epyc-7742-2p-september 2 x AMD EPYC 7742 64-Core testing with a AMD DAYTONA_X (RDY1006G BIOS) and llvmpipe on Ubuntu 20.10 via the Phoronix Test Suite. 1: Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1006G BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 20.10, Kernel: 5.4.0-42-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.1.5 (LLVM 10.0.1 256 bits), Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080 2: Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1006G BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 20.10, Kernel: 5.4.0-42-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.1.5 (LLVM 10.0.1 256 bits), Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080 3: Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1006G BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 20.10, Kernel: 5.4.0-42-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.1.5 (LLVM 10.0.1 256 bits), Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080 LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: 20k Atoms ns/day > Higher Is Better 1 . 1.777 |==================================================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better 2 . 1797890 |================================================================== NCNN 20200916 Target: CPU - Model: yolov4-tiny ms < Lower Is Better 1 . 58.26 |==================================================================== NCNN 20200916 Target: CPU - Model: resnet50 ms < Lower Is Better 1 . 70.99 |==================================================================== NCNN 20200916 Target: CPU - Model: alexnet ms < Lower Is Better 1 . 16.43 |==================================================================== NCNN 20200916 Target: CPU - Model: resnet18 ms < Lower Is Better 1 . 32.58 |==================================================================== NCNN 20200916 Target: CPU - Model: vgg16 ms < Lower Is Better 1 . 62.47 |==================================================================== NCNN 20200916 Target: CPU - Model: googlenet ms < Lower Is Better 1 . 81.76 |==================================================================== NCNN 20200916 Target: CPU - Model: blazeface ms < Lower Is Better 1 . 20.27 |==================================================================== NCNN 20200916 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better 1 . 65.30 |==================================================================== NCNN 20200916 Target: CPU - Model: mnasnet ms < Lower Is Better 1 . 50.81 |==================================================================== NCNN 20200916 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better 1 . 48.86 |==================================================================== NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better 1 . 50.90 |==================================================================== NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better 1 . 54.44 |==================================================================== NCNN 20200916 Target: CPU - Model: mobilenet ms < Lower Is Better 1 . 77.66 |==================================================================== NCNN 20200916 Target: CPU - Model: squeezenet ms < Lower Is Better 1 . 60.82 |==================================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better 2 . 764312 |=================================================================== Mobile Neural Network 2020-09-17 Model: inception-v3 ms < Lower Is Better 1 . 34.28 |==================================================================== Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 ms < Lower Is Better 1 . 9.770 |==================================================================== Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 ms < Lower Is Better 1 . 13.81 |==================================================================== Mobile Neural Network 2020-09-17 Model: resnet-v2-50 ms < Lower Is Better 1 . 34.33 |==================================================================== Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 ms < Lower Is Better 1 . 13.72 |==================================================================== Kripke 1.2.4 Throughput FoM > Higher Is Better 1 . 60938988 |================================================================= PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.338 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Only TPS > Higher Is Better 1 . 750301 |=================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 1.837 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 50 - Mode: Read Write TPS > Higher Is Better 1 . 27999 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 4.597 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 100 - Mode: Read Write TPS > Higher Is Better 1 . 22339 |==================================================================== AI Benchmark Alpha 0.1.2 Device AI Score Score > Higher Is Better 1 . 2663 |===================================================================== AI Benchmark Alpha 0.1.2 Device Training Score Score > Higher Is Better 1 . 932 |====================================================================== AI Benchmark Alpha 0.1.2 Device Inference Score Score > Higher Is Better 1 . 1731 |===================================================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better 2 . 374706 |=================================================================== Monte Carlo Simulations of Ionised Nebulae 2019-03-24 Input: Dust 2D tau100.0 Seconds < Lower Is Better 1 . 307 |=========================================================== 3 . 364 |====================================================================== Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better 2 . 1.69 |===================================================================== TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Microseconds < Lower Is Better 1 . 460906 |=================================================================== TensorFlow Lite 2020-08-23 Model: Inception V4 Microseconds < Lower Is Better 1 . 552858 |=================================================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Float Microseconds < Lower Is Better 1 . 40468.3 |================================================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Microseconds < Lower Is Better 1 . 41092.5 |================================================================== GROMACS 2020.1 Water Benchmark Ns Per Day > Higher Is Better 1 . 0.674 |==================================================================== TensorFlow Lite 2020-08-23 Model: SqueezeNet Microseconds < Lower Is Better 1 . 56306.6 |================================================================== Timed LLVM Compilation 10.0 Time To Compile Seconds < Lower Is Better 1 . 198.37 |=================================================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better 2 . 188017 |=================================================================== Zstd Compression 1.4.5 Compression Level: 3 MB/s > Higher Is Better 1 . 8608.1 |=================================================================== 3 . 8514.7 |================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 5.780 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write TPS > Higher Is Better 1 . 43853 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.310 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only TPS > Higher Is Better 1 . 818255 |=================================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better 2 . 153644 |=================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 2.024 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write TPS > Higher Is Better 1 . 49824 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 1.029 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write TPS > Higher Is Better 1 . 49603 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.094 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 100 - Mode: Read Only TPS > Higher Is Better 1 . 1060481 |================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 13.44 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Write TPS > Higher Is Better 1 . 18693 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.063 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1000 - Clients: 50 - Mode: Read Only TPS > Higher Is Better 1 . 787959 |=================================================================== LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: Rhodopsin Protein ns/day > Higher Is Better 1 . 2.858 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.173 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Only TPS > Higher Is Better 1 . 2916829 |================================================================== InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 val/sec > Higher Is Better 1 . 946615.4 |================================================================= Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better 2 . 40.15 |==================================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better 2 . 77357 |==================================================================== perf-bench Benchmark: Futex Lock-Pi ops/sec > Higher Is Better 1 . 43 |======================================================================= 3 . 43 |======================================================================= InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 val/sec > Higher Is Better 1 . 1309312.3 |================================================================ InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 val/sec > Higher Is Better 1 . 1323652.8 |================================================================ perf-bench Benchmark: Memcpy 1MB GB/sec > Higher Is Better 1 . 9.352837 |=============================================================== 3 . 9.650576 |================================================================= TensorFlow Lite 2020-08-23 Model: NASNet Mobile Microseconds < Lower Is Better 1 . 130664 |=================================================================== Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better 2 . 55.05 |==================================================================== Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA Seconds < Lower Is Better 2 . 10.71 |==================================================================== eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis Seconds < Lower Is Better 1 . 35.51 |==================================================================== WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression Encode Time - Seconds < Lower Is Better 1 . 43.14 |==================================================================== LibRaw 0.20 Post-Processing Benchmark Mpix/sec > Higher Is Better 1 . 29.07 |==================================================================== Zstd Compression 1.4.5 Compression Level: 19 MB/s > Higher Is Better 1 . 125.9 |=================================================================== 3 . 127.3 |==================================================================== AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass Frames Per Second > Higher Is Better 1 . 0.27 |===================================================================== 3 . 0.27 |===================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.060 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only TPS > Higher Is Better 1 . 836075 |=================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.089 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only TPS > Higher Is Better 1 . 1132625 |================================================================== AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass Frames Per Second > Higher Is Better 1 . 3.41 |===================================================================== 3 . 3.36 |==================================================================== perf-bench Benchmark: Epoll Wait ops/sec > Higher Is Better 1 . 1055 |======================================================= 3 . 1321 |===================================================================== AOM AV1 2.0 Encoder Mode: Speed 6 Realtime Frames Per Second > Higher Is Better 1 . 19.78 |==================================================================== 3 . 19.70 |==================================================================== Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better 2 . 25.90 |==================================================================== perf-bench Benchmark: Futex Hash ops/sec > Higher Is Better 1 . 2678699 |================================================================== 3 . 2676681 |================================================================== OpenCV 4.4 Test: DNN - Deep Neural Network ms < Lower Is Better 1 . 5403 |===================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 76.00 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Write TPS > Higher Is Better 1 . 3303 |===================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 19.72 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write TPS > Higher Is Better 1 . 5081 |===================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.076 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only TPS > Higher Is Better 1 . 1371726 |================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better 1 . 8.506 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Write TPS > Higher Is Better 1 . 5880 |===================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better 1 . 0.049 |==================================================================== PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Only TPS > Higher Is Better 1 . 1028949 |================================================================== TNN 0.2.3 Target: CPU - Model: MobileNet v2 ms < Lower Is Better 1 . 332.48 |=================================================================== AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass Frames Per Second > Higher Is Better 1 . 2.12 |=================================================================== 3 . 2.17 |===================================================================== TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 ms < Lower Is Better 1 . 299.38 |=================================================================== WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless Encode Time - Seconds < Lower Is Better 1 . 20.60 |==================================================================== NAMD 2.14 ATPase Simulation - 327,506 Atoms days/ns < Lower Is Better 1 . 0.27852 |================================================================== 3 . 0.27652 |================================================================== Dolfyn 0.527 Computational Fluid Dynamics Seconds < Lower Is Better 2 . 20.30 |==================================================================== AOM AV1 2.0 Encoder Mode: Speed 8 Realtime Frames Per Second > Higher Is Better 1 . 32.90 |==================================================================== perf-bench Benchmark: Memset 1MB GB/sec > Higher Is Better 1 . 54.75 |==================================================================== 3 . 54.06 |=================================================================== perf-bench Benchmark: Sched Pipe ops/sec > Higher Is Better 1 . 330898 |=================================================================== 3 . 327426 |================================================================== WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression Encode Time - Seconds < Lower Is Better 1 . 9.268 |==================================================================== perf-bench Benchmark: Syscall Basic ops/sec > Higher Is Better 1 . 16777649 |================================================================= 3 . 16747582 |================================================================= System GZIP Decompression Seconds < Lower Is Better 1 . 3.553 |==================================================================== WebP Image Encode 1.1 Encode Settings: Quality 100 Encode Time - Seconds < Lower Is Better 1 . 2.813 |==================================================================== WebP Image Encode 1.1 Encode Settings: Default Encode Time - Seconds < Lower Is Better 1 . 1.752 |====================================================================