charley871103 / TPULinks
AI Chip project
☆32Updated 3 years ago
Alternatives and similar repositories for TPU
Users that are interested in TPU are comparing it to the libraries listed below
Sorting:
- ☆39Updated 4 years ago
- IC implementation of TPU☆124Updated 5 years ago
- tpu-systolic-array-weight-stationary☆24Updated 4 years ago
- verilog实现TPU中的脉动阵列计算卷积的module☆118Updated last month
- ☆65Updated 6 years ago
- hardware design of universal NPU(CNN accelerator) for various convolution neural network☆128Updated 3 months ago
- SystemVerilog files for lab project on a DNN hardware accelerator☆16Updated 4 years ago
- AIChip 2021 project, NCKU☆18Updated 4 years ago
- Systolic array based simple TPU for CNN on PYNQ-Z2☆33Updated 3 years ago
- INT8 & FP16 multiplier accumulator (MAC) design with UVM verification completed.☆103Updated 4 years ago
- A Flexible and Energy Efficient Accelerator For Sparse Convolution Neural Network☆78Updated 4 months ago
- ☆112Updated 4 years ago
- 16-bit Adder Multiplier hardware on Digilent Basys 3☆76Updated last year
- 32 - bit floating point Multiplier Accumulator Unit (MAC)☆30Updated 4 years ago
- ☆34Updated 6 years ago
- Designing CNN accelerator using a Xilinx FPGA board and comparing performance with CPU.☆21Updated 4 years ago
- A DNN Accelerator implemented with RTL.☆64Updated 5 months ago
- CNN-Accelerator based on FPGA developed by verilog HDL.☆47Updated 5 years ago
- Convolutional Neural Network Implemented in Verilog for System on Chip☆27Updated 6 years ago
- A SystemVerilog implementation of Row-Stationary dataflow and Hierarchical Mesh Network-on-Chip Architecture based on Eyeriss CNN Acceler…☆162Updated 5 years ago
- ☆15Updated last year
- Convolution Neural Network of vgg19 model in verilog☆47Updated 7 years ago
- General CNN_Accelerator design.卷积神经网络加速器设计。在PYNQ-Z2 FPGA开发板上实现了卷积池化全连接层等硬件加速计算。☆54Updated 3 months ago
- Hardware accelerator for convolutional neural networks☆45Updated 2 years ago
- eyeriss-chisel3☆40Updated 3 years ago
- A VGG accelerator by System Verilog on DE1-SoC FPGA. Row Stationary (RS) dataflow is adopted, and computations are based on fixed point 1…☆34Updated 5 years ago
- High Level Synthesis of a trained Convolutional Neural Network for handwritten digit recongnition.☆39Updated 11 months ago
- A Verilog design of LeNet-5, a Convolutional Neural Network architecture☆34Updated 4 years ago
- ☆66Updated 3 years ago
- A verilog implementation for Network-on-Chip☆73Updated 7 years ago