Logic synthesis using CNN

 Introduction

Logic Synthesis is used in order to realize RTL(Register transfer Level) design which is obtained via a hardware description language(HDL). Various types of machine learning techniques are used in order to optimize the complete process. Convolutional Neural Network(CNN) is one of the many methods used and a preliminary one for this purpose. It can be used from logic synthesis, in placement and routing as well as in power deliver network synthesis and IR drop predictions. CNN models are composed of convolutional layers and other basic blocks such as non-linear activation functions and down sample pooling functions. In the logic synthesis and physical design stage, there are many key sub-problems that can benefit from the power of ML models. Let us see how CNN can be implemented in the above mentioned parts for useful optimizations.

Logic synthesis:

This is an optimization problem with complicated constraints, which requires accurate solutions. Hence, using ML algorithms to directly generate logic synthesis solutions is a bit difficult. There are many logic transformations in current synthesis tools. To select an appropriate synthesis flow we need to formulate a multi-class classification problem and design a CNN to map a synthesis flow. The prediction on unlabeled flows are then used to select the optimal synthesis flow. The CNN takes the one-hot encoding of synthesis flows as inputs and outputs the possibilities of the input flow. Sometimes, reinforcement learning is also employed for logic synthesis for better optimization.

Placement & Routing:

The basic requirements of routing design rules must be considered in the placement stage. However, it is difficult to predict routing information in the placement stage accurately and fast, hence, recently machine learning is employed to solve this. It was first used for design rule checking (DRC) hotspot detection. The input features of a customized fully convolutional network (FCN) include the outputs of rectangular uniform wire density. It can also be employed to predict design rule violation count. Various other advanced networks are also used in this case, for better optimization and prediction.

Power deliver network synthesis:

Power delivery network (PDN) design is a complex iterative optimization task, which strongly influences the performance, area and cost of a chip. To reduce the design time, ML-based algorithms are being recently used. The main challenge is increasing complexity of chip design. The IR drop can be divided into two parts: static and dynamic. A CNN can be used to predict the IR values of different locations and models IR drop estimation problem as a regression task. Further, CNN is used to choose the template for floorplan and placement stages.

Conclusion:

Thus from this we can conclude that with the help of various machine learning techniques like CNN we can get better and optimized results in various steps of logic synthesis, by spending less time, however with higher computational requirements.

Comments

Post a Comment

Popular posts from this blog

FAST STATIC IR DROP PREDICTION USING MACHINE LEARNING

By Anmol Salvi INTRODUCTION: Logic Synthesis , High Level Synthesis , IR drop estimation and Lithography hotspot detection all fall under one broad category in a way which is Electronic Design Automation and are all related to each other to a certain extent.IR drop constraint is one of the fundamental requirements that is enforced in almost every chip design. However, it’s evaluation ends up taking a large amount of time and also the mitigation techniques for fixing any violations may require a number of iterations. Thus , fast and more importantly accurate IR drop prediction becomes essential for reducing the overall design turnaround time. Very recently, machine learning (ML) techniques have been studied very actively so as to allow for fast IR drop estimation owing to their potential promise and recorded success in a lot of fields. IR drop which is also called as voltage drop, is defined as the deviation of a power supply level from its specification which occurs when current begi...
Read more

Machine Learning for Analog Layout

By Ishan Aphale In back-end analog/mixed-signal (AMS) design flow, well generation persists as a fundamental challenge for layout compactness, routing complexity, circuit performance and robustness. The immaturity of AMS layout automation tools comes to a large extent from the difficulty in comprehending and incorporating designer expertise. To mimic the behavior of experienced designers in well generation, we can use a generative adversarial network (GAN) guided well generation framework with a post-refinement stage leveraging the previous high-quality manually-crafted layouts. Guiding regions for wells are first created by a trained GAN model, after which the well generation results are legalized through post-refinement to satisfy design rules. The network learns and mimics designers’ behavior from manual layouts. Experiments show that generated wells have comparable post-layout circuit performance with manual designs on the op-amp circuit. The power of machine learning algorithms ha...
Read more

High Level Synthesis using Linear Regression

Image
High Level Synthesis (HLS) works at the algorithmic level in hardware design systems. HLS tools provide automatic conversion from C/C++/SystemC-based specification to hardware description languages like Verilog or VHDL. It has been inferred that these HLS tools are improving the productivity in customised hardware design systems. In certain cases of HLS, the long synthesis time for each design brings about a restriction on design space exploration (DSE). DSE is the process of finding some design solution which optimally meets the design requirements from a space of tentative design points. This exploration is quite complex considering the various levels of abstraction and the entire process from selection of parameter values to choosing an algorithm and then optimising it. Machine Learning for High Level Synthesis: Machine Learning techniques are applied to improve the performance of HLS tools with 3 major advantages: 1. Fast and accurate result estimation 2. Refining the conventional ...
Read more