Abstract | ||
---|---|---|
Mixed-precision computing offers potential data size reduction and performance improvement at the cost of accuracy, a tradeoff that many practitioners in high-performance computing and related fields are becoming more interested in as workloads become increasingly communication-bound. However, it can be difficult to build valid mixed-precision configurations and navigate the performance/accuracy space without the help of automated tools. We present FloatSmith, an open-source, end-to-end source-level mixed-precision tuner that incorporates several software tools (CRAFT, TypeForge, and ADAPT) into an integrated tool chain. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/Correctness49594.2019.00009 | 2019 IEEE/ACM 3rd International Workshop on Software Correctness for HPC Applications (Correctness) |
Keywords | DocType | ISBN |
Floating-point arithmetic,mixed precision,program analysis,code transformation,tool integration | Conference | 978-1-7281-6016-0 |
Citations | PageRank | References |
1 | 0.35 | 14 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael O. Lam | 1 | 50 | 5.15 |
Tristan Vanderbruggen | 2 | 1 | 1.36 |
Harshitha Menon | 3 | 49 | 6.89 |
Markus Schordan | 4 | 1 | 0.35 |