DeepWok / mase
Machine-Learning Accelerator System Exploration Tools
☆115Updated this week
Related projects: ⓘ
- Allo: A Programming Model for Composable Accelerator Design☆122Updated this week
- ☆38Updated last week
- An MLIR dialect to enable the efficient acceleration of ML model on CGRAs.☆51Updated 2 weeks ago
- HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators☆99Updated last week
- EQueue Dialect☆38Updated 2 years ago
- Multi-core HW accelerator mapping optimization framework for layer-fused ML workloads.☆34Updated this week
- A DSL for Systolic Arrays☆73Updated 5 years ago
- An open-source parameterizable NPU generator with full-stack multi-target compilation stack for intelligent workloads.☆20Updated 5 months ago
- A dataflow architecture for universal graph neural network inference via multi-queue streaming.☆65Updated last year
- An FPGA accelerator for general-purpose Sparse-Matrix Dense-Matrix Multiplication (SpMM).☆62Updated last month
- A Spatial Accelerator Generation Framework for Tensor Algebra.☆48Updated 2 years ago
- PyTorch model to RTL flow for low latency inference☆118Updated 6 months ago
- Torch2Chip (MLSys, 2024)☆49Updated 3 weeks ago
- AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP (Full Paper a…☆19Updated last month
- ACM TODAES Best Paper Award, 2022☆23Updated 10 months ago
- CHARM: Composing Heterogeneous Accelerators on Versal ACAP Architecture☆119Updated last month
- ☆33Updated 6 months ago
- CGRA-Flow is an integrated framework for CGRA compilation, exploration, synthesis, and development.☆102Updated last week
- PyLog: An Algorithm-Centric FPGA Programming and Synthesis Flow☆59Updated last year
- SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration (Full Paper Accepted in FPGA'24)☆23Updated last month
- Implementations of Buffets, which are efficient, composable idioms for implementing Explicit Decoupled Data Orchestration.☆62Updated 5 years ago
- A scheduler for spatial DNN accelerators that generate high-performance schedules in one shot using mixed integer programming (MIP)☆73Updated last year
- Verilog evaluation benchmark for large language model☆158Updated 3 weeks ago
- A fast, accurate trace-based simulator for High-Level Synthesis.☆31Updated 4 months ago
- An Optimizing Framework on MLIR for Efficient FPGA-based Accelerator Generation☆21Updated 5 months ago
- CIRCT-based HLS compilation flows, debugging, and cosimulation tools.☆43Updated last year
- High-Performance Sparse Linear Algebra on HBM-Equipped FPGAs Using HLS☆77Updated last month
- ☆32Updated 2 months ago
- RapidStream-TAPA compiles task-parallel HLS program into high-frequency FPGA accelerators.☆149Updated last week
- RTL implementation of Flex-DPE.☆84Updated 4 years ago