2 x INTEL XEON PLATINUM 8592+ testing with a Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2402196-NE-XEONFEBBY11
xeon febby
2 x INTEL XEON PLATINUM 8592+ testing with a Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.
,,"a","b"
Processor,,2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads),2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads)
Motherboard,,Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS),Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS)
Chipset,,Intel Device 1bce,Intel Device 1bce
Memory,,1008GB,1008GB
Disk,,3201GB Micron_7450_MTFDKCB3T2TFS,3201GB Micron_7450_MTFDKCB3T2TFS
Graphics,,ASPEED,ASPEED
Network,,2 x Intel X710 for 10GBASE-T,2 x Intel X710 for 10GBASE-T
OS,,Ubuntu 23.10,Ubuntu 23.10
Kernel,,6.6.0-060600-generic (x86_64),6.6.0-060600-generic (x86_64)
Compiler,,GCC 13.2.0,GCC 13.2.0
File-System,,ext4,ext4
Screen Resolution,,1024x768,1024x768
,,"a","b"
"PyTorch - Device: CPU - Batch Size: 1 - Model: ResNet-50 (batches/sec)",HIB,51.66,51.00
"PyTorch - Device: CPU - Batch Size: 1 - Model: ResNet-152 (batches/sec)",HIB,19.08,19.21
"PyTorch - Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l (batches/sec)",HIB,0.42,
"Quicksilver - Input: CTS2 (Figure Of Merit)",HIB,9556000,9354000
"Quicksilver - Input: CORAL2 P1 (Figure Of Merit)",HIB,8625000,8820000
"Quicksilver - Input: CORAL2 P2 (Figure Of Merit)",HIB,8000000,8418000
"dav1d - Video Input: Chimera 1080p (FPS)",HIB,204.38,202.83
"dav1d - Video Input: Summer Nature 4K (FPS)",HIB,68.43,68.36
"dav1d - Video Input: Summer Nature 1080p (FPS)",HIB,87.78,86.79
"dav1d - Video Input: Chimera 1080p 10-bit (FPS)",HIB,235.42,239.01
"Intel Open Image Denoise - Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only (Images / Sec)",HIB,5.10,5.16
"Intel Open Image Denoise - Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only (Images / Sec)",HIB,5.14,5.00
"Intel Open Image Denoise - Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only (Images / Sec)",HIB,2.46,2.47
"TensorFlow - Device: CPU - Batch Size: 1 - Model: VGG-16 (images/sec)",HIB,12.25,11.89
"TensorFlow - Device: CPU - Batch Size: 1 - Model: AlexNet (images/sec)",HIB,39.98,37.7
"TensorFlow - Device: CPU - Batch Size: 1 - Model: GoogLeNet (images/sec)",HIB,18.23,17.62
"TensorFlow - Device: CPU - Batch Size: 1 - Model: ResNet-50 (images/sec)",HIB,7.28,7.01
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,205.563,208.993
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,15.3826,17.1686
"ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inferences/sec)",HIB,465.647,360.779
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,15.9646,22.6587
"ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,786.262,789.312
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,9.90267,9.4317
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,35.9174,38.5606
"ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,170.023,170.235
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,256.996,247.665
"ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,38.3302,37.8832
"GROMACS - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day)",HIB,17.918,18.398
"NAMD - Input: ATPase with 327,506 Atoms (ns/day)",HIB,5.98308,4.02029
"NAMD - Input: STMV with 1,066,628 Atoms (ns/day)",HIB,1.74622,1.81638
"Speedb - Test: Random Read (Op/s)",HIB,613257745,490533153
"Speedb - Test: Update Random (Op/s)",HIB,157060,156458
"Speedb - Test: Read While Writing (Op/s)",HIB,16943739,18187110
"Speedb - Test: Read Random Write Random (Op/s)",HIB,1520436,1514331
"Llama.cpp - Model: llama-2-7b.Q4_0.gguf (Tokens/sec)",HIB,0.69,0.58
"Llama.cpp - Model: llama-2-13b.Q4_0.gguf (Tokens/sec)",HIB,0.55,0.45
"Llama.cpp - Model: llama-2-70b-chat.Q5_0.gguf (Tokens/sec)",HIB,0.43,0.34
"Llamafile - Test: llava-v1.5-7b-q4 - Acceleration: CPU (Tokens/sec)",HIB,0.53,0.53
"Llamafile - Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU (Tokens/sec)",HIB,8.57,8.81
"Llamafile - Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU (Tokens/sec)",HIB,3.74,3.86
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,4.86151,4.78113
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,65.0065,58.2438
"ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,2.14695,2.77091
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,62.6361,44.1311
"ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,1.27117,1.26631
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,100.98,106.023
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,27.8405,25.9319
"ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,5.88091,5.87369
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,3.89053,4.03712
"ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,26.0875,26.395
"Y-Cruncher - Pi Digits To Calculate: 1B (sec)",LIB,5.107,5.249
"Y-Cruncher - Pi Digits To Calculate: 500M (sec)",LIB,2.723,2.761