Home > Workload Solutions > Virtual Desktop Infrastructure > White Papers > Technical White Paper—VDI Graphics Acceleration on a Dell MX7000 Modular Chassis > NVIDIA nVector, SPECviewperf 13, Maya–4 users
This section describes the four virtual workstations that ran the NVIDIA nVector automated SPECviewperf 13 Maya workload. All the virtual workstations were connected to virtual machine endpoints.
The following table shows the configuration of the virtual workstations that we tested:
Configuration | Value |
vCPU | 6 |
vMemory | 32768 |
HardDisk | 120 |
GPU | grid_t4-8q |
GPUDriverVersion | 442.06 |
FRL | Disabled |
vSYNC | Default |
vDAVersion | 7.10.1 |
DirectConnectVersion | 7.10.1 |
CPUAffinity | Unset |
Screen Resolution | 1920x1080 |
QuantityMonitors | 1 |
The following table gives the average host utilization metrics for this test:
Workload | Density per host | Average CPU | Average GPU | Average free memory | Average net Mbps per user |
SPECviewperf 13 Maya | 4 | 19% | 74% | 232 GB | 9.24 Mbps |
The following figure shows the CPU core utilization for the system under test. CPU core utilization remained low, with the highest point reaching 26.4 percent.
The following figure shows the GPU utilization for the system under test. We gathered GPU metrics through NVIDIA-SMI on the VMware ESXi host. GPU utilization was quite high for this test, but it is to be expected for this workload as the test is largely a measure of GPU performance.
The following figure shows the free memory in the system during the test. There were no variations in memory usage throughout the test because all vGPU-enabled VM memory was reserved. There was no memory ballooning or swapping on either host.
The following figure shows the network utilization of the system during the test. There was more than enough bandwidth available for the workload and the display protocol to accommodate the workload. Each server had a single 25 GbE (25,000 MBits) network card connected to it.