Kernel 6.7rc7 compiler benchmark Benchmarking GCC and clang with / without march=znver1 via graysky2's patches, with/without ThinLTO. AMD Ryzen 7 PRO 3700U testing with a LENOVO 20QJS03W00 (R13ET54W1.28 BIOS) and AMD Radeon Vega 10 1GB on Debian via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2401023-NE-KERNELCOM52&grr .
Kernel 6.7rc7 compiler benchmark Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL OpenCL Compiler File-System Screen Resolution gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 AMD Ryzen 7 PRO 3700U @ 2.30GHz (4 Cores / 8 Threads) LENOVO 20QJS03W00 (R13ET54W1.28 BIOS) AMD Raven/Raven2 16GB Western Digital WD_BLACK SN850X 2000GB AMD Radeon Vega 10 1GB (1400/1200MHz) AMD Raven/Raven2/Fenghuang Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX210/AX211/AX411 Debian 6.7.0-rc7xps2-dirty (x86_64) KDE Plasma 5.27.10 X Server 1.21.1.10 4.6 Mesa 23.3.1-4 (LLVM 17.0.6 DRM 3.56) OpenCL 1.1 Mesa 23.3.1-4 + OpenCL 3.0 + OpenCL 3.0 PoCL 4.0+debian Linux +Asserts RELOC SPIR LLVM 15.0.7 SLEEF DISTRO POCL_DEBUG GCC 13.2.0 + Clang 16.0.6 + LLVM 16.0.6 ext4 1920x1080 6.7.0-rc7xps3 (x86_64) 6.7.0-rc7xps4-dirty (x86_64) 6.7.0-rc7xps5-dirty (x86_64) 6.7.0-rc7xps6 (x86_64) 6.7.0-rc7xps1 (x86_64) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Environment Details - NVM_CD_FLAGS= Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --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/reproducible-path/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/reproducible-path/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8108109 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Vulnerable + spec_rstack_overflow: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Kernel 6.7rc7 compiler benchmark fio: Rand Write - IO_uring - No - 4KB - 8 - Default Test Directory fio: Rand Write - IO_uring - No - 4KB - 8 - Default Test Directory openssl: SHA512 apache: 500 openssl: RSA4096 openssl: RSA4096 phpbench: PHP Benchmark Suite memcached: 1:5 stress-ng: CPU Cache stress-ng: Malloc perf-bench: Futex Hash stress-ng: Glibc Qsort Data Sorting cachebench: Read cachebench: Write cachebench: Read / Modify / Write memcached: 1:100 stress-ng: Glibc C String Functions stress-ng: Context Switching stress-ng: Socket Activity stress-ng: Mutex stress-ng: System V Message Passing stress-ng: Vector Floating Point stress-ng: Futex stress-ng: Forking stress-ng: IO_uring ethr: UDP - Bandwidth - 8 fio: Rand Read - IO_uring - No - 4KB - 8 - Default Test Directory fio: Rand Read - IO_uring - No - 4KB - 8 - Default Test Directory sqlite-speedtest: Timed Time - Size 1,000 perf-bench: Sched Pipe supertuxkart: 1920 x 1080 - Fullscreen - Ultimate - 2 - Candela City compress-zstd: 12 - Decompression Speed compress-zstd: 12 - Compression Speed tesseract: 1920 x 1080 mutex: Mutex Lock Unlock pthread_mutex perf-bench: Epoll Wait perf-bench: Futex Lock-Pi pybench: Total For Average Test Times perf-bench: Memcpy 1MB mutex: Mutex Lock Unlock std::mutex perf-bench: Memset 1MB network-loopback: Time To Transfer 10GB Via Loopback perf-bench: Syscall Basic gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 153000 598 1050602290 17800.61 39624.7 635.9 436938 576805.91 1246310.92 1355058.48 4177210 73.23 2668.893536 26339.640065 50858.366717 577815.46 1148464.70 1149698.07 1589.88 1436645.37 7398499.77 5109.39 943368.71 10985.08 70103.58 1472267 226333 883 80.589 150039 117.435847 1190.7 35.0 109.8072 13.4 263275 1855 1051 15.455745 16.7 49.164696 17.535 19459124 110147 430 1046471660 17914.30 39102.2 628.1 410608 424516.39 1234895.33 746222.72 4216860 73.27 2637.170857 26082.981315 50351.067839 414930.24 1075373.75 1203058.45 1338.35 1407315.39 7172503.32 5115.29 547997.63 10316.11 70857.41 1371600 62367 244 79.534 57681 117.343485 1194.6 34.8 109.1451 13.6 246716 1370 1063 15.387933 17.0 49.452595 17.692 19546593 112213 438 1029156002 17934.75 38874.4 624.4 409329 423774.74 1223147.59 779938.09 4165135 73.45 2635.965630 26099.456206 50214.585695 411819.55 1092831.38 1205732.52 1362.10 1377924.62 7084240.51 5109.63 525513.32 10507.55 69337.12 1386800 65033 254 79.914 56960 117.578316 1200.5 34.9 108.6189 13.5 244555 1363 1063 15.111257 17.1 48.808800 17.600 19015027 110040 430 1007046867 18063.54 38932.6 625.1 571452 430642.34 1206353.72 808595.98 4208067 73.04 2635.948944 26098.775065 50308.267787 408759.68 1080905.89 1200167.03 1346.65 1369394.08 7025718.08 5148.02 532959.94 10454.71 73843.27 1279316 61433 240 80.029 57861 117.593597 1199.4 35.1 113.2204 13.7 240783 1378 1051 15.235448 17 43.911620 12.168 19089585 102047 399 1028374403 18040.29 38935.4 622.3 412184 412560.50 1229529.72 793711.73 4191476 73.69 2635.371003 26064.734197 50251.957103 398332.83 1077836.73 1210096.27 1339.06 1388484.24 6944116.56 5157.71 509773.24 11088.01 69797.39 1257710 64500 252 79.721 57351 116.650319 1165.6 34.4 109.0030 13.6 235974 1350 1064 15.281093 17.2 47.698161 17.503 19222437 152267 595 1053360105 18194.65 39935.2 638.0 443356 582274.27 1225248.53 1235464.89 4462515 73.78 2672.760464 26395.122762 50992.768123 576981.86 1147586.60 1158150.86 1609.09 1299343.34 7361193.73 5183.35 859898.29 10878.69 69595.80 1480400 223000 871 79.954 148477 117.609055 1189.8 34.8 103.4516 13.4 264802 1886 1069 15.533849 16.7 49.865718 17.698 19951194 OpenBenchmarking.org
Flexible IO Tester Type: Random Write - Engine: IO_uring - Direct: No - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.36 Type: Random Write - Engine: IO_uring - Direct: No - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directory gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 30K 60K 90K 120K 150K SE +/- 1357.40, N = 15 SE +/- 1851.64, N = 15 SE +/- 3496.38, N = 15 SE +/- 3020.58, N = 15 SE +/- 3204.15, N = 15 SE +/- 2658.43, N = 15 152267 153000 110147 112213 110040 102047 1. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -march=native
Flexible IO Tester Type: Random Write - Engine: IO_uring - Direct: No - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.36 Type: Random Write - Engine: IO_uring - Direct: No - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directory gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 130 260 390 520 650 SE +/- 5.15, N = 15 SE +/- 7.31, N = 15 SE +/- 13.60, N = 15 SE +/- 11.91, N = 15 SE +/- 12.40, N = 15 SE +/- 10.42, N = 15 595 598 430 438 430 399 1. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -march=native
OpenSSL Algorithm: SHA512 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: SHA512 gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 200M 400M 600M 800M 1000M SE +/- 8238531.70, N = 10 SE +/- 7472634.40, N = 12 SE +/- 14736736.23, N = 3 SE +/- 10504015.19, N = 5 SE +/- 12473838.00, N = 3 SE +/- 9171095.81, N = 3 1053360105 1050602290 1046471660 1029156002 1007046867 1028374403 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Apache HTTP Server Concurrent Requests: 500 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.56 Concurrent Requests: 500 clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 4K 8K 12K 16K 20K SE +/- 152.78, N = 15 SE +/- 204.81, N = 15 SE +/- 137.13, N = 10 SE +/- 152.22, N = 15 SE +/- 138.08, N = 12 SE +/- 224.27, N = 3 18040.29 18063.54 17934.75 17914.30 17800.61 18194.65 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 9K 18K 27K 36K 45K SE +/- 54.05, N = 13 SE +/- 81.40, N = 12 SE +/- 87.35, N = 12 SE +/- 72.19, N = 15 SE +/- 46.94, N = 9 SE +/- 65.91, N = 9 39935.2 39624.7 39102.2 38874.4 38932.6 38935.4 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 140 280 420 560 700 SE +/- 4.23, N = 13 SE +/- 4.53, N = 12 SE +/- 4.77, N = 12 SE +/- 3.83, N = 15 SE +/- 5.15, N = 9 SE +/- 5.09, N = 9 638.0 635.9 628.1 624.4 625.1 622.3 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 120K 240K 360K 480K 600K SE +/- 9191.34, N = 15 SE +/- 6562.29, N = 3 SE +/- 8590.73, N = 15 SE +/- 8755.89, N = 15 SE +/- 3758.55, N = 15 SE +/- 3991.58, N = 15 412184 571452 409329 410608 436938 443356
Memcached Set To Get Ratio: 1:5 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:5 gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 120K 240K 360K 480K 600K SE +/- 5869.38, N = 6 SE +/- 3379.47, N = 15 SE +/- 2977.10, N = 12 SE +/- 3042.09, N = 15 SE +/- 5204.68, N = 3 SE +/- 4778.65, N = 3 582274.27 576805.91 424516.39 423774.74 430642.34 412560.50 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Cache gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 300K 600K 900K 1200K 1500K SE +/- 11834.03, N = 15 SE +/- 10120.22, N = 15 SE +/- 14067.76, N = 15 SE +/- 13340.20, N = 15 SE +/- 13128.96, N = 15 SE +/- 11310.03, N = 15 1246310.92 1234895.33 1223147.59 1206353.72 1229529.72 1225248.53 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Malloc gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 300K 600K 900K 1200K 1500K SE +/- 10809.98, N = 15 SE +/- 6390.41, N = 8 SE +/- 18129.66, N = 15 SE +/- 21636.39, N = 15 SE +/- 21353.40, N = 15 SE +/- 7310.05, N = 15 1355058.48 746222.72 779938.09 808595.98 793711.73 1235464.89 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
perf-bench Benchmark: Futex Hash OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Hash gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 1000K 2000K 3000K 4000K 5000K SE +/- 29781.43, N = 15 SE +/- 27201.42, N = 14 SE +/- 27034.71, N = 15 SE +/- 26828.75, N = 15 SE +/- 32361.75, N = 10 SE +/- 34344.45, N = 9 4462515 4177210 4216860 4165135 4208067 4191476 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu11 -U_FORTIFY_SOURCE -lunwind-x86_64 -lunwind -llzma -lpthread -lrt -lm -ldl -lelf -ldw -lcrypto -lperl -lc -lcrypt -lpython3.11 -lutil -lz -lzstd -lcap -lnuma
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc Qsort Data Sorting gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 16 32 48 64 80 SE +/- 0.53, N = 15 SE +/- 0.54, N = 15 SE +/- 0.58, N = 10 SE +/- 0.44, N = 15 SE +/- 0.55, N = 11 SE +/- 0.58, N = 10 73.23 73.27 73.45 73.04 73.69 73.78 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
CacheBench Test: Read OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 600 1200 1800 2400 3000 SE +/- 0.39, N = 3 SE +/- 0.28, N = 3 SE +/- 0.67, N = 3 SE +/- 1.39, N = 3 SE +/- 0.35, N = 3 SE +/- 1.26, N = 3 2672.76 2668.89 2637.17 2635.97 2635.95 2635.37 MIN: 2652.44 / MAX: 2678.89 MIN: 2632.17 / MAX: 2678.88 MIN: 2571.61 / MAX: 2649.4 MIN: 2564.69 / MAX: 2649.59 MIN: 2594.58 / MAX: 2649.25 MIN: 2588.86 / MAX: 2650.14 1. (CC) gcc options: -lrt
CacheBench Test: Write OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Write gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 6K 12K 18K 24K 30K SE +/- 27.05, N = 3 SE +/- 75.62, N = 3 SE +/- 45.01, N = 3 SE +/- 24.03, N = 3 SE +/- 18.39, N = 3 SE +/- 12.25, N = 3 26395.12 26339.64 26082.98 26099.46 26098.78 26064.73 MIN: 19877.43 / MAX: 29210.25 MIN: 19497.88 / MAX: 29224.21 MIN: 20112.48 / MAX: 28891.19 MIN: 20074.43 / MAX: 28904.84 MIN: 20084.56 / MAX: 28897.1 MIN: 19985.04 / MAX: 28879.26 1. (CC) gcc options: -lrt
CacheBench Test: Read / Modify / Write OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read / Modify / Write gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 11K 22K 33K 44K 55K SE +/- 78.53, N = 3 SE +/- 48.74, N = 3 SE +/- 1.18, N = 3 SE +/- 100.38, N = 3 SE +/- 102.05, N = 3 SE +/- 101.38, N = 3 50992.77 50858.37 50351.07 50214.59 50308.27 50251.96 MIN: 36877.97 / MAX: 57899.28 MIN: 37800.65 / MAX: 57866.4 MIN: 37300.56 / MAX: 57270.64 MIN: 36887.44 / MAX: 57171.1 MIN: 36906.71 / MAX: 57240.07 MIN: 37068.23 / MAX: 57298.17 1. (CC) gcc options: -lrt
Memcached Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 120K 240K 360K 480K 600K SE +/- 4534.34, N = 10 SE +/- 5728.43, N = 6 SE +/- 5892.60, N = 3 SE +/- 5701.94, N = 3 SE +/- 4857.15, N = 3 SE +/- 3253.49, N = 9 576981.86 577815.46 414930.24 411819.55 408759.68 398332.83 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc C String Functions gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 200K 400K 600K 800K 1000K SE +/- 11069.61, N = 15 SE +/- 6950.93, N = 15 SE +/- 15632.01, N = 3 SE +/- 7050.21, N = 15 SE +/- 7811.38, N = 11 SE +/- 9949.23, N = 15 1148464.70 1075373.75 1092831.38 1080905.89 1077836.73 1147586.60 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Context Switching gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 300K 600K 900K 1200K 1500K SE +/- 8820.34, N = 15 SE +/- 7502.43, N = 15 SE +/- 12045.18, N = 6 SE +/- 10541.49, N = 15 SE +/- 9496.18, N = 15 SE +/- 10669.22, N = 7 1149698.07 1203058.45 1205732.52 1200167.03 1210096.27 1158150.86 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Socket Activity gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 300 600 900 1200 1500 SE +/- 12.09, N = 15 SE +/- 7.73, N = 15 SE +/- 10.95, N = 9 SE +/- 11.09, N = 9 SE +/- 10.41, N = 10 SE +/- 16.20, N = 15 1589.88 1338.35 1362.10 1346.65 1339.06 1609.09 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: Mutex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mutex gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 300K 600K 900K 1200K 1500K SE +/- 6716.82, N = 3 SE +/- 23660.63, N = 15 SE +/- 16029.82, N = 15 SE +/- 8618.78, N = 15 SE +/- 11679.03, N = 15 SE +/- 10535.16, N = 9 1436645.37 1407315.39 1377924.62 1369394.08 1388484.24 1299343.34 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: System V Message Passing gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 1.6M 3.2M 4.8M 6.4M 8M SE +/- 49931.88, N = 14 SE +/- 55613.70, N = 13 SE +/- 50502.32, N = 14 SE +/- 53365.55, N = 10 SE +/- 54938.32, N = 9 SE +/- 56835.29, N = 10 7398499.77 7172503.32 7084240.51 7025718.08 6944116.56 7361193.73 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: Vector Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Floating Point gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 1100 2200 3300 4400 5500 SE +/- 34.78, N = 15 SE +/- 45.97, N = 15 SE +/- 42.82, N = 15 SE +/- 55.34, N = 5 SE +/- 45.48, N = 15 SE +/- 63.22, N = 4 5109.39 5115.29 5109.63 5148.02 5157.71 5183.35 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Futex gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 200K 400K 600K 800K 1000K SE +/- 4556.50, N = 3 SE +/- 7761.26, N = 3 SE +/- 4691.89, N = 15 SE +/- 5050.41, N = 15 SE +/- 7209.94, N = 12 SE +/- 10847.07, N = 15 943368.71 547997.63 525513.32 532959.94 509773.24 859898.29 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Forking gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 2K 4K 6K 8K 10K SE +/- 75.28, N = 13 SE +/- 72.41, N = 12 SE +/- 94.21, N = 7 SE +/- 147.33, N = 3 SE +/- 79.92, N = 11 SE +/- 72.35, N = 14 10985.08 10316.11 10507.55 10454.71 11088.01 10878.69 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: IO_uring gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 gcc -O2 16K 32K 48K 64K 80K SE +/- 604.62, N = 15 SE +/- 506.84, N = 15 SE +/- 760.85, N = 3 SE +/- 608.31, N = 15 SE +/- 813.06, N = 3 SE +/- 646.14, N = 7 70103.58 70857.41 69337.12 73843.27 69797.39 69595.80 1. (CXX) g++ options: -lm -lapparmor -latomic -lbsd -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lmd -lpthread -lrt -lz
Ethr Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 8 OpenBenchmarking.org Packets/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 8 gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 300K 600K 900K 1200K 1500K SE +/- 11379.51, N = 3 SE +/- 8927.36, N = 3 SE +/- 13049.65, N = 3 SE +/- 14362.92, N = 3 SE +/- 10331.97, N = 15 SE +/- 11504.27, N = 15 1480400 1472267 1371600 1386800 1279316 1257710 MIN: 1210000 / MAX: 1600000 MIN: 1180000 / MAX: 1620000 MIN: 1110000 / MAX: 1570000 MIN: 1150000 / MAX: 1550000 MIN: 951040 / MAX: 1510000 MIN: 892060 / MAX: 1510000
Flexible IO Tester Type: Random Read - Engine: IO_uring - Direct: No - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.36 Type: Random Read - Engine: IO_uring - Direct: No - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directory gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 50K 100K 150K 200K 250K SE +/- 577.35, N = 3 SE +/- 1333.33, N = 3 SE +/- 33.33, N = 3 SE +/- 88.19, N = 3 SE +/- 233.33, N = 3 SE +/- 115.47, N = 3 223000 226333 62367 65033 61433 64500 1. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -march=native
Flexible IO Tester Type: Random Read - Engine: IO_uring - Direct: No - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.36 Type: Random Read - Engine: IO_uring - Direct: No - Block Size: 4KB - Job Count: 8 - Disk Target: Default Test Directory gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 200 400 600 800 1000 SE +/- 2.65, N = 3 SE +/- 4.84, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 1.00, N = 3 SE +/- 0.58, N = 3 871 883 244 254 240 252 1. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -laio -lpthread -ldl -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -march=native
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 1.05, N = 3 SE +/- 0.14, N = 3 SE +/- 0.23, N = 3 SE +/- 0.59, N = 3 SE +/- 0.17, N = 3 79.72 80.03 79.91 79.53 80.59 79.95 1. (CC) gcc options: -O2 -lz
perf-bench Benchmark: Sched Pipe OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Sched Pipe gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 30K 60K 90K 120K 150K SE +/- 277.25, N = 3 SE +/- 939.67, N = 3 SE +/- 150.31, N = 3 SE +/- 144.43, N = 3 SE +/- 57.95, N = 3 SE +/- 39.98, N = 3 148477 150039 57681 56960 57861 57351 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu11 -U_FORTIFY_SOURCE -lunwind-x86_64 -lunwind -llzma -lpthread -lrt -lm -ldl -lelf -ldw -lcrypto -lperl -lc -lcrypt -lpython3.11 -lutil -lz -lzstd -lcap -lnuma
SuperTuxKart Resolution: 1920 x 1080 - Mode: Fullscreen - Graphics Effects: Ultimate - Karts: 2 - Scene: Candela City OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.1 Resolution: 1920 x 1080 - Mode: Fullscreen - Graphics Effects: Ultimate - Karts: 2 - Scene: Candela City clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 30 60 90 120 150 SE +/- 1.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.24, N = 3 SE +/- 0.23, N = 3 SE +/- 0.08, N = 3 116.65 117.59 117.58 117.34 117.44 117.61
Zstd Compression Compression Level: 12 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 300 600 900 1200 1500 SE +/- 11.04, N = 3 SE +/- 5.58, N = 3 SE +/- 1.27, N = 3 SE +/- 5.80, N = 3 SE +/- 4.64, N = 3 SE +/- 3.94, N = 3 1165.6 1199.4 1200.5 1194.6 1190.7 1189.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 12 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 8 16 24 32 40 SE +/- 0.30, N = 3 SE +/- 0.15, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.15, N = 3 34.4 35.1 34.9 34.8 35.0 34.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
Tesseract Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better Tesseract 2014-05-12 Resolution: 1920 x 1080 clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 30 60 90 120 150 SE +/- 1.12, N = 3 SE +/- 0.80, N = 3 SE +/- 0.38, N = 3 SE +/- 0.31, N = 3 SE +/- 0.68, N = 3 SE +/- 0.70, N = 15 109.00 113.22 108.62 109.15 109.81 103.45
BenchmarkMutex Benchmark: Mutex Lock Unlock pthread_mutex OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Mutex Lock Unlock pthread_mutex gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 13.4 13.4 13.6 13.5 13.7 13.6 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
perf-bench Benchmark: Epoll Wait OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Epoll Wait gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 60K 120K 180K 240K 300K SE +/- 604.49, N = 3 SE +/- 1080.54, N = 3 SE +/- 984.14, N = 3 SE +/- 2645.93, N = 3 SE +/- 1483.91, N = 3 SE +/- 2201.88, N = 7 264802 263275 246716 244555 240783 235974 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu11 -U_FORTIFY_SOURCE -lunwind-x86_64 -lunwind -llzma -lpthread -lrt -lm -ldl -lelf -ldw -lcrypto -lperl -lc -lcrypt -lpython3.11 -lutil -lz -lzstd -lcap -lnuma
perf-bench Benchmark: Futex Lock-Pi OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Lock-Pi gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 400 800 1200 1600 2000 SE +/- 13.38, N = 3 SE +/- 14.33, N = 3 SE +/- 10.07, N = 3 SE +/- 1.15, N = 3 SE +/- 8.50, N = 3 SE +/- 17.16, N = 3 1886 1855 1370 1363 1378 1350 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu11 -U_FORTIFY_SOURCE -lunwind-x86_64 -lunwind -llzma -lpthread -lrt -lm -ldl -lelf -ldw -lcrypto -lperl -lc -lcrypt -lpython3.11 -lutil -lz -lzstd -lcap -lnuma
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 200 400 600 800 1000 SE +/- 5.78, N = 3 SE +/- 3.71, N = 3 SE +/- 5.84, N = 3 SE +/- 0.88, N = 3 SE +/- 4.84, N = 3 SE +/- 1.53, N = 3 1064 1051 1063 1063 1051 1069
perf-bench Benchmark: Memcpy 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memcpy 1MB gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 15.53 15.46 15.39 15.11 15.24 15.28 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu11 -U_FORTIFY_SOURCE -lunwind-x86_64 -lunwind -llzma -lpthread -lrt -lm -ldl -lelf -ldw -lcrypto -lperl -lc -lcrypt -lpython3.11 -lutil -lz -lzstd -lcap -lnuma
BenchmarkMutex Benchmark: Mutex Lock Unlock std::mutex OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Mutex Lock Unlock std::mutex gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 16.7 16.7 17.0 17.1 17.0 17.2 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
perf-bench Benchmark: Memset 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memset 1MB gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 11 22 33 44 55 SE +/- 0.53, N = 3 SE +/- 0.64, N = 3 SE +/- 0.43, N = 8 SE +/- 0.62, N = 3 SE +/- 0.54, N = 3 SE +/- 0.72, N = 15 49.87 49.16 49.45 48.81 43.91 47.70 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu11 -U_FORTIFY_SOURCE -lunwind-x86_64 -lunwind -llzma -lpthread -lrt -lm -ldl -lelf -ldw -lcrypto -lperl -lc -lcrypt -lpython3.11 -lutil -lz -lzstd -lcap -lnuma
Loopback TCP Network Performance Time To Transfer 10GB Via Loopback OpenBenchmarking.org Seconds, Fewer Is Better Loopback TCP Network Performance Time To Transfer 10GB Via Loopback clang -O2 clang -O2 -march=znver1 clang -O2 -march=znver1 lto clang -O2 lto gcc -O2 -march=znver1 gcc -O2 4 8 12 16 20 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.21, N = 3 SE +/- 0.07, N = 3 17.50 12.17 17.60 17.69 17.54 17.70
perf-bench Benchmark: Syscall Basic OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Syscall Basic gcc -O2 gcc -O2 -march=znver1 clang -O2 lto clang -O2 -march=znver1 lto clang -O2 -march=znver1 clang -O2 4M 8M 12M 16M 20M SE +/- 138380.06, N = 3 SE +/- 22604.63, N = 3 SE +/- 61427.71, N = 3 SE +/- 207490.15, N = 3 SE +/- 206224.44, N = 3 SE +/- 37046.33, N = 3 19951194 19459124 19546593 19015027 19089585 19222437 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu11 -U_FORTIFY_SOURCE -lunwind-x86_64 -lunwind -llzma -lpthread -lrt -lm -ldl -lelf -ldw -lcrypto -lperl -lc -lcrypt -lpython3.11 -lutil -lz -lzstd -lcap -lnuma
Phoronix Test Suite v10.8.4