cpu_2gpu 2 x AMD EPYC 7713 64-Core testing with a GIGABYTE MZ72-HB0-00 v01020102 (M10 BIOS) and ASPEED 80GB on Ubuntu 22.04 via the Phoronix Test Suite. 2 NVIDIA A100 GPUs: Processor: 2 x AMD EPYC 7713 64-Core @ 2.00GHz (128 Cores / 256 Threads), Motherboard: GIGABYTE MZ72-HB0-00 v01020102 (M10 BIOS), Chipset: AMD Starship/Matisse, Memory: 7 x 64 GB DDR4-3200MT/s 36ASF8G72PZ-3G2B2, Disk: 2 x 1000GB Samsung SSD 980 PRO 1TB + 1000GB Western Digital WD Blue SN570 1TB + 1000GB Sabrent Rocket Q, Graphics: ASPEED 80GB, Monitor: PHL 243V7, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA + 2 x Broadcom NetXtreme II BCM57810 10 OS: Ubuntu 22.04, Kernel: 5.15.0-69-generic (x86_64), Display Server: X Server 1.21.1.3, Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 12.2.128, Compiler: GCC 11.4.0 + CUDA 12.2, File-System: ext4, Screen Resolution: 1920x1080 Hashcat 6.2.4 Benchmark: MD5 H/s > Higher Is Better 2 NVIDIA A100 GPUs . 100636418750 |============================================ Hashcat 6.2.4 Benchmark: SHA1 H/s > Higher Is Better 2 NVIDIA A100 GPUs . 43808966667 |============================================= Hashcat 6.2.4 Benchmark: 7-Zip H/s > Higher Is Better 2 NVIDIA A100 GPUs . 2359633 |================================================= Hashcat 6.2.4 Benchmark: SHA-512 H/s > Higher Is Better 2 NVIDIA A100 GPUs . 6365366667 |============================================== Hashcat 6.2.4 Benchmark: TrueCrypt RIPEMD160 + XTS H/s > Higher Is Better 2 NVIDIA A100 GPUs . 1635000 |================================================= Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Integer GIOPS > Higher Is Better 2 NVIDIA A100 GPUs . 19044.55 |================================================ Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Double Precision GFLOPS > Higher Is Better 2 NVIDIA A100 GPUs . 9631.39 |================================================= Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Single Precision GFLOPS > Higher Is Better 2 NVIDIA A100 GPUs . 19044.55 |================================================ SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D GFLOPS > Higher Is Better 2 NVIDIA A100 GPUs . 829.07 |================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 6.6925 |================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP GFLOPS > Higher Is Better 2 NVIDIA A100 GPUs . 4439.22 |================================================= SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash GHash/s > Higher Is Better 2 NVIDIA A100 GPUs . 42.97 |=================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 241.54 |================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N GFLOPS > Higher Is Better 2 NVIDIA A100 GPUs . 13583.1 |================================================= SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops GFLOPS > Higher Is Better 2 NVIDIA A100 GPUs . 19428.3 |================================================= SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 6.7287 |================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 6.7778 |================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 1581.67 |================================================= cl-mem 2017-01-13 Benchmark: Copy GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 235.1 |=================================================== cl-mem 2017-01-13 Benchmark: Read GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 797.6 |=================================================== cl-mem 2017-01-13 Benchmark: Write GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 1404.5 |================================================== RedShift Demo 3.0 Seconds < Lower Is Better FAHBench 2.3.2 Ns Per Day > Higher Is Better 2 NVIDIA A100 GPUs . 267.38 |================================================== clpeak 1.1.2 OpenCL Test: Integer Compute INT GIOPS > Higher Is Better 2 NVIDIA A100 GPUs . 19279.66 |================================================ clpeak 1.1.2 OpenCL Test: Single-Precision Float GFLOPS > Higher Is Better 2 NVIDIA A100 GPUs . 19356.03 |================================================ clpeak 1.1.2 OpenCL Test: Double-Precision Double GFLOPS > Higher Is Better 2 NVIDIA A100 GPUs . 9721.88 |================================================= clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth GBPS > Higher Is Better 2 NVIDIA A100 GPUs . 1494.62 |================================================= LeelaChessZero 0.28 Backend: OpenCL Nodes Per Second > Higher Is Better 2 NVIDIA A100 GPUs . 10182 |=================================================== Rodinia 3.1 Test: OpenCL Particle Filter Seconds < Lower Is Better 2 NVIDIA A100 GPUs . 2.015 |=================================================== ArrayFire 3.7 Test: Conjugate Gradient OpenCL ms < Lower Is Better 2 NVIDIA A100 GPUs . 2.611 |=================================================== LuxCoreRender 2.6 Scene: DLSC - Acceleration: GPU M samples/sec > Higher Is Better 2 NVIDIA A100 GPUs . 8.74 |==================================================== LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: GPU M samples/sec > Higher Is Better 2 NVIDIA A100 GPUs . 0.14 |==================================================== LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: GPU M samples/sec > Higher Is Better 2 NVIDIA A100 GPUs . 1.07 |==================================================== LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: GPU M samples/sec > Higher Is Better 2 NVIDIA A100 GPUs . 0.15 |==================================================== LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: GPU M samples/sec > Higher Is Better 2 NVIDIA A100 GPUs . 57.32 |=================================================== FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL ms < Lower Is Better 2 NVIDIA A100 GPUs . 0.922 |=================================================== ViennaCL 1.7.1 Test: CPU BLAS - sCOPY GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 590 |===================================================== ViennaCL 1.7.1 Test: CPU BLAS - sAXPY GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 633 |===================================================== ViennaCL 1.7.1 Test: CPU BLAS - sDOT GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 469 |===================================================== ViennaCL 1.7.1 Test: CPU BLAS - dCOPY GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 445 |===================================================== ViennaCL 1.7.1 Test: CPU BLAS - dAXPY GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 796.6 |=================================================== ViennaCL 1.7.1 Test: CPU BLAS - dDOT GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 394.52 |================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 24.68 |=================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 511.08 |================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN GFLOPs/s > Higher Is Better 2 NVIDIA A100 GPUs . 77.1 |==================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT GFLOPs/s > Higher Is Better 2 NVIDIA A100 GPUs . 79.3 |==================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN GFLOPs/s > Higher Is Better 2 NVIDIA A100 GPUs . 86.6 |==================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT GFLOPs/s > Higher Is Better 2 NVIDIA A100 GPUs . 83.9 |==================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 233 |===================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 314 |===================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 225 |===================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 442 |===================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 574 |===================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dDOT GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 436 |===================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 68.4 |==================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T GB/s > Higher Is Better 2 NVIDIA A100 GPUs . 245 |===================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN GFLOPs/s > Higher Is Better 2 NVIDIA A100 GPUs . 4263 |==================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT GFLOPs/s > Higher Is Better 2 NVIDIA A100 GPUs . 4667 |==================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN GFLOPs/s > Higher Is Better 2 NVIDIA A100 GPUs . 4233 |==================================================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT GFLOPs/s > Higher Is Better 2 NVIDIA A100 GPUs . 4280 |==================================================== NCNN 20230517 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better 2 NVIDIA A100 GPUs . 74.59 |=================================================== NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better 2 NVIDIA A100 GPUs . 69.06 |=================================================== NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better 2 NVIDIA A100 GPUs . 63.59 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better 2 NVIDIA A100 GPUs . 65.35 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better 2 NVIDIA A100 GPUs . 38.86 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better 2 NVIDIA A100 GPUs . 64.03 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better 2 NVIDIA A100 GPUs . 20.65 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better 2 NVIDIA A100 GPUs . 64.08 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better 2 NVIDIA A100 GPUs . 90.72 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better 2 NVIDIA A100 GPUs . 35.54 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better 2 NVIDIA A100 GPUs . 16.60 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better 2 NVIDIA A100 GPUs . 88.68 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better 2 NVIDIA A100 GPUs . 70.52 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better 2 NVIDIA A100 GPUs . 77.73 |=================================================== NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better 2 NVIDIA A100 GPUs . 166.35 |================================================== NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better 2 NVIDIA A100 GPUs . 135.41 |================================================== NCNN 20230517 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better 2 NVIDIA A100 GPUs . 38.31 |=================================================== 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