The Power7 uses a 45 nanometer process. Each Power7 processor has up to eight cores and four threads per core. That’s four times the maximum number of cores and eight times the number of threads per chip as the Power6.

The Power7 has a TurboCore mode, which is optimized for database and other transaction-oriented workloads. This runs with four cores active and with most of the resources from the other four cores behind the eight active cores. Doing this gives the four active cores more cache memory and memory bandwidth and increases their clock speeds.

Power7 technology has “intelligent threads,” meaning the number of threads varies depending on the workload. More threads increase total capacity, and fewer threads increase individual processing tasks, such as real-time analytics and database transactions.

Active Memory Expansion, a new Power7 technology, dynamically adjusts the amount of compressed memory required based on a workload’s needs. This expands the memory capacity of Power7 systems without requiring the installation of more physical memory. A server using Active Memory Expansion can handle up to 65 percent more transactions or users than servers without this feature, according the IBM’s estimates.

Intelligent Energy technology in the Power7s lets customers power on and off various parts of the system, or dynamically increase or decrease processor clock speeds based on thermal conditions and system utilization. They can do this on a single server or across a pool of multiple servers.

To understand the Internet Protocol you must first understand what the Internet. Mainly the Internet consists of computer groups, each group can be represented by a street or area and theses groups are linked together by devices called passages. When a computer in an area wants to send data to another computer, it can be in the same area or other area and that computer can be a regular host or server.

The device that connects these areas is called passages or routers and the methods they follow to send data are called protocols. Each passage can be configured to use a certain protocol, but this must be the same among all zones to work correctly.

The Internet uses what is called the TCP / IP connection between these areas in order to send data. The IP protocol is used to deliver a packet between the source and destination based on the IP address that is defined in the protocol. The IP address is 32 bits long and are separated in two parts: one part defines the area or sector in which the host and have the other part defines the host itself. This corresponds to the identification of the street where we need to identify the street name and house number. The street name is the network address and the number of home matches at a computer.

Once the IP address defined passages can use these addresses to send packets between the passages until they reach the destination. Remember that these passages are like airports that are used to travel between the countries and areas on the network correspond to those countries, so when the travel of data between different areas, they must first go to the passages to be shipped.

There are many protocols that can be used to send the packet based on IP address but they all share the same function. Some common names are RIP, OSPF, and IS-IS. Each has its own characteristics scalability point of view, convergence, and memory capacity. When the packet arrives at the router, it checks the IP address and sends a specific port as the address. Each packet can be sent to multiple ports, but the protocol chooses the best port. This process is repeated at each router while the package is its way to the destination.