional Torus Fabric. The second generation Freedom ASIC includes high performance network interfaces, storage connectivity, and advanced server management, thereby eliminating the need for multiple sets of network adapters, HBAs, cables, and switches. This results in unmatched density, energy efficiency, and lowered TCO. Some of the key technologies in ASIC 2.0 include:
SeaMicro Input/Output Virtualization Technology (IOTV™) eliminates all but three components from SeaMicro’s motherboard—CPU, DRAM, and the ASIC itself—thereby shrinking the motherboard, while reducing power, cost and space.
SeaMicro new TIO™ (Turn It Off) technology enables SeaMicro to further power-optimize the mini motherboard by turning off unneeded CPU and chipset functions. Together, SeaMicro’s I/O Virtualization Technology and TIO technology produce the smallest and most power efficient server motherboards available.
SeaMicro Freedom Supercompute Fabric built of multiple Freedom ASICs working together, creating a 1.28 terabits per-second fabric that ties together 64 of the power-optimized mini-motherboards at low latency and low power with massive bandwidth.
SeaMicro Freedom Fabric Storage technology allows the Freedom supercompute fabric to extend out of the chassis and across the data center linking not just components inside the chassis, but also those outside as well.
Unified Management – Easily Provision and Manage Servers, Network, and Storage Resources on Demand
The SeaMicro SM15000 implements a rich management system providing unified management of servers, network, and storage. Resources can be rapidly deployed, managed, and repurposed remotely, enabling lights-off data center operations. It offers a broad set of management API including an industry standard CLI, SNMP, IPMI, syslog, and XEN APIs, allowing customers to seamlessly integrate the SeaMicro SM15000 into existing data center management environments.
Redundancy and Availability – Engineered from the Ground Up to Eliminate Single Points of Failure
The SeaMicro SM15000 is designed for the most demanding environments, helping to ensure availability of compute, network, storage, and system management. At the heart of the system is the Freedom Fabric, interconnecting all resources in the system, with the ability to sustain multiple points of failure and allow live component servicing. All active components in the system can be configured redundant and are hot-swappable, including server cards, network uplink cards, storage controller cards, system management cards, disks, fan trays, and power supplies. Key resources can also be configured to be protected in the following ways:
Compute – A shared spare server can be configured to act as a standby spare for multiple primary servers. In the event of failure, the primary server’s personality, including MAC address, assigned disks, and boot configuration can be migrated to the standby spare and brought back online – ensuring fast restoration of services from a remote location.
Network – The highly available fabric ensures network connectivity is maintained between servers and storage in the event of path failure. For uplink high-availability, the system can be configured with multiple uplink modules and port channels providing redundant active/active interfaces.
Storage – The highly available fabric ensures that servers can access fabric storage in the event of failures. The fabric storage system also provides an efficient, high utilization optional hardware RAID to protect data in case of disk failure.
The Industry’s First Data Center in a Box
AMD’s SeaMicro SM15000 family of Fabric Compute Systems provides the equivalent of 32 1RU dual socket servers, massive bandwidth, top of rack Ethernet switching, and high capacity shared storage, with centralized management in a small, compact 10RU form factor. In addition, it provides an integrated server console management for unified management. The SeaMicro SM15000 dramatically reduces CAPEX and significantly reduces the ongoing OPEX of deploying discreet compute, networking, storage, and management systems.
More information:
- An Overview of AMD|SeaMicro Technology [Anil Rao from AMD|SeaMicro, October 2012]
- System Overview for the SM15000 Family [Anil Rao from AMD|SeaMicro, October 2012]
- What a Difference 0.09 Percent Makes [The Wave Newsletter from AMD, September 2013]
Today’s cloud services have helped companies consolidate infrastructure and drive down costs, however, recent service interruptions point to a big downside of relying on public cloud service. Most are built using commodity, off-the-shelf servers to save costs and are standardized around the same computing and storage SLAs of 99.95 and 99.9 percent. This is significantly lower than the four nine availability standard in the data networking world. Leading companies are realizing that the performance and reliability of their applications is inextricably linked to their underlying server architecture. In this issue, we discuss the strategic importance of selecting the right hardware. Whether building an enterprise-caliber cloud service or implementing Apache™ Hadoop® to process and analyze big data, hardware matters.
more >
- Where Does Software End and Hardware Begin? [The Wave Newsletter from AMD, September 2013]
Lines are blurring between software and hardware with some industry leaders choosing to own both. Software companies are realizing that the performance and value of their software depends on their hardware choices. more >
- Improving Cloud Service Resiliency with AMD’s SeaMicro Freedom Fabric [The Wave Newsletter from AMD, December 2013]
Learn why AMD’s SeaMicro Freedom™ Fabric ASIC is the server industry’s first viable solution to cost-effectively improve the resiliency and availability of cloud-based services.
We realize that having an impressive set of hardware features in the first ARM-based Opteron processors is half of the story, and that is why we are hard at work on making sure the software ecosystem will support our cutting edge hardware. Work on software enablement has been happening throughout the stack – from the UEFI, to the operating system and onto application frameworks and developer tools such as compilers and debuggers. This ensures that the software will be ready for ARM-based servers.
AMD developing Linux on ARM at Linaro Connect 2013 [Charbax YouTube channel, March 11, 2013]
[Recorded at Linaro Connect Asia 2013, March 4-8, 2013] Dr. Leendert van Doorn, Corporate Fellow at AMD, talks about what AMD does with Linaro to optimize Linux on ARM. He talks about the expectations that AMD has for results to come from Linaro in terms of achieving a better and more fully featured Linux world on ARM, especially for the ARM Cortex-A57 ARMv8 processor that AMD has announced for the server market.
AMD’s participation in software projects is well documented, being a gold member of the Linux Foundation, the organization that manages the development of the Linux kernel, and a group member of Linaro. AMD is a gold sponsor of the Apache Foundation, which oversees projects such as Hadoop, HTTP Server and Samba among many others, and the company’s engineers are contributors to the OpenJDK project. This is just a small selection of the work AMD is taking part in, and these projects in particular highlight how important AMD feels that open source software is to the data center, and in particular micro servers, that make use of ARM-based processors.
And running ARM-based processors doesn’t mean giving up on the flexibility of virtual machines, with KVM already ported to the ARMv8 architecture. Another popular hypervisor, Xen, is already available for 32-bit ARM architectures with a 64-bit port planned, ensuring that two popular and highly capable hypervisors will be available.
The Linux kernel has supported 64-bit ARMv8 architecture since Linux 3.7, and a number of popular Linux distributions have already signaled their support for the architecture including Canonical’s Ubuntu and the Red Hat sponsored Fedora distribution. In fact there is a downloadable, bootable Ubuntu distribution available in anticipation for ARMv8-based processors.
It’s not just operating systems and applications that are available. Developer tools such as the extremely popular open source GCC compiler and the vital GNU C Library (Glibc) have already been ported to the ARMv8 architecture and are available for download. With GCC and Glibc good to go, a solid foundation for developers to target the ARMv8 architecture is forming.
All of this work on both hardware and software should shed some light on just how big ARM processors will be in the data center. AMD, an established enterprise semiconductor vendor, is uniquely placed to ship both 64-bit ARMv8 and 64-bit x86 processors that enable “mixed rack” environments. And thanks to the army of software engineers at AMD, as well as others around the world who have committed significant time and effort, the software ecosystem will be there to support these revolutionary processors. 2014 is set to see the biggest disruption in the data center in over a decade, with AMD again at the center of it.
Lawrence Latif is a blogger and technical communications representative at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.
End of AMD’s 64-bit “Seattle” ARM processor brings best of breed hardware and software to the data center [AMD Business blog, Dec 12, 2013]
AMD at ARM Techcon 2013 [Charbax YouTube channel, recorded at the ARM Techcon 2013 (Oct 29-31), published on Dec 25, 2013]
AMD in 2014 will be delivering a 64bit ARM processor for servers. The ARM Architecture and Ecosystem enables servers to achieve greater performance per watt and greater performance per dollar. The code name for the product is Seattle. AMD Seattle is expected to reach mass market cloud servers in the second half of 2014.
From: Advanced Micro Devices’ CEO Discusses Q3 2013 Results – Earnings Call Transcript [Seeking Alpha, Oct 17, 2013]
Rory Read – President and CEO:
The three step turnaround plan we outlined a year ago to restructure, accelerate and ultimately transform AMD is clearly paying off. We completed the restructuring phase of our plan, maintaining cash at optimal levels and beating our $450 million quarterly operating expense goal in the third quarter. We are now in the second phase of our strategy – accelerating our performance by consistently executing our product roadmap while growing our new businesses to drive a return to profitability and positive free cash flow.
We are also laying the foundation for the third phase of our strategy, as we transform AMD to compete across a set of high growth markets. Our progress on this front was evident in the third quarter as we generated more than 30% of our revenue from our semi-custom and embedded businesses. Over the next two years we will continue to transform AMD to expand beyond a slowing, transitioning PC industry, as we create a more diverse company and look to generate approximately 50% of our revenue from these new high growth markets.
We have strategically targeted that semi-custom, ultra-low power client, embedded, dense server and the professional graphics market where we can offer differentiated products that leverage our APU and graphics IP. Our strategy allows us to continue to invest in the product that will drive growth, while effectively managing operating expenses. …
… Several of our growth businesses passed key milestones in the third quarter. Most significantly, our semi-custom business ramped in the quarter. We successfully shipped millions of units to support Sony and Microsoft, as they prepared to launch their next-generation game consoles. Our game console wins are generating a lot of customer interest, as we demonstrate our ability to design and reliably ramp production on two of the most complex SOCs ever built for high-volume consumer devices. We have several strong semi-custom design opportunities moving through the pipeline as customers look to tap into AMD’s IP, design and integration expertise to create differentiated winning solutions. … it’s our intention to win and mix in a whole set semicustom offerings as we build out this exciting and important new business.
We made good progress in our embedded business in the third quarter. We expanded our current embedded SOC offering and detailed our plans to be the only company to offer both 64-bit x86 and ARM solutions beginning in 2014. We have developed a strong embedded design pipeline which, we expect, will drive further growth for this business across 2014.
We also continue to make steady progress in another of our growth businesses in the third quarter, as we delivered our fifth consecutive quarter of revenue and share growth in the professional graphics area. We believe we can continue to gain share in this lucrative part of the GPU market, based on our product portfolio, design wins [in place] [ph] and enhanced channel programs.
In the server market, the industry is at the initial stages of a multiyear transition that will fundamentally change the competitive dynamic. Cloud providers are placing a growing importance on how they get better performance from their datacenters while also reducing the physical footprint and power consumption of their server solution.
This will become the defining metric of this industry and will be a key growth driver for t