Abstract: Polysilicon in a trench is etched at an angle to produce a conductor within the trench that has shape characteristics which approximate the shadow of the side wall of the trench closest the beam source. Specifically, when the first side wall is closest to the beam source and the second side wall is furthest from the beam source, the polysilicon on the first side wall is almost as high as the first side wall, while the polysilicon on the more exposed side wall is considerably lower than the first side wall and approximates the shadow of the first side wall on the second side wall relative to the beam. The polysilicon in the trench may be in the shape of a solid angled block approximating the shadow line from the top of side wall to the shadow line on side wall however, it is preferred that the polysilicon take the form of a conformal layer in trench prior to etching such that the polysilicon ultimately has an angled "U" shape which approximates the shadow line.

Abstract: The subject invention provides a method of forming recesses in a substrate such as a capacitor so as to increase the surface area thereof and therefore the charge storage capacity of the capacitor. This is accomplished by utilizing a micro mask formed by agglomeration on the surface of the substrate. The agglomerated material, such as gold, titanium nitride or titanium silicide, is used as a mask for selectively etching the substrate to form recesses therein. Alternatively, an oxide transfer mask can be utilized with the agglomerated material micro mask to etch the substrate.

Abstract: In a data processing system including a pipelined instruction execution unit and a pipelined high speed cache, a storage queue consisting of a set of FIFO registers and associated support logic handles transfer of data from the pipeline instruction execution unit to the high speed cache. When a store request flow from the instruction execution pipeline is forwarded to the high speed cache, instead of placing the data directly into the high speed cache, the starting address, length of store and data to be stored are placed into one of the store queue registers. The instruction execution unit sees the store request as completed and continues processing even though data has not been physically placed in the high speed cache. The write to the high speed cache is finished in the background at a later time during an unused storage pipeline cycle in the high speed cache.