2 x AMD EPYC 9684X 96-Core testing with a AMD Titanite_4G (RTI1007B 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 2403164-NE-DDFG2505160
ddfg
2 x AMD EPYC 9684X 96-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.
,,"a","b","c","d"
Processor,,2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads),2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads),2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads),2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads)
Motherboard,,AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS),AMD Titanite_4G (RTI1007B BIOS)
Chipset,,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4
Memory,,1520GB,1520GB,1520GB,1520GB
Disk,,3201GB Micron_7450_MTFDKCB3T2TFS + 257GB Flash Drive,3201GB Micron_7450_MTFDKCB3T2TFS + 257GB Flash Drive,3201GB Micron_7450_MTFDKCB3T2TFS + 257GB Flash Drive,3201GB Micron_7450_MTFDKCB3T2TFS + 257GB Flash Drive
Graphics,,ASPEED,ASPEED,ASPEED,ASPEED
Network,,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe
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)
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,,640x480,640x480,640x480,640x480
,,"a","b","c","d"
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,24242.3848,24888.1563,28968.9536,24331.0626
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,2.9358,2.8607,2.5008,2.9271
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,5.218,5.2109,5.1985,5.1383
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,191.5137,191.7714,192.2335,194.4729
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,17.2212,17.3043,17.3188,17.257
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,5566.3853,5538.9806,5534.2604,5554.0345
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream (ms/batch)",LIB,47.9735,48.0337,48.2177,48.8364
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream (items/sec)",HIB,20.8303,20.8052,20.7259,20.4622
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,36.8891,36.9324,36.9216,36.9564
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,2598.2083,2595.1763,2595.4788,2592.8516
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,713.5443,717.4900,715.8770,714.456
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,132.9523,132.9817,132.8792,133.012
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,715.4595,717.2565,709.2588,715.4294
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,132.9467,132.7968,133.8061,132.9148
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,14.5734,14.6134,14.5791,14.5348
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,68.5822,68.3972,68.5565,68.7657
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (ms/batch)",LIB,20.6047,20.6727,20.6037,20.6072
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (items/sec)",HIB,48.516,48.3555,48.5178,48.5095
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,20.5991,20.6441,20.6607,20.6629
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (items/sec)",HIB,48.5284,48.4228,48.3841,48.379
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,381.0376,382.1237,382.1742,381.1234
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,249.7234,249.4018,249.0943,249.7754
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (ms/batch)",LIB,15.3899,15.3982,15.3844,15.366
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (items/sec)",HIB,64.8907,64.8586,64.9222,64.997
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (ms/batch)",LIB,4.4325,4.4329,4.4329,4.4307
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (items/sec)",HIB,225.4674,225.4496,225.4415,225.5614
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,83.6574,83.8482,83.9259,83.7657
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1144.5034,1142.9944,1141.2417,1144.0054
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,119.9052,120.1787,120.3976,119.9993
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,798.6248,796.5966,795.0277,797.7062
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,54.3739,54.4869,54.4588,54.3609
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1762.5286,1758.8057,1759.9562,1763.4247
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,5.4946,5.5170,5.5224,5.502
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,17421.4665,17350.4640,17333.3501,17400.5797
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (ms/batch)",LIB,4.8321,4.7642,4.7875,4.7823
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (items/sec)",HIB,206.8154,209.7711,208.7406,208.9767
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,54.3534,54.5660,54.5610,54.505
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1763.1949,1756.1742,1756.5604,1758.3058
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,4.7104,4.7035,4.7002,4.6801
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,212.1812,212.4945,212.6390,213.5555
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,1.2364,1.2409,1.2381,1.2375
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,807.1699,804.4025,806.2338,806.3219
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (ms/batch)",LIB,4.8123,4.7882,4.7905,4.7773
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (items/sec)",HIB,207.6733,208.7235,208.6327,209.1911
"SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 4K (FPS)",HIB,8.557,8.575,8.484,8.634
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,149.069,163.175,160.560,163.5
"Primesieve - Length: 1e13 (sec)",LIB,11.789,11.848,11.871,11.841
"SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p (FPS)",HIB,22.964,22.898,23.474,22.713
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,89.277,91.288,90.441,86.593
"SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 4K (FPS)",HIB,159.218,161.653,162.020,162.377
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 1080p (FPS)",HIB,176.674,182.531,184.132,183.285
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 1080p (FPS)",HIB,572.349,566.993,568.209,577.444
"SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 1080p (FPS)",HIB,564.413,606.376,588.450,598.04
"Primesieve - Length: 1e12 (sec)",LIB,1.164,1.164,1.156,1.142