In-memory computing is one of today's hottest data center trends. Gartner Group projects that software revenue alone for this market will exceed US$9B by the end of 2018. It enables organizations to gain business value from real-time insights by offering faster performance and greater scalability than legacy architectures.
While modern data center applications can benefit from more main memory, today's DRAM approaches are expensive to scale because of that memory's volatility: DRAM stores data in leaky capacitors, and thus needs to be rewritten many times per second to stave off data loss. This refresh power consumption can be as much as 20-30% of the total server energy. Emerging non-volatile memory technologies, such as PCM, do not have this refresh power demand thereby enabling far greater scalability of main memory than DRAM.
Building upon last-year's record-breaking three million I/O per second Phase Change Memory (PCM) demonstration, HGST has teamed up with Mellanox Technologies to demo what it claims is a revolutionary PCM-based, RDMA-enabled in-memory compute cluster architecture that delivers DRAM-like performance at a lower cost of ownership2 with greater scalability.
HGST says its persistent memory fabric technology delivers reliable, scalable, low-power memory with DRAM-like performance, and does not require BIOS modification nor rewriting of applications. Memory mapping of remote PCM using the Remote Direct Memory Access (RDMA) protocol over networking infrastructures, such as Ethernet or InfiniBand, enables a seamless, wide scale deployment of in-memory computing. This network-based approach allows applications to harness the non-volatile PCM across multiple computers to scale out as needed.
The HGST/Mellanox demonstration achieves random access latency of less than two microseconds for 512 B reads, and throughput exceeding 3.5 GB/s for two KB block sizes using RDMA over InfiniBand.
DRAM is expensive and consumes significant power. HGST claims Phase Change Memory is a viable DRAM performance alternative at a new price and capacity tier bridging main memory and persistent storage. To scale out this level of performance across the data center requires further innovation. Its collaboration with Mellanox proves that non-volatile main memory can be mapped across a network with latencies that fit inside the performance envelope of in-memory compute applications.
Mellanox Technologies says to truly shake up the economics of the in-memory compute ecosystem will require a combination of networking and storage working together transparently to minimize latency and maximize scalability.
Dr. Zvonimir Bandic, manager of Storage Architecture at HGST Research says the breakthrough came when the company applied the PCI Express Peer-to-Peer technology, inspired by supercomputers using general purpose GPUs, to create this low latency storage fabric using commodity server hardware.
0 Comment Log in or register to post comments