NVIDIA · Pascal · 2016
P100 GPU accelerator (12 GB card)
P100 GPU accelerator (12 GB card): 12 GB HBM2, 250 W, 3,584 CUDA cores. Launched June 20, 2016.
- Memory
- 12 GB
- Power
- 250 W
- Bus width
- 3,072 bit
Memory12 GB
18 of 32 in Data Center
Power250 W
17 of 40 by higher draw in Data Center
CUDA cores3,584
16 of 47 in Data Center
Current market
Affiliate links — we may earn a commission.
Specifications
Memory
- Capacity
- 12 GB
- Memory type
- HBM2
- Bus width
- 3,072 bit
- Bandwidth
- 549 GB/s
Compute
- CUDA cores
- 3,584
- SM count
- 56
- TMUs
- 224
- ROPs
- 96
Clocks
- Base clock
- 1,126 MHz
- Boost clock
- 1,303 MHz
Board
- TDP
- 250 W
- Form factor
- datacenter
Physical
- Architecture
- Pascal
- Series
- Data Center
- Launch date
- June 20, 2016
Not recorded by the source: generation, codename, process and transistors, or 9 further fields.
Die figure
Silicon, made visible
Die area is drawn against the largest recorded die in the catalog. Shader dots use a labeled, card-specific ratio so both early and modern GPUs remain legible.
Catalog context
Within its series, the P100 GPU accelerator (12 GB card) ranks 18th of 32 for memory capacity. Its 250 W TDP is above the 75 W PCIe slot-power ceiling.
Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16