On GH200, hybrid CPU-GPU splits and managed memory become competitive for sparse conjugate gradient in more cases than on H100 PCIe, though with notable memory-mode outliers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Preliminary Study on Simultaneous Coscheduling for Discrete GPU vs. Fused GPU
On GH200, hybrid CPU-GPU splits and managed memory become competitive for sparse conjugate gradient in more cases than on H100 PCIe, though with notable memory-mode outliers.