AMD Ryzen 9 9950X DDR5 memory module benchmarks by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2408225-NE-RYZEN999510
AMD Ryzen 9 9950X DDR5 Memory Performance
AMD Ryzen 9 9950X DDR5 memory module benchmarks by Michael Larabel for a future article.
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G:
Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 16GB DDR5-6000MT/s G Skill F5-6000J3038F16G, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32:
Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36:
Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 16GB DDR5-8000MT/s Corsair CMH32GX5M2X8000C36, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38:
Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2204 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 24GB DDR5-8000MT/s Corsair CMP48GX5M2X8000C38, Disk: 2000GB Corsair MP700 PRO, Graphics: AMD Radeon RX 7900 GRE 16GB, Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160
RAMspeed SMP 3.5.0
Type: Add - Benchmark: Integer
MB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 61079.93 |=======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 63967.70 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 65113.52 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 62771.00 |=======================
RAMspeed SMP 3.5.0
Type: Copy - Benchmark: Integer
MB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 65797.05 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 70747.00 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 70345.53 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 66545.24 |=======================
RAMspeed SMP 3.5.0
Type: Scale - Benchmark: Integer
MB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 69141.08 |=======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 71754.58 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 73724.88 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 70445.74 |=======================
RAMspeed SMP 3.5.0
Type: Triad - Benchmark: Integer
MB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 62428.70 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 65845.21 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 66963.03 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 64832.86 |=======================
RAMspeed SMP 3.5.0
Type: Average - Benchmark: Integer
MB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 65503.93 |=======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 68588.84 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 69491.42 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 66822.49 |=======================
MBW 2018-09-08
Test: Memory Copy - Array Size: 4096 MiB
MiB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 22774.95 |========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 22510.46 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 22539.72 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 22093.99 |=======================
MBW 2018-09-08
Test: Memory Copy - Array Size: 8192 MiB
MiB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 22247.78 |=======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 22294.06 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 22817.90 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 21444.00 |=======================
MBW 2018-09-08
Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB
MiB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 19534.16 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 20817.57 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 20923.99 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 19747.58 |=======================
MBW 2018-09-08
Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB
MiB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 19467.39 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 20850.88 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 20349.41 |=======================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 20124.94 |=======================
Etcpak 2.0
Benchmark: Multi-Threaded - Configuration: ETC2
Mpx/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 741.78 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 739.74 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 734.53 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 731.23 |==========================
High Performance Conjugate Gradient 3.1
X Y Z: 104 104 104 - RT: 60
GFLOP/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 8.93560 |=======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 8.79737 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 9.51601 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 9.16590 |========================
NAS Parallel Benchmarks 3.4
Test / Class: BT.C
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 55287.37 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 58570.77 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 60124.08 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 58570.03 |=======================
NAS Parallel Benchmarks 3.4
Test / Class: CG.C
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 11144.88 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 11374.51 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 11908.47 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 11662.44 |========================
NAS Parallel Benchmarks 3.4
Test / Class: EP.C
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 3678.46 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 3731.97 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 3741.86 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 3722.56 |=========================
NAS Parallel Benchmarks 3.4
Test / Class: EP.D
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 3823.80 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 3714.66 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 3739.16 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 3712.45 |========================
NAS Parallel Benchmarks 3.4
Test / Class: FT.C
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 27106.18 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 28891.86 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 29713.55 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 28743.49 |=======================
NAS Parallel Benchmarks 3.4
Test / Class: IS.D
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1505.47 |=======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1584.93 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1635.34 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1586.59 |========================
NAS Parallel Benchmarks 3.4
Test / Class: LU.C
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 59920.96 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 62084.72 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 64031.31 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 62375.43 |=======================
NAS Parallel Benchmarks 3.4
Test / Class: MG.C
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 24236.21 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 25622.93 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 26596.46 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 25715.34 |=======================
NAS Parallel Benchmarks 3.4
Test / Class: SP.B
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 21328.28 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 22908.58 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 23254.40 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 22436.81 |=======================
NAS Parallel Benchmarks 3.4
Test / Class: SP.C
Total Mop/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 14528.26 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 15610.30 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 16097.00 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 15531.76 |=======================
LeelaChessZero 0.31.1
Backend: BLAS
Nodes Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 226 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 244 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 264 |=============================
LeelaChessZero 0.31.1
Backend: Eigen
Nodes Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 220 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 236 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 247 |=============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 227 |===========================
Quicksilver 20230818
Input: CORAL2 P1
Figure Of Merit > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 25676667 |========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 25660000 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 25666667 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 25136667 |=======================
miniBUDE 20210901
Implementation: OpenMP - Input Deck: BM1
GFInst/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1922.13 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1926.89 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1903.04 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1899.80 |=========================
miniBUDE 20210901
Implementation: OpenMP - Input Deck: BM1
Billion Interactions/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 76.89 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 77.08 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 76.12 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 75.99 |===========================
miniBUDE 20210901
Implementation: OpenMP - Input Deck: BM2
GFInst/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1934.61 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1931.14 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1904.95 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1898.26 |=========================
miniBUDE 20210901
Implementation: OpenMP - Input Deck: BM2
Billion Interactions/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 77.39 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 77.25 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 76.20 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 75.93 |==========================
NAMD 3.0b6
Input: ATPase with 327,506 Atoms
ns/day > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 3.41007 |========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 3.60464 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 3.57755 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 3.50958 |========================
NAMD 3.0b6
Input: STMV with 1,066,628 Atoms
ns/day > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 0.98084 |========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1.01602 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1.02426 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 0.99852 |========================
Xcompact3d Incompact3d 2021-03-11
Input: input.i3d 129 Cells Per Direction
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 14.09 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 13.40 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 12.97 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 13.26 |=========================
Xcompact3d Incompact3d 2021-03-11
Input: input.i3d 193 Cells Per Direction
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 64.11 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 60.80 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 58.20 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 60.48 |=========================
OpenFOAM 10
Input: motorBike - Mesh Time
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 84.99 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 84.98 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 88.08 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 85.47 |==========================
OpenFOAM 10
Input: motorBike - Execution Time
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 58.57 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 57.25 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 55.57 |==========================
OpenFOAM 10
Input: drivaerFastback, Small Mesh Size - Mesh Time
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 22.58 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 22.82 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 23.14 |===========================
OpenFOAM 10
Input: drivaerFastback, Small Mesh Size - Execution Time
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 157.15 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 148.76 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 145.88 |========================
OpenFOAM 10
Input: drivaerFastback, Medium Mesh Size - Mesh Time
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 181.57 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 177.79 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 174.13 |=========================
OpenFOAM 10
Input: drivaerFastback, Medium Mesh Size - Execution Time
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 2096.57 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1994.75 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1909.67 |=======================
OpenRadioss 2023.09.15
Model: Bumper Beam
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 76.90 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 77.18 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 77.45 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 77.81 |===========================
OpenRadioss 2023.09.15
Model: Chrysler Neon 1M
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 705.55 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 668.16 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 573.33 |=====================
OpenRadioss 2023.09.15
Model: Cell Phone Drop Test
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 44.90 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 43.42 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 43.25 |==========================
OpenRadioss 2023.09.15
Model: Bird Strike on Windshield
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 128.76 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 128.01 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 128.32 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 124.37 |=========================
OpenRadioss 2023.09.15
Model: Rubber O-Ring Seal Installation
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 53.16 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 53.23 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 53.66 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 54.27 |===========================
OpenRadioss 2023.09.15
Model: INIVOL and Fluid Structure Interaction Drop Container
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 247.06 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 239.22 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 242.00 |=========================
SPECFEM3D 4.1.1
Model: Mount St. Helens
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 25.69 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 24.96 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 25.19 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 25.45 |===========================
SPECFEM3D 4.1.1
Model: Layered Halfspace
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 73.14 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 69.44 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 69.82 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 72.44 |===========================
SPECFEM3D 4.1.1
Model: Tomographic Model
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 23.36 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 23.00 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 23.29 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 23.87 |===========================
SPECFEM3D 4.1.1
Model: Homogeneous Halfspace
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 30.68 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 29.82 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 30.54 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 31.98 |===========================
SPECFEM3D 4.1.1
Model: Water-layered Halfspace
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 72.20 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 69.56 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 68.92 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 72.08 |===========================
LULESH 2.0.3
z/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 9945.53 |=======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 10235.72 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 10578.52 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 9832.64 |======================
LuxCoreRender 2.6
Scene: DLSC - Acceleration: CPU
M samples/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 5.40 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 5.42 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 5.36 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 5.34 |============================
LuxCoreRender 2.6
Scene: Danish Mood - Acceleration: CPU
M samples/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 4.62 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 4.69 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 4.65 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 4.60 |===========================
LuxCoreRender 2.6
Scene: Orange Juice - Acceleration: CPU
M samples/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 8.64 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 8.64 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 8.55 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 8.46 |===========================
LuxCoreRender 2.6
Scene: LuxCore Benchmark - Acceleration: CPU
M samples/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 5.15 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 5.14 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 5.04 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 5.05 |===========================
LuxCoreRender 2.6
Scene: Rainbow Colors and Prism - Acceleration: CPU
M samples/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 19.99 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 20.08 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 19.84 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 19.33 |==========================
Embree 4.3
Binary: Pathtracer ISPC - Model: Crown
Frames Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 36.55 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 36.11 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 36.25 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 35.18 |==========================
Embree 4.3
Binary: Pathtracer ISPC - Model: Asian Dragon
Frames Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 41.49 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 40.94 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 41.72 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 40.07 |==========================
x265
Video Input: Bosphorus 4K
Frames Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 38.27 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 38.30 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 38.07 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 37.09 |==========================
x265
Video Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 134.52 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 134.48 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 134.19 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 131.28 |=========================
7-Zip Compression
Test: Compression Rating
MIPS > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 195585 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 203065 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 200810 |==========================
7-Zip Compression
Test: Decompression Rating
MIPS > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 158133 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 157512 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 157005 |==========================
Stockfish
Chess Benchmark
Nodes Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 51377778 |========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 49194155 |=======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 49974210 |=======================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 50101396 |=======================
Timed Gem5 Compilation 23.0.1
Time To Compile
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 221.14 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 219.27 |==========================
Timed Linux Kernel Compilation 6.8
Build: defconfig
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 47.76 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 47.78 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 48.26 |===========================
Timed Linux Kernel Compilation 6.8
Build: allmodconfig
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 590.50 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 589.33 |==========================
Timed LLVM Compilation 16.0
Build System: Ninja
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 301.63 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 298.05 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 304.62 |==========================
Timed Node.js Compilation 21.7.2
Time To Compile
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 345.25 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 341.68 |==========================
Build2 0.17
Time To Compile
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 76.00 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 77.01 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 77.92 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 80.10 |===========================
Y-Cruncher 0.8.5
Pi Digits To Calculate: 1B
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 16.45 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 15.43 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 15.61 |==========================
Y-Cruncher 0.8.5
Pi Digits To Calculate: 500M
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 7.587 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 7.247 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 7.236 |==========================
POV-Ray
Trace Time
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 16.10 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 16.13 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 16.40 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 16.32 |===========================
Memcached 1.6.19
Set To Get Ratio: 1:10
Ops/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 5915791.34 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 5898565.34 |======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 5874747.73 |======================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 5694123.52 |=====================
Memcached 1.6.19
Set To Get Ratio: 1:100
Ops/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 7507615.73 |======================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 7647187.48 |======================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 7498825.19 |======================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 7350932.88 |=====================
GROMACS 2024
Implementation: MPI CPU - Input: water_GMX50_bare
Ns Per Day > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 3.141 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 3.228 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 3.298 |===========================
GROMACS
Input: water_GMX50_bare
Ns Per Day > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1.927 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1.996 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 2.009 |===========================
PyTorch 2.2.1
Device: CPU - Batch Size: 1 - Model: ResNet-50
batches/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 84.89 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 85.52 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 86.79 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 81.89 |=========================
PyTorch 2.2.1
Device: CPU - Batch Size: 256 - Model: ResNet-50
batches/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 57.54 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 58.89 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 58.49 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 56.19 |==========================
TensorFlow 2.16.1
Device: CPU - Batch Size: 1 - Model: ResNet-50
images/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 16.92 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 17.34 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 17.33 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 16.81 |==========================
TensorFlow 2.16.1
Device: CPU - Batch Size: 64 - Model: ResNet-50
images/sec > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 52.27 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 54.30 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 55.19 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 53.54 |==========================
Stress-NG 0.17.08
Test: Memory Copying
Bogo Ops/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 10752.81 |========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 10720.31 |========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 10608.96 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 10608.82 |========================
XNNPACK 2cd86b
Model: FP32MobileNetV2
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1264 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1273 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1272 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1285 |============================
XNNPACK 2cd86b
Model: FP32MobileNetV3Large
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1516 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1527 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1553 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1590 |============================
XNNPACK 2cd86b
Model: FP32MobileNetV3Small
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 812 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 815 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 818 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 836 |=============================
XNNPACK 2cd86b
Model: FP16MobileNetV2
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 985 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 996 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 997 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1018 |============================
XNNPACK 2cd86b
Model: FP16MobileNetV3Large
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1291 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1303 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1302 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1334 |============================
XNNPACK 2cd86b
Model: FP16MobileNetV3Small
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 770 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 776 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 773 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 797 |=============================
XNNPACK 2cd86b
Model: QU8MobileNetV2
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 759 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 765 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 765 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 783 |=============================
XNNPACK 2cd86b
Model: QU8MobileNetV3Large
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1118 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1115 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1124 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1154 |============================
XNNPACK 2cd86b
Model: QU8MobileNetV3Small
us < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 756 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 761 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 764 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 786 |=============================
Blender 4.2
Blend File: BMW27 - Compute: CPU-Only
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 46.38 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 46.56 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 47.72 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 47.51 |===========================
Blender 4.2
Blend File: Junkshop - Compute: CPU-Only
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 62.09 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 62.21 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 63.41 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 64.08 |===========================
Blender 4.2
Blend File: Barbershop - Compute: CPU-Only
Seconds < Lower Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 448.96 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 450.71 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 459.12 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 459.19 |==========================
Llama.cpp b3067
Model: Meta-Llama-3-8B-Instruct-Q8_0.gguf
Tokens Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 8.36 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 8.32 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 9.00 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 8.66 |===========================
Llamafile 0.8.6
Test: Meta-Llama-3-8B-Instruct.F16 - Acceleration: CPU
Tokens Per Second > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G . 4.68 |==============================
Java JMH
Throughput
Ops/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 91554717298.43 |==================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 92045826799.54 |==================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 89012581592.65 |=================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 90340365706.79 |==================
BRL-CAD 7.38.2
VGR Performance Metric
VGR Performance Metric > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 498966 |==========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 494437 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 486954 |=========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 489784 |==========================
libxsmm 2-1.17-3645
M N K: 128
GFLOPS/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 472.0 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 505.9 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 508.9 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 491.1 |==========================
libxsmm 2-1.17-3645
M N K: 32
GFLOPS/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 121.0 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 128.0 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 132.2 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 127.0 |==========================
libxsmm 2-1.17-3645
M N K: 64
GFLOPS/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 237.1 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 253.3 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 258.6 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 249.7 |==========================
simdjson 3.10
Throughput Test: Kostya
GB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 7.71 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 7.63 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 7.57 |===========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 7.50 |===========================
simdjson 3.10
Throughput Test: TopTweet
GB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 13.59 |===========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 13.38 |===========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 13.24 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 12.88 |==========================
simdjson 3.10
Throughput Test: LargeRandom
GB/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 2.12 |============================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 2.11 |============================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 2.10 |============================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 2.11 |============================
Xmrig 6.21
Variant: GhostRider - Hash Count: 1M
H/s > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 3616.6 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 3638.6 |==========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 3699.6 |==========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 3676.5 |==========================
Numpy Benchmark
Score > Higher Is Better
2 x 16GB DDR5-6000 CL30 F5-6000J3038F16G ... 1068.36 |=========================
2 x 32GB DDR5-6400 CL32 CMK64GX5M2B6400C32 . 1070.61 |=========================
2 x 16GB DDR5-8000 CL36 CMH32GX5M2X8000C36 . 1046.91 |========================
2 x 24GB DDR5-8000 CL38 CMP48GX5M2X8000C38 . 1064.17 |=========================