A 16 nm multi-core RISC-V SoC with custom Knuth-Yao sampling instructions, non-linear function interpolation, and direct neighbor-core register access, plus a spatial mapping compiler, for MCMC approximate inference.
Accelerating markov random field inference with uncertainty quantification,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AIA: A Customized Multi-core RISC-V SoC for Discrete Sampling Workloads in 16 nm
A 16 nm multi-core RISC-V SoC with custom Knuth-Yao sampling instructions, non-linear function interpolation, and direct neighbor-core register access, plus a spatial mapping compiler, for MCMC approximate inference.