Real-time embedded systems are increasingly being built using commercial-off-the-shelf (COTS) components. Although these components generally offer high performance, they can occasionally incur significant timing delays. Computing precise bounds on timing delays due to contention is difficult without a proper support from the hardware. Rather than estimating contention safe delays, this work aims to avoid it. We consider hardware architectures where each core has a scratchpad memory and the task execution is divided into a memory phase and a computation phase (Predictable Execution Model-PREM). Tasks are allocated to cores by a partitioned scheduling scheme. Then we schedule memory phases using a non-preemptive scheduling approach, while computation phases are scheduled using preemptive single core schedulers. This paper presents a new artificial deadline based approach to avoid contention in memory phases, where tasks memory phases are assigned appropriate deadlines and scheduled by a nonpreemptive scheduler (EDF). The effectiveness of the proposed method is evaluated using a set of synthetic experiments in terms of schedulability and analysis time.