ARMv8 Neoverse-V2 testing with a Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS) and NVIDIA GH200 480GB on Ubuntu 22.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2403013-NE-NGCSMOKER54
ngc smoke run
ARMv8 Neoverse-V2 testing with a Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS) and NVIDIA GH200 480GB on Ubuntu 22.04 via the Phoronix Test Suite.
,,"a","b","c","d"
Processor,,ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores),ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores),ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores),ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores)
Motherboard,,Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS),Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS),Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS),Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS)
Memory,,1 x 480GB DRAM-6400MT/s,1 x 480GB DRAM-6400MT/s,1 x 480GB DRAM-6400MT/s,1 x 480GB DRAM-6400MT/s
Disk,,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9
Graphics,,NVIDIA GH200 480GB,NVIDIA GH200 480GB,NVIDIA GH200 480GB,NVIDIA GH200 480GB
Network,,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE
OS,,Ubuntu 22.04,Ubuntu 22.04,Ubuntu 22.04,Ubuntu 22.04
Kernel,,6.5.0-1007-NVIDIA-64k (aarch64),6.5.0-1007-NVIDIA-64k (aarch64),6.5.0-1007-NVIDIA-64k (aarch64),6.5.0-1007-NVIDIA-64k (aarch64)
Display Driver,,NVIDIA,NVIDIA,NVIDIA,NVIDIA
OpenCL,,OpenCL 3.0 CUDA 12.4.89,OpenCL 3.0 CUDA 12.4.89,OpenCL 3.0 CUDA 12.4.89,OpenCL 3.0 CUDA 12.4.89
Compiler,,GCC 11.4.0 + CUDA 11.5,GCC 11.4.0 + CUDA 11.5,GCC 11.4.0 + CUDA 11.5,GCC 11.4.0 + CUDA 11.5
File-System,,ext4,ext4,ext4,ext4
Screen Resolution,,1920x1200,1920x1200,1920x1200,1920x1200
,,"a","b","c","d"
"VkFFT - Test: FFT + iFFT R2C / C2R (Benchmark Score)",HIB,42397,41809,42581,43048
"VkFFT - Test: FFT + iFFT C2C 1D batched in half precision (Benchmark Score)",HIB,151912,151910,152866,151969
"VkFFT - Test: FFT + iFFT C2C Bluestein in single precision (Benchmark Score)",HIB,17867,17967,17886,17942
"VkFFT - Test: FFT + iFFT C2C 1D batched in double precision (Benchmark Score)",HIB,58405,58253,58256,58299
"VkFFT - Test: FFT + iFFT C2C 1D batched in single precision (Benchmark Score)",HIB,185774,186082,189944,190310
"VkFFT - Test: FFT + iFFT C2C multidimensional in single precision (Benchmark Score)",HIB,44489,43731,45071,45007
"VkFFT - Test: FFT + iFFT C2C Bluestein benchmark in double precision (Benchmark Score)",HIB,20810,21000,21094,21320
"VkFFT - Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling (Benchmark Score)",HIB,194497,190037,190909,192507
"cl-mem - Benchmark: Copy (GB/s)",HIB,308.6,308.5,308.6,308.5
"cl-mem - Benchmark: Read (GB/s)",HIB,1045.9,1045.9,1046.1,1046.0
"cl-mem - Benchmark: Write (GB/s)",HIB,2354.9,2353.4,2354.9,2352.1
"ViennaCL - Test: CPU BLAS - sCOPY (GB/s)",HIB,2920,2892,2907,2857
"ViennaCL - Test: CPU BLAS - sAXPY (GB/s)",HIB,3943,3924,3917,3920
"ViennaCL - Test: CPU BLAS - sDOT (GB/s)",HIB,667,664,666,663
"ViennaCL - Test: CPU BLAS - dCOPY (GB/s)",HIB,2027,1948,1920,1917
"ViennaCL - Test: CPU BLAS - dAXPY (GB/s)",HIB,1803,1806,1837,1830
"ViennaCL - Test: CPU BLAS - dDOT (GB/s)",HIB,1247,1238,1243,1247
"ViennaCL - Test: CPU BLAS - dGEMV-N (GB/s)",HIB,411,408,405,418
"ViennaCL - Test: CPU BLAS - dGEMV-T (GB/s)",HIB,686,699,691,696
"ViennaCL - Test: OpenCL BLAS - sCOPY (GB/s)",HIB,316,316,316,316
"ViennaCL - Test: OpenCL BLAS - sAXPY (GB/s)",HIB,420,427,427,426
"ViennaCL - Test: OpenCL BLAS - sDOT (GB/s)",HIB,282,282,283,283
"ViennaCL - Test: OpenCL BLAS - dCOPY (GB/s)",HIB,603,604,604,604
"ViennaCL - Test: OpenCL BLAS - dAXPY (GB/s)",HIB,799,798,799,799
"ViennaCL - Test: OpenCL BLAS - dDOT (GB/s)",HIB,550,552,552,553
"ViennaCL - Test: OpenCL BLAS - dGEMV-N (GB/s)",HIB,81.2,81.5,81.2,81.4
"ViennaCL - Test: OpenCL BLAS - dGEMV-T (GB/s)",HIB,308,308,308,307
"clpeak - OpenCL Test: Global Memory Bandwidth (GBPS)",HIB,3483.99,3484.06,3483.95,3484.32
"clpeak - OpenCL Test: Single-Precision Float (GFLOPS)",HIB,64545.62,64547.74,64547.25,64520.97
"clpeak - OpenCL Test: Double-Precision Double (GFLOPS)",HIB,32959.17,32961.21,32941.99,32933.63
"ViennaCL - Test: CPU BLAS - dGEMM-NN (GFLOPs/s)",HIB,135,137,139,141
"ViennaCL - Test: CPU BLAS - dGEMM-NT (GFLOPs/s)",HIB,125,125,124,124
"ViennaCL - Test: CPU BLAS - dGEMM-TN (GFLOPs/s)",HIB,141,140,141,140
"ViennaCL - Test: CPU BLAS - dGEMM-TT (GFLOPs/s)",HIB,137,138,140,136
"ViennaCL - Test: OpenCL BLAS - dGEMM-NN (GFLOPs/s)",HIB,7057,7093,7037,7053
"ViennaCL - Test: OpenCL BLAS - dGEMM-NT (GFLOPs/s)",HIB,7527,7537,7537,7540
"ViennaCL - Test: OpenCL BLAS - dGEMM-TN (GFLOPs/s)",HIB,7027,7067,7000,7070
"ViennaCL - Test: OpenCL BLAS - dGEMM-TT (GFLOPs/s)",HIB,7070,7070,7057,7070
"clpeak - OpenCL Test: Integer Compute INT (GIOPS)",HIB,33119.10,33144.74,33146.12,33129.34
"VkResample - Upscale: 2x - Precision: Double (ms)",LIB,24.296,24.294,24.290,24.297
"VkResample - Upscale: 2x - Precision: Single (ms)",LIB,5.230,5.231,5.230,5.230
"ArrayFire - Test: Conjugate Gradient OpenCL (ms)",LIB,2.997,2.983,2.998,2.997
"FinanceBench - Benchmark: Black-Scholes OpenCL (ms)",LIB,4.347,4.373,4.351,4.339
"NCNN - Target: Vulkan GPU - Model: mobilenet (ms)",LIB,4.89,4.92,4.92,4.91
"NCNN - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,2.13,2.16,2.12,2.12
"NCNN - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,2.26,2.27,2.30,2.27
"NCNN - Target: Vulkan GPU - Model: shufflenet-v2 (ms)",LIB,2.29,2.29,2.27,2.27
"NCNN - Target: Vulkan GPU - Model: mnasnet (ms)",LIB,2.04,2.03,2.04,2.04
"NCNN - Target: Vulkan GPU - Model: efficientnet-b0 (ms)",LIB,3.49,3.55,3.52,3.53
"NCNN - Target: Vulkan GPU - Model: blazeface (ms)",LIB,1.75,1.78,1.74,1.77
"NCNN - Target: Vulkan GPU - Model: googlenet (ms)",LIB,4.16,4.23,4.23,4.21
"NCNN - Target: Vulkan GPU - Model: vgg16 (ms)",LIB,5.26,5.25,5.25,5.26
"NCNN - Target: Vulkan GPU - Model: resnet18 (ms)",LIB,2.16,2.18,2.17,2.20
"NCNN - Target: Vulkan GPU - Model: alexnet (ms)",LIB,1.63,1.63,1.65,1.62
"NCNN - Target: Vulkan GPU - Model: resnet50 (ms)",LIB,4.27,4.28,4.32,4.32
"NCNN - Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 (ms)",LIB,4.89,4.92,4.92,4.91
"NCNN - Target: Vulkan GPU - Model: yolov4-tiny (ms)",LIB,6.79,6.80,6.81,6.82
"NCNN - Target: Vulkan GPU - Model: squeezenet_ssd (ms)",LIB,5.43,5.47,5.48,5.43
"NCNN - Target: Vulkan GPU - Model: regnety_400m (ms)",LIB,14.78,14.74,14.77,15.22
"NCNN - Target: Vulkan GPU - Model: vision_transformer (ms)",LIB,31.52,32.32,31.92,31.13
"NCNN - Target: Vulkan GPU - Model: FastestDet (ms)",LIB,3.09,3.10,3.08,3.12