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.
RHEL 9.5 Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DRAM-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 2048GB SOLIDIGM SSDPFKNU020TZ, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 9.5, Kernel: 5.14.0-503.16.1.el9_5.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server, Compiler: GCC 11.5.0 20240719, File-System: xfs, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --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-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116Java Notes: OpenJDK Runtime Environment (Red_Hat-17.0.13.0.11-1) (build 17.0.13+11-LTS)Python Notes: Python 3.9.21Security Notes: 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 Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFFDisk: 2048GB SOLIDIGM SSDPFKNU020TZ, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 10.0 Beta, Kernel: 6.11.0-0.rc5.23.el10.x86_64 (x86_64), Desktop: GNOME Shell, Compiler: GCC 14.2.1 20240801, File-System: xfs
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --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-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116Java Notes: OpenJDK Runtime Environment (Red_Hat-21.0.4.0.7-1) (build 21.0.4+7-LTS)Python Notes: Python 3.12.5Security Notes: 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 Benchmarks Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution RHEL 9.5 RHEL 10.0 Beta AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads) Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS) AMD Device 153a 12 x 64GB DRAM-6000MT/s Micron MTC40F2046S1RC64BDY QSFF 2048GB SOLIDIGM SSDPFKNU020TZ ASPEED 2 x Broadcom NetXtreme BCM5720 PCIe Red Hat Enterprise Linux 9.5 5.14.0-503.16.1.el9_5.x86_64 (x86_64) GNOME Shell 40.10 X Server GCC 11.5.0 20240719 xfs 1024x768 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF Red Hat Enterprise Linux 10.0 Beta 6.11.0-0.rc5.23.el10.x86_64 (x86_64) GNOME Shell GCC 14.2.1 20240801 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Compiler 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: 0xb002116 Java 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 3.12.5 Security 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 9.5 vs. RHEL 10.0 Beta Comparison Phoronix Test Suite Baseline +48.4% +48.4% +96.8% +96.8% +145.2% +145.2% 193.5% 119.9% 119.8% 100.3% 95.2% 94.9% 63.3% 58.5% 47.4% 44.7% 44.2% 43.7% 43.6% 41.2% 37.8% 36.1% 35.6% 30.9% 27.4% 25.1% 24.1% 20.1% 18.8% 12.7% 12.2% 12% 10.1% 9.8% 9.4% 9.2% 8.9% 8.5% 7.6% 7.4% 6.4% 5.8% 4.9% 4.4% 4.2% 3.3% 3.3% 3% 2.9% 2.9% 2.9% 2.7% 2.6% 2.5% 2.2% 2.2% 2.1% 2% 2% 2.2% 3.4% asyncio_websockets A.X.5.E A.X.5.D go A.X.2.E A.X.2.D chaos raytrace float 8 - Compression Speed HWB Color Space asyncio_tcp_ssl crypto_pyaes pickle_pure_python nbody Swirl Resizing regex_compile Sharpen Enhanced xml_etree Noise-Gaussian gc_collect Writes 14.6% T.F.A.T.T 500 Rotate Time To Compile PBKDF2-sha512 Interpreter P.B.S Apache Xalan XSLT X.b.i.i 8, Long Mode - Compression Speed 3, Long Mode - Compression Speed G.M.M Pod2html Apache Spark Bayes 4.7% CPU I.M.D.S 19 - Compression Speed 3.6% 1000 - 1000 - Read Only - Average Latency 3.6% 1000 - 1000 - Read Only 3.4% 19, Long Mode - Compression Speed 3.3% 19 - D.S 3.3% SHA256 1.R.H.D.F.R.C.C Apache Tomcat T.X.5.E 3% A.A.S.F Preset 5 - Bosphorus 4K MPI CPU - water_GMX50_bare 1000 - 800 - Read Only - Average Latency 2.9% A.S.P 1000 - 800 - Read Only 2.7% Compression Rating pathlib 2.5% json_loads Timed Time - Size 1,000 2.4% T.X.2.E 2.3% Bosphorus 4K B.B.D.F 1.R.H.D.S.R Apache Spark ALS i.i.1.C.P.D Gemma-7b-int4-ov - CPU - T.T.F.T Phi-3-mini-128k-instruct-int4-ov - CPU - T.T.F.T PyPerformance Cryptsetup Cryptsetup PyPerformance Cryptsetup Cryptsetup PyPerformance PyPerformance PyPerformance Zstd Compression GraphicsMagick PyPerformance PyPerformance PyPerformance PyPerformance GraphicsMagick GraphicsMagick PyPerformance GraphicsMagick GraphicsMagick PyPerformance GraphicsMagick PyPerformance Apache Cassandra PyBench nginx GraphicsMagick Timed Node.js Compilation WireGuard + Linux Networking Stack Stress Test Cryptsetup Perl Benchmarks PHPBench DaCapo Benchmark Xcompact3d Incompact3d Zstd Compression Zstd Compression Renaissance Perl Benchmarks Renaissance Chaos Group V-RAY Renaissance Zstd Compression PostgreSQL PostgreSQL Zstd Compression Zstd Compression OpenSSL ClickHouse DaCapo Benchmark Cryptsetup DaCapo Benchmark SVT-AV1 GROMACS PostgreSQL Renaissance PostgreSQL 7-Zip Compression PyPerformance PyPerformance SQLite Speedtest Cryptsetup x265 DaCapo Benchmark ClickHouse Renaissance Xcompact3d Incompact3d OpenVINO GenAI OpenVINO GenAI RHEL 9.5 RHEL 10.0 Beta
RHEL 10.0 Beta AMD EPYC Benchmarks incompact3d: X3D-benchmarking input.i3d tensorflow: CPU - 256 - ResNet-50 wireguard: tensorflow: CPU - 512 - ResNet-50 openssl: RSA4096 openssl: RSA4096 graphics-magick: Rotate openssl: ChaCha20-Poly1305 openssl: AES-256-GCM openssl: ChaCha20 openssl: SHA512 openssl: SHA256 pgbench: 1000 - 1000 - Read Only - Average Latency pgbench: 1000 - 1000 - Read Only pgbench: 1000 - 800 - Read Only - Average Latency pgbench: 1000 - 800 - Read Only svt-av1: Preset 3 - Bosphorus 4K cassandra: Writes clickhouse: 100M Rows Hits Dataset, Third Run clickhouse: 100M Rows Hits Dataset, Second Run clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache blender: Barbershop - CPU-Only renaissance: Apache Spark Bayes pyperformance: xml_etree build-nodejs: Time To Compile compress-zstd: 19 - Decompression Speed compress-zstd: 19 - Compression Speed pyperformance: asyncio_tcp_ssl compress-zstd: 8 - Decompression Speed compress-zstd: 8 - Compression Speed compress-zstd: 19, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed nginx: 500 renaissance: Gaussian Mixture Model renaissance: In-Memory Database Shootout v-ray: CPU renaissance: Apache Spark PageRank perl-benchmark: Pod2html renaissance: Apache Spark ALS graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Noise-Gaussian graphics-magick: Resizing graphics-magick: HWB Color Space graphics-magick: Swirl pyperformance: gc_collect perl-benchmark: Interpreter pyperformance: asyncio_websockets svt-av1: Preset 5 - Bosphorus 4K blender: Pabellon Barcelona - CPU-Only cryptsetup: Twofish-XTS 512b Encryption cryptsetup: Serpent-XTS 512b Encryption cryptsetup: AES-XTS 512b Decryption cryptsetup: AES-XTS 512b Encryption cryptsetup: Twofish-XTS 256b Encryption cryptsetup: Serpent-XTS 256b Encryption cryptsetup: AES-XTS 256b Decryption cryptsetup: AES-XTS 256b Encryption cryptsetup: PBKDF2-whirlpool cryptsetup: PBKDF2-sha512 pyperformance: go pyperformance: raytrace blender: Classroom - CPU-Only sqlite-speedtest: Timed Time - Size 1,000 compress-zstd: 8, Long Mode - Decompression Speed compress-zstd: 8, Long Mode - Compression Speed compress-zstd: 3 - Decompression Speed compress-zstd: 3 - Compression Speed compress-zstd: 3, Long Mode - Decompression Speed compress-zstd: 3, Long Mode - Compression Speed openvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Token openvino-genai: Gemma-7b-int4-ov - CPU - Time To First Token openvino-genai: Gemma-7b-int4-ov - CPU x265: Bosphorus 4K pyperformance: regex_compile pyperformance: pathlib liquid-dsp: 192 - 256 - 512 liquid-dsp: 128 - 256 - 512 liquid-dsp: 64 - 256 - 512 compress-7zip: Decompression Rating compress-7zip: Compression Rating namd: STMV with 1,066,628 Atoms pyperformance: float pyperformance: crypto_pyaes dacapobench: H2 Database Engine openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU pyperformance: chaos pyperformance: nbody pyperformance: pickle_pure_python pyperformance: json_loads blender: Fishy Cat - CPU-Only gromacs: MPI CPU - water_GMX50_bare namd: ATPase with 327,506 Atoms dacapobench: Apache Lucene Search Index dacapobench: Apache Kafka openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU blender: Junkshop - CPU-Only phpbench: PHP Benchmark Suite dacapobench: BioJava Biological Data Framework svt-av1: Preset 8 - Bosphorus 4K incompact3d: input.i3d 193 Cells Per Direction openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU pybench: Total For Average Test Times mt-dgemm: Sustained Floating-Point Rate dacapobench: Avrora AVR Simulation Framework svt-av1: Preset 13 - Bosphorus 4K dacapobench: Apache Tomcat dacapobench: Apache Xalan XSLT RHEL 9.5 RHEL 10.0 Beta 390.734192 167.38 186.373 169.46 2028196.9 50420.0 350 598137198093 1318996105533 875870628703 53817614890 135224180487 0.308 3240478 0.244 3275353 15.831 532385 778.17 780.37 744.33 125.03 175.7 39.1 116.535 5024.8 132.2 684 6160.1 4738.8 4990.5 65.0 378869.13 3404.2 4389.6 194494 2157.6 0.06380345 757.7 350 395 393 1412 831 1100 779 0.00084054 361 55.716 41.08 711.4 754.5 5180.1 5171.6 710.1 752.4 6541.4 6509.8 997402 2781227 148 252 35.70 33.767 6558.7 1430.3 5838.3 13074.2 6251.2 1370.3 26.52 37.53 37.70 18.81 93.3 9.67 2131466667 1975233333 1426466667 624565 939657 4.22607 63.1 60.3 2119 19.72 29.96 50.71 57.0 74.4 233 12.4 18.83 17.394 12.31671 2492 5110 15.18 18.81 65.91 16.86 1168724 4505 186.930 10.7175849 18.01 24.95 55.52 549 4249.879242 2656 438.091 1158 911 363.071906 166.28 169.688 169.53 2030249.2 50685.2 392 596085117563 1321398713187 872714248010 54198025127 139711381210 0.319 3135212 0.251 3189942 16.023 464647 791.13 796.94 768.98 123.35 184.0 31.5 105.891 4863.3 127.6 476 6060.5 6854.7 4971.9 62.9 425156.32 3217.0 4212.6 202977 2101.1 0.06082243 742.5 446 494 472 1914 1198 1497 656 0.00076987 123 57.332 41.03 690.8 744.6 11383.4 11373.4 693.8 742.9 12748.7 12705.7 1009583 3043817 73.9 159 35.14 34.582 6443.3 1536.1 5751.3 13162.3 6182.1 1457.8 26.48 36.74 37.77 19.23 71.3 9.91 2168666667 1993733333 1433900000 627363 963776 4.22989 42.8 42.0 2129 19.59 29.57 51.04 34.9 54.0 165 12.1 18.48 17.894 12.39532 2468 5117 15.13 18.78 66.11 16.65 1273171 4410 190.018 10.5026401 17.78 24.14 56.26 487 4252.679568 2580 441.191 1124 840 OpenBenchmarking.org
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.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d RHEL 10.0 Beta RHEL 9.5 80 160 240 320 400 SE +/- 8.67, N = 9 SE +/- 7.96, N = 9 363.07 390.73 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 RHEL 10.0 Beta RHEL 9.5 40 80 120 160 200 SE +/- 4.10, N = 12 SE +/- 4.20, N = 12 166.28 167.38
WireGuard + Linux Networking Stack Stress Test This is a benchmark of the WireGuard secure VPN tunnel and Linux networking stack stress test. The test runs on the local host but does require root permissions to run. The way it works is it creates three namespaces. ns0 has a loopback device. ns1 and ns2 each have wireguard devices. Those two wireguard devices send traffic through the loopback device of ns0. The end result of this is that tests wind up testing encryption and decryption at the same time -- a pretty CPU and scheduler-heavy workflow. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test RHEL 10.0 Beta RHEL 9.5 40 80 120 160 200 SE +/- 0.87, N = 3 SE +/- 2.88, N = 12 169.69 186.37
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 RHEL 10.0 Beta RHEL 9.5 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 169.53 169.46
OpenSSL OpenBenchmarking.org verify/s, More Is Better OpenSSL Algorithm: RSA4096 RHEL 10.0 Beta RHEL 9.5 400K 800K 1200K 1600K 2000K SE +/- 265.26, N = 3 SE +/- 174.76, N = 3 2030249.2 2028196.9 1. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)
OpenBenchmarking.org sign/s, More Is Better OpenSSL Algorithm: RSA4096 RHEL 10.0 Beta RHEL 9.5 11K 22K 33K 44K 55K SE +/- 25.23, N = 3 SE +/- 19.40, N = 3 50685.2 50420.0 1. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Rotate RHEL 10.0 Beta RHEL 9.5 90 180 270 360 450 SE +/- 2.78, N = 15 SE +/- 1.67, N = 3 392 350 1. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp
OpenSSL OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: ChaCha20-Poly1305 RHEL 10.0 Beta RHEL 9.5 130000M 260000M 390000M 520000M 650000M SE +/- 198992872.07, N = 3 SE +/- 311658956.47, N = 3 596085117563 598137198093 1. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: AES-256-GCM RHEL 10.0 Beta RHEL 9.5 300000M 600000M 900000M 1200000M 1500000M SE +/- 927462302.83, N = 3 SE +/- 1099131454.93, N = 3 1321398713187 1318996105533 1. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: ChaCha20 RHEL 10.0 Beta RHEL 9.5 200000M 400000M 600000M 800000M 1000000M SE +/- 515095183.79, N = 3 SE +/- 561226959.81, N = 3 872714248010 875870628703 1. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: SHA512 RHEL 10.0 Beta RHEL 9.5 12000M 24000M 36000M 48000M 60000M SE +/- 154598274.25, N = 3 SE +/- 56122603.90, N = 3 54198025127 53817614890 1. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: SHA256 RHEL 10.0 Beta RHEL 9.5 30000M 60000M 90000M 120000M 150000M SE +/- 143924649.50, N = 3 SE +/- 219362632.74, N = 3 139711381210 135224180487 1. OpenSSL 3.2.2 4 Jun 2024 (Library: OpenSSL 3.2.2 4 Jun 2024)
PostgreSQL OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 17 Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only - Average Latency RHEL 10.0 Beta RHEL 9.5 0.0718 0.1436 0.2154 0.2872 0.359 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 0.319 0.308 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 17 Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only RHEL 10.0 Beta RHEL 9.5 700K 1400K 2100K 2800K 3500K SE +/- 6126.05, N = 3 SE +/- 4071.13, N = 3 3135212 3240478 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 17 Scaling Factor: 1000 - Clients: 800 - Mode: Read Only - Average Latency RHEL 10.0 Beta RHEL 9.5 0.0565 0.113 0.1695 0.226 0.2825 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 0.251 0.244 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 17 Scaling Factor: 1000 - Clients: 800 - Mode: Read Only RHEL 10.0 Beta RHEL 9.5 700K 1400K 2100K 2800K 3500K SE +/- 7552.31, N = 3 SE +/- 3020.11, N = 3 3189942 3275353 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 3 - Input: Bosphorus 4K RHEL 10.0 Beta RHEL 9.5 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 16.02 15.83 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run RHEL 10.0 Beta RHEL 9.5 200 400 600 800 1000 SE +/- 4.41, N = 3 SE +/- 5.25, N = 3 791.13 778.17 MIN: 69.36 / MAX: 8571.43 MIN: 69.12 / MAX: 8571.43
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run RHEL 10.0 Beta RHEL 9.5 200 400 600 800 1000 SE +/- 2.72, N = 3 SE +/- 6.89, N = 3 796.94 780.37 MIN: 70.26 / MAX: 8571.43 MIN: 69.85 / MAX: 7500
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache RHEL 10.0 Beta RHEL 9.5 170 340 510 680 850 SE +/- 2.01, N = 3 SE +/- 8.90, N = 3 768.98 744.33 MIN: 69.04 / MAX: 8571.43 MIN: 68.97 / MAX: 7500
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Barbershop - Compute: CPU-Only RHEL 10.0 Beta RHEL 9.5 30 60 90 120 150 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 123.35 125.03
Renaissance OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark Bayes RHEL 10.0 Beta RHEL 9.5 40 80 120 160 200 SE +/- 2.28, N = 4 SE +/- 1.74, N = 6 184.0 175.7 MIN: 161.42 / MAX: 229.13 MIN: 158.43 / MAX: 233.67
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed RHEL 10.0 Beta RHEL 9.5 1100 2200 3300 4400 5500 SE +/- 3.26, N = 15 SE +/- 13.96, N = 3 4863.3 5024.8 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Compression Speed RHEL 10.0 Beta RHEL 9.5 30 60 90 120 150 SE +/- 1.25, N = 15 SE +/- 1.72, N = 3 127.6 132.2 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Decompression Speed RHEL 10.0 Beta RHEL 9.5 1300 2600 3900 5200 6500 SE +/- 1.84, N = 3 SE +/- 6.49, N = 15 6060.5 6160.1 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Compression Speed RHEL 10.0 Beta RHEL 9.5 1500 3000 4500 6000 7500 SE +/- 10.63, N = 3 SE +/- 43.63, N = 15 6854.7 4738.8 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Decompression Speed RHEL 10.0 Beta RHEL 9.5 1100 2200 3300 4400 5500 SE +/- 12.19, N = 3 SE +/- 4.52, N = 15 4971.9 4990.5 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Compression Speed RHEL 10.0 Beta RHEL 9.5 15 30 45 60 75 SE +/- 0.87, N = 3 SE +/- 0.49, N = 15 62.9 65.0 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
nginx This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 RHEL 10.0 Beta RHEL 9.5 90K 180K 270K 360K 450K SE +/- 975.49, N = 3 SE +/- 1253.75, N = 3 425156.32 378869.13 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Renaissance OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Gaussian Mixture Model RHEL 10.0 Beta RHEL 9.5 700 1400 2100 2800 3500 SE +/- 6.50, N = 3 SE +/- 38.98, N = 4 3217.0 3404.2 MIN: 2413.84 / MAX: 3226.59 MIN: 2508.31 / MAX: 3518.29
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: In-Memory Database Shootout RHEL 10.0 Beta RHEL 9.5 900 1800 2700 3600 4500 SE +/- 17.04, N = 3 SE +/- 43.74, N = 3 4212.6 4389.6 MIN: 4096.98 / MAX: 4879.42 MIN: 4277.1 / MAX: 4948.49
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 6.0 Mode: CPU RHEL 10.0 Beta RHEL 9.5 40K 80K 120K 160K 200K SE +/- 131.61, N = 3 SE +/- 1664.11, N = 3 202977 194494
Renaissance OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark PageRank RHEL 10.0 Beta RHEL 9.5 500 1000 1500 2000 2500 SE +/- 5.41, N = 3 SE +/- 20.17, N = 3 2101.1 2157.6 MIN: 1501.74 / MAX: 2111.56 MIN: 1547.52 / MAX: 2197.47
Renaissance OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark ALS RHEL 10.0 Beta RHEL 9.5 160 320 480 640 800 SE +/- 2.85, N = 3 SE +/- 1.47, N = 3 742.5 757.7 MIN: 679.16 / MAX: 809.44 MIN: 730.28 / MAX: 833.95
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Sharpen RHEL 10.0 Beta RHEL 9.5 100 200 300 400 500 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 446 350 1. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Enhanced RHEL 10.0 Beta RHEL 9.5 110 220 330 440 550 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 494 395 1. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Noise-Gaussian RHEL 10.0 Beta RHEL 9.5 100 200 300 400 500 SE +/- 1.76, N = 3 SE +/- 0.67, N = 3 472 393 1. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Resizing RHEL 10.0 Beta RHEL 9.5 400 800 1200 1600 2000 SE +/- 7.22, N = 3 SE +/- 2.00, N = 3 1914 1412 1. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: HWB Color Space RHEL 10.0 Beta RHEL 9.5 300 600 900 1200 1500 SE +/- 1.45, N = 3 SE +/- 2.91, N = 3 1198 831 1. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Swirl RHEL 10.0 Beta RHEL 9.5 300 600 900 1200 1500 SE +/- 3.84, N = 3 SE +/- 1.45, N = 3 1497 1100 1. (CC) gcc options: -fopenmp -O2 -ljpeg -lzstd -lz -lm -lpthread -lgomp
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 5 - Input: Bosphorus 4K RHEL 10.0 Beta RHEL 9.5 13 26 39 52 65 SE +/- 0.08, N = 3 SE +/- 0.23, N = 3 57.33 55.72 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Pabellon Barcelona - Compute: CPU-Only RHEL 10.0 Beta RHEL 9.5 9 18 27 36 45 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 41.03 41.08
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Encryption RHEL 10.0 Beta RHEL 9.5 160 320 480 640 800 SE +/- 1.75, N = 3 SE +/- 0.60, N = 2 744.6 754.5
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Decryption RHEL 10.0 Beta RHEL 9.5 2K 4K 6K 8K 10K SE +/- 19.48, N = 3 SE +/- 19.85, N = 3 11383.4 5180.1
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Encryption RHEL 10.0 Beta RHEL 9.5 2K 4K 6K 8K 10K SE +/- 20.36, N = 3 SE +/- 13.89, N = 3 11373.4 5171.6
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Encryption RHEL 10.0 Beta RHEL 9.5 150 300 450 600 750 SE +/- 3.21, N = 3 SE +/- 1.88, N = 3 693.8 710.1
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Encryption RHEL 10.0 Beta RHEL 9.5 160 320 480 640 800 SE +/- 3.14, N = 3 SE +/- 2.33, N = 3 742.9 752.4
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Decryption RHEL 10.0 Beta RHEL 9.5 3K 6K 9K 12K 15K SE +/- 16.08, N = 3 SE +/- 36.60, N = 3 12748.7 6541.4
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Encryption RHEL 10.0 Beta RHEL 9.5 3K 6K 9K 12K 15K SE +/- 19.85, N = 3 SE +/- 10.07, N = 3 12705.7 6509.8
OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-whirlpool RHEL 10.0 Beta RHEL 9.5 200K 400K 600K 800K 1000K SE +/- 4656.87, N = 3 SE +/- 3532.78, N = 3 1009583 997402
OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-sha512 RHEL 10.0 Beta RHEL 9.5 700K 1400K 2100K 2800K 3500K SE +/- 9177.77, N = 3 SE +/- 39092.09, N = 3 3043817 2781227
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Classroom - Compute: CPU-Only RHEL 10.0 Beta RHEL 9.5 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 35.14 35.70
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Decompression Speed RHEL 10.0 Beta RHEL 9.5 1400 2800 4200 5600 7000 SE +/- 15.92, N = 3 SE +/- 15.95, N = 3 6443.3 6558.7 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Compression Speed RHEL 10.0 Beta RHEL 9.5 300 600 900 1200 1500 SE +/- 3.89, N = 3 SE +/- 8.78, N = 3 1536.1 1430.3 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Decompression Speed RHEL 10.0 Beta RHEL 9.5 1300 2600 3900 5200 6500 SE +/- 5.17, N = 3 SE +/- 8.08, N = 3 5751.3 5838.3 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Compression Speed RHEL 10.0 Beta RHEL 9.5 3K 6K 9K 12K 15K SE +/- 121.69, N = 3 SE +/- 109.85, N = 3 13162.3 13074.2 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3, Long Mode - Decompression Speed RHEL 10.0 Beta RHEL 9.5 1300 2600 3900 5200 6500 SE +/- 6.85, N = 3 SE +/- 9.58, N = 3 6182.1 6251.2 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3, Long Mode - Compression Speed RHEL 10.0 Beta RHEL 9.5 300 600 900 1200 1500 SE +/- 2.44, N = 3 SE +/- 4.38, N = 3 1457.8 1370.3 1. RHEL 10.0 Beta: *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet *** 2. RHEL 9.5: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
OpenVINO GenAI OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token RHEL 10.0 Beta RHEL 9.5 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 26.48 26.52
x265 OpenBenchmarking.org Frames Per Second, More Is Better x265 4.1 Video Input: Bosphorus 4K RHEL 10.0 Beta RHEL 9.5 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 19.23 18.81 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 192 - Buffer Length: 256 - Filter Length: 512 RHEL 10.0 Beta RHEL 9.5 500M 1000M 1500M 2000M 2500M SE +/- 4048182.03, N = 3 SE +/- 2313246.88, N = 3 2168666667 2131466667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 512 RHEL 10.0 Beta RHEL 9.5 400M 800M 1200M 1600M 2000M SE +/- 3493008.89, N = 3 SE +/- 1794745.42, N = 3 1993733333 1975233333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 RHEL 10.0 Beta RHEL 9.5 300M 600M 900M 1200M 1500M SE +/- 1357694.12, N = 3 SE +/- 2781686.14, N = 3 1433900000 1426466667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
7-Zip Compression OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Decompression Rating RHEL 10.0 Beta RHEL 9.5 130K 260K 390K 520K 650K SE +/- 210.19, N = 3 SE +/- 1075.29, N = 3 627363 624565 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Compression Rating RHEL 10.0 Beta RHEL 9.5 200K 400K 600K 800K 1000K SE +/- 3243.20, N = 3 SE +/- 1002.71, N = 3 963776 939657 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
NAMD OpenBenchmarking.org ns/day, More Is Better NAMD 3.0 Input: STMV with 1,066,628 Atoms RHEL 10.0 Beta RHEL 9.5 0.9517 1.9034 2.8551 3.8068 4.7585 SE +/- 0.00126, N = 3 SE +/- 0.00043, N = 3 4.22989 4.22607
OpenVINO GenAI OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token RHEL 10.0 Beta RHEL 9.5 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 19.59 19.72
OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token RHEL 10.0 Beta RHEL 9.5 7 14 21 28 35 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 29.57 29.96
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Fishy Cat - Compute: CPU-Only RHEL 10.0 Beta RHEL 9.5 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.21, N = 3 18.48 18.83
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.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare RHEL 10.0 Beta RHEL 9.5 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 17.89 17.39 1. (CXX) g++ options: -O3 -lm
NAMD OpenBenchmarking.org ns/day, More Is Better NAMD 3.0 Input: ATPase with 327,506 Atoms RHEL 10.0 Beta RHEL 9.5 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 12.40 12.32
OpenVINO GenAI OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token RHEL 10.0 Beta RHEL 9.5 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 15.13 15.18
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Junkshop - Compute: CPU-Only RHEL 10.0 Beta RHEL 9.5 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 16.65 16.86
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite RHEL 10.0 Beta RHEL 9.5 300K 600K 900K 1200K 1500K SE +/- 15562.92, N = 3 SE +/- 15498.19, N = 3 1273171 1168724
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 8 - Input: Bosphorus 4K RHEL 10.0 Beta RHEL 9.5 40 80 120 160 200 SE +/- 0.81, N = 3 SE +/- 1.38, N = 3 190.02 186.93 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction RHEL 10.0 Beta RHEL 9.5 3 6 9 12 15 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 10.50 10.72 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenVINO GenAI OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token RHEL 10.0 Beta RHEL 9.5 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 17.78 18.01
OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token RHEL 10.0 Beta RHEL 9.5 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 24.14 24.95
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times RHEL 10.0 Beta RHEL 9.5 120 240 360 480 600 SE +/- 2.08, N = 3 SE +/- 1.33, N = 3 487 549
ACES DGEMM OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate RHEL 10.0 Beta RHEL 9.5 900 1800 2700 3600 4500 SE +/- 4.22, N = 3 SE +/- 3.24, N = 3 4252.68 4249.88 1. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.3 Encoder Mode: Preset 13 - Input: Bosphorus 4K RHEL 10.0 Beta RHEL 9.5 100 200 300 400 500 SE +/- 1.01, N = 3 SE +/- 1.95, N = 3 441.19 438.09 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
RHEL 9.5 Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DRAM-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 2048GB SOLIDIGM SSDPFKNU020TZ, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 9.5, Kernel: 5.14.0-503.16.1.el9_5.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server, Compiler: GCC 11.5.0 20240719, File-System: xfs, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --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-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116Java Notes: OpenJDK Runtime Environment (Red_Hat-17.0.13.0.11-1) (build 17.0.13+11-LTS)Python Notes: Python 3.9.21Security Notes: 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
Testing initiated at 14 December 2024 09:35 by user .
RHEL 10.0 Beta Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 2048GB SOLIDIGM SSDPFKNU020TZ, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Red Hat Enterprise Linux 10.0 Beta, Kernel: 6.11.0-0.rc5.23.el10.x86_64 (x86_64), Desktop: GNOME Shell, Compiler: GCC 14.2.1 20240801, File-System: xfs
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --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-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116Java Notes: OpenJDK Runtime Environment (Red_Hat-21.0.4.0.7-1) (build 21.0.4+7-LTS)Python Notes: Python 3.12.5Security Notes: 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
Testing initiated at 15 December 2024 02:14 by user .