nnn ARMv8 Neoverse-V2 testing with a Pegatron JIMBO P4352 (00022432 BIOS) and NVIDIA GH200 144G HBM3e 143GB on Ubuntu 24.04 via the Phoronix Test Suite. a: Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550 OS: Ubuntu 24.04, Kernel: 6.8.0-50-generic-64k (aarch64), Display Driver: NVIDIA, Compiler: GCC 13.3.0 + CUDA 12.4, File-System: ext4, Screen Resolution: 1920x1200 b: Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550 OS: Ubuntu 24.04, Kernel: 6.8.0-50-generic-64k (aarch64), Display Driver: NVIDIA, Compiler: GCC 13.3.0 + CUDA 12.4, File-System: ext4, Screen Resolution: 1920x1200 c: Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550 OS: Ubuntu 24.04, Kernel: 6.8.0-50-generic-64k (aarch64), Display Driver: NVIDIA, Compiler: GCC 13.3.0 + CUDA 12.4, File-System: ext4, Screen Resolution: 1920x1200 d: Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550 OS: Ubuntu 24.04, Kernel: 6.8.0-50-generic-64k (aarch64), Display Driver: NVIDIA, Compiler: GCC 13.3.0 + CUDA 12.4, File-System: ext4, Screen Resolution: 1920x1200 Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 19.89 |================================================================ b . 21.04 |=================================================================== c . 20.95 |=================================================================== d . 21.27 |==================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 122.47 |=================================================================== b . 123.26 |=================================================================== c . 123.10 |=================================================================== d . 123.00 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 120.08 |=================================================================== b . 120.15 |=================================================================== c . 120.25 |=================================================================== d . 120.26 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 106.46 |=================================================================== b . 106.54 |=================================================================== c . 106.75 |=================================================================== d . 106.77 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 26.04 |==================================================================== b . 22.55 |=========================================================== c . 23.20 |============================================================= d . 22.40 |========================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 122.27 |================================================================== b . 123.13 |=================================================================== c . 123.28 |=================================================================== d . 123.26 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 120.57 |=================================================================== b . 120.86 |=================================================================== c . 121.13 |=================================================================== d . 120.76 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 107.88 |=================================================================== b . 106.97 |================================================================== c . 107.58 |=================================================================== d . 106.76 |================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 57.71 |==================================================================== b . 50.70 |============================================================ c . 51.50 |============================================================= d . 52.89 |============================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 128.95 |================================================================== b . 130.74 |================================================================== c . 129.97 |================================================================== d . 131.82 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 136.37 |================================================================== b . 138.20 |=================================================================== c . 136.15 |================================================================== d . 139.04 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 136.56 |================================================================== b . 136.15 |================================================================== c . 138.75 |=================================================================== d . 138.36 |=================================================================== srsRAN Project 24.10 Test: PDSCH Processor Benchmark, Throughput Total Mbps > Higher Is Better a . 12647.7 |=============================================================== b . 13307.7 |================================================================== c . 13057.6 |================================================================= d . 12934.9 |================================================================ srsRAN Project 24.10 Test: PUSCH Processor Benchmark, Throughput Total Mbps > Higher Is Better a . 1760.1 |============================================================== b . 1821.8 |================================================================ c . 1834.6 |================================================================ d . 1907.0 |=================================================================== srsRAN Project 24.10 Test: PDSCH Processor Benchmark, Throughput Thread Mbps > Higher Is Better a . 328.6 |================================================ b . 464.5 |==================================================================== c . 393.2 |========================================================== d . 389.2 |========================================================= srsRAN Project 24.10 Test: PUSCH Processor Benchmark, Throughput Thread Mbps > Higher Is Better a . 52.6 |===================================================================== b . 48.1 |=============================================================== c . 52.7 |===================================================================== d . 50.6 |================================================================== VVenC 1.13 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 9.430 |==================================================================== b . 9.364 |==================================================================== c . 9.374 |==================================================================== d . 9.390 |==================================================================== VVenC 1.13 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 18.68 |==================================================================== b . 18.65 |==================================================================== c . 18.42 |=================================================================== d . 18.34 |=================================================================== VVenC 1.13 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 19.82 |==================================================================== b . 19.70 |==================================================================== c . 19.70 |==================================================================== d . 19.63 |=================================================================== VVenC 1.13 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 36.79 |==================================================================== b . 36.93 |==================================================================== c . 36.97 |==================================================================== d . 36.80 |==================================================================== x265 4.1 Video Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 13.91 |==================================================================== b . 13.82 |==================================================================== c . 13.89 |==================================================================== d . 13.64 |=================================================================== x265 4.1 Video Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 20.73 |==================================================================== b . 20.12 |================================================================== c . 19.94 |================================================================= d . 19.90 |=================================================================