xeon eo march

2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 22.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2304015-NE-XEONEOMAR92
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

AV1 3 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 12 Tests
CPU Massive 14 Tests
Creator Workloads 11 Tests
Cryptography 2 Tests
Database Test Suite 3 Tests
Encoding 6 Tests
Game Development 3 Tests
HPC - High Performance Computing 6 Tests
Common Kernel Benchmarks 4 Tests
Machine Learning 4 Tests
Multi-Core 18 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 6 Tests
Server 6 Tests
Server CPU Tests 10 Tests
Video Encoding 6 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 31 2023
  8 Hours, 52 Minutes
b
March 31 2023
  7 Hours, 24 Minutes
c
April 01 2023
  6 Hours, 16 Minutes
Invert Hiding All Results Option
  7 Hours, 31 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

xeon eo march 2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 22.10 via the Phoronix Test Suite. a: Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Ice Lake IEH, Memory: 512GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP OS: Ubuntu 22.10, Kernel: 6.2.0-rc5-phx-dodt (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.3, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Ice Lake IEH, Memory: 512GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP OS: Ubuntu 22.10, Kernel: 6.2.0-rc5-phx-dodt (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.3, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Ice Lake IEH, Memory: 512GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP OS: Ubuntu 22.10, Kernel: 6.2.0-rc5-phx-dodt (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.3, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1080 John The Ripper 2023.03.14 Test: HMAC-SHA512 Real C/S > Higher Is Better a . 151993000 |================================================================ b . 152981000 |================================================================ c . 19292000 |======== Stress-NG 0.15.06 Test: System V Message Passing Bogo Ops/s > Higher Is Better a . 10295375.81 |========= b . 10283641.13 |========= c . 73426960.15 |============================================================== John The Ripper 2023.03.14 Test: MD5 Real C/S > Higher Is Better a . 10384000 |================================================================= b . 10295000 |================================================================ c . 2766000 |================= Stress-NG 0.15.06 Test: Atomic Bogo Ops/s > Higher Is Better a . 139.80 |=========================== b . 163.26 |=============================== c . 349.89 |=================================================================== John The Ripper 2023.03.14 Test: Blowfish Real C/S > Higher Is Better a . 114499 |=================================================================== b . 107388 |=============================================================== c . 51517 |============================== John The Ripper 2023.03.14 Test: WPA PSK Real C/S > Higher Is Better a . 483328 |=================================================================== b . 482323 |=================================================================== c . 255829 |=================================== Stress-NG 0.15.06 Test: Socket Activity Bogo Ops/s > Higher Is Better a . 94302.89 |================================================================= b . 79477.34 |======================================================= c . 50201.57 |=================================== John The Ripper 2023.03.14 Test: bcrypt Real C/S > Higher Is Better a . 114777 |=================================================================== b . 114825 |=================================================================== c . 64015 |===================================== Zstd Compression 1.5.4 Compression Level: 8 - Decompression Speed MB/s > Higher Is Better a . 1128.8 |================================================================== b . 1140.4 |=================================================================== c . 831.7 |================================================= OpenCV 4.7 Test: Features 2D ms < Lower Is Better a . 270872 |=================================================== b . 356993 |=================================================================== Stress-NG 0.15.06 Test: MEMFD Bogo Ops/s > Higher Is Better a . 766.90 |=================================================================== b . 583.83 |=================================================== c . 583.20 |=================================================== Memcached 1.6.19 Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 1970590.49 |=============================================================== b . 1946110.38 |============================================================== c . 1527158.77 |================================================= Memcached 1.6.19 Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 2137824.96 |============================================================= b . 1736416.84 |================================================= c . 2222180.60 |=============================================================== OpenCV 4.7 Test: Image Processing ms < Lower Is Better a . 356989 |=================================================================== b . 293481 |======================================================= Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Compression Speed MB/s > Higher Is Better a . 258.0 |======================================================== b . 313.7 |==================================================================== c . 267.4 |========================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 26.54 |======================================================== b . 32.05 |==================================================================== Memcached 1.6.19 Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 1774418.86 |==================================================== b . 2133650.03 |=============================================================== c . 1820534.68 |====================================================== Stress-NG 0.15.06 Test: CPU Cache Bogo Ops/s > Higher Is Better a . 1441584.05 |====================================================== b . 1691720.80 |=============================================================== c . 1657780.82 |============================================================== Stress-NG 0.15.06 Test: Zlib Bogo Ops/s > Higher Is Better a . 6374.22 |================================================================= b . 5549.21 |======================================================== c . 6511.98 |================================================================== Darmstadt Automotive Parallel Heterogeneous Suite 2021.11.02 Backend: OpenMP - Kernel: NDT Mapping Test Cases Per Minute > Higher Is Better a . 817.52 |============================================================= b . 771.26 |========================================================== c . 892.13 |=================================================================== OpenCV 4.7 Test: Object Detection ms < Lower Is Better a . 119494 |=================================================================== b . 103986 |========================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 3.67056 |========================================================== b . 4.16467 |================================================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed MB/s > Higher Is Better a . 7.88 |===================================================================== b . 7.25 |=============================================================== c . 6.95 |============================================================= Darmstadt Automotive Parallel Heterogeneous Suite 2021.11.02 Backend: OpenMP - Kernel: Points2Image Test Cases Per Minute > Higher Is Better a . 9474.39 |=============================================================== b . 9912.90 |================================================================== c . 8791.23 |=========================================================== OpenCV 4.7 Test: Graph API ms < Lower Is Better a . 671086 |=================================================================== b . 597049 |============================================================ Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed MB/s > Higher Is Better a . 161.4 |============================================================= b . 180.6 |==================================================================== c . 169.9 |================================================================ Stress-NG 0.15.06 Test: Futex Bogo Ops/s > Higher Is Better a . 957096.20 |========================================================= b . 1018129.24 |============================================================= c . 1056011.64 |=============================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 36.20 |================================================================== b . 33.68 |============================================================== c . 37.05 |==================================================================== OpenCV 4.7 Test: Video ms < Lower Is Better a . 121173 |============================================================= b . 133100 |=================================================================== Apache HTTP Server 2.4.56 Concurrent Requests: 200 Requests Per Second > Higher Is Better a . 34680.57 |=========================================================== b . 38092.88 |================================================================= Zstd Compression 1.5.4 Compression Level: 3 - Compression Speed MB/s > Higher Is Better a . 2013.1 |============================================================= b . 2185.0 |================================================================== c . 2209.8 |=================================================================== RocksDB 8.0 Test: Read While Writing Op/s > Higher Is Better a . 8059987 |================================================================= b . 7531197 |============================================================= c . 8192793 |================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.201235 |============================================================ b . 0.218330 |================================================================= oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 705.68 |=================================================================== b . 656.80 |============================================================== OpenCV 4.7 Test: DNN - Deep Neural Network ms < Lower Is Better a . 115385 |=================================================================== b . 107827 |=============================================================== Darmstadt Automotive Parallel Heterogeneous Suite 2021.11.02 Backend: OpenMP - Kernel: Euclidean Cluster Test Cases Per Minute > Higher Is Better a . 842.32 |================================================================== b . 796.63 |=============================================================== c . 848.69 |=================================================================== OpenCV 4.7 Test: Core ms < Lower Is Better a . 88425 |==================================================================== b . 83121 |================================================================ ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 3.11560 |================================================================== b . 2.93086 |============================================================== c . 2.93257 |============================================================== Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Compression Speed MB/s > Higher Is Better a . 295.0 |==================================================================== b . 278.4 |================================================================ c . 285.6 |================================================================== Zstd Compression 1.5.4 Compression Level: 8 - Compression Speed MB/s > Higher Is Better a . 624.0 |================================================================== b . 603.0 |================================================================ c . 638.2 |==================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 711.38 |=============================================================== b . 752.43 |=================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 0.875338 |============================================================= b . 0.925478 |================================================================= AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 31.70 |==================================================================== b . 31.10 |=================================================================== c . 30.01 |================================================================ TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: AlexNet images/sec > Higher Is Better a . 138.07 |=============================================================== b . 145.79 |=================================================================== c . 145.45 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 16.15 |=================================================================== b . 15.53 |================================================================= c . 16.33 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 8.16 |=================================================================== b . 8.40 |===================================================================== c . 7.99 |================================================================== OpenSSL 3.1 Algorithm: SHA256 byte/s > Higher Is Better a . 57611766850 |============================================================== b . 54810975320 |=========================================================== c . 57348072400 |============================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 61.79 |==================================================================== b . 58.83 |================================================================= ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 11.36 |================================================================= b . 11.90 |==================================================================== c . 11.69 |=================================================================== Stress-NG 0.15.06 Test: Function Call Bogo Ops/s > Higher Is Better a . 429335.83 |================================================================ b . 413303.53 |============================================================= c . 431183.83 |================================================================ RocksDB 8.0 Test: Read Random Write Random Op/s > Higher Is Better a . 920426 |================================================================ b . 959340 |=================================================================== c . 954852 |=================================================================== SPECFEM3D 4.0 Model: Tomographic Model Seconds < Lower Is Better a . 15.30 |==================================================================== b . 14.71 |================================================================= c . 14.96 |================================================================== AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 15.82 |================================================================= b . 16.43 |==================================================================== c . 16.33 |==================================================================== OpenCV 4.7 Test: Stitching ms < Lower Is Better a . 508105 |=================================================================== b . 489265 |================================================================= oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 453.91 |=================================================================== b . 437.40 |================================================================= Stress-NG 0.15.06 Test: Glibc C String Functions Bogo Ops/s > Higher Is Better a . 60467587.40 |============================================================== b . 59352709.91 |============================================================= c . 58278938.78 |============================================================ TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: AlexNet images/sec > Higher Is Better a . 236.08 |=================================================================== b . 228.16 |================================================================= c . 227.64 |================================================================= AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 16.04 |================================================================== b . 16.56 |==================================================================== c . 16.63 |==================================================================== SPECFEM3D 4.0 Model: Water-layered Halfspace Seconds < Lower Is Better a . 31.47 |==================================================================== b . 30.37 |================================================================== c . 30.96 |=================================================================== VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 5.20 |===================================================================== b . 5.04 |=================================================================== c . 5.02 |=================================================================== Stress-NG 0.15.06 Test: CPU Stress Bogo Ops/s > Higher Is Better a . 152655.29 |============================================================== b . 152455.93 |============================================================== c . 157803.19 |================================================================ Stress-NG 0.15.06 Test: Semaphores Bogo Ops/s > Higher Is Better a . 11840389.35 |============================================================ b . 12234144.91 |============================================================== c . 12232435.50 |============================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 15.97 |==================================================================== b . 15.58 |================================================================== c . 16.07 |==================================================================== Stress-NG 0.15.06 Test: Pthread Bogo Ops/s > Higher Is Better a . 87858.71 |=============================================================== b . 87532.40 |=============================================================== c . 90272.05 |================================================================= AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 30.04 |================================================================== b . 30.21 |================================================================== c . 30.98 |==================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 13.25 |=================================================================== b . 13.03 |================================================================== c . 13.43 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 28.78 |==================================================================== b . 27.93 |================================================================== c . 28.61 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 0.33 |=================================================================== b . 0.34 |===================================================================== c . 0.34 |===================================================================== Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1161.6 |=================================================================== b . 1163.4 |=================================================================== c . 1129.3 |================================================================= FFmpeg 6.0 Encoder: libx264 - Scenario: Video On Demand FPS > Higher Is Better a . 36.21 |==================================================================== b . 35.16 |================================================================== c . 35.33 |================================================================== FFmpeg 6.0 Encoder: libx264 - Scenario: Video On Demand Seconds < Lower Is Better a . 209.22 |================================================================= b . 215.44 |=================================================================== c . 214.38 |=================================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2.10120 |================================================================ b . 2.16346 |================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 13.35 |==================================================================== b . 13.10 |=================================================================== c . 12.98 |================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 624.46 |=================================================================== b . 607.24 |================================================================= c . 624.35 |=================================================================== SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 116.89 |================================================================= b . 119.69 |=================================================================== c . 120.06 |=================================================================== Build2 0.15 Time To Compile Seconds < Lower Is Better a . 93.00 |=================================================================== b . 94.97 |==================================================================== c . 92.48 |================================================================== Stress-NG 0.15.06 Test: Crypto Bogo Ops/s > Higher Is Better a . 105894.93 |============================================================== b . 108459.26 |================================================================ c . 107612.44 |================================================================ Timed Node.js Compilation 19.8.1 Time To Compile Seconds < Lower Is Better a . 203.68 |================================================================== b . 202.83 |================================================================= c . 207.61 |=================================================================== FFmpeg 6.0 Encoder: libx265 - Scenario: Live FPS > Higher Is Better a . 33.78 |================================================================== b . 34.57 |==================================================================== c . 34.24 |=================================================================== FFmpeg 6.0 Encoder: libx265 - Scenario: Live Seconds < Lower Is Better a . 149.48 |=================================================================== b . 146.07 |================================================================= c . 147.51 |================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 32.68 |==================================================================== b . 32.68 |==================================================================== c . 31.93 |================================================================== SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 37.74 |=================================================================== b . 38.18 |==================================================================== c . 37.33 |================================================================== FFmpeg 6.0 Encoder: libx264 - Scenario: Live FPS > Higher Is Better a . 133.05 |=================================================================== b . 130.09 |================================================================== c . 130.88 |================================================================== FFmpeg 6.0 Encoder: libx264 - Scenario: Live Seconds < Lower Is Better a . 37.96 |================================================================== b . 38.82 |==================================================================== c . 38.58 |==================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 16.13 |=================================================================== b . 16.31 |==================================================================== c . 15.96 |=================================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 3.261 |==================================================================== b . 3.221 |=================================================================== c . 3.191 |=================================================================== Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed MB/s > Higher Is Better a . 1095.6 |=================================================================== b . 1075.5 |================================================================== c . 1072.1 |================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: AlexNet images/sec > Higher Is Better a . 178.52 |=================================================================== b . 174.81 |================================================================== c . 175.31 |================================================================== Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed MB/s > Higher Is Better a . 14.6 |===================================================================== b . 14.3 |==================================================================== c . 14.4 |==================================================================== SPECFEM3D 4.0 Model: Mount St. Helens Seconds < Lower Is Better a . 13.74 |==================================================================== b . 13.46 |=================================================================== c . 13.57 |=================================================================== SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 2.375 |==================================================================== b . 2.336 |=================================================================== c . 2.327 |=================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 183.30 |================================================================== b . 186.94 |=================================================================== c . 184.88 |================================================================== Stress-NG 0.15.06 Test: Hash Bogo Ops/s > Higher Is Better a . 12949136.28 |============================================================= b . 13204487.51 |============================================================== c . 13066446.38 |============================================================= VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 11.42 |=================================================================== b . 11.53 |==================================================================== c . 11.31 |=================================================================== Stress-NG 0.15.06 Test: SENDFILE Bogo Ops/s > Higher Is Better a . 1143575.46 |============================================================== b . 1162795.27 |=============================================================== c . 1165355.20 |=============================================================== Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed MB/s > Higher Is Better a . 907.7 |=================================================================== b . 924.0 |==================================================================== c . 907.0 |=================================================================== RocksDB 8.0 Test: Random Read Op/s > Higher Is Better a . 273039094 |================================================================ b . 268195000 |=============================================================== c . 273197200 |================================================================ OpenSSL 3.1 Algorithm: SHA512 byte/s > Higher Is Better a . 22617583540 |============================================================== b . 22641175270 |============================================================== c . 22228899690 |============================================================= oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 455.60 |=================================================================== b . 447.36 |================================================================== RocksDB 8.0 Test: Random Fill Sync Op/s > Higher Is Better a . 73440 |=================================================================== b . 74771 |==================================================================== c . 74573 |==================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 92.43 |=================================================================== b . 91.76 |=================================================================== c . 93.32 |==================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.373237 |================================================================ b . 0.379540 |================================================================= Stress-NG 0.15.06 Test: Matrix Math Bogo Ops/s > Higher Is Better a . 335705.12 |=============================================================== b . 341137.35 |================================================================ c . 341249.75 |================================================================ FFmpeg 6.0 Encoder: libx264 - Scenario: Platform Seconds < Lower Is Better a . 212.62 |=================================================================== b . 212.54 |=================================================================== c . 209.19 |================================================================== FFmpeg 6.0 Encoder: libx264 - Scenario: Upload FPS > Higher Is Better a . 9.91 |===================================================================== b . 9.97 |===================================================================== c . 9.81 |==================================================================== FFmpeg 6.0 Encoder: libx264 - Scenario: Platform FPS > Higher Is Better a . 35.63 |=================================================================== b . 35.64 |=================================================================== c . 36.21 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 5.01 |===================================================================== b . 4.93 |==================================================================== c . 4.95 |==================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 219.83 |=================================================================== b . 216.36 |================================================================== Timed Godot Game Engine Compilation 4.0 Time To Compile Seconds < Lower Is Better a . 148.77 |=================================================================== b . 148.85 |=================================================================== c . 146.51 |================================================================== FFmpeg 6.0 Encoder: libx264 - Scenario: Upload Seconds < Lower Is Better a . 254.90 |================================================================== b . 253.32 |================================================================== c . 257.31 |=================================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 22.29 |==================================================================== b . 21.95 |=================================================================== Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Decompression Speed MB/s > Higher Is Better a . 1190.2 |=================================================================== b . 1172.3 |================================================================== c . 1189.7 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: GoogLeNet images/sec > Higher Is Better a . 73.81 |==================================================================== b . 72.81 |=================================================================== c . 72.70 |=================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 190.26 |=================================================================== b . 187.42 |================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 7.998 |=================================================================== b . 8.014 |=================================================================== c . 8.119 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 images/sec > Higher Is Better a . 23.33 |==================================================================== b . 22.99 |=================================================================== c . 23.23 |==================================================================== nginx 1.23.2 Connections: 500 Requests Per Second > Higher Is Better a . 222945.56 |=============================================================== b . 226231.19 |================================================================ c . 225697.84 |================================================================ dav1d 1.1 Video Input: Summer Nature 4K FPS > Higher Is Better a . 66.17 |==================================================================== b . 65.21 |=================================================================== c . 65.70 |==================================================================== SPECFEM3D 4.0 Model: Homogeneous Halfspace Seconds < Lower Is Better a . 18.03 |=================================================================== b . 18.18 |==================================================================== c . 18.29 |==================================================================== AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 29.39 |=================================================================== b . 29.81 |==================================================================== c . 29.56 |=================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Second > Higher Is Better a . 10.19 |==================================================================== b . 10.14 |==================================================================== c . 10.06 |=================================================================== Embree 4.0.1 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better a . 103.14 |================================================================== b . 104.48 |=================================================================== c . 104.28 |=================================================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed MB/s > Higher Is Better a . 917.2 |=================================================================== b . 928.7 |==================================================================== c . 920.9 |=================================================================== dav1d 1.1 Video Input: Chimera 1080p FPS > Higher Is Better a . 134.66 |=================================================================== b . 133.01 |================================================================== c . 134.10 |=================================================================== VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 5.71 |===================================================================== b . 5.66 |==================================================================== c . 5.73 |===================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: GoogLeNet images/sec > Higher Is Better a . 100.57 |================================================================== b . 101.79 |=================================================================== c . 101.18 |=================================================================== Stress-NG 0.15.06 Test: Forking Bogo Ops/s > Higher Is Better a . 65824.56 |================================================================ b . 66467.95 |================================================================= c . 65696.65 |================================================================ Stress-NG 0.15.06 Test: NUMA Bogo Ops/s > Higher Is Better a . 437.26 |=================================================================== b . 432.40 |================================================================== c . 433.52 |================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 466.73 |================================================================== b . 471.80 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: AlexNet images/sec > Higher Is Better a . 518.73 |=================================================================== b . 513.22 |================================================================== c . 514.40 |================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 9.37499 |================================================================= b . 9.47539 |================================================================== c . 9.40220 |================================================================= ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 699.96 |================================================================== b . 707.31 |=================================================================== c . 705.80 |=================================================================== FFmpeg 6.0 Encoder: libx265 - Scenario: Upload FPS > Higher Is Better a . 8.62 |==================================================================== b . 8.66 |===================================================================== c . 8.71 |===================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: ResNet-50 images/sec > Higher Is Better a . 60.21 |=================================================================== b . 60.09 |=================================================================== c . 60.71 |==================================================================== Stress-NG 0.15.06 Test: MMAP Bogo Ops/s > Higher Is Better a . 3124.36 |================================================================== b . 3115.23 |================================================================== c . 3092.95 |================================================================= FFmpeg 6.0 Encoder: libx265 - Scenario: Upload Seconds < Lower Is Better a . 292.80 |=================================================================== b . 291.57 |=================================================================== c . 289.92 |================================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1.41955 |================================================================== b . 1.40563 |================================================================= Apache HTTP Server 2.4.56 Concurrent Requests: 500 Requests Per Second > Higher Is Better a . 37442.60 |================================================================= b . 37076.95 |================================================================ dav1d 1.1 Video Input: Summer Nature 1080p FPS > Higher Is Better a . 96.80 |==================================================================== b . 96.07 |=================================================================== c . 95.86 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 15.39 |=================================================================== b . 15.36 |=================================================================== c . 15.51 |==================================================================== Google Draco 1.5.6 Model: Church Facade ms < Lower Is Better a . 6765 |===================================================================== b . 6702 |==================================================================== c . 6767 |===================================================================== Timed LLVM Compilation 16.0 Build System: Unix Makefiles Seconds < Lower Is Better a . 286.22 |================================================================== b . 286.24 |================================================================== c . 288.95 |=================================================================== oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.17192 |================================================================== b . 1.16101 |================================================================= Blender 3.5 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 24.20 |=================================================================== b . 24.36 |==================================================================== c . 24.42 |==================================================================== MariaDB 11.0.1 Clients: 1024 Queries Per Second > Higher Is Better a . 110 |===================================================================== b . 110 |===================================================================== c . 111 |====================================================================== MariaDB 11.0.1 Clients: 2048 Queries Per Second > Higher Is Better a . 111 |===================================================================== b . 112 |====================================================================== c . 111 |===================================================================== OpenSSL 3.1 Algorithm: AES-128-GCM byte/s > Higher Is Better a . 799202790060 |============================================================ b . 802646430240 |============================================================= c . 806241823680 |============================================================= MariaDB 11.0.1 Clients: 4096 Queries Per Second > Higher Is Better a . 115 |====================================================================== b . 115 |====================================================================== c . 114 |===================================================================== Embree 4.0.1 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better a . 71.27 |=================================================================== b . 71.83 |==================================================================== c . 71.89 |==================================================================== Embree 4.0.1 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better a . 88.00 |==================================================================== b . 88.57 |==================================================================== c . 87.85 |=================================================================== AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 8.82 |===================================================================== b . 8.79 |==================================================================== c . 8.86 |===================================================================== nginx 1.23.2 Connections: 200 Requests Per Second > Higher Is Better a . 245504.32 |================================================================ b . 244509.87 |================================================================ c . 246434.82 |================================================================ oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 3.90427 |================================================================= b . 3.93436 |================================================================== Google Draco 1.5.6 Model: Lion ms < Lower Is Better a . 5502 |===================================================================== b . 5479 |==================================================================== c . 5521 |===================================================================== GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better a . 9.268 |==================================================================== b . 9.199 |=================================================================== c . 9.259 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 images/sec > Higher Is Better a . 71.38 |==================================================================== b . 71.21 |=================================================================== c . 71.74 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 images/sec > Higher Is Better a . 38.90 |==================================================================== b . 38.63 |==================================================================== c . 38.71 |==================================================================== VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 2.88 |===================================================================== b . 2.90 |===================================================================== c . 2.88 |===================================================================== Stress-NG 0.15.06 Test: Poll Bogo Ops/s > Higher Is Better a . 9551392.98 |=============================================================== b . 9566416.75 |=============================================================== c . 9500903.35 |=============================================================== Blender 3.5 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a . 32.22 |==================================================================== b . 32.29 |==================================================================== c . 32.07 |==================================================================== Blender 3.5 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a . 63.07 |==================================================================== b . 62.71 |==================================================================== c . 63.14 |==================================================================== FFmpeg 6.0 Encoder: libx265 - Scenario: Video On Demand Seconds < Lower Is Better a . 448.21 |=================================================================== b . 448.99 |=================================================================== c . 451.26 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: AlexNet images/sec > Higher Is Better a . 408.72 |=================================================================== b . 407.51 |=================================================================== c . 410.27 |=================================================================== FFmpeg 6.0 Encoder: libx265 - Scenario: Video On Demand FPS > Higher Is Better a . 16.90 |==================================================================== b . 16.87 |==================================================================== c . 16.79 |==================================================================== Embree 4.0.1 Binary: Pathtracer - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 76.17 |==================================================================== b . 76.66 |==================================================================== c . 76.41 |==================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 images/sec > Higher Is Better a . 30.87 |==================================================================== b . 30.80 |==================================================================== c . 31.00 |==================================================================== Stress-NG 0.15.06 Test: Mutex Bogo Ops/s > Higher Is Better a . 36280764.76 |============================================================== b . 36505304.60 |============================================================== c . 36276764.04 |============================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 5.029 |==================================================================== b . 4.998 |==================================================================== c . 5.012 |==================================================================== Timed LLVM Compilation 16.0 Build System: Ninja Seconds < Lower Is Better a . 180.77 |=================================================================== b . 181.17 |=================================================================== c . 180.06 |=================================================================== Stress-NG 0.15.06 Test: Malloc Bogo Ops/s > Higher Is Better a . 190168476.52 |============================================================= b . 191206280.20 |============================================================= c . 190376822.58 |============================================================= Zstd Compression 1.5.4 Compression Level: 3 - Decompression Speed MB/s > Higher Is Better a . 1128.4 |=================================================================== b . 1132.3 |=================================================================== c . 1126.3 |=================================================================== Blender 3.5 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better a . 244.20 |=================================================================== b . 243.71 |=================================================================== c . 244.89 |=================================================================== Blender 3.5 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a . 76.92 |==================================================================== b . 77.29 |==================================================================== c . 77.15 |==================================================================== Embree 4.0.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 89.18 |==================================================================== b . 89.29 |==================================================================== c . 88.89 |==================================================================== dav1d 1.1 Video Input: Chimera 1080p 10-bit FPS > Higher Is Better a . 130.69 |=================================================================== b . 130.12 |=================================================================== c . 130.27 |=================================================================== SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 97.16 |==================================================================== b . 97.19 |==================================================================== c . 97.57 |==================================================================== SPECFEM3D 4.0 Model: Layered Halfspace Seconds < Lower Is Better a . 29.64 |==================================================================== b . 29.52 |==================================================================== c . 29.65 |==================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better a . 196.25 |=================================================================== b . 197.02 |=================================================================== TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: GoogLeNet images/sec > Higher Is Better a . 214.30 |=================================================================== b . 213.49 |=================================================================== c . 213.69 |=================================================================== Embree 4.0.1 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better a . 84.35 |==================================================================== b . 84.28 |==================================================================== c . 84.59 |==================================================================== FFmpeg 6.0 Encoder: libx265 - Scenario: Platform Seconds < Lower Is Better a . 448.63 |=================================================================== b . 448.26 |=================================================================== c . 449.86 |=================================================================== FFmpeg 6.0 Encoder: libx265 - Scenario: Platform FPS > Higher Is Better a . 16.88 |==================================================================== b . 16.90 |==================================================================== c . 16.84 |==================================================================== OpenSSL 3.1 Algorithm: AES-256-GCM byte/s > Higher Is Better a . 709965487310 |============================================================= b . 712463205990 |============================================================= c . 710407167180 |============================================================= TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: GoogLeNet images/sec > Higher Is Better a . 132.43 |=================================================================== b . 132.26 |=================================================================== c . 131.98 |=================================================================== Timed FFmpeg Compilation 6.0 Time To Compile Seconds < Lower Is Better a . 17.81 |==================================================================== b . 17.87 |==================================================================== c . 17.84 |==================================================================== Stress-NG 0.15.06 Test: Memory Copying Bogo Ops/s > Higher Is Better a . 10941.37 |================================================================= b . 10922.24 |================================================================= c . 10908.20 |================================================================= TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: GoogLeNet images/sec > Higher Is Better a . 257.44 |=================================================================== b . 258.17 |=================================================================== c . 258.13 |=================================================================== RocksDB 8.0 Test: Random Fill Op/s > Higher Is Better a . 104159 |=================================================================== b . 104356 |=================================================================== c . 104086 |=================================================================== Stress-NG 0.15.06 Test: Glibc Qsort Data Sorting Bogo Ops/s > Higher Is Better a . 1550.53 |================================================================== b . 1546.69 |================================================================== c . 1547.20 |================================================================== OpenSSL 3.1 Algorithm: RSA4096 sign/s > Higher Is Better a . 36965.0 |================================================================== b . 36899.1 |================================================================== c . 36977.5 |================================================================== OpenSSL 3.1 Algorithm: RSA4096 verify/s > Higher Is Better a . 1189343.7 |================================================================ b . 1186897.4 |================================================================ c . 1188772.4 |================================================================ Stress-NG 0.15.06 Test: IO_uring Bogo Ops/s > Higher Is Better a . 26355.62 |================================================================= b . 26364.63 |================================================================= c . 26405.01 |================================================================= OpenSSL 3.1 Algorithm: ChaCha20-Poly1305 byte/s > Higher Is Better a . 293957452870 |============================================================= b . 294463651570 |============================================================= c . 294001151180 |============================================================= Stress-NG 0.15.06 Test: Vector Math Bogo Ops/s > Higher Is Better a . 306730.85 |================================================================ b . 306299.59 |================================================================ c . 306225.09 |================================================================ RocksDB 8.0 Test: Sequential Fill Op/s > Higher Is Better a . 106061 |=================================================================== b . 106147 |=================================================================== c . 106227 |=================================================================== RocksDB 8.0 Test: Update Random Op/s > Higher Is Better a . 97772 |==================================================================== b . 97861 |==================================================================== c . 97722 |==================================================================== OpenSSL 3.1 Algorithm: ChaCha20 byte/s > Higher Is Better a . 425091630970 |============================================================= b . 425550559910 |============================================================= c . 425195437530 |============================================================= Stress-NG 0.15.06 Test: Context Switching Bogo Ops/s > Higher Is Better a . 3511158.35 |=============================================================== b . 3508321.29 |=============================================================== c . 3511599.94 |=============================================================== Stress-NG 0.15.06 Test: x86_64 RdRand Bogo Ops/s > Higher Is Better a . 658591.72 |================================================================ b . 658461.44 |================================================================ c . 658542.68 |================================================================ MariaDB 11.0.1 Clients: 512 Queries Per Second > Higher Is Better a . 110 |====================================================================== b . 110 |====================================================================== c . 110 |====================================================================== AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 0.73 |===================================================================== b . 0.73 |===================================================================== c . 0.73 |===================================================================== oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 708.53 |================================================================ b . 737.56 |=================================================================== oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 35.46 |============================================================= b . 39.80 |==================================================================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 2.30887 |================================================================== b . 2.21121 |=============================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 18.01146 |================================================================= b . 5.37587 |=================== oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 30.271432 |================================================================ b . 0.668506 |= oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 2.56877 |================= b . 10.05550 |================================================================= oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.03996 |================================================================== b . 1.80895 |=========================================================== oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1.46571 |========================================================== b . 1.65880 |================================================================== Apache HTTP Server 2.4.56 Concurrent Requests: 1000 Requests Per Second > Higher Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 100 Requests Per Second > Higher Is Better ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 37.67 |==================================================================== b . 31.20 |======================================================== ONNX Runtime 1.14 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 44.86 |=================================================================== b . 45.56 |==================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 5.09499 |================================================================== b . 5.07500 |================================================================== ONNX Runtime 1.14 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 16.18 |================================================================= b . 17.00 |==================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 4.54812 |================================================================= b . 4.62093 |================================================================== ONNX Runtime 1.14 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 5.25466 |================================================================= b . 5.33429 |================================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 27.62 |=============================================================== b . 29.69 |==================================================================== c . 26.98 |============================================================== ONNX Runtime 1.14 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 30.60 |================================================================== b . 30.60 |================================================================== c . 31.31 |==================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 106.66 |=================================================================== b . 105.53 |================================================================== c . 106.35 |=================================================================== ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 320.96 |=============================================================== b . 341.19 |=================================================================== c . 340.99 |=================================================================== ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 1.42719 |================================================================== b . 1.41212 |================================================================= c . 1.41518 |================================================================= ONNX Runtime 1.14 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 1.59956 |================================================================ b . 1.64503 |================================================================== c . 1.59992 |================================================================ ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 62.01 |=================================================================== b . 61.29 |=================================================================== c . 62.65 |==================================================================== ONNX Runtime 1.14 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 75.44 |=================================================================== b . 76.75 |==================================================================== c . 74.46 |================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 87.99 |==================================================================== b . 84.05 |================================================================= c . 85.51 |================================================================== ONNX Runtime 1.14 Model: yolov4 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 98.12 |=================================================================== b . 98.61 |=================================================================== c . 99.41 |==================================================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better a . 5.45281 |================================================================== b . 5.34648 |================================================================= c . 5.40610 |================================================================= ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Parallel Inference Time Cost (ms) < Lower Is Better a . 10.81 |==================================================================== b . 10.89 |==================================================================== c . 10.71 |=================================================================== nginx 1.23.2 Connections: 1000 Requests Per Second > Higher Is Better nginx 1.23.2 Connections: 100 Requests Per Second > Higher Is Better