Exabit to Gibibit

One exabit = 10¹⁸ bits = 125,000 terabytes = 125 petabytes. If every person on Earth (8 billion people) each stored 15 GB of data — roughly a modern smartphone's photos and messages — the total would be about 120 exabytes, or about 960 exabits. The entire human genome is about 1.5 GB; sequencing every person on Earth would produce about 12 exabytes of data.

Cisco's annual internet traffic reports estimated global IP traffic at roughly 4.8 exabytes per day in 2022, rising about 20% per year. Expressed in bits, that's about 38 exabits per day or roughly 440 petabits per second continuously. Video streaming accounts for over 60% of total internet traffic volume.

Data gravity is the principle that massive datasets attract applications, services, and additional data toward them — rather than being moved to where processing occurs. At exabit scale, physically transferring data becomes impractical: moving 1 exabit over a 100 Gbps link takes 116 days. Instead, companies deploy compute resources alongside the data. This effect drives cloud concentration — once an organisation stores exabits in AWS or Azure, the cost and latency of moving that data elsewhere creates powerful vendor lock-in, shaping the economics of the entire cloud industry.

The Square Kilometer Array (SKA), under construction in Australia and South Africa, will be the world's largest radio telescope. Its thousands of antennas will collectively produce roughly 1 exabit of raw sensor data per day — more than the entire global internet traffic of the early 2000s. This data cannot be stored in full; instead, on-site supercomputers reduce it by a factor of ~10,000 in real time, keeping only scientifically relevant signals. The SKA illustrates how radio astronomy pushes data processing to extreme scales that rival commercial internet infrastructure.

At 1 Gbps (a fast home connection), downloading 1 exabit would take 1 billion seconds — about 31.7 years. At 1 Tbps (a high-end data center link), it would take 1 million seconds, or about 11.6 days. This illustrates why exabit-scale data movements require massively parallel infrastructure — no single link or device handles exabit transfers directly.

A gigabit (Gbit) = 10⁹ bits = 1,000,000,000 bits (SI). A gibibit (Gibit) = 2³⁰ bits = 1,073,741,824 bits (IEC binary). The difference is 7.37%. Consumer networking equipment and ISP speed ratings use decimal gigabits; memory and chip designers sometimes use gibibits when binary precision is required.

Virtually all networking equipment — routers, switches, NICs, ISP speed ratings — uses decimal gigabits (Gbit). A "1 Gbps" (gigabit per second) connection means exactly 1,000,000,000 bits per second, not 1,073,741,824 bits per second. Network standards (Ethernet IEEE 802.3) are defined in SI units.

DDR memory bandwidth is calculated from clock speed, bus width, and transfers per clock. A DDR5-4800 module on a 64-bit bus delivers 4,800 MT/s × 64 bits = 307,200 Mbit/s ≈ 292.97 Gibit/s. Engineers use gibibits when verifying that memory throughput matches binary-aligned cache line sizes (typically 512 bits = 64 bytes), ensuring no fractional transfers occur during burst reads.

GPU memory bandwidth is typically quoted in gigabytes per second (GB/s) using SI decimal values — not gibibits. For example, NVIDIA's RTX 4090 has 1,008 GB/s of memory bandwidth (decimal). Some academic papers and IEEE publications convert this to GiB/s or Gibit/s for precision, but consumer GPU marketing universally uses SI decimal units.

Gibibit appears in: IEEE standards documents specifying memory interface speeds, JEDEC memory specifications, some academic networking papers, and storage controller datasheets. Consumer-facing software, marketing materials, and OS interfaces virtually never display gibibits — they show gigabits (networking) or gigabytes (storage). It is primarily a precision engineering unit.