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.
☆55Updated last year
Alternatives and similar repositories for PolyLUT
Users that are interested in PolyLUT are comparing it to the libraries listed below
Sorting:
- NeuraLUT-Assemble☆46Updated 4 months ago
- ☆72Updated 2 years ago
- ☆64Updated 5 years ago
- A collection of tutorials for the fpgaConvNet framework.☆47Updated last year
- Quantized ResNet50 Dataflow Acceleration on Alveo, with PYNQ☆59Updated 4 years ago
- CHARM: Composing Heterogeneous Accelerators on Heterogeneous SoC Architecture☆162Updated this week
- An FPGA accelerator for general-purpose Sparse-Matrix Dense-Matrix Multiplication (SpMM).☆92Updated last year
- Implementation of Microscaling data formats in SystemVerilog.☆28Updated 5 months ago
- Train and deploy LUT-based neural networks on FPGAs☆105Updated last year
- FlexASR: A Reconfigurable Hardware Accelerator for Attention-based Seq-to-Seq Networks☆49Updated 9 months ago
- ☆31Updated 8 months ago
- An FPGA Accelerator for Transformer Inference☆92Updated 3 years ago
- SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration (Full Paper Accepted in FPGA'24)☆35Updated this week
- An HLS based winograd systolic CNN accelerator☆54Updated 4 years ago
- An Open Workflow to Build Custom SoCs and run Deep Models at the Edge☆100Updated last week
- ☆22Updated 3 years ago
- Library of approximate arithmetic circuits☆61Updated 3 years ago
- Multi-core HW accelerator mapping optimization framework for layer-fused ML workloads.☆64Updated 5 months ago
- HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators☆171Updated last month
- MaxEVA: Maximizing the Efficiency of Matrix Multiplication on Versal AI Engine (accepted as full paper at FPT'23)☆22Updated last year
- A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching☆73Updated last month
- FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations☆95Updated 4 years ago
- RTL implementation of Flex-DPE.☆115Updated 5 years ago
- ☆39Updated 8 months ago
- ☆35Updated 6 years ago
- Verilog implementation of Softmax function☆78Updated 3 years ago
- An LSTM template and a few examples using Vivado HLS☆46Updated last year
- Performance and resource models for fpgaConvNet: a Streaming-Architecture-based CNN Accelerator.☆30Updated last year
- TAPA compiles task-parallel HLS program into high-performance FPGA accelerators. UCLA-maintained.☆176Updated 4 months ago
- SAMO: Streaming Architecture Mapping Optimisation☆34Updated 2 years ago