Not to be confused with the ATI Xenos, Xenon or Xeon.
Xeon Phi
Xeon Phi 5100 without heatsink
General information
Launched
2010
Discontinued
2020[1]
Marketed by
Intel
Designed by
Intel
Common manufacturer(s)
Intel
Performance
Max. CPU clock rate
1.053 GHz to 1.7 GHz
Cache
L1 cache
32 KB per core
L2 cache
512 KB per core
Architecture and classification
Application
Supercomputers High-performance computing
Technology node
45 nm transistors to 14 nm transistors (tri-gate)
Microarchitecture
Larrabee
Instruction set
IA-32, x86-64[2]
Extensions
AVX, AVX2, AVX-512
Physical specifications
Cores
32-72
Memory (RAM)
Up to 384 GB and 16 GB
Up to DDR4 115.4 GB/s with ECC support
MCDRAM 400+ GB/s
Socket(s)
LGA 3647
PCI Express 3.0 x16
Products, models, variants
Core name(s)
Knights Ferry
Knights Corner
Knights Landing
Knights Mill
Knights Hill
Model(s)
Xeon Phi 3100
Xeon Phi 5100
Xeon Phi 7100
Xeon Phi 7200
Xeon Phi[3] is a discontinued series of x86 manycore processors designed and made by Intel. It was intended for use in supercomputers, servers, and high-end workstations. Its architecture allowed use of standard programming languages and application programming interfaces (APIs) such as OpenMP.[4][5]
Xeon Phi launched in 2010. Since it was originally based on an earlier GPU design (codenamed "Larrabee") by Intel[6] that was cancelled in 2009,[7] it shared application areas with GPUs. The main difference between Xeon Phi and a GPGPU like Nvidia Tesla was that Xeon Phi, with an x86-compatible core, could, with less modification, run software that was originally targeted to a standard x86 CPU.
Initially in the form of PCI Express-based add-on cards, a second-generation product, codenamed Knights Landing, was announced in June 2013.[8] These second-generation chips could be used as a standalone CPU, rather than just as an add-in card.
The Tianhe-2 supercomputer uses Xeon Phi processors.
In June 2013, the Tianhe-2 supercomputer at the National Supercomputer Center in Guangzhou (NSCC-GZ) was announced[9] as the world's fastest supercomputer (as of June 2023[update], it is No. 10[10]). It used Intel Xeon Phi coprocessors and Ivy Bridge-EP Xeon E5 v2 processors to achieve 33.86 petaFLOPS.[11]
The Xeon Phi product line directly competed with Nvidia's Tesla and AMD Radeon Instinct lines of deep learning and GPGPU cards. It was discontinued due to a lack of demand and Intel's problems with its 10nm node.[12]
^Ian Cutress & Anton Shilov (7 May 2019). "The Larrabee Chapter Closes: Intel's Final Xeon Phi Processors Now in EOL". Retrieved 12 March 2020.
^"Intel® Xeon Phi™ Coprocessor System Software Developers Guide" (PDF). Intel. 8 November 2012. p. 16. Archived (PDF) from the original on 21 April 2024. Retrieved 1 May 2024.
^Cite error: The named reference IntelXeonPhiName was invoked but never defined (see the help page).
^robert-reed (4 February 2013). "Best Known Methods for Using OpenMP on Intel Many Integrated Core (Intel MIC) Architecture". software.intel.com.
^Jeffers, James; Reinders, James (1 March 2013). Intel Xeon Phi Coprocessor High Performance Programming. Morgan Kaufmann. ISBN 978-0124104143.
^Hruska, Joel (8 May 2019). "Intel Quietly Kills Off Xeon Phi". ExtremeTech.
^"Intel scraps graphics chip based on Larrabee". Reuters. 6 December 2009.
^"Intel Powers the World's Fastest Supercomputer, Reveals New and Future High Performance Computing Technologies". Retrieved 21 June 2013.
^W1zzard (24 July 2018). "Intel is Giving up on Xeon Phi - Eight More Models Declared End-Of-Life". TechPowerUp.{{cite web}}: CS1 maint: numeric names: authors list (link)
XeonPhi is a discontinued series of x86 manycore processors designed and made by Intel. It was intended for use in supercomputers, servers, and high-end...
Xeon, the design point of the XeonPhi emphasizes more cores with higher memory bandwidth. The first Xeon-branded processor was the Pentium II Xeon (code-named...
is an Intel microprocessor compatible socket used by XeonPhi x200 ("Knights Landing"), XeonPhi 72x5 ("Knights Mill"), Skylake-SP, Cascade Lake-SP, and...
also been used, modified, in the Knight's Landing iteration of Intel's XeonPhi HPC chips. Silvermont was the first Atom processor to feature an out-of-order...
Nvidia Tesla product line competed with AMD's Radeon Instinct and Intel XeonPhi lines of deep learning and GPU cards. Nvidia retired the Tesla brand in...
manufactured by Cray. It consists of Intel Haswell Xeon processors, with optional Nvidia Tesla or Intel XeonPhi accelerators, connected together by Cray's proprietary...
engine. Linaro DDT also supports coprocessor architectures such as Intel XeonPhi coprocessors and Nvidia CUDA GPUs. It is part of Linaro Forge - a suite...
implemented by the Knights Corner XeonPhi processors, and the AVX-512 instructions implemented by the Knights Landing XeonPhi processors and by Skylake-X...
submitted benchmark was run using 1875 nodes with XeonPhi coprocessors and 3900 nodes without XeonPhi coprocessors. For the June 2013 Top500 list, the...
listed in the Intel SDM as removed from 2023 onwards. The first generation XeonPhi processors, codenamed "Knights Corner" (KNC), supported a large number...
with more than 128 logical processors in a single package (e.g. Intel XeonPhi 7290 and AMD Threadripper Pro 7995WX) the value in bit 23:16 is set to...
and newer ones use 2-way SMT (with dual-domain multithreading). Intel XeonPhi has 4-way SMT (with time-multiplexed multithreading) with hardware-based...
canceling it in 2009; this time, the technology developed was used in the XeonPhi, which was discontinued in 2020. In April 2018, it was reported that Intel...
XeonPhi processors support four-way hyper-threading, effectively quadrupling the number of threads. Before the Coffee Lake architecture, most Xeon and...
processing capabilities of many-core architectures (such as GPUs or the Intel XeonPhi) have produced significant speedups in training, because of the suitability...
Processing Unit for the Microsoft HoloLens. In 2012, Intel announced the Intel XeonPhi coprocessor. As of 2016[update], various companies are developing coprocessors...
with Threaded Applications". software.intel.com. June 1, 2017. "Intel® XeonPhi™ Delivers Competitive Performance For Deep Learning—And Getting Better...
Instinct product line directly competes with Nvidia's Tesla and Intel's XeonPhi and Data Center GPU lines of machine learning and GPGPU cards. The brand...
of the Fortran 2003 standard. IA-32 x86-64 (Intel 64 and AMD64) Intel XeonPhi coprocessor IA-64 (Itanium 2) Xe architecture The compilers are available...
Global Information
