oktoberfest Tests for a future article. Intel Core i5-12600K testing with a ASUS PRIME Z690-P WIFI D4 (0605 BIOS) and ASUS Intel ADL-S GT1 15GB on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: Intel Core i5-12600K @ 6.30GHz (10 Cores / 16 Threads), Motherboard: ASUS PRIME Z690-P WIFI D4 (0605 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 15GB (1450MHz), Audio: Realtek ALC897, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7af0 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc6daily20220716-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.2.204, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: Intel Core i5-12600K @ 6.30GHz (10 Cores / 16 Threads), Motherboard: ASUS PRIME Z690-P WIFI D4 (0605 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 15GB (1450MHz), Audio: Realtek ALC897, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7af0 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc6daily20220716-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.2.204, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160 Whisper.cpp 1.4 Model: ggml-medium.en - Input: 2016 State of the Union Seconds < Lower Is Better a . 2723.05 |================================================================== b . 2736.77 |================================================================== Blender 3.6 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better a . 1237.27 |================================================================== b . 1237.36 |================================================================== Timed GCC Compilation 13.2 Time To Compile Seconds < Lower Is Better a . 918.83 |=================================================================== b . 918.94 |=================================================================== BRL-CAD 7.36 VGR Performance Metric VGR Performance Metric > Higher Is Better a . 215292 |=================================================================== b . 215193 |=================================================================== Whisper.cpp 1.4 Model: ggml-small.en - Input: 2016 State of the Union Seconds < Lower Is Better a . 820.20 |=================================================================== b . 818.91 |=================================================================== OpenRadioss 2023.09.15 Model: INIVOL and Fluid Structure Interaction Drop Container Seconds < Lower Is Better a . 717.69 |=================================================================== b . 714.81 |=================================================================== OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU Scalar Items / Sec > Higher Is Better a . 130 |====================================================================== b . 130 |====================================================================== OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC Items / Sec > Higher Is Better a . 277 |====================================================================== b . 277 |====================================================================== nekRS 23.0 Input: Kershaw flops/rank > Higher Is Better a . 3261960000 |=============================================================== b . 3260840000 |=============================================================== QMCPACK 3.17.1 Input: Li2_STO_ae Total Execution Time - Seconds < Lower Is Better a . 445.38 |=================================================================== b . 445.23 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better a . 17.81 |=================================================================== b . 17.95 |==================================================================== Blender 3.6 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a . 385.70 |=================================================================== b . 385.91 |=================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 375733 |=================================================================== b . 375965 |=================================================================== nekRS 23.0 Input: TurboPipe Periodic flops/rank > Higher Is Better b . 4079830000 |=============================================================== OpenRadioss 2023.09.15 Model: Bird Strike on Windshield Seconds < Lower Is Better a . 347.26 |=================================================================== b . 342.50 |================================================================== QMCPACK 3.17.1 Input: FeCO6_b3lyp_gms Total Execution Time - Seconds < Lower Is Better a . 341.81 |=================================================================== b . 338.60 |================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 322602 |=================================================================== b . 322586 |=================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 316965 |=================================================================== b . 317047 |=================================================================== Blender 3.6 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a . 316.24 |=================================================================== b . 316.35 |=================================================================== QMCPACK 3.17.1 Input: O_ae_pyscf_UHF Total Execution Time - Seconds < Lower Is Better a . 314.45 |=================================================================== b . 313.84 |=================================================================== Timed LLVM Compilation 16.0 Build System: Ninja Seconds < Lower Is Better DuckDB 0.9.1 Benchmark: IMDB Seconds < Lower Is Better a . 115.41 |=================================================================== OpenRadioss 2023.09.15 Model: Rubber O-Ring Seal Installation Seconds < Lower Is Better a . 283.82 |=================================================================== b . 283.06 |=================================================================== Timed LLVM Compilation 16.0 Build System: Unix Makefiles Seconds < Lower Is Better Timed Godot Game Engine Compilation 4.0 Time To Compile Seconds < Lower Is Better a . 323.86 |=================================================================== Whisper.cpp 1.4 Model: ggml-base.en - Input: 2016 State of the Union Seconds < Lower Is Better a . 244.73 |================================================================== b . 246.69 |=================================================================== DuckDB 0.9.1 Benchmark: TPC-H Parquet Seconds < Lower Is Better a . 97.82 |==================================================================== OpenRadioss 2023.09.15 Model: Bumper Beam Seconds < Lower Is Better a . 222.32 |================================================================ b . 233.21 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better a . 17.49 |==================================================================== b . 17.50 |==================================================================== QMCPACK 3.17.1 Input: LiH_ae_MSD Total Execution Time - Seconds < Lower Is Better a . 201.74 |=================================================================== b . 202.34 |=================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 189279 |=================================================================== b . 189045 |=================================================================== easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 Seconds < Lower Is Better a . 185.88 |=================================================================== b . 186.00 |=================================================================== Timed Node.js Compilation 19.8.1 Time To Compile Seconds < Lower Is Better OSPRay 2.12 Benchmark: particle_volume/scivis/real_time Items Per Second > Higher Is Better a . 5.68706 |================================================================== b . 5.70261 |================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 162070 |=================================================================== b . 162754 |=================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 159663 |=================================================================== b . 159770 |=================================================================== High Performance Conjugate Gradient 3.1 X Y Z: 104 104 104 - RT: 60 GFLOP/s > Higher Is Better a . 6.95045 |================================================================== b . 6.96238 |================================================================== OpenRadioss 2023.09.15 Model: Cell Phone Drop Test Seconds < Lower Is Better a . 157.04 |=================================================================== b . 152.73 |================================================================= Blender 3.6 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a . 156.02 |=================================================================== b . 156.07 |=================================================================== OSPRay 2.12 Benchmark: particle_volume/pathtracer/real_time Items Per Second > Higher Is Better a . 140.44 |=================================================================== b . 140.59 |=================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 511.33 |=================================================================== b . 511.12 |=================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 9.656 |==================================================================== b . 9.679 |==================================================================== Build2 0.15 Time To Compile Seconds < Lower Is Better a . 137.60 |=================================================================== Apache Cassandra 4.1.3 Test: Writes Op/s > Higher Is Better a . 123080 |=================================================================== b . 122667 |=================================================================== libavif avifenc 1.0 Encoder Speed: 0 Seconds < Lower Is Better a . 127.47 |=================================================================== b . 126.77 |=================================================================== libxsmm 2-1.17-3645 M N K: 128 GFLOPS/s > Higher Is Better a . 247.5 |==================================================================== b . 248.0 |==================================================================== VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 4.931 |==================================================================== b . 4.912 |==================================================================== OSPRay 2.12 Benchmark: particle_volume/ao/real_time Items Per Second > Higher Is Better a . 5.74695 |================================================================== b . 5.76091 |================================================================== Palabos 2.3 Grid Size: 100 Mega Site Updates Per Second > Higher Is Better a . 51.24 |==================================================================== b . 51.31 |==================================================================== Blender 3.6 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 112.43 |=================================================================== b . 112.12 |=================================================================== AOM AV1 3.7 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 6.77 |===================================================================== b . 6.77 |===================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better a . 17.01 |==================================================================== b . 17.09 |==================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 96823 |==================================================================== b . 96957 |==================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 19.68 |================================================================== b . 20.24 |==================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 50.78 |==================================================================== b . 49.40 |================================================================== oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 5530.13 |================================================================== b . 4270.30 |=================================================== nginx 1.23.2 Connections: 1000 Requests Per Second > Higher Is Better a . 82318.98 |================================================================= b . 82032.62 |================================================================= nginx 1.23.2 Connections: 500 Requests Per Second > Higher Is Better a . 89266.33 |================================================================= b . 88913.24 |================================================================= Apache HTTP Server 2.4.56 Concurrent Requests: 1000 Requests Per Second > Higher Is Better a . 120445.38 |================================================================ b . 119665.35 |================================================================ Apache HTTP Server 2.4.56 Concurrent Requests: 500 Requests Per Second > Higher Is Better a . 119690.62 |=============================================================== b . 121041.48 |================================================================ nginx 1.23.2 Connections: 200 Requests Per Second > Higher Is Better a . 102547.95 |================================================================ b . 102479.68 |================================================================ Apache HTTP Server 2.4.56 Concurrent Requests: 200 Requests Per Second > Higher Is Better a . 140860.12 |================================================================ b . 140213.08 |================================================================ nginx 1.23.2 Connections: 100 Requests Per Second > Higher Is Better a . 108258.46 |================================================================ b . 107751.55 |================================================================ Apache HTTP Server 2.4.56 Concurrent Requests: 100 Requests Per Second > Higher Is Better a . 148966.44 |================================================================ b . 145590.45 |=============================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 83367 |==================================================================== b . 83406 |==================================================================== Intel Open Image Denoise 2.1 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better a . 0.34 |===================================================================== b . 0.34 |===================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 9910 |===================================================================== b . 9901 |===================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 82003 |==================================================================== b . 82116 |==================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 9734 |===================================================================== b . 9716 |===================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 43.64 |==================================================================== b . 43.66 |==================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 114.52 |=================================================================== b . 114.29 |=================================================================== AOM AV1 3.7 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 0.24 |===================================================================== b . 0.24 |===================================================================== Palabos 2.3 Grid Size: 400 Mega Site Updates Per Second > Higher Is Better a . 76.76 |==================================================================== b . 76.59 |==================================================================== oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2636.78 |================================================================== b . 2167.50 |====================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 122.77 |=================================================================== b . 122.72 |=================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 8.1450 |=================================================================== b . 8.1485 |=================================================================== OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Items Per Second > Higher Is Better a . 3.88095 |================================================================== b . 3.86334 |================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 2912 |===================================================================== b . 2916 |===================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 2456 |===================================================================== b . 2457 |===================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 2499 |===================================================================== b . 2496 |===================================================================== NCNN 20230517 Target: CPU - Model: FastestDet ms < Lower Is Better a . 3.00 |=================================================================== b . 3.09 |===================================================================== NCNN 20230517 Target: CPU - Model: vision_transformer ms < Lower Is Better a . 100.28 |=================================================================== b . 95.33 |================================================================ NCNN 20230517 Target: CPU - Model: regnety_400m ms < Lower Is Better a . 5.98 |==================================================================== b . 6.05 |===================================================================== NCNN 20230517 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better a . 6.86 |==================================================================== b . 6.99 |===================================================================== NCNN 20230517 Target: CPU - Model: yolov4-tiny ms < Lower Is Better a . 16.64 |================================================================ b . 17.59 |==================================================================== NCNN 20230517 Target: CPU - Model: resnet50 ms < Lower Is Better a . 12.77 |================================================================== b . 13.15 |==================================================================== NCNN 20230517 Target: CPU - Model: alexnet ms < Lower Is Better a . 4.96 |=================================================================== b . 5.14 |===================================================================== NCNN 20230517 Target: CPU - Model: resnet18 ms < Lower Is Better a . 5.52 |===================================================================== b . 5.50 |===================================================================== NCNN 20230517 Target: CPU - Model: vgg16 ms < Lower Is Better a . 37.31 |==================================================================== b . 36.62 |=================================================================== NCNN 20230517 Target: CPU - Model: googlenet ms < Lower Is Better a . 7.77 |===================================================================== b . 7.73 |===================================================================== NCNN 20230517 Target: CPU - Model: blazeface ms < Lower Is Better a . 0.75 |==================================================================== b . 0.76 |===================================================================== NCNN 20230517 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better a . 4.87 |==================================================================== b . 4.91 |===================================================================== NCNN 20230517 Target: CPU - Model: mnasnet ms < Lower Is Better a . 2.54 |=================================================================== b . 2.60 |===================================================================== NCNN 20230517 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better a . 2.24 |==================================================================== b . 2.27 |===================================================================== NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better a . 2.38 |==================================================================== b . 2.41 |===================================================================== NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better a . 2.98 |============================================================== b . 3.34 |===================================================================== NCNN 20230517 Target: CPU - Model: mobilenet ms < Lower Is Better a . 10.24 |================================================================== b . 10.54 |==================================================================== libxsmm 2-1.17-3645 M N K: 64 GFLOPS/s > Higher Is Better a . 167.9 |==================================================================== b . 167.0 |==================================================================== Memcached 1.6.19 Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 3016454.90 |============================================================== b . 3059379.28 |=============================================================== Memcached 1.6.19 Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 3279849.87 |=============================================================== b . 3183290.59 |============================================================= Embree 4.3 Binary: Pathtracer - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 13.51 |==================================================================== b . 13.48 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 11.40 |==================================================================== b . 11.21 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 87.65 |=================================================================== b . 89.12 |==================================================================== Z3 Theorem Prover 4.12.1 SMT File: 2.smt2 Seconds < Lower Is Better a . 62.94 |==================================================================== b . 63.06 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 22.41 |==================================================================== b . 22.35 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 222.92 |=================================================================== b . 223.39 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 144.12 |=================================================================== b . 144.37 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 34.61 |==================================================================== b . 34.56 |==================================================================== libavif avifenc 1.0 Encoder Speed: 2 Seconds < Lower Is Better a . 60.82 |==================================================================== b . 59.36 |================================================================== libxsmm 2-1.17-3645 M N K: 32 GFLOPS/s > Higher Is Better a . 96.3 |===================================================================== b . 96.4 |===================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 586.67 |=================================================================== b . 589.15 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 8.4527 |=================================================================== b . 8.4551 |=================================================================== Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 14.51 |==================================================================== b . 14.57 |==================================================================== Embree 4.3 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better a . 12.71 |==================================================================== b . 12.62 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 588.30 |================================================================== b . 593.64 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 8.4541 |=================================================================== b . 8.3633 |================================================================== VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 10.18 |==================================================================== b . 10.23 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 472.68 |================================================================== b . 479.61 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 10.44 |==================================================================== b . 10.32 |=================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 49884 |==================================================================== b . 49910 |==================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 11549 |==================================================================== b . 11536 |==================================================================== Embree 4.3 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better a . 13.49 |==================================================================== b . 13.54 |==================================================================== AOM AV1 3.7 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 14.25 |==================================================================== b . 14.26 |==================================================================== Embree 4.3 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better a . 14.97 |==================================================================== b . 14.91 |==================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 43199 |==================================================================== b . 43132 |==================================================================== OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Items Per Second > Higher Is Better a . 2.63693 |================================================================== b . 2.63451 |================================================================== OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Items Per Second > Higher Is Better a . 2.55887 |================================================================== b . 2.54893 |================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 42656 |==================================================================== b . 42536 |==================================================================== SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 3.475 |==================================================================== b . 3.455 |==================================================================== Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better a . 16.66 |==================================================================== b . 16.69 |==================================================================== QMCPACK 3.17.1 Input: simple-H2O Total Execution Time - Seconds < Lower Is Better a . 43.89 |=================================================================== b . 44.36 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 35.37 |==================================================================== b . 35.56 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 28.27 |==================================================================== b . 28.12 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 102.64 |================================================================== b . 103.75 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 9.7413 |=================================================================== b . 9.6372 |================================================================== AOM AV1 3.7 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 15.99 |==================================================================== b . 15.99 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 128.97 |=================================================================== b . 129.12 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 7.7535 |=================================================================== b . 7.7442 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 128.96 |=================================================================== b . 129.56 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 7.7540 |=================================================================== b . 7.7181 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 164.22 |=================================================================== b . 163.32 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 30.44 |==================================================================== b . 30.60 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 71.64 |=================================================================== b . 72.24 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 69.72 |==================================================================== b . 69.09 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 49.72 |=================================================================== b . 50.17 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 100.41 |=================================================================== b . 99.57 |================================================================== QMCPACK 3.17.1 Input: H4_ae Total Execution Time - Seconds < Lower Is Better a . 39.88 |=================================================================== b . 40.51 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 47.18 |==================================================================== b . 47.20 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 21.19 |==================================================================== b . 21.18 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 17.80 |==================================================================== b . 17.71 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 56.17 |==================================================================== b . 56.44 |==================================================================== VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 15.11 |=================================================================== b . 15.24 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 18.04 |=================================================================== b . 18.20 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 55.42 |==================================================================== b . 54.94 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 98.08 |==================================================================== b . 98.29 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 50.97 |==================================================================== b . 50.86 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 95.48 |==================================================================== b . 95.20 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 52.32 |==================================================================== b . 52.50 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 22.06 |==================================================================== b . 22.09 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 45.31 |==================================================================== b . 45.25 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 21.99 |================================================================== b . 22.70 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 45.48 |==================================================================== b . 44.05 |================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 46.19 |==================================================================== b . 46.21 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 108.12 |=================================================================== b . 108.07 |=================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 45.79 |==================================================================== b . 45.81 |==================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 109.14 |=================================================================== b . 109.06 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 12.66 |==================================================================== b . 12.65 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 78.99 |==================================================================== b . 79.04 |==================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 12.63 |==================================================================== b . 12.59 |==================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 79.15 |==================================================================== b . 79.37 |==================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 7.0052 |=================================================================== b . 6.9947 |=================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 712.36 |=================================================================== b . 713.32 |=================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 2.8555 |=================================================================== b . 2.8079 |================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 349.62 |================================================================== b . 355.47 |=================================================================== QuantLib 1.32 Configuration: Multi-Threaded MFLOPS > Higher Is Better a . 40312.3 |================================================================== b . 39967.5 |================================================================= Stress-NG 0.16.04 Test: Cloning Bogo Ops/s > Higher Is Better a . 860.48 |=================================================================== b . 865.39 |=================================================================== Stress-NG 0.16.04 Test: Zlib Bogo Ops/s > Higher Is Better a . 1130.39 |================================================================== b . 1129.89 |================================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 80680000 |================================================================= b . 81117000 |================================================================= Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 57879000 |================================================================= b . 57881000 |================================================================= Stress-NG 0.16.04 Test: Vector Floating Point Bogo Ops/s > Higher Is Better a . 19538.35 |================================================================= b . 19468.51 |================================================================= Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 185450000 |============================================================ b . 196230000 |================================================================ Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 41548000 |================================================================= b . 41499000 |================================================================= Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 20784000 |================================================================= b . 20781000 |================================================================= Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 305790000 |================================================================ b . 303380000 |=============================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 221860000 |================================================================ b . 221680000 |================================================================ Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 159380000 |================================================================ b . 160510000 |================================================================ Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 115700000 |================================================================ b . 115690000 |================================================================ Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 78801000 |================================================================ b . 80378000 |================================================================= Stress-NG 0.16.04 Test: Hash Bogo Ops/s > Higher Is Better a . 2294409.16 |=============================================================== b . 2304545.32 |=============================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 130420000 |================================================================ b . 131280000 |================================================================ Stress-NG 0.16.04 Test: Pthread Bogo Ops/s > Higher Is Better a . 186367.10 |================================================================ b . 186386.61 |================================================================ Stress-NG 0.16.04 Test: Matrix 3D Math Bogo Ops/s > Higher Is Better a . 1401.51 |================================================================= b . 1418.21 |================================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 402980000 |================================================================ b . 400370000 |================================================================ Stress-NG 0.16.04 Test: Floating Point Bogo Ops/s > Higher Is Better a . 4377.45 |================================================================= b . 4412.33 |================================================================== Stress-NG 0.16.04 Test: AVL Tree Bogo Ops/s > Higher Is Better a . 81.66 |==================================================================== b . 82.10 |==================================================================== Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 695800000 |================================================================ b . 676010000 |============================================================== Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 757790000 |================================================================ b . 750070000 |=============================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 518790000 |================================================================ b . 515540000 |================================================================ Stress-NG 0.16.04 Test: Vector Shuffle Bogo Ops/s > Higher Is Better a . 9447.65 |================================================================== b . 9457.69 |================================================================== Stress-NG 0.16.04 Test: Fused Multiply-Add Bogo Ops/s > Higher Is Better a . 16384409.66 |============================================================== b . 16391410.53 |============================================================== Stress-NG 0.16.04 Test: Wide Vector Math Bogo Ops/s > Higher Is Better a . 484455.75 |================================================================ b . 484394.85 |================================================================ Stress-NG 0.16.04 Test: Mixed Scheduler Bogo Ops/s > Higher Is Better a . 10186.26 |================================================================ b . 10290.81 |================================================================= Stress-NG 0.16.04 Test: AVX-512 VNNI Bogo Ops/s > Higher Is Better a . 1228899.23 |=============================================================== b . 1229104.91 |=============================================================== Stress-NG 0.16.04 Test: Poll Bogo Ops/s > Higher Is Better a . 1241130.30 |=============================================================== b . 1217218.91 |============================================================== Stress-NG 0.16.04 Test: Pipe Bogo Ops/s > Higher Is Better a . 7171062.72 |=============================================================== b . 7160556.83 |=============================================================== AOM AV1 3.7 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 0.73 |===================================================================== b . 0.73 |===================================================================== eSpeak-NG Speech Engine 1.51 Text-To-Speech Synthesis Seconds < Lower Is Better a . 21.22 |==================================================================== b . 21.29 |==================================================================== oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 9.24791 |================================================================== b . 9.23030 |================================================================== Opus Codec Encoding 1.4 WAV To Opus Encode Seconds < Lower Is Better a . 20.51 |==================================================================== b . 20.54 |==================================================================== Z3 Theorem Prover 4.12.1 SMT File: 1.smt2 Seconds < Lower Is Better a . 19.13 |==================================================================== b . 19.12 |==================================================================== SQLite 3.41.2 Threads / Copies: 4 Seconds < Lower Is Better a . 19.01 |==================================================================== b . 19.00 |==================================================================== VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 33.29 |==================================================================== b . 33.09 |==================================================================== QuantLib 1.32 Configuration: Single-Threaded MFLOPS > Higher Is Better a . 4562.6 |=================================================================== b . 4573.9 |=================================================================== AOM AV1 3.7 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 46.78 |==================================================================== b . 46.68 |==================================================================== dav1d 1.2.1 Video Input: Chimera 1080p 10-bit FPS > Higher Is Better a . 556.38 |=================================================================== b . 555.73 |=================================================================== dav1d 1.2.1 Video Input: Summer Nature 4K FPS > Higher Is Better a . 238.78 |=================================================================== b . 239.22 |=================================================================== oneDNN 3.3 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3.89503 |================================================================== b . 3.89409 |================================================================== SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 11.20 |==================================================================== b . 11.22 |==================================================================== SQLite 3.41.2 Threads / Copies: 2 Seconds < Lower Is Better a . 14.49 |==================================================================== b . 14.46 |==================================================================== SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 44.98 |==================================================================== b . 44.94 |==================================================================== dav1d 1.2.1 Video Input: Chimera 1080p FPS > Higher Is Better a . 683.61 |=================================================================== b . 675.83 |================================================================== easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240 Seconds < Lower Is Better a . 9.046 |==================================================================== b . 9.060 |==================================================================== AOM AV1 3.7 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 63.82 |============================================================= b . 71.58 |==================================================================== AOM AV1 3.7 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 68.67 |==================================================================== b . 68.16 |=================================================================== oneDNN 3.3 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 10.80 |==================================================================== b . 10.69 |=================================================================== libavif avifenc 1.0 Encoder Speed: 6, Lossless Seconds < Lower Is Better a . 9.164 |==================================================================== b . 9.139 |==================================================================== AOM AV1 3.7 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 73.19 |==================================================================== b . 70.73 |================================================================== SQLite 3.41.2 Threads / Copies: 1 Seconds < Lower Is Better a . 8.943 |==================================================================== b . 8.908 |==================================================================== AOM AV1 3.7 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 69.71 |=========================================================== b . 79.90 |==================================================================== AOM AV1 3.7 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 75.67 |=============================================================== b . 81.38 |==================================================================== SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 92.68 |==================================================================== b . 93.34 |==================================================================== libavif avifenc 1.0 Encoder Speed: 6 Seconds < Lower Is Better a . 6.332 |==================================================================== b . 6.274 |=================================================================== oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 14.35 |==================================================================== b . 14.34 |==================================================================== SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 109.88 |=================================================================== b . 109.21 |=================================================================== SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 111.13 |=================================================================== b . 111.54 |=================================================================== libavif avifenc 1.0 Encoder Speed: 10, Lossless Seconds < Lower Is Better a . 4.552 |=================================================================== b . 4.634 |==================================================================== AOM AV1 3.7 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 146.21 |=========================================================== b . 166.68 |=================================================================== dav1d 1.2.1 Video Input: Summer Nature 1080p FPS > Higher Is Better a . 956.18 |=================================================================== b . 962.35 |=================================================================== AOM AV1 3.7 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 183.46 |=================================================================== b . 162.27 |=========================================================== AOM AV1 3.7 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 178.89 |================================================================ b . 188.01 |=================================================================== High Performance Conjugate Gradient 3.1 X Y Z: 144 144 144 - RT: 60 GFLOP/s > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 199.96 |=================================================================== b . 184.04 |============================================================== AOM AV1 3.7 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 193.68 |=================================================================== b . 190.21 |================================================================== oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 8.04899 |================================================================== b . 8.04648 |================================================================== SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 437.37 |=================================================================== b . 427.53 |================================================================= SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 516.20 |=================================================================== b . 499.07 |=================================================================