AMD Ryzen Threadripper 7980X 64-Cores testing with a System76 Thelio Major (FA Z5 BIOS) and AMD Radeon Pro W7900 45GB 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 2403159-PTS-SVTDEEPS65
svt deepsparse
AMD Ryzen Threadripper 7980X 64-Cores testing with a System76 Thelio Major (FA Z5 BIOS) and AMD Radeon Pro W7900 45GB on Ubuntu 23.10 via the Phoronix Test Suite.
,,"a","b","c","d"
Processor,,AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads),AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads),AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads),AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads)
Motherboard,,System76 Thelio Major (FA Z5 BIOS),System76 Thelio Major (FA Z5 BIOS),System76 Thelio Major (FA Z5 BIOS),System76 Thelio Major (FA Z5 BIOS)
Chipset,,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4
Memory,,4 x 32GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2,4 x 32GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2,4 x 32GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2,4 x 32GB DRAM-4800MT/s Micron MTC20F1045S1RC48BA2
Disk,,1000GB CT1000T700SSD5,1000GB CT1000T700SSD5,1000GB CT1000T700SSD5,1000GB CT1000T700SSD5
Graphics,,AMD Radeon Pro W7900 45GB (1760/1124MHz),AMD Radeon Pro W7900 45GB (1760/1124MHz),AMD Radeon Pro W7900 45GB (1760/1124MHz),AMD Radeon Pro W7900 45GB (1760/1124MHz)
Audio,,AMD Device 14cc,AMD Device 14cc,AMD Device 14cc,AMD Device 14cc
Monitor,,DELL P2415Q,DELL P2415Q,DELL P2415Q,DELL P2415Q
Network,,Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411,Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411,Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411,Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX210/AX211/AX411
OS,,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10
Kernel,,6.5.0-25-generic (x86_64),6.5.0-25-generic (x86_64),6.5.0-25-generic (x86_64),6.5.0-25-generic (x86_64)
Desktop,,GNOME Shell 45.2,GNOME Shell 45.2,GNOME Shell 45.2,GNOME Shell 45.2
Display Server,,X Server + Wayland,X Server + Wayland,X Server + Wayland,X Server + Wayland
OpenGL,,4.6 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 DRM 3.54),4.6 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 DRM 3.54),4.6 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 DRM 3.54),4.6 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 DRM 3.54)
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"
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,188.558,195.907,194.065,195.858
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 1080p (FPS)",HIB,193.759,194.769,189.608,195.612
"SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 4K (FPS)",HIB,192.567,193.286,192.638,187.625
"SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 1080p (FPS)",HIB,662.493,653.688,671.832,670.138
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 1080p (FPS)",HIB,616.583,615.540,625.817,621.442
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,3.5332,3.5087,3.5324,3.5604
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,2253.8602,2269.5068,2254.2228,2236.9169
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (ms/batch)",LIB,8.8070,8.7347,8.7752,8.7026
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (items/sec)",HIB,113.4701,114.4072,113.8761,114.8252
"SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p (FPS)",HIB,27.476,27.282,27.518,27.241
"SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 4K (FPS)",HIB,9.892,9.793,9.889,9.866
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream (items/sec)",HIB,11.1249,11.0159,11.0814,11.0145
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream (ms/batch)",LIB,89.8704,90.7521,90.2253,90.7667
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,94.509,93.734,93.930,94.559
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,89.7091,90.4983,89.8053,90.3875
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,11.1350,11.0383,11.1223,11.0513
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,252.3577,251.6102,251.2477,253.0264
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,3.9594,3.9707,3.9766,3.9490
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (items/sec)",HIB,170.3090,171.4934,171.4781,171.3561
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (ms/batch)",LIB,5.8648,5.8243,5.8245,5.8285
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,61.7698,61.9978,61.9371,61.7579
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,129.4408,128.9560,129.1012,129.4552
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,365.3355,365.9832,365.5771,366.6823
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,3.4391,3.4406,3.4298,3.4284
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,2252.4627,2251.6125,2258.1407,2259.2648
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,887.4442,886.1847,884.6567,886.7758
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,8.9970,9.0094,9.0252,9.0040
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,11.4406,11.4159,11.4055,11.4067
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,87.3635,87.5496,87.6317,87.6213
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,39.5729,39.4685,39.4664,39.4525
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,21.8474,21.8225,21.8606,21.7950
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,396.5768,396.4446,397.5870,397.5652
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,20.1516,20.1585,20.1007,20.1014
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,1134.7704,1131.6373,1133.4956,1132.3151
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,0.8788,0.8810,0.8796,0.8806
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,363.5336,364.4283,363.7623,363.5857
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (ms/batch)",LIB,5.8423,5.8302,5.8312,5.8281
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,202.0153,202.5056,202.3677,202.4630
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (items/sec)",HIB,170.9594,171.3099,171.2808,171.3647
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,21.9224,21.9027,21.9041,21.9527
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,58.0689,58.1442,58.1916,58.1383
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (items/sec)",HIB,17.2184,17.1960,17.1825,17.1981
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,188.3255,188.1505,188.2128,188.4415
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,42.4509,42.4853,42.4756,42.4217
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (items/sec)",HIB,29.7744,29.8179,29.7891,29.7882
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (ms/batch)",LIB,33.5681,33.5194,33.5525,33.5532
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,29.1108,29.1324,29.1435,29.1083
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (ms/batch)",LIB,58.0191,58.0188,58.0207,58.0879
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (items/sec)",HIB,17.2332,17.2332,17.2329,17.2130
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,274.5853,274.3872,274.2789,274.5981
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,29.1453,29.1215,29.1230,29.1232
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,274.2576,274.4692,274.4696,274.4604