Crucial DDR5 Memory Benchmarks - AMD Ryzen Crucial memory review benchmarks by Michael Larabel for a future article. DDR5-4800 Crucial: Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2400MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 DDR5-5200 Crucial: Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2600MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 DDR5-5600 Crucial: Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2800MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 DDR5-6000 GSKILL F5-6000J3038F16G: Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/3000MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160 NAS Parallel Benchmarks 3.4 Test / Class: IS.D Total Mop/s > Higher Is Better DDR5-4800 Crucial ................. 1132.47 |======================= DDR5-5200 Crucial ................. 1189.63 |========================= DDR5-5600 Crucial ................. 1234.06 |========================= DDR5-6000 GSKILL F5-6000J3038F16G . 1649.03 |================================== NAS Parallel Benchmarks 3.4 Test / Class: SP.C Total Mop/s > Higher Is Better DDR5-4800 Crucial ................. 10263.25 |======================== DDR5-5200 Crucial ................. 10678.40 |========================= DDR5-5600 Crucial ................. 11236.78 |========================== DDR5-6000 GSKILL F5-6000J3038F16G . 14295.24 |================================= Stream 2013-01-17 Type: Add MB/s > Higher Is Better DDR5-4800 Crucial ................. 36067.9 |========================= DDR5-5200 Crucial ................. 37460.9 |========================= DDR5-5600 Crucial ................. 39357.6 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 50039.7 |================================== Stream 2013-01-17 Type: Triad MB/s > Higher Is Better DDR5-4800 Crucial ................. 36119.7 |========================= DDR5-5200 Crucial ................. 37479.7 |========================= DDR5-5600 Crucial ................. 39385.6 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 50067.8 |================================== NAS Parallel Benchmarks 3.4 Test / Class: SP.B Total Mop/s > Higher Is Better DDR5-4800 Crucial ................. 16635.54 |======================== DDR5-5200 Crucial ................. 17428.05 |========================= DDR5-5600 Crucial ................. 18332.55 |========================== DDR5-6000 GSKILL F5-6000J3038F16G . 22999.92 |================================= Stream 2013-01-17 Type: Scale MB/s > Higher Is Better DDR5-4800 Crucial ................. 32611.1 |========================= DDR5-5200 Crucial ................. 33827.1 |========================== DDR5-5600 Crucial ................. 35521.5 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 45060.9 |================================== RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Integer MB/s > Higher Is Better DDR5-4800 Crucial ................. 57672.12 |======================== DDR5-5200 Crucial ................. 59626.94 |========================= DDR5-5600 Crucial ................. 63082.31 |========================== DDR5-6000 GSKILL F5-6000J3038F16G . 79494.88 |================================= Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction Seconds < Lower Is Better DDR5-4800 Crucial ................. 18.36 |==================================== DDR5-5200 Crucial ................. 17.55 |================================== DDR5-5600 Crucial ................. 16.68 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 13.38 |========================== RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Integer MB/s > Higher Is Better DDR5-4800 Crucial ................. 57863.54 |======================== DDR5-5200 Crucial ................. 59984.42 |========================= DDR5-5600 Crucial ................. 63505.69 |========================== DDR5-6000 GSKILL F5-6000J3038F16G . 79287.35 |================================= RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Floating Point MB/s > Higher Is Better DDR5-4800 Crucial ................. 57636.03 |======================== DDR5-5200 Crucial ................. 59788.30 |========================= DDR5-5600 Crucial ................. 62618.49 |========================== DDR5-6000 GSKILL F5-6000J3038F16G . 78883.29 |================================= RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Floating Point MB/s > Higher Is Better DDR5-4800 Crucial ................. 57705.06 |======================== DDR5-5200 Crucial ................. 60066.67 |========================= DDR5-5600 Crucial ................. 63282.09 |========================== DDR5-6000 GSKILL F5-6000J3038F16G . 78949.19 |================================= Stream 2013-01-17 Type: Copy MB/s > Higher Is Better DDR5-4800 Crucial ................. 50254.0 |========================= DDR5-5200 Crucial ................. 51828.3 |========================== DDR5-5600 Crucial ................. 54426.8 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 68650.4 |================================== RAMspeed SMP 3.5.0 Type: Average - Benchmark: Floating Point MB/s > Higher Is Better DDR5-4800 Crucial ................. 54316.91 |======================== DDR5-5200 Crucial ................. 56333.25 |========================= DDR5-5600 Crucial ................. 59071.14 |========================== DDR5-6000 GSKILL F5-6000J3038F16G . 73941.59 |================================= RAMspeed SMP 3.5.0 Type: Average - Benchmark: Integer MB/s > Higher Is Better DDR5-4800 Crucial ................. 54303.69 |======================== DDR5-5200 Crucial ................. 56191.85 |========================= DDR5-5600 Crucial ................. 59431.97 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 73776.86 |================================= RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Floating Point MB/s > Higher Is Better DDR5-4800 Crucial ................. 50185.11 |======================== DDR5-5200 Crucial ................. 52228.81 |========================= DDR5-5600 Crucial ................. 54896.92 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 68037.84 |================================= RAMspeed SMP 3.5.0 Type: Add - Benchmark: Integer MB/s > Higher Is Better DDR5-4800 Crucial ................. 50829.41 |======================== DDR5-5200 Crucial ................. 52635.90 |========================= DDR5-5600 Crucial ................. 56146.54 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 68724.81 |================================= RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Integer MB/s > Higher Is Better DDR5-4800 Crucial ................. 50696.47 |========================= DDR5-5200 Crucial ................. 52568.18 |========================= DDR5-5600 Crucial ................. 55484.33 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 68139.75 |================================= RAMspeed SMP 3.5.0 Type: Add - Benchmark: Floating Point MB/s > Higher Is Better DDR5-4800 Crucial ................. 51250.68 |========================= DDR5-5200 Crucial ................. 52756.42 |========================= DDR5-5600 Crucial ................. 55117.96 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 68527.11 |================================= Darktable 4.0.0 Test: Server Room - Acceleration: CPU-only Seconds < Lower Is Better DDR5-4800 Crucial ................. 3.117 |==================================== DDR5-5200 Crucial ................. 2.969 |================================== DDR5-5600 Crucial ................. 2.938 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 2.359 |=========================== OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time Seconds < Lower Is Better DDR5-4800 Crucial ................. 214.18 |=================================== DDR5-5200 Crucial ................. 204.19 |================================= DDR5-5600 Crucial ................. 196.26 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 164.69 |=========================== nekRS 22.0 Input: TurboPipe Periodic FLOP/s > Higher Is Better DDR5-4800 Crucial ................. 54139366667 |======================= DDR5-5200 Crucial ................. 56054366667 |======================== DDR5-5600 Crucial ................. 57673866667 |========================= DDR5-6000 GSKILL F5-6000J3038F16G . 70389466667 |============================== NAS Parallel Benchmarks 3.4 Test / Class: CG.C Total Mop/s > Higher Is Better DDR5-4800 Crucial ................. 9459.47 |========================== DDR5-5200 Crucial ................. 10041.11 |=========================== DDR5-5600 Crucial ................. 10111.12 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 12203.79 |================================= NAS Parallel Benchmarks 3.4 Test / Class: FT.C Total Mop/s > Higher Is Better DDR5-4800 Crucial ................. 20676.36 |========================== DDR5-5200 Crucial ................. 21328.14 |========================== DDR5-5600 Crucial ................. 22185.88 |============================ DDR5-6000 GSKILL F5-6000J3038F16G . 26587.49 |================================= NAS Parallel Benchmarks 3.4 Test / Class: BT.C Total Mop/s > Higher Is Better DDR5-4800 Crucial ................. 35720.43 |========================== DDR5-5200 Crucial ................. 36718.64 |=========================== DDR5-5600 Crucial ................. 37635.36 |=========================== DDR5-6000 GSKILL F5-6000J3038F16G . 45575.20 |================================= Darktable 4.0.0 Test: Masskrug - Acceleration: CPU-only Seconds < Lower Is Better DDR5-4800 Crucial ................. 3.630 |==================================== DDR5-5200 Crucial ................. 3.534 |=================================== DDR5-5600 Crucial ................. 3.510 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 2.853 |============================ SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 91.67 |============================= DDR5-5200 Crucial ................. 94.37 |============================== DDR5-5600 Crucial ................. 97.12 |=============================== DDR5-6000 GSKILL F5-6000J3038F16G . 110.75 |=================================== NAS Parallel Benchmarks 3.4 Test / Class: LU.C Total Mop/s > Higher Is Better DDR5-4800 Crucial ................. 38995.38 |=========================== DDR5-5200 Crucial ................. 39990.71 |============================ DDR5-5600 Crucial ................. 41426.36 |============================= DDR5-6000 GSKILL F5-6000J3038F16G . 47062.83 |================================= oneDNN 3.0 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 1.78174 |================================== DDR5-5200 Crucial ................. 1.71172 |================================= DDR5-5600 Crucial ................. 1.66794 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 1.47980 |============================ 7-Zip Compression 22.01 Test: Compression Rating MIPS > Higher Is Better DDR5-4800 Crucial ................. 129906 |============================= DDR5-5200 Crucial ................. 134635 |============================== DDR5-5600 Crucial ................. 135898 |============================== DDR5-6000 GSKILL F5-6000J3038F16G . 156104 |=================================== OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better DDR5-4800 Crucial ................. 601.84 |============================= DDR5-5200 Crucial ................. 623.46 |============================== DDR5-5600 Crucial ................. 635.91 |=============================== DDR5-6000 GSKILL F5-6000J3038F16G . 717.89 |=================================== OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 9.96 |===================================== DDR5-5200 Crucial ................. 9.62 |==================================== DDR5-5600 Crucial ................. 9.43 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 8.35 |=============================== SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 163.06 |============================== DDR5-5200 Crucial ................. 168.00 |=============================== DDR5-5600 Crucial ................. 169.84 |=============================== DDR5-6000 GSKILL F5-6000J3038F16G . 190.70 |=================================== SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 169.54 |============================== DDR5-5200 Crucial ................. 174.46 |=============================== DDR5-5600 Crucial ................. 176.37 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 195.54 |=================================== SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 122.74 |============================== DDR5-5200 Crucial ................. 125.16 |=============================== DDR5-5600 Crucial ................. 127.29 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 141.43 |=================================== dav1d 1.1 Video Input: Summer Nature 4K FPS > Higher Is Better DDR5-4800 Crucial ................. 317.87 |=============================== DDR5-5200 Crucial ................. 314.51 |============================== DDR5-5600 Crucial ................. 332.41 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 361.86 |=================================== Darktable 4.0.0 Test: Boat - Acceleration: CPU-only Seconds < Lower Is Better DDR5-4800 Crucial ................. 3.387 |==================================== DDR5-5200 Crucial ................. 3.331 |=================================== DDR5-5600 Crucial ................. 3.295 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 2.954 |=============================== SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 328.25 |=============================== DDR5-5200 Crucial ................. 335.44 |=============================== DDR5-5600 Crucial ................. 341.29 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 373.77 |=================================== Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed MB/s > Higher Is Better DDR5-4800 Crucial ................. 20.9 |================================= DDR5-5200 Crucial ................. 21.3 |================================= DDR5-5600 Crucial ................. 21.2 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 23.7 |===================================== GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better DDR5-4800 Crucial ................. 1.874 |================================ DDR5-5200 Crucial ................. 1.918 |================================= DDR5-5600 Crucial ................. 1.972 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 2.124 |==================================== SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 79.02 |================================ DDR5-5200 Crucial ................. 80.74 |================================= DDR5-5600 Crucial ................. 82.19 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 89.33 |==================================== dav1d 1.1 Video Input: Chimera 1080p 10-bit FPS > Higher Is Better DDR5-4800 Crucial ................. 724.53 |=============================== DDR5-5200 Crucial ................. 733.20 |=============================== DDR5-5600 Crucial ................. 732.68 |=============================== DDR5-6000 GSKILL F5-6000J3038F16G . 815.29 |=================================== SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 642.93 |=============================== DDR5-5200 Crucial ................. 658.94 |================================ DDR5-5600 Crucial ................. 666.43 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 717.75 |=================================== Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 26.24 |================================ DDR5-5200 Crucial ................. 26.60 |================================= DDR5-5600 Crucial ................. 26.93 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 29.18 |==================================== Xonotic 0.8.5 Resolution: 3840 x 2160 - Effects Quality: Low Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 278.22 |================================ DDR5-5200 Crucial ................. 284.04 |================================ DDR5-5600 Crucial ................. 283.65 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 308.97 |=================================== SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 278.40 |================================ DDR5-5200 Crucial ................. 282.81 |================================ DDR5-5600 Crucial ................. 286.50 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 307.77 |=================================== OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Items / Sec > Higher Is Better DDR5-4800 Crucial ................. 281 |================================== DDR5-5200 Crucial ................. 284 |=================================== DDR5-5600 Crucial ................. 287 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 310 |====================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed MB/s > Higher Is Better DDR5-4800 Crucial ................. 11.8 |================================== DDR5-5200 Crucial ................. 11.8 |================================== DDR5-5600 Crucial ................. 11.9 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 12.9 |===================================== SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 416.96 |================================ DDR5-5200 Crucial ................. 422.83 |================================= DDR5-5600 Crucial ................. 428.88 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 455.12 |=================================== Embree 4.0 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 22.98 |================================= DDR5-5200 Crucial ................. 23.33 |================================== DDR5-5600 Crucial ................. 23.16 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 24.96 |==================================== OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 63.84 |==================================== DDR5-5200 Crucial ................. 62.86 |=================================== DDR5-5600 Crucial ................. 61.67 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 59.00 |================================= OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better DDR5-4800 Crucial ................. 93.93 |================================ DDR5-5200 Crucial ................. 95.39 |================================= DDR5-5600 Crucial ................. 97.23 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 101.63 |=================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 20.05 |==================================== DDR5-5200 Crucial ................. 19.85 |==================================== DDR5-5600 Crucial ................. 19.82 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 18.66 |================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 298.98 |================================= DDR5-5200 Crucial ................. 302.02 |================================= DDR5-5600 Crucial ................. 302.46 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 321.21 |=================================== Darktable 4.0.0 Test: Server Rack - Acceleration: CPU-only Seconds < Lower Is Better DDR5-4800 Crucial ................. 0.246 |==================================== DDR5-5200 Crucial ................. 0.243 |==================================== DDR5-5600 Crucial ................. 0.238 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 0.229 |================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 215.66 |=================================== DDR5-5200 Crucial ................. 212.23 |================================== DDR5-5600 Crucial ................. 209.56 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 200.99 |================================= Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 27.82 |================================== DDR5-5200 Crucial ................. 28.27 |================================== DDR5-5600 Crucial ................. 28.63 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 29.84 |==================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 81.42 |================================== DDR5-5200 Crucial ................. 82.85 |================================== DDR5-5600 Crucial ................. 83.79 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 87.04 |==================================== RawTherapee Total Benchmark Time Seconds < Lower Is Better DDR5-4800 Crucial ................. 38.45 |==================================== DDR5-5200 Crucial ................. 37.91 |=================================== DDR5-5600 Crucial ................. 37.49 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 35.98 |================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 73.60 |==================================== DDR5-5200 Crucial ................. 72.36 |=================================== DDR5-5600 Crucial ................. 71.53 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 68.87 |================================== OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Seconds < Lower Is Better DDR5-4800 Crucial ................. 28.34 |==================================== DDR5-5200 Crucial ................. 27.96 |==================================== DDR5-5600 Crucial ................. 28.25 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 26.63 |================================== VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 21.33 |================================== DDR5-5200 Crucial ................. 21.85 |=================================== DDR5-5600 Crucial ................. 21.41 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 22.64 |==================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 76.31 |==================================== DDR5-5200 Crucial ................. 75.59 |==================================== DDR5-5600 Crucial ................. 74.76 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 72.12 |================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 78.60 |================================== DDR5-5200 Crucial ................. 79.35 |================================== DDR5-5600 Crucial ................. 80.23 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 83.14 |==================================== simdjson 2.0 Throughput Test: Kostya GB/s > Higher Is Better DDR5-4800 Crucial ................. 5.54 |=================================== DDR5-5200 Crucial ................. 5.56 |=================================== DDR5-5600 Crucial ................. 5.64 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 5.85 |===================================== SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 16.23 |=================================== DDR5-5200 Crucial ................. 16.24 |=================================== DDR5-5600 Crucial ................. 16.63 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 15.76 |================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better DDR5-4800 Crucial ................. 16905.91 |================================ DDR5-5200 Crucial ................. 17036.38 |================================ DDR5-5600 Crucial ................. 17347.88 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 16452.83 |=============================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 6.39 |==================================== DDR5-5200 Crucial ................. 6.33 |==================================== DDR5-5600 Crucial ................. 6.21 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 6.54 |===================================== SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 4.09 |==================================== DDR5-5200 Crucial ................. 4.09 |==================================== DDR5-5600 Crucial ................. 4.19 |===================================== DDR5-6000 GSKILL F5-6000J3038F16G . 3.98 |=================================== OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better DDR5-4800 Crucial ................. 1877.55 |================================= DDR5-5200 Crucial ................. 1895.49 |================================= DDR5-5600 Crucial ................. 1929.60 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 1833.24 |================================ Blender 3.4 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better DDR5-4800 Crucial ................. 75.68 |=================================== DDR5-5200 Crucial ................. 75.12 |=================================== DDR5-5600 Crucial ................. 73.40 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 77.19 |==================================== OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar Items / Sec > Higher Is Better DDR5-4800 Crucial ................. 137 |==================================== DDR5-5200 Crucial ................. 138 |==================================== DDR5-5600 Crucial ................. 139 |===================================== DDR5-6000 GSKILL F5-6000J3038F16G . 144 |====================================== miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 GFInst/s > Higher Is Better DDR5-4800 Crucial ................. 930.32 |================================== DDR5-5200 Crucial ................. 931.54 |================================== DDR5-5600 Crucial ................. 951.61 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 906.28 |================================= miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Billion Interactions/s > Higher Is Better DDR5-4800 Crucial ................. 37.21 |=================================== DDR5-5200 Crucial ................. 37.26 |=================================== DDR5-5600 Crucial ................. 38.06 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 36.25 |================================== OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 324.39 |================================== DDR5-5200 Crucial ................. 320.80 |================================== DDR5-5600 Crucial ................. 314.82 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 330.23 |=================================== oneDNN 3.0 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 1.11853 |================================= DDR5-5200 Crucial ................. 1.11001 |================================= DDR5-5600 Crucial ................. 1.08675 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 1.13968 |================================== OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better DDR5-4800 Crucial ................. 18.46 |=================================== DDR5-5200 Crucial ................. 18.67 |=================================== DDR5-5600 Crucial ................. 19.01 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 18.14 |================================== dav1d 1.1 Video Input: Chimera 1080p FPS > Higher Is Better DDR5-4800 Crucial ................. 849.63 |=================================== DDR5-5200 Crucial ................. 847.80 |=================================== DDR5-5600 Crucial ................. 820.13 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 859.06 |=================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 9.49 |==================================== DDR5-5200 Crucial ................. 9.47 |==================================== DDR5-5600 Crucial ................. 9.68 |===================================== DDR5-6000 GSKILL F5-6000J3038F16G . 9.25 |=================================== OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better DDR5-4800 Crucial ................. 1191.68 |================================= DDR5-5200 Crucial ................. 1201.72 |================================= DDR5-5600 Crucial ................. 1224.32 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 1171.24 |================================= OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 5.03 |==================================== DDR5-5200 Crucial ................. 4.99 |==================================== DDR5-5600 Crucial ................. 4.90 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 5.12 |===================================== SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 70.17 |================================== DDR5-5200 Crucial ................. 70.75 |=================================== DDR5-5600 Crucial ................. 72.33 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 73.24 |==================================== OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 0.70 |==================================== DDR5-5200 Crucial ................. 0.70 |==================================== DDR5-5600 Crucial ................. 0.69 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 0.72 |===================================== oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 840.10 |=================================== DDR5-5200 Crucial ................. 831.62 |================================== DDR5-5600 Crucial ................. 816.92 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 851.73 |=================================== dav1d 1.1 Video Input: Summer Nature 1080p FPS > Higher Is Better DDR5-4800 Crucial ................. 1261.98 |================================= DDR5-5200 Crucial ................. 1251.75 |================================= DDR5-5600 Crucial ................. 1264.01 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 1304.19 |================================== Timed PHP Compilation 8.1.9 Time To Compile Seconds < Lower Is Better DDR5-4800 Crucial ................. 41.92 |==================================== DDR5-5200 Crucial ................. 41.17 |=================================== DDR5-5600 Crucial ................. 41.06 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 40.26 |=================================== Timed Mesa Compilation 21.0 Time To Compile Seconds < Lower Is Better DDR5-4800 Crucial ................. 29.61 |==================================== DDR5-5200 Crucial ................. 29.15 |=================================== DDR5-5600 Crucial ................. 28.89 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 28.45 |=================================== oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 1647.12 |================================= DDR5-5200 Crucial ................. 1629.81 |================================= DDR5-5600 Crucial ................. 1608.99 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 1673.32 |================================== OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better DDR5-4800 Crucial ................. 5.07 |==================================== DDR5-5200 Crucial ................. 5.15 |==================================== DDR5-5600 Crucial ................. 5.22 |===================================== DDR5-6000 GSKILL F5-6000J3038F16G . 5.27 |===================================== OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 1178.22 |================================== DDR5-5200 Crucial ................. 1160.41 |================================= DDR5-5600 Crucial ................. 1141.51 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 1134.15 |================================= Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 47.02 |==================================== DDR5-5200 Crucial ................. 46.18 |=================================== DDR5-5600 Crucial ................. 45.27 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 46.24 |=================================== NAMD 2.14 ATPase Simulation - 327,506 Atoms days/ns < Lower Is Better DDR5-4800 Crucial ................. 1.17886 |================================== DDR5-5200 Crucial ................. 1.17476 |================================== DDR5-5600 Crucial ................. 1.14420 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 1.18817 |================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 127.59 |================================== DDR5-5200 Crucial ................. 129.90 |================================== DDR5-5600 Crucial ................. 132.48 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 129.67 |================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 32.49 |=================================== DDR5-5200 Crucial ................. 32.42 |=================================== DDR5-5600 Crucial ................. 33.12 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 31.91 |=================================== SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 54.61 |=================================== DDR5-5200 Crucial ................. 55.42 |=================================== DDR5-5600 Crucial ................. 56.34 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 56.65 |==================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Slow Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 44.98 |==================================== DDR5-5200 Crucial ................. 44.80 |=================================== DDR5-5600 Crucial ................. 45.61 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 43.97 |=================================== VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 40.94 |=================================== DDR5-5200 Crucial ................. 41.62 |=================================== DDR5-5600 Crucial ................. 41.36 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 42.46 |==================================== 7-Zip Compression 22.01 Test: Decompression Rating MIPS > Higher Is Better DDR5-4800 Crucial ................. 123754 |================================== DDR5-5200 Crucial ................. 125579 |================================== DDR5-5600 Crucial ................. 127567 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 123051 |================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 157.25 |================================== DDR5-5200 Crucial ................. 157.09 |================================== DDR5-5600 Crucial ................. 159.87 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 154.49 |================================== uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 132.03 |================================== DDR5-5200 Crucial ................. 132.02 |================================== DDR5-5600 Crucial ................. 134.55 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 130.04 |================================== Timed Godot Game Engine Compilation 3.2.3 Time To Compile Seconds < Lower Is Better DDR5-4800 Crucial ................. 71.33 |==================================== DDR5-5200 Crucial ................. 70.12 |=================================== DDR5-5600 Crucial ................. 70.17 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 69.03 |=================================== uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 38.32 |=================================== DDR5-5200 Crucial ................. 38.36 |=================================== DDR5-5600 Crucial ................. 39.07 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 37.82 |=================================== Build2 0.13 Time To Compile Seconds < Lower Is Better DDR5-4800 Crucial ................. 71.42 |==================================== DDR5-5200 Crucial ................. 70.23 |=================================== DDR5-5600 Crucial ................. 70.11 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 69.21 |=================================== Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 Images / Sec > Higher Is Better DDR5-4800 Crucial ................. 0.63 |==================================== DDR5-5200 Crucial ................. 0.63 |==================================== DDR5-5600 Crucial ................. 0.65 |===================================== DDR5-6000 GSKILL F5-6000J3038F16G . 0.64 |==================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 64.56 |=================================== DDR5-5200 Crucial ................. 64.25 |=================================== DDR5-5600 Crucial ................. 65.82 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 63.87 |=================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 92.92 |==================================== DDR5-5200 Crucial ................. 93.34 |==================================== DDR5-5600 Crucial ................. 91.14 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 93.90 |==================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 31.03 |=================================== DDR5-5200 Crucial ................. 31.28 |=================================== DDR5-5600 Crucial ................. 31.62 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 31.94 |==================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 686.52 |=================================== DDR5-5200 Crucial ................. 681.59 |================================== DDR5-5600 Crucial ................. 672.88 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 691.48 |=================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 682.16 |=================================== DDR5-5200 Crucial ................. 682.40 |=================================== DDR5-5600 Crucial ................. 672.38 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 690.18 |=================================== OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer ms < Lower Is Better DDR5-4800 Crucial ................. 44958 |==================================== DDR5-5200 Crucial ................. 44349 |==================================== DDR5-5600 Crucial ................. 43800 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 44702 |==================================== OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer ms < Lower Is Better DDR5-4800 Crucial ................. 53700 |==================================== DDR5-5200 Crucial ................. 52929 |=================================== DDR5-5600 Crucial ................. 52344 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 53153 |==================================== VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 9.96 |=================================== DDR5-5200 Crucial ................. 10.08 |==================================== DDR5-5600 Crucial ................. 10.14 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 10.21 |==================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 5.107 |=================================== DDR5-5200 Crucial ................. 5.118 |=================================== DDR5-5600 Crucial ................. 5.219 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 5.097 |=================================== OSPRay Studio 0.11 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer ms < Lower Is Better DDR5-4800 Crucial ................. 26806 |==================================== DDR5-5200 Crucial ................. 26472 |==================================== DDR5-5600 Crucial ................. 26189 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 26588 |==================================== Timed FFmpeg Compilation 4.4 Time To Compile Seconds < Lower Is Better DDR5-4800 Crucial ................. 29.36 |==================================== DDR5-5200 Crucial ................. 29.06 |==================================== DDR5-5600 Crucial ................. 28.69 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 29.16 |==================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 11.17 |=================================== DDR5-5200 Crucial ................. 11.23 |=================================== DDR5-5600 Crucial ................. 11.42 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 11.40 |==================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 8.7215 |================================== DDR5-5200 Crucial ................. 8.7768 |=================================== DDR5-5600 Crucial ................. 8.8641 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 8.6721 |================================== OSPRay Studio 0.11 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer ms < Lower Is Better DDR5-4800 Crucial ................. 22406 |==================================== DDR5-5200 Crucial ................. 22155 |==================================== DDR5-5600 Crucial ................. 21925 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 22349 |==================================== Timed MPlayer Compilation 1.5 Time To Compile Seconds < Lower Is Better DDR5-4800 Crucial ................. 21.02 |==================================== DDR5-5200 Crucial ................. 20.85 |==================================== DDR5-5600 Crucial ................. 20.60 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 21.01 |==================================== SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 219.59 |================================== DDR5-5200 Crucial ................. 219.76 |================================== DDR5-5600 Crucial ................. 224.13 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 220.53 |================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 8.7718 |=================================== DDR5-5200 Crucial ................. 8.7719 |=================================== DDR5-5600 Crucial ................. 8.8712 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 8.6916 |================================== Embree 4.0 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 23.92 |=================================== DDR5-5200 Crucial ................. 24.08 |==================================== DDR5-5600 Crucial ................. 24.40 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 24.29 |==================================== simdjson 2.0 Throughput Test: DistinctUserID GB/s > Higher Is Better DDR5-4800 Crucial ................. 9.63 |==================================== DDR5-5200 Crucial ................. 9.73 |===================================== DDR5-5600 Crucial ................. 9.81 |===================================== DDR5-6000 GSKILL F5-6000J3038F16G . 9.70 |===================================== simdjson 2.0 Throughput Test: TopTweet GB/s > Higher Is Better DDR5-4800 Crucial ................. 9.30 |==================================== DDR5-5200 Crucial ................. 9.40 |===================================== DDR5-5600 Crucial ................. 9.43 |===================================== DDR5-6000 GSKILL F5-6000J3038F16G . 9.26 |==================================== Embree 4.0 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 21.44 |=================================== DDR5-5200 Crucial ................. 21.60 |==================================== DDR5-5600 Crucial ................. 21.81 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 21.83 |==================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better DDR5-4800 Crucial ................. 29.68 |==================================== DDR5-5200 Crucial ................. 29.36 |==================================== DDR5-5600 Crucial ................. 29.15 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 29.34 |==================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better DDR5-4800 Crucial ................. 202.06 |================================== DDR5-5200 Crucial ................. 204.28 |=================================== DDR5-5600 Crucial ................. 205.73 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 204.37 |=================================== Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed MB/s > Higher Is Better DDR5-4800 Crucial ................. 1877.1 |================================== DDR5-5200 Crucial ................. 1903.1 |=================================== DDR5-5600 Crucial ................. 1908.4 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 1909.5 |=================================== OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better DDR5-4800 Crucial ................. 1103.40 |================================= DDR5-5200 Crucial ................. 1107.26 |================================== DDR5-5600 Crucial ................. 1120.29 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 1113.20 |================================== OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better DDR5-4800 Crucial ................. 5.43 |===================================== DDR5-5200 Crucial ................. 5.41 |===================================== DDR5-5600 Crucial ................. 5.35 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 5.39 |===================================== simdjson 2.0 Throughput Test: PartialTweets GB/s > Higher Is Better DDR5-4800 Crucial ................. 8.09 |===================================== DDR5-5200 Crucial ................. 8.13 |===================================== DDR5-5600 Crucial ................. 8.15 |===================================== DDR5-6000 GSKILL F5-6000J3038F16G . 8.03 |==================================== Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better DDR5-4800 Crucial ................. 62.97 |==================================== DDR5-5200 Crucial ................. 62.10 |==================================== DDR5-5600 Crucial ................. 62.28 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 62.40 |==================================== Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed MB/s > Higher Is Better DDR5-4800 Crucial ................. 2020.3 |=================================== DDR5-5200 Crucial ................. 2037.3 |=================================== DDR5-5600 Crucial ................. 2044.0 |=================================== DDR5-6000 GSKILL F5-6000J3038F16G . 2029.8 |=================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 12.62 |==================================== DDR5-5200 Crucial ................. 12.66 |==================================== DDR5-5600 Crucial ................. 12.76 |==================================== DDR5-6000 GSKILL F5-6000J3038F16G . 12.61 |==================================== ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inference Time Cost (ms) < Lower Is Better DDR5-4800 Crucial ................. 7.06313 |================================== DDR5-5200 Crucial ................. 7.05429 |================================== DDR5-5600 Crucial ................. 7.13655 |================================== DDR5-6000 GSKILL F5-6000J3038F16G . 6.06455 |============================= ONNX Runtime 1.14 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Second > Higher Is Better DDR5-4800 Crucial ................. 141.55 |============================== DDR5-5200 Crucial ................. 142.05 |============================== DDR5-5600 Crucial ................. 140.73 |============================== DDR5-6000 GSKILL F5-6000J3038F16G . 165.64 |=================================== SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 313.91 |=============================== DDR5-5200 Crucial ................. 320.16 |=============================== DDR5-5600 Crucial ................. 325.05 |================================ DDR5-6000 GSKILL F5-6000J3038F16G . 360.18 |=================================== SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 82.62 |============================= DDR5-5200 Crucial ................. 85.44 |============================== DDR5-5600 Crucial ................. 87.64 |============================== DDR5-6000 GSKILL F5-6000J3038F16G . 100.65 |=================================== SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better DDR5-4800 Crucial ................. 606.01 |================================= DDR5-5200 Crucial ................. 591.83 |================================ DDR5-5600 Crucial ................. 620.70 |================================= DDR5-6000 GSKILL F5-6000J3038F16G . 650.38 |===================================