Supercomputers/Systems/PARAM Kamrupa
India · operational · hpc
PARAM Kamrupa
Also known as IIT Guwahati PARAM Kamrupa
Operated by IIT Guwahati at IIT Guwahati Campus .
Researched with AI assistance, checked by scripts. These rows were researched by AI agents reading public operator, laboratory and vendor sources, appended by scripts and checked by automated validation; no subject-matter expert has reviewed them (how this site is made). A mechanical second-reader pass has since fetched every cited source: 1350 of 1581 systems have a readable citation that names them, and 64 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
- 838.00 TFlop/s
- Rmax ÷ Rpeak
- -
- Cores
- 7,408
- 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 |
|---|---|---|---|---|---|
| Accelerator | NVIDIA Tesla V100 Accelerators CUDA (Volta GV100) · 5,120C · 1.53 GHz · 12 nm · 300 W NVIDIA Tesla V100 16GB, 2 per GPU node on 10 nodes (20 cards; 102,400 CUDA cores at 5,120 each) | NVIDIA | 20 estimated | Reported | iitg.ac.in |
| CPU | - 2 x Intel Xeon Platinum 8268 24-core 2.9 GHz per node on 146 CPU, GPU-ready and high-memory nodes | Intel | - | Reported | iitg.ac.in |
| CPU | - 2 x Intel Xeon Gold 6248 20-core 2.5 GHz per node on 10 GPU nodes | Intel | - | Reported | iitg.ac.in |
The read
IIT Guwahati's flagship cluster under the National Supercomputing Mission, inaugurated by President Droupadi Murmu on 13 October 2022 (IIT Guwahati's HPC page and a Careers360 report agree on the date and on the 838 TF peak). The institute's page lists 75 CPU nodes, 32 GPU-ready CPU nodes and 39 high-memory nodes (768 GB) of dual Xeon Platinum 8268, plus 10 GPU nodes with dual Xeon Gold 6248 and two Tesla V100 16 GB cards each, for 7,408 CPU cores, 102,400 CUDA cores, 52 TB of memory and 1 PB of storage. The 102,400 CUDA-core total is exactly 20 V100s at 5,120 each, which is how the GPU count is derived. Neither page names the system builder or the interconnect, so no integrator or interconnect edge is recorded. The same page also lists an older machine, PARAM Ishan (operational since September 2016, 250 TF), and a separate 8-GPU RTX PRO 6000 Blackwell box dated July 2026, neither of which is counted here.
Timeline
- 2022-10 First operational source
Site & facility
Change history
- 2026-10-29 Added PARAM Kamrupa, IIT Guwahati's 838 TF National Supercomputing Mission cluster
Related systems
Same site
- PARAM Ishan · India, operational, 2016
Same accelerator
- PARAM Ananta · India, operational, 2022
- PARAM Ganga · India, operational, 2022
- PARAM Pravega · India, operational, 2022
- ABCI 2.0 · Japan, operational, 2021
- Altair · Poland, operational, 2021
- Ares · Poland, operational, 2021