Difference Between Processor Features & Installing Expansion Cards Into A Server

1.5 Differentiate between processor features / types and given a scenario select the appropriate processor

Multicore: In this two or more processors are combined to get improved performance, efficient parallel processing and reducing power consumption. A dual core processor setup has multiple separate processors installed in same computer, these two processors are plugged in same socket so connection between them is faster.
A multi-threaded processor executes the instructions in parallel, but shares the other resources like registers. A multi-processor system, on the other hand have independent support units. Therefore, other things being equal, a multi processor system is more efficient than a multi-threaded processor based computer. Further, a multi-threaded processor is a single chip where as a multi-processor system will have several independent processor chips
There are 3 levels of cache
- L1 cache : It is closer to processor and it runs at processors speed not at motherboard speed. It ranges from 8KB to 64KB and uses SRAM.
- L2 cache: It is separate from processor and uses back side bus. Also, called as secondary cache is used to reduce data access time in case same data was already accessed before. Also used for buffer program instructions and data requests by processors.
- L3 cache: Not found now a days as its function is replaced by L2 cache.
Stepping: These are minor revisions issued by processor manufacturers for their devices over device life cycle. These are identified by special numbers printed in body of the device.
VRM: Short for voltage regulator module, a small module that installs on a motherboard to regulate the voltage fed to the microprocessor. Nearly all motherboards have either a built-in voltage regulator or a VRM, the only difference being that the VRM is replaceable. The VRM sense the required power needed by a processor by examining the Voltage ID signal (VID) sent during power on self test.
NX (No-Execute): It is the 63rd bit of page table entry, it allows OS to specify which pages if virtaul address space can can contain executable code and which cannot. If any page marked as No-execute is used for execute code will cause memory error.
XD(Execute Disable): It provides same functionality as NX for recent x86 Intel processors.
Hyperthreating: It is term used by Intel^® for simultaneous threading here a single processor appear as two virtual processors to th operating system.
Intel and AMD integrate virtualization support into their microprocessors.

VT(Intel^® Virtualization Technology) includes
- VT-x which provide basic support for vitualization software.
- VT-d ( Virtualization technology for Directed I/O ) provide support for virtualization of I/O transactions
- VT-c (Virtualization technology for Connectivity ).
AMD-V( Advanced Micro Devices Virtualization technology ): Its functionality is similar to VT-x. AMD-V 2.0 includes extra features, such as I/O level Virtualization, and Extended Migration. AMD V 2.0 is supported only in the latest generation of AMD server-class CPUs.
RISC is acronym for Reduced Instruction Set Computing, information processing using microprocessor(s) that are designed to execute computing tasks with the simplest instructions in the shortest amount of time possible. RISC is the opposite of CISC Servers using RISC processors are usually designed for high end applications with high availability and larger processing power. Hence, RISC based servers are usually much more expensive than Intel processor based servers.
CISC (Complex Instruction Set Computing) chips have a large, complex instruction set. Therefore, they typically process complex codes more quickly.

1.6 Given a scenario, install appropriate expansion cards into a server while taking fault tolerance into consideration.

FAX cards : These simulate function of a fax machine by establishing connection between computer and phone line. An adapter that fits into a PC expansion slot.

SCSI

Single-ended devices are more prone to picking up interference and noise so the cable length is set at a limit - 6 meters or approximately 20 feet.
Cable lengths used by SCSI devices are:
- Single Ended (or un balanced) electronic signaling: 6 m 0r 20ft (apx.)
- Differential signaling (HVD-High Voltage Differential): 25 m or 82 ft (apx.)
- Differential signaling (LVD - Low Voltage Differential): 12 m
HVD and S.E. devices cannot co-exist on a SCSI bus, where as LVD and S.E. devices can co-exist on a SCSI Bus.
LVD is backward compatible with SE, through automatic mode sensing of single-ended (SE) or differential bus-configuration types.

HBA : A host bus adapter (HBA) is a integrated circuit adapter. It provides input and output processing and physical connectivity between a server and a storage device. HBA can improve the server's performance timer by relieving the host microprocessor of both data storage and retrieval tasks. An HBA and its associated disk subsystems are sometimes referred to as a disk channel.

The following are true about Serial ATA (SATA):

Serial ATA (SATA) transfers data in a half-duplex channel at 1.5 Gbps With SATA II, introduced in 2003, speed was increased to 3 Gbps.
SATA drops the master/slave shared bus of Parallel ATA, giving each device a dedicated cable and dedicated bandwidth.
SATA allows hot swapping, whereas Parallel ATA does not.
SATA cables use 7-pin, and can be up to 1 m (39 in) long, PATA ribbon cables, in comparison, carry either 40- or 80-conductor wires and are limited to .46 m (18 in) in length.
SATA drives may be plugged into Serial Attached SCSI (SAS) controllers and communicate on the same physical cable as native SAS disks.
The power connector for SATA is completely different from that of PATA. While SATA uses 15-pin connector, PATA uses 4-pin Molex connector. Note that multiple pins are used for carrying same voltage in SATA.