Multi-Dot Floating-Gates for Nonvolatile Semiconductor Memories - Their Ion Beam Synthesis and Morphology

TL;DR

This paper investigates the fabrication and analysis of multi-dot silicon nanocrystals in SiO2 for nonvolatile memory applications, using ion beam synthesis, advanced electron microscopy, and simulations to understand morphology evolution.

Contribution

It combines experimental PEELS-STEM imaging with kinetic Monte Carlo simulations to study Si nanocrystal formation and morphology changes during ion beam synthesis.

Findings

PEELS-STEM effectively maps Si plasmon losses in nanocrystals.

Morphology of Si nanocrystals transitions from isolated dots to spinodal patterns with increased ion fluence.

Predicted spinodal patterns occur at lower fluence than observed experimentally, possibly due to oxidation effects.

Abstract

Scalability and performance of current flash memories can be improved substantially by replacing the floating poly-Si gate by a layer of Si dots. This multi-dot layer can be fabricated CMOS-compatibly in very thin gate oxide by ion beam synthesis (IBS). Here, we present both experimental and theoretical studies on IBS of multi-dot layers consisting of Si nanocrystals (NCs). The NCs are produced by ultra low energy Si ion implantation, which causes a high Si supersaturation in the shallow implantation region. During post-implantation annealing, this supersaturation leads to phase separation of the excess Si from the SiO2. Till now, the study of this phase separation process suffered from the weak Z contrast between Si and SiO2 in Transmission Electron Microscopy (TEM). Here, this imaging problem is resolved by mapping Si plasmon losses with a Scanning Transmission Electron Microscopy equipped with a parallel Electron Energy Loss Spectroscopy system (PEELS-STEM). Additionally, kinetic lattice Monte Carlo simulations of Si phase separation have been performed and compared with the experimental Si plasmon maps. It has been predicted theoretically that the morphology of the multi-dot Si floating-gate changes with increasing ion fluence from isolated, spherical NCs to percolated spinodal Si pattern. These patterns agree remarkably with PEELS-STEM images. However, the predicted fluence for spinodal patterns is lower than the experimental one. Because oxidants of the ambient atmosphere penetrate into the as-implanted SiO2, a substantial fraction of the implanted Si might be lost due to oxidation.