We present linearizable implementations for two distributed organizations of multiprocessor shared memory. For the full caching organization , where each process keeps a local copy of the whole memory, we present a linearizable implementations of read/write memory objects that achieves essentially optimal eeciency and allows quantitative degradation of the less frequently employed operation. Fo...

We study the cache performance in a symmetric distributed main-memory database. The high performance networks in many large distributed systems enable a machine to reach the main memory of other nodes more quickly than the time to access local disks. We therefore introduce remote memory as an additional layer in the memory hierarchy between local memory and disks. In order to appreciate the tra...

Shared memory architectures often have caches to reduce the number of slow remote memory accesses. The largest possible caches exist in shared memory architectures called Cache-Only Memory Architectures (COMAs). In a COMA all the memory resources are used to implement large caches. Unfortunately, these large caches also have their price. Due to its lack of physically shared memory, COMA may su ...

As an innovative grid computing technique for sharing the distributed memory resources in a highspeed wide-area network, RAM Grid exploits the distributed computing nodes, and provides remote memory for the user nodes which are short of memory. The performance of RAM Grid is constrained with the expensive network communication cost. In order to hide the latency of remote memory access and impro...

Transient epileptic amnesia is a form of temporal lobe epilepsy in which sufferers often complain of irretrievable loss of remote memories. We used a broad range of memory tests to clarify the extent and nature of the remote memory deficits in patients with transient epileptic amnesia. Performance on standard tests of anterograde memory was normal. In contrast, there was a severe impairment of ...

Disaggregation and rack-scale systems have the potential of drastically increasing TCO and utilization of cloud datacenters, while maintaining performance. In this paper, we present a novel rack-scale system architecture featuring softwaredefined remote memory disaggregation. Our hardware design and operating system extensions enable unmodified applications to dynamically attach to memory segme...

Over time, memory retrieval is thought to transfer from the hippocampus to a distributed network of neocortical sites. Of these sites, the retrosplenial cortex (RSC) is robustly activated during retrieval of remotely acquired, emotionally valenced memories. It is unclear, however, whether RSC is specifically involved in memory storage or retrieval, and which neurotransmitter receptor mechanisms...

Mosharaf Chowdhury is an Assistant Professor in the EECS Department at the University of Michigan. His research ranges from resource disaggregation in low-latency RDMA networks to geo-distributed analytics over the WAN, with a common theme of enabling applicationinfrastructure symbiosis across different layers of corresponding software and hardware stacks. [email protected] Memory disaggregati...