Huseyin Simitci

Learn More
Windows Azure Storage (WAS) is a cloud storage system that provides customers the ability to store seemingly limitless amounts of data for any duration of time. WAS customers have access to their data from anywhere, at any time, and only pay for what they use and store. To provide durability for that data and to keep the cost of storage low, WAS uses(More)
Windows Azure Storage (WAS) is a cloud storage system that provides customers the ability to store seemingly limitless amounts of data for any duration of time. WAS customers have access to their data from anywhere at any time and only pay for what they use and store. In WAS, data is stored durably using both local and geographic replication to facilitate(More)
Consider a linear [<i>n</i>,<i>k</i>,<i>d</i>]<sub>q</sub> code <i>C</i>. We say that the <i>i</i>th coordinate of <i>C</i> has locality <i>r</i> , if the value at this coordinate can be recovered from accessing some other <i>r</i> coordinates of <i>C</i>. Data storage applications require codes with small redundancy, low locality for information(More)
• Traditional a posteriori approach 1. Application instrumentation – Instrumented automatically by object code patching or compiler. – Manually insert instrumentation library calls. 2. Execute, measure, and extract performance data 3. Analysis and visualization – Identify performance bottlenecks 4. Application optimization – Modify program, adjust runtime(More)
High-performance computing is rapidly expanding to include distributed collections of heterogeneous sequential and parallel systems and irregular applications with complex, data dependent execution behavior and time varying resource demands. To provide adaptive resource management for dynamic applications, we are developing the Autopilot toolkit. Autopilot(More)
As disk capacities continue to rise more rapidly than transfer rates, adaptive, redundant striping smoothly trades capacity for higher performance. We developed a fuzzy logic rule base for adaptive, redundant striping of les across multiple disks. This rule base is based on a queuing model of disk contention that includes le request sizes and disk hardware(More)
Emerging computational grids consist of distributed collections of heterogeneous sequential and parallel systems and irregular applications with complex, data dependent execution behavior and time varying resource demands. To provide adaptive input/output resource management for these systems, we are developing PPFS II, a portable parallel le system. PPFS(More)
Parallel computing is rapidly evolving to include het erogeneous collections of distributed and parallel sys tems Concurrently applications are becoming in creasingly multidisciplinary with code libraries im plemented using diverse programming models To optimize the behavior of complex applications on heterogeneous systems performance analysis soft ware(More)