AMD EPYC 7601 Xmas 2020 AMD EPYC 7601 32-Core testing with a TYAN B8026T70AE24HR (V1.02.B10 BIOS) and llvmpipe on Ubuntu 20.04 via the Phoronix Test Suite. Run 1: Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD 17h, Memory: 126GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe OS: Ubuntu 20.04, Kernel: 5.4.0-53-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 20.0.8 (LLVM 10.0.0 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 Run 2: Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD 17h, Memory: 126GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe OS: Ubuntu 20.04, Kernel: 5.4.0-53-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 20.0.8 (LLVM 10.0.0 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 Run 3: Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD 17h, Memory: 126GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe OS: Ubuntu 20.04, Kernel: 5.4.0-53-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 20.0.8 (LLVM 10.0.0 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 CLOMP 1.2 Static OMP Speedup Speedup > Higher Is Better Run 1 . 57.1 |================================================================ Run 2 . 57.7 |================================================================= Run 3 . 57.8 |================================================================= Timed HMMer Search 3.3.1 Pfam Database Search Seconds < Lower Is Better Run 1 . 200.30 |=============================================================== Run 2 . 199.71 |=============================================================== Run 3 . 200.75 |=============================================================== Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA Seconds < Lower Is Better Run 1 . 15.02 |=============================================================== Run 2 . 15.15 |================================================================ Run 3 . 15.02 |=============================================================== simdjson 0.7.1 Throughput Test: Kostya GB/s > Higher Is Better Run 1 . 0.33 |================================================================= Run 2 . 0.33 |================================================================= Run 3 . 0.33 |================================================================= simdjson 0.7.1 Throughput Test: LargeRandom GB/s > Higher Is Better Run 1 . 0.28 |================================================================= Run 2 . 0.28 |================================================================= Run 3 . 0.28 |================================================================= simdjson 0.7.1 Throughput Test: PartialTweets GB/s > Higher Is Better Run 1 . 0.36 |================================================================= Run 2 . 0.36 |================================================================= Run 3 . 0.36 |================================================================= simdjson 0.7.1 Throughput Test: DistinctUserID GB/s > Higher Is Better Run 1 . 0.37 |================================================================= Run 2 . 0.37 |================================================================= Run 3 . 0.37 |================================================================= oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 5.34771 |============================================================== Run 2 . 4.49148 |==================================================== Run 3 . 4.33519 |================================================== oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 12.42 |================================================================ Run 2 . 11.77 |============================================================= Run 3 . 12.09 |============================================================== oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 2.67937 |============================================================== Run 2 . 2.68511 |============================================================== Run 3 . 2.66509 |============================================================== oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 3.56511 |============================================================== Run 2 . 3.55970 |============================================================== Run 3 . 3.57153 |============================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 18.51 |=============================================================== Run 2 . 18.68 |================================================================ Run 3 . 18.66 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 4.03281 |============================================================== Run 2 . 4.00713 |============================================================== Run 3 . 4.01827 |============================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 9.04439 |============================================================== Run 2 . 9.03893 |============================================================== Run 3 . 9.08767 |============================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 23.30 |================================================================ Run 2 . 22.46 |============================================================== Run 3 . 23.21 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 4.60248 |============================================================= Run 2 . 4.71473 |============================================================== Run 3 . 4.22841 |======================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 4.41314 |============================================================== Run 2 . 4.37097 |============================================================= Run 3 . 4.40049 |============================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 10732.73 |============================================================= Run 2 . 10747.50 |============================================================= Run 3 . 10314.22 |=========================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 3293.49 |============================================================ Run 2 . 3322.68 |============================================================= Run 3 . 3393.82 |============================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 10583.10 |============================================================ Run 2 . 10647.60 |============================================================ Run 3 . 10812.54 |============================================================= oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 3300.07 |============================================================ Run 2 . 3434.14 |============================================================== Run 3 . 3327.91 |============================================================ oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 1.71220 |============================================================= Run 2 . 1.74056 |============================================================== Run 3 . 1.66512 |=========================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better Run 1 . 10689.16 |=========================================================== Run 2 . 10915.65 |============================================================ Run 3 . 11077.90 |============================================================= oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better Run 1 . 3332.79 |============================================================= Run 2 . 3312.30 |============================================================ Run 3 . 3405.82 |============================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 1.78892 |============================================================== Run 2 . 1.77953 |============================================================== Run 3 . 1.79366 |============================================================== Coremark 1.0 CoreMark Size 666 - Iterations Per Second Iterations/Sec > Higher Is Better Run 1 . 879248.02 |============================================================ Run 2 . 879237.12 |============================================================ Run 3 . 876909.95 |============================================================ Timed FFmpeg Compilation 4.2.2 Time To Compile Seconds < Lower Is Better Run 1 . 39.09 |================================================================ Run 2 . 39.11 |================================================================ Run 3 . 39.19 |================================================================ Build2 0.13 Time To Compile Seconds < Lower Is Better Run 1 . 102.30 |=============================================================== Run 2 . 102.59 |=============================================================== Run 3 . 102.35 |=============================================================== Timed Eigen Compilation 3.3.9 Time To Compile Seconds < Lower Is Better Run 1 . 120.02 |=============================================================== Run 2 . 119.98 |=============================================================== Run 3 . 120.19 |=============================================================== Monkey Audio Encoding 3.99.6 WAV To APE Seconds < Lower Is Better Run 1 . 18.35 |================================================================ Run 2 . 18.33 |================================================================ Run 3 . 18.42 |================================================================ Opus Codec Encoding 1.3.1 WAV To Opus Encode Seconds < Lower Is Better Run 1 . 10.19 |================================================================ Run 2 . 10.22 |================================================================ Run 3 . 10.20 |================================================================ Node.js V8 Web Tooling Benchmark runs/s > Higher Is Better Run 1 . 6.78 |================================================================ Run 2 . 6.74 |================================================================ Run 3 . 6.85 |================================================================= SQLite Speedtest 3.30 Timed Time - Size 1,000 Seconds < Lower Is Better Run 1 . 90.12 |================================================================ Run 2 . 90.32 |================================================================ Run 3 . 90.11 |================================================================ NCNN 20201218 Target: CPU - Model: mobilenet ms < Lower Is Better Run 1 . 43.10 |================================================================ Run 2 . 41.84 |============================================================== Run 3 . 43.26 |================================================================ NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better Run 1 . 17.42 |========================================================= Run 2 . 19.42 |================================================================ Run 3 . 18.22 |============================================================ NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better Run 1 . 16.30 |============================================================ Run 2 . 17.48 |================================================================ Run 3 . 16.91 |============================================================== NCNN 20201218 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better Run 1 . 17.51 |================================================================ Run 2 . 17.35 |=============================================================== Run 3 . 16.94 |============================================================== NCNN 20201218 Target: CPU - Model: mnasnet ms < Lower Is Better Run 1 . 16.17 |================================================================ Run 2 . 15.76 |============================================================== Run 3 . 16.26 |================================================================ NCNN 20201218 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better Run 1 . 22.19 |============================================================= Run 2 . 22.24 |============================================================= Run 3 . 23.22 |================================================================ NCNN 20201218 Target: CPU - Model: blazeface ms < Lower Is Better Run 1 . 7.79 |================================================================ Run 2 . 7.89 |================================================================= Run 3 . 7.90 |================================================================= NCNN 20201218 Target: CPU - Model: googlenet ms < Lower Is Better Run 1 . 48.06 |============================================================== Run 2 . 46.99 |============================================================ Run 3 . 49.81 |================================================================ NCNN 20201218 Target: CPU - Model: vgg16 ms < Lower Is Better Run 1 . 100.72 |=============================================================== Run 2 . 94.33 |=========================================================== Run 3 . 88.55 |======================================================= NCNN 20201218 Target: CPU - Model: resnet18 ms < Lower Is Better Run 1 . 41.83 |=========================================================== Run 2 . 45.70 |================================================================ Run 3 . 43.64 |============================================================= NCNN 20201218 Target: CPU - Model: alexnet ms < Lower Is Better Run 1 . 33.20 |================================================================ Run 2 . 30.19 |========================================================== Run 3 . 31.92 |============================================================== NCNN 20201218 Target: CPU - Model: resnet50 ms < Lower Is Better Run 1 . 60.78 |================================================================ Run 2 . 59.24 |============================================================== Run 3 . 59.49 |=============================================================== NCNN 20201218 Target: CPU - Model: yolov4-tiny ms < Lower Is Better Run 1 . 57.99 |================================================================ Run 2 . 55.80 |============================================================== Run 3 . 56.52 |============================================================== NCNN 20201218 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better Run 1 . 46.68 |================================================================ Run 2 . 46.89 |================================================================ Run 3 . 44.81 |============================================================= NCNN 20201218 Target: CPU - Model: regnety_400m ms < Lower Is Better Run 1 . 117.02 |============================================================== Run 2 . 119.23 |=============================================================== Run 3 . 118.48 |=============================================================== WavPack Audio Encoding 5.3 WAV To WavPack Seconds < Lower Is Better Run 1 . 17.32 |================================================================ Run 2 . 17.31 |================================================================ Run 3 . 17.29 |================================================================