Presents scalable packed layouts and extensions to tiling/fusion/vectorization in MLIR/IREE for VLA ML code generation on Arm SVE, achieving up to 1.45x speedup over NEON and outperforming PyTorch frameworks.
N., Haxel, F., and Bringmann, O.Tensor program optimization for the risc-v vector extension using probabilistic programs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.PF 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Scalable Packed Layouts for Vector-Length-Agnostic ML Code Generation
Presents scalable packed layouts and extensions to tiling/fusion/vectorization in MLIR/IREE for VLA ML code generation on Arm SVE, achieving up to 1.45x speedup over NEON and outperforming PyTorch frameworks.