Addressing multiple bit/symbol errors in DRAM subsystem

As DRAM technology continues to evolve towards smaller feature sizes and increased densities, faults in DRAM subsystem are becoming more severe. Current servers mostly use CHIPKILL based schemes to tolerate up-to one/two symbol errors per DRAM beat. Such schemes may not detect multiple symbol errors arising due to faults in multiple devices and/or data-bus, address bus. In this article, we introduce Single Symbol Correction Multiple Symbol Detection (SSCMSD)—a novel error handling scheme to correct single-symbol errors and detect multi-symbol errors. Our scheme makes use of a hash in combination with Error Correcting Code (ECC) to avoid silent data corruptions (SDCs). We develop a novel scheme that deploys 32-bit CRC along with Reed-Solomon code to implement SSCMSD for a ×4 based DDR4 system. Simulation based experiments show that our scheme effectively guards against device, data-bus and address-bus errors only limited by the aliasing probability of the hash. Our novel design enabled us to achieve this without introducing additional READ latency. We need 19 chips per rank, 76 data bus-lines and additional hash-logic at the memory controller.