yuezuegu / sosa-compiler
Repository for compilation and cycle-accurate simulator for scale-out systolic arrays
☆14Updated 2 years ago
Alternatives and similar repositories for sosa-compiler:
Users that are interested in sosa-compiler are comparing it to the libraries listed below
- A systolic array simulator for multi-cycle MACs and varying-byte words, with the paper accepted to HPCA 2022.☆74Updated 3 years ago
- dMazeRunner: Dataflow acceleration optimization infrastructure for coarse-grained programmable accelerators☆45Updated 3 years ago
- Multi-core HW accelerator mapping optimization framework for layer-fused ML workloads.☆51Updated 2 months ago
- MICRO22 artifact evaluation for Sparseloop☆43Updated 2 years ago
- Linux docker for the DNN accelerator exploration infrastructure composed of Accelergy and Timeloop☆52Updated this week
- A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching☆48Updated 3 weeks ago
- An open-source parameterizable NPU generator with full-stack multi-target compilation stack for intelligent workloads.☆50Updated last month
- RTL implementation of Flex-DPE.☆99Updated 5 years ago
- gem5 repository to study chiplet-based systems☆72Updated 6 years ago
- mNPUsim: A Cycle-accurate Multi-core NPU Simulator (IISWC 2023)☆51Updated 4 months ago
- A scheduler for spatial DNN accelerators that generate high-performance schedules in one shot using mixed integer programming (MIP)☆79Updated last year
- A reference implementation of the Mind Mappings Framework.☆29Updated 3 years ago
- ☆71Updated 2 years ago
- ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference☆108Updated 2 months ago
- ☆28Updated 4 months ago
- ☆26Updated last year
- ☆15Updated 10 months ago
- [ASPLOS 2019] PUMA-simulator provides a detailed simulation model of a dataflow architecture built with NVM (non-volatile memory), and ru…☆63Updated 2 years ago
- A framework for fast exploration of the depth-first scheduling space for DNN accelerators☆38Updated 2 years ago
- ☆24Updated 8 months ago
- ☆39Updated 9 months ago
- Code for paper "FuSeConv Fully Separable Convolutions for Fast Inference on Systolic Arrays" published at DATE 2021☆14Updated 3 years ago
- Serpens is an HBM FPGA accelerator for SpMV☆18Updated 8 months ago
- Eyeriss chip simulator☆36Updated 5 years ago
- A list of our chiplet simulaters☆32Updated 2 weeks ago
- A RISC-V BOOM Microarchitecture Power Modeling Framework☆24Updated last year
- Tool for optimize CNN blocking☆94Updated 5 years ago
- A co-design architecture on sparse attention☆52Updated 3 years ago
- Model LLM inference on single-core dataflow accelerators☆10Updated 2 months ago
- Template-based Reconfigurable Architecture Modeling Framework☆14Updated 2 years ago