AMD Ryzen Threadripper PRO 5965WX 24-Cores testing with a ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS) and ASUS NVIDIA NV106 2GB 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 2402040-NE-2024YEAR116
2024 year
AMD Ryzen Threadripper PRO 5965WX 24-Cores testing with a ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS) and ASUS NVIDIA NV106 2GB on Ubuntu 23.10 via the Phoronix Test Suite.
,,"a","b","c","d"
Processor,,AMD Ryzen Threadripper PRO 5965WX 24-Cores @ 3.80GHz (24 Cores / 48 Threads),AMD Ryzen Threadripper PRO 5965WX 24-Cores @ 3.80GHz (24 Cores / 48 Threads),AMD Ryzen Threadripper PRO 5965WX 24-Cores @ 3.80GHz (24 Cores / 48 Threads),AMD Ryzen Threadripper PRO 5965WX 24-Cores @ 3.80GHz (24 Cores / 48 Threads)
Motherboard,,ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS),ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS),ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS),ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS)
Chipset,,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse
Memory,,8 x 16GB DDR4-2133MT/s Corsair CMK32GX4M2E3200C16,8 x 16GB DDR4-2133MT/s Corsair CMK32GX4M2E3200C16,8 x 16GB DDR4-2133MT/s Corsair CMK32GX4M2E3200C16,8 x 16GB DDR4-2133MT/s Corsair CMK32GX4M2E3200C16
Disk,,2048GB SOLIDIGM SSDPFKKW020X7,2048GB SOLIDIGM SSDPFKKW020X7,2048GB SOLIDIGM SSDPFKKW020X7,2048GB SOLIDIGM SSDPFKKW020X7
Graphics,,ASUS NVIDIA NV106 2GB,ASUS NVIDIA NV106 2GB,ASUS NVIDIA NV106 2GB,ASUS NVIDIA NV106 2GB
Audio,,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse
Monitor,,VA2431,VA2431,VA2431,VA2431
Network,,2 x Intel X550 + Intel Wi-Fi 6 AX200,2 x Intel X550 + Intel Wi-Fi 6 AX200,2 x Intel X550 + Intel Wi-Fi 6 AX200,2 x Intel X550 + Intel Wi-Fi 6 AX200
OS,,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10
Kernel,,6.5.0-13-generic (x86_64),6.5.0-13-generic (x86_64),6.5.0-13-generic (x86_64),6.5.0-13-generic (x86_64)
Desktop,,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0,GNOME Shell 45.0
Display Server,,X Server + Wayland,X Server + Wayland,X Server + Wayland,X Server + Wayland
Display Driver,,nouveau,nouveau,nouveau,nouveau
OpenGL,,4.3 Mesa 23.2.1-1ubuntu3,4.3 Mesa 23.2.1-1ubuntu3,4.3 Mesa 23.2.1-1ubuntu3,4.3 Mesa 23.2.1-1ubuntu3
Compiler,,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0
File-System,,ext4,ext4,ext4,ext4
Screen Resolution,,1920x1080,1920x1080,1920x1080,1920x1080
,,"a","b","c","d"
"TensorFlow - Device: CPU - Batch Size: 1 - Model: GoogLeNet (images/sec)",HIB,9.94,9.74,16.49,9.73
"LeelaChessZero - Backend: BLAS (Nodes/s)",HIB,173,219,225,213
"LeelaChessZero - Backend: Eigen (Nodes/s)",HIB,121,146,154,151
"SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 1080p (FPS)",HIB,543.554,573.042,580.467,565.906
"rav1e - Speed: 5 (FPS)",HIB,3.747,3.791,3.769,3.891
"rav1e - Speed: 10 (FPS)",HIB,10.634,10.885,10.957,11.022
"Llama.cpp - Model: llama-2-13b.Q4_0.gguf (Tokens/sec)",HIB,11.64,11.32,11.27,11.25
"Speedb - Test: Update Random (Op/s)",HIB,431692,418848,423788,417457
"SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p (FPS)",HIB,18.803,18.682,18.409,18.922
"LZ4 Compression - Compression Level: 9 - Compression Speed (MB/s)",HIB,44.28,44.48,45.49,44.52
"PyTorch - Device: CPU - Batch Size: 16 - Model: ResNet-50 (batches/sec)",HIB,32.50,32.10,31.65,32.21
"Speedb - Test: Sequential Fill (Op/s)",HIB,620607,618776,604758,612428
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,2012.2062,1962.7047,1970.6106,1962.1551
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,5.9507,6.1010,6.0747,6.1024
"Speedb - Test: Read While Writing (Op/s)",HIB,7004007,7070407,7047502,6896007
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,306.9919,305.3795,306.5175,299.8295
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,39.0493,39.2555,39.1181,39.977
"TensorFlow - Device: CPU - Batch Size: 16 - Model: ResNet-50 (images/sec)",HIB,19.87,19.45,19.61,19.81
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,5.2624,5.1753,5.1787,5.2804
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,189.9093,193.1106,192.9801,189.2673
"rav1e - Speed: 6 (FPS)",HIB,5.261,5.292,5.282,5.191
"SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 4K (FPS)",HIB,190.794,192.726,189.252,192.603
"PyTorch - Device: CPU - Batch Size: 256 - Model: ResNet-50 (batches/sec)",HIB,31.92,32.15,31.59,32.07
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,757.1631,752.7784,765.9923,757.2715
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,1.3175,1.3252,1.3025,1.3175
"TensorFlow - Device: CPU - Batch Size: 16 - Model: GoogLeNet (images/sec)",HIB,60.85,60.18,60.04,59.82
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,61.53,61.830,61.47,60.95
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,26.9119,26.6672,26.705,26.5435
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (items/sec)",HIB,157.2286,155.4837,155.403,155.2016
"Llama.cpp - Model: llama-2-7b.Q4_0.gguf (Tokens/sec)",HIB,20.76,20.95,20.74,20.68
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (ms/batch)",LIB,6.3518,6.4230,6.4266,6.4345
"Speedb - Test: Random Read (Op/s)",HIB,148134848,147432214,146285738,146473036
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,150.0421,148.2388,148.7561,149.2683
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,79.8855,80.8465,80.5729,80.2684
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,190.916,190.402,192.157,192.683
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (ms/batch)",LIB,45.9976,46.5453,46.0912,46.1334
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (items/sec)",HIB,21.7296,21.4743,21.6853,21.6655
"PyTorch - Device: CPU - Batch Size: 1 - Model: ResNet-50 (batches/sec)",HIB,40.68,40.42,40.82,40.35
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (items/sec)",HIB,156.9701,155.5402,155.6182,155.1926
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (ms/batch)",LIB,6.3619,6.4208,6.4178,6.4346
"TensorFlow - Device: CPU - Batch Size: 1 - Model: ResNet-50 (images/sec)",HIB,8.85,8.79,8.85,8.89
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,151.4666,149.7818,149.9507,149.7647
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,79.1618,80.0470,79.8946,80.052
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,224.1802,221.7053,223.0515,222.7232
"TensorFlow - Device: CPU - Batch Size: 1 - Model: VGG-16 (images/sec)",HIB,2.72,2.70,2.72,2.69
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,53.4699,54.0612,53.7417,53.8237
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 1080p (FPS)",HIB,501.42,506.596,501.156,506.174
"rav1e - Speed: 1 (FPS)",HIB,1.044,1.048,1.044,1.054
"Speedb - Test: Random Fill Sync (Op/s)",HIB,47488,47708,47373,47267
"Speedb - Test: Read Random Write Random (Op/s)",HIB,2327911,2307686,2320670,2316804
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,76.1394,75.5067,75.9898,75.7073
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,13.129,13.2388,13.1545,13.204
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,445.2565,448.0408,448.9031,448.0349
"TensorFlow - Device: CPU - Batch Size: 1 - Model: AlexNet (images/sec)",HIB,6.26,6.23,6.23,6.21
"Quicksilver - Input: CORAL2 P2 (Figure Of Merit)",HIB,24030000,24026667,23890000,23840000
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,39.0436,39.3339,39.1233,39.1902
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,307.0146,304.7712,306.5028,305.8614
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (ms/batch)",LIB,8.9109,8.9755,8.952,8.9586
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (items/sec)",HIB,112.0914,111.2892,111.5864,111.4965
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,26.8394,26.6478,26.6741,26.6902
"Y-Cruncher - Pi Digits To Calculate: 500M (sec)",LIB,7.325,7.349,7.301,7.297
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream (ms/batch)",LIB,58.254,58.3490,57.9978,58.4094
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream (items/sec)",HIB,17.1616,17.1337,17.2376,17.1162
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,30.489,30.2809,30.451,30.3159
"SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 4K (FPS)",HIB,6.677,6.669,6.678,6.633
"CacheBench - Test: Read / Modify / Write (MB/s)",HIB,130857.577562,130069.848338,130806.245683,130851.30507
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,685.1217,681.0038,683.2461,681.5303
"Speedb - Test: Random Fill (Op/s)",HIB,558330,554997,557348,556675
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,17.495,17.5999,17.5377,17.5865
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,446.6313,448.9079,449.2956,449.1605
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,335.3479,333.3674,333.6358,334.6424
"TensorFlow - Device: CPU - Batch Size: 16 - Model: VGG-16 (images/sec)",HIB,8.51,8.46,8.48,8.51
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,35.762,35.9726,35.9278,35.837
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 1080p (FPS)",HIB,122.948,123.293,122.95,122.616
"TensorFlow - Device: CPU - Batch Size: 16 - Model: AlexNet (images/sec)",HIB,100.44,100.01,100.08,99.9
"Llama.cpp - Model: llama-2-70b-chat.Q5_0.gguf (Tokens/sec)",HIB,1.94,1.94,1.95,1.95
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,32.5188,32.3621,32.4212,32.3762
"Llamafile - Test: llava-v1.5-7b-q4 - Acceleration: CPU (Tokens/sec)",HIB,17.22,17.26,17.3,17.25
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,392.9588,394.7759,393.8346,394.3756
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,98.9102,98.7456,98.4979,98.8912
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,10.1046,10.1213,10.146,10.1068
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,368.3051,369.7720,369.6228,369.53
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,54.1194,54.3340,54.1474,54.204
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (items/sec)",HIB,18.4727,18.4000,18.4635,18.4443
"LZ4 Compression - Compression Level: 3 - Compression Speed (MB/s)",HIB,131.24,131.10,131.4,131.61
"Quicksilver - Input: CTS2 (Figure Of Merit)",HIB,20680000,20646667,20620000,20600000
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (items/sec)",HIB,18.3872,18.3317,18.3589,18.3959
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (ms/batch)",LIB,54.3716,54.5365,54.4554,54.3471
"Quicksilver - Input: CORAL2 P1 (Figure Of Merit)",HIB,24210000,24230000,24240000,24290000
"Y-Cruncher - Pi Digits To Calculate: 1B (sec)",LIB,15.545,15.497,15.532,15.501
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream (ms/batch)",LIB,10.1424,10.1362,10.1277,10.1151
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream (items/sec)",HIB,98.516,98.5635,98.6526,98.7671
"Llamafile - Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU (Tokens/sec)",HIB,10.13,10.15,10.14,10.13
"LZ4 Compression - Compression Level: 1 - Compression Speed (MB/s)",HIB,828.78,829.36,829.15,830.37
"LZ4 Compression - Compression Level: 9 - Decompression Speed (MB/s)",HIB,4840.5,4841.4,4842.4,4844.5
"LZ4 Compression - Compression Level: 1 - Decompression Speed (MB/s)",HIB,5019.5,5020.0,5023.2,5019.5
"LZ4 Compression - Compression Level: 3 - Decompression Speed (MB/s)",HIB,4595.9,4597.9,4598,4596.7
"CacheBench - Test: Write (MB/s)",HIB,69134.680498,69140.530992,69142.435503,69142.188854
"CacheBench - Test: Read (MB/s)",HIB,11543.372321,11543.164687,11543.096362,11543.486939
"Llamafile - Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU (Tokens/sec)",HIB,3.25,3.25,3.25,3.25