The ESP Vision
ESP is an open-source research platform for heterogeneous system-on-chip design that combines a scalable tile-based architecture and a flexible system-level design methodology.

ESP provides accelerator flows for RTL, high-level synthesis (HLS), and machine learning frameworks. These design flows converge to the ESP automated SoC integration flow that generates the necessary hardware and software interfaces to rapidly enable full-system prototyping on FPGA.
Overview
- Architecture
- Accelerator design and integration flows
- ESP accelerator design flows
- Third-party accelerator integration flow
- Example: NVIDIA Deep Learning Accelerator (NVDLA)
- SoC design flow
- Mix & match SoC floorplanning GUI
- Automatic SoC generation
- Full-system RTL simulation
- Rapid FPGA prototyping
- Software support
- Bare-metal
- Linux SMP
- FPGA development boards
- Xilinx Virtex UltraScale+ FPGA VCU118 and VCU128
- Xilinx Zynq UltraScale+ MPSoC ZCU102 and ZCU106
- Xilinx Virtex-7 FPGA VC707
- proFPGA Virtex7 XC7V2000T FPGA
- proFPGA Virtex Ultrascale XCVU440 FPGA
- proFPGA Virtex UltraScale+ XCVU19P FPGA
For more information check out the documentation section!
See here some of the supported projects, tools and languages:
Publications
Overview paper:
Agile SoC Development with Open ESP
Paolo Mantovani, Davide Giri, Giuseppe Di Guglielmo, Luca Piccolboni, Joseph Zuckerman, Emilio G. Cota, Michele Petracca, Christian Pilato, Luca P. Carloni
(Invited) IEEE/ACM International Conference On Computer Aided Design (ICCAD), 2020
The Publications page contains the complete list of publications related to ESP.
What’s new
- ESP release 2026.1.0
- Main memory access now uses AXI, with improved AXI-NoC burst transfers
- FPGA memory-link width is configurable
- Dual memory tiles are enabled on the VCU118 FPGA
- AXI support has been expanded across all supported FPGA boards
- Improved ESP GUI
- New GUI rollout with usability fixes and configuration cleanups
- Accelerator and infrastructure updates
- Refined Catapult SystemC and general Catapult HLS flows
- Updated ASIC build scripts and restored EDCL compatibility with GCC 8+
- Fixes for RTL and third-party accelerator compilation, LeakyReLU software, async FIFO reset, cache-line handling, P2P transaction flags and non-power-of-two CPU instances
Coming soon
-
Integration of the open-source Vortex GPU
-
Altera/Intel FPGA board support
-
Support for multiple outstanding AXI transactions
-
Continued AXI, third-party accelerator, ASIC and dynamic partial reconfiguration improvements








