AMD EPYC Genoa Memory Scaling

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 2212240-NE-AMDEPYCGE62
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 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 3 Tests
C++ Boost Tests 2 Tests
Timed Code Compilation 11 Tests
C/C++ Compiler Tests 10 Tests
CPU Massive 15 Tests
Creator Workloads 14 Tests
Database Test Suite 2 Tests
Encoding 4 Tests
Fortran Tests 5 Tests
Game Development 5 Tests
HPC - High Performance Computing 21 Tests
Java Tests 2 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
Machine Learning 5 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 5 Tests
Multi-Core 30 Tests
NVIDIA GPU Compute 4 Tests
Intel oneAPI 6 Tests
OpenMPI Tests 13 Tests
Programmer / Developer System Benchmarks 13 Tests
Python Tests 11 Tests
Renderers 3 Tests
Scientific Computing 7 Tests
Server 4 Tests
Server CPU Tests 11 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
12c
December 21 2022
  11 Hours, 55 Minutes
10c
December 21 2022
  12 Hours, 59 Minutes
8c
December 22 2022
  13 Hours, 22 Minutes
6c
December 23 2022
  15 Hours, 14 Minutes
Invert Hiding All Results Option
  13 Hours, 22 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):

AMD EPYC Genoa Memory Scaling Benchmarks by Michael Larabel for a future article. ,,"12c","10c","8c","6c" Processor,,2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads),2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads),2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads),2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) Motherboard,,AMD Titanite_4G (RTI1002E BIOS),AMD Titanite_4G (RTI1002E BIOS),AMD Titanite_4G (RTI1002E BIOS),AMD Titanite_4G (RTI1002E BIOS) Chipset,,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4,AMD Device 14a4 Memory,,1520GB,1264GB,1008GB,768GB Disk,,800GB INTEL SSDPF21Q800GB,800GB INTEL SSDPF21Q800GB,800GB INTEL SSDPF21Q800GB,800GB INTEL SSDPF21Q800GB Graphics,,ASPEED,ASPEED,ASPEED,ASPEED Monitor,,VGA HDMI,VGA HDMI,VGA HDMI,VGA HDMI Network,,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe,Broadcom NetXtreme BCM5720 PCIe OS,,Ubuntu 22.10,Ubuntu 22.10,Ubuntu 22.10,Ubuntu 22.10 Kernel,,6.1.0-phx (x86_64),6.1.0-phx (x86_64),6.1.0-phx (x86_64),6.1.0-phx (x86_64) Desktop,,GNOME Shell 43.0,GNOME Shell 43.0,GNOME Shell 43.0,GNOME Shell 43.0 Display Server,,X Server 1.21.1.4,X Server 1.21.1.4,X Server 1.21.1.4,X Server 1.21.1.4 Vulkan,,1.3.224,1.3.224,1.3.224,1.3.224 Compiler,,GCC 12.2.0 + Clang 15.0.2-1,GCC 12.2.0 + Clang 15.0.2-1,GCC 12.2.0 + Clang 15.0.2-1,GCC 12.2.0 + Clang 15.0.2-1 File-System,,ext4,ext4,ext4,ext4 Screen Resolution,,1920x1080,1920x1080,1920x1080,1920x1080 ,,"12c","10c","8c","6c" "Xcompact3d Incompact3d - Input: X3D-benchmarking input.i3d (sec)",LIB,125.526248,146.289830,270.091271,348.880025 "OpenFOAM - Input: drivaerFastback, Medium Mesh Size - Execution Time (sec)",LIB,109.53721,117.94003,166.14971,227.89595 "RELION - Test: Basic - Device: CPU (sec)",LIB,128.101,151.398,221.336,258.500 "WRF - Input: conus 2.5km (sec)",LIB,4070.19,4563.183,6551.876,7432.655 "NAS Parallel Benchmarks - Test / Class: MG.C (Mop/s)",HIB,209846.76,177097.42,153458.78,117733.57 "NAS Parallel Benchmarks - Test / Class: SP.C (Mop/s)",HIB,260471.50,239496.01,208535.23,167474.70 "Graph500 - Scale: 26 (sssp median_TEPS)",HIB,565152000,574018000,531854000,392496000 "Neural Magic DeepSparse - Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,111.8909,113.4079,123.8576,150.9167 "Neural Magic DeepSparse - Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,856.0186,844.4268,773.0686,635.0246 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,125.7196,128.9249,135.6212,166.4322 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,761.4853,742.7956,705.7116,575.7518 "nekRS - Input: TurboPipe Periodic (FLOP/s)",HIB,821462000000,786258000000,740247000000,659554333333 "OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (ms)",LIB,49.98,51.29,54.80,58.67 "OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (FPS)",HIB,959.16,934.71,875.39,817.27 "TensorFlow - Device: CPU - Batch Size: 256 - Model: ResNet-50 (images/sec)",HIB,109.13,105.91,105.01,95.67 "GPAW - Input: Carbon Nanotube (sec)",LIB,23.151,23.373,24.598,26.308 "NAS Parallel Benchmarks - Test / Class: CG.C (Mop/s)",HIB,80225.01,81179.00,79784.15,71662.28 "7-Zip Compression - Test: Compression Rating (MIPS)",HIB,923176,893433,879430,824926 "OpenVKL - Benchmark: vklBenchmark ISPC (Items / Sec)",HIB,1325,1317,1325,1212 "oneDNN - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,2275.86,2325.71,2371.78,2471.57 "NAS Parallel Benchmarks - Test / Class: LU.C (Mop/s)",HIB,489164.65,489995.20,466769.54,454360.62 "Intel Open Image Denoise - Run: RTLightmap.hdr.4096x4096 (Images / Sec)",HIB,1.65,1.63,1.64,1.54 "Intel Open Image Denoise - Run: RT.hdr_alb_nrm.3840x2160 (Images / Sec)",HIB,3.52,3.44,3.47,3.29 "Rodinia - Test: OpenMP Streamcluster (sec)",LIB,6.001,6.285,6.018,6.409 "oneDNN - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,2344.29,2438.00,2375.45,2479.62 "Kvazaar - Video Input: Bosphorus 4K - Video Preset: Very Fast (FPS)",HIB,73.44,75.35,73.04,71.41 "Apache Cassandra - Test: Writes (Op/s)",HIB,251793,243603,240854,246882 "GROMACS - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day)",HIB,18.706,18.677,18.678,17.940 "oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,0.446930,0.463454,0.465796,0.465059 "OpenVINO - Model: Person Detection FP32 - Device: CPU (FPS)",HIB,42.95,43.18,42.22,41.44 "OpenVINO - Model: Person Detection FP32 - Device: CPU (ms)",LIB,1110.68,1104.59,1129.01,1150.54 "Xmrig - Variant: Monero - Hash Count: 1M (H/s)",HIB,104604.6,102599.6,101953.5,100446.2 "OpenVINO - Model: Person Detection FP16 - Device: CPU (FPS)",HIB,42.98,42.94,42.59,41.33 "OpenVINO - Model: Person Detection FP16 - Device: CPU (ms)",LIB,1109.45,1110.44,1119.79,1153.70 "Timed GDB GNU Debugger Compilation - Time To Compile (sec)",LIB,41.709,42.412,42.409,43.245 "Timed Gem5 Compilation - Time To Compile (sec)",LIB,139.238,134.373,136.793,134.695 "CockroachDB - Workload: KV, 50% Reads - Concurrency: 512 (ops/s)",HIB,47621.9,49102.7,47596.6,47428.0 "Embree - Binary: Pathtracer ISPC - Model: Asian Dragon (FPS)",HIB,213.7507,214.3093,217.4060,221.2898 "CockroachDB - Workload: KV, 10% Reads - Concurrency: 512 (ops/s)",HIB,35970.0,35993.1,34832.9,35742.3 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (FPS)",HIB,119606.21,122938.23,123571.68,121027.25 "Timed Linux Kernel Compilation - Build: defconfig (sec)",LIB,25.501,25.407,25.528,24.747 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (FPS)",HIB,147769.26,147717.32,152292.39,151213.17 "Rodinia - Test: OpenMP CFD Solver (sec)",LIB,6.050,6.074,5.970,6.152 "Blender - Blend File: BMW27 - Compute: CPU-Only (sec)",LIB,8.58,8.42,8.34,8.33 "CockroachDB - Workload: KV, 10% Reads - Concurrency: 1024 (ops/s)",HIB,36846.9,35776.8,36685.7,36329.6 "Embree - Binary: Pathtracer ISPC - Model: Crown (FPS)",HIB,182.4498,184.7346,185.4907,187.6107 "Kvazaar - Video Input: Bosphorus 4K - Video Preset: Ultra Fast (FPS)",HIB,77.83,77.30,76.84,75.86 "OSPRay - Benchmark: particle_volume/scivis/real_time (Items/sec)",HIB,42.7970,42.9999,43.8442,43.2396 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,84.2470,84.2657,84.1546,82.2613 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,84.3506,84.4822,84.2115,82.4869 "CockroachDB - Workload: KV, 60% Reads - Concurrency: 512 (ops/s)",HIB,52330.1,51748.8,52515.2,51275.1 "libavif avifenc - Encoder Speed: 10, Lossless (sec)",LIB,4.241,4.337,4.252,4.250 "OSPRay - Benchmark: particle_volume/ao/real_time (Items/sec)",HIB,43.7061,43.0316,43.9700,43.3575 "nginx - Connections: 500 (Reqs/sec)",HIB,201032.06,198858.66,197081.98,196805.30 "DaCapo Benchmark - Java Test: H2 (msec)",LIB,4802,4832,4731,4830 "CockroachDB - Workload: KV, 50% Reads - Concurrency: 1024 (ops/s)",HIB,47465.5,48449.0,47498.1,47593.9 "libavif avifenc - Encoder Speed: 6 (sec)",LIB,2.459,2.411,2.420,2.435 "Kvazaar - Video Input: Bosphorus 4K - Video Preset: Medium (FPS)",HIB,62.56,62.23,61.81,61.40 "7-Zip Compression - Test: Decompression Rating (MIPS)",HIB,1181435,1171627,1159901,1177484 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (ms)",LIB,0.55,0.55,0.55,0.54 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1964.2730,1965.5606,1954.1227,1930.3277 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,48.7673,48.7431,48.9982,49.6278 "Timed LLVM Compilation - Build System: Ninja (sec)",LIB,75.655,75.440,75.725,76.747 "OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (ms)",LIB,6.48,6.45,6.49,6.56 "OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (FPS)",HIB,7394.65,7425.10,7389.00,7306.47 "Timed Node.js Compilation - Time To Compile (sec)",LIB,101.465,101.941,101.149,102.776 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inferences/min)",HIB,254,255,257,253 "OSPRay - Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time (Items/sec)",HIB,53.7748,54.4083,54.5087,54.6054 "simdjson - Throughput Test: TopTweet (GB/s)",HIB,6.59,6.49,6.57,6.55 "DaCapo Benchmark - Java Test: Jython (msec)",LIB,3380,3329,3369,3345 "Blender - Blend File: Barbershop - Compute: CPU-Only (sec)",LIB,81.03,80.37,80.18,79.93 "Timed Linux Kernel Compilation - Build: allmodconfig (sec)",LIB,147.147,145.410,147.377,145.766 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,1133.2823,1133.1821,1136.8544,1148.4964 "libavif avifenc - Encoder Speed: 0 (sec)",LIB,63.247,63.246,62.961,63.803 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,1133.4774,1135.1845,1137.5119,1148.3278 "CockroachDB - Workload: KV, 60% Reads - Concurrency: 1024 (ops/s)",HIB,52573.3,51959.5,52559.0,52626.4 "Timed Apache Compilation - Time To Compile (sec)",LIB,20.461,20.480,20.589,20.720 "NWChem - Input: C240 Buckyball (sec)",LIB,1537.1,1531,1519.6,1517.9 "CockroachDB - Workload: MoVR - Concurrency: 512 (ops/s)",HIB,948.5,949.6,960.3,954.7 "Timed Godot Game Engine Compilation - Time To Compile (sec)",LIB,34.032,33.616,33.905,33.671 "OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (FPS)",HIB,11018.37,11066.16,11108.16,11150.32 "OpenRadioss - Model: Bird Strike on Windshield (sec)",LIB,216.88,218.22,219.45,219.10 "OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (ms)",LIB,4.35,4.33,4.31,4.30 "Blender - Blend File: Classroom - Compute: CPU-Only (sec)",LIB,20.92,20.76,20.68,20.71 "libavif avifenc - Encoder Speed: 6, Lossless (sec)",LIB,5.287,5.286,5.270,5.330 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,615.4474,611.2926,614.6105,608.5336 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,155.4797,156.5374,155.8191,157.2164 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (ms)",LIB,0.97,0.98,0.98,0.97 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1195.9102,1201.1391,1201.9839,1190.5286 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,80.0790,79.7139,79.6865,80.4399 "OpenRadioss - Model: INIVOL and Fluid Structure Interaction Drop Container (sec)",LIB,81.57,81.15,81.09,80.81 "OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (FPS)",HIB,9867.41,9900.47,9931.49,9959.38 "Xmrig - Variant: Wownero - Hash Count: 1M (H/s)",HIB,126465.6,127226.6,127081.2,126057.7 "OpenVINO - Model: Face Detection FP16 - Device: CPU (FPS)",HIB,101.74,102.01,101.26,101.08 "OpenVINO - Model: Face Detection FP16 - Device: CPU (ms)",LIB,470.98,469.43,472.84,473.69 "ACES DGEMM - Sustained Floating-Point Rate (GFLOP/s)",HIB,70.407733,70.613775,71.010323,70.898312 "OpenRadioss - Model: Bumper Beam (sec)",LIB,79.86,79.70,79.20,79.62 "OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (ms)",LIB,4.85,4.83,4.82,4.81 "OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (FPS)",HIB,9038.47,9063.84,9113.11,9081.73 "ASTC Encoder - Preset: Exhaustive (MT/s)",HIB,11.7250,11.7637,11.8090,11.8207 "Stargate Digital Audio Workstation - Sample Rate: 192000 - Buffer Size: 1024 (Render Ratio)",HIB,2.829061,2.806190,2.811555,2.824814 "OSPRay - Benchmark: particle_volume/pathtracer/real_time (Items/sec)",HIB,229.269,230.282,228.581,230.440 "simdjson - Throughput Test: LargeRandom (GB/s)",HIB,1.25,1.25,1.25,1.24 "OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (ms)",LIB,5.30,5.28,5.26,5.28 "OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (FPS)",HIB,19171.51,19254.08,19278.93,19314.04 "CockroachDB - Workload: MoVR - Concurrency: 1024 (ops/s)",HIB,953.8,949.5,946.9,952.7 "simdjson - Throughput Test: PartialTweets (GB/s)",HIB,5.65,5.67,5.66,5.69 "OSPRay - Benchmark: gravity_spheres_volume/dim_512/scivis/real_time (Items/sec)",HIB,43.1262,43.3287,43.4310,43.2899 "Timed MPlayer Compilation - Time To Compile (sec)",LIB,7.777,7.755,7.808,7.773 "OSPRay - Benchmark: gravity_spheres_volume/dim_512/ao/real_time (Items/sec)",HIB,43.9775,43.9969,44.2302,44.2716 "libavif avifenc - Encoder Speed: 2 (sec)",LIB,34.848,34.909,34.687,34.874 "OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (ms)",LIB,9.95,9.91,9.90,9.89 "miniBUDE - Implementation: OpenMP - Input Deck: BM2 (GFInst/s)",HIB,8640.310,8666.980,8615.967,8651.924 "miniBUDE - Implementation: OpenMP - Input Deck: BM2 (Billion Interactions/s)",HIB,345.612,346.679,344.639,346.077 "Build2 - Time To Compile (sec)",LIB,49.917,49.800,49.871,50.084 "ASTC Encoder - Preset: Thorough (MT/s)",HIB,106.5663,106.8542,107.1108,106.5095 "OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (ms)",LIB,250.34,249.12,249.26,250.49 "OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (FPS)",HIB,191.43,192.30,192.25,191.29 "Timed Mesa Compilation - Time To Compile (sec)",LIB,20.117,20.205,20.107,20.157 "NAMD - ATPase Simulation - 327,506 Atoms (days/ns)",LIB,0.12783,0.12759,0.12768,0.12820 "simdjson - Throughput Test: DistinctUserID (GB/s)",HIB,6.86,6.84,6.86,6.83 "Stargate Digital Audio Workstation - Sample Rate: 96000 - Buffer Size: 1024 (Render Ratio)",HIB,4.345890,4.354556,4.351402,4.364767 "Timed PHP Compilation - Time To Compile (sec)",LIB,44.519,44.608,44.583,44.698 "Liquid-DSP - Threads: 256 - Buffer Length: 256 - Filter Length: 57 (samples/s)",HIB,10347000000,10340000000,10337666667,10340333333 "Liquid-DSP - Threads: 384 - Buffer Length: 256 - Filter Length: 57 (samples/s)",HIB,10347000000,10352666667,10349666667,10349000000 "simdjson - Throughput Test: Kostya (GB/s)",HIB,4.11,4.11,4.11,4.11 "CockroachDB - Workload: KV, 95% Reads - Concurrency: 1024 (ops/s)",HIB,64661.8,62029.8,58195.5,60137.3 "CockroachDB - Workload: KV, 95% Reads - Concurrency: 512 (ops/s)",HIB,64467.6,60769.7,64111.9,62666.5 "oneDNN - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,1968.70,2030.72,1982.15,2072.57 "oneDNN - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,3.95471,4.00938,3.99305,3.96488 "SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,251.769,241.369,227.898,221.161 "LuxCoreRender - Scene: Orange Juice - Acceleration: CPU (M samples/sec)",HIB,28.82,28.19,29.04,28.90 "LuxCoreRender - Scene: Danish Mood - Acceleration: CPU (M samples/sec)",HIB,9.69,9.62,9.56,9.49 "NAS Parallel Benchmarks - Test / Class: IS.D (Mop/s)",HIB,8491.01,7124.92,6675.71,5690.01 "High Performance Conjugate Gradient - (GFLOP/s)",HIB,86.8143,48.2945,45.0005,36.5411