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 1801075-AL-RETPOLINE03 retpoline-testing - Phoronix Test Suite retpoline-testing Tests for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1801075-AL-RETPOLINE03&grw&sor&rro .
Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Driver OpenCL Compiler File-System Screen Resolution EPYC 7601 2 x Xeon Gold 6138 noretpoline Retpoline Retpoline + GCC no retpoline Retpoline Retpoline + GCC AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads) TYAN B8026T70AE24HR AMD Device 1450 129024MB 280GB INTEL SSDPE21D280GA ASPEED ASPEED Family VE228 Broadcom Limited NetXtreme BCM5720 Gigabit PCIe Ubuntu 17.10 4.14.0-phx-retpoline (x86_64) GNOME Shell 3.26.1 modesetting 1.19.5 OpenCL 1.2 pocl 1.0 LLVM 5.0.0 GCC 7.2.0 + Clang 5.0.0-3 + LLVM 5.0.0 ext4 1920x1080 4.14.0-phx-retpoline-gcc-retpo (x86_64) 2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads) TYAN S7106 Intel Device 2020 96256MB 256GB Samsung SSD 850 + 2000GB Seagate ST2000DM006-2DM1 + 2 x 120GB TOSHIBA-TR150 Intel I210 Gigabit Connection 4.14.0-phx-retpoline (x86_64) GCC 7.2.0 4.14.0-phx-retpoline-gcc-retpo (x86_64) 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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Disk Details - EPYC 7601: noretpoline: NONE / data=ordered,errors=remount-ro,relatime,rw - EPYC 7601: Retpoline: NONE / data=ordered,errors=remount-ro,relatime,rw - EPYC 7601: Retpoline + GCC: NONE / data=ordered,errors=remount-ro,relatime,rw - 2 x Xeon Gold 6138: no retpoline: CFQ / data=ordered,errors=remount-ro,relatime,rw - 2 x Xeon Gold 6138: Retpoline: CFQ / data=ordered,errors=remount-ro,relatime,rw - 2 x Xeon Gold 6138: Retpoline + GCC: CFQ / data=ordered,errors=remount-ro,relatime,rw Processor Details - EPYC 7601: noretpoline: Scaling Governor: acpi-cpufreq ondemand - EPYC 7601: Retpoline: Scaling Governor: acpi-cpufreq ondemand - EPYC 7601: Retpoline + GCC: Scaling Governor: acpi-cpufreq ondemand - 2 x Xeon Gold 6138: no retpoline: Scaling Governor: intel_pstate powersave - 2 x Xeon Gold 6138: Retpoline: Scaling Governor: intel_pstate powersave - 2 x Xeon Gold 6138: Retpoline + GCC: Scaling Governor: intel_pstate powersave System Details - Python 2.7.14.
compilebench: Compile compilebench: Initial Create t-test1: 1 t-test1: 2 lzbench: XZ 0 - Compression lzbench: Zstd 1 - Compression cachebench: Read cachebench: Write cachebench: Read / Modify / Write glibc-bench: ffs glibc-bench: sqrt glibc-bench: pthread_once tjbench: Decompression Throughput fio: Rand Read - Libaio - No - Yes - 2MB - Default Test Directory fio: Rand Read - Libaio - No - Yes - 4KB - Default Test Directory fio: Rand Write - Libaio - No - Yes - 2MB - Default Test Directory fio: Rand Write - Libaio - No - Yes - 4KB - Default Test Directory fio: Seq Read - Libaio - No - Yes - 2MB - Default Test Directory fio: Seq Read - Libaio - No - Yes - 4KB - Default Test Directory fio: Seq Write - Libaio - No - Yes - 2MB - Default Test Directory fio: Seq Write - Libaio - No - Yes - 4KB - Default Test Directory fs-mark: 1000 Files, 1MB Size fs-mark: 4000 Files, 32 Sub Dirs, 1MB Size scikit-learn: parboil: OpenMP CUTCP parboil: OpenMP MRI Gridding compress-lzma: 256MB File Compression rodinia: OpenMP LavaMD rodinia: OpenMP CFD Solver build-apache: Time To Compile stockfish: Total Time john-the-ripper: Blowfish build-linux-kernel: Time To Compile c-ray: Total Time apache: Static Web Page Serving redis: LPOP redis: SADD redis: LPUSH redis: GET redis: SET pgbench: Buffer Test - Normal Load - Read Only pgbench: Buffer Test - Normal Load - Read Write ebizzy: pybench: Total For Average Test Times EPYC 7601 2 x Xeon Gold 6138 noretpoline Retpoline Retpoline + GCC no retpoline Retpoline Retpoline + GCC 1696.87 410.85 37.76 14.38 24 335 2205.73 21622.77 22924.24 4.83 4.70 4.83 140.83 2509.83 1176.20 1972.70 1059.73 2511.77 1183.53 1971.10 1081.23 597.93 581.87 34.00 2.71 283.16 329.57 31.65 10.97 31.71 4507 35458 38.30 3.50 16587.34 1520530.25 1233207.56 1117859.50 1394712.79 1131889.69 1093230 1794 1691.37 406.41 36.68 14.46 24 336 2215.24 21556.98 22918.96 4.83 4.70 4.83 140.99 2615.60 1165.97 2157.60 1046.93 2618.67 1160.83 2158.03 1091.50 639.77 629.27 33.91 2.73 283.25 328.95 31.86 10.76 32.21 4507 35714 38.44 3.45 16838.76 1394465.79 1293172.50 1147686.87 1362255.92 1161527.67 1073587 1801 1693.10 406.91 38.18 14.66 24 335 2214.25 21835.76 22900.81 4.83 4.70 4.83 140.87 2637.27 1128.57 2158.27 1048.77 2618.20 1193.80 2156.87 1072.57 619.67 631.30 34.47 2.70 288.36 329.00 31.87 11.08 32.12 4501 35715 38.52 3.48 16716.48 1230732.38 1249051.08 1123252.42 1352327.02 1162399.91 952691 1795 1496.78 533.70 65.91 23.12 32 361 2973.08 24954.96 25777.79 3.26 12.30 3.87 145.81 543.05 383.14 523.89 338.58 519.38 457.26 514.75 415.49 128.67 111.02 184.75 2.35 407.91 281.84 28.50 9.73 26.24 3437 49652 30.25 3.16 22258.72 1423431.25 1589703.69 1357638.81 1627717.71 1564339.04 599258.14 2136.64 946321 1307 1694.04 508.92 66.56 23.29 30 369 2872.09 23882.88 25061.33 3.26 9.95 3.80 154.02 543.18 384.79 514.67 341.01 518.49 454.44 526.12 413.25 133.73 136.67 185.68 2.38 413.85 281.25 28.70 9.93 26.31 3654 48399 30.46 3.15 21347.64 1486377.46 1573307.83 1382896.04 1738340.06 1525833.21 597483.03 2467.38 954773 1306 1637.02 478.76 64.45 23.04 31 370 2839.79 23753.79 24928.44 3.26 9.96 4.49 146.51 543.37 388.19 512.18 341.98 518.48 456.92 527.34 416.94 129.63 111.17 186.08 2.38 405.25 282.04 28.43 10.54 26.32 3613 51089 30.63 3.18 18757.65 1347143.44 1604656.60 1454926.31 1574731.42 1399642.27 577641.99 3976.32 950671 1315 OpenBenchmarking.org
Compile Bench Test: Compile 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile no retpoline Retpoline + GCC Retpoline noretpoline 400 800 1200 1600 2000 SE +/- 7.13, N = 3 SE +/- 40.27, N = 6 SE +/- 62.71, N = 6 SE +/- 3.64, N = 3 SE +/- 4.84, N = 3 SE +/- 9.70, N = 3 1496.78 1637.02 1694.04 1691.37 1693.10 1696.87
Compile Bench Test: Initial Create EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Retpoline Retpoline + GCC noretpoline no retpoline 120 240 360 480 600 SE +/- 3.88, N = 3 SE +/- 4.20, N = 3 SE +/- 2.54, N = 3 SE +/- 27.64, N = 3 SE +/- 25.41, N = 3 SE +/- 1.88, N = 3 406.41 406.91 410.85 478.76 508.92 533.70
t-test1 Threads: 1 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 1 Retpoline no retpoline Retpoline + GCC noretpoline 15 30 45 60 75 SE +/- 0.09, N = 3 SE +/- 0.15, N = 3 SE +/- 0.14, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 66.56 65.91 64.45 38.18 37.76 36.68 1. (CC) gcc options: -pthread
t-test1 Threads: 2 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 2 Retpoline no retpoline Retpoline + GCC noretpoline 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 23.29 23.12 23.04 14.66 14.46 14.38 1. (CC) gcc options: -pthread
lzbench Test: XZ 0 - Process: Compression EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: XZ 0 - Process: Compression noretpoline Retpoline Retpoline + GCC no retpoline 7 14 21 28 35 SE +/- 0.56, N = 6 SE +/- 0.50, N = 6 SE +/- 0.72, N = 6 24 24 24 30 31 32 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 1 - Process: Compression EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Zstd 1 - Process: Compression noretpoline Retpoline + GCC Retpoline no retpoline 80 160 240 320 400 SE +/- 1.33, N = 3 SE +/- 1.20, N = 3 SE +/- 1.33, N = 3 SE +/- 0.88, N = 3 SE +/- 2.52, N = 3 SE +/- 2.08, N = 3 335 335 336 361 369 370 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
CacheBench Test: Read EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read noretpoline Retpoline + GCC Retpoline no retpoline 600 1200 1800 2400 3000 SE +/- 9.38, N = 3 SE +/- 0.98, N = 3 SE +/- 0.02, N = 3 SE +/- 11.39, N = 3 SE +/- 12.31, N = 3 SE +/- 7.30, N = 3 2205.73 2214.25 2215.24 2839.79 2872.09 2973.08 1. (CC) gcc options: -lrt
CacheBench Test: Write EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Write Retpoline noretpoline Retpoline + GCC no retpoline 5K 10K 15K 20K 25K SE +/- 133.19, N = 3 SE +/- 53.65, N = 3 SE +/- 25.70, N = 3 SE +/- 82.06, N = 3 SE +/- 197.71, N = 3 SE +/- 34.79, N = 3 21556.98 21622.77 21835.76 23753.79 23882.88 24954.96 1. (CC) gcc options: -lrt
CacheBench Test: Read / Modify / Write EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read / Modify / Write Retpoline + GCC Retpoline noretpoline no retpoline 6K 12K 18K 24K 30K SE +/- 12.91, N = 3 SE +/- 9.68, N = 3 SE +/- 5.63, N = 3 SE +/- 226.86, N = 3 SE +/- 271.49, N = 3 SE +/- 112.30, N = 3 22900.81 22918.96 22924.24 24928.44 25061.33 25777.79 1. (CC) gcc options: -lrt
glibc bench Benchmark: ffs EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs Retpoline + GCC Retpoline noretpoline no retpoline 1.0868 2.1736 3.2604 4.3472 5.434 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.83 4.83 4.83 3.26 3.26 3.26
glibc bench Benchmark: sqrt 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sqrt no retpoline Retpoline + GCC Retpoline noretpoline 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.62, N = 6 SE +/- 0.62, N = 6 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 12.30 9.96 9.95 4.70 4.70 4.70
glibc bench Benchmark: pthread_once EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once Retpoline + GCC Retpoline noretpoline no retpoline 1.0868 2.1736 3.2604 4.3472 5.434 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.24, N = 6 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 4.83 4.83 4.83 4.49 3.87 3.80
libjpeg-turbo tjbench Test: Decompression Throughput EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 1.5.1 Test: Decompression Throughput noretpoline Retpoline + GCC Retpoline no retpoline 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 5.29, N = 6 SE +/- 6.27, N = 6 SE +/- 1.27, N = 3 140.83 140.87 140.99 145.81 146.51 154.02 1. (CC) gcc options: -O3 -lm
Flexible IO Tester Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 2.1.13 Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 600 1200 1800 2400 3000 SE +/- 1.17, N = 3 SE +/- 0.14, N = 3 SE +/- 0.10, N = 3 SE +/- 0.24, N = 3 SE +/- 0.45, N = 3 SE +/- 22.27, N = 3 543.05 543.18 543.37 2509.83 2615.60 2637.27 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 2.1.13 Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 300 600 900 1200 1500 SE +/- 4.29, N = 3 SE +/- 1.24, N = 3 SE +/- 2.02, N = 3 SE +/- 1.94, N = 3 SE +/- 13.29, N = 3 SE +/- 17.24, N = 3 383.14 384.79 388.19 1128.57 1165.97 1176.20 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 2.1.13 Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory Retpoline + GCC Retpoline no retpoline noretpoline 500 1000 1500 2000 2500 SE +/- 2.16, N = 3 SE +/- 2.04, N = 3 SE +/- 0.94, N = 3 SE +/- 1.43, N = 3 SE +/- 3.16, N = 3 SE +/- 3.18, N = 3 512.18 514.67 523.89 1972.70 2157.60 2158.27 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 2.1.13 Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 200 400 600 800 1000 SE +/- 1.94, N = 3 SE +/- 1.78, N = 3 SE +/- 1.80, N = 3 SE +/- 17.28, N = 6 SE +/- 11.31, N = 3 SE +/- 11.43, N = 3 338.58 341.01 341.98 1046.93 1048.77 1059.73 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 2.1.13 Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory Retpoline + GCC Retpoline no retpoline noretpoline 600 1200 1800 2400 3000 SE +/- 0.05, N = 3 SE +/- 0.25, N = 3 SE +/- 0.72, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 518.48 518.49 519.38 2511.77 2618.20 2618.67 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 2.1.13 Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Retpoline Retpoline + GCC no retpoline noretpoline 300 600 900 1200 1500 SE +/- 0.14, N = 3 SE +/- 1.52, N = 3 SE +/- 0.98, N = 3 SE +/- 6.24, N = 3 SE +/- 18.11, N = 3 SE +/- 17.58, N = 3 454.44 456.92 457.26 1160.83 1183.53 1193.80 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 2.1.13 Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 500 1000 1500 2000 2500 SE +/- 8.78, N = 4 SE +/- 0.90, N = 3 SE +/- 0.39, N = 3 SE +/- 1.26, N = 3 SE +/- 4.03, N = 3 SE +/- 3.77, N = 3 514.75 526.12 527.34 1971.10 2156.87 2158.03 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 2.1.13 Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Retpoline no retpoline Retpoline + GCC noretpoline 200 400 600 800 1000 SE +/- 0.97, N = 3 SE +/- 2.46, N = 3 SE +/- 1.44, N = 3 SE +/- 7.38, N = 3 SE +/- 14.34, N = 3 SE +/- 17.15, N = 6 413.25 415.49 416.94 1072.57 1081.23 1091.50 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
FS-Mark Test: 1000 Files, 1MB Size 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size no retpoline Retpoline + GCC Retpoline noretpoline 140 280 420 560 700 SE +/- 2.17, N = 3 SE +/- 2.15, N = 6 SE +/- 0.20, N = 3 SE +/- 5.75, N = 3 SE +/- 3.59, N = 3 SE +/- 1.90, N = 3 128.67 129.63 133.73 597.93 619.67 639.77 1. (CC) gcc options: -static
FS-Mark Test: 4000 Files, 32 Sub Dirs, 1MB Size 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size no retpoline Retpoline + GCC Retpoline noretpoline 140 280 420 560 700 SE +/- 2.97, N = 6 SE +/- 7.23, N = 6 SE +/- 0.54, N = 3 SE +/- 1.13, N = 3 SE +/- 1.74, N = 3 SE +/- 4.00, N = 3 111.02 111.17 136.67 581.87 629.27 631.30 1. (CC) gcc options: -static
Scikit-Learn 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 0.17.1 Retpoline + GCC Retpoline no retpoline noretpoline 40 80 120 160 200 SE +/- 2.58, N = 3 SE +/- 0.29, N = 3 SE +/- 0.99, N = 3 SE +/- 0.48, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 186.08 185.68 184.75 34.47 34.00 33.91
Parboil Test: OpenMP CUTCP EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP CUTCP Retpoline noretpoline Retpoline + GCC no retpoline 0.6143 1.2286 1.8429 2.4572 3.0715 SE +/- 0.04, N = 6 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 2.73 2.71 2.70 2.38 2.38 2.35 1. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp
Parboil Test: OpenMP MRI Gridding 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP MRI Gridding Retpoline no retpoline Retpoline + GCC noretpoline 90 180 270 360 450 SE +/- 6.92, N = 3 SE +/- 6.83, N = 3 SE +/- 6.86, N = 4 SE +/- 1.39, N = 3 SE +/- 0.14, N = 3 SE +/- 0.38, N = 3 413.85 407.91 405.25 288.36 283.25 283.16 1. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp
LZMA Compression 256MB File Compression EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Seconds, Fewer Is Better LZMA Compression 256MB File Compression noretpoline Retpoline + GCC Retpoline no retpoline 70 140 210 280 350 SE +/- 0.18, N = 3 SE +/- 0.42, N = 3 SE +/- 0.22, N = 3 SE +/- 2.80, N = 3 SE +/- 0.34, N = 3 SE +/- 0.60, N = 3 329.57 329.00 328.95 282.04 281.84 281.25 1. (CXX) g++ options: -O2
Rodinia Test: OpenMP LavaMD EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD Retpoline + GCC Retpoline noretpoline no retpoline 7 14 21 28 35 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 31.87 31.86 31.65 28.70 28.50 28.43 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP CFD Solver Retpoline + GCC noretpoline Retpoline no retpoline 3 6 9 12 15 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.30, N = 6 SE +/- 0.15, N = 5 SE +/- 0.16, N = 3 11.08 10.97 10.76 10.54 9.93 9.73 1. (CXX) g++ options: -O2 -lOpenCL
Timed Apache Compilation Time To Compile EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.7 Time To Compile Retpoline Retpoline + GCC noretpoline no retpoline 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 32.21 32.12 31.71 26.32 26.31 26.24
Stockfish Total Time EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org ms, Fewer Is Better Stockfish 2014-11-26 Total Time Retpoline noretpoline Retpoline + GCC no retpoline 1000 2000 3000 4000 5000 SE +/- 3.48, N = 3 SE +/- 2.65, N = 3 SE +/- 202.73, N = 6 SE +/- 210.25, N = 6 SE +/- 37.22, N = 3 4507 4507 4501 3654 3613 3437 1. (CXX) g++ options: -lpthread -fno-exceptions -fno-rtti -ansi -pedantic -O3 -msse -msse3 -mpopcnt -flto
John The Ripper Test: Blowfish EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0 Test: Blowfish noretpoline Retpoline Retpoline + GCC no retpoline 11K 22K 33K 44K 55K SE +/- 400.35, N = 3 SE +/- 192.26, N = 3 SE +/- 232.00, N = 3 SE +/- 1882.95, N = 6 SE +/- 562.61, N = 3 SE +/- 357.46, N = 3 35458 35714 35715 48399 49652 51089 1. (CC) gcc options: -fopenmp -lcrypt
Timed Linux Kernel Compilation Time To Compile EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.13 Time To Compile Retpoline + GCC Retpoline noretpoline no retpoline 9 18 27 36 45 SE +/- 0.63, N = 6 SE +/- 0.76, N = 6 SE +/- 0.68, N = 6 SE +/- 0.80, N = 6 SE +/- 0.77, N = 6 SE +/- 0.75, N = 6 38.52 38.44 38.30 30.63 30.46 30.25
C-Ray Total Time EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time noretpoline Retpoline + GCC Retpoline no retpoline 0.7875 1.575 2.3625 3.15 3.9375 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.50 3.48 3.45 3.18 3.16 3.15 1. (CC) gcc options: -lm -lpthread -O3
Apache Benchmark Static Web Page Serving EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.7 Static Web Page Serving noretpoline Retpoline + GCC Retpoline no retpoline 5K 10K 15K 20K 25K SE +/- 41.45, N = 3 SE +/- 296.19, N = 3 SE +/- 97.15, N = 3 SE +/- 51.11, N = 3 SE +/- 63.48, N = 3 SE +/- 139.49, N = 3 16587.34 16716.48 16838.76 18757.65 21347.64 22258.72 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Redis Test: LPOP EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: LPOP Retpoline + GCC Retpoline no retpoline noretpoline 300K 600K 900K 1200K 1500K SE +/- 11491.58, N = 3 SE +/- 61195.38, N = 6 SE +/- 1539.75, N = 3 SE +/- 25234.38, N = 6 SE +/- 36207.27, N = 6 SE +/- 77843.26, N = 6 1230732.38 1394465.79 1520530.25 1347143.44 1423431.25 1486377.46 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread
Redis Test: SADD EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: SADD noretpoline Retpoline + GCC Retpoline no retpoline 300K 600K 900K 1200K 1500K SE +/- 19184.10, N = 4 SE +/- 7598.74, N = 3 SE +/- 51667.16, N = 6 SE +/- 95230.31, N = 6 SE +/- 68212.97, N = 6 SE +/- 62798.70, N = 6 1233207.56 1249051.08 1293172.50 1573307.83 1589703.69 1604656.60 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread
Redis Test: LPUSH EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: LPUSH noretpoline Retpoline + GCC Retpoline no retpoline 300K 600K 900K 1200K 1500K SE +/- 8338.77, N = 3 SE +/- 6595.02, N = 3 SE +/- 3427.20, N = 3 SE +/- 57810.96, N = 6 SE +/- 51060.27, N = 6 SE +/- 49927.23, N = 6 1117859.50 1123252.42 1147686.87 1357638.81 1382896.04 1454926.31 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread
Redis Test: GET EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: GET Retpoline + GCC Retpoline noretpoline no retpoline 400K 800K 1200K 1600K 2000K SE +/- 28137.42, N = 6 SE +/- 27266.47, N = 3 SE +/- 2966.06, N = 3 SE +/- 80851.67, N = 6 SE +/- 50934.82, N = 6 SE +/- 96355.24, N = 6 1352327.02 1362255.92 1394712.79 1574731.42 1627717.71 1738340.06 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread
Redis Test: SET EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: SET noretpoline Retpoline Retpoline + GCC no retpoline 300K 600K 900K 1200K 1500K SE +/- 26854.76, N = 6 SE +/- 7115.17, N = 3 SE +/- 5879.00, N = 3 SE +/- 55833.41, N = 6 SE +/- 90449.67, N = 6 SE +/- 28059.92, N = 3 1131889.69 1161527.67 1162399.91 1399642.27 1525833.21 1564339.04 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only Retpoline + GCC Retpoline no retpoline 130K 260K 390K 520K 650K SE +/- 4346.70, N = 3 SE +/- 1869.94, N = 3 SE +/- 2613.28, N = 3 577641.99 597483.03 599258.14 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -fPIC -lpgcommon -lpgport -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write no retpoline Retpoline Retpoline + GCC 900 1800 2700 3600 4500 SE +/- 40.05, N = 3 SE +/- 49.01, N = 6 SE +/- 15.09, N = 3 2136.64 2467.38 3976.32 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -fPIC -lpgcommon -lpgport -lpthread -lrt -lcrypt -ldl -lm
ebizzy 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 no retpoline Retpoline + GCC Retpoline noretpoline 200K 400K 600K 800K 1000K SE +/- 7835.23, N = 3 SE +/- 13692.48, N = 5 SE +/- 13516.78, N = 6 SE +/- 23463.01, N = 6 SE +/- 26430.87, N = 6 SE +/- 19950.45, N = 3 946321 950671 954773 952691 1073587 1093230 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
PyBench Total For Average Test Times EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2008-08-14 Total For Average Test Times Retpoline Retpoline + GCC noretpoline no retpoline 400 800 1200 1600 2000 SE +/- 11.33, N = 3 SE +/- 7.97, N = 3 SE +/- 1.76, N = 3 SE +/- 1.53, N = 3 1801 1795 1794 1315 1307 1306
Flexible IO Tester Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 2.1.13 Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 300 600 900 1200 1500 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 11.00, N = 3 262 262 262 1251 1304 1315 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 2.1.13 Type: Random Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 60K 120K 180K 240K 300K SE +/- 1071.43, N = 3 SE +/- 309.68, N = 3 SE +/- 504.90, N = 3 SE +/- 591.14, N = 3 SE +/- 3375.56, N = 3 SE +/- 4402.78, N = 3 95782 96194 97043 288951 298428 301037 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 2.1.13 Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory Retpoline + GCC Retpoline no retpoline noretpoline 200 400 600 800 1000 SE +/- 1.20, N = 3 SE +/- 1.20, N = 3 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 SE +/- 1.53, N = 3 SE +/- 1.67, N = 3 246 248 252 983 1075 1076 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 2.1.13 Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 60K 120K 180K 240K 300K SE +/- 484.83, N = 3 SE +/- 444.91, N = 3 SE +/- 451.27, N = 3 SE +/- 4419.58, N = 6 SE +/- 2976.09, N = 3 SE +/- 2932.09, N = 3 84641 85249 85492 268041 268542 271273 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 2.1.13 Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 300 600 900 1200 1500 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 250 250 250 1252 1306 1306 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 2.1.13 Type: Sequential Read - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Retpoline Retpoline + GCC no retpoline noretpoline 70K 140K 210K 280K 350K SE +/- 33.79, N = 3 SE +/- 379.04, N = 3 SE +/- 246.03, N = 3 SE +/- 1598.66, N = 3 SE +/- 4646.93, N = 3 SE +/- 4452.90, N = 3 113608 114227 114311 297144 302950 305665 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 2.1.13 Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory no retpoline Retpoline Retpoline + GCC noretpoline 200 400 600 800 1000 SE +/- 4.34, N = 4 SE +/- 0.58, N = 3 SE +/- 1.86, N = 3 SE +/- 1.86, N = 3 248 253 254 982 1075 1075 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 2 x Xeon Gold 6138 EPYC 7601 OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 2.1.13 Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Retpoline no retpoline Retpoline + GCC noretpoline 60K 120K 180K 240K 300K SE +/- 241.21, N = 3 SE +/- 614.11, N = 3 SE +/- 361.30, N = 3 SE +/- 1888.66, N = 3 SE +/- 3663.70, N = 3 SE +/- 4389.73, N = 6 103308 103868 104232 274530 276778 279404 1. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl
lzbench Test: XZ 0 - Process: Decompression EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: XZ 0 - Process: Decompression Retpoline noretpoline Retpoline + GCC no retpoline 20 40 60 80 100 SE +/- 1.77, N = 6 SE +/- 2.00, N = 6 SE +/- 1.03, N = 6 76 77 77 86 87 89 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 1 - Process: Decompression EPYC 7601 2 x Xeon Gold 6138 OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Zstd 1 - Process: Decompression Retpoline + GCC noretpoline Retpoline no retpoline 200 400 600 800 1000 SE +/- 3.93, N = 3 SE +/- 4.33, N = 3 SE +/- 4.51, N = 3 SE +/- 4.58, N = 3 SE +/- 4.18, N = 3 SE +/- 3.00, N = 3 910 911 911 975 982 983 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Phoronix Test Suite v10.8.4