Acceleration of Lattice Models for Pricing Portfolios of Fixed-Income Derivatives
This paper reports on the acceleration of a standard, lattice-based numerical algorithm that is widely used in finance for pricing a class of fixed-income vanilla derivatives. We start with a high-level algorithmic specification, exhibiting irregular-nested parallelism, which is challenging to map efficiently to GPU hardware. From it we systematically derive and optimize two CUDA implementations, which utilize only the outer or all levels of parallelism, respectively. A detailed evaluation demonstrates (i) the high impact of the proposed optimizations, (ii) the complementary strength and weaknesses of the two GPU versions, and that (iii) they are on average 2.4x faster than our well-tuned CPU-parallel implementation (OpenMP+AVX2) running on 104 hardware threads, and by 3-to-4 order of magnitude faster than an OpenMP-parallel implementation using the popular QuantLib library.
Mon 21 JunDisplayed time zone: Eastern Time (US & Canada) change
13:30 - 16:15 | Session 2 (keynote) and 3 (applications)ARRAY at ARRAY Chair(s): Aggelos Biboudis Swisscom AG, Sandra Catalán | ||
13:30 75mKeynote | Keynote: Tilting at Windmills with the Humble Array ARRAY Tim Mattson Intel, USA File Attached | ||
15:15 30mTalk | Array Languages Make Neural Networks Fast ARRAY Artjoms Šinkarovs Heriot-Watt University, UK, Hans-Nikolai Vießmann Radboud University Nijmegen, Netherlands, Sven-Bodo Scholz Radboud University | ||
15:45 30mTalk | Acceleration of Lattice Models for Pricing Portfolios of Fixed-Income Derivatives ARRAY Wojciech Michal Pawlak University of Copenhagen, Denmark, Marek Hlava Department of Computer Science, University of Copenhagen, Martin Metaksov Department of Computer Science, University of Copenhagen, Cosmin Oancea University of Copenhagen, Denmark |