Affiliation:
1. Technical University of Cluj-Napoca, Romania
2. LIP, projet Arénaire, ENS de Lyon, Lyon Cedex, France
Abstract
The implementation of high-precision floating-point applications on reconfigurable hardware requires large multipliers. Full multipliers are the core of floating-point multipliers. Truncated multipliers, trading resources for a well-controlled accuracy degradation, are useful building blocks in situations where a full multiplier is not needed.
This work studies the automated generation of such multipliers using the embedded multipliers and adders present in the DSP blocks of current FPGAs. The optimization of such multipliers is expressed as a tiling problem, where a tile represents a hardware multiplier, and super-tiles represent combinations of several hardware multipliers and adders, making efficient use of the DSP internal resources. This tiling technique is shown to adapt to full or truncated multipliers. It addresses arbitrary precisions including single, double but also the quadruple precision introduced by the IEEE-754-2008 standard and currently unsupported by processor hardware. An open-source implementation is provided in the FloPoCo project.
Publisher
Association for Computing Machinery (ACM)
Reference17 articles.
1. ISE 11.4 CORE Generator IP. ISE 11.4 CORE Generator IP.
2. MegaWizard Plug-In Manager. MegaWizard Plug-In Manager.
3. Large multipliers with fewer DSP blocks
Cited by
30 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. High Performance and Energy Efficient Floating-Point Multiplier on FPGA;2023 IEEE 3rd International Conference on Computer Systems (ICCS);2023-09-22
2. Towards Globally Optimal Design of Multipliers for FPGAs;IEEE Transactions on Computers;2023-05-01
3. Resource Optimal Squarers for FPGAs;2022 32nd International Conference on Field-Programmable Logic and Applications (FPL);2022-08
4. Resource Optimal Truncated Multipliers for FPGAs;2021 IEEE 28th Symposium on Computer Arithmetic (ARITH);2021-06
5. Folded Integer Multiplication for FPGAs;The 2021 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays;2021-02-17