NVIDIA A10 Tensor Core GPU 24GB
Graphic Cards And Accessories\ Datacenter GPUs
NVIDIA A10 GPU delivers the performance that designers, engineers, artists, and scientists need to meet today’s challenges. A compact, single-slot, 150W GPU, when combined with NVIDIA virtual GPU (vGPU) software, can accelerate multiple data center workloads—from graphics-rich virtual desktop infrastructure (VDI) to AI—in an easily managed, secure, and flexible infrastructure that can scale to accommodate every need.
Specifications
| GPU Features | NVIDIA A10 24GB |
| GPU Memory | 24GB GDDR6 |
| Memory bandwidth | 600 GB/s |
| FP32 Tensor Core | 62.5 teraFLOPS | 125 teraFLOPS* |
| BFLOAT16 Tensor Core | 125 teraFLOPS | 250 teraFLOPS* |
| FP16 Tensor Core | 125 teraFLOPS | 250 teraFLOPS* |
| INT8 Tensor Core | 250 TOPS | 500 TOPS* |
| INT4 Tensor Core | 500 TOPS | 1,000 TOPS* |
| RT Core | 72 RT Cores |
| Max thermal design power (TDP) | 150W |
| Interconnect | PCIe Gen4: 64GB/s |
| Form factor | 1-slot FHFL |
Enrich Graphics and Video Applications with Powerful AI
NVIDIA AMPERE ARCHITECTURE
Double-speed processing for single-precision floatingpoint (FP32) operations and improved power efficiency provide significant performance gains in graphics and compute workflows, such as complex 3D computer-aided design (CAD) and computer-aided engineering (CAE). THIRD-GENERATION TENSOR CORES
Tensor Float 32 (TF32) precision provides up to 5X the training throughput over the previousgeneration to accelerate AI and data science model training without any code changes. Hardware support for structural sparsity provides up to double the throughput for inferencing. Tensor Cores also bring AI to graphics with capabilities like deep learning super sampling (DLSS), AI denoising, and enhanced editing for select applications. SECOND-GENERATION RT CORES
With up to 2X the throughput over the previous generation and the ability to concurrentlyrun ray tracing with either shading or denoising capabilities, second-generation RT Cores deliver massive speedups for workloads like photorealistic rendering of movie content, architectural design evaluations, and virtual prototyping of product designs. This technology also speeds up the rendering of ray-traced motion blur for faster results with greater visual accuracy. 24 GB GDDR6
Ultra-fast GDDR6 memory, delivering 600 GB/s of bandwidth for rendering, data science, engineering simulation, and other GPU-memory intensive workloads. PCIE EXPRESS GEN 4
PCI Express Gen 4 doubles the bandwidth of PCIe Gen 3, improving data-transfer speeds from CPU memory for data-intensive tasks like AI, data science, and 3D design. Faster PCIe performance also accelerates GPU direct memory access (DMA) transfers, providing faster input/output communication of video data between the GPU and NVIDIA GPUDirect® for video-enabled devices, delivering a powerful solution for live broadcast. A10 is also backwards compatible with PCI Express Gen 3 for deployment flexibility. DATA CENTER EFFICIENCY
Featuring a single-slot, full-height, full-length power efficient design, NVIDIA A10 iscompatible with a wide range of servers from worldwide OEMs. The NVIDIA A10 includes secure and measured boot with hardware rootof-trust technology, ensuring that firmware isn’t tampered with or corrupted.