This article includes a list of references, related reading or external links, but its sources remain unclear because it lacks inline citations .(October 2009) |
GIO is a computer bus standard developed by SGI and used in a variety of their products in the 1990s as their primary expansion system. GIO was similar in concept to competing standards such as NuBus or (later) PCI, but saw little use outside SGI and severely limited the devices available on their platform as a result. Most devices using GIO were SGI's own graphics cards, although a number of cards supporting high-speed data access such as Fibre Channel and FDDI were available from third parties. Later SGI machines use the XIO bus, which is laid out as a computer network as opposed to a bus.
Like most busses of the era, GIO was a 32-bit address and data multiplexed bus that was normally clocked at 25 or 33 MHz. This meant that the bus uses the same path for addressing and data, thus normally requiring three cycles to transfer a single 32-bit value; one cycle to send the address, the next to send the data and then another to read or write it. This limited the bus to a maximum throughput of about 16 Mbyte/s at 33 MHz for these sorts of small transfers. However the system also included a long-burst read/write mode that allowed continual transfers of up to 4 kilobytes of data (the fundamental page size in R3000-based SGI machines); using this mode dramatically increased the throughput to 132 Mbyte/s (32 bits per cycle * 33 MHz). GIO also included a "real time" interrupt allowing devices to interrupt these long transfers if needed. Bus arbitration was controlled by the Processor Interface Controller (PIC) in the original R3000-based SGI Indigo systems.
Physically, GIO used a 96-pin connector and fairly small cards 6.44 inches (16.3576 cm) long by 3.375 inches (8.5725 cm) wide. In the Indigo series, the cards were aligned vertically above each other within the case, as opposed to the more common arrangement where the cards lie at right angles to the motherboard. This led to a "tall and skinny" case design. Since the cards were "above" each other in-line, it was possible to build a card that connected to both connectors on the computer's motherboard, thereby offering more room.
GIO was later expanded to a 64-bit form, GIO64, retroactively renaming the earlier version GIO32. Addressing remained 32-bit but now allowed for both big-endian and little-endian addressing as indicated by a new control pin, whereas GIO32 only supported the SGI-style big-endian addresses. Data could now be transferred 64-bits at a time thereby doubling the speed. GIO64 could also be run faster than GIO32, up to 40 MHz, providing a maximum streaming throughput of 320 Mbyte/s. The page sizes were also adjusted to allow for the changing CPU's, starting at 4 kbyte for R3000 based machines, and up to 16 Mbyte for R4400 based ones.
Physically the GIO64 bus used much larger cards that were generally similar in size and layout to EISA cards, a deliberate choice that made development somewhat easier as well as allowing SGI to place EISA slots in the same machines. Specifically the external connector (the metal flange) was identical to EISA, but the shape of the board itself was slightly different.
Two versions of GIO64 were specified. The "non-pipelined" system worked in a fashion similar to that of GIO32, with transfers being set up directly on the bus. The newer "pipelined" system was what the actual boards used, and as the name implies the system set up transfers in a several-step operation that was decoded in the controller's internal pipeline. Internally the non-pipelined bus transferred data between the various parts of the computer, including GIO cards, EISA devices, SCSI and so forth. GIO cards used the pipelined controller to arbitrate and control timing, the data then being fed into main memory via the internal non-pipelined side.
A third standard, GIO32-bis, used the signals and timing of GIO64, but with the 32-bit connectors from GIO32. Properly designed GIO32-bis cards could be used in GIO64, GIO32 or GIO32-bis slots, differentiating the later two by looking at a pin tied to the ground in the original GIO32, and tied "high" in GIO32-bis. For low-throughput cards, GIO32-bis allowed a single device to be used on any machine supporting GIO, no matter what generation.
The Extended Industry Standard Architecture is a bus standard for IBM PC compatible computers. It was announced in September 1988 by a consortium of PC clone vendors as an alternative to IBM's proprietary Micro Channel architecture (MCA) in its PS/2 series.
Industry Standard Architecture (ISA) is the 16-bit internal bus of IBM PC/AT and similar computers based on the Intel 80286 and its immediate successors during the 1980s. The bus was (largely) backward compatible with the 8-bit bus of the 8088-based IBM PC, including the IBM PC/XT as well as IBM PC compatibles.
The Intel 486, officially named i486 and also known as 80486, is a higher-performance follow-up to the Intel 386 microprocessor. The i486 was introduced in 1989 and was the first tightly pipelined x86 design as well as the first x86 chip to use more than a million transistors, due to a large on-chip cache and an integrated floating-point unit. It represents a fourth generation of binary compatible CPUs since the original 8086 of 1978.
Peripheral Component Interconnect (PCI) is a local computer bus for attaching hardware devices in a computer and is part of the PCI Local Bus standard. The PCI bus supports the functions found on a processor bus but in a standardized format that is independent of any given processor's native bus. Devices connected to the PCI bus appear to a bus master to be connected directly to its own bus and are assigned addresses in the processor's address space. It is a parallel bus, synchronous to a single bus clock. Attached devices can take either the form of an integrated circuit fitted onto the motherboard or an expansion card that fits into a slot. The PCI Local Bus was first implemented in IBM PC compatibles, where it displaced the combination of several slow Industry Standard Architecture (ISA) slots and one fast VESA Local Bus (VLB) slot as the bus configuration. It has subsequently been adopted for other computer types. Typical PCI cards used in PCs include: network cards, sound cards, modems, extra ports such as Universal Serial Bus (USB) or serial, TV tuner cards and hard disk drive host adapters. PCI video cards replaced ISA and VLB cards until rising bandwidth needs outgrew the abilities of PCI. The preferred interface for video cards then became Accelerated Graphics Port (AGP), a superset of PCI, before giving way to PCI Express.
The VESA Local Bus is a short-lived expansion bus introduced during the i486 generation of x86 IBM-compatible personal computers. Created by VESA, the VESA Local Bus worked alongside the then-dominant ISA bus to provide a standardized high-speed conduit intended primarily to accelerate video (graphics) operations. VLB provides a standardized fast path that add-in (video) card makers could tap for greatly accelerated memory-mapped I/O and DMA, while still using the familiar ISA bus to handle basic device duties such as interrupts and port-mapped I/O.
Direct memory access (DMA) is a feature of computer systems that allows certain hardware subsystems to access main system memory independently of the central processing unit (CPU).
NuBus is a 32-bit parallel computer bus, originally developed at MIT and standardized in 1987 as a part of the NuMachine workstation project. The first complete implementation of the NuBus was done by Western Digital for their NuMachine, and for the Lisp Machines Inc. LMI Lambda. The NuBus was later incorporated in Lisp products by Texas Instruments (Explorer), and used as the main expansion bus by Apple Computer and a variant called NeXTBus was developed by NeXT. It is no longer widely used outside the embedded market.
Micro Channel architecture, or the Micro Channel bus, was a proprietary 16- or 32-bit parallel computer bus introduced by IBM in 1987 which was used on PS/2 and other computers until the mid-1990s. Its name is commonly abbreviated as "MCA", although not by IBM. In IBM products, it superseded the ISA bus and was itself subsequently superseded by the PCI bus architecture.
A SCSI host adapter is a device used to connect one or more other SCSI devices to a computer bus. It is commonly called a SCSI controller, which is not strictly correct as any component understanding the SCSI protocol can be called a controller. In this sense all SCSI devices have a SCSI controller built into them, while host adapters bear responsibility for transferring data between the SCSI bus and the computer's input/output bus. SCSI adapters serve as a worthy adapter for FireWire Ports.
The SGI Indigo2 and the SGI Challenge M are Unix workstations which were designed and sold by SGI from 1992 to 1997.
Octane series of IRIX workstations was developed and sold by SGI in the 2000s. Octane and Octane2 are two-way multiprocessing-capable workstations, originally based on the MIPS Technologies R10000 microprocessor. Newer Octanes are based on the R12000 and R14000. The Octane2 has four improvements: a revised power supply, system board, and Xbow ASIC. The Octane2 has VPro graphics and supports all the VPro cards. Later revisions of the Octane include some of the improvements introduced in the Octane2. The codenames for the Octane and Octane2 are "Racer" and "Speedracer" respectively.
PCI-X, short for Peripheral Component Interconnect eXtended, is a computer bus and expansion card standard that enhances the 32-bit PCI local bus for higher bandwidth demanded mostly by servers and workstations. It uses a modified protocol to support higher clock speeds, but is otherwise similar in electrical implementation. PCI-X 2.0 added speeds up to 533 MHz, with a reduction in electrical signal levels.
XIO is a packet-based, high-performance computer bus employed by the SGI Origin 2000, Octane, Altix, Fuel and Tezro machines. The XIO forms a bus between high-performance system devices and the memory controller.
The Indigo, introduced as the IRIS Indigo, is a line of workstation computers developed and manufactured by Silicon Graphics, Inc. (SGI). SGI first announced the system in July 1991.
Multibus is a computer bus standard used in industrial systems. It was developed by Intel Corporation and was adopted as the IEEE 796 bus.
The feature connector was an internal connector found mostly in some older ISA, VESA Local Bus, and PCI graphics cards, but also on some early AGP ones. It was intended for use by devices which needed to exchange large amounts of data with the graphics card without hogging a computer system's CPU or data bus, such as TV tuner cards, video capture cards, MPEG video decoders, and first generation 3D graphic accelerator cards. Early examples include the IBM EGA video adapter.
Released as the expansion bus of the Commodore Amiga 3000 in 1990, the Zorro III computer bus was used to attach peripheral devices to an Amiga motherboard. Designed by Commodore International lead engineer Dave Haynie, the 32-bit Zorro III replaced the 16-bit Zorro II bus used in the Amiga 2000. As with the Zorro II bus, Zorro III allowed for true Plug and Play autodetection wherein devices were dynamically allocated the resources they needed on boot.
The R10000, code-named "T5", is a RISC microprocessor implementation of the MIPS IV instruction set architecture (ISA) developed by MIPS Technologies, Inc. (MTI), then a division of Silicon Graphics, Inc. (SGI). The chief designers are Chris Rowen and Kenneth C. Yeager. The R10000 microarchitecture is known as ANDES, an abbreviation for Architecture with Non-sequential Dynamic Execution Scheduling. The R10000 largely replaces the R8000 in the high-end and the R4400 elsewhere. MTI was a fabless semiconductor company; the R10000 was fabricated by NEC and Toshiba. Previous fabricators of MIPS microprocessors such as Integrated Device Technology (IDT) and three others did not fabricate the R10000 as it was more expensive to do so than the R4000 and R4400.
The R5000 is a 64-bit, little endian (mipsel) superscalar, in-order execution 2-issue design microprocessor, that implements the MIPS IV instruction set architecture (ISA) developed by Quantum Effect Design (QED) in 1996. The project was funded by MIPS Technologies, Inc (MTI), also the licensor. MTI then licensed the design to Integrated Device Technology (IDT), NEC, NKK, and Toshiba. The R5000 succeeded the QED R4600 and R4700 as their flagship high-end embedded microprocessor. IDT marketed its version of the R5000 as the 79RV5000, NEC as VR5000, NKK as the NR5000, and Toshiba as the TX5000. The R5000 was sold to PMC-Sierra when the company acquired QED. Derivatives of the R5000 are still in production today for embedded systems.
Since 1985, many processors implementing some version of the MIPS architecture have been designed and used widely.