Cutting Edge Analytics

Xeon Phi – Consulting & Advisory

Xeon Phi is a main/co-processor accelerator from Intel. If features 512-bit wide vector instructions, up to 68 cores, and can yield large performance gains. Programming the Xeon Phi is challenging and requires specialized knowledge.

Model Generation Launch Cores Threads Clock SIMD Width Memory Cache (L2) Memory B/W
Xeon Phi 7120 Knights Corner Q2 2014 61 244 1.238GHz 512bits 16GB 30.5MB 352GB/s
Xeon Phi 7210 Knights Landing Q2 2016 64 256 1.3GHz 512bits max. 384GB 32MB 102GB/s
Xeon Phi 7230 Knights Landing Q2 2016 64 256 1.3GHz 512bits max. 384GB 32MB 115.2GB/s
Xeon Phi 7250 Knights Landing Q2 2016 68 272 1.4GHz 512bits max. 384GB 34MB 115.2GB/s

Xcelerit team of expert Xeon Phi programmers can help you tackle the most challenging acceleration project. From initial Xeon Phi code migration, to advanced performance tuning of existing Xeon Phi code.

Xcelerit has developed a unique workflow to help clients accelerate large code bases, while achieving massive performance gains and controlling the memory footprint.

Whitepaper: A Guide to Xeon Phi Code Acceleration

Even though just recompiling x86 code will generate executables that can run on the Xeon Phi, the resulting binary is far from optimal. The code has to be optimised for 60+ cores, wider vector units, simpler cache hierarchy and more. This white paper discusses the challenges involved when developing code for Xeon Phi and give practical guides on how to maximise performance.

  • Xeon Phi features
  • Native and offload modes
  • Thread scalability
  • Vectorisation: Automatic and manual
  • Memory organisation and cache efficiency
  • This field is for validation purposes and should be left unchanged.

Accelerate your code with Xeon Phi

  • This field is for validation purposes and should be left unchanged.
  • Code analysis and profiling
  • Xeon Phi code migration
  • CPU / Xeon Phi code portability
  • Multi-threading, vectorisation, cache-blocking
  • Advanced performance optimisation
  • Memory tuning
  • Detailed optimisation report
  • C/C++, Java, C#, Fortran

About Xcelerit

Xcelerit is a leading provider of acceleration solutions for Quantitative Finance, engineering, and research. Our portfolio of solutions addresses a range of acceleration challenges from algorithmic optimisations to software acceleration. Xcelerit is the maker of the award-winning toolkit that allows domain-specialists to unlock the performance of accelerators (GPUs and Xeon Phi), and optimally deploy the advanced features of conventional multi-core processors. All of this is achieved with minor modifications to the existing source code.

Xcelerit extensive experience enables the firm to deliver a full solution from expert consultancy, bespoke development, training, and software acceleration. Our distinct competitive advantage derives from our unique combination of domain specialist knowledge and High Performance Computing expertise. This allows us to forge the most efficient solutions to better address our clients’ computational challenges.

Xcelerit has received recognition as a finalist in the Red Herring Europe Top 100 award, the Red Herring Top 100 Global award, and a two-time winner of HPC Wire’s “Best use of High Performance Computing in Financial Services” award. Our satisfied customers include the leading firms in investment banking, asset management, and insurance.

top