Linux 6.14 Early Benchmarks AMD EPYC

Benchmarks for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2501308-NE-LINUX614E01&sro&grr.

Linux 6.14 Early Benchmarks AMD EPYCProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolutionv6.13v6.14 29 JanAMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores / 128 Threads)Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS)AMD 1Ah12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF3201GB Micron_7450_MTFDKCB3T2TFSASPEED2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 24.106.13.0-phx (x86_64)GNOME Shell 47.0X ServerGCC 14.2.0ext41024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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-build-config=bootstrap-lto-lean --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: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116 Java Details- OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10)Python Details- Python 3.12.7Security Details- v6.13: 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - v6.14 29 Jan: 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: Mitigation of IBPB on VMEXIT only + 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Linux 6.14 Early Benchmarks AMD EPYCrelion: Basic - CPUpgbench: 100 - 800 - Read Write - Average Latencypgbench: 100 - 800 - Read Writetensorflow: CPU - 512 - ResNet-50build-linux-kernel: allmodconfigjava-jmh: Throughputstress-ng: Pipeblender: Barbershop - CPU-Onlysvt-av1: Preset 3 - Bosphorus 4Kpgbench: 100 - 800 - Read Only - Average Latencypgbench: 100 - 800 - Read Onlycassandra: Writesbuild-nodejs: Time To Compileclickhouse: 100M Rows Hits Dataset, Third Runclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timebuild-llvm: Ninjadacapobench: Tradebeansllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048memcached: 1:5memcached: 1:10memcached: 1:100rocksdb: Update Randrocksdb: Read Rand Write Randrocksdb: Read While Writingrocksdb: Rand Readblender: Pabellon Barcelona - CPU-Onlydacapobench: Tradesoapdacapobench: Apache Lucene Search Engineblender: Classroom - CPU-Onlysvt-av1: Preset 5 - Bosphorus 4Kdacapobench: Avrora AVR Simulation Frameworkstress-ng: NUMAstress-ng: SENDFILEstress-ng: Futexstress-ng: Context Switchingstress-ng: Socket Activitystress-ng: Mutexllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048astcenc: Very Thoroughastcenc: Exhaustivebuild-linux-kernel: defconfigdacapobench: Eclipsenamd: STMV with 1,066,628 Atomsblender: Junkshop - CPU-Onlygromacs: MPI CPU - water_GMX50_baredacapobench: Apache Lucene Search Indexopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128svt-av1: Preset 8 - Bosphorus 4Knamd: ATPase with 327,506 Atomsllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128svt-av1: Preset 13 - Bosphorus 4Kdacapobench: Apache Tomcatopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPUv6.13v6.14 29 Jan165.8326.216128762253.76191.014316508832117.0582801426.52146.6917.0330.1654850455461247124.240803.99802.09778.02230.2254289.311917101.0464870143.45143.263888552.687054421.8813460038.7669202773984351173490353525586246.852977398141.1560.57421832144.572105661.954271894.4752538077.7747642.2642972205.27448.2210.17506.233621.75662443.7574919.9714.585223613.0616.1676.5749.9152.55200.46113.07300118.47471.6791043174.7296.387125263253.53190.882316375911973.0681959177.61147.0517.0940.1674801097494806124.276801.13802.93778.75226.9936588.166581101.4134872144.23145.083911714.467187440.1213605595.6569142173484851208393553546537747.083033361541.1660.39221842062.272099036.564224604.0752207921.6546759.6142507064.95432.9410.17566.229321.75863213.7564119.9414.583223312.8016.1078.1450.0052.55197.30212.83401117.88471.8251060OpenBenchmarking.org

RELION

Test: Basic - Device: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 5.0Test: Basic - Device: CPUv6.13v6.14 29 Jan4080120160200SE +/- 3.02, N = 12SE +/- 1.63, N = 12165.83174.731. (CXX) g++ options: -fPIC -std=c++14 -fopenmp -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -lmpi

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latencyv6.13v6.14 29 Jan246810SE +/- 0.042, N = 12SE +/- 0.031, N = 36.2166.3871. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 800 - Mode: Read Writev6.13v6.14 29 Jan30K60K90K120K150KSE +/- 895.52, N = 12SE +/- 608.11, N = 31287621252631. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

TensorFlow

Device: CPU - Batch Size: 512 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50v6.13v6.14 29 Jan60120180240300SE +/- 0.26, N = 3SE +/- 0.19, N = 3253.76253.53

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigv6.13v6.14 29 Jan4080120160200SE +/- 0.40, N = 3SE +/- 0.30, N = 3191.01190.88

Java JMH

Throughput

OpenBenchmarking.orgOps/s, More Is BetterJava JMHThroughputv6.13v6.14 29 Jan70000M140000M210000M280000M350000M316508832117.05316375911973.06

Stress-NG

Test: Pipe

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Pipev6.13v6.14 29 Jan20M40M60M80M100MSE +/- 1013892.33, N = 15SE +/- 1868912.16, N = 1582801426.5281959177.611. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: CPU-Onlyv6.13v6.14 29 Jan306090120150SE +/- 0.07, N = 3SE +/- 0.22, N = 3146.69147.05

SVT-AV1

Encoder Mode: Preset 3 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 3 - Input: Bosphorus 4Kv6.13v6.14 29 Jan48121620SE +/- 0.03, N = 3SE +/- 0.05, N = 317.0317.091. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latencyv6.13v6.14 29 Jan0.03760.07520.11280.15040.188SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1650.1671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 800 - Mode: Read Onlyv6.13v6.14 29 Jan1000K2000K3000K4000K5000KSE +/- 12547.95, N = 3SE +/- 2758.89, N = 3485045548010971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 5.0Test: Writesv6.13v6.14 29 Jan110K220K330K440K550KSE +/- 2230.81, N = 3SE +/- 4037.80, N = 3461247494806

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To Compilev6.13v6.14 29 Jan306090120150SE +/- 0.04, N = 3SE +/- 0.16, N = 3124.24124.28

ClickHouse

100M Rows Hits Dataset, Third Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third Runv6.13v6.14 29 Jan2004006008001000SE +/- 1.04, N = 3SE +/- 5.26, N = 3803.99801.13MIN: 66.08 / MAX: 10000MIN: 65.01 / MAX: 8571.43

ClickHouse

100M Rows Hits Dataset, Second Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second Runv6.13v6.14 29 Jan2004006008001000SE +/- 7.48, N = 3SE +/- 5.08, N = 3802.09802.93MIN: 65.43 / MAX: 8571.43MIN: 66.01 / MAX: 8571.43

ClickHouse

100M Rows Hits Dataset, First Run / Cold Cache

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold Cachev6.13v6.14 29 Jan2004006008001000SE +/- 6.64, N = 3SE +/- 4.26, N = 3778.02778.75MIN: 65.22 / MAX: 8571.43MIN: 65.57 / MAX: 7500

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution Timev6.13v6.14 29 Jan50100150200250230.23226.991. (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

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Mesh Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh Timev6.13v6.14 29 Jan2040608010089.3188.171. (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

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Ninjav6.13v6.14 29 Jan20406080100SE +/- 0.25, N = 3SE +/- 0.18, N = 3101.05101.41

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Tradebeansv6.13v6.14 29 Jan10002000300040005000SE +/- 93.65, N = 15SE +/- 91.74, N = 1548704872

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048v6.13v6.14 29 Jan306090120150SE +/- 0.48, N = 3SE +/- 0.77, N = 3143.45144.231. (CXX) g++ options: -O3

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048v6.13v6.14 29 Jan306090120150SE +/- 0.13, N = 3SE +/- 0.59, N = 3143.26145.081. (CXX) g++ options: -O3

Memcached

Set To Get Ratio: 1:5

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:5v6.13v6.14 29 Jan800K1600K2400K3200K4000KSE +/- 987.88, N = 3SE +/- 5274.38, N = 33888552.683911714.461. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Memcached

Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10v6.13v6.14 29 Jan1.5M3M4.5M6M7.5MSE +/- 11715.29, N = 3SE +/- 21122.44, N = 37054421.887187440.121. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Memcached

Set To Get Ratio: 1:100

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100v6.13v6.14 29 Jan3M6M9M12M15MSE +/- 65975.03, N = 3SE +/- 9305.87, N = 313460038.7613605595.651. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

RocksDB

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update Randomv6.13v6.14 29 Jan150K300K450K600K750KSE +/- 200.83, N = 3SE +/- 1034.41, N = 36920276914211. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

RocksDB

Test: Read Random Write Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write Randomv6.13v6.14 29 Jan1.6M3.2M4.8M6.4M8MSE +/- 47503.65, N = 3SE +/- 69319.41, N = 3739843573484851. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While Writingv6.13v6.14 29 Jan3M6M9M12M15MSE +/- 94771.95, N = 3SE +/- 116959.75, N = 311734903120839351. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Readv6.13v6.14 29 Jan110M220M330M440M550MSE +/- 1082500.13, N = 3SE +/- 657385.47, N = 35352558625354653771. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: CPU-Onlyv6.13v6.14 29 Jan1122334455SE +/- 0.07, N = 3SE +/- 0.09, N = 346.8547.08

DaCapo Benchmark

Java Test: Tradesoap

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Tradesoapv6.13v6.14 29 Jan7001400210028003500SE +/- 17.32, N = 3SE +/- 24.47, N = 1529773033

DaCapo Benchmark

Java Test: Apache Lucene Search Engine

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search Enginev6.13v6.14 29 Jan9001800270036004500SE +/- 47.78, N = 15SE +/- 39.07, N = 439813615

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: CPU-Onlyv6.13v6.14 29 Jan918273645SE +/- 0.05, N = 3SE +/- 0.01, N = 341.1541.16

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 5 - Input: Bosphorus 4Kv6.13v6.14 29 Jan1428425670SE +/- 0.27, N = 3SE +/- 0.05, N = 360.5760.391. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

DaCapo Benchmark

Java Test: Avrora AVR Simulation Framework

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation Frameworkv6.13v6.14 29 Jan5001000150020002500SE +/- 27.74, N = 15SE +/- 33.19, N = 1521832184

Stress-NG

Test: NUMA

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: NUMAv6.13v6.14 29 Jan5001000150020002500SE +/- 3.79, N = 3SE +/- 4.06, N = 32144.572062.271. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Stress-NG

Test: SENDFILE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: SENDFILEv6.13v6.14 29 Jan500K1000K1500K2000K2500KSE +/- 3455.33, N = 3SE +/- 4114.32, N = 32105661.952099036.561. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Stress-NG

Test: Futex

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Futexv6.13v6.14 29 Jan900K1800K2700K3600K4500KSE +/- 31436.04, N = 3SE +/- 47235.90, N = 34271894.474224604.071. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Context Switchingv6.13v6.14 29 Jan11M22M33M44M55MSE +/- 424783.11, N = 3SE +/- 58765.40, N = 352538077.7752207921.651. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Stress-NG

Test: Socket Activity

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Socket Activityv6.13v6.14 29 Jan10K20K30K40K50KSE +/- 61.51, N = 3SE +/- 50.78, N = 347642.2646759.611. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Stress-NG

Test: Mutex

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Mutexv6.13v6.14 29 Jan9M18M27M36M45MSE +/- 125947.68, N = 3SE +/- 317020.74, N = 342972205.2742507064.951. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048v6.13v6.14 29 Jan100200300400500SE +/- 3.77, N = 3SE +/- 2.05, N = 3448.22432.941. (CXX) g++ options: -O3

ASTC Encoder

Preset: Very Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Very Thoroughv6.13v6.14 29 Jan3691215SE +/- 0.00, N = 3SE +/- 0.01, N = 310.1810.181. (CXX) g++ options: -O3 -flto -pthread

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Exhaustivev6.13v6.14 29 Jan246810SE +/- 0.0010, N = 3SE +/- 0.0014, N = 36.23366.22931. (CXX) g++ options: -O3 -flto -pthread

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigv6.13v6.14 29 Jan510152025SE +/- 0.24, N = 4SE +/- 0.28, N = 321.7621.76

DaCapo Benchmark

Java Test: Eclipse

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Eclipsev6.13v6.14 29 Jan14002800420056007000SE +/- 9.71, N = 3SE +/- 13.28, N = 362446321

NAMD

Input: STMV with 1,066,628 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: STMV with 1,066,628 Atomsv6.13v6.14 29 Jan0.84541.69082.53623.38164.227SE +/- 0.01116, N = 3SE +/- 0.00440, N = 33.757493.75641

Blender

Blend File: Junkshop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: CPU-Onlyv6.13v6.14 29 Jan510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 319.9719.94

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_barev6.13v6.14 29 Jan48121620SE +/- 0.08, N = 3SE +/- 0.16, N = 314.5914.581. (CXX) g++ options: -O3 -lm

DaCapo Benchmark

Java Test: Apache Lucene Search Index

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search Indexv6.13v6.14 29 Jan5001000150020002500SE +/- 6.03, N = 3SE +/- 17.23, N = 322362233

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Tokenv6.13v6.14 29 Jan3691215SE +/- 0.13, N = 3SE +/- 0.02, N = 313.0612.80

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Tokenv6.13v6.14 29 Jan48121620SE +/- 0.08, N = 3SE +/- 0.11, N = 316.1616.10

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPUv6.13v6.14 29 Jan20406080100SE +/- 0.76, N = 3SE +/- 0.12, N = 376.5778.14

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128v6.13v6.14 29 Jan1122334455SE +/- 0.09, N = 3SE +/- 0.03, N = 349.9150.001. (CXX) g++ options: -O3

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128v6.13v6.14 29 Jan1224364860SE +/- 0.15, N = 3SE +/- 0.02, N = 352.5552.551. (CXX) g++ options: -O3

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 8 - Input: Bosphorus 4Kv6.13v6.14 29 Jan4080120160200SE +/- 0.02, N = 3SE +/- 1.79, N = 3200.46197.301. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

NAMD

Input: ATPase with 327,506 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: ATPase with 327,506 Atomsv6.13v6.14 29 Jan3691215SE +/- 0.09, N = 3SE +/- 0.16, N = 413.0712.83

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128v6.13v6.14 29 Jan306090120150SE +/- 0.52, N = 3SE +/- 0.46, N = 3118.47117.881. (CXX) g++ options: -O3

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 13 - Input: Bosphorus 4Kv6.13v6.14 29 Jan100200300400500SE +/- 4.76, N = 3SE +/- 2.61, N = 3471.68471.831. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

DaCapo Benchmark

Java Test: Apache Tomcat

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Tomcatv6.13v6.14 29 Jan2004006008001000SE +/- 2.08, N = 3SE +/- 12.17, N = 310431060

Phoronix Test Suite v10.8.5