2 papers
cs.PL2026
Hexagon-MLIR: An AI Compilation Stack For Qualcomm's Neural Processing Units (NPUs)
Mohammed Javed Absar, Muthu Baskaran, Abhikrant Sharma +22
In this paper, we present Hexagon-MLIR,an open-source compilation stack that targets Qualcomm Hexagon Neural Processing Unit (NPU) and provides unified support for lowering Triton…
cs.PL2026
Analyzing Latency Hiding and Parallelism in an MLIR-based AI Kernel Compiler
Javed Absar, Samarth Narang, Muthu Baskaran
AI kernel compilation for edge devices depends on the compiler's ability to exploit parallelism and hide memory latency in the presence of hierarchical memory and explicit data mov…