Showing headlines posted by visionofarun

The Xeon Phi is a co-processor that can speed up numerical calculations. It cannot operate without a main processor. The many core server is based on the Intel Many Integrated Cores (MIC) architecture.

I am a great fan of Staged Event Driven Architecture. Few of my architectures and designs are heavily influenced by this approach and thus have resulted in a proven high performance and low latent systems. Here I'm going to discuss about how an application can be designed using SEDA approach. Later, when I get time, I'll write about designing systems with different queuing systems like AMQP, etc.

Static member variables are inevitable in singleton implementations. If we define the static member variable in the header file and include it in more than one source file, the linker would throw multiple definition errors when trying to link the translation units. So it is a little tricky to design the singleton in header only implementations. Nevertheless it is not difficult.

In high performance computing it is common for applications to have all of the data in the physical memory to meet performance criticality. When multiple processes communicate, as we know, shared memory serves as the fastest way of IPC. Any such typical application would initialize the shared memory by loading the data from the disk into the shared memory. Now a question arises - what is the maximum data size that my application can hold in the physical memory, of course, without swapping.

Having a seamless build system with GNU make to manage external libraries.