A SIMD abstraction of nonlinear programs plus condensed-space IPM enables GPU-only ACOPF solving with roughly 10x speedup over CPU baselines in the reported benchmarks.
Leveraging GPU batching for scalable nonlinear programming through massive lagrangian decomposition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accelerating Optimal Power Flow with GPUs: SIMD Abstraction of Nonlinear Programs and Condensed-Space Interior-Point Methods
A SIMD abstraction of nonlinear programs plus condensed-space IPM enables GPU-only ACOPF solving with roughly 10x speedup over CPU baselines in the reported benchmarks.