NVIDIA GPU Compute Benchmarks Benchmarks for a future article. RTX 3080 RBAR: 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 3080 10GB, Audio: NVIDIA GA102 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211 OS: Ubuntu 21.04, Kernel: 5.11.0-17-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Display Driver: NVIDIA 465.31, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 11.3.116, Vulkan: 1.2.168, Compiler: GCC 10.3.0 + CUDA 11.3, File-System: ext4, Screen Resolution: 3840x2160 Hashcat 6.1.1 Benchmark: MD5 H/s > Higher Is Better RTX 3080 RBAR . 58598366667 |================================================== Hashcat 6.1.1 Benchmark: SHA1 H/s > Higher Is Better RTX 3080 RBAR . 19164533333 |================================================== Hashcat 6.1.1 Benchmark: SHA-512 H/s > Higher Is Better RTX 3080 RBAR . 2753700000 |=================================================== Hashcat 6.1.1 Benchmark: 7-Zip H/s > Higher Is Better RTX 3080 RBAR . 995733 |======================================================= Hashcat 6.1.1 Benchmark: TrueCrypt RIPEMD160 + XTS H/s > Higher Is Better RTX 3080 RBAR . 720167 |======================================================= FAHBench 2.3.2 Ns Per Day > Higher Is Better RTX 3080 RBAR . 321.05 |======================================================= NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms days/ns < Lower Is Better RTX 3080 RBAR . 0.12157 |====================================================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Single Precision GFLOPS > Higher Is Better RTX 3080 RBAR . 29095.86 |===================================================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Double Precision GFLOPS > Higher Is Better RTX 3080 RBAR . 417.98 |======================================================= Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Half Precision GFLOPS > Higher Is Better RTX 3080 RBAR . 31706.66 |===================================================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Integer GIOPS > Higher Is Better RTX 3080 RBAR . 13924.20 |===================================================== OctaneBench 2020.1 Total Score Score > Higher Is Better RTX 3080 RBAR . 567.03 |======================================================= LuxCoreRender 2.5 Scene: DLSC - Acceleration: GPU M samples/sec > Higher Is Better RTX 3080 RBAR . 11.62 |======================================================== LuxCoreRender 2.5 Scene: Rainbow Colors and Prism - Acceleration: GPU M samples/sec > Higher Is Better RTX 3080 RBAR . 28.49 |======================================================== LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: GPU M samples/sec > Higher Is Better RTX 3080 RBAR . 9.98 |========================================================= LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: GPU M samples/sec > Higher Is Better RTX 3080 RBAR . 10.87 |======================================================== LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: GPU M samples/sec > Higher Is Better RTX 3080 RBAR . 8.03 |========================================================= ArrayFire 3.7 Test: BLAS OpenCL GFLOPS > Higher Is Better RTX 3080 RBAR . 7394.20 |====================================================== ArrayFire 3.7 Test: Conjugate Gradient OpenCL ms < Lower Is Better RTX 3080 RBAR . 1.563 |======================================================== clpeak OpenCL Test: Global Memory Bandwidth GBPS > Higher Is Better RTX 3080 RBAR . 659.40 |======================================================= clpeak OpenCL Test: Single-Precision Float GFLOPS > Higher Is Better RTX 3080 RBAR . 29422.68 |===================================================== clpeak OpenCL Test: Double-Precision Double GFLOPS > Higher Is Better RTX 3080 RBAR . 540.44 |======================================================= clpeak OpenCL Test: Integer Compute INT GIOPS > Higher Is Better RTX 3080 RBAR . 15383.91 |===================================================== vkpeak 20210424 fp32-scalar GFLOPS > Higher Is Better RTX 3080 RBAR . 17141.92 |===================================================== vkpeak 20210424 fp32-vec4 GFLOPS > Higher Is Better RTX 3080 RBAR . 22762.96 |===================================================== vkpeak 20210424 fp16-scalar GFLOPS > Higher Is Better RTX 3080 RBAR . 17075.80 |===================================================== vkpeak 20210424 fp16-vec4 GFLOPS > Higher Is Better RTX 3080 RBAR . 34257.55 |===================================================== vkpeak 20210424 fp64-scalar GFLOPS > Higher Is Better RTX 3080 RBAR . 534.10 |======================================================= vkpeak 20210424 fp64-vec4 GFLOPS > Higher Is Better RTX 3080 RBAR . 536.05 |======================================================= vkpeak 20210424 int32-scalar GIOPS > Higher Is Better RTX 3080 RBAR . 17069.59 |===================================================== vkpeak 20210424 int32-vec4 GIOPS > Higher Is Better RTX 3080 RBAR . 17007.03 |===================================================== vkpeak 20210424 int16-scalar GIOPS > Higher Is Better RTX 3080 RBAR . 11282.67 |===================================================== vkpeak 20210424 int16-vec4 GIOPS > Higher Is Better RTX 3080 RBAR . 14506.52 |===================================================== PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL FPS > Higher Is Better RTX 3080 RBAR . 727.41 |======================================================= PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL FPS > Higher Is Better RTX 3080 RBAR . 280.78 |======================================================= PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL FPS > Higher Is Better RTX 3080 RBAR . 223.01 |======================================================= LeelaChessZero 0.26 Backend: OpenCL Nodes Per Second > Higher Is Better RTX 3080 RBAR . 37359 |======================================================== cl-mem 2017-01-13 Benchmark: Read GB/s > Higher Is Better RTX 3080 RBAR . 670.3 |======================================================== cl-mem 2017-01-13 Benchmark: Write GB/s > Higher Is Better RTX 3080 RBAR . 634.5 |======================================================== cl-mem 2017-01-13 Benchmark: Copy GB/s > Higher Is Better RTX 3080 RBAR . 353.4 |======================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY GB/s > Higher Is Better RTX 3080 RBAR . 354 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY GB/s > Higher Is Better RTX 3080 RBAR . 477 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY GB/s > Higher Is Better RTX 3080 RBAR . 552 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY GB/s > Higher Is Better RTX 3080 RBAR . 627 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dDOT GB/s > Higher Is Better RTX 3080 RBAR . 596 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN GFLOPs/s > Higher Is Better RTX 3080 RBAR . 496 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT GFLOPs/s > Higher Is Better RTX 3080 RBAR . 498 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN GFLOPs/s > Higher Is Better RTX 3080 RBAR . 494 |========================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth GB/s > Higher Is Better RTX 3080 RBAR . 2205.99 |====================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP GFLOPS > Higher Is Better RTX 3080 RBAR . 1914.11 |====================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N GFLOPS > Higher Is Better RTX 3080 RBAR . 6243.80 |====================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash GHash/s > Higher Is Better RTX 3080 RBAR . 37.22 |======================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D GFLOPS > Higher Is Better RTX 3080 RBAR . 337.64 |======================================================= IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar M samples/s > Higher Is Better RTX 3080 RBAR . 46.14 |======================================================== IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom M samples/s > Higher Is Better RTX 3080 RBAR . 17.47 |======================================================== Blender 2.92 Blend File: BMW27 - Compute: CUDA Seconds < Lower Is Better RTX 3080 RBAR . 22.11 |======================================================== Blender 2.92 Blend File: BMW27 - Compute: NVIDIA OptiX Seconds < Lower Is Better RTX 3080 RBAR . 11.36 |======================================================== Blender 2.92 Blend File: Classroom - Compute: CUDA Seconds < Lower Is Better RTX 3080 RBAR . 61.22 |======================================================== Blender 2.92 Blend File: Classroom - Compute: NVIDIA OptiX Seconds < Lower Is Better RTX 3080 RBAR . 36.41 |======================================================== Blender 2.92 Blend File: Fishy Cat - Compute: CUDA Seconds < Lower Is Better RTX 3080 RBAR . 41.69 |======================================================== Blender 2.92 Blend File: Fishy Cat - Compute: NVIDIA OptiX Seconds < Lower Is Better RTX 3080 RBAR . 22.98 |======================================================== Blender 2.92 Blend File: Pabellon Barcelona - Compute: CUDA Seconds < Lower Is Better RTX 3080 RBAR . 147.02 |======================================================= Blender 2.92 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX Seconds < Lower Is Better RTX 3080 RBAR . 53.33 |======================================================== Blender 2.92 Blend File: Barbershop - Compute: CUDA Seconds < Lower Is Better RTX 3080 RBAR . 445.39 |======================================================= Blender 2.92 Blend File: Barbershop - Compute: NVIDIA OptiX Seconds < Lower Is Better RTX 3080 RBAR . 408.75 |======================================================= Chaos Group V-RAY 5 Mode: NVIDIA CUDA GPU vpaths > Higher Is Better RTX 3080 RBAR . 1773 |========================================================= Chaos Group V-RAY 5 Mode: NVIDIA RTX GPU vrays > Higher Is Better RTX 3080 RBAR . 2379 |========================================================= VkResample 1.0 Upscale: 2x - Precision: Single ms < Lower Is Better RTX 3080 RBAR . 11.30 |======================================================== RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Seconds < Lower Is Better RTX 3080 RBAR . 32.57 |======================================================== RealSR-NCNN 20200818 Scale: 4x - TAA: No Seconds < Lower Is Better RTX 3080 RBAR . 6.115 |======================================================== Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes Seconds < Lower Is Better RTX 3080 RBAR . 3.386 |======================================================== Betsy GPU Compressor 1.1 Beta Codec: ETC1 - Quality: Highest Seconds < Lower Is Better RTX 3080 RBAR . 3.344 |======================================================== Betsy GPU Compressor 1.1 Beta Codec: ETC2 RGB - Quality: Highest Seconds < Lower Is Better RTX 3080 RBAR . 4.528 |======================================================== RedShift Demo 3.0 Seconds < Lower Is Better RTX 3080 RBAR . 165 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT GB/s > Higher Is Better RTX 3080 RBAR . 363 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N GB/s > Higher Is Better RTX 3080 RBAR . 240 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T GB/s > Higher Is Better RTX 3080 RBAR . 374 |========================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT GFLOPs/s > Higher Is Better RTX 3080 RBAR . 496 |==========================================================