- Lightsolver reveals laser processor device designed to solve high -speed physics equations
- Laser Computing system uses optical memory to avoid bottlenecks in processor and memory data
- The company starts offering early lab access by roadmap to one million variables in 2029
Laser -based computing appears as a potential challenger to established computing systems with high performance computing, where light solver reveals what it calls a laser treatment unit (LPU).
The Tel Aviv-based startup says its hardware can directly resolve partial differential equations, a basic class of problems in physics and technique.
Unlike quantum systems or GPU clusters, the procedure is based on a grid of lasers that trade unisont.
Mapping equations at LPU
Lightsolver says its hardware can map equations such as the Heat equation (which models heat current) and Schrödinger’s equation (a core equation in quantum mechanics) directly on the LPU.
By using laser’s natural properties as electromagnetic waves, Lights Solver’s tech avoids many of the limitations found in digital systems.
This includes bottlenecks caused by data transfer between memory and processor.
According to Light Solver, LPU works with embedded optical memory. In practice, this means that laser states are preserved inside the resonator, allowing each calculation step to build on the latter without having to move data externally.
The result is iteration of constant time measured in nanoseconds, regardless of problem size.
While Light Solver compares its platform with both high performance and quantum computers, it emphasizes that it is not built on photonic chips.
Today’s photonic processors are two dimensional, while its laser -based design is three -dimensional, which the start -up claims will give greater scalability.
Light Solver has set a roadmap to reach 100,000 variables in 2027 and one million in 2029.
The company has already started making its hardware available for testing. An alpha version of its processor and a digital emulator is offered researchers through what it calls its LPU lab.
Light Solver believes this step will help researchers and engineers experiment with the technology before it reaches commercial quality.
“Classic computers digitize analogous character, and we pay the price in longer driving times and wasted energy. By running large physics simulations on a physical machine, we can solve them more efficiently than any HPC or quantum system available today,” said Ruti Ben-Shlomi, CEO and co-founder of Lights Solver.
Research articles have been published on the subject and presentations have been given at computer conferences, including ACM Computing Frontiers 2025.
The company has also formed partnerships with simulation software providers and works with HPC centers and national laboratories.
