openvino epyc Benchmarks for a future article. AMD EPYC 9655P 96-Core testing with a Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS) and ASPEED on Ubuntu 24.10 via the Phoronix Test Suite. a: Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-linux-pm-next-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768 b: Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-linux-pm-next-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768 OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 79.23 |==================================================================== b . 79.56 |==================================================================== OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 709.67 |=================================================================== b . 709.47 |=================================================================== OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 708.52 |================================================================== b . 714.43 |=================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 5076.85 |================================================================== b . 5113.06 |================================================================== OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 146.86 |=================================================================== b . 146.68 |=================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU FPS > Higher Is Better a . 16632.46 |================================================================= b . 16681.62 |================================================================= OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU FPS > Higher Is Better a . 2103.66 |================================================================= b . 2132.64 |================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 8214.12 |================================================================== b . 8226.70 |================================================================== OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 7597.71 |================================================================== b . 7593.68 |================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU FPS > Higher Is Better a . 23550.10 |================================================================= b . 23608.37 |================================================================= OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU FPS > Higher Is Better a . 2511.13 |================================================================== b . 2500.56 |================================================================== OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 853.62 |=================================================================== b . 855.69 |=================================================================== OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 14008.92 |================================================================= b . 14006.95 |================================================================= OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 6644.20 |================================================================== b . 6636.17 |================================================================== OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU FPS > Higher Is Better a . 6744.58 |================================================================== b . 6770.28 |================================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU FPS > Higher Is Better a . 3480.55 |================================================================== b . 3489.53 |================================================================== OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU FPS > Higher Is Better a . 10520.88 |================================================================= b . 10522.18 |================================================================= OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 133379.44 |================================================================ b . 133562.06 |================================================================ OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU FPS > Higher Is Better a . 3543.72 |================================================================== b . 3558.77 |================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 151728.40 |================================================================ b . 150585.90 |================================================================ OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU tokens/s > Higher Is Better a . 37.54 |==================================================================== b . 37.70 |==================================================================== OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU tokens/s > Higher Is Better a . 64.59 |=================================================================== b . 65.52 |==================================================================== OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU tokens/s > Higher Is Better a . 51.14 |==================================================================== b . 51.33 |==================================================================== OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU tokens/s > Higher Is Better a . 55.64 |=================================================================== b . 56.20 |==================================================================== OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 603.07 |=================================================================== b . 601.06 |=================================================================== OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 67.50 |==================================================================== b . 67.52 |==================================================================== OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 67.62 |==================================================================== b . 67.06 |=================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 9.41 |===================================================================== b . 9.34 |==================================================================== OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 326.08 |=================================================================== b . 326.47 |=================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU ms < Lower Is Better a . 2.81 |===================================================================== b . 2.80 |===================================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU ms < Lower Is Better a . 22.76 |==================================================================== b . 22.45 |=================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 5.81 |===================================================================== b . 5.80 |===================================================================== OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 12.54 |==================================================================== b . 12.55 |==================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU ms < Lower Is Better a . 3.94 |===================================================================== b . 3.93 |===================================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU ms < Lower Is Better a . 19.03 |==================================================================== b . 19.12 |==================================================================== OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 56.18 |==================================================================== b . 56.05 |==================================================================== OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 6.72 |===================================================================== b . 6.71 |===================================================================== OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 7.16 |===================================================================== b . 7.17 |===================================================================== OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU ms < Lower Is Better a . 13.69 |==================================================================== b . 13.64 |==================================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU ms < Lower Is Better a . 27.56 |==================================================================== b . 27.49 |==================================================================== OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU ms < Lower Is Better a . 4.53 |===================================================================== b . 4.53 |===================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 0.44 |===================================================================== b . 0.44 |===================================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU ms < Lower Is Better a . 27.06 |==================================================================== b . 26.95 |==================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 0.31 |===================================================================== b . 0.31 |===================================================================== OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token ms < Lower Is Better a . 36.31 |==================================================================== b . 35.88 |=================================================================== OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token ms < Lower Is Better a . 26.64 |==================================================================== b . 26.52 |==================================================================== OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token ms < Lower Is Better a . 19.01 |==================================================================== b . 18.79 |=================================================================== OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token ms < Lower Is Better a . 15.49 |==================================================================== b . 15.26 |=================================================================== OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token ms < Lower Is Better a . 29.24 |==================================================================== b . 29.29 |==================================================================== OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token ms < Lower Is Better a . 19.55 |==================================================================== b . 19.48 |==================================================================== OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token ms < Lower Is Better a . 24.25 |==================================================================== b . 23.98 |=================================================================== OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token ms < Lower Is Better a . 17.97 |==================================================================== b . 17.79 |===================================================================