Newegg.com - A great place to buy computers, computer parts, electronics, software, accessories, and DVDs online. With great prices, fast shipping, and top-rated customer service - once you know, you Newegg.
Server Motherboard Glossary
Table of contents
AC '97 (Audio Codec '97) is the audio standard/architecture developed by Intel in 1997. It delivers multichannel 16-bit, 48 KHz recording and playback, with optional support of 18-bit and 20-bit resolution and up to 96 KHz sampling frequency (stereo). AC '97 is widely used in on-board audio, modems and sound cards.
The AGP (Accelerated Graphics Port) slot on the computer motherboard is designed specifically for AGP graphics cards. AGP 8X can provide 16 times the bandwidth of the common 32-bit PCI slot. AGP is currently being phased out in favor of PCI Express on PC systems.
AGP Pro is an extension to the AGP interface specification; it is designed to meet the increasing power requirement of workstation level graphics cards by delivering additional electrical power. AGP Pro graphics cards and slots are often longer than their standard AGP counterparts.
Developed by Intel in 1995, ATX (Advanced Technology Extended) was designed to replace the AT/Baby AT form factor. An ATX motherboard is essentially a Baby AT motherboard rotated 90 degrees within the case with a new mounting configuration for the power supply so that the IDE connectors are closer to the drive bays and the CPU is closer to the power supply and cooling fan. There are many variants of the ATX form factor for smaller boards (such as microATX and Flex ATX), usually providing the basic rear layout but reducing the board size and the number of expansion slots. There are also Extended ATX (EATX) motherboards, which are larger than standard ATX form factor and often used for workstation/server systems.
The BIOS (Basic Input/Output System) refers to the program/software code residing in a ROM chip. It provides the basic instructions for booting up your computer and controlling computer hardware so other software programs such as the operating systems can be loaded and executed.
The bus often refers to a data pathway (sometimes called the power pathway) which transfers data (or power) between computer components inside a computer system or between different computers. For example, there is a front side bus to connect the CPU to the chipset, and there is the PCI bus to connect the chipset to PCI devices.
An advanced ECC memory technology developed by IBM. Chipkill technology distributes the bits of an ECC word across multiple memory chips so that a single memory chip failure will only affect one ECC bit out of an ECC word. In this way, Chipkill allows memory data to be reconstructed with one memory chip failure and multi-bit data errors from a single memory chip.
In motherboards the CMOS (Complementary Metal-Oxide Semiconductors) refers to the chips that contains the basic start-up information for the BIOS (aka BIOS settings).
In motherboards, the "codec" (Compressor-Decompressor or Coder-Decoder) or "audio codec" refers to the combined audio AD/DA (analog to digital/digital to analog) converter, which is a required hardware for most onboard audio solutions.
The CPU socket or slot is the interface of both the processor and the motherboard. The processor's socket type must match the motherboard's CPU socket to be installed properly. For example, an LGA 771 processor must be installed on an LGA 771 motherboard. Socket 603/604 and LGA 771 are often seen on Intel-compatible server motherboards, and Socket 940 and Socket F (Socket 1207) are for AMD-compatible server motherboards.
DDR (Double Data Rate) SDRAM sends and receives data twice as often as common SDRAM. This is achieved by transferring data on both the rising edge and the falling edge of a clock cycle.
Second generation DDR memory provides greater bandwidth and other new features such as On-Chip Termination (OCT). 4 bits of data are moved from the memory array to the I/O buffers (per data line) each core cycle. This can be described as 4-bit prefetch, as opposed to the single-bit fetch in SDRAM and 2-bit prefetch with DDR SDRAM.
The most common type of memory module is the DIMM (Dual In-Line Memory Module), which is capable of transferring 64 bits of data per cycle.
The memory cells of DRAM (Dynamic Random Access Memory) memory modules require constant refreshing because they utilize both transistors and capacitors. Capacitors lose the values they store as time elapses without refreshing.
In the memory system, this describes a motherboard/memory controller with two 64-bit wide channels. When memory is used in dual channel mode, the bandwidth doubles - for instance, dual channel DDR400 provides 6400MB/s (or 6.4GB/s) bandwidth as opposed to 3200MB/s for single channel DDR400.
DVI (Digital Video Interface) is a display/monitor interface standard. There are three types DVI: DVI-I (digital and analog), DVI-D (digital only) and DVI-A (analog only). Many current display devices use DVI to receive video signals, such as LCD monitors and projectors. For compatibility with these display devices, most video cards today equip the DVI port as a standard output port.
ECC (Error Checking and Correction) can be accomplished through a variety of methods. The most popular method utilized by memory modules is single bit error correction, which is capable of detecting and correcting single-bit errors. It will also detect two-bit and some multiple bit errors, but is unable to correct them.
Fully Buffered DIMM technology aims to increase reliability, bandwidth and density of the memory system. FB-DIMM architecture introduces Advanced Memory Buffer (AMB) between the memory controller and DRAM chips. The interface between AMB and DRAM chips now supports DDR2 with the potential to, support DDR3 in the future, which is the same as common memory modules. But unlike the parallel interface utilized by traditional memory modules, the interface between the memory controller and the AMB of FB-DIMM memory is a point-to-point serial bus.
In computing, form factor is an industry term for the size, shape and format of computer motherboards, power supplies, cases, add-in cards and so on. The ATX and BTX form factors are the most prevalent form factors today.
Also known by the trademarked names of FireWire and i.LINK, IEEE 1394 is a standard for high-speed transfer of digital information. It is one of the most popular standards for connecting computers and other digital devices to various components and peripherals, such as external hard disk drives, scanners and digital video camcorders.
I/O (Input / Output) often refers to the connection or interface between your computer system and other internal or peripheral hardware devices.
IPMI (Intelligent Platform Management Interface) specifications define common interfaces to the platform management subsystem for system health monitoring and system management. Typical monitoring elements include system voltages, temperatures, fans, power supplies, and etc. IPMI includes the definition of interfaces for extending platform management between motherboards within the main chassis, and between multiple chassis.
A LAN (Local-Area Network) is a computer network that connects PCs, workstations or other LANs and networks to enable data and device access and sharing. It is used to cover a small local area such as a home, office or small group of buildings. Current LANs are most likely to be Ethernet (wired) or Wi-Fi (wireless) based.
Originally called LPT, the Parallel Port is an interface in a computer system where data is transferred in parallel. It has been replaced by the USB port, and is considered to be a legacy port.
ATA is the acronym for Advanced Technology Attachment, and it has become an industry standard hard drive interface for 15 years. ATA uses a 16-bit parallel connection to make the link between storage devices and motherboards, and is also called PATA (Parallel ATA) to distinguish it from the newer SATA standard. In additional, ATA is also known as IDE or EIDE (Enhanced Integrated Drive Electronics). Currently the two most popular standards for ATA hard drives are the ATA-6 (which is also known as Ultra ATA 100 or Ultra DMA 100) and ATA 133. The maximum bandwidth for the former is 100MB/s, and 133 MB/s for the latter.
The PCI (Peripheral Component Interconnect) bus is a computer bus type used to connect computer peripherals. Most PCI buses in a PC system work at 33MHz with a 32bit bit-width. This allows it to deliver a bandwidth of 133MB/s. 64-bit/66MHz PCI slots can also be found in server/workstation systems.
PCI Express is the next generation computer bus following PCI and AGP. PCI Express can come in several physical configurations to offer a variety of maximum bandwidths. For example, the fastest PCI Express x16 (first generation) configuration is used mainly for graphics card application and provides up to 8GB/s (bi-directional) bandwidth, or 4 times the bandwidth of AGP 8X. At the other end of the spectrum, PCI Express x1 is typically used for other types of peripherals and offers up to 500MB/s (bi-directional) bandwidth. The latest PCI Express 2.0 doubles the bandwidth by delivering up to 1GB/s (bi-directional) bandwidth over an x1 link.
PCI-X was introduced to address the need for increased bandwidth of PCI devices. PCI-X specification enables higher operating frequency (66MHz, 133MHz, 266MHz and even 533MHz) with up to 64-bit bit-width of the bus, so it is capable of delivering more than 1066MB/s of bandwidth. PCI-X protocol enhancements allow devices to operate at much higher efficiency to provide more useable bandwidth at any clock frequency.
The Personal System/2 or PS/2 was the designation for IBM's second generation of personal computers. The PS/2 keyboard and mouse ports were introduced with it. PS/2 ports connect the keyboard and mouse to a computer and are usually color-coded on today’s systems - purple for keyboards and green for mice. Most desktop motherboards still provide PS/2 ports, but an increasing number of keyboards and mice are using USB ports.
RAID (Redundant Array of Independent/Inexpensive Disks) is a method of using multiple hard drives together for data storage. A RAID system with multiple hard drives appears as a single drive to the operating system. Depending on the RAID level, the benefits provided by RAID is one or more of the following: better throughput, fault-tolerance or capacity (or something else) when compared to single hard drive.
1. RAID level 0 (or RAID 0) is known as striping, where data is striped across multiple hard drives. RAID 0 provides the most advanced throughput and capacity, but offers no fault-tolerance.
2. RAID level 1 (RAID 1) is known as mirroring, which stores the exact same data within at least two hard drives, this method shows excellent fault-tolerance and reliability, but delivers less capacity efficiency.
3. RAID level 0+1 and RAID 1+0 are both striping and mirroring, providing good fault-tolerance and throughput all at the same time.
4. RAID level 5 utilizes data block striping with distributed parity data blocks across all the array disks. RAID 5 provides excellent read performance but relatively poor write performance. RAID 5 is able to recover the whole array when one of its array disks fails, but the failure of a second disk results in data loss.
5. RAID level 6 is an extension of RAID 5 and an additional parity block is added for extra fault-tolerance. RAID 6 is able to recover the array when two disks fail.
There are other RAID levels available too, such as RAID level 3 and RAID level 4, which are not widely used nowadays.
Almost all system memory in today's PCs is unbuffered memory. With increasing system memory, the stability and performance deterioration of memory is inevitable since the memory controller has to address each memory chip on all modules directly. To solve this problem, higher density systems use registered memory instead which contains registers as buffer to temporarily hold data for one clock cycle before it is transferred. This increases the reliability of high-speed data access to high density memory. Registered memory modules are typically used only in servers and other mission-critical systems where it is extremely important that the data is properly handled.
Serial Attached SCSI. Earmarked as the next-generation enterprise storage interface to replace parallel SCSI, SAS utilizes serial communication protocol for high bandwidth and throughput performance in corporate and enterprise applications. Thanks to SAS' compatibility with serial ATA, it may also be the interface of choice for high-performance desktop storage in the future.
SATA (Serial ATA) is an interface standard for connecting hard drives to computer systems, and is based on serial signaling technology. The advantages over PATA include longer, thinner cables for more efficient airflow within a computer chassis, fewer pin conductors for reduced electromagnetic interference, and lower signal voltage to minimize noise margin. The bandwidth of SATA is also far improved over today's PATA - the SATA 1.0 can reach a maximum of 1.5Gb/s (150MB/s), while the latest SATA 2.5 standard can support up to 3Gb/s (300MB/s). As a result of so many advantages, the SATA interface is gradually replacing PATA as the mainstream hard drive interface in the personal storage market.
SCSI (Small Computer System Interface) is a standard interface for transferring data between devices and computers. Thanks to its outstanding ability to compartmentalize diverse operation, SCSI is very suitable for multitasking operating environments. Also, SCSI enhances critical performance in situations where more than one device is connected. Before serial signaling technology was applied into the SCSI field, all SCSI interface standards used parallel technology to transfer data.
SDRAM (Synchronous Dynamic Random Access Memory) has a synchronous interface. It waits for a clock pulse before transferring data and is therefore synchronous with the computer system bus and processor. This greatly improves performance over asynchronous DRAM.
Unlike parallel port, serial port (aka COM) is an interface on a computer system which transfers information one bit at a time. Most serial ports of personal computer uses RS-232 standard, and RS-232 is still commonly used in industry devices. Serial port has also been replaced by USB ports (and PS/2 ports).
S/PDIF (Sony/Philips Digital Interface) is a digital audio interface widely used in consumer electronics and sound cards. There are several different types of cables and connectors for S/PDIF:
1. Coaxial or RCA jack, digital audio information is transferred in the form of an electronic signal.
2. Optical or "TOSLINK", all information is transferred in optical signal form.
This 15-pin VGA (Video Graphics Array) output port (aka D-sub) finds widespread usage and is used to connect a computer to CRT monitors and LCD monitors that support analog input. Digital signals must go through RAMDAC conversion before being sent through the D-Sub port as it is capable of only analog input.