Data centres and servers
Xeon, EPYC, Graviton, H100 and the chips of the cloud. 296 chips on EveryChip so far.
Data centres and cloud servers use the largest and most power-hungry chips: server CPUs with up to a few hundred cores, AI accelerators drawing 700 W to over 1,000 W each, network chips and DPUs, and huge amounts of memory. Intel's Xeon and AMD's Epyc dominate general-purpose servers, while Arm designs such as Amazon's Graviton have grown fast. Nvidia's GPUs lead in AI.
Server CPUs
A server processor is built for many tasks at once and for long, reliable running. It supports large amounts of error-correcting memory, many PCIe lanes for storage and network cards, and two or more sockets on one board. AMD's Epyc, launched in 2017, used chiplets to fit more cores than single-die designs, and took a large share of the market from Intel's Xeon.
Custom cloud chips
The largest cloud companies now design their own chips. Amazon has Graviton CPUs and Trainium and Inferentia AI chips, Google its TPU and Axion CPU, and Microsoft its Cobalt CPU and Maia accelerator. They buy fewer standard parts this way and tune chips to their own software. The power used by AI servers has become a constraint on where data centres can be built.
Famous data centres and servers chips
Still to be written: AWS Graviton.
Further reading
🇺🇸 United StatesClipper
32-bit RISC-like CPU architecture by Fairchild and IntergraphCPU · RISC · 1986
🇺🇸 United StatesBroadwell
Intel's 14 nm shrink of the Haswell CPU microarchitectureCPU · x86 · 2014
🇯🇵 JapanSPARC64 V
Single-core SPARC V9 server microprocessor by FujitsuCPU · Other · 2001
🇺🇸 United StatesMotorola 68010
16/32-bit microprocessor with virtual memory support from 1982CPU · 68k · 1982
Photo credits on this page
The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.
- Epyc: Smial ( talk ), FAL, source
- Granite Rapids: Intel Corporation, Public domain, source
- HP FOCUS: Thomas Schanz, CC BY-SA 3.0, source
- Zen 4: FritzchensFritz, CC0, source
- Bulldozer: htomari, CC BY-SA 2.0, source
- Clipper: Unknown author, CC BY-SA 3.0, source
- Broadwell: Asimzb, CC BY-SA 4.0, source
- Ice Lake: Fritzchens Fritz, CC0, source
- Rocket Lake: 4300streetcar, CC BY 4.0, source
- Sapphire Rapids: 极客湾Geekerwan, CC BY 3.0, source
- Cascade Lake: Smial ( talk ), FAL, source
- Rigel: Pauli Rautakorpi, CC BY 3.0, source
- SX-Aurora TSUBASA: Vectoriser, CC BY-SA 4.0, source
- TILEPro64: CoreGuy, CC BY-SA 3.0, source
- SPARC64 V: 223系新快速, CC BY-SA 4.0, source
- POWER1: Retro-Computing Society of Rhode Island, CC BY-SA 3.0, source
- POWER2: Henriok, CC0, source
- POWER3: Henriok, CC0, source
- POWER4: Henriok, CC0, source
- POWER8: Henriok, CC0, source
- POWER6: Henriok, CC0, source
- Kentsfield: MrBurns, CC BY-SA 3.0, source
- IBM RS64: Henriok, CC0, source
- PA-7100: Konstantin Lanzet (with permission), CC BY-SA 3.0, source
- Tensor Processing Unit: Norman P. Jouppi, George Kurian, Sheng Li, Peter Ma, Rahul Nagarajan,, CC BY 4.0, source
- PA-7200: Thomas Schanz, CC BY-SA 4.0, source
- PA-8000: Thomas Schanz, CC BY-SA 4.0, source
- Motorola 68020: David Monniaux, CC BY-SA 3.0, source
- Motorola 68010: Konstantin Lanzet (with permission), CC BY-SA 3.0, source
- Elbrus-8S: Fritzchens Fritz, CC0, source
- IBM Power: Henriok, CC0, source
- Hopper: 极客湾Geekerwan, CC BY 3.0, source