IPRC-ICT / Heron
Heron: Automatically Constrained High-Performance Library Generation for Deep Learning Accelerators
☆15Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for Heron
- Automatic Mapping Generation, Verification, and Exploration for ISA-based Spatial Accelerators☆102Updated 2 years ago
- agile hardware-software co-design☆44Updated 2 years ago
- A scheduler for spatial DNN accelerators that generate high-performance schedules in one shot using mixed integer programming (MIP)☆74Updated last year
- ☆14Updated 3 years ago
- EQueue Dialect☆39Updated 2 years ago
- TileFlow is a performance analysis tool based on Timeloop for fusion dataflows☆55Updated 7 months ago
- ☆25Updated 3 years ago
- STONNE Simulator integrated into SST Simulator☆17Updated 7 months ago
- ☆36Updated 7 months ago
- ☆10Updated 9 months ago
- DietCode Code Release☆61Updated 2 years ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆43Updated 5 months ago
- A hardware synthesis framework with multi-level paradigm☆35Updated last year
- ArchExplorer: Microarchitecture Exploration Via Bottleneck Analysis☆30Updated 8 months ago
- Artifact repository for paper Automatic Generation of High-Performance Quantized Machine Learning Kernels☆17Updated 4 years ago
- OSDI 2023 Welder, deeplearning compiler☆16Updated 11 months ago
- Bridging polyhedral analysis tools to the MLIR framework☆102Updated last year
- ☆27Updated 3 months ago
- ☆10Updated last month
- Stencil with Optimized Dataflow Architecture Compiler☆16Updated 4 years ago
- An MLIR dialect to enable the efficient acceleration of ML model on CGRAs.☆53Updated last month
- Domain-Specific Architecture Generator 2☆20Updated 2 years ago
- ☆36Updated 7 months ago
- An analytical framework that models hardware dataflow of tensor applications on spatial architectures using the relation-centric notation…☆80Updated 6 months ago
- GNNear: Accelerating Full-Batch Training of Graph NeuralNetworks with Near-Memory Processing☆13Updated 2 years ago
- The Artifact of NeoMem: Hardware/Software Co-Design for CXL-Native Memory Tiering☆27Updated 3 months ago
- ☆83Updated 4 months ago
- HeteroCL-MLIR dialect for accelerator design☆40Updated last month
- Polyhedral High-Level Synthesis in MLIR☆29Updated last year
- ☆32Updated 2 years ago