NVIDIA A100 Tensor Core GPU
Get it at affordable price

NVIDIA A100 Tensor Core GPU delivers unprecedented acceleration and A100 provides up to 20X higher performance over the prior generation.

The NVIDIA A100 Tensor Core GPU delivers unprecedented acceleration—at every scale—to power the world’s highest-performing elastic data centers for AI, data analytics, and high-performance computing (HPC) applications. As the engine of the NVIDIA data center platform, A100 provides up to 20X higher performance over the prior NVIDIA Volta™ generation.

NVIDIA A100 Tensor Core  Graph

NVIDIA A100 Tensor Core technology comes with a wide range of math precisions, providing a single accelerator for every workload. The latest generation A100 80GB doubles GPU memory and debuts the world’s fastest memory bandwidth at 2 terabytes per second (TB/s)

NVIDIA A100 Tensor Core  Graph
Linux A100 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
A100-LIX-01 1 x 40 GB 16 vCPUs 115 GB 1500 GB ₹71,250
A100-LIX-02 2 x 40 GB 32 vCPUs 230 GB 3000 GB ₹1,42,500
A100-LIX-03 4 x 40 GB 64 vCPUs 460 GB 6000 GB ₹2,85,000
A100-LIX-04 8 x 40 GB 128 vCPUs 920 GB 6000 GB ₹6,65,000
A100-LIX-05 1 x 80 GB 16 vCPUs 115 GB 1500 GB ₹95,000
A100-LIX-06 2 x 80 GB 32 vCPUs 230 GB 3000 GB ₹1,90,000
A100-LIX-07 4 x 80 GB 64 vCPUs 460 GB 6000 GB ₹3,80,000
Windows A100 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
A100-WIN-01 1 x 40 GB 16 vCPUs 115 GB 1500 GB ₹75,671
A100-WIN-02 2 x 40 GB 32 vCPUs 230 GB 3000 GB ₹1,50,085
A100-WIN-03 2 x 40 GB 64 vCPUs 460 GB 6000 GB ₹2,98,913
A100-WIN-04 8 x 40 GB 128 vCPUs 920 GB 6000 GB ₹6,91,569
A100-WIN-05 1 x 80 GB 16 vCPUs 115 GB 1500 GB ₹99,421
A100-WIN-06 2 x 80 GB 32 vCPUs 230 GB 3000 GB ₹1,97,585
A100-WIN-07 4 x 80 GB 64 vCPUs 460 GB 6000 GB ₹3,93,913
Linux A40 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
A40-LIX-01 1 x 48 GB 16 vCPUs 100 GB 750 GB ₹51,775
A40-LIX-02 2 x 48 GB 32 vCPUs 200 GB 1500 GB ₹1,03,550
A40-LIX-03 4 x 48 GB 64 vCPUs 400 GB 3000 GB ₹2,07,100
Windows A40 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
A40-WIN-01 1 x 48 GB 16 vCPUs 100 GB 750 GB ₹56,907
A40-WIN-02 2 x 48 GB 32 vCPUs 200 GB 1500 GB ₹1,12,208
A40-WIN-03 4 x 48 GB 64 vCPUs 400 GB 3000 GB ₹2,22,811
Linux A30 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
A30-LIX-01 1 x 24 GB 16 vCPUs 90 GB 640 GB ₹38,000
A30-LIX-02 2 x 24 GB 32 vCPUs 180 GB 1280 GB ₹76,000
A30-LIX-03 4 x 24 GB 64 vCPUs 360 GB 2560 GB ₹1,52,000
Windows A30 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
A30-WIN-01 1 x 24 GB 16 vCPUs 90 GB 640 GB ₹42,777
A30-WIN-02 2 x 24 GB 32 vCPUs 180 GB 1280 GB ₹83,940
A30-WIN-03 4 x 24 GB 64 vCPUs 360 GB 2560 GB ₹1,66,268
Linux V100 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
V100-LIX-01 1 x 32 GB 8 vCPUs 120 GB 900 GB ₹40,000
V100-LIX-02 2 x 32 GB 16 vCPUs 240 GB 1800 GB ₹60,000
V100-LIX-03 4 x 32 GB 32 vCPUs 480 GB 3600 GB ₹1,44,000
Windows V100 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated Ram SSD Storage Monthly Billing
V100-WIN-01 1 x 32 GB 8 vCPUs 120 GB 900 GB ₹50,349
V100-WIN-02 2 x 32 GB 16 vCPUs 240 GB 1800 GB ₹75,671
V100-WIN-03 4 x 32 GB 32 vCPUs 480 GB 3600 GB ₹1,78,585
Linux RTX 8000 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
RTX-8000-LIX-01 1 x 48GB (DDR6) 16 vCPUs 115 GB 900 GB ₹38,000
RTX-8000-LIX-02 2 x 48GB (DDR6) 32 vCPUs 230 GB 1800 GB ₹76,000
RTX-8000-LIX-03 4 x 48GB (DDR6) 64 vCPUs 460 GB 3600 GB ₹1,52,000
Windows RTX 8000 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
RTX-8000-WIN-01 1 x 48GB 16 vCPUs 115 GB 900 GB ₹42,421
RTX-8000-WIN-02 2 x 48GB 32 vCPUs 230 GB 1800 GB ₹83,585
RTX-8000-WIN-03 4 x 48GB 64 vCPUs 460 GB 3600 GB ₹1,66,268
Linux T4 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
T4-LIX-01 1 x 16 GB 12 vCPUs 50 GB 900 GB ₹16,625
T4-LIX-02 2 x 16 GB 24 vCPUs 100 GB 1800 GB ₹34,200
Windows T4 GPU Dedicated Compute
Plan GPU Memory vCPUs Dedicated RAM SSD Storage Monthly Billing
T4-WIN-01 1 x 16 GB 12 vCPUs 50 GB 900 GB ₹20,255
T4-WIN-02 2 x 16 GB 24 vCPUs 100 GB 1800 GB ₹40,203

Applications & Use cases


app1
app2
app3

A100 adds a powerful new third-generation Tensor Core that boosts throughput over V100 while adding comprehensive support for DL and HPC data types, together with a new Sparsity feature that delivers a further doubling of throughput.

New TensorFloat-32 (TF32) Tensor Core operations in A100 provide an easy path to accelerate FP32 input/output data in DL frameworks and HPC, running 10x faster than V100 FP32 FMA operations or 20x faster with sparsity. For FP16/FP32 mixed-precision DL, the A100 Tensor Core delivers 2.5x the performance of V100, increasing to 5x with sparsity.

New Bfloat16 (BF16)/FP32 mixed-precision Tensor Core operations run at the same rate as FP16/FP32 mixed-precision. Tensor Core acceleration of INT8, INT4, and binary round out support for DL inferencing, with A100 sparse INT8 running 20x faster than V100 INT8. For HPC, the A100 Tensor Core includes new IEEE-compliant FP64 processing that delivers 2.5x the FP64 performance of V100.

The NVIDIA A100 GPU is architected to not only accelerate large complex workloads, but also efficiently accelerate many smaller workloads. A100 enables building data centers that can accommodate unpredictable workload demand, while providing fine-grained workload provisioning, higher GPU utilization, and improved TCO. The NVIDIA A100 GPU delivers exceptional speedups over V100 for AI training and inference workloads as shown in Figure 2. Similarly, Figure 3 shows substantial performance improvements across different HPC applications.

A huge Breakthroughs in GPU architecture


The NVIDIA A100 GPU is a technical design breakthrough that is fueled by five key innovations, and the outcome of these innovations result in 6x higher performance than NVIDIA’s previous generation Volta architecture for training and 7x higher performance for inference. The innovations are mentioned below:


  1. NVIDIA Ampere Architecture: At the core of this chip is the NVIDIA Ampere GPU architecture that contains more than 54 billion transistors and hence, making it the largest 7-nanometer processor in the world

  2. Third-generation Tensor Cores with TF32: The A100 includes new TF32 for artificial intelligence that allows for up to 20x the AI performance of FP32 precision, without making any changes in the code.

  3. Multi-Instance GPU: Multi-instance GPU or MIG is a new technology that allows multiple networks to operate simultaneously on a single A100 GPU for optimal utilization of computing resources. It enables a single A100 GPU to be partitioned into as many as seven separate GPUs in order to deliver varying degrees of computing for jobs of different sizes while providing optimal utilization as well as maximizing return on investment.

  4. Third-Generation NVIDIA NVLink: The 3rd-generation NVIDIA NVLink helps in doubling the high-speed connectivity between GPUs, and thus provide efficient performance scaling in a server.

  5. 5.Structural Sparsity: Structural sparsity is a new technique that harnesses the inherently sparse nature of AI math to double the performance.