AMD EPYC 9575F 1P SMT comparison benchmarks by Michael Larabel for a future article. Fresh tests repeated with SMT on/off from SMCI BIOS toggle.
SMT Enabled - Default Processor: AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores / 128 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.10, Kernel: 6.13.0-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116Python Notes: Python 3.12.7Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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
SMT Disabled Changed Processor to AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores) .
Security Change: 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: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
AMD EPYC Zen 5 SMT Comparison OpenBenchmarking.org Phoronix Test Suite AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores / 128 Threads) AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores) Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS) AMD 1Ah 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF 3201GB Micron_7450_MTFDKCB3T2TFS ASPEED 2 x Broadcom NetXtreme BCM5720 PCIe Ubuntu 24.10 6.13.0-phx (x86_64) GNOME Shell 47.0 X Server GCC 14.2.0 ext4 1024x768 Processors Motherboard Chipset Memory Disk Graphics Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution AMD EPYC Zen 5 SMT Comparison Benchmarks System Logs - Transparent Huge Pages: madvise - --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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116 - Python 3.12.7 - SMT Enabled - Default: 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 - SMT Disabled: 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: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
SMT Enabled - Default vs. SMT Disabled Comparison Phoronix Test Suite Baseline +24.8% +24.8% +49.6% +49.6% +74.4% +74.4% 99% 89.9% 89.2% 85.7% 84.8% 78.9% 75% 70.8% 22.7% 17.4% 15.8% 14.7% 14.3% 12% 11.5% 10.8% 8.7% 8.5% 8.5% 8.4% 8% 7.8% 7% 6.7% 5.6% 5.6% 5.1% 4.6% 3.3% 2.9% 2.8% 2.7% 2.2% 2.2% 2.2% 2.1% 2.1% 2% R.S.A.F.I - CPU V.D.F.I - CPU Resizing P.V.B.D.F - CPU Update Rand M.T.E.T.D.F - CPU P.R.I.R.F - CPU Read While Writing 72.7% Update Rand D.R 61.3% Pathtracer ISPC - Crown 56.8% Pathtracer ISPC - Asian Dragon 56.2% Pathtracer ISPC - Asian Dragon Obj 55.9% WPA PSK 54% Read While Writing 47.9% bcrypt 44.3% Blowfish 44.2% ChaCha20-Poly1305 42.9% CoreMark Size 666 - I.P.S 41.9% H.T.M 41.5% CPU Stress 41.3% ChaCha20 41.2% R.C.a.P - CPU 41.1% LuxCore Benchmark - CPU 40.4% Danish Mood - CPU 39.8% Vector Math 38.6% Chess Benchmark 38.1% 3 - 4K - 1 - Path Tracer - CPU 37.7% 2 - 4K - 1 - Path Tracer - CPU 37.4% 1 - 4K - 1 - Path Tracer - CPU 36.3% 1:100 36.1% 3 - 4K - 32 - Path Tracer - CPU 34.4% Enhanced 34.1% 2 - 4K - 32 - Path Tracer - CPU 34.1% SHA256 34% 100 - 800 - Read Only - Average Latency 33.9% Orange Juice - CPU 33.8% 1 - 4K - 32 - Path Tracer - CPU 33.5% 100 - 800 - Read Only 33.4% v.I 33.3% 100 - 1000 - Read Only 33.1% 100 - 1000 - Read Only - Average Latency 32.7% Pabellon Barcelona - CPU-Only 32.1% MD5 31.4% Compression Rating 30.2% Junkshop - CPU-Only 30.1% Barbershop - CPU-Only 29.7% 100 - 800 - Read Write 29.6% 100 - 800 - Read Write - Average Latency 29.5% DLSC - CPU 28.5% Context Switching 27.5% Classroom - CPU-Only 26.6% BMW27 - CPU-Only 25.8% R.R.W.R 23.8% Noise-Gaussian 23.8% 100 - 1000 - Read Write 23.7% 100 - 1000 - Read Write - Average Latency 23.7% SP.B Integer Math 21.8% 128 - 256 - 512 21.6% AVX-512 VNNI 19.2% EP.C N.S.P.L.F - CPU 16.5% RSA4096 16.3% 500 15.9% CG.C allmodconfig 15.8% P.R.I.R.F - CPU 15.1% FT.C CPU Cache A.w.3.5.A 14.1% S.w.1.0.6.A 13.9% Ninja 13.4% HMAC-SHA512 13% Swirl 12.4% N.S.P.L.F - CPU 12.4% MG.C M.T.E.T.D.F - CPU 12% 1000 11.5% LU.C 1:10 11.4% P.P.B.T.T 11% Total Time 10.8% EP.D F.D.R.F.I - CPU 10.6% I.B.O 10% Time To Compile 9.6% P.P.B.T.T 9.4% SHA512 9.1% Bosphorus 4K - Slow Bosphorus 4K - Faster Bosphorus 4K - Medium HWB Color Space Bosphorus 4K - Fast Bosphorus 4K - Slow Time To Compile 7.7% P.V.B.D.F - CPU 7.6% Time To Compile 7.1% BT.C 1e13 7% Bosphorus 4K - Medium AES-256-GCM 6.6% Bosphorus 4K - Very Fast 6.1% Bosphorus 4K - Very Fast 5.9% F.D.R.F.I - CPU 5.7% V.D.F.I - CPU 5.7% Preset 13 - Bosphorus 4K Preset 8 - Bosphorus 4K S.F.P.R Bosphorus 4K - Ultra Fast NUMA 4.4% Bosphorus 4K - Super Fast Preset 5 - Bosphorus 4K SP.C 1.R.H.D.S.R H.E.R.F.I - CPU 2.3% Bosphorus 4K - Ultra Fast Memory Copying 2.2% Rotate CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - T.G.1 H.E.R.F.I - CPU 2.1% Rand Read 5K - 16 2.1% 1.R.H.D.F.R.C.C Preset 3 - Bosphorus 4K 4K - 16 2% OpenVINO OpenVINO GraphicsMagick OpenVINO RocksDB OpenVINO OpenVINO Speedb Speedb 7-Zip Compression Embree Embree Embree John The Ripper RocksDB John The Ripper John The Ripper OpenSSL Coremark Stress-NG Stress-NG OpenSSL LuxCoreRender LuxCoreRender LuxCoreRender Stress-NG Stockfish OSPRay Studio OSPRay Studio OSPRay Studio Memcached OSPRay Studio GraphicsMagick OSPRay Studio OpenSSL PostgreSQL LuxCoreRender OSPRay Studio PostgreSQL OpenVKL PostgreSQL PostgreSQL Blender John The Ripper 7-Zip Compression Blender Blender PostgreSQL PostgreSQL LuxCoreRender Stress-NG Blender Blender RocksDB GraphicsMagick PostgreSQL PostgreSQL NAS Parallel Benchmarks Stress-NG Liquid-DSP Stress-NG NAS Parallel Benchmarks OpenVINO OpenSSL nginx NAS Parallel Benchmarks Timed Linux Kernel Compilation OpenVINO NAS Parallel Benchmarks Stress-NG NAMD NAMD Timed LLVM Compilation John The Ripper GraphicsMagick OpenVINO NAS Parallel Benchmarks OpenVINO nginx NAS Parallel Benchmarks Memcached srsRAN Project Tachyon NAS Parallel Benchmarks OpenVINO Stress-NG Timed Node.js Compilation srsRAN Project OpenSSL Kvazaar VVenC Kvazaar GraphicsMagick VVenC uvg266 Timed Eigen Compilation OpenVINO Timed Gem5 Compilation NAS Parallel Benchmarks Primesieve uvg266 OpenSSL Kvazaar uvg266 OpenVINO OpenVINO SVT-AV1 SVT-AV1 ACES DGEMM uvg266 Stress-NG Kvazaar SVT-AV1 NAS Parallel Benchmarks ClickHouse OpenVINO Kvazaar Stress-NG GraphicsMagick Llama.cpp OpenVINO Speedb C-Ray ClickHouse SVT-AV1 C-Ray SMT Enabled - Default SMT Disabled
AMD EPYC Zen 5 SMT Comparison openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Token llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128 llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128 stress-ng: CPU Stress stress-ng: Memory Copying stress-ng: Vector Math stress-ng: Context Switching stress-ng: CPU Cache stress-ng: NUMA stress-ng: AVX-512 VNNI stress-ng: Integer Math stress-ng: Integer Bit Operations stress-ng: Hyperbolic Trigonometric Math srsran: PUSCH Processor Benchmark, Throughput Total srsran: PDSCH Processor Benchmark, Throughput Total blender: BMW27 - CPU-Only blender: Classroom - CPU-Only blender: Pabellon Barcelona - CPU-Only blender: Barbershop - CPU-Only blender: Junkshop - CPU-Only luxcorerender: DLSC - CPU luxcorerender: Rainbow Colors and Prism - CPU luxcorerender: LuxCore Benchmark - CPU luxcorerender: Orange Juice - CPU luxcorerender: Danish Mood - CPU npb: BT.C npb: EP.C npb: EP.D npb: FT.C npb: LU.C npb: SP.B npb: SP.C npb: IS.D npb: MG.C npb: CG.C ospray-studio: 1 - 4K - 1 - Path Tracer - CPU ospray-studio: 1 - 4K - 32 - Path Tracer - CPU ospray-studio: 2 - 4K - 1 - Path Tracer - CPU ospray-studio: 2 - 4K - 32 - Path Tracer - CPU ospray-studio: 3 - 4K - 1 - Path Tracer - CPU ospray-studio: 3 - 4K - 32 - Path Tracer - CPU openvkl: vklBenchmarkCPU ISPC embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer ISPC - Asian Dragon Obj embree: Pathtracer ISPC - Crown build-eigen: Time To Compile build-linux-kernel: allmodconfig build-llvm: Ninja build-nodejs: Time To Compile build-gem5: Time To Compile palabos: 500 laghos: Sedov Blast Wave, ube_922_hex.mesh laghos: Triple Point Problem svt-av1: Preset 13 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 5 - Bosphorus 4K svt-av1: Preset 3 - Bosphorus 4K kvazaar: Bosphorus 4K - Slow kvazaar: Bosphorus 4K - Medium kvazaar: Bosphorus 4K - Very Fast kvazaar: Bosphorus 4K - Super Fast kvazaar: Bosphorus 4K - Ultra Fast vvenc: Bosphorus 4K - Fast vvenc: Bosphorus 4K - Faster uvg266: Bosphorus 4K - Slow uvg266: Bosphorus 4K - Medium uvg266: Bosphorus 4K - Very Fast uvg266: Bosphorus 4K - Super Fast uvg266: Bosphorus 4K - Ultra Fast liquid-dsp: 64 - 256 - 512 liquid-dsp: 128 - 256 - 512 nginx: 500 nginx: 1000 rustls: handshake - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 rustls: handshake - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 rustls: handshake - TLS13_CHACHA20_POLY1305_SHA256 rustls: handshake-ticket - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 rustls: handshake-ticket - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 rustls: handshake-ticket - TLS13_CHACHA20_POLY1305_SHA256 rustls: handshake-resume - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 rustls: handshake-resume - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 rustls: handshake-resume - TLS13_CHACHA20_POLY1305_SHA256 openssl: RSA4096 openssl: RSA4096 openssl: SHA256 openssl: SHA512 openssl: AES-128-GCM openssl: AES-256-GCM openssl: ChaCha20 openssl: ChaCha20-Poly1305 john-the-ripper: MD5 john-the-ripper: Blowfish john-the-ripper: HMAC-SHA512 john-the-ripper: bcrypt john-the-ripper: WPA PSK clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache clickhouse: 100M Rows Hits Dataset, Second Run clickhouse: 100M Rows Hits Dataset, Third Run pgbench: 100 - 800 - Read Write pgbench: 100 - 800 - Read Write - Average Latency pgbench: 100 - 800 - Read Only pgbench: 100 - 800 - Read Only - Average Latency pgbench: 100 - 1000 - Read Write pgbench: 100 - 1000 - Read Write - Average Latency pgbench: 100 - 1000 - Read Only pgbench: 100 - 1000 - Read Only - Average Latency memcached: 1:100 memcached: 1:10 rocksdb: Rand Read rocksdb: Read While Writing rocksdb: Read Rand Write Rand rocksdb: Update Rand speedb: Rand Read speedb: Read While Writing speedb: Read Rand Write Rand speedb: Update Rand coremark: CoreMark Size 666 - Iterations Per Second graphics-magick: HWB Color Space graphics-magick: Noise-Gaussian graphics-magick: Enhanced graphics-magick: Resizing graphics-magick: Rotate graphics-magick: Sharpen graphics-magick: Swirl mt-dgemm: Sustained Floating-Point Rate lammps: 20k Atoms namd: ATPase with 327,506 Atoms namd: STMV with 1,066,628 Atoms financebench: Bonds OpenMP financebench: Repo OpenMP compress-7zip: Compression Rating compress-7zip: Decompression Rating primesieve: 1e13 stockfish: Chess Benchmark tachyon: Total Time c-ray: 4K - 16 c-ray: 5K - 16 SMT Enabled - Default SMT Disabled 7670.87 4.14 6268.38 5.05 790.57 40.44 22207.98 2.8 3186.97 20.07 2341.28 13.63 9483.91 3.36 6539.33 9.46 78.06 15.84 12.81 50.43 117.03 52.93 207237.29 26334.21 553414.27 52341805.75 2704684.59 2094.07 13250045.88 6977901.84 19006107.55 488803.14 20677.2 118394.6 14.88 41.25 46.69 146.57 20.01 15.11 31.54 12.27 21.98 11.49 329182.78 9641.86 10642.01 149810.23 284866.89 185256.17 147801.32 7000.73 159653.78 62539.00 1017 35249 1027 35541 1203 41325 2391 137.9946 118.3267 111.9620 28.337 190.674 101.113 124.156 121.003 770.439 562.40 295.09 456.699 199.939 60.388 16.953 40.49 41.35 93.25 108.96 112.00 12.114 25.608 27.75 30.84 74.75 76.47 78.36 1515900000 1833800000 574247.25 563863.85 117122.32 708240.91 111705.91 3173966.53 2250219.43 507739.28 4285728.04 2766520.21 408236.41 45520.0 1684833.1 114247738153 45656086733 1293797662083 1189125968417 735906787330 502160719143 18460333 199040 427958667 199325 859423 774.37 797.78 811.04 126692 6.315 4836769 0.165 114622 8.725 4743490 0.211 13615896.00 7150348.98 535512581 12039196 7425304 696417 547341883 10386364 3653992 532848 4035383.567815 477 281 338 213 275 297 679 5217.645595 53.787 12.97277 3.74317 27898.721354 17136.710286 637318 533210 24.576 244437822 16.3825 33.606 59.698 7258.66 2.18 5824.65 2.72 706.18 22.60 20077.07 2.96 3116.45 20.50 2331.65 6.85 8237.15 1.92 5615.27 10.63 78.55 15.89 12.73 50.49 119.56 52.86 146670.47 25765.78 399202.60 41052099.15 3091182.20 2004.87 11117419.40 5730701.52 17279400.36 345394.67 18626.3 108233.2 18.72 52.23 61.69 190.13 26.04 11.76 22.36 8.74 16.43 8.22 352266.66 11316.88 11786.07 171779.61 317628.32 227311.90 151971.93 7078.61 178843.53 72412.04 1386 47071 1411 47644 1656 55556 1794 88.3402 75.8835 71.4190 30.523 220.741 114.663 136.087 129.535 772.342 566.24 298.52 482.463 211.071 62.119 17.296 44.01 44.85 87.85 112.56 114.50 13.080 27.776 29.92 32.91 70.59 76.71 81.97 1512433333 1507800000 495324.89 505544.05 117111.87 708330.20 111713.22 3180516.79 2238161.49 505551.88 4279636.21 2750461.27 409213.51 45691.7 1448237.7 85249996367 41832374577 1285906152473 1115036388103 521259281067 351349708757 14054000 138073 378876000 138135 558160 790.42 819.66 825.31 97782 8.181 3625079 0.221 92680 10.790 3564643 0.280 10001671.48 6416279.96 545826282 8141717 5997026 1286685 558902450 6012789 3620451 910104 2844496.906314 517 227 252 403 281 292 604 5484.789702 53.658 11.36709 3.28552 27904.246745 17164.102864 489525 330536 26.286 176973221 18.1512 34.280 60.954 OpenBenchmarking.org
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU SMT Enabled - Default SMT Disabled 1600 3200 4800 6400 8000 SE +/- 4.72, N = 3 SE +/- 9.98, N = 3 7670.87 7258.66 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU SMT Enabled - Default SMT Disabled 1300 2600 3900 5200 6500 SE +/- 3.28, N = 3 SE +/- 29.65, N = 3 6268.38 5824.65 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU SMT Enabled - Default SMT Disabled 200 400 600 800 1000 SE +/- 0.82, N = 3 SE +/- 1.50, N = 3 790.57 706.18 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU SMT Enabled - Default SMT Disabled 5K 10K 15K 20K 25K SE +/- 42.14, N = 3 SE +/- 26.61, N = 3 22207.98 20077.07 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU SMT Enabled - Default SMT Disabled 700 1400 2100 2800 3500 SE +/- 2.16, N = 3 SE +/- 2.44, N = 3 3186.97 3116.45 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU SMT Enabled - Default SMT Disabled 500 1000 1500 2000 2500 SE +/- 2.80, N = 3 SE +/- 3.04, N = 3 2341.28 2331.65 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU SMT Enabled - Default SMT Disabled 2K 4K 6K 8K 10K SE +/- 12.91, N = 3 SE +/- 9.64, N = 3 9483.91 8237.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU SMT Enabled - Default SMT Disabled 1400 2800 4200 5600 7000 SE +/- 2.29, N = 3 SE +/- 2.51, N = 3 6539.33 5615.27 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Timed Linux Kernel Compilation This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.
Timed Node.js Compilation This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.
Timed Gem5 Compilation This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
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.
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.
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 SMT Disabled SMT Enabled - Default 10K 20K 30K 40K 50K SE +/- 103.99, N = 3 SE +/- 114.98, N = 3 45691.7 45520.0 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: bcrypt SMT Enabled - Default SMT Disabled 40K 80K 120K 160K 200K SE +/- 205.13, N = 3 SE +/- 48.59, N = 3 199325 138135 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
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, First Run / Cold Cache SMT Disabled SMT Enabled - Default 200 400 600 800 1000 SE +/- 7.72, N = 3 SE +/- 3.81, N = 3 790.42 774.37 MIN: 58.77 / MAX: 8571.43 MIN: 66.08 / MAX: 8571.43
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run SMT Disabled SMT Enabled - Default 200 400 600 800 1000 SE +/- 4.42, N = 3 SE +/- 8.66, N = 3 819.66 797.78 MIN: 59.41 / MAX: 8571.43 MIN: 67.04 / MAX: 8571.43
PostgreSQL OpenBenchmarking.org TPS, More Is Better PostgreSQL 17 Scaling Factor: 100 - Clients: 800 - Mode: Read Write SMT Enabled - Default SMT Disabled 30K 60K 90K 120K 150K SE +/- 322.78, N = 3 SE +/- 144.52, N = 3 126692 97782 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 17 Scaling Factor: 100 - Clients: 800 - Mode: Read Only SMT Enabled - Default SMT Disabled 1000K 2000K 3000K 4000K 5000K SE +/- 14712.71, N = 3 SE +/- 8567.74, N = 3 4836769 3625079 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 17 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write SMT Enabled - Default SMT Disabled 20K 40K 60K 80K 100K SE +/- 547.52, N = 3 SE +/- 151.71, N = 3 114622 92680 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 17 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only SMT Enabled - Default SMT Disabled 1000K 2000K 3000K 4000K 5000K SE +/- 17122.75, N = 3 SE +/- 1560.76, N = 3 4743490 3564643 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm
FinanceBench FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.
7-Zip Compression OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Compression Rating SMT Enabled - Default SMT Disabled 140K 280K 420K 560K 700K SE +/- 5367.73, N = 3 SE +/- 5895.67, N = 3 637318 489525 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Tachyon This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. The sample scene used is the Teapot scene ray-traced to 8K x 8K with 32 samples. Learn more via the OpenBenchmarking.org test page.
SMT Enabled - Default Processor: AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores / 128 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.10, Kernel: 6.13.0-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116Python Notes: Python 3.12.7Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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
Testing initiated at 30 January 2025 11:27 by user phoronix.
SMT Disabled Processor: AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.10, Kernel: 6.13.0-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116Python Notes: Python 3.12.7Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 30 January 2025 22:20 by user phoronix.