Latitude System 1/5 Test 2 x AMD EPYC 9354 32-Core testing with a Supermicro H13DSG-O-CPU v1.10 (1.5 BIOS) and ASPEED 80GB on Ubuntu 22.04 via the Phoronix Test Suite. SYS01 Full Test: Processor: 2 x AMD EPYC 9354 32-Core @ 3.25GHz (64 Cores / 128 Threads), Motherboard: Supermicro H13DSG-O-CPU v1.10 (1.5 BIOS), Chipset: AMD Device 14a4, Memory: 24 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N, Disk: 4 x 3841GB SAMSUNG MZQL23T8HCLS-00A07, Graphics: ASPEED 80GB (210/1512MHz), Network: 2 x Intel X710 for 10GBASE-T OS: Ubuntu 22.04, Kernel: 6.2.0-34-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA 535.113.01, OpenGL: 4.5 Mesa 23.0.4-0ubuntu1~22.04.1 (LLVM 15.0.7 256 bits), OpenCL: OpenCL 3.0 CUDA 12.2.146, Vulkan: 1.3.242, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 1024x768 IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom M samples/s > Higher Is Better SYS01 Full Test . 22.15 |====================================================== NeatBench 5 Acceleration: All FPS > Higher Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better SYS01 Full Test . 1221397 |==================================================== LeelaChessZero 0.28 Backend: BLAS Nodes Per Second > Higher Is Better SYS01 Full Test . 7876 |======================================================= NCNN 20230517 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better SYS01 Full Test . 19.71 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better SYS01 Full Test . 57.89 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better SYS01 Full Test . 54.45 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better SYS01 Full Test . 27.37 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better SYS01 Full Test . 34.51 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better SYS01 Full Test . 25.18 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better SYS01 Full Test . 9.38 |======================================================= NCNN 20230517 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better SYS01 Full Test . 15.29 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better SYS01 Full Test . 42.96 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better SYS01 Full Test . 27.81 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better SYS01 Full Test . 7.40 |======================================================= NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better SYS01 Full Test . 18.01 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better SYS01 Full Test . 11.88 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better SYS01 Full Test . 17.46 |====================================================== NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better SYS01 Full Test . 14.13 |====================================================== NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better SYS01 Full Test . 12.86 |====================================================== NCNN 20230517 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better SYS01 Full Test . 22.90 |====================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better SYS01 Full Test . 453741 |===================================================== LeelaChessZero 0.28 Backend: Eigen Nodes Per Second > Higher Is Better SYS01 Full Test . 8460 |======================================================= LeelaChessZero 0.28 Backend: OpenCL Nodes Per Second > Higher Is Better SYS01 Full Test . 5678 |======================================================= LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU M samples/sec > Higher Is Better SYS01 Full Test . 15.29 |====================================================== LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU M samples/sec > Higher Is Better SYS01 Full Test . 11.15 |====================================================== LuxCoreRender 2.6 Scene: DLSC - Acceleration: GPU M samples/sec > Higher Is Better SYS01 Full Test . 76.05 |====================================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better SYS01 Full Test . 246739 |===================================================== IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar M samples/s > Higher Is Better SYS01 Full Test . 49.90 |====================================================== LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: GPU M samples/sec > Higher Is Better SYS01 Full Test . 47.82 |====================================================== NCNN 20230517 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better SYS01 Full Test . 18.04 |====================================================== NCNN 20230517 Target: CPU - Model: FastestDet ms < Lower Is Better SYS01 Full Test . 18.95 |====================================================== NCNN 20230517 Target: CPU - Model: vision_transformer ms < Lower Is Better SYS01 Full Test . 57.77 |====================================================== NCNN 20230517 Target: CPU - Model: regnety_400m ms < Lower Is Better SYS01 Full Test . 53.56 |====================================================== NCNN 20230517 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better SYS01 Full Test . 25.38 |====================================================== NCNN 20230517 Target: CPU - Model: yolov4-tiny ms < Lower Is Better SYS01 Full Test . 35.18 |====================================================== NCNN 20230517 Target: CPU - Model: resnet50 ms < Lower Is Better SYS01 Full Test . 24.28 |====================================================== NCNN 20230517 Target: CPU - Model: alexnet ms < Lower Is Better SYS01 Full Test . 9.18 |======================================================= NCNN 20230517 Target: CPU - Model: resnet18 ms < Lower Is Better SYS01 Full Test . 14.70 |====================================================== NCNN 20230517 Target: CPU - Model: vgg16 ms < Lower Is Better SYS01 Full Test . 39.88 |====================================================== NCNN 20230517 Target: CPU - Model: googlenet ms < Lower Is Better SYS01 Full Test . 26.55 |====================================================== NCNN 20230517 Target: CPU - Model: blazeface ms < Lower Is Better SYS01 Full Test . 6.94 |======================================================= NCNN 20230517 Target: CPU - Model: mnasnet ms < Lower Is Better SYS01 Full Test . 11.30 |====================================================== NCNN 20230517 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better SYS01 Full Test . 16.67 |====================================================== NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better SYS01 Full Test . 13.97 |====================================================== NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better SYS01 Full Test . 12.90 |====================================================== NCNN 20230517 Target: CPU - Model: mobilenet ms < Lower Is Better SYS01 Full Test . 21.54 |====================================================== OctaneBench 2020.1 Total Score Score > Higher Is Better SYS01 Full Test . 516.56 |===================================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better SYS01 Full Test . 125612 |===================================================== LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: GPU M samples/sec > Higher Is Better SYS01 Full Test . 39.23 |====================================================== FAHBench 2.3.2 Ns Per Day > Higher Is Better SYS01 Full Test . 263.12 |===================================================== Rodinia 3.1 Test: OpenMP Leukocyte Seconds < Lower Is Better SYS01 Full Test . 37.55 |====================================================== Rodinia 3.1 Test: OpenMP HotSpot3D Seconds < Lower Is Better SYS01 Full Test . 74.81 |====================================================== NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms days/ns < Lower Is Better SYS01 Full Test . 0.02347 |==================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better SYS01 Full Test . 91880 |====================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops GFLOPS > Higher Is Better SYS01 Full Test . 19428.8 |==================================================== ArrayFire 3.7 Test: BLAS CPU GFLOPS > Higher Is Better SYS01 Full Test . 1337.71 |==================================================== LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: GPU M samples/sec > Higher Is Better SYS01 Full Test . 60.10 |====================================================== Hashcat 6.2.4 Benchmark: SHA1 H/s > Higher Is Better SYS01 Full Test . 98836825000 |================================================ IndigoBench 4.4 Acceleration: CPU - Scene: Bedroom M samples/s > Higher Is Better SYS01 Full Test . 13.89 |====================================================== Hashcat 6.2.4 Benchmark: MD5 H/s > Higher Is Better SYS01 Full Test . 305914100000 |=============================================== LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: CPU M samples/sec > Higher Is Better SYS01 Full Test . 6.50 |======================================================= IndigoBench 4.4 Acceleration: CPU - Scene: Supercar M samples/s > Higher Is Better SYS01 Full Test . 30.45 |====================================================== LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: CPU M samples/sec > Higher Is Better SYS01 Full Test . 6.54 |======================================================= FinanceBench 2016-07-25 Benchmark: Bonds OpenMP ms < Lower Is Better SYS01 Full Test . 47810.07 |=================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better SYS01 Full Test . 46330 |====================================================== LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: CPU M samples/sec > Higher Is Better SYS01 Full Test . 24.73 |====================================================== FinanceBench 2016-07-25 Benchmark: Repo OpenMP ms < Lower Is Better SYS01 Full Test . 30890.76 |=================================================== Rodinia 3.1 Test: OpenMP LavaMD Seconds < Lower Is Better SYS01 Full Test . 35.50 |====================================================== Libplacebo 5.229.1 FPS > Higher Is Better Rodinia 3.1 Test: OpenCL Myocyte Seconds < Lower Is Better SYS01 Full Test . 29.82 |====================================================== MandelGPU 1.3pts1 OpenCL Device: CPU+GPU Samples/sec > Higher Is Better SYS01 Full Test . 116018825.9 |================================================ clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueWriteBuffer GBPS > Higher Is Better SYS01 Full Test . 22.30 |====================================================== GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better SYS01 Full Test . 9.624 |====================================================== clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueReadBuffer GBPS > Higher Is Better SYS01 Full Test . 22.31 |====================================================== Hashcat 6.2.4 Benchmark: SHA-512 H/s > Higher Is Better SYS01 Full Test . 22440066667 |================================================ Hashcat 6.2.4 Benchmark: TrueCrypt RIPEMD160 + XTS H/s > Higher Is Better SYS01 Full Test . 6559100 |==================================================== Hashcat 6.2.4 Benchmark: 7-Zip H/s > Higher Is Better SYS01 Full Test . 9608167 |==================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT GFLOPs/s > Higher Is Better SYS01 Full Test . 4280 |======================================================= ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN GFLOPs/s > Higher Is Better SYS01 Full Test . 4237 |======================================================= ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT GFLOPs/s > Higher Is Better SYS01 Full Test . 4667 |======================================================= ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN GFLOPs/s > Higher Is Better SYS01 Full Test . 4257 |======================================================= ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T GB/s > Higher Is Better SYS01 Full Test . 245 |======================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N GB/s > Higher Is Better SYS01 Full Test . 68.4 |======================================================= ViennaCL 1.7.1 Test: OpenCL BLAS - dDOT GB/s > Higher Is Better SYS01 Full Test . 438 |======================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY GB/s > Higher Is Better SYS01 Full Test . 575 |======================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY GB/s > Higher Is Better SYS01 Full Test . 441 |======================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT GB/s > Higher Is Better SYS01 Full Test . 225 |======================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY GB/s > Higher Is Better SYS01 Full Test . 313 |======================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY GB/s > Higher Is Better SYS01 Full Test . 233 |======================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT GFLOPs/s > Higher Is Better SYS01 Full Test . 115 |======================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN GFLOPs/s > Higher Is Better SYS01 Full Test . 121 |======================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT GFLOPs/s > Higher Is Better SYS01 Full Test . 105 |======================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN GFLOPs/s > Higher Is Better SYS01 Full Test . 110 |======================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T GB/s > Higher Is Better SYS01 Full Test . 815 |======================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N GB/s > Higher Is Better SYS01 Full Test . 76.7 |======================================================= ViennaCL 1.7.1 Test: CPU BLAS - dDOT GB/s > Higher Is Better SYS01 Full Test . 1008 |======================================================= ViennaCL 1.7.1 Test: CPU BLAS - dAXPY GB/s > Higher Is Better SYS01 Full Test . 2227 |======================================================= ViennaCL 1.7.1 Test: CPU BLAS - dCOPY GB/s > Higher Is Better SYS01 Full Test . 1790 |======================================================= ViennaCL 1.7.1 Test: CPU BLAS - sDOT GB/s > Higher Is Better SYS01 Full Test . 536 |======================================================== ViennaCL 1.7.1 Test: CPU BLAS - sAXPY GB/s > Higher Is Better SYS01 Full Test . 1950 |======================================================= ViennaCL 1.7.1 Test: CPU BLAS - sCOPY GB/s > Higher Is Better SYS01 Full Test . 1390 |======================================================= Blender 3.6 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better SYS01 Full Test . 20.04 |====================================================== ArrayFire 3.7 Test: BLAS OpenCL GFLOPS > Higher Is Better SYS01 Full Test . 9644.25 |==================================================== ArrayFire 3.7 Test: Conjugate Gradient CPU ms < Lower Is Better SYS01 Full Test . 25.28 |====================================================== PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: Inception V3 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: NASNer Large - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: NASNer Large - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: DenseNet 201 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: IMDB LSTM - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: DenseNet 201 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: ResNet 50 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: IMDB LSTM - 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: Yes - Mode: Training - Network: VGG16 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: VGG19 - Device: OpenCL Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: Mobilenet - Device: OpenCL Examples Per Second > Higher Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth GB/s > Higher Is Better SYS01 Full Test . 1581.66 |==================================================== VkResample 1.0 Upscale: 2x - Precision: Single ms < Lower Is Better SYS01 Full Test . 6.947 |====================================================== FinanceBench 2016-07-25 Benchmark: Monte-Carlo OpenCL ms < Lower Is Better SYS01 Full Test . 103.26 |===================================================== Rodinia 3.1 Test: OpenMP CFD Solver Seconds < Lower Is Better SYS01 Full Test . 8.277 |====================================================== ArrayFire 3.7 Test: Conjugate Gradient OpenCL ms < Lower Is Better SYS01 Full Test . 2.611 |====================================================== LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: GPU M samples/sec > Higher Is Better SYS01 Full Test . 254.59 |===================================================== Rodinia 3.1 Test: OpenCL Particle Filter Seconds < Lower Is Better SYS01 Full Test . 3.836 |====================================================== Rodinia 3.1 Test: OpenMP Streamcluster Seconds < Lower Is Better SYS01 Full Test . 6.173 |====================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D GFLOPS > Higher Is Better SYS01 Full Test . 827.59 |===================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback GB/s > Higher Is Better SYS01 Full Test . 27.12 |====================================================== clpeak 1.1.2 OpenCL Test: Single-Precision Compute GFLOPS > Higher Is Better SYS01 Full Test . 19346.29 |=================================================== clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth GBPS > Higher Is Better SYS01 Full Test . 1494.78 |==================================================== cl-mem 2017-01-13 Benchmark: Copy GB/s > Higher Is Better SYS01 Full Test . 235 |======================================================== cl-mem 2017-01-13 Benchmark: Read GB/s > Higher Is Better SYS01 Full Test . 796.5 |====================================================== cl-mem 2017-01-13 Benchmark: Write GB/s > Higher Is Better SYS01 Full Test . 1402.4 |===================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP GFLOPS > Higher Is Better SYS01 Full Test . 4438.11 |==================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction GB/s > Higher Is Better SYS01 Full Test . 241.64 |===================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad GB/s > Higher Is Better SYS01 Full Test . 26.07 |====================================================== clpeak 1.1.2 OpenCL Test: Integer 24-bit Compute GIOPS > Higher Is Better SYS01 Full Test . 19300.84 |=================================================== clpeak 1.1.2 OpenCL Test: Integer Compute GIOPS > Higher Is Better SYS01 Full Test . 19264.19 |=================================================== clpeak 1.1.2 OpenCL Test: Double-Precision Compute GFLOPS > Higher Is Better SYS01 Full Test . 9719.80 |==================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N GFLOPS > Higher Is Better SYS01 Full Test . 13584.9 |==================================================== clpeak 1.1.2 OpenCL Test: Kernel Latency us < Lower Is Better SYS01 Full Test . 5.38 |======================================================= SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download GB/s > Higher Is Better SYS01 Full Test . 26.86 |====================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash GHash/s > Higher Is Better SYS01 Full Test . 42.97 |====================================================== FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL ms < Lower Is Better SYS01 Full Test . 1.090 |====================================================== PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: ResNet 50 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG19 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: VGG16 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: NASNer Large - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: Inception V3 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: Mobilenet - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: VGG19 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: DenseNet 201 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: NASNer Large - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: DenseNet 201 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Inference - Network: IMDB LSTM - Device: CPU Examples Per Second > Higher Is Better PlaidML FP16: Yes - Mode: Training - Network: IMDB LSTM - Device: CPU Examples Per Second > Higher Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Seconds < Lower Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes Seconds < Lower Is Better vkpeak 20230730 GFLOPS > Higher Is Better CUDA Mini-Nbody 2015-11-10 Test: Original RedShift Demo 3.0 Seconds < Lower Is Better