Complier Tool-chain Services
Inferencing of AI/ML models on the edge
Helprack has been developing AI/ML compilers for models written in TensorFlow, ONNX, PyTorch etc, to run on custom compute fabric for Edge Computing (Inferencing) for a couple of stealth mode startups in the AI/ML chip space
Translate ONNX operations to the custom dialect of MLIR
Helprack has been helping lower code from ONNX dialect of MLIR to a proprietary custom dialect that is targeted at large scale acceleration of ML training workloads
for a Bay Area Enterprise
Optimization using Vectorization
Helprack is working with a customer to implement vectorization in their GCC based compiler. This customer develops licensable processor IPs for media processing. Learn how Helprack is developing a vectorizing compiler for their variable length vector processing units
Performance Optimization
The Helprack team worked over a period of 10 months with this Semiconductor major to fix some performance issues in the LLVM compiler (Aarch64) with the GeekBench benchmark and a few other functional issues. The fixes were upstreamed to the LLVM community.
