SKA computing will be a pioneer HPC challenge tackled by Dark-Era. The exascale radio telescope Square Kilometer Array (SKA) will require supercomputers with high technical constraints. The Science Data Processor (SDP) pipeline in charge of producing the multidimensional images of the sky will have to execute in realtime a complex algorithm chain from data coming from telescopes at an incredible rate of several Tb/s and without any storage capabilities. The SDP will also have to be as green as possible with an energy budget of only 1 MWatt for 250 Petaflops. Such energy and computation requirements imply the SDP to be an innovative dataflow oriented and heterogeneous architecture. This supercomputer will be based on a standard HPC system combined with Field Programmable Gate Array (FPGA) or application-specific architectures like Graphical Processing Unit (GPU) or the manycore Kalray Massively Parallel Processor Array (MPPA). One crucial challenge is to assess the performance both in time and energy of new complex scientific dataflow algorithms on not-yet-existing complex computing infrastructures. It will be hardly possible without efficient co-design methods and rapid prototyping tools. SimSDP is a rapid prototyping tool for SKA-like dataflow applications developed by the Dark-Era project. Through an original mixed approach based on execution and simulation, SimSDP purpose is to provide early analyses in terms of memory usage, latency, throughput, and energy consumption. Following an Algorithm Architecture Matching (AAM) approach, SimSDP will rely on a dataflow model of the algorithm and a model of the target architecture. SimSDP will be based on two existing tools: PREESM and SimGrid. PREESM accurately evaluates heterogeneous single node performance; SimGrid accurately simulates inter-node communications. Then, the association of PREESM and SimGrid will allow for reliable simulations of large scale heterogeneous HPC systems. Thanks to SimSDP, algorithm and architecture spaces will be explored in the SKA context. The new generation of radio astronomy imaging pipelines like ddfacet will be described at a high-level of abstraction suitable for targeting any heterogeneous multinode HPC system SKA may choose in the future. Then, several SDP architecture configurations (number of nodes, kind of accelerators) and several SDP algorithm configurations will be explored together through the large scale simulations offered by SimSDP. Besides, SDP prototypes on MPPA and FPGA designed through High-Level Synthesis (HLS) tools and set up at the NenuFAR radio telescope will be developed and profiled on small scale datasets. It will allow to evaluating the potential of low power accelerators as an alternative to the mainstream GPU architecture. These SDP profiling feedbacks on GPU/MPPA/FPGA will fill out SimSDP with annotations on the dataflow graph. SDP prototypes will also be compared with SimSDP simulations on medium scale datasets to evaluate SimSDP new features. Dark-Era will be a consortium gathering complementary skills in computer science, signal processing, and astronomy with twelve permanent members from the SimGrid development Team at IRISA, the PREESM development team at IETR, the inverse problem team at L2S, and two radio astronomy teams at Observatories of Paris and Cˆote d’Azur. Preliminary results obtained by this consortium in collaboration with Atos-Bull during the CNRS SKALLAS project will be pursued. Two PhD students will work on the association of PREESM and SimGrid tools in SimSDP, and two post-docs will be hired. With the support of SKA-France, this 4-year project aims to promote french contributions to SKA such as ddfacet and to be a force of proposal for SKA computing. Finally, Dark-Era intends to be the breeding ground for new international collaborations notably through the Rising STARS European and International network.

LOFAR (the European LOw Frequency ARray) is the first of the new-generation radiotelescopes of the 21st century, that will culminate with SKA (Square Kilometer Array) after 2020. NenuFAR is a giant extension of LOFAR, that is also a powerful standalone low-frequency (LF) radiotelescope in the range 10-85 MHz. Its construction has started in 2014 in Nançay, supported by CNRS/INSU, Observatoire de Paris, Université d’Orléans/OSUC, and the FLOW consortium. NenuFAR is a compact antenna array (400 m in diameter) connected to the LOFAR receivers and to a local digitizer and beamformer (synthesizing narrow steerable 200 kHz beams in the sky up to a total instantaneous bandwidth of 150 MHz). We propose here to give NenuFAR the additional capability of a powerful LF imager with ~7’ resolution, by adding a realtime correlator, offline computing power, massive storage, and 6 small arrays (of 19 antennas each) within 3 km of the compact core. These extensions will considerably reduce the confusion noise limiting the imaging sensitivity of the instrument, down to about the thermal noise. The scientific topics that will greatly benefit from the use of NenuFAR in Standalone as an imager include: (a) in multi-frequency, long integration imaging: the detection of the cosmological HI signal from the “dark ages” to the reionization era through the "cosmic dawn", the systematic and sensitive search for yet unconfirmed LF radio signatures of exoplanets and star-planet plasma interactions (SPI), and the radio afterglows of high energy collapses generating gravitational waves and Gamma Ray Bursts ; (b) in snapshot imaging mode: the systematic sensitive search for fast radio transients in a broad field of view, including the prompt emission associated with gravitational waves, pulsar giant pulses, Fast Radio Bursts, and exoplanetary / stellar / SPI bursts ; Detection and study of ~10^5 galactic and extragalactic sources, with their diffuse LF emission, will also be made possible. For topics (a) & (b) the NenuFAR Radio Imager (NRI) will be in its frequency range the most powerful existing instrument before SKA (more powerful than LOFAR and the LWA), combining a high instantaneous sensitivity, very large total bandwidth, good angular resolution, and full polarization measurement capability. The proposed imaging capability, adding to its beamformer capability and its enhancement of LOFAR as a “Super Station” (LSS) will make NenuFAR a truly unique LF radio facility of the 21st century. In the SKA era, it will remain complementary to SKA in terms of spectral range and hemisphere. France has a strong expertise in development of imaging, calibration, deconvolution, and RFI mitigation algorithms for LF radioastronomy, that will be applied to and optimized for the NRI, preparing the exploitation of SKA. NenuFAR has received the official status of SKA pathfinder from the SKA office, for the experience it will bring in terms of hardware, algorithms, multimode operations (super-station / standalone beamformer / imager), and science preparation. The NRI will contribute to the organization and development of the French LF radio community – which started with the collective writing of a broad science case by 80 French and International scientists –, reinforcing its role and influence in Europe. The CNRS prospective in 2014 and the Haut Conseil TGIR in 2016 gave a high priority to the completion of NenuFAR (labelled “Infrastructure de Recherche” by the MESR), and the “Conseil Stratégique de Direction” of USN identified the NRI as the development of highest importance. The NRI project includes a Public Outreach part in the form of an Art Project integrated with the instrument and that will enhance its interest for the general public.