Be the first to review “PNY NVIDIA A40 48GB Passive Ampere GPU” Cancel reply
Our website uses cookies to give you the best experience possible. By continuing to use our site, you agree with our use of cookies outlined in our Privacy Policy
PNY NVIDIA A40 48GB Passive Ampere GPU
SKU: GPURETAILNA4048GBPCIE
Categories: NVIDIA Data Centre GPUs
The NVIDIA A40 is the best in class GPU for multi-workload capabilities. This powerful Data Centre GPU combines the latest top of the range professional graphics with highly advanced compute and AI acceleration capabilities making it the perfect choice for design, creative and scientific workflows. Ideally suited for virtual workstations and remote server-based configurations, the NVIDIA A40 excels at GPU accelerated simulation & analysis, ray-traced rendering, virtual production and many more professional tasks.
Details & Specifications
Details & Specifications
| Manufacturer | |
|---|---|
| Manufacturer Part Number | NVA40TCGPU-KIT |
Cooling:
| Passive Cooling | Yes |
|---|
Dimensions:
| Item Depth (CM) | 26.67 |
|---|---|
| Item Width (CM) | 11.176 |
External IO:
| # DisplayPort | 3x 1.4 |
|---|
GPU:
| # CUDA Cores | 10752 |
|---|---|
| # RT Cores | 84 |
| # Tensor Cores | 336 |
| ECC Support | Yes |
| GPU Architecture | |
| GPU Slot Size | |
| Lithography | 8nm |
| NEBS ready | Level 3 |
| NVENC | NVDEC | 1x | 2x (includes AV1 decode) |
| NVLINK Bandwidth | 112.5 GB/s (bidirectional) PCIe Gen4 31.5 GB/s (bidirectional) |
| NVLINK Support | Yes |
| Peak BF16 Tensor TFLOPS with FP32 Accumulate | 149.7 | 299.4 |
| Peak FP16 Tensor TFLOPS with FP16 Accumulate | 149.7 | 299.4 |
| Peak FP32 TFLOPS (non-Tensor) | 37.4 |
| Peak INT 4 Tensor TOPS | 598.7 | 1,197.4 |
| Peak INT8 Tensor TOPS | Up to 299.3 | 598.6 |
| Peak TF32 Tensor TFLOPS | 74.8 | 149.6 |
| RT Core Performance (TFLOPS) | 73.1 |
Memory:
| Memory Bandwidth (GB/s) | 696 |
|---|---|
| Memory Capacity (GB) | 48 |
| Memory Interface (bit) | 384 |
| Memory Type | GDDR6 |
PCIe:
| PCIe Version | PCIe 4.0 |
|---|
Power:
| # 8 Pin CPU | 1 |
|---|---|
| Max Power Consumption (W) | 300W |
Software:
| API Support | CUDA, DirectCompute, DirectX 12.07, OpenACC®, OpenCL™, OpenGL 4.68, Shader Model 5.17, Vulkan 1.18 |
|---|---|
| Supported OS | Windows Server 2012 R2, Windows Server 2016 1607, 1709, Windows Server 2019, RedHat CoreOS 4.7, Red Hat Enterprise Linux 8.1-8.3, Red Hat Enterprise Linux 7.7-7.9, Red Hat Linux 6.6+, SUSE Linux Enterprise Server 15 SP2, SUSE Linux Enterprise Server 12 SP 3+, Ubuntu 14.04 LTS/16.04/18.04 LTS/20.04 LTS |
| Virtual GPU (vGPU) | NVIDIA RTX Virtual Workstation, NVIDIA Virtual Compute Server, NVIDIA vPC/vApps |
Reviews
There are no reviews yet.