Investigating The Efficiency Of The VPR And COFFE Area Models In Predicting The Layout Area Of FPGA Lookup Tables

A single tile in a mesh-based FPGA includes both the routing block and the logic block. The area estimate of a tile in an FPGA is used to determine the physical length of an FPGA’s routing segments. An estimate of the physical length of the routing segments is needed in order to accurately assess the performance of a proposed FPGA architecture. The VPR (Versatile Place and Route) and the COFFE (Circuit Optimization for FPGA Exploration) tools are widely used meshbased FPGA exploration environments. These tools map, place, and route benchmark circuits on FPGA architectures. Subsequently, based on area and delay measurements, the best architectural parameters of an FPGA are decided. The area models of the VPR and COFEE tools take only transistor size as input to estimate the area of a circuit. Realistically, the layout area of a circuit depends on both the transistor size and the number of metal layers that are available to route the circuit. This work measures the effect of the number of metal layers that are available for routing on FPGA layout area through a series of carefully laid out 4-LUTs (4-input Lookup Tables). Based on measured results, a correction factor for the COFFE area equation is determined. The correction factor is a function of both the transistor drive strength and the number of metal layers that are available for routing. Consequently, a new area estimation equation, that is based on the COFFE area model, is determined. The proposed area equation takes into consideration the effect of both the transistor drive strength and the number of metal layers that are available for routing on layout area. The area prediction error of the proposed area equation is significantly less than the area prediction errors of the VPR and COFFE area models.

Investigating The Efficiency Of The VPR And COFFE Area Models In Predicting The Layout Area Of FPGA Lookup Tables

A single tile in a mesh-based FPGA includes both the routing block and the logic block. The area estimate of a tile in an FPGA is used to determine the physical length of an FPGA’s routing segments. An estimate of the physical length of the routing segments is needed in order to accurately assess the performance of a proposed FPGA architecture. The VPR (Versatile Place and Route) and the COFFE (Circuit Optimization for FPGA Exploration) tools are widely used meshbased FPGA exploration environments. These tools map, place, and route benchmark circuits on FPGA architectures. Subsequently, based on area and delay measurements, the best architectural parameters of an FPGA are decided. The area models of the VPR and COFEE tools take only transistor size as input to estimate the area of a circuit. Realistically, the layout area of a circuit depends on both the transistor size and the number of metal layers that are available to route the circuit. This work measures the effect of the number of metal layers that are available for routing on FPGA layout area through a series of carefully laid out 4-LUTs (4-input Lookup Tables). Based on measured results, a correction factor for the COFFE area equation is determined. The correction factor is a function of both the transistor drive strength and the number of metal layers that are available for routing. Consequently, a new area estimation equation, that is based on the COFFE area model, is determined. The proposed area equation takes into consideration the effect of both the transistor drive strength and the number of metal layers that are available for routing on layout area. The area prediction error of the proposed area equation is significantly less than the area prediction errors of the VPR and COFFE area models.

Forest, forest, forest. Sometimes we sleep. Walking, sleep, walking, sleep. It’s dangerous on this way

Hidden migrant routes through Croatia lead through forest areas (among other types of terrain) which include those along state borders, but also forests in the interior of the territory. Those forests can variously be seen as shelters for migrants, albeit harsh, or as green tunnels leading to desired destinations, and as scenes of suffering and violence. This article approaches the forests in question as landscapes that have been transformed from a neutral natural environment into active factors for creating and maintaining border control regimes and deterring and expelling unwanted migrants. Based on our long-term field research and publicly available (archival, media and other) sources, we seek to document, interpret, and interconnect the objects and practices involved in constructing the forest as a hostile terrain and perilous environment for migrants, and as an important element in controlling unwanted migrations. These are, on the one hand, objects and practices that intervene into forests, such as setting up cameras or cutting down trees, and, on the other, interventions that take place in forests, such as police interception or expulsion. Apart from these external interventions, in this context of remodeling forests into dangerous environments, one can also discuss the role of nature itself and its characteristics, as well as the causes of why migrants find themselves in nature in the first place. Although, at first glance, it seems that people on the move choose the forest as the place and route of their movement of their own volition, they are pushed and expelled into these forests by exclusionary policies (visa regimes, asylum systems, etc.). This, ultimately, classifies forests in Croatia as weaponized landscapes of exclusion and death, such as the desert (e.g., De León 2015), mountain (Del Biaggio et al. 2020), maritime (e.g., Albahari 2015) or archipelago (Mountz 2017) landscapes

A Deep Learning Framework to Predict Routability for FPGA Circuit Placement

The ability to accurately and efficiently estimate the routability of a circuit based on its placement is one of the most challenging and difficult tasks in the Field Programmable Gate Array (FPGA) flow. In this article, we present a novel, deep learning framework based on a Convolutional Neural Network (CNN) model for predicting the routability of a placement. Since the performance of the CNN model is strongly dependent on the hyper-parameters selected for the model, we perform an exhaustive parameter tuning that significantly improves the model’s performance and we also avoid overfitting the model. We also incorporate the deep learning model into a state-of-the-art placement tool and show how the model can be used to (1) avoid costly, but futile, place-and-route iterations, and (2) improve the placer’s ability to produce routable placements for hard-to-route circuits using feedback based on routability estimates generated by the proposed model. The model is trained and evaluated using over 26K placement images derived from 372 benchmarks supplied by Xilinx Inc. We also explore several opportunities to further improve the reliability of the predictions made by the proposed DLRoute technique by splitting the model into two separate deep learning models for (a) global and (b) detailed placement during the optimization process. Experimental results show that the proposed framework achieves a routability prediction accuracy of 97% while exhibiting runtimes of only a few milliseconds.

Multi-Tier 3D IC Physical Design with Analytical Quadratic Partitioning Algorithm Using 2D P&R Tool

In this study, we developed a complete flow for the design of monolithic 3D ICs. We have taken the register-transfer level netlist of a circuit as the input and synthesized it to construct the gate-level netlist. Next, we partitioned the circuit using custom-made partitioning algorithms and implemented the place and route flow of the entire 3D IC by repurposing 2D electronic design automation tools. We implemented two different partitioning algorithms, namely the min-cut and the analytical quadratic (AQ) algorithms, to assign the cells in different tiers. We applied our flow on three different benchmark circuits and compared the total power dissipation of the 3D designs with their 2D counterparts. We also compared our results with that of similar works and obtained significantly better performance. Our two-tier 3D flow with AQ partitioner obtained 37.69%, 35.06%, and 12.15% power reduction compared to its 2D counterparts on the advanced encryption standard, floating-point unit, and fast Fourier transform benchmark circuits, respectively. Finally, we analyzed the type of circuits that are more applicable for a 3D layout and the impact of increasing the number of tiers of the 3D design on total power dissipation.

Practical Model Checking on FPGAs

Software verification is an important stage of the software development process, particularly for mission-critical systems. As the traditional methodology of using unit tests falls short of verifying complex software, developers are increasingly relying on formal verification methods, such as explicit state model checking, to automatically verify that the software functions properly. However, due to the ever-increasing complexity of software designs, model checking cannot be performed in a reasonable amount of time when running on general-purpose cores, leading to the exploration of hardware-accelerated model checking. FPGAs have been demonstrated to be promising verification accelerators, exhibiting nearly three orders of magnitude speedup over software. Unfortunately, the “FPGA programmability wall,” particularly the long synthesis and place-and-route times, block the general adoption of FPGAs for model checking. To address this problem, we designed a runtime-programmable pipeline specifically for model checkers on FPGAs to minimize the “preparation time” before a model can be checked. Our design of the successor state generator and the state validator modules enables FPGA-acceleration of model checking without incurring the time-consuming FPGA implementation stages, reducing the preparation time before checking a model from hours to less than a minute, while incurring only a 26% execution time overhead compared to model-specific implementations.