maestro-project / maestro
An analytical cost model evaluating DNN mappings (dataflows and tiling).
☆209Updated 10 months ago
Alternatives and similar repositories for maestro:
Users that are interested in maestro are comparing it to the libraries listed below
- Repository to host and maintain scale-sim-v2 code☆270Updated this week
- Accelergy is an energy estimation infrastructure for accelerator energy estimations☆134Updated 2 weeks ago
- STONNE: A Simulation Tool for Neural Networks Engines☆125Updated 9 months ago
- RTL implementation of Flex-DPE.☆98Updated 5 years ago
- HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators☆135Updated 2 weeks ago
- SMAUG: Simulating Machine Learning Applications Using Gem5-Aladdin☆105Updated 2 years ago
- Tool for optimize CNN blocking☆93Updated 4 years ago
- AutoSA: Polyhedral-Based Systolic Array Compiler☆212Updated 2 years ago
- End-to-end SoC simulation: integrating the gem5 system simulator with the Aladdin accelerator simulator.☆229Updated 2 years ago
- A pre-RTL, power-performance model for fixed-function accelerators☆173Updated last year
- Simulator for BitFusion☆96Updated 4 years ago
- Explore the energy-efficient dataflow scheduling for neural networks.☆220Updated 4 years ago
- Timeloop performs modeling, mapping and code-generation for tensor algebra workloads on various accelerator architectures.☆368Updated this week
- ☆345Updated last year
- The framework for the paper "Inter-layer Scheduling Space Definition and Exploration for Tiled Accelerators" in ISCA 2023.☆62Updated this week
- Processing-In-Memory (PIM) Simulator☆151Updated 3 months ago
- PIMSim is a Process-In-Memory Simulator with the compatibility of GEM5 full-system simulation.☆193Updated last year
- An analytical framework that models hardware dataflow of tensor applications on spatial architectures using the relation-centric notation…☆83Updated 10 months ago
- ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference☆94Updated last month
- CHARM: Composing Heterogeneous Accelerators on Heterogeneous SoC Architecture☆130Updated 2 months ago
- ☆64Updated last month
- A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching☆46Updated 5 months ago
- An FPGA accelerator for general-purpose Sparse-Matrix Dense-Matrix Multiplication (SpMM).☆77Updated 7 months ago
- A dataflow architecture for universal graph neural network inference via multi-queue streaming.☆71Updated 2 years ago
- A Fast DNN Accelerator Design Space Exploration Framework.☆46Updated 2 years ago
- Implementations of Buffets, which are efficient, composable idioms for implementing Explicit Decoupled Data Orchestration.☆68Updated 5 years ago
- A framework for fast exploration of the depth-first scheduling space for DNN accelerators☆37Updated 2 years ago
- ☆39Updated 8 months ago
- Automatic generation of FPGA-based learning accelerators for the neural network family☆63Updated 5 years ago
- A co-design architecture on sparse attention☆50Updated 3 years ago