Conversion from Gigabits per second to Teraoctets per second

=

Invert

Formula to convert Gigabits per second (Gbit/s) to Teraoctets per second (To/s)

More information

Gigabits per second to Teraoctets per second conversion table

Gigabits per second (Gbit/s)Teraoctets per second (To/s)
1 Gigabit per second0.000125 To/s
2 Gigabits per second0.00025 To/s
3 Gigabits per second0.000375 To/s
4 Gigabits per second0.0005 To/s
5 Gigabits per second0.000625 To/s
10 Gigabits per second0.00125 To/s
20 Gigabits per second0.0025 To/s
25 Gigabits per second0.003125 To/s
50 Gigabits per second0.00625 To/s
100 Gigabits per second0.0125 To/s

Data-transfer rate reference points

ReferenceGigabits per second (Gbit/s)Teraoctets per second (To/s)
A dial-up modem0.000056 Gbit/s0.000000007 To/s
Typical home broadband0.1 Gbit/s0.0000125 To/s
Gigabit Ethernet1 Gbit/s0.000125 To/s
Streaming a 4K film0.025 Gbit/s0.000003125 To/s

Try our other unit converters

LengthMassTemperatureEnergyVolumeSpeedTimeDataPressureFrequencyData-transfer rateVolumetric flow rateAngleArea

Information about the Gigabit per second (Gbit/s)

The gigabit per second is a unit of data transfer rate equal to one thousand million bits per second. Its symbol is Gbit/s, often written Gbps. It names the standard of wired local networking and, increasingly, of domestic fibre connections.

Gigabit Ethernet was standardised in 1998 for optical fibre and in 1999 for ordinary twisted-pair copper, and the copper version is what made it universal. It runs a hundred metres over the same cabling that carried the hundred-megabit standard before it, which meant buildings could be upgraded by replacing equipment rather than wiring. That single property fixed the gigabit as the default connection for a generation.

In octets a gigabit per second is 125 megaoctets per second. That is roughly the speed of a good mechanical hard drive and well below a modern solid-state drive, which is why gigabit networking is no longer the bottleneck it once was: the network can now outrun the storage at one end or the other in many common setups.

Domestic fibre services advertise a gigabit routinely, and the figure has become a marketing threshold more than a technical one. Practically no household can saturate it — a gigabit is enough for around two hundred simultaneous high-definition video streams — and the benefit in daily use is not throughput but the absence of congestion, which keeps latency low and steady.

Above the gigabit the ladder continues in the same steps. Ten-gigabit Ethernet is standard between servers and switches in data centres; twenty-five, forty, hundred and four-hundred-gigabit links join racks, buildings and cities. Each is a multiple of the same unit, and each is still counted in bits per second because that is what the optics and the copper actually carry.

Wireless has followed. The later wireless local network standards quote peak rates above a gigabit per second, though those figures assume a single device, ideal conditions and the full width of the channel. Real wireless throughput in a normal home is typically a third to a half of the advertised peak, and the gap widens with every additional device.

One gigabit per second equals 1,000,000,000 bits per second, 125 megaoctets per second, or about 0.9313 gibibits per second.


Information about the Teraoctet per second (To/s)

The teraoctet per second is a unit of data transfer rate equal to a thousand gigaoctets per second, or eight terabits per second. Its symbol is To/s. It describes memory bandwidth inside the fastest processors and the aggregate throughput of large computing systems, rather than any link between separate machines.

Graphics and accelerator chips are the clearest example. A modern accelerator uses stacked memory placed alongside the processor on the same package, and the bandwidth between them reaches several teraoctets per second. That figure is what allows thousands of arithmetic units to be kept busy at once, and it is now the property that most often determines how fast a machine learning workload runs.

The reason bandwidth rather than arithmetic has become the limiting factor is worth stating. Processors have grown far faster at computing than memory has at supplying data, so a modern chip can perform tens of operations for every octet it reads. Any calculation that touches memory more often than that is limited by the memory, and most real calculations are.

Supercomputer interconnects reach this range in aggregate. The network joining thousands of nodes carries teraoctets per second across the whole machine, though no single link does. The design problem is to arrange the topology so that any node can reach any other quickly, which is why these networks are built as multi-dimensional meshes and trees rather than as simple stars.

To make the number concrete, one teraoctet per second would fill a large consumer hard drive in twenty seconds and transfer the entire text of every book in a national library within a minute. Nothing in ordinary use approaches it, and no external cable of any kind carries it.

The unit also appears in descriptions of storage arrays. A large parallel filesystem, spread across thousands of drives, can deliver a few teraoctets per second in aggregate to a supercomputer, and that figure is quoted as a headline specification because it determines how quickly a simulation can be written out and read back.

One teraoctet per second equals 1,000 gigaoctets per second, 8 terabits per second, or about 0.9095 tebioctets per second.