NVIDIA Ada L40 48GB GDDR6 PCIe Gen 4th 300w - GPU-NVL40
Graphics chip: NVIDIA L40 BUS: PCIe 4.0 x16 Memory size: 48 GB Memory type: GDDR6 Stream processors: 18176 Number of tensor cores: 568 Theoretical performance: 90,5 TFLOP
All NVIDIA Ampere, NVIDIA Grace Hopper, NVIDIA Ada Lovelace GPU and NVIDIA Blackwell architectures are subject to a non-cancellable, non-returnable (NCNR) period of 52 weeks. Additionally, the product is subject to sanctions for certain countries and the end customer must be documented.
We can supply these GPU cards directly and with an individual B2B price. Contact us with your inquiry today.
| Product code | 214.165233 |
|---|---|
| Part number | 900-2G133-0010-000 |
| Supermicro Part No. | GPU-NVL40 |
| Manufacturer | NVIDIA |
| Availability |
In stock 0 pc
Stock allocation and delivery options
Delivery to selected address Friday 10. 1. at the latest Tuesday 21. 1. |
| Supplier availability | In stock 12 pc |
| Warranty | 24 months |
| Weight | 1.2 kg |
Server system integrator & worldwide shipping
Personal approach and tailor-made servers
NBD warranties & cross-shipping
Private cloud infrastructure
Pre-sales & After-sales support
Detailed information
NVIDIA AI GPU
NVIDIA's products are widely regarded as the pinnacle of AI-powered computing. These innovative offers boast ample memory and exceptional performance, unlocking the full potential of your systems by connecting hundreds of cards into a single cohesive unit. The proprietary Tensor Core technology is specifically designed for efficient AI training and inference, ensuring seamless harmony between software and hardware, making NVIDIA products the coveted choice for the world.
Floating point
Using the FLOPS unit, we can estimate the raw performance of graphics cards today. It indicates how many operations per second a graphics card can perform, allowing us to compare them against each other. However, these values can vary depending on the bit size of the floating-point (FP) representation. The larger the bit size, the more accurate the calculations, but also the fewer of them there are. Since gaming PCs need precise values for smooth operation, they mainly use 32-bit FP (or FP32). On the other hand, Deep Learning does not necessarily require such precise calculations, and therefore AI graphics cards use FP8. This drastically reduces the accuracy, but on the other hand increases the number of calculations.
Graphics memory
VRAM, these days primarily of GDDR type, is a synchronous memory, similar to standard RAM. However, in the case of graphic memory, memory chips with faster throughput and multiple data transfer rates are concerned. The result is a much faster buffering of data that the graphics card or coprocessor calculates and passes to the processor.
CUDA Technology
Users of professional applications can benefit from CUDA graphics stream processors thanks to CUDA architecture. Thanks to this, the raw power of the graphics card can be used for specific calculations, which can accelerate the work manifold compared to a classic processor, which is significantly limited by a lower amount of cores.
PCI Express
PCI Express is an interface that usually takes the form of an expansion slot to ensure the modularity of the entire system, whether it is GPU, network cards, controllers, M.2 drives or other expansion cards. It is true that the newer the generation and wider the interface, the higher the performance and throughput. Most modern graphics cards use 16 lanes to connect with the processor. Currently, the most up-to-date generation is PCI Express generation 6.0 with a speed of 7.5 GB/s per lane.
Parameters
| Product line | Tesla |
|---|---|
| Architecture | Ada Lovelace |
| Gigabytes of memory | 48 |
| Number of stream processors | 18176 |
| Memory type | GDDR6 |
| Slot count | Unknown |
| Monitor output | |
| Profile | FH/LP |
| Interface | PCI-E 4.0 16x |
| Cooling type | Active |
| Power consumption (W) | 300 |
