Hardware Accelerated GPU Scheduling (Win 10)
Moderators: Site Moderators, FAHC Science Team
-
- Posts: 704
- Joined: Tue Dec 04, 2007 6:56 am
- Hardware configuration: Ryzen 7 5700G, 22.40.46 VGA driver; 32GB G-Skill Trident DDR4-3200; Samsung 860EVO 1TB Boot SSD; VelociRaptor 1TB; MSI GTX 1050ti, 551.23 studio driver; BeQuiet FM 550 PSU; Lian Li PC-9F; Win11Pro-64, F@H 8.3.5.
[Suspended] Ryzen 7 3700X, MSI X570MPG, 32GB G-Skill Trident Z DDR4-3600; Corsair MP600 M.2 PCIe Gen4 Boot, Samsung 840EVO-250 SSDs; VelociRaptor 1TB, Raptor 150; MSI GTX 1050ti, 526.98 driver; Kingwin Stryker 500 PSU; Lian Li PC-K7B. Win10Pro-64, F@H 8.3.5. - Location: @Home
- Contact:
Re: Hardware Accelerated GPU Scheduling (Win 10)
I noticed that CPUid HWInfo now reports GPU load as 0, while GPUz correctly reports 92-100%.
Ryzen 7 5700G, 22.40.46 VGA driver; MSI GTX 1050ti, 551.23 studio driver
Ryzen 7 3700X; MSI GTX 1050ti, 551.23 studio driver [Suspended]
Ryzen 7 3700X; MSI GTX 1050ti, 551.23 studio driver [Suspended]
Re: Hardware Accelerated GPU Scheduling (Win 10)
There's much more than 1 readout for GPUs.
Your average GPU utilization is derived from 3D calculations.
There are 2D calculations (usually not compute intensive), compute data and more.
Here's an example of the sensor metrics of a relatively simple intel GPU:
If HWmonitor took the TDG values, it would show only 1% GPU utilization. While it's easy to see that the GPU is crunching on data.
Your average GPU utilization is derived from 3D calculations.
There are 2D calculations (usually not compute intensive), compute data and more.
Here's an example of the sensor metrics of a relatively simple intel GPU:
Code: Select all
render busy: 100%: ████████████████████ render space: 2232/16384
task percent busy
CS: 99%: ███████████████████▉ vert fetch: 0 (0/sec)
TSG: 98%: ███████████████████▋ prim fetch: 0 (0/sec)
VFE: 97%: ███████████████████▌ VS invocations: 0 (0/sec)
GAM: 61%: ████████████▎ GS invocations: 0 (0/sec)
GAFS: 2%: ▌ GS prims: 0 (0/sec)
TDG: 1%: ▎ CL invocations: 0 (0/sec)
CL prims: 0 (0/sec)
PS invocations: 0 (0/sec)
PS depth pass: 0 (0/sec)