Ultra 9 with two 5080GPU best performance

Software Tuning, Performance Optimization & Platform Monitoring

Discussion regarding monitoring and software tuning methodologies, Performance Monitoring Unit (PMU) of Intel microprocessors, and platform updating.

Ultra 9 with two 5080GPU best performance

1,248 Views

Hello, we need direct personnel assistance at proffessional level for our understanding how to use Ultra9 with two 5080GPU efficiently, and to verify our workflow for best performance.
This support can be remotely/online/offline (chargeable basis also fine for us)

Application:

1. Operating System version: Window 11 Pro 24H
2. CPU model (Ultra 9 exact model): Intel core ultra 9 15th gen 285k
3. GPU model(s) (e.g., RTX 5080 ×2): RTX 5080 16GB DDR7 X 2 Nos
4. Motherboard: MSI MEG Z890 GODLIKE
5. RAM: CV 32X2 RGB PRO 6000 MHZ32X2 kit
6. SSD: Samsung 990 pro 1TB SSD
7. Programming language and framework: Python 3.10; Cuda 12.9.0; Pytorch 2.8.0.Dev 2025+CU128; Torchaudio 2.6.0Dev; Torchvision 0.22.0; Ultralytics 8.3.137
8. Type of workload: During Inference GPU usage reaching upto 20% only, other processing part CPU maximum 4 cores uage outof 24 core, (how to use multithreading and enable all core usage)

127 KB

467 KB

Link Copied

0 Replies

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.