Speaker
Description
IRONSmith: A Visual Dataflow Design Environment for AMD Ryzen AI NPUs
Brock Sorenson, Samer Ali, Curt Bansil, Aman Arora — Arizona State University
Machine learning inference increasingly relies on specialized hardware
accelerators for throughput and power efficiency. Neural Processing Units
(NPUs), such as the AMD Ryzen AI NPU, offer significant ML advantages over
CPUs and GPUs, but programming them requires deep expertise in specialized
frameworks. The AMD Ryzen AI NPU uses IRON Python and mlir-aie, a
tile-level spatial programming model requiring specification of inter-tile
dataflow buffers (ObjectFIFOs), runtime data transfers, and compute tile
kernel operations. Even experienced ML developers must invest substantial
time in hardware documentation and programming guides before mapping a
simple operation to the hardware.
We present IRONSmith, the first visual dataflow design environment for NPU
programming. IRONSmith provides an interactive canvas displaying the AMD
AIE tile grid as visually connected blocks, allowing users to design ML
dataflow applications by connecting tiles with wires representing ObjectFIFO
buffers, split/join patterns, broadcast connections, and DDR transfers
without writing code. Compute kernels are assigned from a pre-built library
and worker kernels are configured through structured property panels.
Structural design verification checks designs for disconnected dataflow, DMA
channel limit violations, and kernel argument mismatches before code
generation, providing actionable feedback that would otherwise only surface
as cryptic compiler or runtime failures. IRONSmith's backend pipeline
automatically translates the visual design into executable IRON Python,
handling structural completion, import resolution, and dependency management
automatically. Generated code executes directly on the AMD Ryzen AI NPU.
We demonstrate IRONSmith across ML designs of increasing complexity, from a
single-tile vector passthrough to multi-tile matrix operations to a complete
Multi-Layer Perceptron, all designed visually and successfully executed on
the AMD Ryzen AI NPU.
IRONSmith serves educators, students, ML researchers, and engineers by
bridging the gap between ML knowledge and NPU programming expertise,
widening access to hardware that is rapidly becoming standard across consumer
and enterprise devices. By bringing visual design principles to NPU
programming, IRONSmith lowers the barrier to entry in much the same way
that graphical development environments broadened access to software
development.
| Do you plan to submit a 4-page extended abstract on OpenReview (only for Presentations/Posters)? | Yes |
|---|