Ryzen 9 3900X Memory Scaling Benchmarks

AMD Ryzen 9 3900X memory benchmarks on Linux for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1907047-HV-MEMORYTES32&grs&sor.

Ryzen 9 3900X Memory Scaling BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionDDR4-2600DDR4-2933DDR4-3000DDR4-3200DDR4-3400DDR4-3600DDR4-3800AMD Ryzen 9 3900X 12-Core @ 3.80GHz (12 Cores / 24 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (0066 BIOS)AMD Device 148016384MB2000GB Force MP600Sapphire AMD Baffin [Polaris11] 4GB (1300/1750MHz)AMD Device aae0ASUS VP28URealtek Device 8125 + Intel I211 + Intel Device 2723Ubuntu 18.045.2.0-999-generic (x86_64) 20190627GNOME Shell 3.28.3X Server 1.20.1modesetting 1.20.14.5 Mesa 18.2.2 (LLVM 7.0.0)GCC 7.4.0ext43840x21602000GB Force MP600 + 64GB Flash Drive2000GB Force MP600OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq ondemandJava Details- OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu218.04.1)Python Details- Python 2.7.15+ + Python 3.6.8Security Details- l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: always-on RSB filling

Ryzen 9 3900X Memory Scaling Benchmarksramspeed: Add - Floating Pointramspeed: Scale - Integerramspeed: Triad - Integerramspeed: Average - Integerramspeed: Triad - Floating Pointtinymembench: Standard Memcpyramspeed: Average - Floating Pointmbw: Memory Copy - 4096 MiBramspeed: Add - Integerramspeed: Copy - Floating Pointramspeed: Scale - Floating Pointmbw: Memory Copy, Fixed Block Size - 4096 MiBramspeed: Copy - Integertinymembench: Standard Memsetstream: Copycloverleaf: Lagrangian-Eulerian Hydrodynamicsdarktable: Server Rack - CPU-onlystream: Triadnpb: SP.Astream: Addparboil: OpenMP LBMdarktable: Boat - CPU-onlystream: Scalenpb: LU.Ccompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19darktable: Masskrug - CPU-onlydarktable: Server Room - CPU-onlyparboil: OpenMP CUTCPcp2k: Fayalite-FIST Datadacapobench: Tradebeansrodinia: OpenMP Streamclusternpb: BT.At-test1: 2dacapobench: H2build-llvm: Time To Compilecompress-7zip: Compress Speed Testvpxenc: vpxenc VP9 1080p Video Encodet-test1: 1dacapobench: Jythonjohn-the-ripper: Blowfishbuild-linux-kernel: Time To Compilepgbench: Buffer Test - Normal Load - Read Onlysvt-av1: 1080p 8-bit YUV To AV1 Video Encodex265: H.265 1080p Video Encodingnpb: EP.Capache-siege: 250DDR4-2600DDR4-2933DDR4-3000DDR4-3200DDR4-3400DDR4-3600DDR4-380024407.9521296.2424547.3823491.7125784.9315670.6024013.2915049.0025917.7422300.9922067.378209.2222449.7912743.2329638.043.870.2118127.484011.8118201.16159.0911.9215734.8620554.3619.464.943.692.31338.84431821.916191.117.393247293.5275996166.0520.5740832824047.96287832.4345.5751.65481.4635420.8227702.7823520.3827392.8925661.6627663.6716893.3525268.5516761.8526242.7023711.5823464.128972.9522990.9813528.0230565.243.780.2018422.564156.6318473.14155.5511.7216041.9820905.5818.814.823.652.26327.98424721.196287.047.273215288.0277127168.2320.6640952853547.70286245.9745.7551.85481.6635618.3828422.1223109.9527791.3626088.0628134.6517281.6826060.8816728.5226760.8924048.3923843.608918.2824113.9313944.9731245.103.690.2018836.894196.7018913.51152.3211.4616383.6521261.6218.644.773.602.25329.42423621.616302.297.233208288.7777403168.0220.5340752854647.83286901.8445.8451.75482.0236243.0530133.1724129.0629514.9026046.3129678.6818332.2327592.2917614.7728102.7725441.5725111.929333.0824349.7114495.7031772.283.760.2018471.244297.1018558.69154.4711.5916155.8321039.9418.624.753.642.23326.66417521.556365.607.203169291.4777626170.2820.4040222849847.66287137.0445.8551.90481.9935904.8128988.8824913.0230158.8227137.5430689.8518921.9728359.7518220.8631268.4326064.5325704.509572.3225065.6914548.0231772.193.690.2018788.934341.0418861.26152.1611.4516382.8821294.6718.244.723.612.20327.69414121.376378.477.133155288.7478070170.6920.5040382847547.90287495.9245.9251.88480.7934741.6332701.4227101.1331843.3829841.5432478.6520005.0728017.3519076.9532971.5027567.1027229.6110142.1727729.3414896.2032715.883.670.1919113.044410.0819210.34150.3411.2316602.4821491.3318.054.623.572.20327.02414021.016448.107.273183292.1078317169.1220.5340392847648.12287775.2245.6951.92482.2734559.7233448.8627762.0130646.7830421.6433133.6720027.0730641.6919171.0531771.9628318.2927971.469846.4625698.7914842.1032900.983.500.1919967.604286.8519972.44145.0010.8717172.5222301.0018.474.723.472.21323.90416121.176354.697.193136297.2278362169.2120.2140812868848.20288637.5645.6051.68481.9127601.72OpenBenchmarking.org

RAMspeed SMP

Type: Add - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating PointDDR4-3800DDR4-3600DDR4-3200DDR4-3400DDR4-3000DDR4-2933DDR4-26007K14K21K28K35KSE +/- 38.19, N = 20SE +/- 118.94, N = 20SE +/- 87.09, N = 20SE +/- 159.31, N = 20SE +/- 3.00, N = 2033448.8632701.4230133.1728988.8828422.1227702.7824407.951. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Scale - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: IntegerDDR4-3800DDR4-3600DDR4-3400DDR4-3200DDR4-2933DDR4-3000DDR4-26006K12K18K24K30KSE +/- 89.84, N = 20SE +/- 40.23, N = 20SE +/- 54.82, N = 20SE +/- 111.68, N = 20SE +/- 33.23, N = 2027762.0127101.1324913.0224129.0623520.3823109.9521296.241. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Triad - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: IntegerDDR4-3600DDR4-3800DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-26007K14K21K28K35KSE +/- 128.33, N = 20SE +/- 8.67, N = 20SE +/- 88.25, N = 20SE +/- 7.20, N = 20SE +/- 130.16, N = 2031843.3830646.7830158.8229514.9027791.3627392.8924547.381. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Average - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: IntegerDDR4-3800DDR4-3600DDR4-3400DDR4-3000DDR4-3200DDR4-2933DDR4-26007K14K21K28K35KSE +/- 135.97, N = 20SE +/- 48.49, N = 20SE +/- 81.80, N = 20SE +/- 7.17, N = 20SE +/- 138.27, N = 2030421.6429841.5427137.5426088.0626046.3125661.6623491.711. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Triad - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating PointDDR4-3800DDR4-3600DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-26007K14K21K28K35KSE +/- 132.40, N = 20SE +/- 149.21, N = 20SE +/- 133.22, N = 20SE +/- 134.97, N = 20SE +/- 82.21, N = 2033133.6732478.6530689.8529678.6828134.6527663.6725784.931. (CC) gcc options: -O3 -march=native

Tinymembench

Standard Memcpy

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard MemcpyDDR4-3800DDR4-3600DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-26004K8K12K16K20KSE +/- 48.20, N = 3SE +/- 56.85, N = 3SE +/- 27.24, N = 6SE +/- 9.10, N = 6SE +/- 28.03, N = 6SE +/- 6.95, N = 6SE +/- 6.30, N = 620027.0720005.0718921.9718332.2317281.6816893.3515670.601. (CC) gcc options: -O2 -lm

RAMspeed SMP

Type: Average - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating PointDDR4-3800DDR4-3400DDR4-3600DDR4-3200DDR4-3000DDR4-2933DDR4-26007K14K21K28K35KSE +/- 106.06, N = 20SE +/- 4.98, N = 20SE +/- 113.13, N = 20SE +/- 166.35, N = 20SE +/- 8.72, N = 2030641.6928359.7528017.3527592.2926060.8825268.5524013.291. (CC) gcc options: -O3 -march=native

MBW

Test: Memory Copy - Array Size: 4096 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiBDDR4-3800DDR4-3600DDR4-3400DDR4-3200DDR4-2933DDR4-3000DDR4-26004K8K12K16K20KSE +/- 11.96, N = 3SE +/- 59.69, N = 3SE +/- 56.94, N = 6SE +/- 46.28, N = 6SE +/- 30.89, N = 6SE +/- 41.97, N = 6SE +/- 14.58, N = 619171.0519076.9518220.8617614.7716761.8516728.5215049.001. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Add - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: IntegerDDR4-3600DDR4-3800DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-26007K14K21K28K35KSE +/- 154.97, N = 20SE +/- 111.27, N = 20SE +/- 149.01, N = 20SE +/- 64.84, N = 20SE +/- 78.22, N = 2032971.5031771.9631268.4328102.7726760.8926242.7025917.741. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Copy - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating PointDDR4-3800DDR4-3600DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-26006K12K18K24K30KSE +/- 50.97, N = 20SE +/- 4.70, N = 20SE +/- 95.27, N = 20SE +/- 49.82, N = 20SE +/- 3.12, N = 2028318.2927567.1026064.5325441.5724048.3923711.5822300.991. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Scale - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating PointDDR4-3800DDR4-3600DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-26006K12K18K24K30KSE +/- 70.70, N = 20SE +/- 5.25, N = 20SE +/- 30.98, N = 20SE +/- 2.62, N = 20SE +/- 2.48, N = 2027971.4627229.6125704.5025111.9223843.6023464.1222067.371. (CC) gcc options: -O3 -march=native

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiBDDR4-3600DDR4-3800DDR4-3400DDR4-3200DDR4-2933DDR4-3000DDR4-26002K4K6K8K10KSE +/- 47.20, N = 3SE +/- 110.89, N = 6SE +/- 64.98, N = 6SE +/- 98.85, N = 6SE +/- 58.11, N = 6SE +/- 45.10, N = 6SE +/- 69.12, N = 610142.179846.469572.329333.088972.958918.288209.221. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerDDR4-3600DDR4-3800DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-26006K12K18K24K30KSE +/- 10.74, N = 20SE +/- 83.09, N = 20SE +/- 87.01, N = 20SE +/- 137.89, N = 20SE +/- 3.80, N = 2027729.3425698.7925065.6924349.7124113.9322990.9822449.791. (CC) gcc options: -O3 -march=native

Tinymembench

Standard Memset

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard MemsetDDR4-3600DDR4-3800DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-26003K6K9K12K15KSE +/- 33.94, N = 3SE +/- 272.70, N = 3SE +/- 44.09, N = 6SE +/- 70.31, N = 6SE +/- 38.42, N = 6SE +/- 43.45, N = 6SE +/- 42.93, N = 614896.2014842.1014548.0214495.7013944.9713528.0212743.231. (CC) gcc options: -O2 -lm

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: CopyDDR4-3800DDR4-3600DDR4-3200DDR4-3400DDR4-3000DDR4-2933DDR4-26007K14K21K28K35KSE +/- 16.92, N = 5SE +/- 43.81, N = 5SE +/- 12.28, N = 10SE +/- 65.51, N = 10SE +/- 11.52, N = 10SE +/- 8.13, N = 10SE +/- 10.06, N = 1032900.9832715.8831772.2831772.1931245.1030565.2429638.041. (CC) gcc options: -O3 -march=native -fopenmp

CloverLeaf

Lagrangian-Eulerian Hydrodynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsDDR4-3800DDR4-3600DDR4-3000DDR4-3400DDR4-3200DDR4-2933DDR4-26000.87081.74162.61243.48324.354SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 203.503.673.693.693.763.783.871. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Darktable

Test: Server Rack - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Server Rack - Acceleration: CPU-onlyDDR4-3600DDR4-3800DDR4-2933DDR4-3000DDR4-3200DDR4-3400DDR4-26000.04730.09460.14190.18920.2365SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 200.190.190.200.200.200.200.21

Stream

Type: Triad

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: TriadDDR4-3800DDR4-3600DDR4-3000DDR4-3400DDR4-3200DDR4-2933DDR4-26004K8K12K16K20KSE +/- 20.23, N = 5SE +/- 7.62, N = 5SE +/- 17.18, N = 10SE +/- 8.82, N = 10SE +/- 4.47, N = 10SE +/- 8.57, N = 10SE +/- 5.83, N = 1019967.6019113.0418836.8918788.9318471.2418422.5618127.481. (CC) gcc options: -O3 -march=native -fopenmp

NAS Parallel Benchmarks

Test / Class: SP.A

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: SP.ADDR4-3600DDR4-3400DDR4-3200DDR4-3800DDR4-3000DDR4-2933DDR4-26009001800270036004500SE +/- 6.07, N = 3SE +/- 3.76, N = 20SE +/- 3.36, N = 20SE +/- 2.44, N = 3SE +/- 3.33, N = 20SE +/- 3.33, N = 20SE +/- 3.08, N = 204410.084341.044297.104286.854196.704156.634011.811. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: AddDDR4-3800DDR4-3600DDR4-3000DDR4-3400DDR4-3200DDR4-2933DDR4-26004K8K12K16K20KSE +/- 57.45, N = 5SE +/- 13.35, N = 5SE +/- 30.27, N = 10SE +/- 20.53, N = 10SE +/- 12.85, N = 10SE +/- 6.78, N = 10SE +/- 8.33, N = 1019972.4419210.3418913.5118861.2618558.6918473.1418201.161. (CC) gcc options: -O3 -march=native -fopenmp

Parboil

Test: OpenMP LBM

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBMDDR4-3800DDR4-3600DDR4-3400DDR4-3000DDR4-3200DDR4-2933DDR4-26004080120160200SE +/- 0.23, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 20SE +/- 0.04, N = 20SE +/- 0.06, N = 20SE +/- 0.05, N = 20SE +/- 0.04, N = 20145.00150.34152.16152.32154.47155.55159.091. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Darktable

Test: Boat - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Boat - Acceleration: CPU-onlyDDR4-3800DDR4-3600DDR4-3400DDR4-3000DDR4-3200DDR4-2933DDR4-26003691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 20SE +/- 0.01, N = 20SE +/- 0.01, N = 20SE +/- 0.01, N = 20SE +/- 0.01, N = 2010.8711.2311.4511.4611.5911.7211.92

Stream

Type: Scale

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: ScaleDDR4-3800DDR4-3600DDR4-3000DDR4-3400DDR4-3200DDR4-2933DDR4-26004K8K12K16K20KSE +/- 10.32, N = 5SE +/- 7.37, N = 5SE +/- 2.33, N = 10SE +/- 5.49, N = 10SE +/- 0.78, N = 10SE +/- 2.33, N = 10SE +/- 1.14, N = 1017172.5216602.4816383.6516382.8816155.8316041.9815734.861. (CC) gcc options: -O3 -march=native -fopenmp

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: LU.CDDR4-3800DDR4-3600DDR4-3400DDR4-3000DDR4-3200DDR4-2933DDR4-26005K10K15K20K25KSE +/- 9.92, N = 3SE +/- 8.06, N = 3SE +/- 3.38, N = 20SE +/- 3.95, N = 20SE +/- 3.07, N = 20SE +/- 3.40, N = 20SE +/- 4.56, N = 2022301.0021491.3321294.6721261.6221039.9420905.5820554.361. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19DDR4-3600DDR4-3400DDR4-3800DDR4-3200DDR4-3000DDR4-2933DDR4-2600510152025SE +/- 0.06, N = 3SE +/- 0.01, N = 20SE +/- 0.05, N = 3SE +/- 0.01, N = 20SE +/- 0.01, N = 20SE +/- 0.02, N = 20SE +/- 0.02, N = 2018.0518.2418.4718.6218.6418.8119.461. (CC) gcc options: -O3 -pthread -lz

Darktable

Test: Masskrug - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Masskrug - Acceleration: CPU-onlyDDR4-3600DDR4-3400DDR4-3800DDR4-3200DDR4-3000DDR4-2933DDR4-26001.11152.2233.33454.4465.5575SE +/- 0.01, N = 3SE +/- 0.01, N = 20SE +/- 0.02, N = 3SE +/- 0.01, N = 20SE +/- 0.01, N = 20SE +/- 0.01, N = 20SE +/- 0.01, N = 204.624.724.724.754.774.824.94

Darktable

Test: Server Room - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Server Room - Acceleration: CPU-onlyDDR4-3800DDR4-3600DDR4-3000DDR4-3400DDR4-3200DDR4-2933DDR4-26000.83031.66062.49093.32124.1515SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 203.473.573.603.613.643.653.69

Parboil

Test: OpenMP CUTCP

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPDDR4-3400DDR4-3600DDR4-3800DDR4-3200DDR4-3000DDR4-2933DDR4-26000.51981.03961.55942.07922.599SE +/- 0.00, N = 20SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 20SE +/- 0.00, N = 202.202.202.212.232.252.262.311. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

CP2K Molecular Dynamics

Fayalite-FIST Data

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 6.1Fayalite-FIST DataDDR4-3800DDR4-3200DDR4-3600DDR4-3400DDR4-2933DDR4-3000DDR4-260070140210280350SE +/- 1.52, N = 3SE +/- 0.89, N = 3SE +/- 0.10, N = 3SE +/- 0.25, N = 3SE +/- 0.75, N = 3323.90326.66327.02327.69327.98329.42338.84

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansDDR4-3600DDR4-3400DDR4-3800DDR4-3200DDR4-3000DDR4-2933DDR4-26009001800270036004500SE +/- 36.89, N = 4SE +/- 8.25, N = 20SE +/- 14.74, N = 4SE +/- 8.44, N = 20SE +/- 8.31, N = 20SE +/- 10.10, N = 20SE +/- 11.16, N = 204140414141614175423642474318

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterDDR4-3600DDR4-3800DDR4-2933DDR4-3400DDR4-3200DDR4-3000DDR4-2600510152025SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 20SE +/- 0.01, N = 20SE +/- 0.02, N = 20SE +/- 0.04, N = 20SE +/- 0.01, N = 2021.0121.1721.1921.3721.5521.6121.911. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

Test / Class: BT.A

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: BT.ADDR4-3600DDR4-3400DDR4-3200DDR4-3800DDR4-3000DDR4-2933DDR4-260014002800420056007000SE +/- 12.49, N = 3SE +/- 6.73, N = 20SE +/- 6.96, N = 20SE +/- 10.84, N = 3SE +/- 4.92, N = 20SE +/- 6.84, N = 20SE +/- 7.38, N = 206448.106378.476365.606354.696302.296287.046191.111. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

t-test1

Threads: 2

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2DDR4-3400DDR4-3800DDR4-3200DDR4-3000DDR4-2933DDR4-3600DDR4-2600246810SE +/- 0.01, N = 20SE +/- 0.01, N = 3SE +/- 0.01, N = 20SE +/- 0.01, N = 20SE +/- 0.01, N = 20SE +/- 0.05, N = 3SE +/- 0.01, N = 207.137.197.207.237.277.277.391. (CC) gcc options: -pthread

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2DDR4-3800DDR4-3400DDR4-3200DDR4-3600DDR4-3000DDR4-2933DDR4-26007001400210028003500SE +/- 9.43, N = 4SE +/- 10.22, N = 100SE +/- 14.94, N = 40SE +/- 26.42, N = 4SE +/- 16.09, N = 35SE +/- 18.60, N = 20SE +/- 16.69, N = 343136315531693183320832153247

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileDDR4-2933DDR4-3400DDR4-3000DDR4-3200DDR4-3600DDR4-2600DDR4-380060120180240300SE +/- 3.07, N = 3SE +/- 1.89, N = 3SE +/- 2.83, N = 3SE +/- 1.94, N = 3SE +/- 3.75, N = 3288.02288.74288.77291.47292.10293.52297.22

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestDDR4-3800DDR4-3600DDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-260020K40K60K80K100KSE +/- 291.81, N = 3SE +/- 205.24, N = 3SE +/- 77.07, N = 20SE +/- 80.47, N = 20SE +/- 95.84, N = 20SE +/- 82.54, N = 20SE +/- 71.04, N = 20783627831778070776267740377127759961. (CXX) g++ options: -pipe -lpthread

VP9 libvpx Encoding

vpxenc VP9 1080p Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.0vpxenc VP9 1080p Video EncodeDDR4-3400DDR4-3200DDR4-3800DDR4-3600DDR4-2933DDR4-3000DDR4-26004080120160200SE +/- 0.29, N = 20SE +/- 0.31, N = 20SE +/- 0.54, N = 3SE +/- 0.20, N = 3SE +/- 0.23, N = 20SE +/- 0.27, N = 20SE +/- 0.25, N = 20170.69170.28169.21169.12168.23168.02166.051. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

t-test1

Threads: 1

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1DDR4-3800DDR4-3200DDR4-3400DDR4-3000DDR4-3600DDR4-2600DDR4-2933510152025SE +/- 0.05, N = 3SE +/- 0.02, N = 20SE +/- 0.01, N = 20SE +/- 0.02, N = 20SE +/- 0.07, N = 3SE +/- 0.01, N = 20SE +/- 0.02, N = 2020.2120.4020.5020.5320.5320.5720.661. (CC) gcc options: -pthread

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonDDR4-3200DDR4-3400DDR4-3600DDR4-3000DDR4-3800DDR4-2600DDR4-29339001800270036004500SE +/- 12.62, N = 20SE +/- 13.61, N = 20SE +/- 25.17, N = 4SE +/- 8.72, N = 20SE +/- 11.83, N = 4SE +/- 10.33, N = 20SE +/- 10.72, N = 204022403840394075408140834095

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishDDR4-3800DDR4-3000DDR4-2933DDR4-3200DDR4-3600DDR4-3400DDR4-26006K12K18K24K30KSE +/- 54.48, N = 3SE +/- 15.74, N = 20SE +/- 15.70, N = 20SE +/- 15.75, N = 20SE +/- 31.80, N = 3SE +/- 14.85, N = 20SE +/- 182.62, N = 80286882854628535284982847628475282401. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To CompileDDR4-3200DDR4-2933DDR4-3000DDR4-3400DDR4-2600DDR4-3600DDR4-38001122334455SE +/- 0.14, N = 20SE +/- 0.13, N = 20SE +/- 0.15, N = 20SE +/- 0.13, N = 20SE +/- 0.13, N = 20SE +/- 0.60, N = 3SE +/- 0.70, N = 447.6647.7047.8347.9047.9648.1248.20

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyDDR4-3800DDR4-2600DDR4-3600DDR4-3400DDR4-3200DDR4-3000DDR4-293360K120K180K240K300KSE +/- 388.60, N = 3SE +/- 93.01, N = 20SE +/- 247.98, N = 3SE +/- 104.50, N = 20SE +/- 85.84, N = 20SE +/- 104.75, N = 20SE +/- 108.29, N = 20288637.56287832.43287775.22287495.92287137.04286901.84286245.971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

SVT-AV1

1080p 8-bit YUV To AV1 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.51080p 8-bit YUV To AV1 Video EncodeDDR4-3400DDR4-3200DDR4-3000DDR4-2933DDR4-3600DDR4-3800DDR4-26001020304050SE +/- 0.07, N = 20SE +/- 0.08, N = 20SE +/- 0.04, N = 20SE +/- 0.06, N = 20SE +/- 0.35, N = 3SE +/- 0.18, N = 3SE +/- 0.06, N = 2045.9245.8545.8445.7545.6945.6045.571. (CXX) g++ options: -O3 -pie -lpthread -lm

x265

H.265 1080p Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video EncodingDDR4-3600DDR4-3200DDR4-3400DDR4-2933DDR4-3000DDR4-3800DDR4-26001224364860SE +/- 0.34, N = 3SE +/- 0.06, N = 20SE +/- 0.06, N = 20SE +/- 0.10, N = 20SE +/- 0.09, N = 20SE +/- 0.28, N = 3SE +/- 0.08, N = 2051.9251.9051.8851.8551.7551.6851.651. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: EP.CDDR4-3600DDR4-3000DDR4-3200DDR4-3800DDR4-2933DDR4-2600DDR4-3400100200300400500SE +/- 0.25, N = 3SE +/- 0.07, N = 20SE +/- 0.08, N = 20SE +/- 0.45, N = 3SE +/- 0.11, N = 20SE +/- 0.07, N = 20SE +/- 0.12, N = 20482.27482.02481.99481.91481.66481.46480.791. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

Apache Siege

Concurrent Users: 250

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250DDR4-3000DDR4-3200DDR4-2933DDR4-2600DDR4-3400DDR4-3600DDR4-38008K16K24K32K40KSE +/- 262.87, N = 6SE +/- 243.63, N = 25SE +/- 468.26, N = 24SE +/- 485.67, N = 26SE +/- 651.91, N = 30SE +/- 1098.14, N = 15SE +/- 230.57, N = 336243.0535904.8135618.3835420.8234741.6334559.7227601.721. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Phoronix Test Suite v10.8.4