res.txt docker testing on Ubuntu 20.04.6 LTS via the Phoronix Test Suite. llvmpipe - Intel Core i7-12700H: Processor: Intel Core i7-12700H @ 4.60GHz (14 Cores / 20 Threads), Motherboard: NB02 PHxARX1_PHxAQF1 (N.1.04A03 BIOS), Memory: 64GB, Disk: 2000GB Samsung SSD 980 PRO 2TB, Graphics: llvmpipe, Audio: Realtek ALC256, Monitor: U28E590 OS: Ubuntu 20.04.6 LTS, Kernel: 6.5.0-15-generic (x86_64), Desktop: MATE, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA, OpenGL: 4.5 Mesa 21.2.6 (LLVM 12.0.0 256 bits), Vulkan: 1.2.182, Compiler: GCC 9.4.0 + CUDA 12.0, File-System: ext4, Screen Resolution: 3840x2160, System Layer: docker NVIDIA GeForce RTX 3050 Ti Laptop GPU: Processor: Intel Core i7-12700H @ 4.60GHz (14 Cores / 20 Threads), Motherboard: NB02 PHxARX1_PHxAQF1 (N.1.04A03 BIOS), Memory: 64GB, Disk: 2000GB Samsung SSD 980 PRO 2TB, Graphics: NVIDIA GeForce RTX 3050 Ti Laptop GPU 4GB, Audio: Realtek ALC256, Monitor: U28E590 OS: Ubuntu 20.04.6 LTS, Kernel: 6.5.0-15-generic (x86_64), Desktop: MATE, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA, Vulkan: 1.2.182, Compiler: GCC 9.4.0 + CUDA 12.0, File-System: ext4, Screen Resolution: 3840x2160, System Layer: docker vkpeak 20230730 fp32-scalar GFLOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 878.31 |=============================== vkpeak 20230730 fp32-vec4 GFLOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 1366.62 |============================== vkpeak 20230730 fp16-scalar GFLOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 2030.24 |============================== vkpeak 20230730 fp16-vec4 GFLOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 2828.13 |============================== vkpeak 20230730 int32-scalar GIOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 403.31 |=============================== vkpeak 20230730 int32-vec4 GIOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 428.32 |=============================== vkpeak 20230730 int16-scalar GIOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 789.83 |=============================== vkpeak 20230730 int16-vec4 GIOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 864.22 |=============================== RealSR-NCNN 20200818 Scale: 4x - TAA: No Seconds < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 98.22 |================================ RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Seconds < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 675.85 |=============================== Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: No Seconds < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 5.048 |================================ Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes Seconds < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 32.44 |================================ VkFFT 1.2.31 Test: FFT + iFFT R2C / C2R Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in half precision Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C Bluestein in single precision Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in double precision Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in single precision Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C multidimensional in single precision Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C Bluestein benchmark in double precision Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling Benchmark Score > Higher Is Better Hashcat 6.2.4 Benchmark: MD5 H/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 12631000000 |========================== Hashcat 6.2.4 Benchmark: SHA1 H/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 4214633333 |=========================== Hashcat 6.2.4 Benchmark: 7-Zip H/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 184500 |=============================== Hashcat 6.2.4 Benchmark: SHA-512 H/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 601566667 |============================ Hashcat 6.2.4 Benchmark: TrueCrypt RIPEMD160 + XTS H/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 154433 |=============================== Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Integer Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Integer GIOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 3852.66 |============================== Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Double Precision Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Single Precision Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Half Precision GFLOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 8650.27 |============================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Double Precision GFLOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 116.51 |=============================== Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Single Precision GFLOPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 8315.17 |============================== 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 Libplacebo 5.229.1 FPS > Higher Is Better cl-mem 2017-01-13 Benchmark: Copy cl-mem 2017-01-13 Benchmark: Read cl-mem 2017-01-13 Benchmark: Write NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms days/ns < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 0.32841 |============================== Betsy GPU Compressor 1.1 Beta Codec: ETC1 - Quality: Highest Seconds < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 197.66 |=============================== Betsy GPU Compressor 1.1 Beta Codec: ETC2 RGB - Quality: Highest Seconds < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 197.17 |=============================== VkResample 1.0 Upscale: 2x - Precision: Double ms < Lower Is Better VkResample 1.0 Upscale: 2x - Precision: Single ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 100.01 |=============================== OctaneBench 2020.1 Total Score Score > Higher Is Better RedShift Demo 3.0 Seconds < Lower Is Better FAHBench 2.3.2 Ns Per Day > Higher Is Better clpeak 1.1.2 OpenCL Test: Integer Compute INT clpeak 1.1.2 OpenCL Test: Single-Precision Float clpeak 1.1.2 OpenCL Test: Double-Precision Double clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth LeelaChessZero 0.30 Backend: OpenCL Nodes Per Second > Higher Is Better Rodinia 3.1 Test: OpenCL Particle Filter Seconds < Lower Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: GPU M samples/sec > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 3.11 |================================= LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: GPU M samples/sec > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 0.81 |================================= LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: GPU M samples/sec > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 3.39 |================================= LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: GPU M samples/sec > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 1.35 |================================= LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: GPU M samples/sec > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 8.62 |================================= ArrayFire 3.9 Test: Conjugate Gradient OpenCL FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL ms < Lower Is Better ViennaCL 1.7.1 Test: CPU BLAS - sCOPY GB/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 38.6 |================================= ViennaCL 1.7.1 Test: CPU BLAS - sAXPY GB/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 43.9 |================================= ViennaCL 1.7.1 Test: CPU BLAS - sDOT GB/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 45.5 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dCOPY GB/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 32.9 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dAXPY GB/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 40.6 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dDOT GB/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 42.1 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N GB/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 32.6 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T GB/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 36.1 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN GFLOPs/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 14.8 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT GFLOPs/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 16.0 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN GFLOPs/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 16.6 |================================= ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT GFLOPs/s > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 16.9 |================================= ViennaCL 1.7.1 Test: OpenCL BLAS GFLOPS > Higher Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 100 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 200 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 1000 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 100 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 200 Milli-Seconds < Lower Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 1000 Milli-Seconds < Lower Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 24.89 |================================ NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 7.99 |================================= NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 6.98 |================================= NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 7.02 |================================= NCNN 20230517 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 7.36 |================================= NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 13.15 |================================ NCNN 20230517 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 2.23 |================================= NCNN 20230517 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 21.35 |================================ NCNN 20230517 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 70.68 |================================ NCNN 20230517 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 15.02 |================================ NCNN 20230517 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 11.18 |================================ NCNN 20230517 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 36.44 |================================ NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 39.81 |================================ NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 18.44 |================================ NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 19.70 |================================ NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 268.29 |=============================== NCNN 20230517 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 8.89 |================================= 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 Blender 4.0 Blend File: BMW27 - Compute: NVIDIA OptiX Seconds < Lower Is Better Blender 4.0 Blend File: Classroom - Compute: NVIDIA OptiX Seconds < Lower Is Better Blender 4.0 Blend File: Fishy Cat - Compute: NVIDIA OptiX Seconds < Lower Is Better Blender 4.0 Blend File: Barbershop - Compute: NVIDIA OptiX Seconds < Lower Is Better Blender 4.0 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX Seconds < Lower Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom M samples/s > Higher Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar M samples/s > Higher Is Better MandelGPU 1.3pts1 OpenCL Device: GPU Samples/sec > Higher Is Better NeatBench 5 Acceleration: GPU FPS > Higher Is Better NVIDIA GeForce RTX 3050 Ti Laptop GPU . 3050 |=================================