Search for: All records

The development of FPGA-based applications using HLS is fraught with performance pitfalls and large design space exploration times. These issues are exacerbated when the application is complicated and its performance is dependent on the input data set, as is often the case with graph neural network approaches to machine learning. Here, we introduce HLPerf, an open-source, simulation-based performance evaluation framework for dataflow architectures that both supports early exploration of the design space and shortens the performance evaluation cycle. We apply the methodology to GNNHLS, an HLS-based graph neural network benchmark containing 6 commonly used graph neural network models and 4 datasets with distinct topologies and scales. The results show that HLPerf achieves over 10 000 × average simulation acceleration relative to RTL simulation and over 400 × acceleration relative to state-of-the-art cycle-accurate tools at the cost of 7% mean error rate relative to actual FPGA implementation performance. This acceleration positions HLPerf as a viable component in the design cycle.

Single-cell ATAC-seq has emerged as a powerful approach for revealing candidate cis-regulatory elements genome-wide at cell-type resolution. However, current single-cell methods suffer from limited throughput and high costs. Here, we present a novel technique called scifi-ATAC-seq, single-cell combinatorial fluidic indexing ATAC-sequencing, which combines a barcoded Tn5 pre-indexing step with droplet-based single-cell ATAC-seq using the 10X Genomics platform. With scifi-ATAC-seq, up to 200,000 nuclei across multiple samples can be indexed in a single emulsion reaction, representing an approximately 20-fold increase in throughput compared to the standard 10X Genomics workflow.