RHEL 10.0 Beta AMD EPYC Benchmarks

Red Hat Enterprise Linux 10 benchmarks on AMD EPYC. RHEL 10.0 Bets vs. RHEL 9.5 performance. Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2412153-NE-RHEL1045196&grr&rdt.

RHEL 10.0 Beta AMD EPYC BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionRHEL 9.5RHEL 10.0 BetaAMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads)Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS)AMD Device 153a12 x 64GB DRAM-6000MT/s Micron MTC40F2046S1RC64BDY QSFF2048GB SOLIDIGM SSDPFKNU020TZASPEED2 x Broadcom NetXtreme BCM5720 PCIeRed Hat Enterprise Linux 9.55.14.0-503.16.1.el9_5.x86_64 (x86_64)GNOME Shell 40.10X ServerGCC 11.5.0 20240719xfs1024x76812 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFFRed Hat Enterprise Linux 10.0 Beta6.11.0-0.rc5.23.el10.x86_64 (x86_64)GNOME ShellGCC 14.2.1 20240801OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- RHEL 9.5: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl - RHEL 10.0 Beta: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none,amdgcn-amdhsa --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v3 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl Processor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116Java Details- RHEL 9.5: OpenJDK Runtime Environment (Red_Hat-17.0.13.0.11-1) (build 17.0.13+11-LTS)- RHEL 10.0 Beta: OpenJDK Runtime Environment (Red_Hat-21.0.4.0.7-1) (build 21.0.4+7-LTS)Python Details- RHEL 9.5: Python 3.9.21- RHEL 10.0 Beta: Python 3.12.5Security Details- SELinux + 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

RHEL 10.0 Beta AMD EPYC Benchmarksincompact3d: X3D-benchmarking input.i3dtensorflow: CPU - 256 - ResNet-50wireguard: tensorflow: CPU - 512 - ResNet-50openssl: RSA4096openssl: RSA4096graphics-magick: Rotateopenssl: ChaCha20-Poly1305openssl: AES-256-GCMopenssl: ChaCha20openssl: SHA512openssl: SHA256pgbench: 1000 - 1000 - Read Only - Average Latencypgbench: 1000 - 1000 - Read Onlypgbench: 1000 - 800 - Read Only - Average Latencypgbench: 1000 - 800 - Read Onlysvt-av1: Preset 3 - Bosphorus 4Kcassandra: Writesclickhouse: 100M Rows Hits Dataset, Third Runclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheblender: Barbershop - CPU-Onlyrenaissance: Apache Spark Bayespyperformance: xml_etreebuild-nodejs: Time To Compilecompress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedpyperformance: asyncio_tcp_sslcompress-zstd: 8 - Decompression Speedcompress-zstd: 8 - Compression Speedcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speednginx: 500renaissance: Gaussian Mixture Modelrenaissance: In-Memory Database Shootoutv-ray: CPUrenaissance: Apache Spark PageRankperl-benchmark: Pod2htmlrenaissance: Apache Spark ALSgraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Noise-Gaussiangraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Swirlpyperformance: gc_collectperl-benchmark: Interpreterpyperformance: asyncio_websocketssvt-av1: Preset 5 - Bosphorus 4Kblender: Pabellon Barcelona - CPU-Onlycryptsetup: Twofish-XTS 512b Encryptioncryptsetup: Serpent-XTS 512b Encryptioncryptsetup: AES-XTS 512b Decryptioncryptsetup: AES-XTS 512b Encryptioncryptsetup: Twofish-XTS 256b Encryptioncryptsetup: Serpent-XTS 256b Encryptioncryptsetup: AES-XTS 256b Decryptioncryptsetup: AES-XTS 256b Encryptioncryptsetup: PBKDF2-whirlpoolcryptsetup: PBKDF2-sha512pyperformance: gopyperformance: raytraceblender: Classroom - CPU-Onlysqlite-speedtest: Timed Time - Size 1,000compress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 3 - Decompression Speedcompress-zstd: 3 - Compression Speedcompress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 3, Long Mode - Compression Speedopenvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time To First Tokenopenvino-genai: Gemma-7b-int4-ov - CPUx265: Bosphorus 4Kpyperformance: regex_compilepyperformance: pathlibliquid-dsp: 192 - 256 - 512liquid-dsp: 128 - 256 - 512liquid-dsp: 64 - 256 - 512compress-7zip: Decompression Ratingcompress-7zip: Compression Ratingnamd: STMV with 1,066,628 Atomspyperformance: floatpyperformance: crypto_pyaesdacapobench: H2 Database Engineopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPUpyperformance: chaospyperformance: nbodypyperformance: pickle_pure_pythonpyperformance: json_loadsblender: Fishy Cat - CPU-Onlygromacs: MPI CPU - water_GMX50_barenamd: ATPase with 327,506 Atomsdacapobench: Apache Lucene Search Indexdacapobench: Apache Kafkaopenvino-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 - CPUblender: Junkshop - CPU-Onlyphpbench: PHP Benchmark Suitedacapobench: BioJava Biological Data Frameworksvt-av1: Preset 8 - Bosphorus 4Kincompact3d: input.i3d 193 Cells Per Directionopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPUpybench: Total For Average Test Timesmt-dgemm: Sustained Floating-Point Ratedacapobench: Avrora AVR Simulation Frameworksvt-av1: Preset 13 - Bosphorus 4Kdacapobench: Apache Tomcatdacapobench: Apache Xalan XSLTRHEL 9.5RHEL 10.0 Beta390.734192167.38186.373169.462028196.950420.03505981371980931318996105533875870628703538176148901352241804870.30832404780.244327535315.831532385778.17780.37744.33125.03175.739.1116.5355024.8132.26846160.14738.84990.565.0378869.133404.24389.61944942157.60.06380345757.7350395393141283111007790.0008405436155.71641.08711.4754.55180.15171.6710.1752.46541.46509.8997402278122714825235.7033.7676558.71430.35838.313074.26251.21370.326.5237.5337.7018.8193.39.672131466667197523333314264666676245659396574.2260763.160.3211919.7229.9650.7157.074.423312.418.8317.39412.316712492511015.1818.8165.9116.8611687244505186.93010.717584918.0124.9555.525494249.8792422656438.0911158911363.071906166.28169.688169.532030249.250685.23925960851175631321398713187872714248010541980251271397113812100.31931352120.251318994216.023464647791.13796.94768.98123.35184.031.5105.8914863.3127.64766060.56854.74971.962.9425156.323217.04212.62029772101.10.06082243742.54464944721914119814976560.0007698712357.33241.03690.8744.611383.411373.4693.8742.912748.712705.71009583304381773.915935.1434.5826443.31536.15751.313162.36182.11457.826.4836.7437.7719.2371.39.912168666667199373333314339000006273639637764.2298942.842.0212919.5929.5751.0434.954.016512.118.4817.89412.395322468511715.1318.7866.1116.6512731714410190.01810.502640117.7824.1456.264874252.6795682580441.1911124840OpenBenchmarking.org

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dRHEL 9.5RHEL 10.0 Beta80160240320400SE +/- 7.96, N = 9SE +/- 8.67, N = 9390.73363.071. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi

TensorFlow

Device: CPU - Batch Size: 256 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50RHEL 9.5RHEL 10.0 Beta4080120160200SE +/- 4.20, N = 12SE +/- 4.10, N = 12167.38166.28

WireGuard + Linux Networking Stack Stress Test

OpenBenchmarking.orgSeconds, Fewer Is BetterWireGuard + Linux Networking Stack Stress TestRHEL 9.5RHEL 10.0 Beta4080120160200SE +/- 2.88, N = 12SE +/- 0.87, N = 3186.37169.69

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50RHEL 9.5RHEL 10.0 Beta4080120160200SE +/- 0.11, N = 3SE +/- 0.08, N = 3169.46169.53

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgverify/s, More Is BetterOpenSSLAlgorithm: RSA4096RHEL 9.5RHEL 10.0 Beta400K800K1200K1600K2000KSE +/- 174.76, N = 3SE +/- 265.26, N = 32028196.92030249.21. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgsign/s, More Is BetterOpenSSLAlgorithm: RSA4096RHEL 9.5RHEL 10.0 Beta11K22K33K44K55KSE +/- 19.40, N = 3SE +/- 25.23, N = 350420.050685.21. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: RotateRHEL 9.5RHEL 10.0 Beta90180270360450SE +/- 1.67, N = 3SE +/- 2.78, N = 153503921. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp

OpenSSL

Algorithm: ChaCha20-Poly1305

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: ChaCha20-Poly1305RHEL 9.5RHEL 10.0 Beta130000M260000M390000M520000M650000MSE +/- 311658956.47, N = 3SE +/- 198992872.07, N = 35981371980935960851175631. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)

OpenSSL

Algorithm: AES-256-GCM

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: AES-256-GCMRHEL 9.5RHEL 10.0 Beta300000M600000M900000M1200000M1500000MSE +/- 1099131454.93, N = 3SE +/- 927462302.83, N = 3131899610553313213987131871. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)

OpenSSL

Algorithm: ChaCha20

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: ChaCha20RHEL 9.5RHEL 10.0 Beta200000M400000M600000M800000M1000000MSE +/- 561226959.81, N = 3SE +/- 515095183.79, N = 38758706287038727142480101. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)

OpenSSL

Algorithm: SHA512

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: SHA512RHEL 9.5RHEL 10.0 Beta12000M24000M36000M48000M60000MSE +/- 56122603.90, N = 3SE +/- 154598274.25, N = 353817614890541980251271. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)

OpenSSL

Algorithm: SHA256

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSLAlgorithm: SHA256RHEL 9.5RHEL 10.0 Beta30000M60000M90000M120000M150000MSE +/- 219362632.74, N = 3SE +/- 143924649.50, N = 31352241804871397113812101. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)

PostgreSQL

Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only - Average LatencyRHEL 9.5RHEL 10.0 Beta0.07180.14360.21540.28720.359SE +/- 0.000, N = 3SE +/- 0.001, N = 30.3080.3191. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

PostgreSQL

Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 1000 - Clients: 1000 - Mode: Read OnlyRHEL 9.5RHEL 10.0 Beta700K1400K2100K2800K3500KSE +/- 4071.13, N = 3SE +/- 6126.05, N = 3324047831352121. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

PostgreSQL

Scaling Factor: 1000 - Clients: 800 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 1000 - Clients: 800 - Mode: Read Only - Average LatencyRHEL 9.5RHEL 10.0 Beta0.05650.1130.16950.2260.2825SE +/- 0.000, N = 3SE +/- 0.001, N = 30.2440.2511. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

PostgreSQL

Scaling Factor: 1000 - Clients: 800 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 1000 - Clients: 800 - Mode: Read OnlyRHEL 9.5RHEL 10.0 Beta700K1400K2100K2800K3500KSE +/- 3020.11, N = 3SE +/- 7552.31, N = 3327535331899421. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

SVT-AV1

Encoder Mode: Preset 3 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 3 - Input: Bosphorus 4KRHEL 9.5RHEL 10.0 Beta48121620SE +/- 0.06, N = 3SE +/- 0.02, N = 315.8316.021. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 5.0Test: WritesRHEL 9.5RHEL 10.0 Beta110K220K330K440K550KSE +/- 1670.37, N = 3SE +/- 2840.33, N = 3532385464647

ClickHouse

100M Rows Hits Dataset, Third Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunRHEL 9.5RHEL 10.0 Beta2004006008001000SE +/- 5.25, N = 3SE +/- 4.41, N = 3778.17791.13MIN: 69.12 / MAX: 8571.43MIN: 69.36 / 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 RunRHEL 9.5RHEL 10.0 Beta2004006008001000SE +/- 6.89, N = 3SE +/- 2.72, N = 3780.37796.94MIN: 69.85 / MAX: 7500MIN: 70.26 / 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 CacheRHEL 9.5RHEL 10.0 Beta170340510680850SE +/- 8.90, N = 3SE +/- 2.01, N = 3744.33768.98MIN: 68.97 / MAX: 7500MIN: 69.04 / MAX: 8571.43

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: CPU-OnlyRHEL 9.5RHEL 10.0 Beta306090120150SE +/- 0.09, N = 3SE +/- 0.18, N = 3125.03123.35

Renaissance

Test: Apache Spark Bayes

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark BayesRHEL 9.5RHEL 10.0 Beta4080120160200SE +/- 1.74, N = 6SE +/- 2.28, N = 4175.7184.0MIN: 158.43 / MAX: 233.67MIN: 161.42 / MAX: 229.13

PyPerformance

Benchmark: xml_etree

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: xml_etreeRHEL 9.5RHEL 10.0 Beta918273645SE +/- 0.00, N = 3SE +/- 0.03, N = 339.131.5

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To CompileRHEL 9.5RHEL 10.0 Beta306090120150SE +/- 0.19, N = 3SE +/- 0.21, N = 3116.54105.89

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19 - Decompression SpeedRHEL 9.5RHEL 10.0 Beta11002200330044005500SE +/- 13.96, N = 3SE +/- 3.26, N = 155024.84863.31. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19 - Compression SpeedRHEL 9.5RHEL 10.0 Beta306090120150SE +/- 1.72, N = 3SE +/- 1.25, N = 15132.2127.61. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

PyPerformance

Benchmark: asyncio_tcp_ssl

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: asyncio_tcp_sslRHEL 9.5RHEL 10.0 Beta150300450600750SE +/- 1.45, N = 3SE +/- 0.33, N = 3684476

Zstd Compression

Compression Level: 8 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8 - Decompression SpeedRHEL 9.5RHEL 10.0 Beta13002600390052006500SE +/- 6.49, N = 15SE +/- 1.84, N = 36160.16060.51. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 8 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8 - Compression SpeedRHEL 9.5RHEL 10.0 Beta15003000450060007500SE +/- 43.63, N = 15SE +/- 10.63, N = 34738.86854.71. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19, Long Mode - Decompression SpeedRHEL 9.5RHEL 10.0 Beta11002200330044005500SE +/- 4.52, N = 15SE +/- 12.19, N = 34990.54971.91. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19, Long Mode - Compression SpeedRHEL 9.5RHEL 10.0 Beta1530456075SE +/- 0.49, N = 15SE +/- 0.87, N = 365.062.91. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

nginx

Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500RHEL 9.5RHEL 10.0 Beta90K180K270K360K450KSE +/- 1253.75, N = 3SE +/- 975.49, N = 3378869.13425156.321. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Renaissance

Test: Gaussian Mixture Model

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Gaussian Mixture ModelRHEL 9.5RHEL 10.0 Beta7001400210028003500SE +/- 38.98, N = 4SE +/- 6.50, N = 33404.23217.0MIN: 2508.31 / MAX: 3518.29MIN: 2413.84 / MAX: 3226.59

Renaissance

Test: In-Memory Database Shootout

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: In-Memory Database ShootoutRHEL 9.5RHEL 10.0 Beta9001800270036004500SE +/- 43.74, N = 3SE +/- 17.04, N = 34389.64212.6MIN: 4277.1 / MAX: 4948.49MIN: 4096.98 / MAX: 4879.42

Chaos Group V-RAY

Mode: CPU

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPURHEL 9.5RHEL 10.0 Beta40K80K120K160K200KSE +/- 1664.11, N = 3SE +/- 131.61, N = 3194494202977

Renaissance

Test: Apache Spark PageRank

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark PageRankRHEL 9.5RHEL 10.0 Beta5001000150020002500SE +/- 20.17, N = 3SE +/- 5.41, N = 32157.62101.1MIN: 1547.52 / MAX: 2197.47MIN: 1501.74 / MAX: 2111.56

Perl Benchmarks

Test: Pod2html

OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: Pod2htmlRHEL 9.5RHEL 10.0 Beta0.01440.02880.04320.05760.072SE +/- 0.00013781, N = 3SE +/- 0.00035686, N = 30.063803450.06082243

Renaissance

Test: Apache Spark ALS

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark ALSRHEL 9.5RHEL 10.0 Beta160320480640800SE +/- 1.47, N = 3SE +/- 2.85, N = 3757.7742.5MIN: 730.28 / MAX: 833.95MIN: 679.16 / MAX: 809.44

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenRHEL 9.5RHEL 10.0 Beta100200300400500SE +/- 0.00, N = 3SE +/- 0.33, N = 33504461. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedRHEL 9.5RHEL 10.0 Beta110220330440550SE +/- 0.33, N = 3SE +/- 0.88, N = 33954941. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianRHEL 9.5RHEL 10.0 Beta100200300400500SE +/- 0.67, N = 3SE +/- 1.76, N = 33934721. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: ResizingRHEL 9.5RHEL 10.0 Beta400800120016002000SE +/- 2.00, N = 3SE +/- 7.22, N = 3141219141. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: HWB Color SpaceRHEL 9.5RHEL 10.0 Beta30060090012001500SE +/- 2.91, N = 3SE +/- 1.45, N = 383111981. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlRHEL 9.5RHEL 10.0 Beta30060090012001500SE +/- 1.45, N = 3SE +/- 3.84, N = 3110014971. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp

PyPerformance

Benchmark: gc_collect

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: gc_collectRHEL 9.5RHEL 10.0 Beta2004006008001000SE +/- 1.76, N = 3SE +/- 2.65, N = 3779656

Perl Benchmarks

Test: Interpreter

OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: InterpreterRHEL 9.5RHEL 10.0 Beta0.00020.00040.00060.00080.001SE +/- 0.00000284, N = 3SE +/- 0.00000166, N = 30.000840540.00076987

PyPerformance

Benchmark: asyncio_websockets

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: asyncio_websocketsRHEL 9.5RHEL 10.0 Beta80160240320400SE +/- 0.33, N = 3SE +/- 0.00, N = 3361123

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 5 - Input: Bosphorus 4KRHEL 9.5RHEL 10.0 Beta1326395265SE +/- 0.23, N = 3SE +/- 0.08, N = 355.7257.331. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: CPU-OnlyRHEL 9.5RHEL 10.0 Beta918273645SE +/- 0.07, N = 3SE +/- 0.08, N = 341.0841.03

Cryptsetup

Twofish-XTS 512b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 512b EncryptionRHEL 9.5RHEL 10.0 Beta150300450600750SE +/- 0.20, N = 3SE +/- 1.74, N = 3711.4690.8

Cryptsetup

Serpent-XTS 512b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 512b EncryptionRHEL 9.5RHEL 10.0 Beta160320480640800SE +/- 0.60, N = 2SE +/- 1.75, N = 3754.5744.6

Cryptsetup

AES-XTS 512b Decryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 512b DecryptionRHEL 9.5RHEL 10.0 Beta2K4K6K8K10KSE +/- 19.85, N = 3SE +/- 19.48, N = 35180.111383.4

Cryptsetup

AES-XTS 512b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 512b EncryptionRHEL 9.5RHEL 10.0 Beta2K4K6K8K10KSE +/- 13.89, N = 3SE +/- 20.36, N = 35171.611373.4

Cryptsetup

Twofish-XTS 256b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 256b EncryptionRHEL 9.5RHEL 10.0 Beta150300450600750SE +/- 1.88, N = 3SE +/- 3.21, N = 3710.1693.8

Cryptsetup

Serpent-XTS 256b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 256b EncryptionRHEL 9.5RHEL 10.0 Beta160320480640800SE +/- 2.33, N = 3SE +/- 3.14, N = 3752.4742.9

Cryptsetup

AES-XTS 256b Decryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 256b DecryptionRHEL 9.5RHEL 10.0 Beta3K6K9K12K15KSE +/- 36.60, N = 3SE +/- 16.08, N = 36541.412748.7

Cryptsetup

AES-XTS 256b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 256b EncryptionRHEL 9.5RHEL 10.0 Beta3K6K9K12K15KSE +/- 10.07, N = 3SE +/- 19.85, N = 36509.812705.7

Cryptsetup

PBKDF2-whirlpool

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-whirlpoolRHEL 9.5RHEL 10.0 Beta200K400K600K800K1000KSE +/- 3532.78, N = 3SE +/- 4656.87, N = 39974021009583

Cryptsetup

PBKDF2-sha512

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-sha512RHEL 9.5RHEL 10.0 Beta700K1400K2100K2800K3500KSE +/- 39092.09, N = 3SE +/- 9177.77, N = 327812273043817

PyPerformance

Benchmark: go

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: goRHEL 9.5RHEL 10.0 Beta306090120150SE +/- 0.33, N = 3SE +/- 0.12, N = 3148.073.9

PyPerformance

Benchmark: raytrace

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: raytraceRHEL 9.5RHEL 10.0 Beta60120180240300SE +/- 0.00, N = 3SE +/- 0.00, N = 3252159

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: CPU-OnlyRHEL 9.5RHEL 10.0 Beta816243240SE +/- 0.04, N = 3SE +/- 0.04, N = 335.7035.14

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000RHEL 9.5RHEL 10.0 Beta816243240SE +/- 0.03, N = 3SE +/- 0.02, N = 333.7734.581. (CC) gcc options: -O2 -lz

Zstd Compression

Compression Level: 8, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8, Long Mode - Decompression SpeedRHEL 9.5RHEL 10.0 Beta14002800420056007000SE +/- 15.95, N = 3SE +/- 15.92, N = 36558.76443.31. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 8, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8, Long Mode - Compression SpeedRHEL 9.5RHEL 10.0 Beta30060090012001500SE +/- 8.78, N = 3SE +/- 3.89, N = 31430.31536.11. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 3 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 3 - Decompression SpeedRHEL 9.5RHEL 10.0 Beta13002600390052006500SE +/- 8.08, N = 3SE +/- 5.17, N = 35838.35751.31. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 3 - Compression SpeedRHEL 9.5RHEL 10.0 Beta3K6K9K12K15KSE +/- 109.85, N = 3SE +/- 121.69, N = 313074.213162.31. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 3, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 3, Long Mode - Decompression SpeedRHEL 9.5RHEL 10.0 Beta13002600390052006500SE +/- 9.58, N = 3SE +/- 6.85, N = 36251.26182.11. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

Zstd Compression

Compression Level: 3, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 3, Long Mode - Compression SpeedRHEL 9.5RHEL 10.0 Beta30060090012001500SE +/- 4.38, N = 3SE +/- 2.44, N = 31370.31457.81. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***2. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output TokenRHEL 9.5RHEL 10.0 Beta612182430SE +/- 0.07, N = 3SE +/- 0.09, N = 326.5226.48

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time To First TokenRHEL 9.5RHEL 10.0 Beta918273645SE +/- 0.03, N = 3SE +/- 0.11, N = 337.5336.74

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPURHEL 9.5RHEL 10.0 Beta918273645SE +/- 0.10, N = 3SE +/- 0.14, N = 337.7037.77

x265

Video Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 4.1Video Input: Bosphorus 4KRHEL 9.5RHEL 10.0 Beta510152025SE +/- 0.03, N = 3SE +/- 0.02, N = 318.8119.231. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

PyPerformance

Benchmark: regex_compile

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: regex_compileRHEL 9.5RHEL 10.0 Beta20406080100SE +/- 0.00, N = 3SE +/- 0.03, N = 393.371.3

PyPerformance

Benchmark: pathlib

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: pathlibRHEL 9.5RHEL 10.0 Beta3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 39.679.91

Liquid-DSP

Threads: 192 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 192 - Buffer Length: 256 - Filter Length: 512RHEL 9.5RHEL 10.0 Beta500M1000M1500M2000M2500MSE +/- 2313246.88, N = 3SE +/- 4048182.03, N = 3213146666721686666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 128 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512RHEL 9.5RHEL 10.0 Beta400M800M1200M1600M2000MSE +/- 1794745.42, N = 3SE +/- 3493008.89, N = 3197523333319937333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 64 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512RHEL 9.5RHEL 10.0 Beta300M600M900M1200M1500MSE +/- 2781686.14, N = 3SE +/- 1357694.12, N = 3142646666714339000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Decompression RatingRHEL 9.5RHEL 10.0 Beta130K260K390K520K650KSE +/- 1075.29, N = 3SE +/- 210.19, N = 36245656273631. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Compression RatingRHEL 9.5RHEL 10.0 Beta200K400K600K800K1000KSE +/- 1002.71, N = 3SE +/- 3243.20, N = 39396579637761. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

NAMD

Input: STMV with 1,066,628 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: STMV with 1,066,628 AtomsRHEL 9.5RHEL 10.0 Beta0.95171.90342.85513.80684.7585SE +/- 0.00043, N = 3SE +/- 0.00126, N = 34.226074.22989

PyPerformance

Benchmark: float

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: floatRHEL 9.5RHEL 10.0 Beta1428425670SE +/- 0.03, N = 3SE +/- 0.07, N = 363.142.8

PyPerformance

Benchmark: crypto_pyaes

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: crypto_pyaesRHEL 9.5RHEL 10.0 Beta1326395265SE +/- 0.00, N = 3SE +/- 0.03, N = 360.342.0

DaCapo Benchmark

Java Test: H2 Database Engine

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2 Database EngineRHEL 9.5RHEL 10.0 Beta5001000150020002500SE +/- 30.15, N = 3SE +/- 19.31, N = 321192129

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output TokenRHEL 9.5RHEL 10.0 Beta510152025SE +/- 0.04, N = 3SE +/- 0.02, N = 319.7219.59

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First TokenRHEL 9.5RHEL 10.0 Beta714212835SE +/- 0.11, N = 3SE +/- 0.12, N = 329.9629.57

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPURHEL 9.5RHEL 10.0 Beta1224364860SE +/- 0.12, N = 3SE +/- 0.04, N = 350.7151.04

PyPerformance

Benchmark: chaos

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: chaosRHEL 9.5RHEL 10.0 Beta1326395265SE +/- 0.15, N = 3SE +/- 0.03, N = 357.034.9

PyPerformance

Benchmark: nbody

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: nbodyRHEL 9.5RHEL 10.0 Beta20406080100SE +/- 0.20, N = 3SE +/- 0.15, N = 374.454.0

PyPerformance

Benchmark: pickle_pure_python

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: pickle_pure_pythonRHEL 9.5RHEL 10.0 Beta50100150200250SE +/- 0.00, N = 3SE +/- 0.33, N = 3233165

PyPerformance

Benchmark: json_loads

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.11Benchmark: json_loadsRHEL 9.5RHEL 10.0 Beta3691215SE +/- 0.03, N = 3SE +/- 0.00, N = 312.412.1

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: CPU-OnlyRHEL 9.5RHEL 10.0 Beta510152025SE +/- 0.21, N = 3SE +/- 0.10, N = 318.8318.48

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareRHEL 9.5RHEL 10.0 Beta48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 317.3917.891. (CXX) g++ options: -O3 -lm

NAMD

Input: ATPase with 327,506 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: ATPase with 327,506 AtomsRHEL 9.5RHEL 10.0 Beta3691215SE +/- 0.04, N = 3SE +/- 0.01, N = 312.3212.40

DaCapo Benchmark

Java Test: Apache Lucene Search Index

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search IndexRHEL 9.5RHEL 10.0 Beta5001000150020002500SE +/- 4.06, N = 3SE +/- 16.29, N = 324922468

DaCapo Benchmark

Java Test: Apache Kafka

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache KafkaRHEL 9.5RHEL 10.0 Beta11002200330044005500SE +/- 28.51, N = 3SE +/- 22.34, N = 351105117

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 TokenRHEL 9.5RHEL 10.0 Beta48121620SE +/- 0.18, N = 3SE +/- 0.08, N = 315.1815.13

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 TokenRHEL 9.5RHEL 10.0 Beta510152025SE +/- 0.14, N = 3SE +/- 0.09, N = 318.8118.78

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: CPURHEL 9.5RHEL 10.0 Beta1530456075SE +/- 0.77, N = 3SE +/- 0.33, N = 365.9166.11

Blender

Blend File: Junkshop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: CPU-OnlyRHEL 9.5RHEL 10.0 Beta48121620SE +/- 0.13, N = 3SE +/- 0.02, N = 316.8616.65

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteRHEL 9.5RHEL 10.0 Beta300K600K900K1200K1500KSE +/- 15498.19, N = 3SE +/- 15562.92, N = 311687241273171

DaCapo Benchmark

Java Test: BioJava Biological Data Framework

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: BioJava Biological Data FrameworkRHEL 9.5RHEL 10.0 Beta10002000300040005000SE +/- 6.57, N = 3SE +/- 5.17, N = 345054410

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 8 - Input: Bosphorus 4KRHEL 9.5RHEL 10.0 Beta4080120160200SE +/- 1.38, N = 3SE +/- 0.81, N = 3186.93190.021. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionRHEL 9.5RHEL 10.0 Beta3691215SE +/- 0.06, N = 3SE +/- 0.08, N = 310.7210.501. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output TokenRHEL 9.5RHEL 10.0 Beta48121620SE +/- 0.10, N = 3SE +/- 0.10, N = 318.0117.78

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First TokenRHEL 9.5RHEL 10.0 Beta612182430SE +/- 0.09, N = 3SE +/- 0.08, N = 324.9524.14

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPURHEL 9.5RHEL 10.0 Beta1326395265SE +/- 0.31, N = 3SE +/- 0.32, N = 355.5256.26

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesRHEL 9.5RHEL 10.0 Beta120240360480600SE +/- 1.33, N = 3SE +/- 2.08, N = 3549487

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateRHEL 9.5RHEL 10.0 Beta9001800270036004500SE +/- 3.24, N = 3SE +/- 4.22, N = 34249.884252.681. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas

DaCapo Benchmark

Java Test: Avrora AVR Simulation Framework

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation FrameworkRHEL 9.5RHEL 10.0 Beta6001200180024003000SE +/- 10.17, N = 3SE +/- 13.05, N = 326562580

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 13 - Input: Bosphorus 4KRHEL 9.5RHEL 10.0 Beta100200300400500SE +/- 1.95, N = 3SE +/- 1.01, N = 3438.09441.191. (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 TomcatRHEL 9.5RHEL 10.0 Beta2004006008001000SE +/- 12.53, N = 3SE +/- 3.61, N = 311581124

DaCapo Benchmark

Java Test: Apache Xalan XSLT

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Xalan XSLTRHEL 9.5RHEL 10.0 Beta2004006008001000SE +/- 9.24, N = 5SE +/- 9.85, N = 3911840

Phoronix Test Suite v10.8.5