On a 64-core RISC-V chip, FFTW with MPI scales to 64 cores, OpenMP needs measured planning, and x86-64 remains about 8 times faster for a double-precision 2D FFT.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Parallel FFTW on RISC-V: A Comparative Study including OpenMP, MPI, and HPX
On a 64-core RISC-V chip, FFTW with MPI scales to 64 cores, OpenMP needs measured planning, and x86-64 remains about 8 times faster for a double-precision 2D FFT.