Prefix adders are widely used in compute-intensive applications for their high speed. However, designing optimized prefix adders is challenging due to strict design rules and an exponentially large design space. We introduce PrefixGPT, a generative pre-trained Transformer (GPT) that directly generates optimized prefix adders from scratch. Our approach represents an adder's topology as a two-dimensional coordinate sequence and applies a legality mask during generation, ensuring every design is valid by construction. PrefixGPT features a customized decoder-only Transformer architecture. The model is first pre-trained on a corpus of randomly synthesized valid prefix adders to learn design rules and then fine-tuned to navigate the design space for optimized design quality. Compared with existing works, PrefixGPT not only finds a new optimal design with a 7.7% improved area-delay product (ADP) but exhibits superior exploration quality, lowering the average ADP by up to 79.1%. This demonstrates the potential of GPT-style models to first master complex hardware design principles and then apply them for more efficient design optimization.

Trajectory sharing and searching have received significant attentions in recent years. In this paper, we propose and investigate a novel problem called User Oriented Trajectory Search (UOTS) for trip recommendation. In contrast to conventional trajectory search by locations (spatial domain only), we consider both spatial and textual domains in the new UOTS query. Given a trajectory data set, the query input contains a set of intended places given by the traveler and a set of textual attributes describing the traveler's preference. If a trajectory is connecting/close to the specified query locations, and the textual attributes of the trajectory are similar to the traveler'e preference, it will be recommended to the traveler for reference. This type of queries can bring significant benefits to travelers in many popular applications such as trip planning and recommendation.

MOTIVATION: A high-quality assembly of reads generated from shotgun sequencing is a substantial step in metagenome projects. Although traditional assemblers have been employed in initial analysis of metagenomes, they cannot surmount the challenges created by the features of metagenomic data. RESULT: We present a de novo assembly approach and its implementation named MAP (metagenomic assembly program). Based on an improved overlap/layout/consensus (OLC) strategy incorporated with several special algorithms, MAP uses the mate pair information, resulting in being more applicable to shotgun DNA reads (recommended as >200 bp) currently widely used in metagenome projects. Results of extensive tests on simulated data show that MAP can be superior to both Celera and Phrap for typical longer reads by Sanger sequencing, as well as has an evident advantage over Celera, Newbler and the newest Genovo, for typical shorter reads by 454 sequencing. AVAILABILITY AND IMPLEMENTATION: The source code of MAP is distributed as open source under the GNU GPL license, the MAP program and all simulated datasets can be freely available at http://bioinfo.ctb.pku.edu.cn/MAP/