Memory scaling is in jeopardy as charge storage and sensing mechanisms become less reliable for prevalent memory technologies, such as dynamic random access memory (DRAM). In contrast, phase change memory (PCM) relies on programmable resistances, as well as scalable current and thermal mechanisms. To deploy PCM as a DRAM alternative and to exploit its scalability, PCM must be architected to address relatively long latencies, high energy writes, and finite endurance. We propose architectural

more »

... ncements that address these limitations and make PCM competitive with DRAM. A baseline PCM system is 1.6× slower and requires 2.2× more energy than a DRAM system. Buffer reorganizations reduce this delay and energy gap to 1.2× and 1.0×, using narrow rows to mitigate write energy as well as multiple rows to improve locality and write coalescing. Partial writes mitigate limited memory endurance to provide more than 10 years of lifetime. Process scaling will further reduce PCM energy costs and improve endurance. intRoduction Memory technology scaling drives increasing density, increasing capacity, and falling price-capability ratios. Memory scaling, a first-order technology objective, is in jeopardy for conventional technologies. Storage mechanisms in prevalent memory technologies require inherently unscalable charge placement and control. In the nonvolatile space, Flash memories must precisely control the discrete charge placed on a floating gate. In volatile main memory, DRAM must not only place charge in a storage capacitor but must also mitigate subthreshold charge leakage through the access device. Given these challenges, solutions for scaling DRAM beyond 40nm are unknown. 17 CM provides a nonvolatile storage mechanism amenable to process scaling. During writes, an access transistor injects current into the storage material and thermally induces phase change, which is detected as a programmed resistance during reads. PCM, relying on analog current and thermal effects, does not require control over discrete electrons. As technologies scale and heating contact areas shrink, programming current scales linearly. This PCM scaling mechanism has been demonstrated in a 32 nm device prototype. 15 As a scalable DRAM alternative, PCM could provide a clear roadmap for increasing main memory density and capacity.