MartaAndronic / PolyLUTLinks
PolyLUT is the first quantized neural network training methodology that maps a neuron to a LUT while using multivariate polynomial function learning to exploit the flexibility of the FPGA soft logic.
☆54Updated last year
Alternatives and similar repositories for PolyLUT
Users that are interested in PolyLUT are comparing it to the libraries listed below
Sorting:
- NeuraLUT: Hiding Neural Network Density in Boolean Synthesizable Functions☆37Updated 3 months ago
- Implementation of Microscaling data formats in SystemVerilog.☆21Updated last week
- A collection of tutorials for the fpgaConvNet framework.☆42Updated 9 months ago
- ☆58Updated 5 years ago
- CHARM: Composing Heterogeneous Accelerators on Heterogeneous SoC Architecture☆147Updated this week
- Multi-core HW accelerator mapping optimization framework for layer-fused ML workloads.☆54Updated last week
- An FPGA accelerator for general-purpose Sparse-Matrix Dense-Matrix Multiplication (SpMM).☆80Updated 11 months ago
- ☆71Updated 2 years ago
- An Open Workflow to Build Custom SoCs and run Deep Models at the Edge☆85Updated last month
- ☆27Updated 3 months ago
- ☆35Updated 3 months ago
- Quantized ResNet50 Dataflow Acceleration on Alveo, with PYNQ☆58Updated 3 years ago
- Open-source of MSD framework☆16Updated last year
- An HLS based winograd systolic CNN accelerator☆53Updated 3 years ago
- A systolic array simulator for multi-cycle MACs and varying-byte words, with the paper accepted to HPCA 2022.☆79Updated 3 years ago
- HLS implemented systolic array structure☆41Updated 7 years ago
- RTL implementation of Flex-DPE.☆106Updated 5 years ago
- ☆44Updated 2 years ago
- A framework for fast exploration of the depth-first scheduling space for DNN accelerators☆39Updated 2 years ago
- Train and deploy LUT-based neural networks on FPGAs☆97Updated last year
- SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration (Full Paper Accepted in FPGA'24)☆32Updated this week
- FPGA-based hardware accelerator for Vision Transformer (ViT), with Hybrid-Grained Pipeline.☆73Updated 5 months ago
- FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations☆94Updated 3 years ago
- Verilog implementation of Softmax function☆67Updated 2 years ago
- HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators☆151Updated last week
- A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching☆54Updated 3 months ago
- An FPGA Accelerator for Transformer Inference☆85Updated 3 years ago
- ☆30Updated 8 months ago
- SAMO: Streaming Architecture Mapping Optimisation☆33Updated last year
- [TCAD'23] AccelTran: A Sparsity-Aware Accelerator for Transformers☆49Updated last year