3090-clpeak AMD Ryzen Threadripper 1950X 16-Core testing with a ASRock X399 Taichi (P3.90 BIOS) and NVIDIA GeForce RTX 3090 24GB on Ubuntu 22.04 via the Phoronix Test Suite. 3090-clpeak: Processor: AMD Ryzen Threadripper 1950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASRock X399 Taichi (P3.90 BIOS), Chipset: AMD 17h, Memory: 64GB, Disk: 1024GB ADATA SX8200PNP + 1000GB KINGSTON SA2000M81000G + Samsung SSD 970 EVO Plus 500GB + 256GB SAMSUNG MZVLW256HEHP-000L7 + 2000GB Samsung SSD 970 EVO Plus 2TB, Graphics: NVIDIA GeForce RTX 3090 24GB, Audio: NVIDIA GA102 HD Audio, Monitor: C27JG5x, Network: 2 x Intel I211 + Intel Dual Band-AC 3168NGW 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: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.146, Vulkan: 1.3.242, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 2560x1440 clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueWriteBuffer GBPS > Higher Is Better 3090-clpeak . 12.76 |========================================================== clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueReadBuffer GBPS > Higher Is Better 3090-clpeak . 7.32 |=========================================================== clpeak 1.1.2 OpenCL Test: Double-Precision Compute GFLOPS > Higher Is Better 3090-clpeak . 635.74 |========================================================= clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth GBPS > Higher Is Better 3090-clpeak . 812.86 |========================================================= clpeak 1.1.2 OpenCL Test: Kernel Latency us < Lower Is Better 3090-clpeak . 5.32 |=========================================================== clpeak 1.1.2 OpenCL Test: Single-Precision Compute GFLOPS > Higher Is Better 3090-clpeak . 34505.80 |======================================================= clpeak 1.1.2 OpenCL Test: Integer Compute GIOPS > Higher Is Better 3090-clpeak . 17411.94 |======================================================= clpeak 1.1.2 OpenCL Test: Integer 24-bit Compute GIOPS > Higher Is Better 3090-clpeak . 17703.89 |=======================================================