Intel Core i9-14900K testing with a ASUS PRIME Z790-P WIFI (1402 BIOS) and ASUS Intel RPL-S 31GB 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 2403152-PTS-DEEPSPAR00
deepsparse 1.7 raptor lake
Intel Core i9-14900K testing with a ASUS PRIME Z790-P WIFI (1402 BIOS) and ASUS Intel RPL-S 31GB on Ubuntu 23.10 via the Phoronix Test Suite.
,,"a","b","c","d","e"
Processor,,Intel Core i9-14900K @ 5.70GHz (24 Cores / 32 Threads),Intel Core i9-14900K @ 5.70GHz (24 Cores / 32 Threads),Intel Core i9-14900K @ 5.70GHz (24 Cores / 32 Threads),Intel Core i9-14900K @ 5.70GHz (24 Cores / 32 Threads),Intel Core i9-14900K @ 5.70GHz (24 Cores / 32 Threads)
Motherboard,,ASUS PRIME Z790-P WIFI (1402 BIOS),ASUS PRIME Z790-P WIFI (1402 BIOS),ASUS PRIME Z790-P WIFI (1402 BIOS),ASUS PRIME Z790-P WIFI (1402 BIOS),ASUS PRIME Z790-P WIFI (1402 BIOS)
Chipset,,Intel Device 7a27,Intel Device 7a27,Intel Device 7a27,Intel Device 7a27,Intel Device 7a27
Memory,,2 x 16GB DRAM-6000MT/s Corsair CMK32GX5M2B6000C36,2 x 16GB DRAM-6000MT/s Corsair CMK32GX5M2B6000C36,2 x 16GB DRAM-6000MT/s Corsair CMK32GX5M2B6000C36,2 x 16GB DRAM-6000MT/s Corsair CMK32GX5M2B6000C36,2 x 16GB DRAM-6000MT/s Corsair CMK32GX5M2B6000C36
Disk,,Western Digital WD_BLACK SN850X 1000GB,Western Digital WD_BLACK SN850X 1000GB,Western Digital WD_BLACK SN850X 1000GB,Western Digital WD_BLACK SN850X 1000GB,Western Digital WD_BLACK SN850X 1000GB
Graphics,,ASUS Intel RPL-S 31GB (1650MHz),ASUS Intel RPL-S 31GB (1650MHz),ASUS Intel RPL-S 31GB (1650MHz),ASUS Intel RPL-S 31GB (1650MHz),ASUS Intel RPL-S 31GB (1650MHz)
Audio,,Realtek ALC897,Realtek ALC897,Realtek ALC897,Realtek ALC897,Realtek ALC897
Monitor,,ASUS VP28U,ASUS VP28U,ASUS VP28U,ASUS VP28U,ASUS VP28U
OS,,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10
Kernel,,6.8.0-phx (x86_64),6.8.0-phx (x86_64),6.8.0-phx (x86_64),6.8.0-phx (x86_64),6.8.0-phx (x86_64)
Desktop,,GNOME Shell 45.1,GNOME Shell 45.1,GNOME Shell 45.1,GNOME Shell 45.1,GNOME Shell 45.1
Display Server,,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7,X Server 1.21.1.7
OpenGL,,4.6 Mesa 24.0~git2312240600.c05261~oibaf~m (git-c05261a 2023-12-24 mantic-oibaf-ppa),4.6 Mesa 24.0~git2312240600.c05261~oibaf~m (git-c05261a 2023-12-24 mantic-oibaf-ppa),4.6 Mesa 24.0~git2312240600.c05261~oibaf~m (git-c05261a 2023-12-24 mantic-oibaf-ppa),4.6 Mesa 24.0~git2312240600.c05261~oibaf~m (git-c05261a 2023-12-24 mantic-oibaf-ppa),4.6 Mesa 24.0~git2312240600.c05261~oibaf~m (git-c05261a 2023-12-24 mantic-oibaf-ppa)
Compiler,,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0
File-System,,ext4,ext4,ext4,ext4,ext4
Screen Resolution,,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160
,,"a","b","c","d","e"
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,975.8077,941.7863,927.7726,1011.7146,994.7677
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,1.0225,1.0591,1.0746,0.9856,1.0024
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,3.4607,3.4488,3.53,3.4601,3.4336
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1152.2519,1156.1766,1129.727,1152.7523,1161.2978
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,7.6693,7.7518,7.5635,7.6435,7.6128
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,518.2458,512.6893,525.3862,520.0115,521.9992
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (ms/batch)",LIB,20.0825,19.6607,19.6462,19.8227,19.9587
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (items/sec)",HIB,49.7864,50.8544,50.892,50.4405,50.0942
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (ms/batch)",LIB,72.9891,71.4267,71.4383,72.0667,71.9383
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (items/sec)",HIB,13.6991,13.9983,13.9961,13.8746,13.8988
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,374.6573,368.5855,373.1233,375.6293,368.2256
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,10.6773,10.8516,10.7197,10.6496,10.8623
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (ms/batch)",LIB,8.0391,7.8904,7.9405,7.9734,7.9248
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (items/sec)",HIB,124.3319,126.6727,125.8707,125.3512,126.1129
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (ms/batch)",LIB,104.1188,104.392,105.1934,105.5378,104.5183
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (items/sec)",HIB,9.6041,9.5789,9.5059,9.4750,9.5673
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,27.9745,27.7941,27.9005,27.9110,27.6188
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,105.8800,106.2107,105.4393,106.7958,106.6262
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,142.9151,143.8358,143.2884,143.2367,144.7457
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (items/sec)",HIB,9.4444,9.4148,9.4838,9.3639,9.3782
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,324.5630,327.1912,326.888,327.2907,328.5605
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,3.0776,3.0531,3.056,3.0521,3.0404
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (ms/batch)",LIB,7.9967,7.9282,7.9467,7.9961,7.9452
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream (items/sec)",HIB,124.9918,126.0684,125.7691,125.0031,125.7981
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,269.9726,268.0825,267.9952,269.6208,268.5519
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,14.8156,14.9195,14.9245,14.8348,14.8935
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,81.4912,81.5021,81.5086,81.6823,81.1745
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,49.0714,49.066,49.0612,48.9564,49.2619
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,379.7141,379.1422,378.2626,378.1676,377.3639
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,10.5338,10.5495,10.5739,10.5769,10.5993
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,9.1560,9.199,9.1596,9.1642,9.2062
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,436.2483,434.2205,436.1158,435.8541,433.8822
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,67.2624,67.6241,67.3817,67.4110,67.3195
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,14.8628,14.7838,14.8369,14.8305,14.8504
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,20.3301,20.2407,20.2619,20.2703,20.2315
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,196.6202,197.4838,197.2772,197.1962,197.5747
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,7.9348,7.9643,7.9518,7.9571,7.9673
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream (items/sec)",HIB,125.9194,125.4487,125.6334,125.5685,125.4108
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,27.9492,27.9208,27.8803,27.9572,27.8453
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,143.0378,143.1866,143.3914,142.9982,143.5701
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream (ms/batch)",LIB,88.8680,88.8701,88.9381,88.9280,88.978
"Neural Magic DeepSparse - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream (items/sec)",HIB,11.2508,11.2506,11.242,11.2433,11.2371
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,71.6975,71.7457,71.7627,71.7605,71.7753
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,55.7746,55.7375,55.7242,55.7256,55.7142