VTC eliminates unnecessary data movement in DNN compilation using virtual tensors tracked by index mappings, achieving up to 1.93x speedup and 60% memory savings on NVIDIA GPUs.
Welder: Scheduling deep learning memory access via tile-graph
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VTC: DNN Compilation with Virtual Tensors for Data Movement Elimination
VTC eliminates unnecessary data movement in DNN compilation using virtual tensors tracked by index mappings, achieving up to 1.93x speedup and 60% memory savings on NVIDIA GPUs.