Presentation
Efficient Continuous Logic Optimization with Diffusion Model
SessionML-Powered Logic Synthesis
DescriptionLogic synthesis involves applying a sequence of logic transformations to circuits that significantly impact their quality-of-result (QoR).
Recently, there has been a growing focus on optimizing synthesis sequences to improve QoR.
However, previous efforts treat sequence optimization as a discrete transformation-selection task and fall short in scalability due to the exponentially sized search space.
Continuous optimization, in contrast, offers favorable efficiency advantages thanks to mature gradient-based optimization techniques.
Still, it is non-trivial to directly apply it to the discrete sequence optimization task since the gradient may lead to out-of-distribution solutions.
In this paper, we propose an efficient approach to optimize synthesis sequences within a continuous latent space.
We map discrete transformations to and from a continuous representation, enabling gradient-based optimization.
To tackle the out-of-distribution issue, we incorporate a diffusion model to constrain the optimized transformations to be in-distribution.
Without the need to search combinatorial solution space, our method is more than 5 times faster than previous methods.
Besides, the sequences found by our method reach a lower area and delay compared with baseline methods.
Recently, there has been a growing focus on optimizing synthesis sequences to improve QoR.
However, previous efforts treat sequence optimization as a discrete transformation-selection task and fall short in scalability due to the exponentially sized search space.
Continuous optimization, in contrast, offers favorable efficiency advantages thanks to mature gradient-based optimization techniques.
Still, it is non-trivial to directly apply it to the discrete sequence optimization task since the gradient may lead to out-of-distribution solutions.
In this paper, we propose an efficient approach to optimize synthesis sequences within a continuous latent space.
We map discrete transformations to and from a continuous representation, enabling gradient-based optimization.
To tackle the out-of-distribution issue, we incorporate a diffusion model to constrain the optimized transformations to be in-distribution.
Without the need to search combinatorial solution space, our method is more than 5 times faster than previous methods.
Besides, the sequences found by our method reach a lower area and delay compared with baseline methods.
Event Type
Research Manuscript
TimeWednesday, June 2511:15am - 11:30am PDT
Location3004, Level 3