zn 2 x AMD EPYC 7773X 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 22.04, Kernel: 5.15.0-47-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 22.04, Kernel: 5.15.0-47-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 22.04, Kernel: 5.15.0-47-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 Apache HTTP Server 2.4.56 Concurrent Requests: 100 Requests Per Second > Higher Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 200 Requests Per Second > Higher Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 500 Requests Per Second > Higher Is Better a . 132220.73 |============================================================= b . 136743.33 |=============================================================== c . 138201.89 |================================================================ Apache HTTP Server 2.4.56 Concurrent Requests: 1000 Requests Per Second > Higher Is Better Blender 3.5 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 14.88 |==================================================================== b . 14.86 |==================================================================== c . 14.62 |=================================================================== Blender 3.5 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a . 37.20 |==================================================================== b . 37.33 |==================================================================== c . 37.37 |==================================================================== Blender 3.5 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a . 18.53 |=================================================================== b . 18.74 |==================================================================== c . 18.72 |==================================================================== Blender 3.5 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better a . 136.18 |=================================================================== b . 136.92 |=================================================================== c . 136.80 |=================================================================== Blender 3.5 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a . 45.39 |=================================================================== b . 46.05 |==================================================================== c . 45.67 |=================================================================== BRL-CAD 7.34 VGR Performance Metric VGR Performance Metric > Higher Is Better a . 3089503 |================================================================== c . 3047016 |================================================================= Build2 0.15 Time To Compile Seconds < Lower Is Better a . 67.56 |==================================================================== b . 63.33 |================================================================ c . 63.67 |================================================================ ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Queries Per Minute, Geo Mean > Higher Is Better a . 269.19 |============================================= b . 401.11 |=================================================================== c . 398.91 |=================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Queries Per Minute, Geo Mean > Higher Is Better a . 273.45 |============================================ b . 413.04 |=================================================================== c . 403.80 |================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Queries Per Minute, Geo Mean > Higher Is Better a . 274.77 |============================================= b . 404.69 |================================================================== c . 410.26 |=================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 128 ops/s > Higher Is Better a . 754.5 |==================================================================== b . 757.2 |==================================================================== c . 745.2 |=================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 256 ops/s > Higher Is Better a . 748.2 |==================================================================== b . 750.5 |==================================================================== c . 751.5 |==================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 512 ops/s > Higher Is Better a . 745.5 |==================================================================== b . 750.7 |==================================================================== c . 744.0 |=================================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 128 ops/s > Higher Is Better a . 49533.1 |================================================================== b . 49454.9 |================================================================== c . 48767.1 |================================================================= CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 256 ops/s > Higher Is Better a . 50683.8 |================================================================== b . 47146.4 |============================================================= c . 50241.0 |================================================================= CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 512 ops/s > Higher Is Better a . 50885.4 |================================================================ b . 52529.5 |================================================================== c . 46271.6 |========================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 128 ops/s > Higher Is Better a . 65133.4 |================================================================= b . 66115.6 |================================================================== c . 57115.1 |========================================================= CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 256 ops/s > Higher Is Better a . 58777.4 |========================================================= b . 68400.0 |================================================================== c . 57909.1 |======================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 512 ops/s > Higher Is Better a . 68395.4 |================================================================== b . 56432.6 |====================================================== c . 68164.4 |================================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 128 ops/s > Higher Is Better a . 70322.4 |================================================================ b . 72193.2 |================================================================== c . 69343.2 |=============================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 256 ops/s > Higher Is Better a . 72158.1 |================================================================= b . 63269.0 |========================================================= c . 73004.2 |================================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 512 ops/s > Higher Is Better a . 60903.7 |======================================================= b . 62154.2 |======================================================== c . 73656.2 |================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 128 ops/s > Higher Is Better a . 88685.5 |================================================================== b . 88959.8 |================================================================== c . 87476.4 |================================================================= CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 256 ops/s > Higher Is Better a . 88008.4 |================================================================== b . 74468.4 |======================================================== c . 73252.3 |======================================================= CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 512 ops/s > Higher Is Better a . 72445.0 |===================================================== b . 90237.5 |================================================================== c . 86788.8 |=============================================================== DeepRec Model: BST - Data Type: BF16 Throughput > Higher Is Better DeepRec Model: BST - Data Type: FP32 Throughput > Higher Is Better DeepRec Model: DIN - Data Type: BF16 Throughput > Higher Is Better DeepRec Model: DIN - Data Type: FP32 Throughput > Higher Is Better DeepRec Model: PLE - Data Type: BF16 Throughput > Higher Is Better DeepRec Model: PLE - Data Type: FP32 Throughput > Higher Is Better DeepRec Model: DLRM - Data Type: BF16 Throughput > Higher Is Better DeepRec Model: DLRM - Data Type: FP32 Throughput > Higher Is Better DeepRec Model: MMOE - Data Type: BF16 Throughput > Higher Is Better DeepRec Model: MMOE - Data Type: FP32 Throughput > Higher Is Better DeepRec Model: DCNv2 - Data Type: BF16 Throughput > Higher Is Better DeepRec Model: DCNv2 - Data Type: FP32 Throughput > Higher Is Better Embree 4.0.1 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better a . 128.02 |================================================================== b . 128.02 |================================================================== c . 129.41 |=================================================================== Embree 4.0.1 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better a . 115.16 |================================================================= b . 117.90 |=================================================================== c . 117.68 |=================================================================== Embree 4.0.1 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better a . 72.60 |========================================================== b . 83.22 |================================================================== c . 85.24 |==================================================================== Embree 4.0.1 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better a . 69.30 |========================================================= b . 82.54 |==================================================================== c . 79.64 |================================================================== Google Draco 1.5.6 Model: Lion ms < Lower Is Better a . 4954 |===================================================================== b . 4942 |===================================================================== c . 4951 |===================================================================== Google Draco 1.5.6 Model: Church Facade ms < Lower Is Better a . 5872 |===================================================================== b . 5856 |===================================================================== c . 5876 |===================================================================== GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better a . 10.34 |=============================================================== b . 11.10 |==================================================================== c . 11.13 |==================================================================== Intel TensorFlow 2.12 Model: resnet50_fp32_pretrained_model - Batch Size: 1 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_int8_pretrained_model - Batch Size: 1 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_fp32_pretrained_model - Batch Size: 16 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_fp32_pretrained_model - Batch Size: 32 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_fp32_pretrained_model - Batch Size: 64 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_fp32_pretrained_model - Batch Size: 96 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_int8_pretrained_model - Batch Size: 16 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_int8_pretrained_model - Batch Size: 32 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_int8_pretrained_model - Batch Size: 64 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_int8_pretrained_model - Batch Size: 96 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_fp32_pretrained_model - Batch Size: 256 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_fp32_pretrained_model - Batch Size: 512 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_fp32_pretrained_model - Batch Size: 960 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_int8_pretrained_model - Batch Size: 256 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_int8_pretrained_model - Batch Size: 512 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: resnet50_int8_pretrained_model - Batch Size: 960 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_fp32_pretrained_model - Batch Size: 1 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_int8_pretrained_model - Batch Size: 1 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_fp32_pretrained_model - Batch Size: 1 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_int8_pretrained_model - Batch Size: 1 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_fp32_pretrained_model - Batch Size: 16 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_fp32_pretrained_model - Batch Size: 32 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_fp32_pretrained_model - Batch Size: 64 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_fp32_pretrained_model - Batch Size: 96 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_int8_pretrained_model - Batch Size: 16 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_int8_pretrained_model - Batch Size: 32 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_int8_pretrained_model - Batch Size: 64 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_int8_pretrained_model - Batch Size: 96 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_fp32_pretrained_model - Batch Size: 16 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_fp32_pretrained_model - Batch Size: 32 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_fp32_pretrained_model - Batch Size: 64 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_fp32_pretrained_model - Batch Size: 96 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_int8_pretrained_model - Batch Size: 16 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_int8_pretrained_model - Batch Size: 32 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_int8_pretrained_model - Batch Size: 64 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_int8_pretrained_model - Batch Size: 96 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_fp32_pretrained_model - Batch Size: 256 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_fp32_pretrained_model - Batch Size: 512 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_fp32_pretrained_model - Batch Size: 960 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_int8_pretrained_model - Batch Size: 256 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_int8_pretrained_model - Batch Size: 512 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: inceptionv4_int8_pretrained_model - Batch Size: 960 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_fp32_pretrained_model - Batch Size: 256 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_fp32_pretrained_model - Batch Size: 512 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_fp32_pretrained_model - Batch Size: 960 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_int8_pretrained_model - Batch Size: 256 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_int8_pretrained_model - Batch Size: 512 images/sec > Higher Is Better Intel TensorFlow 2.12 Model: mobilenetv1_int8_pretrained_model - Batch Size: 960 images/sec > Higher Is Better John The Ripper 2023.03.14 Test: bcrypt Real C/S > Higher Is Better a . 165909 |================================================================== b . 168729 |=================================================================== c . 167500 |=================================================================== John The Ripper 2023.03.14 Test: WPA PSK Real C/S > Higher Is Better a . 391304 |================================================================== b . 394864 |=================================================================== c . 394449 |=================================================================== John The Ripper 2023.03.14 Test: Blowfish Real C/S > Higher Is Better a . 158999 |=============================================================== b . 169154 |=================================================================== c . 169113 |=================================================================== John The Ripper 2023.03.14 Test: HMAC-SHA512 Real C/S > Higher Is Better a . 91862000 |================================================================= b . 80447000 |========================================================= c . 83472000 |=========================================================== John The Ripper 2023.03.14 Test: MD5 Real C/S > Higher Is Better a . 10348000 |================================================================= b . 10330000 |================================================================= c . 10376000 |================================================================= Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 73.20 |==================================================================== b . 73.23 |==================================================================== c . 73.18 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 870.12 |=================================================================== b . 869.75 |=================================================================== c . 868.95 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 20.51 |=================================================================== b . 20.83 |==================================================================== c . 20.41 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 48.75 |==================================================================== b . 47.99 |=================================================================== c . 48.99 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 931.46 |=================================================================== b . 931.56 |=================================================================== c . 931.12 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 68.62 |==================================================================== b . 68.55 |==================================================================== c . 68.58 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 110.58 |================================================================== b . 112.37 |=================================================================== c . 107.32 |================================================================ Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 9.0399 |================================================================= b . 8.8949 |================================================================ c . 9.3134 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 310.23 |=================================================================== b . 309.49 |=================================================================== c . 310.12 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 205.64 |=================================================================== b . 205.90 |=================================================================== c . 205.77 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 42.23 |==================================================================== b . 42.28 |==================================================================== c . 40.47 |================================================================= Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 23.66 |================================================================= b . 23.63 |================================================================= c . 24.69 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 409.68 |=================================================================== b . 409.40 |=================================================================== c . 410.16 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 155.82 |=================================================================== b . 155.82 |=================================================================== c . 155.34 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 111.84 |=================================================================== b . 111.95 |=================================================================== c . 111.43 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 8.9373 |=================================================================== b . 8.9292 |=================================================================== c . 8.9700 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 829.94 |=================================================================== b . 828.03 |=================================================================== c . 826.51 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 76.99 |==================================================================== b . 77.11 |==================================================================== c . 77.30 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 148.86 |=================================================================== b . 148.36 |=================================================================== c . 148.13 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 6.7151 |=================================================================== b . 6.7380 |=================================================================== c . 6.7480 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 609.62 |=================================================================== b . 609.86 |=================================================================== c . 607.01 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 104.84 |=================================================================== b . 104.73 |=================================================================== c . 104.98 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 152.26 |=================================================================== b . 152.09 |=================================================================== c . 150.05 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 6.5656 |================================================================== b . 6.5727 |================================================================== c . 6.6621 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 108.36 |=================================================================== b . 108.23 |=================================================================== c . 108.44 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 586.72 |=================================================================== b . 587.70 |=================================================================== c . 587.22 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 28.91 |==================================================================== b . 28.76 |==================================================================== c . 28.90 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 34.56 |==================================================================== b . 34.75 |==================================================================== c . 34.58 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 307.29 |=================================================================== b . 308.48 |=================================================================== c . 307.58 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 207.55 |=================================================================== b . 206.88 |=================================================================== c . 207.63 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 58.39 |==================================================================== b . 58.04 |==================================================================== c . 56.68 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 17.12 |================================================================== b . 17.22 |================================================================== c . 17.63 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 73.17 |==================================================================== b . 72.91 |==================================================================== c . 73.00 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 868.78 |=================================================================== b . 868.33 |=================================================================== c . 871.15 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 20.81 |==================================================================== b . 20.76 |==================================================================== c . 20.48 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 48.04 |=================================================================== b . 48.16 |=================================================================== c . 48.80 |==================================================================== nginx 1.23.2 Connections: 100 Requests Per Second > Higher Is Better nginx 1.23.2 Connections: 200 Requests Per Second > Higher Is Better nginx 1.23.2 Connections: 500 Requests Per Second > Higher Is Better a . 157063.78 |=============================================================== b . 158866.84 |================================================================ c . 158520.97 |================================================================ nginx 1.23.2 Connections: 1000 Requests Per Second > Higher Is Better OpenSSL 3.1 Algorithm: SHA256 byte/s > Higher Is Better a . 152584380080 |============================================================= b . 152693644050 |============================================================= c . 152508733130 |============================================================= OpenSSL 3.1 Algorithm: SHA512 byte/s > Higher Is Better a . 48236952220 |============================================================== b . 48315690210 |============================================================== c . 48197587440 |============================================================== OpenSSL 3.1 Algorithm: RSA4096 sign/s > Higher Is Better a . 27007.5 |================================================================== b . 27049.8 |================================================================== c . 26996.1 |================================================================== OpenSSL 3.1 Algorithm: RSA4096 verify/s > Higher Is Better a . 1780535.1 |================================================================ b . 1779979.3 |================================================================ c . 1780224.1 |================================================================ OpenSSL 3.1 Algorithm: ChaCha20 byte/s > Higher Is Better a . 434799000510 |============================================================= b . 435044716540 |============================================================= c . 434402920310 |============================================================= OpenSSL 3.1 Algorithm: AES-128-GCM byte/s > Higher Is Better a . 464927934750 |============================================================= b . 464448030860 |============================================================= c . 464259772140 |============================================================= OpenSSL 3.1 Algorithm: AES-256-GCM byte/s > Higher Is Better a . 424974892240 |============================================================= b . 425089252010 |============================================================= c . 424554074930 |============================================================= OpenSSL 3.1 Algorithm: ChaCha20-Poly1305 byte/s > Higher Is Better a . 285698755410 |============================================================= b . 285959794140 |============================================================= c . 286255847010 |============================================================= OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Items / Sec > Higher Is Better a . 489 |================================================================ b . 539 |====================================================================== c . 521 |==================================================================== OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar Items / Sec > Higher Is Better a . 337 |============================================================== b . 381 |====================================================================== c . 363 |=================================================================== Opus Codec Encoding 1.4 WAV To Opus Encode Seconds < Lower Is Better a . 31.86 |==================================================================== b . 31.90 |==================================================================== c . 32.01 |==================================================================== PETSc 3.19 Test: Streams MB/s > Higher Is Better a . 180447.27 |============================================== b . 251700.50 |================================================================ c . 250852.55 |================================================================ QuantLib 1.30 MFLOPS > Higher Is Better a . 2765.5 |=================================================================== b . 2758.8 |=================================================================== c . 2760.6 |=================================================================== RocksDB 8.0 Test: Random Read Op/s > Higher Is Better a . 454636874 |================================================================ b . 452696371 |================================================================ c . 454644374 |================================================================ RocksDB 8.0 Test: Update Random Op/s > Higher Is Better a . 294796 |=================================================================== b . 277428 |=============================================================== c . 292628 |=================================================================== RocksDB 8.0 Test: Read While Writing Op/s > Higher Is Better a . 13440214 |===================================================== b . 11473082 |============================================= c . 16535579 |================================================================= RocksDB 8.0 Test: Read Random Write Random Op/s > Higher Is Better a . 1926550 |================================================================== b . 1867319 |================================================================ c . 1884492 |================================================================= SPECFEM3D 4.0 Model: Mount St. Helens Seconds < Lower Is Better a . 6.744564640 |============================================================= b . 6.630654167 |============================================================ c . 6.834107424 |============================================================== SPECFEM3D 4.0 Model: Layered Halfspace Seconds < Lower Is Better a . 17.29 |==================================================================== b . 16.07 |=============================================================== c . 16.29 |================================================================ SPECFEM3D 4.0 Model: Tomographic Model Seconds < Lower Is Better a . 8.348192148 |============================================================== b . 8.303506049 |============================================================== c . 8.278936477 |============================================================= SPECFEM3D 4.0 Model: Homogeneous Halfspace Seconds < Lower Is Better a . 10.329585274 |============================================================= b . 10.107559726 |============================================================ c . 9.966862195 |=========================================================== SPECFEM3D 4.0 Model: Water-layered Halfspace Seconds < Lower Is Better a . 17.33 |================================================================== b . 17.73 |==================================================================== c . 17.86 |==================================================================== SVT-AV1 1.5 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 4.699 |=================================================================== b . 4.765 |==================================================================== c . 4.769 |==================================================================== SVT-AV1 1.5 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 66.31 |================================================================== b . 68.75 |==================================================================== c . 68.69 |==================================================================== SVT-AV1 1.5 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 146.39 |====================================================== b . 174.03 |================================================================= c . 180.03 |=================================================================== SVT-AV1 1.5 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 187.16 |=================================================================== b . 173.18 |============================================================== c . 180.54 |================================================================= SVT-AV1 1.5 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 10.08 |=================================================================== b . 10.15 |==================================================================== c . 10.16 |==================================================================== SVT-AV1 1.5 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 103.43 |=============================================================== b . 109.92 |=================================================================== c . 105.24 |================================================================ SVT-AV1 1.5 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 484.43 |========================================================= b . 521.27 |============================================================= c . 571.56 |=================================================================== SVT-AV1 1.5 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 500.49 |============================================================== b . 541.91 |=================================================================== c . 527.03 |================================================================= TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better a . 12.54 |==================================================================== b . 12.48 |==================================================================== c . 12.33 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better a . 13.24 |=================================================================== b . 13.37 |==================================================================== c . 13.10 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better a . 13.76 |==================================================================== b . 13.74 |==================================================================== c . 13.59 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: ResNet-50 images/sec > Higher Is Better a . 15.04 |==================================================================== b . 15.12 |==================================================================== c . 14.77 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 images/sec > Higher Is Better a . 16.59 |==================================================================== b . 16.67 |==================================================================== c . 16.34 |=================================================================== Timed FFmpeg Compilation 6.0 Time To Compile Seconds < Lower Is Better a . 15.70 |==================================================================== b . 13.66 |=========================================================== c . 13.71 |=========================================================== Timed Godot Game Engine Compilation 4.0 Time To Compile Seconds < Lower Is Better a . 102.83 |=================================================================== b . 98.42 |================================================================ c . 98.30 |================================================================ Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better a . 31.06 |==================================================================== b . 22.63 |================================================== c . 22.58 |================================================= Timed Linux Kernel Compilation 6.1 Build: allmodconfig Seconds < Lower Is Better a . 285.35 |=================================================================== b . 160.58 |====================================== c . 160.79 |====================================== Timed LLVM Compilation 16.0 Build System: Ninja Seconds < Lower Is Better a . 132.97 |=================================================================== b . 113.36 |========================================================= c . 112.52 |========================================================= Timed LLVM Compilation 16.0 Build System: Unix Makefiles Seconds < Lower Is Better a . 228.85 |=================================================================== b . 210.17 |============================================================== c . 211.16 |============================================================== Timed Node.js Compilation 19.8.1 Time To Compile Seconds < Lower Is Better a . 132.53 |=================================================================== b . 115.74 |=========================================================== c . 114.59 |========================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow Frames Per Second > Higher Is Better a . 24.73 |==================================================================== b . 24.79 |==================================================================== c . 24.70 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Frames Per Second > Higher Is Better a . 27.17 |==================================================================== b . 27.33 |==================================================================== c . 27.26 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Slow Frames Per Second > Higher Is Better a . 60.62 |==================================================================== b . 60.72 |==================================================================== c . 60.15 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium Frames Per Second > Higher Is Better a . 67.11 |==================================================================== b . 67.02 |==================================================================== c . 67.15 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 46.42 |==================================================================== b . 44.67 |================================================================= c . 43.75 |================================================================ uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 45.43 |==================================================================== b . 45.07 |=================================================================== c . 44.29 |================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 47.56 |==================================================================== b . 46.27 |================================================================== c . 46.24 |================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 158.96 |=============================================================== b . 162.07 |================================================================ c . 170.10 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 166.10 |=================================================================== b . 165.32 |=================================================================== c . 165.97 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 172.09 |================================================================== b . 168.21 |================================================================= c . 173.89 |=================================================================== VVenC 1.8 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 5.509 |=================================================================== b . 5.570 |==================================================================== c . 5.577 |==================================================================== VVenC 1.8 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 8.875 |================================================================ b . 9.131 |================================================================== c . 9.358 |==================================================================== VVenC 1.8 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 14.66 |=================================================================== b . 14.74 |=================================================================== c . 14.88 |==================================================================== VVenC 1.8 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 23.52 |=================================================================== b . 24.05 |==================================================================== c . 23.08 |=================================================================