Applying Vectorisation to CVA Aggregation
New challenges in the financial markets driven by changes in market structure, regulations and accounting rules like Basel III, EMIR, Dodd Frank, MiFID II, Solvency II, IFRS 13, IRFS 9 and FRTB have increased demand for higher performance risk and analytics. Problems like XVA can be extremely computationally expensive to solve accurately. This demand for higher performance has put a focus on how to get the most out of the latest generation of hardware.

Co-hosted by Quantifi & Intel


  • What is vectorisation?
  • The rise of parallelism
  • What kind of problems can be vectorised?
  • Implementation challenges: Intel’s 6 step program
  • Applying vectorisation to CVA aggregation


  • Jamie Elliot, Development Manager, Risk Architecture, Quantifi
  • Evgueny Khartchenko, Senior Software Application Engineer, Intel


Navigate major trends & developments shaping the industry


A First View on the New CVA Risk Capital Charge

The impact of the new CVA risk regulation framework on calculation methods and the infrastructure of banks could potentially be the turning point for many of the medium-sized institutes we are seeing in the market.


Comparing Alternate Methods for Calculating CVA Capital Charges Under Basel III

There are two ways for banks to compute CVA VaR, standardised and advanced methods, depending on their current regulatory approval. Furthermore, firms can potentially reduce the capital charges via eligible hedges.


CVA, DVA and Bank Earnings

Credit Value Adjustment (CVA) is the amount subtracted from the mark-to-market (MTM) value of derivative positions to account for the expected loss due to counterparty defaults. CVA is easy to understand in the context of a loan – it is the loan principal, minus anticipated recovery, multiplied by the counterparty’s default probability over the term of the loan. For derivatives, the loan amount is the net MTM value of derivative positions with that counterparty.

Let's Talk!

Schedule a personalised demo today