RTX 3070 Compute AMD Ryzen 9 5900X 12-Core testing with a ASUS ROG CROSSHAIR VIII HERO (3402 BIOS) and NVIDIA GeForce RTX 3070 8GB on Ubuntu 20.04 via the Phoronix Test Suite. 1: Processor: AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (3402 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 1000GB Sabrent Rocket 4.0 Plus + 2000GB, Graphics: NVIDIA GeForce RTX 3070 8GB, Audio: NVIDIA Device 228b, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 20.04, Kernel: 5.8.0-48-generic (x86_64), Desktop: GNOME Shell 3.36.7, Display Server: X Server 1.20.9, Display Driver: NVIDIA 460.67, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.2.162, Vulkan: 1.2.155, Compiler: GCC 9.3.0 + CUDA 11.2, File-System: ext4, Screen Resolution: 3840x2160 2: Processor: AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (3402 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 1000GB Sabrent Rocket 4.0 Plus + 2000GB, Graphics: NVIDIA GeForce RTX 3070 8GB, Audio: NVIDIA Device 228b, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 20.04, Kernel: 5.8.0-48-generic (x86_64), Desktop: GNOME Shell 3.36.7, Display Server: X Server 1.20.9, Display Driver: NVIDIA 460.67, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.2.162, Vulkan: 1.2.155, Compiler: GCC 9.3.0 + CUDA 11.2, File-System: ext4, Screen Resolution: 3840x2160 3: Processor: AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (3402 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 1000GB Sabrent Rocket 4.0 Plus + 2000GB, Graphics: NVIDIA GeForce RTX 3070 8GB, Audio: NVIDIA Device 228b, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 20.04, Kernel: 5.8.0-48-generic (x86_64), Desktop: GNOME Shell 3.36.7, Display Server: X Server 1.20.9, Display Driver: NVIDIA 460.67, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.2.162, Vulkan: 1.2.155, Compiler: GCC 9.3.0 + CUDA 11.2, File-System: ext4, Screen Resolution: 3840x2160 VkFFT 1.1.1 Benchmark Score > Higher Is Better 1 . 32004 |=================================================================== 2 . 32323 |==================================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad GB/s > Higher Is Better 1 . 24.67 |==================================================================== 2 . 24.67 |==================================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction GB/s > Higher Is Better 1 . 325.67 |=================================================================== 2 . 325.80 |=================================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download GB/s > Higher Is Better 1 . 26.28 |==================================================================== 2 . 26.31 |==================================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback GB/s > Higher Is Better 1 . 26.40 |==================================================================== 2 . 26.39 |==================================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth GB/s > Higher Is Better 1 . 2120.56 |================================================================== 2 . 2131.28 |================================================================== cl-mem 2017-01-13 Benchmark: Copy GB/s > Higher Is Better 1 . 297.6 |==================================================================== 2 . 296.9 |==================================================================== cl-mem 2017-01-13 Benchmark: Read GB/s > Higher Is Better 1 . 393.6 |==================================================================== 2 . 393.2 |==================================================================== cl-mem 2017-01-13 Benchmark: Write GB/s > Higher Is Better 1 . 380.2 |==================================================================== 2 . 379.9 |==================================================================== ViennaCL 1.7.1 Test: CPU BLAS - sCOPY GB/s > Higher Is Better 1 . 62.0 |=================================================================== 2 . 63.4 |===================================================================== ViennaCL 1.7.1 Test: CPU BLAS - sAXPY GB/s > Higher Is Better 1 . 94.0 |===================================================================== 2 . 92.8 |==================================================================== ViennaCL 1.7.1 Test: CPU BLAS - sDOT GB/s > Higher Is Better 1 . 141 |====================================================================== 2 . 139 |===================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dCOPY GB/s > Higher Is Better 1 . 23.2 |===================================================================== 2 . 22.6 |=================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dAXPY GB/s > Higher Is Better 1 . 34.5 |===================================================================== 2 . 33.4 |=================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dDOT GB/s > Higher Is Better 1 . 44.3 |===================================================================== 2 . 43.5 |==================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N GB/s > Higher Is Better 1 . 76.5 |===================================================================== 2 . 77.0 |===================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T GB/s > Higher Is Better 1 . 81.3 |==================================================================== 2 . 81.9 |===================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY GB/s > Higher Is Better 1 . 293 |====================================================================== 2 . 293 |====================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY GB/s > Higher Is Better 1 . 358 |====================================================================== 2 . 357 |====================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT GB/s > Higher Is Better 1 . 325 |====================================================================== 2 . 324 |====================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY GB/s > Higher Is Better 1 . 365 |====================================================================== 2 . 364 |====================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY GB/s > Higher Is Better 1 . 396 |====================================================================== 2 . 395 |====================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dDOT GB/s > Higher Is Better 1 . 397 |====================================================================== 2 . 396 |====================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N GB/s > Higher Is Better 1 . 222 |====================================================================== 2 . 220 |===================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T GB/s > Higher Is Better 1 . 334 |====================================================================== 2 . 332 |====================================================================== clpeak OpenCL Test: Global Memory Bandwidth GBPS > Higher Is Better 1 . 389.57 |=================================================================== 2 . 389.61 |=================================================================== Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Double Precision GFLOPS > Higher Is Better 1 . 295.11 |================================================================== 2 . 299.65 |=================================================================== Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Single Precision GFLOPS > Higher Is Better 1 . 22081.79 |================================================================= 2 . 21965.66 |================================================================= SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D GFLOPS > Higher Is Better 1 . 218.44 |=================================================================== 2 . 218.61 |=================================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP GFLOPS > Higher Is Better 1 . 1134.99 |================================================================== 2 . 1133.82 |================================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N GFLOPS > Higher Is Better 1 . 3806.57 |================================================================== 2 . 3769.31 |================================================================= SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops GFLOPS > Higher Is Better 1 . 23117.8 |================================================================== 2 . 23179.0 |================================================================== clpeak OpenCL Test: Single-Precision Float GFLOPS > Higher Is Better 1 . 20099.75 |================================================================= 2 . 19991.73 |================================================================= clpeak OpenCL Test: Double-Precision Double GFLOPS > Higher Is Better 1 . 360.90 |================================================================== 2 . 364.99 |=================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN GFLOPs/s > Higher Is Better 1 . 54.7 |===================================================================== 2 . 53.5 |=================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT GFLOPs/s > Higher Is Better 1 . 53.4 |===================================================================== 2 . 52.7 |==================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN GFLOPs/s > Higher Is Better 1 . 57.0 |===================================================================== 2 . 55.8 |==================================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT GFLOPs/s > Higher Is Better 1 . 55.3 |===================================================================== 2 . 54.5 |==================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN GFLOPs/s > Higher Is Better 1 . 342 |====================================================================== 2 . 338 |===================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT GFLOPs/s > Higher Is Better 1 . 343 |====================================================================== 2 . 340 |===================================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN GFLOPs/s > Higher Is Better 1 . 342 |====================================================================== 2 . 336 |===================================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash GHash/s > Higher Is Better 1 . 25.47 |==================================================================== 2 . 25.49 |==================================================================== Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Integer GIOPS > Higher Is Better 1 . 11433.74 |================================================================= 2 . 11336.97 |================================================================ clpeak OpenCL Test: Integer Compute INT GIOPS > Higher Is Better 1 . 10264.28 |================================================================= 2 . 10202.39 |================================================================= Hashcat 6.1.1 Benchmark: MD5 H/s > Higher Is Better 1 . 38778833333 |============================================================== 2 . 38839033333 |============================================================== Hashcat 6.1.1 Benchmark: SHA1 H/s > Higher Is Better 1 . 13120133333 |============================================================== 2 . 13144266667 |============================================================== Hashcat 6.1.1 Benchmark: 7-Zip H/s > Higher Is Better 1 . 686733 |=================================================================== 2 . 686700 |=================================================================== Hashcat 6.1.1 Benchmark: SHA-512 H/s > Higher Is Better 1 . 1664800000 |=============================================================== 2 . 1669566667 |=============================================================== Hashcat 6.1.1 Benchmark: TrueCrypt RIPEMD160 + XTS H/s > Higher Is Better 1 . 501033 |=================================================================== 2 . 502833 |=================================================================== IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom M samples/s > Higher Is Better 1 . 12.92 |==================================================================== 2 . 12.88 |==================================================================== IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar M samples/s > Higher Is Better 1 . 37.26 |==================================================================== 2 . 37.16 |==================================================================== LuxCoreRender OpenCL 2.3 Scene: DLSC M samples/sec > Higher Is Better 1 . 7.97 |===================================================================== 2 . 7.94 |===================================================================== LuxCoreRender OpenCL 2.3 Scene: Food M samples/sec > Higher Is Better 1 . 3.39 |===================================================================== 2 . 3.39 |===================================================================== LuxCoreRender OpenCL 2.3 Scene: LuxCore Benchmark M samples/sec > Higher Is Better 1 . 6.51 |===================================================================== 2 . 6.50 |===================================================================== LuxCoreRender OpenCL 2.3 Scene: Rainbow Colors and Prism M samples/sec > Higher Is Better 1 . 19.18 |==================================================================== 2 . 19.19 |==================================================================== LeelaChessZero 0.26 Backend: OpenCL Nodes Per Second > Higher Is Better 1 . 28914 |==================================================================== 2 . 29117 |==================================================================== GROMACS 2020.3 Water Benchmark Ns Per Day > Higher Is Better 1 . 8.138 |==================================================================== 2 . 8.083 |==================================================================== FAHBench 2.3.2 Ns Per Day > Higher Is Better 1 . 267.09 |=================================================================== 2 . 265.83 |=================================================================== MandelGPU 1.3pts1 OpenCL Device: GPU Samples/sec > Higher Is Better 1 . 319970658.9 |============================================================== 2 . 319688588.0 |============================================================== OctaneBench 2020.1 Total Score Score > Higher Is Better 1 . 410.51 |=================================================================== 2 . 411.11 |=================================================================== Chaos Group V-RAY 5 Mode: NVIDIA CUDA GPU vpaths > Higher Is Better 1 . 1342 |===================================================================== 2 . 1337 |===================================================================== Chaos Group V-RAY 5 Mode: NVIDIA RTX GPU vrays > Higher Is Better 1 . 1713 |===================================================================== 2 . 1710 |===================================================================== NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms days/ns < Lower Is Better 1 . 0.13273 |================================================================= 2 . 0.13388 |================================================================== VkResample 1.0 Upscale: 2x - Precision: Double ms < Lower Is Better 1 . 220.45 |=================================================================== 2 . 221.04 |=================================================================== VkResample 1.0 Upscale: 2x - Precision: Single ms < Lower Is Better 1 . 17.49 |==================================================================== 2 . 17.53 |==================================================================== ArrayFire 3.7 Test: Conjugate Gradient OpenCL ms < Lower Is Better 1 . 2.086 |==================================================================== 2 . 2.094 |==================================================================== FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL ms < Lower Is Better 1 . 10.48 |==================================================================== 2 . 10.50 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better 1 . 12.85 |================================================================ 2 . 13.56 |==================================================================== NCNN 20201218 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better 1 . 4.39 |===================================================================== 2 . 4.35 |==================================================================== NCNN 20201218 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better 1 . 4.22 |===================================================================== 2 . 4.24 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better 1 . 4.85 |==================================================================== 2 . 4.92 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better 1 . 4.05 |==================================================================== 2 . 4.10 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better 1 . 5.58 |===================================================================== 2 . 5.62 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better 1 . 1.84 |=================================================================== 2 . 1.90 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better 1 . 13.27 |==================================================================== 2 . 13.17 |=================================================================== NCNN 20201218 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better 1 . 55.71 |==================================================================== 2 . 55.89 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better 1 . 13.95 |==================================================================== 2 . 14.03 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better 1 . 11.08 |=================================================================== 2 . 11.22 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better 1 . 24.47 |=================================================================== 2 . 24.75 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better 1 . 22.20 |================================================================ 2 . 23.73 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better 1 . 14.49 |================================================================ 2 . 15.45 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better 1 . 16.75 |==================================================================== 2 . 16.87 |==================================================================== RealSR-NCNN 20200818 Scale: 4x - TAA: No Seconds < Lower Is Better 1 . 8.438 |==================================================================== 2 . 8.427 |==================================================================== 3 . 8.437 |==================================================================== RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Seconds < Lower Is Better 1 . 50.06 |==================================================================== 2 . 49.99 |==================================================================== 3 . 50.18 |==================================================================== Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes Seconds < Lower Is Better 1 . 4.297 |==================================================================== 2 . 4.303 |==================================================================== 3 . 4.321 |==================================================================== Betsy GPU Compressor 1.1 Beta Codec: ETC1 - Quality: Highest Seconds < Lower Is Better 1 . 4.309 |==================================================================== 2 . 4.300 |==================================================================== Betsy GPU Compressor 1.1 Beta Codec: ETC2 RGB - Quality: Highest Seconds < Lower Is Better 1 . 6.039 |==================================================================== 2 . 6.051 |==================================================================== RedShift Demo 3.0 Seconds < Lower Is Better 1 . 228 |====================================================================== 2 . 228 |====================================================================== Rodinia 3.1 Test: OpenCL Particle Filter Seconds < Lower Is Better 1 . 5.958 |=================================================================== 2 . 6.016 |==================================================================== Blender 2.92 Blend File: BMW27 - Compute: CUDA Seconds < Lower Is Better 1 . 29.07 |==================================================================== 2 . 29.03 |==================================================================== Blender 2.92 Blend File: Classroom - Compute: CUDA Seconds < Lower Is Better 1 . 76.10 |==================================================================== 2 . 76.49 |==================================================================== Blender 2.92 Blend File: Fishy Cat - Compute: CUDA Seconds < Lower Is Better 1 . 54.20 |==================================================================== 2 . 54.44 |==================================================================== Blender 2.92 Blend File: Barbershop - Compute: CUDA Seconds < Lower Is Better 1 . 509.33 |=================================================================== 2 . 508.38 |=================================================================== Blender 2.92 Blend File: BMW27 - Compute: NVIDIA OptiX Seconds < Lower Is Better 1 . 16.11 |==================================================================== 2 . 16.17 |==================================================================== Blender 2.92 Blend File: Classroom - Compute: NVIDIA OptiX Seconds < Lower Is Better 1 . 48.17 |==================================================================== 2 . 48.26 |==================================================================== Blender 2.92 Blend File: Fishy Cat - Compute: NVIDIA OptiX Seconds < Lower Is Better 1 . 35.70 |==================================================================== 2 . 35.84 |==================================================================== Blender 2.92 Blend File: Barbershop - Compute: NVIDIA OptiX Seconds < Lower Is Better 1 . 465.14 |=================================================================== 2 . 464.01 |=================================================================== Blender 2.92 Blend File: Pabellon Barcelona - Compute: CUDA Seconds < Lower Is Better 1 . 190.29 |=================================================================== 2 . 190.98 |=================================================================== Blender 2.92 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX Seconds < Lower Is Better 1 . 76.77 |==================================================================== 2 . 77.16 |====================================================================