5950x sundat AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4402 BIOS) and llvmpipe on Ubuntu 22.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4402 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 500GB Western Digital WDS500G3X0C-00SJG0 + 2000GB, Graphics: llvmpipe, Audio: Intel Device 4f92, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.10, Kernel: 5.19.0-23-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4, OpenGL: 4.5 Mesa 22.2.1 (LLVM 15.0.2 256 bits), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4402 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 500GB Western Digital WDS500G3X0C-00SJG0 + 2000GB, Graphics: llvmpipe, Audio: Intel Device 4f92, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.10, Kernel: 5.19.0-23-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4, OpenGL: 4.5 Mesa 22.2.1 (LLVM 15.0.2 256 bits), Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 Zstd Compression 1.5.4 Compression Level: 3 - Compression Speed MB/s > Higher Is Better a . 2781.2 |================================================================== b . 2803.5 |=================================================================== Zstd Compression 1.5.4 Compression Level: 3 - Decompression Speed MB/s > Higher Is Better a . 1722.4 |================================================================= b . 1768.7 |=================================================================== Zstd Compression 1.5.4 Compression Level: 8 - Compression Speed MB/s > Higher Is Better a . 432.2 |==================================================================== b . 429.5 |==================================================================== Zstd Compression 1.5.4 Compression Level: 8 - Decompression Speed MB/s > Higher Is Better a . 1887.7 |=================================================================== b . 1853.1 |================================================================== Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed MB/s > Higher Is Better a . 128.0 |==================================================================== b . 127.7 |==================================================================== Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed MB/s > Higher Is Better a . 1882.7 |================================================================== b . 1916.8 |=================================================================== Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed MB/s > Higher Is Better a . 18.5 |==================================================================== b . 18.7 |===================================================================== Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed MB/s > Higher Is Better a . 1701.6 |=================================================================== b . 1672.0 |================================================================== Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Compression Speed MB/s > Higher Is Better a . 722.2 |=================================================================== b . 732.1 |==================================================================== Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1757.8 |================================================================== b . 1797.9 |=================================================================== Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Compression Speed MB/s > Higher Is Better a . 429.5 |=================================================================== b . 434.8 |==================================================================== Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1896.5 |================================================================== b . 1912.1 |=================================================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed MB/s > Higher Is Better a . 10 |======================================================================= b . 10 |======================================================================= Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1617.9 |================================================================== b . 1633.3 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 0.31 |===================================================================== b . 0.31 |===================================================================== AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 9.71 |==================================================================== b . 9.84 |===================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 58.91 |=================================================================== b . 59.54 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 16.98 |=================================================================== b . 17.27 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 55.92 |==================================================================== b . 51.37 |============================================================== AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 63.21 |=================================================================== b . 64.48 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 63.05 |================================================================== b . 65.40 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 0.91 |==================================================================== b . 0.92 |===================================================================== AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 20.32 |==================================================================== b . 20.46 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 115.45 |=================================================================== b . 110.58 |================================================================ AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 40.10 |=================================================================== b . 40.55 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 123.88 |=================================================================== b . 122.97 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 104.28 |=================================================================== b . 99.56 |================================================================ AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 119.21 |=================================================================== b . 116.63 |================================================================== Embree 4.0 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better a . 23.75 |==================================================================== b . 23.81 |==================================================================== Embree 4.0 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better a . 22.60 |==================================================================== b . 22.73 |==================================================================== Embree 4.0 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better a . 24.32 |================================================================== b . 24.88 |==================================================================== Embree 4.0 Binary: Pathtracer - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 21.89 |=================================================================== b . 22.10 |==================================================================== Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better a . 24.51 |==================================================================== b . 24.60 |==================================================================== Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 21.26 |=================================================================== b . 21.44 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Frames Per Second > Higher Is Better a . 15.16 |==================================================================== b . 15.17 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Frames Per Second > Higher Is Better a . 15.46 |=================================================================== b . 15.61 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Slow Frames Per Second > Higher Is Better a . 62.18 |==================================================================== b . 62.39 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Medium Frames Per Second > Higher Is Better a . 64.52 |==================================================================== b . 64.66 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 34.26 |==================================================================== b . 34.51 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 44.11 |==================================================================== b . 44.13 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 57.01 |==================================================================== b . 57.02 |==================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 135.84 |=================================================================== b . 136.82 |=================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 175.59 |=================================================================== b . 176.19 |=================================================================== Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 218.35 |=================================================================== b . 218.96 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow Frames Per Second > Higher Is Better a . 9.72 |===================================================================== b . 9.74 |===================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Frames Per Second > Higher Is Better a . 10.92 |==================================================================== b . 10.90 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Slow Frames Per Second > Higher Is Better a . 41.50 |==================================================================== b . 41.17 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium Frames Per Second > Higher Is Better a . 46.51 |==================================================================== b . 46.30 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 30.93 |==================================================================== b . 30.80 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 32.98 |==================================================================== b . 32.64 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 38.68 |==================================================================== b . 38.61 |==================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast Frames Per Second > Higher Is Better a . 123.09 |=================================================================== b . 123.24 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast Frames Per Second > Higher Is Better a . 131.42 |=================================================================== b . 131.34 |=================================================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Frames Per Second > Higher Is Better a . 151.22 |=================================================================== b . 150.45 |=================================================================== VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 8.62 |===================================================================== b . 8.55 |==================================================================== VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 20.56 |==================================================================== b . 20.67 |==================================================================== VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 17.25 |==================================================================== b . 17.07 |=================================================================== VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 36.07 |=================================================================== b . 36.61 |==================================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 4.477 |==================================================================== b . 4.501 |==================================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 9.462 |==================================================================== b . 9.489 |==================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 11.05 |=================================================================== b . 11.20 |==================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 25.96 |=================================================================== b . 26.31 |==================================================================== OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Items / Sec > Higher Is Better a . 227 |====================================================================== b . 228 |====================================================================== OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar Items / Sec > Higher Is Better a . 142 |====================================================================== b . 143 |====================================================================== Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better a . 69.97 |=================================================================== b . 71.40 |==================================================================== Timed Linux Kernel Compilation 6.1 Build: allmodconfig Seconds < Lower Is Better a . 812.17 |================================================================= b . 831.22 |=================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Queries Per Minute, Geo Mean > Higher Is Better a . 118.22 |================================================================= b . 122.32 |=================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Queries Per Minute, Geo Mean > Higher Is Better a . 130.72 |================================================================== b . 132.24 |=================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Queries Per Minute, Geo Mean > Higher Is Better a . 134.32 |================================================================== b . 136.05 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 3.20 |===================================================================== b . 3.17 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 86.52 |==================================================================== b . 86.45 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 5.07 |===================================================================== b . 5.04 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 3.48 |===================================================================== b . 3.43 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 1.98 |===================================================================== b . 1.95 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 1.649008243 |============================================================== b . 1.620000000 |============================================================= Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 1.40 |============================================================== b . 1.55 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 15.86 |==================================================================== b . 15.92 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 86.31 |==================================================================== b . 86.63 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 5.05 |===================================================================== b . 5.06 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 6.91 |===================================================================== b . 6.73 |=================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 10.05 |==================================================================== b . 10.06 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 11.98 |==================================================================== b . 11.27 |================================================================ Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 11.43 |==================================================================== b . 11.05 |================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 31.53 |==================================================================== b . 29.92 |================================================================= Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 86.47 |==================================================================== b . 86.27 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 5.09 |===================================================================== b . 5.05 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 10.34 |=================================================================== b . 10.46 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 19.79 |================================================================== b . 20.49 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 21.64 |================================================================== b . 22.33 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 22.02 |==================================================================== b . 22.00 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 58.63 |==================================================================== b . 58.76 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 87.08 |==================================================================== b . 86.18 |=================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 5.09 |===================================================================== b . 5.07 |===================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 30.31 |==================================================================== b . 30.19 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 40.28 |==================================================================== b . 39.59 |=================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 45.15 |==================================================================== b . 43.05 |================================================================= Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 44.50 |==================================================================== b . 44.09 |=================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 128 ops/s > Higher Is Better a . 729.5 |=================================================================== b . 737.4 |==================================================================== CockroachDB 22.2 Workload: MoVR - Concurrency: 1024 ops/s > Higher Is Better a . 737.4 |==================================================================== b . 737.4 |==================================================================== CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 128 ops/s > Higher Is Better a . 50930.0 |============================================================== b . 54375.8 |================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 128 ops/s > Higher Is Better a . 66349.7 |================================================================= b . 67666.0 |================================================================== CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 128 ops/s > Higher Is Better a . 71625.1 |================================================================ b . 73703.7 |================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 128 ops/s > Higher Is Better a . 95581.2 |================================================================== b . 93880.3 |================================================================= CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 41319.9 |================================================================== b . 41158.6 |================================================================== CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 49144.6 |================================================================== b . 48708.5 |================================================================= CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 51077.9 |=============================================================== b . 53184.2 |================================================================== CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 1024 ops/s > Higher Is Better a . 71285.1 |================================================================== b . 70079.9 |================================================================= GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better a . 1.270 |==================================================================== b . 1.278 |==================================================================== RocksDB 7.9.2 Test: Random Fill Op/s > Higher Is Better a . 1273257 |================================================================== b . 1278893 |================================================================== RocksDB 7.9.2 Test: Random Read Op/s > Higher Is Better a . 94785075 |================================================================= b . 94703211 |================================================================= RocksDB 7.9.2 Test: Update Random Op/s > Higher Is Better a . 733550 |=================================================================== b . 737184 |=================================================================== RocksDB 7.9.2 Test: Sequential Fill Op/s > Higher Is Better a . 1454965 |================================================================== b . 1441186 |================================================================= RocksDB 7.9.2 Test: Random Fill Sync Op/s > Higher Is Better a . 27798 |==================================================================== b . 27749 |==================================================================== RocksDB 7.9.2 Test: Read While Writing Op/s > Higher Is Better a . 3594042 |================================================================= b . 3623493 |================================================================== RocksDB 7.9.2 Test: Read Random Write Random Op/s > Higher Is Better a . 2510683 |================================================================== b . 2501578 |================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 107.98 |=================================================================== b . 107.78 |=================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 9.25704 |================================================================== b . 9.27425 |================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 119.88 |================================================================= b . 122.78 |=================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 8.33864 |================================================================== b . 8.14204 |================================================================ ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 8.37549 |================================================================== b . 8.32324 |================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 119.39 |=================================================================== b . 120.14 |=================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 7.72199 |================================================= b . 10.23540 |================================================================= ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 129.50 |=================================================================== b . 97.70 |=================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 13.43 |=================================================================== b . 13.63 |==================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 74.48 |==================================================================== b . 73.34 |=================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 16.98 |==================================================================== b . 17.08 |==================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 58.89 |==================================================================== b . 58.56 |==================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 691.24 |=================================================================== b . 671.58 |================================================================= ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 1.44574 |================================================================ b . 1.48798 |================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 712.70 |=========================================================== b . 803.47 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 1.40262 |================================================================== b . 1.24424 |=========================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 1.38126 |================================================================== b . 1.38396 |================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 723.97 |=================================================================== b . 722.56 |=================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 1.46417 |============================================= b . 2.13179 |================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 682.98 |=================================================================== b . 469.09 |============================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 27.86 |==================================================================== b . 27.70 |==================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 35.89 |==================================================================== b . 36.10 |==================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 26.61 |======================================================== b . 32.33 |==================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 37.57 |==================================================================== b . 30.93 |======================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 233.40 |================================================================== b . 236.54 |=================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 4.28386 |================================================================== b . 4.22687 |================================================================= ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 235.49 |================================================================== b . 240.42 |=================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 4.24607 |================================================================== b . 4.15881 |================================================================= ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 101.53 |=================================================================== b . 101.35 |=================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 9.84858 |================================================================== b . 9.86564 |================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 166.40 |=================================================================== b . 103.55 |========================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 6.00923 |========================================= b . 9.65702 |================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 36.04 |==================================================================== b . 36.19 |==================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 27.74 |==================================================================== b . 27.63 |==================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 41.35 |==================================================================== b . 41.10 |==================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 24.18 |==================================================================== b . 24.33 |==================================================================== BRL-CAD 7.34 VGR Performance Metric VGR Performance Metric > Higher Is Better a . 273690 |=================================================================== b . 274004 |===================================================================