Supercomputers/Systems/Yotta D2 Blackwell Ultra Cluster
India · under construction · ai training
Yotta D2 Blackwell Ultra Cluster
Also known as Yotta Blackwell Ultra supercluster
Operated by Yotta Data Services at Yotta D2 Data Centre (Greater Noida) .
Phase 1 seed dataset, compiled by hand. These rows were built from public operator, laboratory and vendor sources. A mechanical second-reader pass has since fetched every cited source: 1092 of 1153 systems have a readable citation that names them, and 40 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.
Measured performance
- Rmax
- -
- Rpeak
- -
- Rmax ÷ Rpeak
- -
- Cores
- -
- Power
- -
- Per watt
- - GF/W
Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.
What this machine is made of
One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.
| Role | Part | Supplier at build | Quantity | Confidence | Source |
|---|---|---|---|---|---|
| Integrator | - Yotta Data Services deploys and operates the supercluster at its D2 data center | Yotta Data Services | - | Reported | cxotoday.com |
| Accelerator | - 20,736 liquid-cooled NVIDIA Blackwell Ultra (HGX B300) GPUs | NVIDIA | 20,736 reported | Reported | cxotoday.comtechtimes.com |
| Interconnect | NVIDIA InfiniBand XDR (Quantum-X800) Interconnect Fat tree or dragonfly+ · 800 Gb/s per port 800 Gbps NVIDIA Quantum-X800 InfiniBand | NVIDIA | - | Reported | cxotoday.com |
AI datacenter metrics
Figures beyond an accelerator count, each with who stated it. What can and cannot be compared across AI datacenters.
| Metric | Value | As of | Basis | Note | Source |
|---|---|---|---|---|---|
| Accelerators | 20,736 accelerators | 2026-02 | Design target | Liquid-cooled Blackwell Ultra GPUs announced 18 Feb 2026 with go-live stated as August 2026. Announcement figure. | cxotoday.com |
| Stated investment | 2 USD bn | 2026-02 | Design target | 'Over $2 billion' stated investment for the supercluster; excludes a separate 'over $1 Bn' four-year NVIDIA DGX Cloud engagement. | cxotoday.com |
| Facility power | 60 MW | 2026-02 | Design target | Capacity of Yotta D2 hyperscale data centre (Greater Noida) hosting the cluster; page also says scalable to 250 MW across campus. Not cluster-only draw. | cxotoday.com |
Compute deals
- 2026-02-18: Yotta Data Services and NVIDIA (chip supply , 60 MW, headline $2bn). cxotoday.com
All compute deals. Headline values are as announced, not additive.
The read
Yotta Data Services' 20,736-GPU NVIDIA Blackwell Ultra (HGX B300) supercluster at its 60 MW D2 data center in Greater Noida, announced on 18 February 2026 at the India AI Impact Summit on an investment above 2 billion dollars. It is liquid-cooled with 800 Gbps Quantum-X800 InfiniBand, and more than 10,000 of the GPUs are committed to the IndiaAI Mission for sovereign foundation models, plus a DGX Cloud engagement with NVIDIA. Go-live was targeted for August 2026; TechTimes on 12 September 2026 still describes it as targeted and does not confirm operation, so it is recorded as under construction pending confirmation. Yotta's separate September 2026 plan for 40,000 Vera Rubin GPUs at a 120 MW D4 facility (May to August 2027) and 40,000 GB300 at NM2 Navi Mumbai is not recorded here. Distinct from the operational Shakti Cloud TOP500 system.
Timeline
- 2026-02-18 Announced source
Site & facility
Yotta D2 Data Centre (Greater Noida)
- Location
- Greater Noida, Uttar Pradesh, India
Change history
- 2026-10-04 Added AI datacenter metrics for yotta-d2-blackwell-ultra
- 2026-10-02 Added Yotta D2 Blackwell Ultra Cluster, 20,736 B300 GPUs for India
Source check
We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.
| Cited source | Result | Found on the page |
|---|---|---|
| cxotoday.com | blocked our fetch | - |
| techtimes.com | names system only | - |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.
Inside a node
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.