Intel Releases Knights Corner ISA, Lays Groundwork for MIC Launch

By Michael Feldman

June 11, 2012

Intel has released a partial software stack for Knights Corner, the company’s first commercial chip based on its Many Integrated Core (MIC) architecture. Also released were a number of documents describing the processor’s micro-architecture, including the Knights Corner Instruction Set (ISA) Manual, which will help toolmakers and application developers build software for the upcoming chip. The newly released information was described in a couple of blog posts last week by James Reinders, Intel’s chief evangelist and director of marketing for the company’s software development portfolio.

Up until now, Intel had not shared this software or documentation with anyone outside of its partner network. That posed something of a problem for third-party developers who don’t have that relationship with the Intel, but are looking to get MIC software products out the door in time for the upcoming Knights Corner launch. That chip is expected to go into production sometime in late 2012 or early 2013. Giving this first MIC product a running start is crucial, since it going to be competing against a GPU computing ecosystem with a five-year head start and an already-established product portfolio.

The newly released software from Intel includes source modifications for Linux, the GCC compiler and the GDB debugger, as well as new MIC drivers, which, together, will allow developers to build a Linux OS kernel capable of running on the manycore coprocessor. In this case, that applies to the current Knights Ferry prototype hardware, which is currently being used as a development platform at a number of sites, as well as the future Knights Corner chips.

Embedding an operating system on a coprocessor might seem a bit exotic since usually the host CPU, alone, runs the OS. But since the MIC architecture is essentially a variant of a Pentium CPU, it’s quite capable of acting as its own host. That will allow the Knights Corner to behave as a peer to the CPU, rather than just its slave. How that gets used in practice is still up in the air, but it would certainly make for a more flexible development environment, inasmuch as entire Linux apps could be launched and controlled locally on the MIC chip.

Even though this software is now public, the mods still have to work their way into the various Linux, GCC and GDB distributions, which could take awhile. In the meantime, anyone with a Knights Ferry test setup or simulator can pick up the new code on Intel’s MIC software resource page and have at it.

It’s important to note that the current set of mods delivered last week does not include MIC application support, which would have to encompass GCC and GDB support for the Knight Corner vector instructions. (The Linux kernel running on the coprocessor has no need for vector instructions.) That means for the time being, developers will still have to rely on Intel’s own compilers (or a CAPS enterprise compiler that is hooked into the Intel MIC back-end) if they want to build Knights Ferry or Knights Corner applications.

Also left out is compiler support for any coprocessor offload directives (text that can be inserted into high-level source that tells the compiler to execute specific code on the accelerator). Intel has not endorsed OpenACC, the budding accelerator directives standard backed by NVIDIA and some of its partners (PGI, CAPS enterprise, and Cray). Instead it has invented its own offload technology, known as LEO (Language Extensions for Offload), which users of the Intel compiler can tap into to offload chunks of their application onto the MIC hardware.

LEO is a less restrictive and more generalized set of offload directives than OpenACC since its allows the programmer to offload virtually any function or even a whole application to the MIC hardware. Remember that MIC is based on the Pentium, an older Intel architecture chosen for its simpler design, which is more suitable for a manycore throughput processor. Although the individual cores are relatively slow, they have almost all the functional capabilities of Xeon cores. Thus MIC can behave as a general-purpose CPU, albeit one with limited single-thread performance and smaller memory.

In any case, LEO will likely never become a public standard on its own. The end game for Intel is to get its capabilities incorporated into OpenMP’s future extension for accelerator directives. That effort will somehow have to blend the more GPU-oriented OpenACC standard with the CPU-oriented LEO model and come up with a platform-independent standard that can be applied across all types of accelerators.

Although the MIC software stack that Intel donated last week didn’t do much for application developers, the documentation that was made public should help them, at least indirectly. In addition to the Knights Corner ISA manual, the chip maker also provided the ABI (Application Binary Interface) and Performance Monitoring Unit documents. With this documentation in hand, software tool makers now have the information needed to build their own MIC compilers, libraries and other developer gadgets like debuggers and simulators. All the docs are available for download on the MIC resources page mentioned above.

The ISA and the ABI documents are more like addendums to the standard IA versions since MIC itself is just an x86 variant. MIC, though, overlays 64-bit processing, extra wide vector instructions, and a manycore design on top of the original Pentium architecture, which makes it a unique IA64 processor family.

Not surprisingly, most of the ISA doc focuses on the 512-bit wide vector instructions, along with all the fancy vector masking and shifting that turns the new chip into a SIMD powerhouse. MIC’s vector width is twice that of AVX (256 bits), the SIMD instruction set in the latest Intel Sandy Bridge and AMD Bulldozer CPUs. AVX, in turn, doubled the 128-bit wide vectors available in the previous SSE vector units.

Although the ISA is intended to grease the wheels for third-party MIC software tools, the information can also be used by application developers who are looking to access MIC instruction directly via intrinsics (assembly instructions that can be inserted into high level source code). With the intrinsics, bare-metal programmers can tap directly into the hardware to eke out maximum performance.

Now that some of the software and supporting docs are in the public domain, Intel will be able to work more openly with MIC developers and third-party toolmakers. All of this should help to jumpstart the ecosystem in preparation for the upcoming Knights Corner launch, which is only about half a year away. At the International Supercomputing Conference (ISC’12) next week in Germany, we should get a much better sense of how far along Intel is with its MIC rollout.

Subscribe to HPCwire's Weekly Update!

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

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire