Spectre V4 mitigation tests using SSBD on Linux 4.17 Git. Tests for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1805225-AR-SPECTRE4S17 Initial AMD Spectre Variant 4 Benchmarks On Linux 4.17 - Phoronix Test Suite Initial AMD Spectre Variant 4 Benchmarks On Linux 4.17 Spectre V4 mitigation tests using SSBD on Linux 4.17 Git. Tests for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1805225-AR-SPECTRE4S17&grr&sro&export=txt .
Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Driver OpenGL Compiler File-System Screen Resolution Ryzen 7 2700X Ryzen 3 2200G EPYC 7601 SSBD Vulnerable SSBD Vulnerable SSBD Vulnerable AMD Ryzen 7 2700X Eight-Core @ 3.70GHz (8 Cores / 16 Threads) ASUS ROG CROSSHAIR VII HERO (WI-FI) (0509 BIOS) AMD Family 17h 16384MB 525GB SABRENT + Samsung SSD 950 PRO 256GB NV132 11264MB NVIDIA GP102 HDMI Audio DELL P2415Q Intel I211 Gigabit Connection + Realtek Device b822 Ubuntu 18.04 4.17.0-999-generic (x86_64) 20180521 GNOME Shell 3.28.1 modesetting 1.19.6 4.3 Mesa 18.2.0-devel GCC 7.3.0 ext4 3840x2160 AMD Ryzen 3 2200G @ 3.50GHz (4 Cores) MSI B350M GAMING PRO (MS-7A39) v1.0 (2.G0 BIOS) AMD Device 15d0 7168MB 29GB INTEL MEMPEK1W032GA MSI AMD Radeon Vega 8 Mobile 1024MB AMD Device 15de Realtek RTL8111/8168/8411 GNOME Shell 3.28.0 4.5 Mesa 18.0.0-rc5 (LLVM 6.0.0) AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads) TYAN B8026T70AE24HR (V0.05.B10 BIOS) AMD Family 17h 129024MB 280GB INTEL SSDPE21D280GA ASPEED ASPEED Family VE228 Broadcom Limited NetXtreme BCM5720 Gigabit PCIe GNOME Shell 3.28.1 1920x1080 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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-as=/usr/bin/x86_64-linux-gnu-as --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-ld=/usr/bin/x86_64-linux-gnu-ld --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Disk Details - NONE / errors=remount-ro,relatime,rw Processor Details - Scaling Governor: acpi-cpufreq ondemand Python Details - Python 2.7.15rc1 + Python 3.6.5 Security Details - Ryzen 7 2700X: SSBD: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp Protection - Ryzen 7 2700X: Vulnerable: __user pointer sanitization + Full AMD retpoline IBPB Protection - Ryzen 3 2200G: SSBD: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp Protection - Ryzen 3 2200G: Vulnerable: __user pointer sanitization + Full AMD retpoline IBPB Protection - EPYC 7601: SSBD: __user pointer sanitization + Full AMD retpoline + SSB disabled via prctl and seccomp Protection - EPYC 7601: Vulnerable: __user pointer sanitization + Full AMD retpoline Protection
build-linux-kernel: Time To Compile rbenchmark: scikit-learn: stockfish: Total Time pgbench: Buffer Test - Normal Load - Read Only perl-benchmark: Pod2html pgbench: Buffer Test - Heavy Contention - Read Only pgbench: Buffer Test - Normal Load - Read Write pgbench: Buffer Test - Heavy Contention - Read Write perl-benchmark: Interpreter apache: Static Web Page Serving stress-ng: Socket Activity java-scimark2: Composite aobench: 2048 x 2048 - Total Time stress-ng: System V Message Passing postmark: Disk Transaction Performance pybench: Total For Average Test Times encode-mp3: WAV To MP3 iozone: 4Kb - 8GB - Write Performance stress-ng: Context Switching stress-ng: Forking stress-ng: Semaphores luajit: Composite ebizzy: sqlite: Timed SQLite Insertions phpbench: PHP Benchmark Suite openssl: RSA 4096-bit Performance git: Time To Complete Common Git Commands luajit: Jacobi Successive Over-Relaxation luajit: Dense LU Matrix Factorization luajit: Sparse Matrix Multiply luajit: Fast Fourier Transform luajit: Monte Carlo java-scimark2: Jacobi Successive Over-Relaxation java-scimark2: Dense LU Matrix Factorization java-scimark2: Sparse Matrix Multiply java-scimark2: Fast Fourier Transform java-scimark2: Monte Carlo Ryzen 7 2700X Ryzen 3 2200G EPYC 7601 SSBD Vulnerable SSBD Vulnerable SSBD Vulnerable 73.92 0.3947 25.36 24152025 195458.93 0.14383901 191709.25 4152.53 4556.94 0.00106965 30561.02 6889.69 2949.91 38.80 11846350.76 7142 1539 32.46 484.77 4734667.28 58451.48 4490592.84 1504.56 559670 62.60 519603 1719.50 5.46 1922.06 3575.11 1215.05 302.71 507.90 1636.85 6943.53 2634.63 1887.32 1647.20 73.27 0.3911 25.31 24133230 197760.12 0.14530132 189690.99 4270.12 4511.55 0.00110452 30813.59 7205.82 2959.81 38.68 11899692.71 7212 1559 32.56 827.10 4766643.10 59902.92 4470215.22 1492.84 566374 63.83 517478 1724.83 5.40 1934.33 3524.26 1213.50 283.48 508.62 1639.11 6996.91 2644.61 1866.30 1652.12 200.19 0.8008 125.96 7993776 57005.68 0.16692850 50134.27 7519.28 6654.57 0.00139883 34805.09 2917.46 2587.38 44.86 5087012.74 6148 1790 37.84 280.55 1377134.64 28512.83 7641293.74 1104.94 85804 3.50 458502 6.13 1644.45 2135.52 1065.83 237.57 441.33 1400.40 6319.11 2288.47 1505.81 1423.13 198.91 0.7894 123.74 7957417 56687.08 0.16440514 51360.22 7497.78 6830.52 0.00136430 35083.36 3044.42 2620.41 44.86 3424065.12 6049 1794 37.80 279.57 1376458.10 29784.79 8057541.78 1097.67 86028 3.55 455102 6.11 1643.83 2105.37 1062.32 236.74 440.09 1400.53 6384.79 2288.22 1602.07 1426.43 37.75 0.9055 144.48 58372393 395388.07 0.20045042 0.00209126 17901.87 2177.16 51.96 5434 2086 43.72 928.86 43442.24 1597032.40 1114.90 1122614 2.94 386120 4610.47 7.36 1421.63 2614.12 917.87 240.91 379.97 1207.65 5230.06 1682.48 1365.76 1230.92 37.57 0.9079 144.50 58183837 393664.75 0.19238990 0.00209769 17887.19 17227.19 2177.73 51.96 10735107.79 5396 2076 43.86 1024.23 17597048.97 49686.60 1593274.94 1134.76 1134210 2.86 386088 4608.33 7.27 1422.25 2728.63 914.14 228.85 379.92 1208.41 5110.10 1974.16 1366.74 1229.24 OpenBenchmarking.org
Timed Linux Kernel Compilation Time To Compile EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.13 Time To Compile SSBD Vulnerable 40 80 120 160 200 SE +/- 0.65, N = 6 SE +/- 0.61, N = 6 SE +/- 1.43, N = 2 SE +/- 1.01, N = 3 SE +/- 0.82, N = 3 SE +/- 0.85, N = 3 37.75 37.57 200.19 198.91 73.92 73.27
R Benchmark EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better R Benchmark SSBD Vulnerable 0.2043 0.4086 0.6129 0.8172 1.0215 SE +/- 0.0029, N = 3 SE +/- 0.0037, N = 3 SE +/- 0.0045, N = 3 SE +/- 0.0014, N = 3 SE +/- 0.0021, N = 3 SE +/- 0.0011, N = 3 0.9055 0.9079 0.8008 0.7894 0.3947 0.3911 1. R scripting front-end version 3.4.4 (2018-03-15)
Scikit-Learn EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 0.17.1 SSBD Vulnerable 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 144.48 144.50 125.96 123.74 25.36 25.31
Stockfish Total Time EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time SSBD Vulnerable 13M 26M 39M 52M 65M SE +/- 78695.70, N = 3 SE +/- 248044.53, N = 3 SE +/- 64483.45, N = 3 SE +/- 45175.52, N = 3 SE +/- 55084.41, N = 3 SE +/- 166857.89, N = 3 58372393 58183837 7993776 7957417 24152025 24133230 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only SSBD Vulnerable 80K 160K 240K 320K 400K SE +/- 1438.48, N = 3 SE +/- 7161.59, N = 3 SE +/- 1005.67, N = 3 SE +/- 871.71, N = 3 SE +/- 124.36, N = 3 SE +/- 389.44, N = 3 395388.07 393664.75 57005.68 56687.08 195458.93 197760.12 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Perl Benchmarks Test: Pod2html EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better Perl Benchmarks Test: Pod2html SSBD Vulnerable 0.0451 0.0902 0.1353 0.1804 0.2255 SE +/- 0.00462084, N = 6 SE +/- 0.00096119, N = 3 SE +/- 0.00047617, N = 3 SE +/- 0.00040548, N = 3 SE +/- 0.00067477, N = 3 SE +/- 0.00018090, N = 3 0.20045042 0.19238990 0.16692850 0.16440514 0.14383901 0.14530132
PostgreSQL pgbench Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only SSBD Vulnerable 40K 80K 120K 160K 200K SE +/- 678.00, N = 3 SE +/- 800.05, N = 4 SE +/- 1191.31, N = 3 SE +/- 661.44, N = 3 50134.27 51360.22 191709.25 189690.99 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write SSBD Vulnerable 1600 3200 4800 6400 8000 SE +/- 37.17, N = 3 SE +/- 26.59, N = 3 SE +/- 29.85, N = 3 SE +/- 63.04, N = 3 7519.28 7497.78 4152.53 4270.12 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write SSBD Vulnerable 1500 3000 4500 6000 7500 SE +/- 84.82, N = 3 SE +/- 45.07, N = 3 SE +/- 11.19, N = 3 SE +/- 62.83, N = 3 6654.57 6830.52 4556.94 4511.55 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Perl Benchmarks Test: Interpreter EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better Perl Benchmarks Test: Interpreter SSBD Vulnerable 0.0005 0.001 0.0015 0.002 0.0025 SE +/- 0.00000625, N = 3 SE +/- 0.00000814, N = 3 SE +/- 0.00000471, N = 3 SE +/- 0.00000685, N = 3 SE +/- 0.00000698, N = 3 SE +/- 0.00001123, N = 3 0.00209126 0.00209769 0.00139883 0.00136430 0.00106965 0.00110452
Apache Benchmark Static Web Page Serving EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving SSBD Vulnerable 8K 16K 24K 32K 40K SE +/- 367.69, N = 6 SE +/- 273.53, N = 3 SE +/- 117.28, N = 3 SE +/- 149.88, N = 3 SE +/- 119.70, N = 3 SE +/- 68.81, N = 3 17901.87 17887.19 34805.09 35083.36 30561.02 30813.59 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Stress-NG Test: Socket Activity EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity Vulnerable SSBD 4K 8K 12K 16K 20K SE +/- 342.31, N = 6 SE +/- 191.34, N = 6 SE +/- 198.25, N = 6 SE +/- 106.79, N = 3 SE +/- 54.40, N = 3 17227.19 2917.46 3044.42 6889.69 7205.82 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Java SciMark Computational Test: Composite EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Composite SSBD Vulnerable 600 1200 1800 2400 3000 SE +/- 29.46, N = 8 SE +/- 10.78, N = 4 SE +/- 21.33, N = 4 SE +/- 1.76, N = 4 SE +/- 14.81, N = 4 SE +/- 6.98, N = 4 2177.16 2177.73 2587.38 2620.41 2949.91 2959.81
AOBench Size: 2048 x 2048 - Total Time EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time SSBD Vulnerable 12 24 36 48 60 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 51.96 51.96 44.86 44.86 38.80 38.68 1. (CC) gcc options: -lm -O3
Stress-NG Test: System V Message Passing EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing Vulnerable SSBD 3M 6M 9M 12M 15M SE +/- 221694.35, N = 6 SE +/- 66867.32, N = 3 SE +/- 329210.70, N = 6 SE +/- 16750.99, N = 3 SE +/- 23451.50, N = 3 10735107.79 5087012.74 3424065.12 11846350.76 11899692.71 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
PostMark Disk Transaction Performance EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance SSBD Vulnerable 1500 3000 4500 6000 7500 SE +/- 38.33, N = 3 SE +/- 51.00, N = 3 SE +/- 48.33, N = 3 SE +/- 70.00, N = 3 5434 5396 6148 6049 7142 7212 1. (CC) gcc options: -O3
PyBench Total For Average Test Times EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times SSBD Vulnerable 400 800 1200 1600 2000 SE +/- 5.24, N = 3 SE +/- 4.06, N = 3 SE +/- 2.89, N = 3 SE +/- 1.73, N = 3 SE +/- 1.76, N = 3 SE +/- 3.84, N = 3 2086 2076 1790 1794 1539 1559
LAME MP3 Encoding WAV To MP3 EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 SSBD Vulnerable 10 20 30 40 50 SE +/- 0.01, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 43.72 43.86 37.84 37.80 32.46 32.56 1. (CC) gcc options: -lncurses -lm
IOzone Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance SSBD Vulnerable 200 400 600 800 1000 SE +/- 4.66, N = 3 SE +/- 2.30, N = 3 SE +/- 0.38, N = 3 SE +/- 1.01, N = 3 SE +/- 23.08, N = 6 SE +/- 8.28, N = 3 928.86 1024.23 280.55 279.57 484.77 827.10 1. (CC) gcc options: -O3
Stress-NG Test: Context Switching EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Vulnerable SSBD 4M 8M 12M 16M 20M SE +/- 482829.82, N = 6 SE +/- 2857.46, N = 3 SE +/- 1713.32, N = 3 SE +/- 14072.03, N = 3 SE +/- 8571.75, N = 3 17597048.97 1377134.64 1376458.10 4734667.28 4766643.10 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Forking EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Forking SSBD Vulnerable 13K 26K 39K 52K 65K SE +/- 1535.43, N = 6 SE +/- 286.24, N = 3 SE +/- 200.62, N = 3 SE +/- 215.66, N = 3 SE +/- 124.42, N = 3 SE +/- 189.76, N = 3 43442.24 49686.60 28512.83 29784.79 58451.48 59902.92 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Semaphores EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores SSBD Vulnerable 2M 4M 6M 8M 10M SE +/- 3942.06, N = 3 SE +/- 4657.01, N = 3 SE +/- 118037.24, N = 5 SE +/- 76921.41, N = 3 SE +/- 29011.98, N = 3 SE +/- 35422.35, N = 3 1597032.40 1593274.94 7641293.74 8057541.78 4490592.84 4470215.22 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
LuaJIT Test: Composite EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Composite SSBD Vulnerable 300 600 900 1200 1500 SE +/- 5.65, N = 3 SE +/- 1.62, N = 3 SE +/- 1.34, N = 3 SE +/- 3.14, N = 3 SE +/- 11.04, N = 3 SE +/- 3.67, N = 3 1114.90 1134.76 1104.94 1097.67 1504.56 1492.84 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
ebizzy EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 SSBD Vulnerable 200K 400K 600K 800K 1000K SE +/- 15282.50, N = 5 SE +/- 24867.55, N = 6 SE +/- 191.32, N = 3 SE +/- 61.17, N = 3 SE +/- 10512.67, N = 3 SE +/- 9494.40, N = 6 1122614 1134210 85804 86028 559670 566374 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
SQLite Timed SQLite Insertions EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.22 Timed SQLite Insertions SSBD Vulnerable 14 28 42 56 70 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.17, N = 3 SE +/- 0.31, N = 3 2.94 2.86 3.50 3.55 62.60 63.83 1. (CC) gcc options: -O2 -lreadline -ltermcap -lz -ldl -lpthread
PHPBench PHP Benchmark Suite EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite SSBD Vulnerable 110K 220K 330K 440K 550K SE +/- 2093.04, N = 3 SE +/- 564.17, N = 3 SE +/- 1559.17, N = 3 SE +/- 2108.68, N = 3 SE +/- 3125.52, N = 3 SE +/- 3330.02, N = 3 386120 386088 458502 455102 519603 517478
OpenSSL RSA 4096-bit Performance EPYC 7601 Ryzen 7 2700X OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.0f RSA 4096-bit Performance SSBD Vulnerable 1000 2000 3000 4000 5000 SE +/- 19.40, N = 3 SE +/- 21.60, N = 3 SE +/- 2.67, N = 3 SE +/- 1.98, N = 3 4610.47 4608.33 1719.50 1724.83 1. (CC) gcc options: -O3 -pthread -m64 -lssl -lcrypto -ldl
Git Time To Complete Common Git Commands EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands SSBD Vulnerable 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 7.36 7.27 6.13 6.11 5.46 5.40 1. git version 2.17.0
LuaJIT Test: Jacobi Successive Over-Relaxation EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Jacobi Successive Over-Relaxation SSBD Vulnerable 400 800 1200 1600 2000 SE +/- 0.27, N = 3 SE +/- 0.21, N = 3 SE +/- 0.35, N = 3 SE +/- 0.20, N = 3 SE +/- 5.86, N = 3 SE +/- 0.18, N = 3 1421.63 1422.25 1644.45 1643.83 1922.06 1934.33 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
LuaJIT Test: Dense LU Matrix Factorization EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Dense LU Matrix Factorization SSBD Vulnerable 800 1600 2400 3200 4000 SE +/- 26.26, N = 3 SE +/- 4.40, N = 3 SE +/- 4.44, N = 3 SE +/- 14.04, N = 3 SE +/- 48.48, N = 3 SE +/- 19.77, N = 3 2614.12 2728.63 2135.52 2105.37 3575.11 3524.26 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
LuaJIT Test: Sparse Matrix Multiply EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Sparse Matrix Multiply SSBD Vulnerable 300 600 900 1200 1500 SE +/- 2.38, N = 3 SE +/- 8.77, N = 3 SE +/- 1.82, N = 3 SE +/- 1.83, N = 3 SE +/- 5.42, N = 3 SE +/- 1.23, N = 3 917.87 914.14 1065.83 1062.32 1215.05 1213.50 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
LuaJIT Test: Fast Fourier Transform EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Fast Fourier Transform SSBD Vulnerable 70 140 210 280 350 SE +/- 0.06, N = 3 SE +/- 1.26, N = 3 SE +/- 0.19, N = 3 SE +/- 0.67, N = 3 SE +/- 0.50, N = 3 SE +/- 1.49, N = 3 240.91 228.85 237.57 236.74 302.71 283.48 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
LuaJIT Test: Monte Carlo EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Monte Carlo SSBD Vulnerable 110 220 330 440 550 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 1.08, N = 3 SE +/- 0.02, N = 3 SE +/- 1.81, N = 3 SE +/- 1.69, N = 3 379.97 379.92 441.33 440.09 507.90 508.62 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
Java SciMark Computational Test: Jacobi Successive Over-Relaxation EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation SSBD Vulnerable 400 800 1200 1600 2000 SE +/- 0.98, N = 4 SE +/- 0.09, N = 4 SE +/- 0.36, N = 4 SE +/- 0.13, N = 4 SE +/- 3.44, N = 4 SE +/- 2.95, N = 4 1207.65 1208.41 1400.40 1400.53 1636.85 1639.11
Java SciMark Computational Test: Dense LU Matrix Factorization EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Dense LU Matrix Factorization SSBD Vulnerable 1500 3000 4500 6000 7500 SE +/- 16.30, N = 4 SE +/- 56.49, N = 4 SE +/- 85.95, N = 4 SE +/- 12.16, N = 4 SE +/- 82.46, N = 4 SE +/- 23.94, N = 4 5230.06 5110.10 6319.11 6384.79 6943.53 6996.91
Java SciMark Computational Test: Sparse Matrix Multiply EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Sparse Matrix Multiply SSBD Vulnerable 600 1200 1800 2400 3000 SE +/- 281.26, N = 4 SE +/- 0.56, N = 4 SE +/- 0.41, N = 4 SE +/- 0.25, N = 4 SE +/- 3.58, N = 4 SE +/- 5.42, N = 4 1682.48 1974.16 2288.47 2288.22 2634.63 2644.61
Java SciMark Computational Test: Fast Fourier Transform EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Fast Fourier Transform SSBD Vulnerable 400 800 1200 1600 2000 SE +/- 25.40, N = 4 SE +/- 28.92, N = 4 SE +/- 98.64, N = 4 SE +/- 2.37, N = 4 SE +/- 17.88, N = 4 SE +/- 5.77, N = 4 1365.76 1366.74 1505.81 1602.07 1887.32 1866.30
Java SciMark Computational Test: Monte Carlo EPYC 7601 Ryzen 3 2200G Ryzen 7 2700X OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Monte Carlo SSBD Vulnerable 400 800 1200 1600 2000 SE +/- 1.33, N = 4 SE +/- 0.00, N = 4 SE +/- 2.06, N = 4 SE +/- 1.42, N = 4 SE +/- 4.87, N = 4 SE +/- 5.05, N = 4 1230.92 1229.24 1423.13 1426.43 1647.20 1652.12
Phoronix Test Suite v10.8.4