AMD EPYC 72F3 Retpoline benchmarks by Michael Larabel.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2203111-NE-EPYC72F3R09 EPYC 72F3 Retpolines Change In Linux 5.17 - Phoronix Test Suite EPYC 72F3 Retpolines Change In Linux 5.17 AMD EPYC 72F3 Retpoline benchmarks by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/2203111-NE-EPYC72F3R09&export=pdf&grr&sor&rro .
EPYC 72F3 Retpolines Change In Linux 5.17 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution New Default - Generic Retpolines AMD Retpolines Former Default AMD EPYC 72F3 8-Core @ 3.70GHz (8 Cores / 16 Threads) Supermicro H12SSL-i v1.01 (2.0 BIOS) AMD Starship/Matisse 128GB 3841GB Micron_9300_MTFDHAL3T8TDP + 1000GB Corsair Force MP600 ASPEED VE228 2 x Broadcom NetXtreme BCM5720 2-port PCIe Ubuntu 21.04 5.17.0-051700rc7daily20220310-generic (x86_64) GNOME Shell 3.38.4 X Server GCC 10.3.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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 Disk Details - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119 Java Details - OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.21.04) Python Details - Python 3.9.5 Security Details - New Default - Generic Retpolines: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected - AMD Retpolines Former Default: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Vulnerable: LFENCE + srbds: Not affected + tsx_async_abort: Not affected
EPYC 72F3 Retpolines Change In Linux 5.17 pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 100 - Read Write pgbench: 100 - 50 - Read Only - Average Latency pgbench: 100 - 50 - Read Only keydb: wireguard: compress-zstd: 19 - Decompression Speed compress-zstd: 19 - Compression Speed openssl: SHA256 compress-lz4: 3 - Decompression Speed compress-lz4: 3 - Compression Speed pgbench: 100 - 100 - Read Only - Average Latency pgbench: 100 - 100 - Read Only cassandra: Writes hackbench: 32 - Process build-godot: Time To Compile ebizzy: fio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory apache: 500 nginx: 200 nginx: 100 apache: 200 apache: 100 nginx: 20 renaissance: In-Memory Database Shootout influxdb: 4 - 10000 - 2,5000,1 - 10000 build-linux-kernel: defconfig node-web-tooling: memtier-benchmark: Redis rocksdb: Read While Writing sockperf: Throughput influxdb: 64 - 10000 - 2,5000,1 - 10000 hackbench: 16 - Thread build-eigen: Time To Compile rocksdb: Rand Fill rocksdb: Update Rand rocksdb: Read Rand Write Rand rocksdb: Rand Read openssl: RSA4096 openssl: RSA4096 hackbench: 16 - Process leveldb: Rand Delete compress-lz4: 9 - Decompression Speed compress-lz4: 9 - Compression Speed build-gdb: Time To Compile leveldb: Seq Fill leveldb: Seq Fill leveldb: Overwrite leveldb: Overwrite sqlite-speedtest: Timed Time - Size 1,000 sockperf: Latency Under Load compress-zstd: 8 - Decompression Speed compress-zstd: 8 - Compression Speed postmark: Disk Transaction Performance compress-7zip: Decompression Rating compress-7zip: Compression Rating renaissance: Finagle HTTP Requests hackbench: 8 - Thread leveldb: Rand Fill leveldb: Rand Fill fio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory build-mplayer: Time To Compile stress-ng: SENDFILE stress-ng: Context Switching stress-ng: Socket Activity stress-ng: System V Message Passing stress-ng: Semaphores hackbench: 8 - Process dacapobench: H2 redis: SET rocksdb: Seq Fill redis: GET dacapobench: Jython leveldb: Seek Rand leveldb: Hot Read compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression node-express-loadtest: dacapobench: Tradebeans dacapobench: Tradesoap leveldb: Rand Read draco: Church Facade osbench: Launch Programs draco: Lion osbench: Create Files osbench: Create Processes osbench: Create Threads leveldb: Fill Sync New Default - Generic Retpolines AMD Retpolines Former Default 9.641 10383 0.170 295179 136793.59 257.104 3694.5 51.6 13238722860 14455.1 61.24 0.331 302523 86420 119.831 111.507 619271 223933 80298.15 213684.40 215190.56 86362.18 82500.75 215287.79 4788.2 1326859.1 78.618 11.26 1324327.32 1734878 539724 1638195.7 62.203 61.685 605572 393101 1391000 61331721 155003.1 2372.3 58.782 99.876 14586.2 59.57 54.955 105.116 16.9 103.365 17.1 50.483 3.666 4255.1 1343.6 6944 69393 86357 2378.7 31.275 103.217 17.2 239667 30.709 200771.29 4296558.49 10751.13 4521841.84 1326767.92 29.950 4268 1998825.92 657523 2506720.25 3761 17.139 10.537 10.784 6692 5762 3660 10.577 6697 49.362977 5088 14.706538 43.140253 17.376741 1820.488 9.590 10440 0.169 295730 142573.34 248.756 3668.5 51.9 13234833737 14817.3 61.36 0.330 302399 85956 117.984 111.580 596554 229500 80970.15 206147.39 207615.65 86408.48 83397.57 210605.86 4878.7 1323460.2 78.591 11.31 1313054.11 1746524 587523 1639910.0 62.029 61.098 617250 398526 1386586 61586232 155031.8 2374.1 58.356 98.953 14807.4 59.69 55.032 106.946 16.5 104.608 16.9 49.007 3.641 4160.1 1338.6 7282 69308 87210 2366.9 31.046 103.680 17.1 243000 30.802 193652.98 4326244.50 10567.09 4530010.92 1342170.84 28.828 4228 1995692.89 670760 2438721.71 3697 17.011 10.502 10.664 6910 5634 3628 10.545 6649 48.627853 5070 13.723014 43.362777 17.703374 1806.759 OpenBenchmarking.org
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency New Default - Generic Retpolines AMD Retpolines Former Default 3 6 9 12 15 SE +/- 0.094, N = 12 SE +/- 0.099, N = 12 9.641 9.590 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write New Default - Generic Retpolines AMD Retpolines Former Default 2K 4K 6K 8K 10K SE +/- 102.24, N = 12 SE +/- 108.62, N = 12 10383 10440 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency New Default - Generic Retpolines AMD Retpolines Former Default 0.0383 0.0766 0.1149 0.1532 0.1915 SE +/- 0.001, N = 12 SE +/- 0.002, N = 12 0.170 0.169 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only New Default - Generic Retpolines AMD Retpolines Former Default 60K 120K 180K 240K 300K SE +/- 2460.01, N = 12 SE +/- 3223.57, N = 12 295179 295730 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.2.0 New Default - Generic Retpolines AMD Retpolines Former Default 30K 60K 90K 120K 150K SE +/- 1054.95, N = 10 SE +/- 1055.00, N = 15 136793.59 142573.34 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
WireGuard + Linux Networking Stack Stress Test OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test New Default - Generic Retpolines AMD Retpolines Former Default 60 120 180 240 300 SE +/- 1.39, N = 3 SE +/- 0.99, N = 3 257.10 248.76
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed AMD Retpolines Former Default New Default - Generic Retpolines 800 1600 2400 3200 4000 SE +/- 14.48, N = 15 SE +/- 18.20, N = 15 3668.5 3694.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed New Default - Generic Retpolines AMD Retpolines Former Default 12 24 36 48 60 SE +/- 0.47, N = 15 SE +/- 0.45, N = 15 51.6 51.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 AMD Retpolines Former Default New Default - Generic Retpolines 3000M 6000M 9000M 12000M 15000M SE +/- 9115647.24, N = 3 SE +/- 6459514.72, N = 3 13234833737 13238722860 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed New Default - Generic Retpolines AMD Retpolines Former Default 3K 6K 9K 12K 15K SE +/- 24.84, N = 15 SE +/- 22.12, N = 3 14455.1 14817.3 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed New Default - Generic Retpolines AMD Retpolines Former Default 14 28 42 56 70 SE +/- 0.47, N = 15 SE +/- 0.30, N = 3 61.24 61.36 1. (CC) gcc options: -O3
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency New Default - Generic Retpolines AMD Retpolines Former Default 0.0745 0.149 0.2235 0.298 0.3725 SE +/- 0.004, N = 4 SE +/- 0.000, N = 3 0.331 0.330 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only AMD Retpolines Former Default New Default - Generic Retpolines 60K 120K 180K 240K 300K SE +/- 303.18, N = 3 SE +/- 3587.18, N = 4 302399 302523 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Writes AMD Retpolines Former Default New Default - Generic Retpolines 20K 40K 60K 80K 100K SE +/- 518.75, N = 3 SE +/- 31.48, N = 3 85956 86420
Hackbench Count: 32 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process New Default - Generic Retpolines AMD Retpolines Former Default 30 60 90 120 150 SE +/- 0.30, N = 3 SE +/- 0.59, N = 3 119.83 117.98 1. (CC) gcc options: -lpthread
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile AMD Retpolines Former Default New Default - Generic Retpolines 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.22, N = 3 111.58 111.51
ebizzy OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 AMD Retpolines Former Default New Default - Generic Retpolines 130K 260K 390K 520K 650K SE +/- 6095.03, N = 15 SE +/- 5150.50, N = 15 596554 619271 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
Flexible IO Tester Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.29 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory New Default - Generic Retpolines AMD Retpolines Former Default 50K 100K 150K 200K 250K SE +/- 3027.60, N = 15 SE +/- 2958.04, N = 4 223933 229500 1. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
Apache HTTP Server Concurrent Requests: 500 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 500 New Default - Generic Retpolines AMD Retpolines Former Default 20K 40K 60K 80K 100K SE +/- 264.49, N = 3 SE +/- 149.43, N = 3 80298.15 80970.15 1. (CC) gcc options: -shared -fPIC -O2 -pthread
nginx Concurrent Requests: 200 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 200 AMD Retpolines Former Default New Default - Generic Retpolines 50K 100K 150K 200K 250K SE +/- 466.89, N = 3 SE +/- 275.98, N = 3 206147.39 213684.40 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 100 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 100 AMD Retpolines Former Default New Default - Generic Retpolines 50K 100K 150K 200K 250K SE +/- 369.20, N = 3 SE +/- 1627.81, N = 3 207615.65 215190.56 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
Apache HTTP Server Concurrent Requests: 200 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 200 New Default - Generic Retpolines AMD Retpolines Former Default 20K 40K 60K 80K 100K SE +/- 557.73, N = 3 SE +/- 123.84, N = 3 86362.18 86408.48 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Apache HTTP Server Concurrent Requests: 100 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 100 New Default - Generic Retpolines AMD Retpolines Former Default 20K 40K 60K 80K 100K SE +/- 56.43, N = 3 SE +/- 311.80, N = 3 82500.75 83397.57 1. (CC) gcc options: -shared -fPIC -O2 -pthread
nginx Concurrent Requests: 20 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 20 AMD Retpolines Former Default New Default - Generic Retpolines 50K 100K 150K 200K 250K SE +/- 247.73, N = 3 SE +/- 627.93, N = 3 210605.86 215287.79 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: In-Memory Database Shootout AMD Retpolines Former Default New Default - Generic Retpolines 1000 2000 3000 4000 5000 SE +/- 64.75, N = 3 SE +/- 22.81, N = 3 4878.7 4788.2 MIN: 4512.55 / MAX: 5542.48 MIN: 4452.21 / MAX: 5160.31
InfluxDB Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 AMD Retpolines Former Default New Default - Generic Retpolines 300K 600K 900K 1200K 1500K SE +/- 2326.89, N = 3 SE +/- 1561.10, N = 3 1323460.2 1326859.1
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.16 Build: defconfig New Default - Generic Retpolines AMD Retpolines Former Default 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 78.62 78.59
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark New Default - Generic Retpolines AMD Retpolines Former Default 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 11.26 11.31
Memtier_benchmark Protocol: Redis OpenBenchmarking.org Ops/sec, More Is Better Memtier_benchmark 1.3 Protocol: Redis AMD Retpolines Former Default New Default - Generic Retpolines 300K 600K 900K 1200K 1500K SE +/- 1363.28, N = 3 SE +/- 3316.11, N = 3 1313054.11 1324327.32 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing New Default - Generic Retpolines AMD Retpolines Former Default 400K 800K 1200K 1600K 2000K SE +/- 24226.58, N = 3 SE +/- 20451.18, N = 4 1734878 1746524 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Sockperf Test: Throughput OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.7 Test: Throughput New Default - Generic Retpolines AMD Retpolines Former Default 130K 260K 390K 520K 650K SE +/- 4906.55, N = 25 SE +/- 5255.38, N = 25 539724 587523 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
InfluxDB Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 New Default - Generic Retpolines AMD Retpolines Former Default 400K 800K 1200K 1600K 2000K SE +/- 3111.87, N = 3 SE +/- 1145.84, N = 3 1638195.7 1639910.0
Hackbench Count: 16 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread New Default - Generic Retpolines AMD Retpolines Former Default 14 28 42 56 70 SE +/- 0.19, N = 3 SE +/- 0.11, N = 3 62.20 62.03 1. (CC) gcc options: -lpthread
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.3.9 Time To Compile New Default - Generic Retpolines AMD Retpolines Former Default 14 28 42 56 70 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 61.69 61.10
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill New Default - Generic Retpolines AMD Retpolines Former Default 130K 260K 390K 520K 650K SE +/- 5871.64, N = 3 SE +/- 3544.93, N = 3 605572 617250 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random New Default - Generic Retpolines AMD Retpolines Former Default 90K 180K 270K 360K 450K SE +/- 2036.18, N = 3 SE +/- 1232.53, N = 3 393101 398526 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random AMD Retpolines Former Default New Default - Generic Retpolines 300K 600K 900K 1200K 1500K SE +/- 6491.63, N = 3 SE +/- 2292.69, N = 3 1386586 1391000 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read New Default - Generic Retpolines AMD Retpolines Former Default 13M 26M 39M 52M 65M SE +/- 195189.61, N = 3 SE +/- 78029.55, N = 3 61331721 61586232 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 New Default - Generic Retpolines AMD Retpolines Former Default 30K 60K 90K 120K 150K SE +/- 7.94, N = 3 SE +/- 8.58, N = 3 155003.1 155031.8 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 New Default - Generic Retpolines AMD Retpolines Former Default 500 1000 1500 2000 2500 SE +/- 2.17, N = 3 SE +/- 0.15, N = 3 2372.3 2374.1 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Hackbench Count: 16 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process New Default - Generic Retpolines AMD Retpolines Former Default 13 26 39 52 65 SE +/- 0.16, N = 3 SE +/- 0.23, N = 3 58.78 58.36 1. (CC) gcc options: -lpthread
LevelDB Benchmark: Random Delete OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Delete New Default - Generic Retpolines AMD Retpolines Former Default 20 40 60 80 100 SE +/- 0.42, N = 3 SE +/- 1.08, N = 4 99.88 98.95 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed New Default - Generic Retpolines AMD Retpolines Former Default 3K 6K 9K 12K 15K SE +/- 17.39, N = 3 SE +/- 61.43, N = 3 14586.2 14807.4 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 9 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed New Default - Generic Retpolines AMD Retpolines Former Default 13 26 39 52 65 SE +/- 0.63, N = 3 SE +/- 0.04, N = 3 59.57 59.69 1. (CC) gcc options: -O3
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 10.2 Time To Compile AMD Retpolines Former Default New Default - Generic Retpolines 12 24 36 48 60 SE +/- 0.16, N = 3 SE +/- 0.13, N = 3 55.03 54.96
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Sequential Fill AMD Retpolines Former Default New Default - Generic Retpolines 20 40 60 80 100 SE +/- 0.61, N = 3 SE +/- 0.43, N = 3 106.95 105.12 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Sequential Fill AMD Retpolines Former Default New Default - Generic Retpolines 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 16.5 16.9 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite AMD Retpolines Former Default New Default - Generic Retpolines 20 40 60 80 100 SE +/- 0.70, N = 14 SE +/- 0.87, N = 15 104.61 103.37 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite AMD Retpolines Former Default New Default - Generic Retpolines 4 8 12 16 20 SE +/- 0.11, N = 14 SE +/- 0.15, N = 15 16.9 17.1 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 New Default - Generic Retpolines AMD Retpolines Former Default 11 22 33 44 55 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 50.48 49.01 1. (CC) gcc options: -O2 -ldl -lz -lpthread
Sockperf Test: Latency Under Load OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.7 Test: Latency Under Load New Default - Generic Retpolines AMD Retpolines Former Default 0.8249 1.6498 2.4747 3.2996 4.1245 SE +/- 0.035, N = 5 SE +/- 0.033, N = 25 3.666 3.641 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed AMD Retpolines Former Default New Default - Generic Retpolines 900 1800 2700 3600 4500 SE +/- 4.29, N = 3 SE +/- 54.59, N = 3 4160.1 4255.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed AMD Retpolines Former Default New Default - Generic Retpolines 300 600 900 1200 1500 SE +/- 10.10, N = 3 SE +/- 3.86, N = 3 1338.6 1343.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
PostMark Disk Transaction Performance OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance New Default - Generic Retpolines AMD Retpolines Former Default 1600 3200 4800 6400 8000 SE +/- 70.00, N = 3 6944 7282 1. (CC) gcc options: -O3
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Decompression Rating AMD Retpolines Former Default New Default - Generic Retpolines 15K 30K 45K 60K 75K SE +/- 59.62, N = 5 SE +/- 8.76, N = 3 69308 69393 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Compression Rating New Default - Generic Retpolines AMD Retpolines Former Default 20K 40K 60K 80K 100K SE +/- 438.70, N = 3 SE +/- 870.19, N = 5 86357 87210 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Finagle HTTP Requests New Default - Generic Retpolines AMD Retpolines Former Default 500 1000 1500 2000 2500 SE +/- 24.88, N = 3 SE +/- 15.84, N = 3 2378.7 2366.9 MIN: 2177.37 / MAX: 2449.07 MIN: 2178.29 / MAX: 2434.21
Hackbench Count: 8 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Thread New Default - Generic Retpolines AMD Retpolines Former Default 7 14 21 28 35 SE +/- 0.16, N = 3 SE +/- 0.14, N = 3 31.28 31.05 1. (CC) gcc options: -lpthread
LevelDB Benchmark: Random Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Fill AMD Retpolines Former Default New Default - Generic Retpolines 20 40 60 80 100 SE +/- 1.34, N = 3 SE +/- 0.90, N = 15 103.68 103.22 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
LevelDB Benchmark: Random Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Random Fill AMD Retpolines Former Default New Default - Generic Retpolines 4 8 12 16 20 SE +/- 0.22, N = 3 SE +/- 0.15, N = 15 17.1 17.2 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
Flexible IO Tester Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.29 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory New Default - Generic Retpolines AMD Retpolines Former Default 50K 100K 150K 200K 250K SE +/- 333.33, N = 3 SE +/- 577.35, N = 3 239667 243000 1. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
Timed MPlayer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed MPlayer Compilation 1.5 Time To Compile AMD Retpolines Former Default New Default - Generic Retpolines 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 30.80 30.71
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: SENDFILE AMD Retpolines Former Default New Default - Generic Retpolines 40K 80K 120K 160K 200K SE +/- 443.51, N = 3 SE +/- 510.20, N = 3 193652.98 200771.29 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Context Switching New Default - Generic Retpolines AMD Retpolines Former Default 900K 1800K 2700K 3600K 4500K SE +/- 18653.91, N = 3 SE +/- 26201.07, N = 3 4296558.49 4326244.50 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Socket Activity AMD Retpolines Former Default New Default - Generic Retpolines 2K 4K 6K 8K 10K SE +/- 13.84, N = 3 SE +/- 12.31, N = 3 10567.09 10751.13 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: System V Message Passing New Default - Generic Retpolines AMD Retpolines Former Default 1000K 2000K 3000K 4000K 5000K SE +/- 16005.42, N = 3 SE +/- 10539.69, N = 3 4521841.84 4530010.92 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Semaphores New Default - Generic Retpolines AMD Retpolines Former Default 300K 600K 900K 1200K 1500K SE +/- 4542.73, N = 3 SE +/- 10886.78, N = 3 1326767.92 1342170.84 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lsctp -lz -ldl -pthread -lc -latomic
Hackbench Count: 8 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Process New Default - Generic Retpolines AMD Retpolines Former Default 7 14 21 28 35 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 29.95 28.83 1. (CC) gcc options: -lpthread
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 New Default - Generic Retpolines AMD Retpolines Former Default 900 1800 2700 3600 4500 SE +/- 26.89, N = 4 SE +/- 25.85, N = 16 4268 4228
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SET AMD Retpolines Former Default New Default - Generic Retpolines 400K 800K 1200K 1600K 2000K SE +/- 18125.41, N = 7 SE +/- 2446.32, N = 3 1995692.89 1998825.92 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Sequential Fill New Default - Generic Retpolines AMD Retpolines Former Default 140K 280K 420K 560K 700K SE +/- 1947.52, N = 3 SE +/- 3478.74, N = 3 657523 670760 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: GET AMD Retpolines Former Default New Default - Generic Retpolines 500K 1000K 1500K 2000K 2500K SE +/- 22769.87, N = 6 SE +/- 15897.48, N = 3 2438721.71 2506720.25 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython New Default - Generic Retpolines AMD Retpolines Former Default 800 1600 2400 3200 4000 SE +/- 28.58, N = 4 SE +/- 24.35, N = 20 3761 3697
LevelDB Benchmark: Seek Random OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Seek Random New Default - Generic Retpolines AMD Retpolines Former Default 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 17.14 17.01 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
LevelDB Benchmark: Hot Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Hot Read New Default - Generic Retpolines AMD Retpolines Former Default 3 6 9 12 15 SE +/- 0.11, N = 6 SE +/- 0.05, N = 3 10.54 10.50 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
Parallel BZIP2 Compression FreeBSD-13.0-RELEASE-amd64-memstick.img Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression New Default - Generic Retpolines AMD Retpolines Former Default 3 6 9 12 15 SE +/- 0.11, N = 6 SE +/- 0.15, N = 3 10.78 10.66 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
Node.js Express HTTP Load Test OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test New Default - Generic Retpolines AMD Retpolines Former Default 1500 3000 4500 6000 7500 SE +/- 34.82, N = 3 SE +/- 43.97, N = 3 6692 6910
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans New Default - Generic Retpolines AMD Retpolines Former Default 1200 2400 3600 4800 6000 SE +/- 34.00, N = 4 SE +/- 38.99, N = 4 5762 5634
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap New Default - Generic Retpolines AMD Retpolines Former Default 800 1600 2400 3200 4000 SE +/- 40.14, N = 4 SE +/- 33.50, N = 4 3660 3628
LevelDB Benchmark: Random Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Read New Default - Generic Retpolines AMD Retpolines Former Default 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 10.58 10.55 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.0 Model: Church Facade New Default - Generic Retpolines AMD Retpolines Former Default 1400 2800 4200 5600 7000 SE +/- 17.74, N = 3 SE +/- 5.21, N = 3 6697 6649 1. (CXX) g++ options: -O3
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs New Default - Generic Retpolines AMD Retpolines Former Default 11 22 33 44 55 SE +/- 0.10, N = 3 SE +/- 0.53, N = 5 49.36 48.63 1. (CC) gcc options: -lm
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.0 Model: Lion New Default - Generic Retpolines AMD Retpolines Former Default 1100 2200 3300 4400 5500 SE +/- 7.37, N = 3 SE +/- 0.88, N = 3 5088 5070 1. (CXX) g++ options: -O3
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files New Default - Generic Retpolines AMD Retpolines Former Default 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 14.71 13.72 1. (CC) gcc options: -lm
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes AMD Retpolines Former Default New Default - Generic Retpolines 10 20 30 40 50 SE +/- 0.54, N = 3 SE +/- 0.23, N = 3 43.36 43.14 1. (CC) gcc options: -lm
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads AMD Retpolines Former Default New Default - Generic Retpolines 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 17.70 17.38 1. (CC) gcc options: -lm
LevelDB Benchmark: Fill Sync OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync New Default - Generic Retpolines AMD Retpolines Former Default 400 800 1200 1600 2000 SE +/- 8.19, N = 3 SE +/- 3.85, N = 3 1820.49 1806.76 1. (CXX) g++ options: -O3 -lsnappy -ltcmalloc -lpthread
Phoronix Test Suite v10.8.4