Instance Details
| Compute | Value |
|---|---|
| vCPUs | 16 |
| Memory (GiB) | 64 |
| Memory per vCPU (GiB) | 4 |
| Physical Processor | AMD EPYC 7R32 |
| Clock Speed (GHz) | 2.8 GHz |
| CPU Architecture | x86_64 |
| GPU | 1 |
| GPU Average Wattage | 0 W |
| GPU Architecture | AMD Radeon Pro V520 |
| Video Memory (GiB) | 8 |
| GPU Compute Capability ? | 0 |
| FPGA | 0 |
| ffmpeg FPS | 99 |
| CoreMark iterations/Second | 25738.369474 |
| NUMA Architecture | Value |
|---|---|
| Uses NUMA Architecture Non-Uniform Memory Access (NUMA) is a computer memory design where memory access time depends on the memory location relative to the processor. In a NUMA system, processors are divided into nodes, each with its own local memory. Accessing local memory is faster than accessing memory from another node. | No |
| NUMA Node Count | N/A |
| Max NUMA Distance | N/A |
| Cores per NUMA Node (Avg) | N/A |
| Threads per NUMA Node (Avg) | N/A |
| Memory per NUMA Node (Avg MB) | N/A |
| L3 Cache per NUMA Node (Avg MB) | N/A |
| L3 Cache Shared | N/A |
| Networking | Value |
|---|---|
| Network Performance (Gibps) | up to 10 |
| Enhanced Networking | true |
| IPv6 | true |
| Placement Group ? |
| Storage | Value |
|---|---|
| EBS Optimized | true |
| Max Bandwidth (Mbps) on EBS | 3170 |
| Max Throughput (MB/s) on EBS | 396.25 |
| Max I/O operations/second IOPS | 13333 |
| Baseline Bandwidth (Mbps) on EBS | 1580 |
| Baseline Throughput (MB/s) on EBS | 197.5 |
| Baseline I/O operations/second IOPS | 6700 |
| Devices | 1 |
| Swap Partition | false |
| NVME Drive ? | true |
| Disk Space (GiB) | 600 |
| SSD | true |
| Initialize Storage | false |
| Amazon | Value |
|---|---|
| Generation | current |
| Instance Type | g4ad.4xlarge |
| Family | GPU instance |
| Name | G4AD Quadruple Extra Large |
| Elastic Map Reduce EMR | false |
