Xeon Phi is a brand name given to a series of manycore processors designed, manufactured, marketed, and sold by Intel, targeted at supercomputing, enterprise, and high-end workstation markets. Intel's MIC (Many Integrated Core) architecture allows use of standard programming language APIs such as OpenMP.
Initially in the form of PCIe-based add-on cards, a second generation product, codenamed Knights Landing was announced in June 2013. These second generation chips could be used as a standalone CPU, not just as an add-in card.
In June 2013, the Tianhe-2 supercomputer at the National Supercomputing Center in Guangzhou (NSCC-GZ) was announced as the world's fastest supercomputer (As of November 2016, it is #2). It uses Intel Xeon Phi coprocessors and Ivy Bridge-EP Xeon processors to achieve 33.86Â petaFLOPS.
Competitors include Nvidia's Tesla-branded product lines.
History
Background
The Larrabee microarchitecture (in development since 2006) introduced very wide (512-bit) SIMD units to a x86 architecture based processor design, extended to a cache-coherent multiprocessor system connected via a ring bus to memory; each core was capable of four-way multithreading. Due to the design being intended for GPU as well as general purpose computing the Larrabee chips also included specialised hardware for texture sampling. The project to produce a retail GPU product directly from the Larrabee research project was terminated in May 2010.
Another contemporary Intel research project implementing x86 architecture on a many-multicore processor was the 'Single-chip Cloud Computer' (prototype introduced 2009), a design mimicking a cloud computing computer datacentre on a single chip with multiple independent cores: the prototype design included 48 cores per chip with hardware support for selective frequency and voltage control of cores to maximize energy efficiency, and incorporated a mesh network for interchip messaging. The design lacked cache-coherent cores and focused on principles that would allow the design to scale to many more cores.
The Teraflops Research Chip (prototype unveiled 2007) is an experimental 80-core chip with two floating point units per core, implementing a 96-bit VLIW architecture instead of the x86 architecture. The project investigated intercore communication methods, per-chip power management, and achieved 1.01Â TFLOPS at 3.16Â GHz consuming 62Â W of power.
Knights Ferry
Intel's MIC prototype board, named Knights Ferry, incorporating a processor codenamed Aubrey Isle was announced May 31, 2010. The product was stated to be a derivative of the Larrabee project and other Intel research including the Single-chip Cloud Computer.
The development product was offered as a PCIe card with 32 in-order cores at up to 1.2Â GHz with four threads per core, 2Â GB GDDR5 memory, and 8Â MB coherent L2 cache (256Â KB per core with 32Â KB L1 cache), and a power requirement of ~300Â W, built at a 45Â nm process. In the Aubrey Isle core a 1,024-bit ring bus (512-bit bi-directional) connects processors to main memory. Single board performance has exceeded 750Â GFLOPS. The prototype boards only support single precision floating point instructions.
Initial developers included CERN, Korea Institute of Science and Technology Information (KISTI) and Leibniz Supercomputing Centre. Hardware vendors for prototype boards included IBM, SGI, HP, Dell and others.
Knights Corner
The Knights Corner product line is made at a 22Â nm process size, using Intel's Tri-gate technology with more than 50 cores per chip, and is Intel's first many-cores commercial product.
In June 2011, SGI announced a partnership with Intel to use the MIC architecture in its high performance computing products. In September 2011, it was announced that the Texas Advanced Computing Center (TACC) will use Knights Corner cards in their 10Â petaFLOPS "Stampede" supercomputer, providing 8Â petaFLOPS of compute power. According to "Stampede: A Comprehensive Petascale Computing Environment" the "second generation Intel (Knights Landing) MICs will be added when they become available, increasing Stampede's aggregate peak performance to at least 15Â PetaFLOPS."
On November 15, 2011, Intel showed an early silicon version of a Knights Corner processor.
On June 5, 2012, Intel released open source software and documentation regarding Knights Corner.
On June 18, 2012, Intel announced at the 2012 Hamburg International Supercomputing Conference that Xeon Phi will be the brand name used for all products based on their Many Integrated Core architecture. In June 2012, Cray announced it would be offering 22Â nm 'Knight's Corner' chips (branded as 'Xeon Phi') as a co-processor in its 'Cascade' systems.
In June 2012, ScaleMP announced it will provide its virtualization software to allow using 'Knight's Corner' chips (branded as 'Xeon Phi') as main processor transparent extension. The virtualization software will allow 'Knight's Corner' to run legacy MMX/SSE code and access unlimited amount of (host) memory without need for code changes. An important component of the Intel Xeon Phi coprocessor’s core is its vector processing unit (VPU). The VPU features a novel 512-bit SIMD instruction set, officially known as Intel® Initial Many Core Instructions (Intel® IMCI). Thus, the VPU can execute 16 single-precision (SP) or 8 double-precision (DP) operations per cycle. The VPU also supports Fused Multiply-Add (FMA) instructions and hence can execute 32 SP or 16 DP floating point operations per cycle. It also provides support for integers. The VPU also features an Extended Math Unit (EMU) that can execute operations such as reciprocal, square root, and logarithm, thereby allowing these operations to be executed in a vector fashion with high bandwidth. The EMU operates by calculating polynomial approximations of these functions.
On November 12, 2012, Intel announced two Xeon Phi coprocessor families using the 22Â nm process size: the Xeon Phi 3100 and the Xeon Phi 5110P. The Xeon Phi 3100 will be capable of more than 1Â teraFLOPS of double precision floating point instructions with 240Â GB/sec memory bandwidth at 300Â W. The Xeon Phi 5110P will be capable of 1.01Â teraFLOPS of double precision floating point instructions with 320Â GB/sec memory bandwidth at 225Â W. The Xeon Phi 7120P will be capable of 1.2Â teraFLOPS of double precision floating point instructions with 352Â GB/sec memory bandwidth at 300Â W.
On June 17, 2013, the Tianhe-2 supercomputer was announced by TOP500 as the world's fastest. Tianhe-2 used Intel Ivy Bridge Xeon and Xeon Phi processors to achieve 33.86Â petaFLOPS. It was the fastest on the list for two and a half years, lastly in November 2015.
Design and programming
The cores of Knights Corner are based on a modified version of P54C design, used in the original Pentium. The basis of the Intel MIC architecture is to leverage x86 legacy by creating an x86-compatible multiprocessor architecture that can use existing parallelization software tools. Programming tools include OpenMP, OpenCL, Cilk/Cilk Plus and specialised versions of Intel's Fortran, C++ and math libraries.
Design elements inherited from the Larrabee project include x86 ISA, 4-way SMT per core, 512-bit SIMD units, 32 KB L1 instruction cache, 32 KB L1 data cache, coherent L2 cache (512 KB per core), and ultra-wide ring bus connecting processors and memory.
The Knights Corner instruction set documentation is available from Intel.
- Models
Knights Landing
Code name for the second generation MIC architecture product from Intel. Intel officially first revealed details of its second generation Intel Xeon Phi products on June 17, 2013. Intel said that the next generation of Intel MIC Architecture-based products will be available in two forms, as a coprocessor or a host processor (CPU), and be manufactured using Intel's 14 nm process technology. Knights Landing products will include integrated on-package memory for significantly higher memory bandwidth.
Knights Landing will be built using up to 72 Airmont (Atom) cores with four threads per core, using LGA 3647 socket supporting for up to 384 GB of "far" DDR4 RAM and 8â€"16 GB of stacked "near" 3D MCDRAM, a version of the Hybrid Memory Cube. Each core will have two 512-bit vector units and will support AVX-512 SIMD instructions, specifically the Intel AVX-512 Foundational Instructions (AVX-512F) with Intel AVX-512 Conflict Detection Instructions (AVX-512CD), Intel AVX-512 Exponential and Reciprocal Instructions (AVX-512ER), and Intel AVX-512 Prefetch Instructions (AVX-512PF).
The National Energy Research Scientific Computing Center announced that Phase 2 of its newest supercomputing system "Cori" would use Knights Landing Xeon Phi coprocessors.
On June 20, 2016, Intel launched the Intel Xeon Phi product family x200 based on the Knights Landing architecture, stressing its applicability to not just traditional simulation workloads, but also to machine learning. The model lineup announced at launch included only Xeon Phi of bootable form-factor, but two versions of it: standard processors and processors with integrated Intel Omni-Path architecture fabric. The latter is denoted by the suffix F in the model number. Integrated fabric is expected to provide better latency at a lower cost than discrete high-performance network cards.
On November 14, 2016, the 48th list of TOP500 contained 10 systems using Knights Landing platforms.
The PCIe based co-processor variant of Knight's Landing was never offered to the general market and was discontinued by August 2017.
- Models
All models can boost to their peak speeds, adding 200Â MHz to their base frequency when running just one or two cores. When running from 3 to the maximum number of cores, the chips can only boost 100Â MHz above the base frequency. All chips run high-AVX code at a frequency reduced by 200Â MHz.
Knights Hill
Knights Hill is the codename for the third-generation MIC architecture, for which Intel announced the first details at SC14. It will be manufactured in a 10Â nm process.
In April 2015, the United States Department of Energy announced that a supercomputer named Aurora will be deployed at Argonne National Laboratory based upon the "third-generation Intel Xeon Phi" processor.
Knights Mill
Knights Mill is Intel's codename for a Xeon Phi product specialized in deep learning. While little is known about Knights Mill yet, it has been announced that it will improve efficiency. It is also expected to support reduced variable precision which have been used to accelerate machine learning in other products, such as half-precision floating-point variables in Nvidia's Tesla.
Programming
An empirical performance and programmability study has been performed by researchers, in which the authors claim that achieving high performance with Xeon Phi still needs help from programmers and that merely relying on compilers with traditional programming models is still far from reality. However, research in various domains, such as life sciences, deep learning and computer-aided engineering demonstrated that exploiting both the thread- and SIMD-parallelism of Xeon Phi achieves significant speed-ups.
Competitors
- Nvidia Tesla, a direct competitor in the HPC market
- AMD Radeon Pro and AMD Radeon Instinct direct competitors in the HPC market
See also
- Texas Advanced Computing Center - "Stampede" supercomputer incorporates Xeon Phi chips. Stampede is capable of 10Â petaFLOPS.
- AVX-512
- Cell (microprocessor)
- Intel Tera-Scale
References
External links
- Intel pages: Xeon Phi Product Family
- Hazra, Raj (June 18, 2012), "Intel® Xeon® Phi™ coprocessors accelerate the pace of discovery and innovation", blogs.intel.com,
Today, with the announcement of Intel® Xeon® Phi™ coprocessors, we’re going to accelerate the pace of these discoveries and innovations. Intel® Xeon Phi products extend the Intel® Xeon® brand..
 - Intel teaches Xeon Phi x86 coprocessor snappy new tricks