AMD Ryzen 9 7900X Performance With ECC DDR5 Memory

Written by Michael Larabel in Memory on 5 October 2023 at 04:00 PM EDT. Page 2 of 5. 53 Comments.
NAS Parallel Benchmarks benchmark with settings of Test / Class: CG.C. ECC was the fastest.
NAS Parallel Benchmarks benchmark with settings of Test / Class: FT.C. ECC was the fastest.
NAS Parallel Benchmarks benchmark with settings of Test / Class: MG.C. ECC Disabled was the fastest.
NAMD benchmark with settings of ATPase Simulation, 327,506 Atoms. ECC was the fastest.
libxsmm benchmark with settings of M N K: 64. ECC Disabled was the fastest.
Laghos benchmark with settings of Test: Triple Point Problem. ECC was the fastest.
Laghos benchmark with settings of Test: Sedov Blast Wave, ube_922_hex.mesh. ECC Disabled was the fastest.
Xcompact3d Incompact3d benchmark with settings of Input: input.i3d 129 Cells Per Direction. ECC Disabled was the fastest.
OpenRadioss benchmark with settings of Model: Chrysler Neon 1M. ECC was the fastest.

Similar to what we've seen with ECC memory performance now for the past decade or so, the performance overhead of running with ECC memory enabled is very small to insignificant. In the vast majority of workloads tested, there wasn't any measurable difference from having ECC enabled.

RAMspeed SMP benchmark with settings of Type: Copy, Benchmark: Integer. ECC Disabled was the fastest.
RAMspeed SMP benchmark with settings of Type: Average, Benchmark: Integer. ECC Disabled was the fastest.
RAMspeed SMP benchmark with settings of Type: Triad, Benchmark: Floating Point. ECC Disabled was the fastest.
Tinymembench benchmark with settings of Standard Memcpy. ECC was the fastest.
MBW benchmark with settings of Test: Memory Copy, Array Size: 8192 MiB. ECC Disabled was the fastest.

Even for the synthetic memory benchmarks, only in a few cases like with MBW did it report any memory performance difference when running with ECC inactive.


Related Articles