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 industy updates delivered to you every week!

China Plans 2019 Exascale Machine To Grow Sea Power

August 23, 2017

The glory of having the world's fastest supercomputer, as measured by the Linpack benchmark, has been China's for four years running, first with the 33-petaflops Tianhe-2 and currently with the 93-petaflops TaihuLight. T Read more…

By Tiffany Trader

Microsoft, Intel Unveil FPGA-driven Project Brainwave

August 23, 2017

We know about the seeming light-speed processing power of FPGAs and the natural fit they pose for data-dense AI workloads. But we also know that FPGAs present usability and programmability problems that flummox IT shops. Read more…

By Doug Black

Study Identifies Best Practices for Public-Private HPC Engagement

August 22, 2017

What's the best way for HPC centers in the public sphere to engage with private industry partners to boost the competitiveness of the companies and the larger communities? That question is at the heart of a new study pub Read more…

By Tiffany Trader

HPE Extreme Performance Solutions

Leveraging Deep Learning for Fraud Detection

Advancements in computing technologies and the expanding use of e-commerce platforms have dramatically increased the risk of fraud for financial services companies and their customers. Read more…

Google Launches Site to Share its NYC-based Algorithm Research

August 22, 2017

Much of Google’s algorithm development occurs in groups scattered throughout New York City. Yesterday, Google launched a single website - NYC Algorithms and Optimization Team page - to provide a deeper view into all of Read more…

By John Russell

China Plans 2019 Exascale Machine To Grow Sea Power

August 23, 2017

The glory of having the world's fastest supercomputer, as measured by the Linpack benchmark, has been China's for four years running, first with the 33-petaflop Read more…

By Tiffany Trader

Microsoft, Intel Unveil FPGA-driven Project Brainwave

August 23, 2017

We know about the seeming light-speed processing power of FPGAs and the natural fit they pose for data-dense AI workloads. But we also know that FPGAs present u Read more…

By Doug Black

Study Identifies Best Practices for Public-Private HPC Engagement

August 22, 2017

What's the best way for HPC centers in the public sphere to engage with private industry partners to boost the competitiveness of the companies and the larger c Read more…

By Tiffany Trader

Tech Giants Outline Battle Plans for Future HPC Market

August 21, 2017

Four companies engaged in a cage fight for leadership in the emerging HPC market of the 2020s are, despite deep differences in some areas, in violent agreement Read more…

By Doug Black

Microsoft Bolsters Azure With Cloud HPC Deal

August 15, 2017

Microsoft has acquired cloud computing software vendor Cycle Computing in a move designed to bring orchestration tools along with high-end computing access capabilities to the cloud. Terms of the acquisition were not disclosed. Read more…

By George Leopold

HPE Ships Supercomputer to Space Station, Final Destination Mars

August 14, 2017

With a manned mission to Mars on the horizon, the demand for space-based supercomputing is at hand. Today HPE and NASA sent the first off-the-shelf HPC system i Read more…

By Tiffany Trader

AMD EPYC Video Takes Aim at Intel’s Broadwell

August 14, 2017

Let the benchmarking begin. Last week, AMD posted a YouTube video in which one of its EPYC-based systems outperformed a ‘comparable’ Intel Broadwell-based s Read more…

By John Russell

Deep Learning Thrives in Cancer Moonshot

August 8, 2017

The U.S. War on Cancer, certainly a worthy cause, is a collection of programs stretching back more than 40 years and abiding under many banners. The latest is t Read more…

By John Russell

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Nvidia’s Mammoth Volta GPU Aims High for AI, HPC

May 10, 2017

At Nvidia's GPU Technology Conference (GTC17) in San Jose, Calif., this morning, CEO Jensen Huang announced the company's much-anticipated Volta architecture a Read more…

By Tiffany Trader

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

Russian Researchers Claim First Quantum-Safe Blockchain

May 25, 2017

The Russian Quantum Center today announced it has overcome the threat of quantum cryptography by creating the first quantum-safe blockchain, securing cryptocurrencies like Bitcoin, along with classified government communications and other sensitive digital transfers. Read more…

By Doug Black

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Just how close real-wo Read more…

By John Russell

Google Debuts TPU v2 and will Add to Google Cloud

May 25, 2017

Not long after stirring attention in the deep learning/AI community by revealing the details of its Tensor Processing Unit (TPU), Google last week announced the Read more…

By John Russell

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money

April 24, 2017

CPUs and GPUs, move over. Thanks to recent revelations surrounding Google’s new Tensor Processing Unit (TPU), the computing world appears to be on the cusp of Read more…

By Alex Woodie

Leading Solution Providers

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its a Read more…

By Tiffany Trader

Six Exascale PathForward Vendors Selected; DoE Providing $258M

June 15, 2017

The much-anticipated PathForward awards for hardware R&D in support of the Exascale Computing Project were announced today with six vendors selected – AMD Read more…

By John Russell

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the cam Read more…

By John Russell

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

In this contributed perspective piece, Intel’s Jim Jeffers makes the case that CPU-based visualization is now widely adopted and as such is no longer a contrarian view, but is rather an exascale requirement. Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

Top500 Results: Latest List Trends and What’s in Store

June 19, 2017

Greetings from Frankfurt and the 2017 International Supercomputing Conference where the latest Top500 list has just been revealed. Although there were no major Read more…

By Tiffany Trader

IBM Clears Path to 5nm with Silicon Nanosheets

June 5, 2017

Two years since announcing the industry’s first 7nm node test chip, IBM and its research alliance partners GlobalFoundries and Samsung have developed a proces Read more…

By Tiffany Trader

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

Singularity HPC Container Technology Moves Out of the Lab

May 4, 2017

Last week, Singularity – the fast-growing HPC container technology whose development has been spearheaded by Gregory Kurtzer at Lawrence Berkeley National Lab Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Share This