AMD Refreshes Roadmap, Transitions Back to HPC

By Tiffany Trader

May 7, 2015

AMD revealed key elements of its multi-year strategy as part of its 2015 Financial Analyst Day event in New York on Wednesday. Out of the gate, CEO Lisa Su acknowledged the company’s recent challenges, pointing to a weak PC market and market share losses, before turning her attention to the game plan that AMD is counting on to turn its earnings statement from red to green. It’s a game plan that has AMD returning to the high-end server space as it seeks to diversify its revenue base and grow into new markets.

“We are focused on areas that require high performance compute, high performance graphics, visualization technologies, and complex system on chips,” said Su, who kicked off the proceedings, “those are the areas that are uniquely suited to AMD…and we think this represents about a $60+ billion TAM.”

AMD FAD 2015_3 year game plan slide

“Datacenter is probably the single biggest bet that we are making as a company,” she declared. “We have not been competitive the last few years, we will be competitive in the datacenter market.”

Su also spoke about the decision to exit the SeaMicro dense server system business line “for one because microservers were not growing as fast as originally thought and two we really aren’t a systems company, however on the silicon side, very very clearly we are an x86 company, we have tremendous x86 heritage and are absolutely going to invest in high-performance x86.”

With regard to technology, Su said that AMD portfolio decisions will be focused on high-performance cores, immersive technologies, 2.5/3D packaging and software/APIs. This will align with increased x86 investment, focused ARM investment and a simplified CPU roadmap.

Su also offered an appeasement for those wondering why AMD didn’t make these changes sooner.

“On the platform side, to those of you that ask what have you guys been doing for a couple of years. The truth is, it takes a while to really transform both the R&D capabilities, the technologies and the modularity,” she said.

And now…Getting Zen with simplified roadmaps

The highlight of AMD’s revamped technology roadmap is a brand new x86 processor core codenamed “Zen,” touting improved instructions per clock of up to 40 percent over “Excavator” cores. Absent from the lineup, however, is the Skybridge project. Announced last year, the plan to join x86 and ARM together on a common platform was dropped, according to Su, due to customer feedback indicating a desire for x86 and ARM, but not necessarily in socket-compatible factors.


Mark Papermaster, AMD chief technology officer and senior vice president, addressed AMD’s x86 positioning and laid out some of Zen’s specs in anticipation of its 2016 debut. AMD is counting on its new Zen core to drive its re-entry into high-performance desktop and server markets and put it back on a competitive track against arch rival Intel.

“It’s got high-throughput, very efficient design, and a new cache and memory subsystem design to feed this core,” he said, referring to the feature of simultaneous multi-threading (SMT). The performance is the result of doubling down on the previous generation core, Excavator, due out this summer, said Papermaster.

“This wasn’t one silver bullet,” Papermaster continued, “but a number of elements combining to drive the microarchitecture improvement and deliver what I’ve not seen in the industry before, a 40 percent improvement in instructions per clock.”

It’s the core design for the workload of the future and it’s available next year, he added. It’s also a commitment to sustainable innovation, according to Papermaster, who says the company has leapfrogging design teams and is already working on the successor to Zen as it works to establish a family of cores over time.

Papermaster also revealed that AMD’s first custom 64-bit ARM core, “K12” core, is on track for a 2017 sampling. These enterprise-class ARM cores are designed for efficiency and are intended for server and embedded workloads.

AMD FAD 2015_cg roadmap detail

On the graphics side, AMD is readying to launch its high-performance graphics processing unit (GPU) with die stacked High Bandwidth Memory (HBM) using a 2.5D silicon interposer design. This core is optimized for graphics and parallel compute and includes a number of other enhancements (depicted in the slide below). AMD reported that future generations of its high-performance GPUs will be based on FinFET process technology, which will contribute to a doubling of performance-per-watt.


These three essential chip technologies will be the building blocks of AMD’s Enterprise, Embedded and Semi-Custom Business Group (EESC). A new group launched in 2014 as part of AMD’s business unit reorganization, EESC is focused on high-priority markets that will leverage high-performance CPU and GPU cores inside differentiated solutions.

Forrest Norrod, senior vice president and general manager of the business group, referred to the EESC segment as “a principal driver of growth for the last few years and one we think is central to the growth story of AMD going forward.”

Norrod added that these three businesses (enterprise, embedded and semi-custom) share a perspective around the best way to showcase AMD technology.

“In all of these businesses our customers are building products around the technology ingredients that we give to them and bringing differentiated solutions to the end customer that leverage AMD unique IP,” he stated.

“So we really think now of ESSC as being a continuum leveraging technology, customer relationships and the modular design approach at both the chip as well as the systems level.”

Norad went on to share in broad strokes AMD’s datacenter roadmap for the 2016-2017 timeframe, which includes its next-gen x86 Opteron, next-gen ARM, and an APU that we will be tracking closely.

AMD FAD 2015_eesc roadmap

The upcoming next-generation AMD Opteron processors are based on the x86 “Zen” core and target mainstream servers. These x86 Opterons tout high core count with full multi-threading, disruptive memory bandwidth and high native I/O capacity. Norrrod also introduced “the highest performance ARM server GPUs,” powered by AMD’s upcoming “K12” core.

Most relevant for HPC, though, is the new high-performance server APU, a multi-teraflops chip targeting HPC and workstation markets.

“We’re bringing the APU concept fully into the server realm,” Norrod stated. “These are high performance server APUs offering not just high-performance CPU cores and memory but multi-teraflops GPU-capability, providing a level of performance for machine learning, a level of performance for finite element analysis, and a level of performance for memory bandwidth for reverse time migration algorithms that the oil companies use to do reservoir simulation.”

The APU line (APU stands for accelerated processing unit) is an outcome of the Fusion project, which started in 2006 with AMD’s acquisition of the graphics chipset manufacturer ATI. AMD has talked up the potential benefits of tight CPU-GPU integration for HPC workloads in the past, but until now AMD’s APU efforts have primarily been relegated to desktop space.

In January 2012, AMD rebranded the Fusion platform as the Heterogeneous Systems Architecture (HSA) and has in recent months begun championing the CPU+accelerator architecture for a wide range of workloads, including HPC.

AMD says the next-gen server APU stands to deliver massive improvements to vector applications with scale-up graphics performance, HSA enablement, and optimized memory architecture. “We think we’ve got unique and compelling technology that is only possible by wedding together the CPU and world-class GPU and combining them with an open standard HSA software interface,” said Norrod.

What’s not clear at this point is whether the APU’s multi-teraflops will be of the half- single- or double-precision variety, and the workloads that Norrod lists are a mixed bag in that respect (FEA and machine learning, for example). Of course, there is no reason AMD can’t launch variants for each, but it would be hard to claim HPC cred without an FP64-heavy version.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Kyoto University ACCMS Implements Fine-grained Power Management

September 19, 2018

Data center power management is a ubiquitous challenge and in few places is it more so than at Kyoto University Academic Center for Computing and Media Studies (ACCMS)) where power consumption limits were imposed followi Read more…

By Staff

What’s New in HPC Research: September (Part 1)

September 18, 2018

In this new bimonthly feature, HPCwire will highlight newly published research in the high-performance computing community and related domains. From exascale to quantum computing, the details are here. Check back every Read more…

By Oliver Peckham

House Passes $1.275B National Quantum Initiative

September 17, 2018

Last Thursday the U.S. House of Representatives passed the National Quantum Initiative Act (NQIA) intended to accelerate quantum computing research and development. Among other things it would establish a National Quantu Read more…

By John Russell

HPE Extreme Performance Solutions

Introducing the First Integrated System Management Software for HPC Clusters from HPE

How do you manage your complex, growing cluster environments? Answer that big challenge with the new HPC cluster management solution: HPE Performance Cluster Manager. Read more…

IBM Accelerated Insights

A Crystal Ball for HPC

People are notoriously bad at predicting the future.  This very much includes experts. In the Forbes article “Why Most Predictions Are So Bad” Philip Tetlock discusses the largest and best-known test of the accuracy of expert predictions which show that any experts would do better if they make random guesses. Read more…

Nvidia Accelerates AI Inference in the Datacenter with T4 GPU

September 14, 2018

Nvidia is upping its game for AI inference in the datacenter with a new platform consisting of an inference accelerator chip--the new Turing-based Tesla T4 GPU--and a refresh of its inference server software packaged as Read more…

By George Leopold

House Passes $1.275B National Quantum Initiative

September 17, 2018

Last Thursday the U.S. House of Representatives passed the National Quantum Initiative Act (NQIA) intended to accelerate quantum computing research and developm Read more…

By John Russell

Nvidia Accelerates AI Inference in the Datacenter with T4 GPU

September 14, 2018

Nvidia is upping its game for AI inference in the datacenter with a new platform consisting of an inference accelerator chip--the new Turing-based Tesla T4 GPU- Read more…

By George Leopold

DeepSense Combines HPC and AI to Bolster Canada’s Ocean Economy

September 13, 2018

We often hear scientists say that we know less than 10 percent of the life of the oceans. This week, IBM and a group of Canadian industry and government partner Read more…

By Tiffany Trader

Rigetti (and Others) Pursuit of Quantum Advantage

September 11, 2018

Remember ‘quantum supremacy’, the much-touted but little-loved idea that the age of quantum computing would be signaled when quantum computers could tackle Read more…

By John Russell

How FPGAs Accelerate Financial Services Workloads

September 11, 2018

While FSI companies are unlikely, for competitive reasons, to disclose their FPGA strategies, James Reinders offers insights into the case for FPGAs as accelerators for FSI by discussing performance, power, size, latency, jitter and inline processing. Read more…

By James Reinders

Update from Gregory Kurtzer on Singularity’s Push into FS and the Enterprise

September 11, 2018

Container technology is hardly new but it has undergone rapid evolution in the HPC space in recent years to accommodate traditional science workloads and HPC systems requirements. While Docker containers continue to dominate in the enterprise, other variants are becoming important and one alternative with distinctly HPC roots – Singularity – is making an enterprise push targeting advanced scale workload inclusive of HPC. Read more…

By John Russell

At HPC on Wall Street: AI-as-a-Service Accelerates AI Journeys

September 10, 2018

AIaaS – artificial intelligence-as-a-service – is the technology discipline that eases enterprise entry into the mysteries of the AI journey while lowering Read more…

By Doug Black

No Go for GloFo at 7nm; and the Fujitsu A64FX post-K CPU

September 5, 2018

It’s been a news worthy couple of weeks in the semiconductor and HPC industry. There were several HPC relevant disclosures at Hot Chips 2018 to whet appetites Read more…

By Dairsie Latimer

TACC Wins Next NSF-funded Major Supercomputer

July 30, 2018

The Texas Advanced Computing Center (TACC) has won the next NSF-funded big supercomputer beating out rivals including the National Center for Supercomputing Ap Read more…

By John Russell

IBM at Hot Chips: What’s Next for Power

August 23, 2018

With processor, memory and networking technologies all racing to fill in for an ailing Moore’s law, the era of the heterogeneous datacenter is well underway, Read more…

By Tiffany Trader

Requiem for a Phi: Knights Landing Discontinued

July 25, 2018

On Monday, Intel made public its end of life strategy for the Knights Landing "KNL" Phi product set. The announcement makes official what has already been wide Read more…

By Tiffany Trader

CERN Project Sees Orders-of-Magnitude Speedup with AI Approach

August 14, 2018

An award-winning effort at CERN has demonstrated potential to significantly change how the physics based modeling and simulation communities view machine learni Read more…

By Rob Farber

ORNL Summit Supercomputer Is Officially Here

June 8, 2018

Oak Ridge National Laboratory (ORNL) together with IBM and Nvidia celebrated the official unveiling of the Department of Energy (DOE) Summit supercomputer toda Read more…

By Tiffany Trader

New Deep Learning Algorithm Solves Rubik’s Cube

July 25, 2018

Solving (and attempting to solve) Rubik’s Cube has delighted millions of puzzle lovers since 1974 when the cube was invented by Hungarian sculptor and archite Read more…

By John Russell

AMD’s EPYC Road to Redemption in Six Slides

June 21, 2018

A year ago AMD returned to the server market with its EPYC processor line. The earth didn’t tremble but folks took notice. People remember the Opteron fondly Read more…

By John Russell

MLPerf – Will New Machine Learning Benchmark Help Propel AI Forward?

May 2, 2018

Let the AI benchmarking wars begin. Today, a diverse group from academia and industry – Google, Baidu, Intel, AMD, Harvard, and Stanford among them – releas Read more…

By John Russell

Leading Solution Providers

SC17 Booth Video Tours Playlist

Altair @ SC17


AMD @ SC17


ASRock Rack @ SC17

ASRock Rack



DDN Storage @ SC17

DDN Storage

Huawei @ SC17


IBM @ SC17


IBM Power Systems @ SC17

IBM Power Systems

Intel @ SC17


Lenovo @ SC17


Mellanox Technologies @ SC17

Mellanox Technologies

Microsoft @ SC17


Penguin Computing @ SC17

Penguin Computing

Pure Storage @ SC17

Pure Storage

Supericro @ SC17


Tyan @ SC17


Univa @ SC17


Pattern Computer – Startup Claims Breakthrough in ‘Pattern Discovery’ Technology

May 23, 2018

If it weren’t for the heavy-hitter technology team behind start-up Pattern Computer, which emerged from stealth today in a live-streamed event from San Franci Read more…

By John Russell

Sandia to Take Delivery of World’s Largest Arm System

June 18, 2018

While the enterprise remains circumspect on prospects for Arm servers in the datacenter, the leadership HPC community is taking a bolder, brighter view of the x86 server CPU alternative. Amongst current and planned Arm HPC installations – i.e., the innovative Mont-Blanc project, led by Bull/Atos, the 'Isambard’ Cray XC50 going into the University of Bristol, and commitments from both Japan and France among others -- HPE is announcing that it will be supply the United States National Nuclear Security Administration (NNSA) with a 2.3 petaflops peak Arm-based system, named Astra. Read more…

By Tiffany Trader

D-Wave Breaks New Ground in Quantum Simulation

July 16, 2018

Last Friday D-Wave scientists and colleagues published work in Science which they say represents the first fulfillment of Richard Feynman’s 1982 notion that Read more…

By John Russell

Intel Pledges First Commercial Nervana Product ‘Spring Crest’ in 2019

May 24, 2018

At its AI developer conference in San Francisco yesterday, Intel embraced a holistic approach to AI and showed off a broad AI portfolio that includes Xeon processors, Movidius technologies, FPGAs and Intel’s Nervana Neural Network Processors (NNPs), based on the technology it acquired in 2016. Read more…

By Tiffany Trader

Intel Announces Cooper Lake, Advances AI Strategy

August 9, 2018

Intel's chief datacenter exec Navin Shenoy kicked off the company's Data-Centric Innovation Summit Wednesday, the day-long program devoted to Intel's datacenter Read more…

By Tiffany Trader

TACC’s ‘Frontera’ Supercomputer Expands Horizon for Extreme-Scale Science

August 29, 2018

The National Science Foundation and the Texas Advanced Computing Center announced today that a new system, called Frontera, will overtake Stampede 2 as the fast Read more…

By Tiffany Trader

GPUs Power Five of World’s Top Seven Supercomputers

June 25, 2018

The top 10 echelon of the newly minted Top500 list boasts three powerful new systems with one common engine: the Nvidia Volta V100 general-purpose graphics proc Read more…

By Tiffany Trader

The Machine Learning Hype Cycle and HPC

June 14, 2018

Like many other HPC professionals I’m following the hype cycle around machine learning/deep learning with interest. I subscribe to the view that we’re probably approaching the ‘peak of inflated expectation’ but not quite yet starting the descent into the ‘trough of disillusionment. This still raises the probability that... Read more…

By Dairsie Latimer

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This