The number of parameters in deep neural networks (DNNs) is scaling at about 5 Ă the rate of Mooreâs Law. To sustain this growth, photonic computing is a promising avenue, as it enables higher throughput in dominant general matrix-matrix multiplication (GEMM) operations in DNNs than their electrical counterpart. However, purely photonic systems face several challenges including lack of photonic memory and accumulation of noise. In this paper, we present an electro-photonic accelerator, ADEPT, which leverages a photonic computing unit for performing GEMM operations, a vectorized digital electronic ASIC for performing non-GEMM operations, and SRAM arrays for storing DNN parameters and activations. In contrast to prior works in photonic DNN accelerators, we adopt a system-level perspective and show that the gains while large are tempered relative to prior expectations. Our goal is to encourage architects to explore photonic technology in a more pragmatic way considering the system as a whole to understand its general applicability in accelerating todayâs DNNs. Our evaluation shows that ADEPT can provide, on average, 5.73 Ă higher throughput per Watt compared to the traditional systolic arrays (SAs) in a full-system, and at least 6.8 Ă and 2.5 Ă better throughput per Watt, compared to state-of-the-art electronic and photonic accelerators, respectively.