Xeon Max Linux 6.9 Kernel Benchmarks

2 x Intel Xeon Max 9480 benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2404031-NE-XEONMAXLI10
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:

Timed Code Compilation 3 Tests
C/C++ Compiler Tests 4 Tests
Compression Tests 2 Tests
CPU Massive 14 Tests
Creator Workloads 17 Tests
Database Test Suite 2 Tests
Encoding 4 Tests
Game Development 3 Tests
HPC - High Performance Computing 7 Tests
Imaging 3 Tests
Common Kernel Benchmarks 3 Tests
Large Language Models 2 Tests
Machine Learning 6 Tests
Multi-Core 19 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 6 Tests
Programmer / Developer System Benchmarks 3 Tests
Python Tests 5 Tests
Raytracing 2 Tests
Renderers 4 Tests
Server 3 Tests
Server CPU Tests 8 Tests
Video Encoding 3 Tests
Common Workstation Benchmarks 2 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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 6.8
March 29
  1 Day, 19 Hours, 46 Minutes
Linux 6.9-rc2
April 01
  1 Day, 17 Hours, 48 Minutes
Invert Hiding All Results Option
  1 Day, 18 Hours, 47 Minutes
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 Max Linux 6.9 Kernel Benchmarks 2 x Intel Xeon Max 9480 benchmarks for a future article. ,,"Linux 6.8","Linux 6.9-rc2" Processor,,2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads),2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads) Motherboard,,Supermicro SYS-221H-TNR X13DEM v1.10 (1.3 BIOS),Supermicro SYS-221H-TNR X13DEM v1.10 (1.3 BIOS) Chipset,,Intel Device 1bce,Intel Device 1bce Memory,,512GB,512GB Disk,,7682GB INTEL SSDPF2KX076TZ,7682GB INTEL SSDPF2KX076TZ Graphics,,ASPEED,ASPEED Network,,2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb,2 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb OS,,Ubuntu 23.10,Ubuntu 23.10 Kernel,,6.8.0-060800-generic (x86_64),6.9.0-060900rc2-generic (x86_64) Desktop,,GNOME Shell 45.0,GNOME Shell 45.0 Display Server,,X Server 1.21.1.7,X Server 1.21.1.7 Compiler,,GCC 13.2.0,GCC 13.2.0 File-System,,ext4,ext4 Screen Resolution,,1024x768,1024x768 ,,"Linux 6.8","Linux 6.9-rc2" "Stress-NG - Test: Hash (Bogo Ops/s)",HIB,17071694.52,17199190.09 "Stress-NG - Test: MMAP (Bogo Ops/s)",HIB,6169.36,6427.33 "Stress-NG - Test: NUMA (Bogo Ops/s)",HIB,482.62,487.60 "Stress-NG - Test: Pipe (Bogo Ops/s)",HIB,30377557.97,29814480.67 "Stress-NG - Test: Poll (Bogo Ops/s)",HIB,10389186.02,10232390.41 "Stress-NG - Test: Zlib (Bogo Ops/s)",HIB,9670.37,9446.07 "Stress-NG - Test: MEMFD (Bogo Ops/s)",HIB,688.26,688.76 "Stress-NG - Test: Mutex (Bogo Ops/s)",HIB,28490133.28,28934422.16 "Stress-NG - Test: Crypto (Bogo Ops/s)",HIB,143967.24,147978.33 "Stress-NG - Test: Malloc (Bogo Ops/s)",HIB,163551396.40,161652700.09 "Stress-NG - Test: Pthread (Bogo Ops/s)",HIB,39599.26,35919.64 "Stress-NG - Test: AVL Tree (Bogo Ops/s)",HIB,810.19,808.99 "Stress-NG - Test: IO_uring (Bogo Ops/s)",HIB,3468957.59,3346567.80 "Stress-NG - Test: SENDFILE (Bogo Ops/s)",HIB,1798203.12,1900682.08 "Stress-NG - Test: CPU Stress (Bogo Ops/s)",HIB,202073.08,200671.70 "Stress-NG - Test: Semaphores (Bogo Ops/s)",HIB,154589461.19,150005776.47 "Stress-NG - Test: Matrix Math (Bogo Ops/s)",HIB,384748.54,392750.09 "Stress-NG - Test: Floating Point (Bogo Ops/s)",HIB,29600.02,29139.60 "Stress-NG - Test: Matrix 3D Math (Bogo Ops/s)",HIB,31442.69,31460.42 "Stress-NG - Test: Memory Copying (Bogo Ops/s)",HIB,21085.10,20605.39 "Stress-NG - Test: Vector Shuffle (Bogo Ops/s)",HIB,576905.92,569593.00 "Stress-NG - Test: Mixed Scheduler (Bogo Ops/s)",HIB,70407.96,70036.20 "Stress-NG - Test: Socket Activity (Bogo Ops/s)",HIB,47927.75,46123.32 "Stress-NG - Test: Wide Vector Math (Bogo Ops/s)",HIB,5874353.63,5908316.03 "Stress-NG - Test: Context Switching (Bogo Ops/s)",HIB,20343491.52,19390362.90 "Stress-NG - Test: Fused Multiply-Add (Bogo Ops/s)",HIB,204365411.59,200468629.32 "Stress-NG - Test: Vector Floating Point (Bogo Ops/s)",HIB,234669.74,230503.34 "Stress-NG - Test: Glibc C String Functions (Bogo Ops/s)",HIB,80643523.24,85035507.55 "Stress-NG - Test: Glibc Qsort Data Sorting (Bogo Ops/s)",HIB,1866.58,1858.70 "Stress-NG - Test: System V Message Passing (Bogo Ops/s)",HIB,17859304.38,18740350.56 "OpenSSL - Algorithm: SHA256 (byte/s)",HIB,84678420667,81678284176 "OpenSSL - Algorithm: SHA512 (byte/s)",HIB,29940735740,29665499053 "Quicksilver - Input: CTS2 (Figure Of Merit)",HIB,8425444,8129143 "Quicksilver - Input: CORAL2 P1 (Figure Of Merit)",HIB,6814667,6916667 "Quicksilver - Input: CORAL2 P2 (Figure Of Merit)",HIB,6677333,6689667 "FFmpeg - Encoder: libx264 - Scenario: Live (FPS)",HIB,181.51,182.12 "FFmpeg - Encoder: libx265 - Scenario: Live (FPS)",HIB,112.43,113.99 "FFmpeg - Encoder: libx264 - Scenario: Upload (FPS)",HIB,11.50,11.51 "FFmpeg - Encoder: libx265 - Scenario: Upload (FPS)",HIB,22.31,22.24 "FFmpeg - Encoder: libx264 - Scenario: Platform (FPS)",HIB,42.76,42.77 "FFmpeg - Encoder: libx265 - Scenario: Platform (FPS)",HIB,42.74,40.20 "FFmpeg - Encoder: libx264 - Scenario: Video On Demand (FPS)",HIB,42.94,42.88 "FFmpeg - Encoder: libx265 - Scenario: Video On Demand (FPS)",HIB,44.80,44.24 "OpenVINO - Model: Face Detection FP16 - Device: CPU (FPS)",HIB,119.92,121.93 "OpenVINO - Model: Person Detection FP16 - Device: CPU (FPS)",HIB,451.13,466.45 "OpenVINO - Model: Person Detection FP32 - Device: CPU (FPS)",HIB,445.90,467.79 "OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (FPS)",HIB,2530.04,2656.42 "OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (FPS)",HIB,331.23,330.73 "OpenVINO - Model: Face Detection Retail FP16 - Device: CPU (FPS)",HIB,11260.98,11295.92 "OpenVINO - Model: Road Segmentation ADAS FP16 - Device: CPU (FPS)",HIB,1018.47,1051.30 "OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (FPS)",HIB,5067.40,5052.71 "OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (FPS)",HIB,16147.57,16349.05 "OpenVINO - Model: Face Detection Retail FP16-INT8 - Device: CPU (FPS)",HIB,15532.54,15589.59 "OpenVINO - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU (FPS)",HIB,1446.42,1442.21 "OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (FPS)",HIB,671.66,673.46 "OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (FPS)",HIB,26732.88,27790.24 "OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (FPS)",HIB,6336.78,6306.42 "OpenVINO - Model: Noise Suppression Poconet-Like FP16 - Device: CPU (FPS)",HIB,4621.32,4600.95 "OpenVINO - Model: Handwritten English Recognition FP16 - Device: CPU (FPS)",HIB,3626.41,3608.21 "OpenVINO - Model: Person Re-Identification Retail FP16 - Device: CPU (FPS)",HIB,11638.51,11564.78 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (FPS)",HIB,67789.25,73754.74 "OpenVINO - Model: Handwritten English Recognition FP16-INT8 - Device: CPU (FPS)",HIB,3777.56,3704.38 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (FPS)",HIB,121702.12,119735.57 "Embree - Binary: Pathtracer - Model: Crown (FPS)",HIB,36.6011,35.0788 "Embree - Binary: Pathtracer ISPC - Model: Crown (FPS)",HIB,38.8350,35.7348 "Embree - Binary: Pathtracer - Model: Asian Dragon (FPS)",HIB,35.4033,35.6507 "Embree - Binary: Pathtracer - Model: Asian Dragon Obj (FPS)",HIB,39.8177,36.5030 "Embree - Binary: Pathtracer ISPC - Model: Asian Dragon (FPS)",HIB,31.5957,32.8297 "Embree - Binary: Pathtracer ISPC - Model: Asian Dragon Obj (FPS)",HIB,36.4359,37.4335 "SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 4K (FPS)",HIB,5.865,5.760 "SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,48.943,48.568 "SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,127.202,126.187 "SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 4K (FPS)",HIB,123.246,123.098 "SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p (FPS)",HIB,18.662,18.934 "VVenC - Video Input: Bosphorus 4K - Video Preset: Fast (FPS)",HIB,4.902,4.936 "VVenC - Video Input: Bosphorus 4K - Video Preset: Faster (FPS)",HIB,9.847,9.524 "VVenC - Video Input: Bosphorus 1080p - Video Preset: Fast (FPS)",HIB,15.913,16.152 "VVenC - Video Input: Bosphorus 1080p - Video Preset: Faster (FPS)",HIB,33.986,33.094 "Xmrig - Variant: KawPow - Hash Count: 1M (H/s)",HIB,32860.8,33072.5 "Xmrig - Variant: Monero - Hash Count: 1M (H/s)",HIB,32361.2,33015.5 "Xmrig - Variant: Wownero - Hash Count: 1M (H/s)",HIB,36096.6,36180.7 "Xmrig - Variant: GhostRider - Hash Count: 1M (H/s)",HIB,9592.3,9602.7 "Xmrig - Variant: CryptoNight-Heavy - Hash Count: 1M (H/s)",HIB,32856.3,32826.1 "Xmrig - Variant: CryptoNight-Femto UPX2 - Hash Count: 1M (H/s)",HIB,33002.2,32993.8 "Intel Open Image Denoise - Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only (Images / Sec)",HIB,2.28,2.23 "Intel Open Image Denoise - Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only (Images / Sec)",HIB,2.32,2.22 "Intel Open Image Denoise - Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only (Images / Sec)",HIB,1.06,1.04 "TensorFlow - Device: CPU - Batch Size: 1 - Model: AlexNet (images/sec)",HIB,17.23,18.28 "TensorFlow - Device: CPU - Batch Size: 16 - Model: AlexNet (images/sec)",HIB,213.35,210.71 "TensorFlow - Device: CPU - Batch Size: 32 - Model: AlexNet (images/sec)",HIB,346.10,341.97 "TensorFlow - Device: CPU - Batch Size: 64 - Model: AlexNet (images/sec)",HIB,495.72,471.88 "TensorFlow - Device: CPU - Batch Size: 1 - Model: GoogLeNet (images/sec)",HIB,6.05,5.98 "TensorFlow - Device: CPU - Batch Size: 1 - Model: ResNet-50 (images/sec)",HIB,1.88,1.90 "TensorFlow - Device: CPU - Batch Size: 256 - Model: AlexNet (images/sec)",HIB,723.16,711.74 "TensorFlow - Device: CPU - Batch Size: 16 - Model: GoogLeNet (images/sec)",HIB,58.50,58.83 "TensorFlow - Device: CPU - Batch Size: 16 - Model: ResNet-50 (images/sec)",HIB,24.12,24.80 "TensorFlow - Device: CPU - Batch Size: 32 - Model: GoogLeNet (images/sec)",HIB,96.31,97.53 "TensorFlow - Device: CPU - Batch Size: 32 - Model: ResNet-50 (images/sec)",HIB,35.30,34.86 "TensorFlow - Device: CPU - Batch Size: 64 - Model: GoogLeNet (images/sec)",HIB,135.18,128.71 "TensorFlow - Device: CPU - Batch Size: 64 - Model: ResNet-50 (images/sec)",HIB,47.03,47.96 "TensorFlow - Device: CPU - Batch Size: 256 - Model: GoogLeNet (images/sec)",HIB,202.37,203.63 "TensorFlow - Device: CPU - Batch Size: 256 - Model: ResNet-50 (images/sec)",HIB,70.10,70.53 "ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,101.901,105.7827 "ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,167.343,154.205 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,7.91321,8.04142 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,8.22351,8.90936 "ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,185.294,196.076 "ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inferences/sec)",HIB,353.573,402.669 "ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,10.7817,10.6006 "ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,14.2656,15.4110 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,292.173,293.029 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,541.827,571.190 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,1.35994,1.50300 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,4.43649,5.41259 "ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,16.7832,17.5623 "ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,23.4613,24.2328 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,94.2487,95.1441 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,111.5706,122.601 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,152.635,153.564 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,205.414,213.737 "ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,23.4276,23.1727 "ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,32.4503,34.3512 "OSPRay - Benchmark: particle_volume/ao/real_time (Items/sec)",HIB,29.7336,28.8754 "OSPRay - Benchmark: particle_volume/scivis/real_time (Items/sec)",HIB,29.2815,29.0693 "OSPRay - Benchmark: particle_volume/pathtracer/real_time (Items/sec)",HIB,102.9501,98.8690 "OSPRay - Benchmark: gravity_spheres_volume/dim_512/ao/real_time (Items/sec)",HIB,10.70212,10.5090 "OSPRay - Benchmark: gravity_spheres_volume/dim_512/scivis/real_time (Items/sec)",HIB,10.50412,10.8236 "OSPRay - Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time (Items/sec)",HIB,24.2805,25.1712 "CacheBench - Test: Read (MB/s)",HIB,13344.699620,13341.467325 "CacheBench - Test: Write (MB/s)",HIB,93036.302415,93862.763311 "CacheBench - Test: Read / Modify / Write (MB/s)",HIB,99112.699260,98711.076947 "LZ4 Compression - Compression Level: 1 - Compression Speed (MB/s)",HIB,602.69,602.54 "LZ4 Compression - Compression Level: 1 - Decompression Speed (MB/s)",HIB,3601.0,3628.0 "LZ4 Compression - Compression Level: 3 - Compression Speed (MB/s)",HIB,98.43,98.41 "LZ4 Compression - Compression Level: 3 - Decompression Speed (MB/s)",HIB,3364.8,3349.6 "LZ4 Compression - Compression Level: 9 - Compression Speed (MB/s)",HIB,32.61,32.66 "LZ4 Compression - Compression Level: 9 - Decompression Speed (MB/s)",HIB,3537.0,3492.0 "srsRAN Project - Test: PDSCH Processor Benchmark, Throughput Total (Mbps)",HIB,17006.8,16877.6 "srsRAN Project - Test: PDSCH Processor Benchmark, Throughput Thread (Mbps)",HIB,662.4,650.8 "JPEG-XL libjxl - Input: PNG - Quality: 80 (MP/s)",HIB,32.477,33.045 "JPEG-XL libjxl - Input: PNG - Quality: 90 (MP/s)",HIB,30.969,30.128 "JPEG-XL libjxl - Input: JPEG - Quality: 80 (MP/s)",HIB,34.604,34.187 "JPEG-XL libjxl - Input: JPEG - Quality: 90 (MP/s)",HIB,32.562,33.888 "JPEG-XL libjxl - Input: PNG - Quality: 100 (MP/s)",HIB,25.666,25.607 "JPEG-XL libjxl - Input: JPEG - Quality: 100 (MP/s)",HIB,26.002,25.960 "JPEG-XL Decoding libjxl - CPU Threads: All (MP/s)",HIB,386.232,381.657 "WebP2 Image Encode - Encode Settings: Default (MP/s)",HIB,5.90,5.65 "WebP2 Image Encode - Encode Settings: Quality 75, Compression Effort 7 (MP/s)",HIB,0.64,0.61 "WebP2 Image Encode - Encode Settings: Quality 95, Compression Effort 7 (MP/s)",HIB,0.34,0.33 "WebP2 Image Encode - Encode Settings: Quality 100, Compression Effort 5 (MP/s)",HIB,8.35,8.45 "WebP2 Image Encode - Encode Settings: Quality 100, Lossless Compression (MP/s)",HIB,0.07,0.07 "Stockfish - Chess Benchmark (Nodes/s)",HIB,61999717,64443099 "GROMACS - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day)",HIB,12.085,11.764 "RocksDB - Test: Overwrite (Op/s)",HIB,388010,391968 "RocksDB - Test: Random Read (Op/s)",HIB,360498518,361586083 "RocksDB - Test: Update Random (Op/s)",HIB,359825,361502 "RocksDB - Test: Read Random Write Random (Op/s)",HIB,2120844,2068588 "Speedb - Test: Random Fill (Op/s)",HIB,326499,322816 "Speedb - Test: Random Read (Op/s)",HIB,380419389,375837479 "Speedb - Test: Update Random (Op/s)",HIB,292180,293414 "Speedb - Test: Sequential Fill (Op/s)",HIB,327637,330167 "Speedb - Test: Random Fill Sync (Op/s)",HIB,257446,259603 "Speedb - Test: Read Random Write Random (Op/s)",HIB,1181758,1175562 "MariaDB mariadb-slap - Clients: 512 (Queries/sec)",HIB,86,86 "MariaDB mariadb-slap - Clients: 1024 (Queries/sec)",HIB,34,36 "OpenSSL - Algorithm: RSA4096 (sign/s)",HIB,38204.6,38147.4 "Llama.cpp - Model: llama-2-7b.Q4_0.gguf (Tokens/sec)",HIB,1.99,2.49 "Llama.cpp - Model: llama-2-13b.Q4_0.gguf (Tokens/sec)",HIB,1.48,1.53 "Llama.cpp - Model: llama-2-70b-chat.Q5_0.gguf (Tokens/sec)",HIB,0.36,0.37 "Llamafile - Test: llava-v1.5-7b-q4 - Acceleration: CPU (Tokens/sec)",HIB,1.84,1.56 "Llamafile - Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU (Tokens/sec)",HIB,4.50,4.58 "Llamafile - Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU (Tokens/sec)",HIB,0.79,0.77 "OpenSSL - Algorithm: RSA4096 (verify/s)",HIB,1358616.4,1396904.0 "BRL-CAD - VGR Performance Metric (VGR Performance Metric)",HIB,3906839,3991802 "Chaos Group V-RAY - Mode: CPU (vsamples)",HIB,59852,58995 "ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,9.80514,9.46496 "ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,6.03604,6.57623 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,126.384,124.376 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,122.236,112.428 "ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,5.41191,5.10755 "ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,2.89501,2.48234 "ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,92.7467,94.3330 "ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,70.9566,65.9960 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,3.42357,3.40972 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,1.84807,1.74973 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,747.084,668.699 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,231.284,184.785 "ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,59.6021,56.9478 "ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,42.7819,41.5048 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,10.6098,10.5119 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,9.01538,8.23121 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,6.55011,6.51127 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,4.88181,4.67811 "ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,42.6833,43.1511 "ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,30.8209,29.1107 "oneDNN - Harness: IP Shapes 1D - Engine: CPU (ms)",LIB,4.50055,4.51166 "oneDNN - Harness: IP Shapes 3D - Engine: CPU (ms)",LIB,4.79853,4.84245 "oneDNN - Harness: Convolution Batch Shapes Auto - Engine: CPU (ms)",LIB,9.00621,8.81043 "oneDNN - Harness: Deconvolution Batch shapes_1d - Engine: CPU (ms)",LIB,18.3377,18.0275 "oneDNN - Harness: Deconvolution Batch shapes_3d - Engine: CPU (ms)",LIB,6.16576,5.78202 "oneDNN - Harness: Recurrent Neural Network Training - Engine: CPU (ms)",LIB,4821.32,10195.75 "oneDNN - Harness: Recurrent Neural Network Inference - Engine: CPU (ms)",LIB,748.495,753.364 "OSPRay Studio - Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,1801,1774 "OSPRay Studio - Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,1861,1839 "OSPRay Studio - Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,2108,2164 "OSPRay Studio - Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,34412,34953 "OSPRay Studio - Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,61363,61162 "OSPRay Studio - Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,35317,35422 "OSPRay Studio - Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,63514,63529 "OSPRay Studio - Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,40657,39794 "OSPRay Studio - Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,72172,73367 "OSPRay Studio - Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,466,478 "OSPRay Studio - Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,501,489 "OSPRay Studio - Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,569,570 "OSPRay Studio - Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,6909,6804 "OSPRay Studio - Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,13867,13807 "OSPRay Studio - Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,7402,7506 "OSPRay Studio - Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,14836,15415 "OSPRay Studio - Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,8732,8552 "OSPRay Studio - Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU (ms)",LIB,17204,16687 "Google Draco - Model: Lion (ms)",LIB,6129,6054 "Google Draco - Model: Church Facade (ms)",LIB,7747,7762 "OpenVINO - Model: Face Detection FP16 - Device: CPU (ms)",LIB,307.74,302.77 "OpenVINO - Model: Person Detection FP16 - Device: CPU (ms)",LIB,81.90,79.23 "OpenVINO - Model: Person Detection FP32 - Device: CPU (ms)",LIB,82.87,79.00 "OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (ms)",LIB,14.58,13.89 "OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (ms)",LIB,337.21,337.78 "OpenVINO - Model: Face Detection Retail FP16 - Device: CPU (ms)",LIB,9.92,9.89 "OpenVINO - Model: Road Segmentation ADAS FP16 - Device: CPU (ms)",LIB,36.28,35.14 "OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (ms)",LIB,22.06,22.12 "OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (ms)",LIB,6.85,6.76 "OpenVINO - Model: Face Detection Retail FP16-INT8 - Device: CPU (ms)",LIB,7.17,7.14 "OpenVINO - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU (ms)",LIB,77.34,77.57 "OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (ms)",LIB,54.98,54.83 "OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (ms)",LIB,4.05,3.89 "OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (ms)",LIB,17.52,17.58 "OpenVINO - Model: Noise Suppression Poconet-Like FP16 - Device: CPU (ms)",LIB,23.68,23.97 "OpenVINO - Model: Handwritten English Recognition FP16 - Device: CPU (ms)",LIB,30.85,31.01 "OpenVINO - Model: Person Re-Identification Retail FP16 - Device: CPU (ms)",LIB,9.59,9.65 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (ms)",LIB,0.78,0.71 "OpenVINO - Model: Handwritten English Recognition FP16-INT8 - Device: CPU (ms)",LIB,29.61,30.20 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (ms)",LIB,0.38,0.38 "Timed FFmpeg Compilation - Time To Compile (sec)",LIB,17.245,17.283 "Timed Linux Kernel Compilation - Build: defconfig (sec)",LIB,38.462,37.698 "Timed Linux Kernel Compilation - Build: allmodconfig (sec)",LIB,307.502,311.745 "Timed Mesa Compilation - Time To Compile (sec)",LIB,19.511,19.888 "Parallel BZIP2 Compression - FreeBSD-13.0-RELEASE-amd64-memstick.img Compression (sec)",LIB,2.933717,2.926551 "Primesieve - Length: 1e12 (sec)",LIB,3.356,3.299 "Primesieve - Length: 1e13 (sec)",LIB,39.619,39.461 "Y-Cruncher - Pi Digits To Calculate: 1B (sec)",LIB,13.416,13.335 "Y-Cruncher - Pi Digits To Calculate: 500M (sec)",LIB,6.483,6.202 "Hackbench - Count: 16 - Type: Thread (sec)",LIB,14.679,14.298 "Hackbench - Count: 16 - Type: Process (sec)",LIB,13.112,13.357 "Hackbench - Count: 32 - Type: Process (sec)",LIB,24.748,27.994 "Blender - Blend File: BMW27 - Compute: CPU-Only (sec)",LIB,21.82,22.02 "Blender - Blend File: Junkshop - Compute: CPU-Only (sec)",LIB,45.60,46.56 "Blender - Blend File: Classroom - Compute: CPU-Only (sec)",LIB,53.98,53.82 "Blender - Blend File: Fishy Cat - Compute: CPU-Only (sec)",LIB,38.09,39.37 "Blender - Blend File: Barbershop - Compute: CPU-Only (sec)",LIB,271.99,279.74 "Blender - Blend File: Pabellon Barcelona - Compute: CPU-Only (sec)",LIB,76.20,75.56 "WavPack Audio Encoding - WAV To WavPack (sec)",LIB,6.349,6.340