mighty-3090x2-2 AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 DESIGNARE (F5 BIOS) and NVIDIA GeForce RTX 3090 24GB on Ubuntu 20.04 via the Phoronix Test Suite. RTX 3090 x 2: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 DESIGNARE (F5 BIOS), Chipset: AMD Starship/Matisse, Memory: 256GB, Disk: 2048GB ADATA SX8200PNP + 3 x 2048GB SPCC M.2 PCIe SSD + 5 x 14001GB Western Digital WUH721414AL, Graphics: NVIDIA GeForce RTX 3090 24GB, Audio: NVIDIA Device 1aef, Network: 2 x Intel I210 + Intel Wi-Fi 6 AX200 OS: Ubuntu 20.04, Kernel: 5.15.0-67-generic (x86_64), Display Server: X Server 1.20.11, Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 11.6.134, Vulkan: 1.3.194, Compiler: GCC 9.4.0 + CUDA 11.6, File-System: btrfs, Screen Resolution: 1024x768 Hashcat 6.2.4 Benchmark: MD5 H/s > Higher Is Better RTX 3090 x 2 . 100686168750 |================================================== Hashcat 6.2.4 Benchmark: SHA1 H/s > Higher Is Better RTX 3090 x 2 . 42287666667 |=================================================== Hashcat 6.2.4 Benchmark: 7-Zip H/s > Higher Is Better RTX 3090 x 2 . 2145400 |======================================================= Hashcat 6.2.4 Benchmark: SHA-512 H/s > Higher Is Better RTX 3090 x 2 . 6099166667 |==================================================== Hashcat 6.2.4 Benchmark: TrueCrypt RIPEMD160 + XTS H/s > Higher Is Better RTX 3090 x 2 . 1584767 |======================================================= Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Integer GIOPS > Higher Is Better RTX 3090 x 2 . 17461.90 |====================================================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Integer GIOPS > Higher Is Better RTX 3090 x 2 . 16566.76 |====================================================== Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Double Precision GFLOPS > Higher Is Better RTX 3090 x 2 . 512.43 |======================================================== Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Single Precision GFLOPS > Higher Is Better RTX 3090 x 2 . 36828.07 |====================================================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Half Precision GFLOPS > Higher Is Better RTX 3090 x 2 . 36773.91 |====================================================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Double Precision GFLOPS > Higher Is Better RTX 3090 x 2 . 493.23 |======================================================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Single Precision GFLOPS > Higher Is Better RTX 3090 x 2 . 34440.08 |====================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth cl-mem 2017-01-13 Benchmark: Copy GB/s > Higher Is Better RTX 3090 x 2 . 360.3 |========================================================= cl-mem 2017-01-13 Benchmark: Read GB/s > Higher Is Better RTX 3090 x 2 . 795.6 |========================================================= cl-mem 2017-01-13 Benchmark: Write GB/s > Higher Is Better RTX 3090 x 2 . 749.3 |========================================================= RedShift Demo 3.0 Seconds < Lower Is Better FAHBench 2.3.2 Ns Per Day > Higher Is Better RTX 3090 x 2 . 334.54 |======================================================== clpeak 1.1.2 OpenCL Test: Integer Compute INT GIOPS > Higher Is Better RTX 3090 x 2 . 17621.66 |====================================================== clpeak 1.1.2 OpenCL Test: Single-Precision Float GFLOPS > Higher Is Better RTX 3090 x 2 . 34570.34 |====================================================== clpeak 1.1.2 OpenCL Test: Double-Precision Double GFLOPS > Higher Is Better RTX 3090 x 2 . 642.61 |======================================================== clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth GBPS > Higher Is Better RTX 3090 x 2 . 816.35 |======================================================== LeelaChessZero 0.28 Backend: OpenCL Nodes Per Second > Higher Is Better RTX 3090 x 2 . 19173 |========================================================= Rodinia 3.1 Test: OpenCL Particle Filter Seconds < Lower Is Better RTX 3090 x 2 . 3.898 |========================================================= ArrayFire 3.7 Test: Conjugate Gradient OpenCL ms < Lower Is Better RTX 3090 x 2 . 1.501 |========================================================= LuxCoreRender 2.6 Scene: DLSC - Acceleration: GPU M samples/sec > Higher Is Better RTX 3090 x 2 . 27.82 |========================================================= LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: GPU M samples/sec > Higher Is Better RTX 3090 x 2 . 19.41 |========================================================= LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: GPU M samples/sec > Higher Is Better RTX 3090 x 2 . 22.61 |========================================================= LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: GPU M samples/sec > Higher Is Better RTX 3090 x 2 . 21.48 |========================================================= LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: GPU M samples/sec > Higher Is Better RTX 3090 x 2 . 61.65 |========================================================= FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL ms < Lower Is Better RTX 3090 x 2 . 6.326 |========================================================= ViennaCL 1.7.1 Test: CPU BLAS - sCOPY GB/s > Higher Is Better RTX 3090 x 2 . 825 |=========================================================== ViennaCL 1.7.1 Test: CPU BLAS - sAXPY GB/s > Higher Is Better RTX 3090 x 2 . 764 |=========================================================== ViennaCL 1.7.1 Test: CPU BLAS - sDOT GB/s > Higher Is Better RTX 3090 x 2 . 617 |=========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dCOPY GB/s > Higher Is Better RTX 3090 x 2 . 1753 |========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dAXPY GB/s > Higher Is Better RTX 3090 x 2 . 1447 |========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dDOT GB/s > Higher Is Better RTX 3090 x 2 . 1130 |========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N GB/s > Higher Is Better RTX 3090 x 2 . 42.2 |========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T GB/s > Higher Is Better RTX 3090 x 2 . 717 |=========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN GFLOPs/s > Higher Is Better RTX 3090 x 2 . 106 |=========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN GFLOPs/s > Higher Is Better RTX 3090 x 2 . 111 |=========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT GFLOPs/s > Higher Is Better RTX 3090 x 2 . 110 |=========================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT GFLOPs/s > Higher Is Better RTX 3090 x 2 . 106 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY GB/s > Higher Is Better RTX 3090 x 2 . 361 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY GB/s > Higher Is Better RTX 3090 x 2 . 493 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT GB/s > Higher Is Better RTX 3090 x 2 . 365 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY GB/s > Higher Is Better RTX 3090 x 2 . 599 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY GB/s > Higher Is Better RTX 3090 x 2 . 714 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dDOT GB/s > Higher Is Better RTX 3090 x 2 . 648 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N GB/s > Higher Is Better RTX 3090 x 2 . 235 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T GB/s > Higher Is Better RTX 3090 x 2 . 370 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN GFLOPs/s > Higher Is Better RTX 3090 x 2 . 588 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT GFLOPs/s > Higher Is Better RTX 3090 x 2 . 590 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN GFLOPs/s > Higher Is Better RTX 3090 x 2 . 585 |=========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT GFLOPs/s > Higher Is Better RTX 3090 x 2 . 587 |=========================================================== GROMACS 2023 Implementation: NVIDIA CUDA GPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 100 Milli-Seconds < Lower Is Better RTX 3090 x 2 . 699.57 |======================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 200 Milli-Seconds < Lower Is Better RTX 3090 x 2 . 1381.71 |======================================================= Caffe 2020-02-13 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 1000 Milli-Seconds < Lower Is Better RTX 3090 x 2 . 6874.60 |======================================================= Caffe 2020-02-13 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 100 Milli-Seconds < Lower Is Better RTX 3090 x 2 . 2800.17 |======================================================= Caffe 2020-02-13 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 200 Milli-Seconds < Lower Is Better RTX 3090 x 2 . 5566.12 |======================================================= Caffe 2020-02-13 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 1000 Milli-Seconds < Lower Is Better RTX 3090 x 2 . 27981.1 |======================================================= NCNN 20220729 Target: Vulkan GPU ms < Lower Is Better PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL Examples Per Second > Higher Is Better MandelGPU 1.3pts1 OpenCL Device: GPU Samples/sec > Higher Is Better NeatBench 5 Acceleration: GPU FPS > Higher Is Better RTX 3090 x 2 . 3090 |==========================================================