dfgg Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus ICL GT2 16GB on Ubuntu 23.04 via the Phoronix Test Suite. a: Processor: Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: Dell 06CDVY (1.0.9 BIOS), Chipset: Intel Ice Lake-LP DRAM, Memory: 16GB, Disk: Toshiba KBG40ZPZ512G NVMe 512GB, Graphics: Intel Iris Plus ICL GT2 16GB (1100MHz), Audio: Realtek ALC289, Network: Intel Ice Lake-LP PCH CNVi WiFi OS: Ubuntu 23.04, Kernel: 6.2.0-36-generic (x86_64), Desktop: GNOME Shell 44.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.4-0ubuntu1~23.04.1, OpenCL: OpenCL 3.0, Compiler: GCC 12.3.0, File-System: ext4, Screen Resolution: 1920x1200 b: Processor: Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: Dell 06CDVY (1.0.9 BIOS), Chipset: Intel Ice Lake-LP DRAM, Memory: 16GB, Disk: Toshiba KBG40ZPZ512G NVMe 512GB, Graphics: Intel Iris Plus ICL GT2 16GB (1100MHz), Audio: Realtek ALC289, Network: Intel Ice Lake-LP PCH CNVi WiFi OS: Ubuntu 23.04, Kernel: 6.2.0-36-generic (x86_64), Desktop: GNOME Shell 44.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.4-0ubuntu1~23.04.1, OpenCL: OpenCL 3.0, Compiler: GCC 12.3.0, File-System: ext4, Screen Resolution: 1920x1200 LeelaChessZero 0.30 Backend: BLAS Nodes Per Second > Higher Is Better a . 32 |================================================== b . 45 |======================================================================= LeelaChessZero 0.30 Backend: Eigen Nodes Per Second > Higher Is Better a . 20 |=========================================================== b . 24 |======================================================================= Xmrig 6.21 Variant: KawPow - Hash Count: 1M H/s > Higher Is Better a . 1296.4 |================================================================= b . 1333.9 |=================================================================== Xmrig 6.21 Variant: Monero - Hash Count: 1M H/s > Higher Is Better a . 1308.1 |=================================================================== b . 1290.3 |================================================================== Xmrig 6.21 Variant: Wownero - Hash Count: 1M H/s > Higher Is Better a . 1573.6 |=================================================================== b . 1524.2 |================================================================= Xmrig 6.21 Variant: GhostRider - Hash Count: 1M H/s > Higher Is Better a . 187.4 |==================================================================== b . 185.2 |=================================================================== Xmrig 6.21 Variant: CryptoNight-Heavy - Hash Count: 1M H/s > Higher Is Better a . 1298.8 |=================================================================== b . 1282.1 |================================================================== Xmrig 6.21 Variant: CryptoNight-Femto UPX2 - Hash Count: 1M H/s > Higher Is Better a . 1302.3 |=================================================================== b . 1281.7 |================================================================== Java SciMark 2.2 Computational Test: Composite Mflops > Higher Is Better a . 2605.95 |================================================================== b . 2611.98 |================================================================== Java SciMark 2.2 Computational Test: Monte Carlo Mflops > Higher Is Better a . 935.32 |=================================================================== b . 936.54 |=================================================================== Java SciMark 2.2 Computational Test: Fast Fourier Transform Mflops > Higher Is Better a . 518.57 |=================================================================== b . 516.53 |=================================================================== Java SciMark 2.2 Computational Test: Sparse Matrix Multiply Mflops > Higher Is Better a . 1999.02 |================================================================== b . 1994.16 |================================================================== Java SciMark 2.2 Computational Test: Dense LU Matrix Factorization Mflops > Higher Is Better a . 8173.69 |================================================================== b . 8211.45 |================================================================== Java SciMark 2.2 Computational Test: Jacobi Successive Over-Relaxation Mflops > Higher Is Better a . 1403.14 |================================================================== b . 1401.22 |================================================================== WebP2 Image Encode 20220823 Encode Settings: Default MP/s > Higher Is Better a . 2.60 |===================================================================== b . 2.45 |================================================================= WebP2 Image Encode 20220823 Encode Settings: Quality 75, Compression Effort 7 MP/s > Higher Is Better a . 0.03 |===================================================================== b . 0.03 |===================================================================== WebP2 Image Encode 20220823 Encode Settings: Quality 95, Compression Effort 7 MP/s > Higher Is Better a . 0.01 |===================================================================== b . 0.01 |===================================================================== WebP2 Image Encode 20220823 Encode Settings: Quality 100, Compression Effort 5 MP/s > Higher Is Better a . 0.95 |===================================================================== b . 0.95 |===================================================================== WebP2 Image Encode 20220823 Encode Settings: Quality 100, Lossless Compression MP/s > Higher Is Better SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 0.892 |==================================================================== b . 0.858 |================================================================= SVT-AV1 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 7.044 |==================================================================== b . 6.765 |================================================================= SVT-AV1 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 31.31 |==================================================================== b . 28.23 |============================================================= SVT-AV1 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 33.86 |==================================================================== b . 31.87 |================================================================ SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 3.684 |==================================================================== b . 3.605 |=================================================================== SVT-AV1 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 26.04 |================================================================== b . 26.97 |==================================================================== SVT-AV1 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 192.19 |=================================================================== b . 192.67 |=================================================================== SVT-AV1 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 254.96 |=================================================================== b . 256.08 |=================================================================== OpenSSL Algorithm: SHA256 byte/s > Higher Is Better a . 2139384230 |=============================================================== b . 2104039050 |============================================================== OpenSSL Algorithm: SHA512 byte/s > Higher Is Better a . 856037790 |================================================================ b . 813051380 |============================================================= OpenSSL Algorithm: RSA4096 sign/s > Higher Is Better a . 769.0 |==================================================================== b . 727.2 |================================================================ OpenSSL Algorithm: RSA4096 verify/s > Higher Is Better a . 45019.3 |================================================================== b . 43229.0 |=============================================================== OpenSSL Algorithm: ChaCha20 byte/s > Higher Is Better a . 15375647270 |============================================================== b . 14830093930 |============================================================ OpenSSL Algorithm: AES-128-GCM byte/s > Higher Is Better a . 15202890820 |============================================================== b . 15081739060 |============================================================== OpenSSL Algorithm: AES-256-GCM byte/s > Higher Is Better a . 13364107950 |============================================================== b . 12548378350 |========================================================== OpenSSL Algorithm: ChaCha20-Poly1305 byte/s > Higher Is Better a . 10536056700 |============================================================== b . 9830306880 |========================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Geometric Mean Of All Queries Seconds < Lower Is Better a . 4.7325257 |=============================================================== b . 4.8087436 |================================================================ Apache Spark TPC-H 3.5 Scale Factor: 1 - Q01 Seconds < Lower Is Better a . 7.15123463 |=============================================================== b . 7.08784056 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q02 Seconds < Lower Is Better a . 3.88890910 |=============================================================== b . 3.41797328 |======================================================= Apache Spark TPC-H 3.5 Scale Factor: 1 - Q03 Seconds < Lower Is Better a . 6.39238787 |========================================================= b . 7.07467794 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q04 Seconds < Lower Is Better a . 6.71648932 |============================================================ b . 7.08578300 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q05 Seconds < Lower Is Better a . 6.38540220 |========================================================= b . 7.11330652 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q06 Seconds < Lower Is Better a . 3.51144052 |=============================================================== b . 3.24464250 |========================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q07 Seconds < Lower Is Better a . 6.48225832 |=============================================================== b . 5.84497738 |========================================================= Apache Spark TPC-H 3.5 Scale Factor: 1 - Q08 Seconds < Lower Is Better a . 4.97744513 |========================================================== b . 5.44389009 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q09 Seconds < Lower Is Better a . 7.87298393 |========================================================= b . 8.69179630 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q10 Seconds < Lower Is Better a . 5.49699688 |========================================================== b . 5.96171904 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q11 Seconds < Lower Is Better a . 1.93730366 |============================================================ b . 2.02040172 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q12 Seconds < Lower Is Better a . 5.02531958 |=============================================================== b . 4.83623695 |============================================================= Apache Spark TPC-H 3.5 Scale Factor: 1 - Q13 Seconds < Lower Is Better a . 3.23068547 |=============================================================== b . 2.99688220 |========================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q14 Seconds < Lower Is Better a . 3.69340801 |=========================================================== b . 3.97235441 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q15 Seconds < Lower Is Better a . 3.91055250 |=============================================================== b . 3.84038305 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q16 Seconds < Lower Is Better a . 1.72381175 |===================================================== b . 2.04605532 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q17 Seconds < Lower Is Better a . 8.40441418 |============================================================== b . 8.57745552 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q18 Seconds < Lower Is Better a . 10.34 |==================================================================== b . 10.20 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q19 Seconds < Lower Is Better a . 4.04202414 |=============================================================== b . 3.57351255 |======================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q20 Seconds < Lower Is Better a . 4.86529493 |============================================================ b . 5.14292622 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q21 Seconds < Lower Is Better a . 20.62 |==================================================================== b . 20.04 |================================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q22 Seconds < Lower Is Better a . 2.24996281 |=============================================================== b . 2.04710698 |========================================================= Apache Spark TPC-H 3.5 Scale Factor: 10 - Geometric Mean Of All Queries Seconds < Lower Is Better a . 41.82 |==================================================================== b . 41.34 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q01 Seconds < Lower Is Better a . 41.61 |=============================================================== b . 44.68 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q02 Seconds < Lower Is Better a . 12.79 |==================================================================== b . 12.19 |================================================================= Apache Spark TPC-H 3.5 Scale Factor: 10 - Q03 Seconds < Lower Is Better a . 55.94 |==================================================================== b . 55.58 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q04 Seconds < Lower Is Better a . 48.48 |==================================================================== b . 48.52 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q05 Seconds < Lower Is Better a . 62.50 |================================================================ b . 66.50 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q06 Seconds < Lower Is Better a . 36.56 |=================================================================== b . 37.06 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q07 Seconds < Lower Is Better a . 54.83 |=================================================================== b . 55.61 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q08 Seconds < Lower Is Better a . 62.19 |==================================================================== b . 60.07 |================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q09 Seconds < Lower Is Better a . 73.76 |==================================================================== b . 73.32 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q10 Seconds < Lower Is Better a . 51.23 |==================================================================== b . 51.32 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q11 Seconds < Lower Is Better a . 10.60 |================================================================== b . 10.96 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q12 Seconds < Lower Is Better a . 48.54 |==================================================================== b . 47.39 |================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q13 Seconds < Lower Is Better a . 20.44 |================================================================== b . 21.21 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q14 Seconds < Lower Is Better a . 38.60 |=================================================================== b . 38.96 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q15 Seconds < Lower Is Better a . 37.03 |==================================================================== b . 35.77 |================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q16 Seconds < Lower Is Better a . 11.41 |=================================================================== b . 11.61 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q17 Seconds < Lower Is Better a . 100.78 |=================================================================== b . 94.20 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q18 Seconds < Lower Is Better a . 106.44 |=================================================================== b . 103.68 |================================================================= Apache Spark TPC-H 3.5 Scale Factor: 10 - Q19 Seconds < Lower Is Better a . 39.19 |==================================================================== b . 38.37 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q20 Seconds < Lower Is Better a . 49.49 |==================================================================== b . 47.05 |================================================================= Apache Spark TPC-H 3.5 Scale Factor: 10 - Q21 Seconds < Lower Is Better a . 196.26 |=================================================================== b . 189.40 |================================================================= Apache Spark TPC-H 3.5 Scale Factor: 10 - Q22 Seconds < Lower Is Better a . 12.72 |================================================================== b . 13.09 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 2.1073 |=================================================================== b . 1.9736 |=============================================================== Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 946.79 |============================================================== b . 1010.44 |================================================================== Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 2.1503 |=================================================================== b . 2.0978 |================================================================= Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 465.03 |================================================================= b . 476.67 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 84.71 |==================================================================== b . 83.38 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 23.57 |=================================================================== b . 23.94 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 76.32 |==================================================================== b . 75.06 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 13.09 |=================================================================== b . 13.31 |==================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 34.00 |==================================================================== b . 33.08 |================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 58.77 |================================================================== b . 60.41 |==================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 33.34 |==================================================================== b . 32.51 |================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 29.98 |================================================================== b . 30.75 |==================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 233.27 |=================================================================== b . 227.73 |================================================================= Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 8.5472 |================================================================= b . 8.7547 |=================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 209.81 |=================================================================== b . 194.45 |============================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 4.7530 |============================================================== b . 5.1288 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 14.02 |==================================================================== b . 13.57 |================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 142.62 |================================================================= b . 147.35 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 12.45 |==================================================================== b . 12.42 |==================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 80.29 |==================================================================== b . 80.51 |==================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 2.7047 |=================================================================== b . 2.6521 |================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 737.65 |================================================================== b . 752.24 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 2.6753 |=================================================================== b . 2.6391 |================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 373.77 |================================================================== b . 378.91 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 34.28 |==================================================================== b . 33.34 |================================================================== Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 58.30 |================================================================== b . 59.93 |==================================================================== Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 33.29 |==================================================================== b . 32.75 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 30.02 |=================================================================== b . 30.51 |==================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 14.16 |==================================================================== b . 13.91 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 141.23 |================================================================== b . 143.49 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 12.85 |==================================================================== b . 12.70 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 77.81 |=================================================================== b . 78.72 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 19.38 |==================================================================== b . 19.30 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 103.17 |=================================================================== b . 103.50 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 18.22 |==================================================================== b . 18.04 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 54.87 |=================================================================== b . 55.43 |==================================================================== Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 4.2078 |=================================================================== b . 4.1657 |================================================================== Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 475.16 |================================================================== b . 480.05 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 4.3550 |=================================================================== b . 4.2633 |================================================================== Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 229.59 |================================================================== b . 234.54 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 37.34 |==================================================================== b . 36.98 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 53.52 |=================================================================== b . 54.04 |==================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 33.76 |==================================================================== b . 33.44 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 29.60 |=================================================================== b . 29.89 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 2.153 |==================================================================== b . 2.142 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 926.22 |=================================================================== b . 931.34 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 2.1502 |=================================================================== b . 2.1345 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 465.05 |=================================================================== b . 468.48 |=================================================================== ScyllaDB 5.2.9 Test: Writes Op/s > Higher Is Better a . 27851 |==================================================================== b . 25475 |==============================================================