Google Cloud c3 Sapphire Rapids vs. AMD Milan

Benchmarks by Michael Larabel 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 2303280-NE-2303286NE24
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 2 Tests
C/C++ Compiler Tests 8 Tests
Compression Tests 2 Tests
CPU Massive 14 Tests
Creator Workloads 9 Tests
Cryptography 2 Tests
Database Test Suite 4 Tests
Fortran Tests 2 Tests
Game Development 4 Tests
HPC - High Performance Computing 12 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 5 Tests
Molecular Dynamics 4 Tests
MPI Benchmarks 2 Tests
Multi-Core 16 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 5 Tests
OpenMPI Tests 6 Tests
Programmer / Developer System Benchmarks 3 Tests
Python Tests 2 Tests
Renderers 2 Tests
Scientific Computing 4 Tests
Server 6 Tests
Server CPU Tests 9 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
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable

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
c3-highcpu-8 SPR
March 21 2023
  12 Hours, 6 Minutes
c2-standard-8 CLX
March 21 2023
  13 Hours
n2-standard-8 CLX
March 22 2023
  16 Hours, 1 Minute
n2-highcpu-8 CLX
March 23 2023
  14 Hours, 13 Minutes
t2d-standard-8 AMD
March 27 2023
  11 Hours, 20 Minutes
c2d-highcpu-8 AMD
March 28 2023
  11 Hours, 59 Minutes
Invert Hiding All Results Option
  13 Hours, 7 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):

Google Cloud c3 Sapphire Rapids vs. AMD Milan Benchmarks by Michael Larabel for a future article. ,,"c3-highcpu-8 SPR","c2-standard-8 CLX","n2-standard-8 CLX","n2-highcpu-8 CLX","t2d-standard-8 AMD","c2d-highcpu-8 AMD" Processor,,Intel Xeon Platinum 8481C (4 Cores / 8 Threads),Intel Xeon (4 Cores / 8 Threads),Intel Xeon (4 Cores / 8 Threads),Intel Xeon (4 Cores / 8 Threads),AMD EPYC 7B13 (8 Cores),AMD EPYC 7B13 (4 Cores / 8 Threads) Motherboard,,Google Compute Engine c3-highcpu-8,Google Compute Engine c2-standard-8,Google Compute Engine n2-standard-8,Google Compute Engine n2-highcpu-8,Google Compute Engine t2d-standard-8,Google Compute Engine c2d-highcpu-8 Chipset,,Intel 440FX 82441FX PMC,Intel 440FX 82441FX PMC,Intel 440FX 82441FX PMC,Intel 440FX 82441FX PMC,Intel 440FX 82441FX PMC,Intel 440FX 82441FX PMC Memory,,16GB,32GB,32GB,8GB,32GB,16GB Disk,,322GB nvme_card-pd,322GB PersistentDisk,322GB PersistentDisk,322GB PersistentDisk,322GB PersistentDisk,322GB PersistentDisk Network,,Google Compute Engine Virtual,Red Hat Virtio device,Red Hat Virtio device,Red Hat Virtio device,Red Hat Virtio device,Red Hat Virtio device OS,,Ubuntu 22.10,Ubuntu 22.10,Ubuntu 22.10,Ubuntu 22.10,Ubuntu 22.10,Ubuntu 22.10 Kernel,,5.19.0-1015-gcp (x86_64),5.19.0-1015-gcp (x86_64),5.19.0-1015-gcp (x86_64),5.19.0-1015-gcp (x86_64),5.19.0-1015-gcp (x86_64),5.19.0-1015-gcp (x86_64) Vulkan,,1.3.224,1.3.224,1.3.224,1.3.224,1.3.224,1.3.224 Compiler,,GCC 12.2.0,GCC 12.2.0,GCC 12.2.0,GCC 12.2.0,GCC 12.2.0,GCC 12.2.0 File-System,,ext4,ext4,ext4,ext4,ext4,ext4 System Layer,,KVM,KVM,KVM,KVM,KVM,KVM ,,"c3-highcpu-8 SPR","c2-standard-8 CLX","n2-standard-8 CLX","n2-highcpu-8 CLX","t2d-standard-8 AMD","c2d-highcpu-8 AMD" "nekRS - Input: TurboPipe Periodic (FLOP/s)",HIB,30667900000,25100766667,22963566667,,40756366667,27115200000 "OpenRadioss - Model: Bird Strike on Windshield (sec)",LIB,595.14,724.80,811.76,800.02,386.35,621.88 "TensorFlow - Device: CPU - Batch Size: 64 - Model: ResNet-50 (images/sec)",HIB,15.69,14.79,13.74,13.70,10.48,8.46 "MariaDB - Clients: 2048 (Queries/sec)",HIB,332,248,220,220,301,305 "OpenRadioss - Model: Rubber O-Ring Seal Installation (sec)",LIB,367.00,523.45,591.71,584.09,208.81,364.33 "OpenCV - Test: Core (ms)",LIB,87372,142770,209277,208199,90443,80771 "MariaDB - Clients: 4096 (Queries/sec)",HIB,317,237,207,214,280,292 "SPECFEM3D - Model: Water-layered Halfspace (sec)",LIB,321.625251668,347.812814070,380.129762523,374.194312999,197.520490133,287.423691806 "LeelaChessZero - Backend: Eigen (Nodes/s)",HIB,1221,902,808,801,1039,743 "OpenVKL - Benchmark: vklBenchmark ISPC (Items / Sec)",HIB,98,70,63,81,75,62 "LeelaChessZero - Backend: BLAS (Nodes/s)",HIB,1272,909,810,770,1202,856 "SPECFEM3D - Model: Layered Halfspace (sec)",LIB,372.089480857,374.756877204,415.183075434,416.413137338,223.109853428,324.852582801 "OpenRadioss - Model: Bumper Beam (sec)",LIB,303.38,390.61,436.27,433.87,176.83,286.02 "OpenCV - Test: Graph API (ms)",LIB,219931,236186,267250,289162,210214,199470 "OpenCV - Test: Stitching (ms)",LIB,214760,250833,278493,281338,195823,187400 "TensorFlow - Device: CPU - Batch Size: 32 - Model: ResNet-50 (images/sec)",HIB,14.93,14.11,12.95,12.99,10.61,8.55 "Intel Open Image Denoise - Run: RTLightmap.hdr.4096x4096 (Images / Sec)",HIB,0.12,0.11,0.10,0.09,0.15,0.08 "BRL-CAD - VGR Performance Metric (VGR Performance Metric)",HIB,71072,50314,44563,44556,99168,67437 "Timed Linux Kernel Compilation - Build: defconfig (sec)",LIB,244.800,289.662,322.381,327.755,184.683,259.335 "GROMACS - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day)",HIB,0.777,0.579,0.528,0.529,1.098,0.690 "OpenRadioss - Model: Cell Phone Drop Test (sec)",LIB,219.73,291.49,322.22,320.36,135.99,213.88 "OpenCV - Test: Image Processing (ms)",LIB,128163,147234,178704,172842,114410,117618 "PostgreSQL - Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency (ms)",LIB,2.565,4.616,5.055,5.274,2.475,3.206 "PostgreSQL - Scaling Factor: 100 - Clients: 800 - Mode: Read Only (TPS)",HIB,311942,173317,158267,152093,323353,249490 "PostgreSQL - Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency (ms)",LIB,3.405,5.895,6.450,6.862,3.118,4.096 "PostgreSQL - Scaling Factor: 100 - Clients: 1000 - Mode: Read Only (TPS)",HIB,293725,169643,155196,145790,320827,244198 "NAMD - ATPase Simulation - 327,506 Atoms (days/ns)",LIB,3.35779,4.44534,5.06706,5.05544,3.10822,4.45765 "SPECFEM3D - Model: Homogeneous Halfspace (sec)",LIB,179.545901627,190.794140810,213.892383575,215.274502309,102.336558318,163.999040336 "OpenFOAM - Input: drivaerFastback, Small Mesh Size - Execution Time (sec)",LIB,422.67836,560.60744,574.23602,563.86556,294.3444,403.83354 "OpenFOAM - Input: drivaerFastback, Small Mesh Size - Mesh Time (sec)",LIB,62.044277,85.518264,95.062233,91.505362,48.749592,63.91618 "OpenSSL - Algorithm: SHA256 (byte/s)",HIB,4283873987,1318193530,1178513873,1177333613,6876127730,5824179883 "OpenSSL - Algorithm: ChaCha20-Poly1305 (byte/s)",HIB,15970781140,10919151843,9576513353,9567474300,17592600077,11759326457 "OpenSSL - Algorithm: AES-256-GCM (byte/s)",HIB,48008361573,16945000630,15129238003,15133854923,31447472720,16968938653 "OpenSSL - Algorithm: AES-128-GCM (byte/s)",HIB,57594077823,23237312603,20765256453,20753550177,33948315373,18522423023 "OpenSSL - Algorithm: ChaCha20 (byte/s)",HIB,22091557637,21346811813,19055130217,19065485903,26325286910,17266517790 "OpenSSL - Algorithm: SHA512 (byte/s)",HIB,1568572920,1465815227,1308154027,1306223720,3158654817,1863352067 "TensorFlow - Device: CPU - Batch Size: 16 - Model: ResNet-50 (images/sec)",HIB,14.20,13.33,12.18,12.18,10.74,8.66 "Embree - Binary: Pathtracer ISPC - Model: Crown (FPS)",HIB,5.8475,3.9340,3.4584,3.4714,5.4928,4.9231 "SPECFEM3D - Model: Tomographic Model (sec)",LIB,143.937022875,150.915292633,166.377622705,167.348051891,81.806465318,128.165738351 "Intel Open Image Denoise - Run: RT.hdr_alb_nrm.3840x2160 (Images / Sec)",HIB,0.24,0.22,0.20,0.20,0.30,0.16 "SPECFEM3D - Model: Mount St. Helens (sec)",LIB,139.524469614,145.379328519,162.425332308,160.296159080,81.185672352,125.623694120 "Timed FFmpeg Compilation - Time To Compile (sec)",LIB,120.438,139.039,154.899,154.903,80.649,119.640 "OSPRay Studio - Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer (ms)",LIB,20952,30911,35884,35193,25306,31370 "Embree - Binary: Pathtracer ISPC - Model: Asian Dragon (FPS)",HIB,7.3642,5.1542,4.5768,4.5994,6.4173,5.8350 "miniBUDE - Implementation: OpenMP - Input Deck: BM1 (Billion Interactions/s)",HIB,7.546,6.112,5.358,5.358,12.162,7.443 "miniBUDE - Implementation: OpenMP - Input Deck: BM1 (GFInst/s)",HIB,188.651,152.798,133.951,133.950,304.053,186.080 "Zstd Compression - Compression Level: 19, Long Mode - Decompression Speed (MB/s)",HIB,907.2,713.8,660.3,650.0,1075.8,1183.8 "Zstd Compression - Compression Level: 19, Long Mode - Compression Speed (MB/s)",HIB,6.5,5.86,5.13,5.04,5.42,6.71 "OSPRay Studio - Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer (ms)",LIB,25819,37892,61337,61150,30299,37227 "CockroachDB - Workload: KV, 50% Reads - Concurrency: 128 (ops/s)",HIB,19321.6,13684.5,12699.1,12635.1,19110.4,17168.4 "CockroachDB - Workload: KV, 95% Reads - Concurrency: 128 (ops/s)",HIB,24960.1,16184.2,14976.8,14884.7,22148.8,20571.8 "oneDNN - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,4660.70,5767.70,6078.81,6112.65,4004.68,6503.63 "uvg266 - Video Input: Bosphorus 4K - Video Preset: Very Fast (FPS)",HIB,6.99,5.69,4.97,4.93,10.68,7.90 "nginx - Connections: 4000 (Reqs/sec)",HIB,32814.75,21594.94,19947.56,19477.31,33592.77,23747.52 "nginx - Connections: 1000 (Reqs/sec)",HIB,32118.58,21446.27,19683.60,19418.08,34079.62,23758.47 "nginx - Connections: 100 (Reqs/sec)",HIB,36310.35,25148.28,22830.19,22444.40,35257.77,25019.86 "nginx - Connections: 500 (Reqs/sec)",HIB,34672.65,21957.17,20146.10,19806.60,35127.26,24265.31 "nginx - Connections: 200 (Reqs/sec)",HIB,35602.10,24695.91,22570.18,21431.42,35225.04,24677.03 "uvg266 - Video Input: Bosphorus 4K - Video Preset: Super Fast (FPS)",HIB,7.48,6.03,5.28,5.17,11.36,8.14 "Zstd Compression - Compression Level: 19 - Decompression Speed (MB/s)",HIB,905.2,701.1,649.5,640.8,1129.0,1253.6 "Zstd Compression - Compression Level: 19 - Compression Speed (MB/s)",HIB,10.3,9.24,8.24,8.29,10.9,11.0 "oneDNN - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,2337.31,2998.03,3172.34,3157.38,2107.39,3335.70 "OpenCV - Test: Object Detection (ms)",LIB,38999,58056,64284,66269,32014,37666 "uvg266 - Video Input: Bosphorus 4K - Video Preset: Ultra Fast (FPS)",HIB,9.12,7.45,6.51,6.41,13.67,9.82 "Memcached - Set To Get Ratio: 1:10 (Ops/sec)",HIB,1044947.13,715723.53,641713.60,614742.62,1200527.42,842830.77 "Memcached - Set To Get Ratio: 1:100 (Ops/sec)",HIB,1030937.28,702291.93,624980.66,604363.37,1224550.68,835405.06 "John The Ripper - Test: MD5 (Real C/S)",HIB,765713,683546,599637,598971,738210,436585 "OpenSSL - Algorithm: RSA4096 (sign/s)",HIB,2062.7,1156.6,1028.6,1028.8,1765.0,1025.7 "7-Zip Compression - Test: Compression Rating (MIPS)",HIB,35306,30989,28062,28093,48449,39203 "Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,305.8991,323.0828,347.8299,354.0487,489.0758,436.2508 "Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,6.5372,6.1893,5.7491,5.6481,8.1654,4.5842 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,528.0193,682.3748,752.1925,761.3379,645.4229,584.5598 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,3.7873,2.9308,2.6587,2.6268,6.1611,3.4194 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,530.6100,681.3449,751.9383,752.6763,642.9791,588.6132 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,3.7693,2.9352,2.6597,2.6570,6.1956,3.3909 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,123.2931,142.8892,156.9026,155.2278,153.1562,139.2022 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,16.2194,13.9932,12.7443,12.8809,26.0592,14.3549 "Blender - Blend File: BMW27 - Compute: CPU-Only (sec)",LIB,315.24,,,,, "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,104.3102,125.4746,130.0183,132.2178,167.6700,147.4795 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,19.1677,15.9179,15.3621,15.1135,23.8083,13.5466 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,60.3858,68.5076,76.9661,77.8099,77.7789,70.1289 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,33.1064,29.1783,25.9736,25.6937,51.3541,28.4895 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,30.7952,33.2924,36.3447,36.6426,57.9885,52.4150 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,64.8747,59.9914,54.9590,54.5159,68.8551,38.1242 "Xcompact3d Incompact3d - Input: input.i3d 129 Cells Per Direction (sec)",LIB,32.3943163,37.7575671,40.5390091,40.0328242,21.5001178,26.5214876 "John The Ripper - Test: bcrypt (Real C/S)",HIB,6932,6687,5970,5962,10585,7620 "John The Ripper - Test: Blowfish (Real C/S)",HIB,6930,6684,5968,5959,10611,7619 "uvg266 - Video Input: Bosphorus 1080p - Video Preset: Very Fast (FPS)",HIB,32.39,26.30,22.81,22.87,49.19,36.45 "uvg266 - Video Input: Bosphorus 1080p - Video Preset: Super Fast (FPS)",HIB,34.50,27.72,24.15,24.15,52.25,37.79 "uvg266 - Video Input: Bosphorus 1080p - Video Preset: Ultra Fast (FPS)",HIB,42.24,34.47,30.05,29.97,61.85,45.53 "Google Draco - Model: Lion (ms)",LIB,6250,7437,8355,8391,6073,5617 "oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,1.47145,52.9421,60.5925,60.5549,, "Google Draco - Model: Church Facade (ms)",LIB,7573,11462,12332,12882,8754,7442 "oneDNN - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,1.50004,19.5287,22.0252,22.0356,, "oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,0.968986,7.43260,8.50678,8.44515,, "oneDNN - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,5.34218,8.02416,8.51864,8.62637,, "oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,4.17707,34.1893,38.8717,38.9676,, "oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,3.54944,35.9164,40.6542,40.7787,, "Geometric Mean Of All Test Results - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Geometric Mean)",HIB,54.762,41.962,37.562,37.358,62.186,47.046 "Geometric Mean Of Timed Code Compilation Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.311,1.122,1.007,1.000,1.845,1.279 "Geometric Mean Of C/C++ Compiler Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.648,1.124,1.015,1.000,1.834,1.350 "Geometric Mean Of Compression Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.318,1.114,1.008,1.000,1.480,1.544 "Geometric Mean Of CPU Massive Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.570,1.120,1.012,1.000,1.638,1.227 "Geometric Mean Of Creator Workloads Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.484,1.143,1.000,1.004,1.710,1.291 "Geometric Mean Of Cryptography Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.742,1.125,1.001,1.000,1.955,1.250 "Geometric Mean Of Database Test Suite - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.760,1.134,1.026,1.000,1.796,1.482 "Geometric Mean Of Fortran Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.175,1.102,1.000,1.004,1.964,1.334 "Geometric Mean Of Game Development Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.376,1.103,1.000,1.018,1.388,1.091 "Geometric Mean Of HPC - High Performance Computing Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.367,1.114,1.004,1.000,1.515,1.149 "Geometric Mean Of Common Kernel Benchmarks Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,2.041,1.134,1.019,1.000,2.152,1.449 "Geometric Mean Of Machine Learning Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.343,1.120,1.010,1.000,1.312,1.057 "Geometric Mean Of Molecular Dynamics Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.421,1.089,1.000,1.015,1.894,1.369 "Geometric Mean Of MPI Benchmarks Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.358,1.085,1.000,1.008,1.981,1.414 "Geometric Mean Of Multi-Core Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.466,1.133,1.003,1.000,1.700,1.316 "Geometric Mean Of NVIDIA GPU Compute Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.546,1.133,1.019,1.000,1.614,1.104 "Geometric Mean Of Intel oneAPI Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.523,1.157,1.000,1.020,1.510,1.078 "Geometric Mean Of OpenMPI Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.324,1.102,1.000,1.010,2.107,1.397 "Geometric Mean Of Programmer / Developer System Benchmarks Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.326,1.119,1.010,1.000,1.553,1.475 "Geometric Mean Of Python Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.349,1.174,1.077,1.070,1.267,1.000 "Geometric Mean Of Renderers Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,2.000,1.500,1.000,1.000,2.000,1.500 "Geometric Mean Of Scientific Computing Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.421,1.089,1.000,1.015,1.894,1.369 "Geometric Mean Of Server Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.825,1.127,1.018,1.000,1.875,1.365 "Geometric Mean Of Server CPU Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan (Relative Performance)",HIB,1.536,1.116,1.001,1.000,1.699,1.286 "nekRS - Performance / Cost - Input: TurboPipe Periodic (FLOP/s/Dollar)",HIB,393178205128.205,216385919543.103,194606497177.966,,702695977017.241,352145454545.455 "OpenRadioss - Performance / Cost - Model: Bird Strike on Windshield (sec x Dollar)",LIB,33.923,60.883,71.435,51.201,13.909,32.338 "TensorFlow - Performance / Cost - Device: CPU - Batch Size: 64 - Model: ResNet-50 (images/sec/Dollar)",HIB,364.884,264.107,245.357,326.190,163.750,120.857 "MariaDB - Performance / Cost - Clients: 2048 (Queries/sec/Dollar)",HIB,11066.667,5166.667,4313.725,5945.946,9406.250,10892.857 "OpenRadioss - Performance / Cost - Model: Rubber O-Ring Seal Installation (sec x Dollar)",LIB,12.845,31.930,38.461,27.452,4.176,11.294 "OpenCV - Performance / Cost - Test: Core (ms x Dollar)",LIB,698.976,2427.090,4813.371,3539.383,813.987,565.397 "MariaDB - Performance / Cost - Clients: 4096 (Queries/sec/Dollar)",HIB,9906.250,4647.059,3833.333,5487.179,8000.000,9733.333 "SPECFEM3D - Performance / Cost - Model: Water-layered Halfspace (sec x Dollar)",LIB,10.292,14.608,16.346,11.600,3.753,7.186 "LeelaChessZero - Performance / Cost - Backend: Eigen (Nodes/s/Dollar)",HIB,35911.765,21476.190,20717.949,27620.690,30558.824,24766.667 "OpenVKL - Performance / Cost - Benchmark: vklBenchmark ISPC (Items / Sec/Dollar)",HIB,2450.000,1458.333,1369.565,3375.000,1973.684,1823.529 "LeelaChessZero - Performance / Cost - Backend: BLAS (Nodes/s/Dollar)",HIB,37411.765,21642.857,20769.231,26551.724,35352.941,28533.333 "SPECFEM3D - Performance / Cost - Model: Layered Halfspace (sec x Dollar)",LIB,13.395,16.489,18.683,13.742,4.685,8.771 "OpenRadioss - Performance / Cost - Model: Bumper Beam (sec x Dollar)",LIB,8.798,17.577,20.505,15.185,3.006,6.864 "OpenCV - Performance / Cost - Test: Graph API (ms x Dollar)",LIB,4618.551,6377.022,7750.250,6650.726,4204.280,3390.990 "OpenCV - Performance / Cost - Test: Stitching (ms x Dollar)",LIB,4509.960,7274.157,8354.790,6189.436,3524.814,2998.400 "TensorFlow - Performance / Cost - Device: CPU - Batch Size: 32 - Model: ResNet-50 (images/sec/Dollar)",HIB,649.130,470.333,431.667,590.455,331.563,244.286 "Intel Open Image Denoise - Performance / Cost - Run: RTLightmap.hdr.4096x4096 (Images / Sec/Dollar)",HIB,4.800,3.438,2.941,3.600,7.895,2.667 "BRL-CAD - Performance / Cost - VGR Performance Metric (VGR Performance Metric/Dollar)",HIB,1076848.485,541010.753,512218.391,655235.294,1166682.353,923794.521 "Timed Linux Kernel Compilation - Performance / Cost - Build: defconfig (sec x Dollar)",LIB,5.630,9.849,11.283,8.522,3.140,5.705 "GROMACS - Performance / Cost - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day/Dollar)",HIB,35.318,16.543,14.667,19.593,73.200,32.857 "OpenRadioss - Performance / Cost - Model: Cell Phone Drop Test (sec x Dollar)",LIB,4.834,10.202,11.600,8.329,1.768,3.850 "OpenCV - Performance / Cost - Test: Image Processing (ms x Dollar)",LIB,1537.956,2502.978,3395.376,2419.788,1258.510,1176.180 "PostgreSQL - Performance / Cost - Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency (ms x Dollar)",LIB,0.036,0.078,0.081,0.063,0.032,0.038 "PostgreSQL - Performance / Cost - Scaling Factor: 100 - Clients: 800 - Mode: Read Only (TPS/Dollar)",HIB,22281571.429,10195117.647,9891687.500,12674416.667,24873307.692,20790833.333 "PostgreSQL - Performance / Cost - Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency (ms x Dollar)",LIB,0.048,0.100,0.103,0.082,0.041,0.049 "PostgreSQL - Performance / Cost - Scaling Factor: 100 - Clients: 1000 - Mode: Read Only (TPS/Dollar)",HIB,20980357.143,9979000.000,9699750.000,12149166.667,24679000.000,20349833.333 "NAMD - Performance / Cost - ATPase Simulation - 327,506 Atoms (days/ns x Dollar)",LIB,0.054,0.116,0.137,0.101,0.044,0.080 "SPECFEM3D - Performance / Cost - Model: Homogeneous Halfspace (sec x Dollar)",LIB,3.232,4.388,5.133,3.875,1.023,2.296 "OpenFOAM - Performance / Cost - Input: drivaerFastback, Small Mesh Size - Execution Time (sec x Dollar)",LIB,19.866,42.046,41.919,29.885,9.713,15.750 "OpenFOAM - Performance / Cost - Input: drivaerFastback, Small Mesh Size - Mesh Time (sec x Dollar)",LIB,2.916,6.414,6.940,4.850,1.609,2.493 "OpenSSL - Performance / Cost - Algorithm: SHA256 (byte/s/Dollar)",HIB,251992587470.588,62771120476.191,62027045947.368,84095258071.429,404478101764.706,388278658866.667 "OpenSSL - Performance / Cost - Algorithm: ChaCha20-Poly1305 (byte/s/Dollar)",HIB,939457714117.647,519959611571.429,504027018578.947,683391021428.571,1034858828058.823,783955097133.333 "OpenSSL - Performance / Cost - Algorithm: AES-256-GCM (byte/s/Dollar)",HIB,2824021269000.000,806904791904.762,796275684368.421,1080989637357.143,1849851336470.588,1131262576866.667 "OpenSSL - Performance / Cost - Algorithm: AES-128-GCM (byte/s/Dollar)",HIB,3387886930764.706,1106538695380.952,1092908234368.421,1482396441214.286,1996959727823.529,1234828201533.333 "OpenSSL - Performance / Cost - Algorithm: ChaCha20 (byte/s/Dollar)",HIB,1299503390411.765,1016514848238.095,1002901590368.421,1361820421642.857,1548546288823.529,1151101186000.000 "OpenSSL - Performance / Cost - Algorithm: SHA512 (byte/s/Dollar)",HIB,92268995294.118,69800725095.238,68850211947.368,93301694285.714,185803224529.412,124223471133.333 "TensorFlow - Performance / Cost - Device: CPU - Batch Size: 16 - Model: ResNet-50 (images/sec/Dollar)",HIB,1183.333,833.125,761.250,1015.000,671.250,509.412 "Embree - Performance / Cost - Binary: Pathtracer ISPC - Model: Crown (FPS/Dollar)",HIB,531.591,207.053,172.920,231.427,499.345,447.555 "SPECFEM3D - Performance / Cost - Model: Tomographic Model (sec x Dollar)",LIB,2.015,2.716,2.995,2.343,0.654,1.410 "Intel Open Image Denoise - Performance / Cost - Run: RT.hdr_alb_nrm.3840x2160 (Images / Sec/Dollar)",HIB,20.000,14.667,12.500,16.667,33.333,10.667 "SPECFEM3D - Performance / Cost - Model: Mount St. Helens (sec x Dollar)",LIB,1.953,2.471,2.924,2.084,0.649,1.382 "Timed FFmpeg Compilation - Performance / Cost - Time To Compile (sec x Dollar)",LIB,1.325,2.225,2.633,1.859,0.645,1.196 "OSPRay Studio - Performance / Cost - Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer (ms x Dollar)",LIB,209.520,432.754,538.260,387.123,278.366,282.330 "Embree - Performance / Cost - Binary: Pathtracer ISPC - Model: Asian Dragon (FPS/Dollar)",HIB,920.525,343.613,305.120,418.127,713.033,648.333 "miniBUDE - Performance / Cost - Implementation: OpenMP - Input Deck: BM1 (Billion Interactions/s/Dollar)",HIB,754.600,407.467,334.875,446.500,2027.000,827.000 "miniBUDE - Performance / Cost - Implementation: OpenMP - Input Deck: BM1 (GFInst/s/Dollar)",HIB,18865.100,10186.533,8371.938,11162.500,50675.500,20675.556 "Zstd Compression - Performance / Cost - Compression Level: 19, Long Mode - Decompression Speed (MB/s/Dollar)",HIB,151200.000,89225.000,82537.500,108333.333,153685.714,236760.000 "Zstd Compression - Performance / Cost - Compression Level: 19, Long Mode - Compression Speed (MB/s/Dollar)",HIB,1083.333,732.500,641.250,840.000,774.286,1342.000 "OSPRay Studio - Performance / Cost - Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer (ms x Dollar)",LIB,309.828,606.272,490.696,366.900,393.887,372.270 "CockroachDB - Performance / Cost - Workload: KV, 50% Reads - Concurrency: 128 (ops/s/Dollar)",HIB,1932160.000,1140375.000,1058258.333,1403900.000,1911040.000,1907600.000 "CockroachDB - Performance / Cost - Workload: KV, 95% Reads - Concurrency: 128 (ops/s/Dollar)",HIB,2496010.000,1348683.333,1248066.667,1653855.556,2214880.000,2285755.556 "oneDNN - Performance / Cost - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU (ms x Dollar)",LIB,41.946,63.445,66.867,48.901,36.042,52.029 "uvg266 - Performance / Cost - Video Input: Bosphorus 4K - Video Preset: Very Fast (FPS/Dollar)",HIB,873.750,474.167,382.308,493.000,2136.000,1316.667 "nginx - Performance / Cost - Connections: 4000 (Reqs/sec/Dollar)",HIB,3646083.333,2159494.000,1994756.000,2782472.857,4199096.250,3392502.857 "nginx - Performance / Cost - Connections: 1000 (Reqs/sec/Dollar)",HIB,3568731.111,2144627.000,1968360.000,2774011.429,4259952.500,3394067.143 "nginx - Performance / Cost - Connections: 100 (Reqs/sec/Dollar)",HIB,4034483.333,2514828.000,2283019.000,3206342.857,4407221.250,3574265.714 "nginx - Performance / Cost - Connections: 500 (Reqs/sec/Dollar)",HIB,3852516.667,2195717.000,2014610.000,2829514.286,4390907.500,3466472.857 "nginx - Performance / Cost - Connections: 200 (Reqs/sec/Dollar)",HIB,3955788.889,2469591.000,2257018.000,3061631.429,4403130.000,3525290.000 "uvg266 - Performance / Cost - Video Input: Bosphorus 4K - Video Preset: Super Fast (FPS/Dollar)",HIB,935.000,502.500,440.000,574.444,2272.000,1356.667 "Zstd Compression - Performance / Cost - Compression Level: 19 - Decompression Speed (MB/s/Dollar)",HIB,129314.286,77900.000,72166.667,91542.857,161285.714,208933.333 "Zstd Compression - Performance / Cost - Compression Level: 19 - Compression Speed (MB/s/Dollar)",HIB,1471.429,1026.667,915.556,1184.286,1557.143,1833.333 "oneDNN - Performance / Cost - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU (ms x Dollar)",LIB,18.698,29.980,28.551,22.102,16.859,23.350 "OpenCV - Performance / Cost - Test: Object Detection (ms x Dollar)",LIB,155.996,406.392,449.988,331.345,96.042,112.998 "uvg266 - Performance / Cost - Video Input: Bosphorus 4K - Video Preset: Ultra Fast (FPS/Dollar)",HIB,1520.000,827.778,651.000,915.714,3417.500,1964.000 "Memcached - Performance / Cost - Set To Get Ratio: 1:10 (Ops/sec/Dollar)",HIB,174157855.000,89465441.250,91673371.429,122948524.000,200087903.333,168566154.000 "Memcached - Performance / Cost - Set To Get Ratio: 1:100 (Ops/sec/Dollar)",HIB,171822880.000,87786491.250,89282951.429,120872674.000,204091780.000,167081012.000 "John The Ripper - Performance / Cost - Test: MD5 (Real C/S/Dollar)",HIB,127618833.333,97649428.571,99939500.000,119794200.000,123035000.000,87317000.000 "OpenSSL - Performance / Cost - Algorithm: RSA4096 (sign/s/Dollar)",HIB,343783.333,165228.571,171433.333,205760.000,294166.667,205140.000 "7-Zip Compression - Performance / Cost - Test: Compression Rating (MIPS/Dollar)",HIB,8826500.000,7747250.000,7015500.000,9364333.333,24224500.000,19601500.000 "Neural Magic DeepSparse - Performance / Cost - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch x Dollar)",LIB,1.529,2.262,2.435,1.770,2.445,1.745 "Neural Magic DeepSparse - Performance / Cost - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec/Dollar)",HIB,1307.440,884.186,821.300,1129.620,1633.080,1146.050 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch x Dollar)",LIB,2.640,4.777,4.513,3.807,3.227,2.338 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec/Dollar)",HIB,757.460,418.686,443.117,525.360,1232.220,854.850 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch x Dollar)",LIB,2.653,4.088,4.512,3.763,3.215,2.354 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec/Dollar)",HIB,753.860,489.200,443.283,531.400,1239.120,847.725 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (ms/batch x Dollar)",LIB,0.616,0.857,0.941,0.776,0.766,0.557 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (items/sec/Dollar)",HIB,3243.880,2332.200,2124.050,2576.180,5211.840,3588.725 "Blender - Performance / Cost - Blend File: BMW27 - Compute: CPU-Only (sec x Dollar)",LIB,9.457,,,,, "Neural Magic DeepSparse - Performance / Cost - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (ms/batch x Dollar)",LIB,0.417,0.753,0.650,0.529,0.838,0.590 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (items/sec/Dollar)",HIB,4791.925,2652.983,3072.420,3778.375,4761.660,3386.650 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch x Dollar)",LIB,0.242,0.343,0.385,0.233,0.311,0.210 "Neural Magic DeepSparse - Performance / Cost - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec/Dollar)",HIB,8276.600,5835.660,5194.720,8564.567,12838.525,9496.500 "Neural Magic DeepSparse - Performance / Cost - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch x Dollar)",LIB,0.123,0.133,0.145,0.110,0.232,0.157 "Neural Magic DeepSparse - Performance / Cost - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec/Dollar)",HIB,16218.675,14997.850,13739.750,18171.967,17213.775,12708.067 "Xcompact3d Incompact3d - Performance / Cost - Input: input.i3d 129 Cells Per Direction (sec x Dollar)",LIB,0.097,0.151,0.162,0.120,0.043,0.053 "John The Ripper - Performance / Cost - Test: bcrypt (Real C/S/Dollar)",HIB,2310666.667,2229000.000,1990000.000,2981000.000,3528333.333,3810000.000 "John The Ripper - Performance / Cost - Test: Blowfish (Real C/S/Dollar)",HIB,2310000.000,2228000.000,1989333.333,2979500.000,3537000.000,3809500.000 "uvg266 - Performance / Cost - Video Input: Bosphorus 1080p - Video Preset: Very Fast (FPS/Dollar)",HIB,16195.000,8766.667,7603.333,11435.000,49190.000,36450.000 "uvg266 - Performance / Cost - Video Input: Bosphorus 1080p - Video Preset: Super Fast (FPS/Dollar)",HIB,17250.000,9240.000,8050.000,12075.000,52250.000,37790.000 "uvg266 - Performance / Cost - Video Input: Bosphorus 1080p - Video Preset: Ultra Fast (FPS/Dollar)",HIB,42240.000,17235.000,15025.000,14985.000,61850.000,45530.000 "Google Draco - Performance / Cost - Model: Lion (ms x Dollar)",LIB,6.250,7.437,8.355,8.391,6.073,5.617 "oneDNN - Performance / Cost - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU (ms x Dollar)",LIB,0.003,0.106,0.121,0.121,, "Google Draco - Performance / Cost - Model: Church Facade (ms x Dollar)",LIB,7.573,22.924,24.664,12.882,8.754,7.442 "oneDNN - Performance / Cost - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU (ms x Dollar)",LIB,0.002,0.039,0.044,0.022,, "oneDNN - Performance / Cost - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU (ms x Dollar)",LIB,0.001,0.007,0.009,0.008,, "oneDNN - Performance / Cost - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU (ms x Dollar)",LIB,0.005,0.008,0.009,0.009,, "oneDNN - Performance / Cost - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU (ms x Dollar)",LIB,0.004,0.034,0.039,,,