Granite Rapids MRDIMM vs. DDR5 Benchmarks

Benchmarks for a future article. 2 x Intel Xeon 6980P testing with a Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2410037-NE-2410039NE61
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

C++ Boost Tests 2 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 3 Tests
CPU Massive 8 Tests
Database Test Suite 2 Tests
Fortran Tests 4 Tests
HPC - High Performance Computing 9 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 3 Tests
Memory Test Suite 3 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 5 Tests
Multi-Core 9 Tests
OpenMPI Tests 10 Tests
Programmer / Developer System Benchmarks 4 Tests
Python Tests 2 Tests
Scientific Computing 6 Tests
Server 2 Tests
Server CPU Tests 4 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
24 x DDR5-6400
October 03
  4 Hours, 28 Minutes
24 x MRDIMM 88800
September 30
  6 Hours, 46 Minutes
Invert Hiding All Results Option
  5 Hours, 37 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

24 x MRDIMM 88800

Processor: 2 x Intel Xeon 6980P @ 3.90GHz (256 Cores / 512 Threads), Motherboard: Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 1520GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92 + 960GB SAMSUNG MZ1L2960HCJR-00A07, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected

24 x DDR5-6400

Processor: 2 x Intel Xeon 6980P @ 3.90GHz (256 Cores / 512 Threads), Motherboard: Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 1520GB, Disk: 960GB SAMSUNG MZ1L2960HCJR-00A07 + 2 x 3201GB KIOXIA KCMYXVUG3T20, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2

OS: Ubuntu 24.04, Kernel: 6.8.0-22-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Granite Rapids MRDIMM vs. DDR5 BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen Resolution24 x MRDIMM 8880024 x DDR5-64002 x Intel Xeon 6980P @ 3.90GHz (256 Cores / 512 Threads)Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS)Intel Ice Lake IEH1520GB2 x 1920GB KIOXIA KCD8XPUG1T92 + 960GB SAMSUNG MZ1L2960HCJR-00A07ASPEEDIntel I210 + 2 x Intel 10-Gigabit X540-AT2Ubuntu 24.046.10.0-phx (x86_64)GCC 13.2.0ext41920x1200960GB SAMSUNG MZ1L2960HCJR-00A07 + 2 x 3201GB KIOXIA KCMYXVUG3T206.8.0-22-generic (x86_64)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0Java Details- OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Details- Python 3.12.2Security Details- 24 x MRDIMM 88800: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected - 24 x DDR5-6400: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

24 x MRDIMM 88800 vs. 24 x DDR5-6400 ComparisonPhoronix Test SuiteBaseline+11.6%+11.6%+23.2%+23.2%+34.8%+34.8%+46.4%+46.4%34.1%34%2%Chrysler Neon 1M46.5%100 - 1000 - Read Only - Average Latency100 - 1000 - Read Only144 144 144 - 6032.4%104 104 104 - 6030.7%d.S.M.S - Mesh Time23.4%X.b.i.i23.4%MG.C23%d.M.M.S - Mesh Time14%IS.D12.7%Scale12.2%d.M.M.S - Execution Time11.3%i.i.1.C.P.D10.4%Memory Copy - 8192 MiB7.7%SP.B7%Layered Halfspace6.5%BT.C5.9%H.H5.9%Add5.6%Writes5.6%LU.C4.6%CG.C4%W.l.H3.8%d.S.M.S - Execution Time3.3%EP.DOpenRadiossPostgreSQLPostgreSQLHigh Performance Conjugate GradientHigh Performance Conjugate GradientOpenFOAMXcompact3d Incompact3dNAS Parallel BenchmarksOpenFOAMNAS Parallel BenchmarksStreamOpenFOAMXcompact3d Incompact3dMBWNAS Parallel BenchmarksSPECFEM3DNAS Parallel BenchmarksSPECFEM3DStreamApache CassandraNAS Parallel BenchmarksNAS Parallel BenchmarksSPECFEM3DOpenFOAMNAS Parallel Benchmarks24 x MRDIMM 8880024 x DDR5-6400

Granite Rapids MRDIMM vs. DDR5 Benchmarksmbw: Memory Copy - 8192 MiBmbw: Memory Copy, Fixed Block Size - 8192 MiBtinymembench: Standard Memcpytinymembench: Standard Memsetstream: Copystream: Scalestream: Addstream: Triadspecfem3d: Layered Halfspaceopenradioss: Chrysler Neon 1Mspecfem3d: Tomographic Modelspecfem3d: Mount St. Helensspecfem3d: Homogeneous Halfspacegromacs: MPI CPU - water_GMX50_barespecfem3d: Water-layered Halfspacehpcg: 104 104 104 - 60hpcg: 144 144 144 - 60npb: BT.Cnpb: EP.Dnpb: LU.Cnpb: SP.Bnpb: IS.Dnpb: MG.Cnpb: CG.Cpennant: leblancbigpennant: sedovbigamg: lulesh: openfoam: drivaerFastback, Small Mesh Size - Mesh Timeopenfoam: drivaerFastback, Small Mesh Size - Execution Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeincompact3d: input.i3d 193 Cells Per Directionincompact3d: X3D-benchmarking input.i3djava-jmh: Throughputbuild-llvm: Ninjabuild-llvm: Unix Makefilesbuild-linux-kernel: defconfigbuild-linux-kernel: allmodconfigbuild-nodejs: Time To Compilecassandra: Writespgbench: 100 - 800 - Read Writepgbench: 100 - 800 - Read Write - Average Latencypgbench: 100 - 800 - Read Onlypgbench: 100 - 800 - Read Only - Average Latencypgbench: 100 - 1000 - Read Writepgbench: 100 - 1000 - Read Write - Average Latencylibxsmm: 128pgbench: 100 - 1000 - Read Onlylibxsmm: 64pgbench: 100 - 1000 - Read Only - Average Latency24 x MRDIMM 8880024 x DDR5-640015316.4138766.21315008.930001.0861560.8952124.6937751.9879963.67.11355356160.824.3799271793.9554891795.41776132133.3069.216693066170.946169.491804396.2632324.72769386.67373559.4615638.56449470.32118207.171.3427686.4726718606553000124013.2723.41625618.389208137.8487171.9363342.6202349769.8064524790759705068.8176.600198.67723.431131.839138.989870631445255.3725091601.5961375772.6927398.54756214501.42.12114219.8228683.00715023.630044.8870313.7848431.9887756.1893252.77.57659414189.115.7354518129.566090575130.836128.043759415.2132963.42735889.76349232.5113871.96365424.17113647.2328.9064718.999965157.0874280.0466312.8929663586.1528244824801420756.3115039501.5951368673.0786374581.582OpenBenchmarking.org

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 8192 MiB24 x DDR5-640024 x MRDIMM 888003K6K9K12K15KSE +/- 119.22, N = 8SE +/- 26.98, N = 314219.8215316.411. (CC) gcc options: -O3 -march=native
MinAvgMax24 x MRDIMM 88800204.6291.3297.2OpenBenchmarking.orgWatts, Fewer Is BetterMBW 2018-09-08System Power Consumption Monitor701402102803501. 24 x MRDIMM 88800: Approximate power consumption of 3399 Joules per run.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB24 x DDR5-640024 x MRDIMM 888002K4K6K8K10KSE +/- 35.08, N = 3SE +/- 34.71, N = 38683.018766.211. (CC) gcc options: -O3 -march=native
MinAvgMax24 x MRDIMM 88800200.8289.6295.1OpenBenchmarking.orgWatts, Fewer Is BetterMBW 2018-09-08System Power Consumption Monitor701402102803501. 24 x MRDIMM 88800: Approximate power consumption of 5503 Joules per run.

Tinymembench

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memcpy24 x DDR5-640024 x MRDIMM 888003K6K9K12K15KSE +/- 0.23, N = 3SE +/- 10.01, N = 315023.615008.91. (CC) gcc options: -O2 -lm

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memset24 x DDR5-640024 x MRDIMM 888006K12K18K24K30KSE +/- 3.48, N = 3SE +/- 19.60, N = 330044.830001.01. (CC) gcc options: -O2 -lm
MinAvgMax24 x MRDIMM 88800213.8286.2394.6OpenBenchmarking.orgWatts, Fewer Is BetterTinymembench 2018-05-28System Power Consumption Monitor1102203304405501. 24 x MRDIMM 88800: Approximate power consumption of 12594 Joules per run.

Stream

This is a benchmark of Stream, the popular system memory (RAM) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copy24 x DDR5-640024 x MRDIMM 88800200K400K600K800K1000KSE +/- 5160.21, N = 25SE +/- 7612.22, N = 25870313.7861560.81. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp
MinAvgMax24 x MRDIMM 88800198585924OpenBenchmarking.orgWatts, Fewer Is BetterStream 2013-01-17System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 4700 Joules per run.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Scale24 x DDR5-640024 x MRDIMM 88800200K400K600K800K1000KSE +/- 18666.81, N = 5SE +/- 15910.14, N = 5848431.9952124.61. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Add24 x DDR5-640024 x MRDIMM 88800200K400K600K800K1000KSE +/- 19594.57, N = 5SE +/- 13677.37, N = 5887756.1937751.91. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triad24 x DDR5-640024 x MRDIMM 88800200K400K600K800K1000KSE +/- 18029.90, N = 5SE +/- 16674.48, N = 5893252.7879963.61. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp

QuantLib

Size: S

24 x MRDIMM 88800: The test run did not produce a result. E: sh: 1: exec: ./quantlib: not found

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Layered Halfspace24 x DDR5-640024 x MRDIMM 88800246810SE +/- 0.059546245, N = 3SE +/- 0.043473328, N = 37.5765941417.1135535611. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMax24 x MRDIMM 88800204422804OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 4498 Joules per run.

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1M24 x DDR5-640024 x MRDIMM 8880020406080100SE +/- 0.10, N = 3SE +/- 0.29, N = 389.1160.82
MinAvgMax24 x MRDIMM 88800209534864OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 10141 Joules per run.

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Tomographic Model24 x MRDIMM 888000.98551.9712.95653.9424.9275SE +/- 0.009660353, N = 34.3799271791. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMax24 x MRDIMM 88800198402790OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 3885 Joules per run.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Mount St. Helens24 x MRDIMM 888000.891.782.673.564.45SE +/- 0.025428571, N = 33.9554891791. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMax24 x MRDIMM 88800205429801OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 4151 Joules per run.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Homogeneous Halfspace24 x DDR5-640024 x MRDIMM 888001.29052.5813.87155.1626.4525SE +/- 0.044695936, N = 3SE +/- 0.013586641, N = 35.7354518125.4177613211. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMax24 x MRDIMM 88800201421756OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 4069 Joules per run.

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bare24 x MRDIMM 88800816243240SE +/- 0.08, N = 233.311. (CXX) g++ options: -O3 -lm
MinAvgMax24 x MRDIMM 88800184310809OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2024System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 63031 Joules per run.

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Water-layered Halfspace24 x DDR5-640024 x MRDIMM 888003691215SE +/- 0.071811125, N = 3SE +/- 0.111895654, N = 49.5660905759.2166930661. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMax24 x MRDIMM 88800204470805OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 4819 Joules per run.

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 6024 x DDR5-640024 x MRDIMM 888004080120160200SE +/- 0.48, N = 3SE +/- 0.19, N = 3130.84170.951. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
MinAvgMax24 x MRDIMM 888002239601108OpenBenchmarking.orgWatts, Fewer Is BetterHigh Performance Conjugate Gradient 3.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 28475 Joules per run.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 6024 x DDR5-640024 x MRDIMM 888004080120160200SE +/- 0.22, N = 3SE +/- 0.12, N = 3128.04169.491. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
MinAvgMax24 x MRDIMM 8880035410401107OpenBenchmarking.orgWatts, Fewer Is BetterHigh Performance Conjugate Gradient 3.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 59962 Joules per run.

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C24 x DDR5-640024 x MRDIMM 88800200K400K600K800K1000KSE +/- 553.04, N = 3SE +/- 1537.19, N = 3759415.21804396.261. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
MinAvgMax24 x MRDIMM 88800203476900OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 2540 Joules per run.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D24 x DDR5-640024 x MRDIMM 888007K14K21K28K35KSE +/- 90.50, N = 3SE +/- 1574.53, N = 1332963.4232324.721. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
MinAvgMax24 x MRDIMM 88800204435782OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 2345 Joules per run.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C24 x DDR5-640024 x MRDIMM 88800160K320K480K640K800KSE +/- 786.48, N = 3SE +/- 2025.53, N = 3735889.76769386.671. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
MinAvgMax24 x MRDIMM 88800205399760OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 1997 Joules per run.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B24 x DDR5-640024 x MRDIMM 8880080K160K240K320K400KSE +/- 2373.46, N = 3SE +/- 3986.08, N = 4349232.51373559.461. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
MinAvgMax24 x MRDIMM 88800220.3386.6564.3OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor1402804205607001. 24 x MRDIMM 88800: Approximate power consumption of 1836 Joules per run.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.D24 x DDR5-640024 x MRDIMM 888003K6K9K12K15KSE +/- 60.96, N = 3SE +/- 36.61, N = 313871.9615638.561. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
MinAvgMax24 x MRDIMM 88800202.8367.3498.6OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor1302603905206501. 24 x MRDIMM 88800: Approximate power consumption of 1959 Joules per run.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C24 x DDR5-640024 x MRDIMM 88800100K200K300K400K500KSE +/- 966.97, N = 3SE +/- 1588.36, N = 3365424.17449470.321. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
MinAvgMax24 x MRDIMM 88800201.5368.8500.7OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor1302603905206501. 24 x MRDIMM 88800: Approximate power consumption of 1844 Joules per run.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.C24 x DDR5-640024 x MRDIMM 8880030K60K90K120K150KSE +/- 1173.69, N = 3SE +/- 1589.02, N = 3113647.23118207.171. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
MinAvgMax24 x MRDIMM 88800199.6357.7502.0OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor1302603905206501. 24 x MRDIMM 88800: Approximate power consumption of 1788 Joules per run.

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbig24 x MRDIMM 888000.30210.60420.90631.20841.5105SE +/- 0.011876, N = 151.3427681. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMax24 x MRDIMM 88800200394681OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 1892 Joules per run.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbig24 x MRDIMM 88800246810SE +/- 0.009571, N = 36.4726711. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMax24 x MRDIMM 88800207455805OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 2731 Joules per run.

Algebraic Multi-Grid Benchmark

AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.224 x MRDIMM 888002000M4000M6000M8000M10000MSE +/- 17997194.71, N = 386065530001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
MinAvgMax24 x MRDIMM 88800194564954OpenBenchmarking.orgWatts, Fewer Is BetterAlgebraic Multi-Grid Benchmark 1.2System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 4514 Joules per run.

LULESH

LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.324 x MRDIMM 8880030K60K90K120K150KSE +/- 801.06, N = 15124013.271. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
MinAvgMax24 x MRDIMM 88800198496911OpenBenchmarking.orgWatts, Fewer Is BetterLULESH 2.0.3System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 3174 Joules per run.

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh Time24 x DDR5-640024 x MRDIMM 8880071421283528.9123.421. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution Time24 x DDR5-640024 x MRDIMM 8880051015202519.0018.391. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
MinAvgMax24 x MRDIMM 88800282523764OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10System Power Consumption Monitor2004006008001000

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh Time24 x DDR5-640024 x MRDIMM 88800306090120150157.09137.851. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution Time24 x DDR5-640024 x MRDIMM 888002040608010080.0571.941. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
MinAvgMax24 x MRDIMM 88800221652934OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10System Power Consumption Monitor2004006008001000

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Direction24 x DDR5-640024 x MRDIMM 888000.65091.30181.95272.60363.2545SE +/- 0.00797243, N = 3SE +/- 0.02984810, N = 32.892966352.620234971. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMax24 x MRDIMM 88800205424852OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 2260 Joules per run.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3d24 x DDR5-640024 x MRDIMM 8880020406080100SE +/- 0.38, N = 3SE +/- 0.04, N = 386.1569.811. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMax24 x MRDIMM 888002028071051OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 13994 Joules per run.

Java JMH

This very basic test profile runs the stock benchmark of the Java JMH benchmark via Maven. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/s, More Is BetterJava JMHThroughput24 x MRDIMM 88800200000M400000M600000M800000M1000000M790759705068.81
MinAvgMax24 x MRDIMM 88800206766882OpenBenchmarking.orgWatts, Fewer Is BetterJava JMHSystem Power Consumption Monitor2004006008001000

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Ninja24 x MRDIMM 8880020406080100SE +/- 0.18, N = 376.60
MinAvgMax24 x MRDIMM 88800203470858OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 7835 Joules per run.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix Makefiles24 x MRDIMM 888004080120160200SE +/- 1.12, N = 3198.68
MinAvgMax24 x MRDIMM 88800192359827OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 13993 Joules per run.

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfig24 x MRDIMM 88800612182430SE +/- 0.15, N = 1523.43
MinAvgMax24 x MRDIMM 88800198366848OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.8System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 2101 Joules per run.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfig24 x MRDIMM 88800306090120150SE +/- 0.82, N = 3131.84
MinAvgMax24 x MRDIMM 88800204555811OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.8System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 14801 Joules per run.

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To Compile24 x MRDIMM 88800306090120150SE +/- 1.02, N = 3138.99
MinAvgMax24 x MRDIMM 88800207445834OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 21.7.2System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 11726 Joules per run.

Apache Cassandra

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 5.0Test: Writes24 x DDR5-640024 x MRDIMM 8880020K40K60K80K100KSE +/- 1732.33, N = 9SE +/- 1099.82, N = 128248087063
MinAvgMax24 x MRDIMM 88800217.7372.0431.6OpenBenchmarking.orgWatts, Fewer Is BetterApache Cassandra 5.0System Power Consumption Monitor1102203304405501. 24 x MRDIMM 88800: Approximate power consumption of 9208 Joules per run.

PostgreSQL

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 800 - Mode: Read Write24 x DDR5-640024 x MRDIMM 888003K6K9K12K15KSE +/- 44.90, N = 3SE +/- 174.94, N = 314207144521. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency24 x DDR5-640024 x MRDIMM 888001326395265SE +/- 0.18, N = 3SE +/- 0.67, N = 356.3155.371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
MinAvgMax24 x MRDIMM 88800199.5339.2373.5OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 17System Power Consumption Monitor1002003004005001. 24 x MRDIMM 88800: Approximate power consumption of 8705 Joules per run.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 800 - Mode: Read Only24 x DDR5-640024 x MRDIMM 88800110K220K330K440K550KSE +/- 12217.99, N = 9SE +/- 19798.84, N = 125039505091601. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency24 x DDR5-640024 x MRDIMM 888000.35910.71821.07731.43641.7955SE +/- 0.037, N = 9SE +/- 0.058, N = 121.5951.5961. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
MinAvgMax24 x MRDIMM 88800197.7488.2566.6OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 17System Power Consumption Monitor1402804205607001. 24 x MRDIMM 88800: Approximate power consumption of 12326 Joules per run.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Write24 x DDR5-640024 x MRDIMM 888003K6K9K12K15KSE +/- 104.01, N = 3SE +/- 20.41, N = 313686137571. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency24 x DDR5-640024 x MRDIMM 888001632486480SE +/- 0.55, N = 3SE +/- 0.11, N = 373.0872.691. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
MinAvgMax24 x MRDIMM 88800204.9344.0378.0OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 17System Power Consumption Monitor1002003004005001. 24 x MRDIMM 88800: Approximate power consumption of 8944 Joules per run.

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 12824 x MRDIMM 8880016003200480064008000SE +/- 660.65, N = 67398.51. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2
MinAvgMax24 x MRDIMM 88800188.8310.1387.9OpenBenchmarking.orgWatts, Fewer Is Betterlibxsmm 2-1.17-3645System Power Consumption Monitor1002003004005001. 24 x MRDIMM 88800: Approximate power consumption of 12613 Joules per run.

PostgreSQL

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Only24 x DDR5-640024 x MRDIMM 88800140K280K420K560K700KSE +/- 18280.50, N = 12SE +/- 13155.72, N = 126374584756211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 6424 x MRDIMM 8880010002000300040005000SE +/- 244.26, N = 154501.41. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2
MinAvgMax24 x MRDIMM 88800203466879OpenBenchmarking.orgWatts, Fewer Is Betterlibxsmm 2-1.17-3645System Power Consumption Monitor20040060080010001. 24 x MRDIMM 88800: Approximate power consumption of 746 Joules per run.

PostgreSQL

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency24 x DDR5-640024 x MRDIMM 888000.47720.95441.43161.90882.386SE +/- 0.042, N = 12SE +/- 0.060, N = 121.5822.1211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
MinAvgMax24 x MRDIMM 88800201.1483.3564.2OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 17System Power Consumption Monitor1402804205607001. 24 x MRDIMM 88800: Approximate power consumption of 12164 Joules per run.

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System Monitoring24 x MRDIMM 888002004006008001000Min: 183.7 / Avg: 465.09 / Max: 1108.2

24 x MRDIMM 88800

Processor: 2 x Intel Xeon 6980P @ 3.90GHz (256 Cores / 512 Threads), Motherboard: Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 1520GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92 + 960GB SAMSUNG MZ1L2960HCJR-00A07, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 30 September 2024 14:18 by user phoronix.

24 x DDR5-6400

Processor: 2 x Intel Xeon 6980P @ 3.90GHz (256 Cores / 512 Threads), Motherboard: Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 1520GB, Disk: 960GB SAMSUNG MZ1L2960HCJR-00A07 + 2 x 3201GB KIOXIA KCMYXVUG3T20, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2

OS: Ubuntu 24.04, Kernel: 6.8.0-22-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 3 October 2024 10:26 by user phoronix.