The p3dn.24xlarge instance is part of the p3dn series, featuring 96 vCPUs and 100 Gigabit of RAM, with Gpu Instances. It is available at a rate of $31.2120/hour.
Amazon EC2 P3 instances offer superior computational power in the cloud, featuring up to 8 NVIDIA® V100 Tensor Core GPUs and up to 100 Gbps of network throughput, ideal for machine learning and HPC tasks.
Up to 8 NVIDIA Tesla V100 GPUs, each equipped with 5,120 CUDA Cores and 640 Tensor Cores
High-frequency Intel Xeon Scalable Processor (Broadwell E5-2686 v4) used in p3.2xlarge, p3.8xlarge, and p3.16xlarge instances
High-frequency 2.5 GHz (base) Intel Xeon Scalable Processor (Skylake 8175) utilized in p3dn.24xlarge instances
Supports NVLink for direct GPU-to-GPU communication
Delivers up to 100 Gbps of total network bandwidth
Includes Elastic Fabric Adapter (EFA) support for p3dn.24xlarge instances
Credits: AWS Resources, Updated At: 2024-08-23
Deep learning and machine learning, high-performance computing, fluid dynamics, financial modeling, seismic analysis, speech recognition, autonomous vehicle simulations, and drug discovery.
| Instances | vCPUs | Memory (GiB) |
|---|---|---|
| p3.2xlarge | 8 | 61 GiB |
| p3.8xlarge | 32 | 244 GiB |
| p3.16xlarge | 64 | 488 GiB |
| p3dn.24xlarge | 96 | 768 GiB |
| General | |
|---|---|
| Type | p3dn.24xlarge |
| Region | N. Virginia |
| Family Group | P3 |
| Family Category | Gpu Instances |
| Instance Generation | Current |
| Term Type | On-demand |
| Pricing (USD/hr) | $ 31.2120 |
| Compute | |
|---|---|
| vCPU | 96 |
| Memory | 768 GiB |
| Storage | 2 x 900 NVMe SSD |
| Processor Architecture | 64-bit |
| Operating System | Linux |
| EBS Optimized | NA |
| Tenancy | Shared |
| Clock Speed | 2.5 GHz |
| GPU | 8.000000 |
| ECU | 337.0000 |
| Virtualization | HVM |
| Networking | |
|---|---|
| Network Performance | 100 Gigabit |
| ENA Support | True |
| Region | Price / Unit | Monthly Pricing |
|---|---|---|
| Oregon | $31.2120 | $22784.76 |
| Ireland | $33.7110 | $24609.03 |
| Tokyo | $42.7830 | $31231.59 |