Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1803219-FO-1803193FO28 CentOS 7 Mitigation Tests - Phoronix Test Suite CentOS 7 Mitigation Tests Comparison with older Xeon
HTML result view exported from: https://openbenchmarking.org/result/1803219-FO-1803193FO28&sor&grs .
Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Default No Mitigation Default No Mitigation Default Xeon Xeon EPYC EPYC C240M4-E52650v4 2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads) TYAN S7106 (V1.00 BIOS) Intel Device 2020 95232MB 256GB Samsung SSD 850 + 2000GB Seagate ST2000DM006-2DM1 + 2 x 120GB TOSHIBA-TR150 LLVMpipe VE228 Intel I210 Gigabit Connection CentOS Linux 7 3.10.0-693.21.1.el7.x86_64 (x86_64) GNOME Shell 3.22.3 X Server 1.19.3 modesetting 1.19.3 2.1 Mesa 17.0.1 Gallium 0.4 (LLVM 3.9 256 bits) GCC 4.8.5 20150623 xfs 1920x1080 AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads) TYAN B8026T70AE24HR (V0.05.B10 BIOS) AMD Device 1450 129024MB 280GB INTEL SSDPE21D280GA Broadcom Limited NetXtreme BCM5720 Gigabit PCIe 2.1 Mesa 17.0.1 Gallium 0.4 (LLVM 3.9 128 bits) 2 x Intel Xeon E5-2650 v4 @ 2.90GHz (24 Cores / 48 Threads) Cisco s UCSC-C220-M4S (C220M4.3.0.3c.0.0831170216 BIOS) 299GB UCSC-MRAID12G mgadrmfb 1024x768 OpenBenchmarking.org Compiler Details - --build=x86_64-redhat-linux --disable-libgcj --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,objc,obj-c++,java,fortran,ada,go,lto --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-linker-hash-style=gnu --with-tune=generic Disk Details - Default: Xeon: CFQ / attr2,inode64,noquota,relatime,rw,seclabel - No Mitigation: Xeon: CFQ / attr2,inode64,noquota,relatime,rw,seclabel - Default: EPYC: none / attr2,inode64,noquota,relatime,rw,seclabel - No Mitigation: EPYC: none / attr2,inode64,noquota,relatime,rw,seclabel - Default: C240M4-E52650v4: DEADLINE / attr2,inode64,noquota,relatime,rw,seclabel Processor Details - Default: Xeon: Scaling Governor: intel_pstate powersave - No Mitigation: Xeon: Scaling Governor: intel_pstate powersave - Default: EPYC: Scaling Governor: acpi-cpufreq conservative - No Mitigation: EPYC: Scaling Governor: acpi-cpufreq conservative - Default: C240M4-E52650v4: Scaling Governor: intel_pstate performance Python Details - Python 2.7.5 Security Details - Default: Xeon, No Mitigation: Xeon, Default: EPYC, No Mitigation: EPYC: SELinux Protection
fio: Seq Read - Linux AIO - No - Yes - 2MB - Default Test Directory iozone: 4Kb - 8GB - Write Performance blogbench: Write systemd-boot-total: Firmware systemd-boot-total: Loader pgbench: Buffer Test - Single Thread - Read Write systemd-boot-total: Userspace pgbench: Buffer Test - Normal Load - Read Write stress-ng: Context Switching fio: Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directory systemd-boot-total: Total fio: Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directory fio: Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directory pgbench: Buffer Test - Normal Load - Read Only compilebench: Initial Create systemd-boot-total: Kernel blogbench: Read build-linux-kernel: Time To Compile pgbench: Buffer Test - Single Thread - Read Only redis: LPUSH stress-ng: System V Message Passing git: Time To Complete Common Git Commands compilebench: Compile hackbench: 16 - Thread netperf: 192.168.1.55 - TCP Stream - Client To Server - 60 Seconds netperf: 192.168.1.55 - TCP Stream - Server To Client - 60 Seconds netperf: 192.168.1.55 - TCP Send File - 60 Seconds netperf: 192.168.1.55 - UDP Stream - Server To Client - 10G - 60 Seconds schbench: 8 - 6 schbench: 8 - 4 compress-rar: Linux Source Tree Archiving To RAR stress-ng: Socket Activity stress-ng: Semaphores stress-ng: Forking redis: SET redis: GET redis: SADD redis: LPOP hackbench: 16 - Process ebizzy: netperf: 192.168.1.55 - UDP Request Response - 60 Seconds netperf: 192.168.1.55 - TCP Request Response - 60 Seconds compilebench: Read Compiled Tree sqlite: Timed SQLite Insertions Default No Mitigation Default No Mitigation Default Xeon Xeon EPYC EPYC C240M4-E52650v4 534 366.83 10718 2487421 2310 454.83 44463 8904.44 15540101.78 516 2538816 516 534 589604.88 222.55 2948 1347194 25.82 19183.95 1105101.92 5535241.82 6.23 1460.15 29.23 788.06 941.35 941.44 961.78 119 131 163.79 3300.35 229301.54 64139.63 1232095.75 1610474.09 1360277.75 1605734.42 25.31 496979 748.07 715.57 1786.12 47.17 533 379.23 10960 463.33 18428 8863.35 17854342.78 515 23018 516 533 606672.77 253.30 2791 1419432 24.94 20927.92 1155179.38 5877638.95 6.24 1536.84 25.81 788.10 941.27 941.38 961.71 122 107 169.81 3297.64 247476.16 64683.94 1308916.96 1609005.09 1421813.12 1449609.17 24.07 488760 835.27 795.77 2097.64 47.01 2616 815.37 12734 44496 5492 2035.47 52882 19123.50 14023842.08 2179 106009 2178 2614 350860.98 155.50 1826 1077180 31.86 13418.48 790912.27 4828921.70 7.52 1275.37 30.36 786.77 940.85 941.15 961.65 394 379 212.20 3409.01 237838.14 42635.50 899226.97 1153713.90 1000430.87 1167236.62 17.74 1128609 325.74 528.16 1461.13 6.56 2617 851.68 13165 46473 13432 2056.96 20117 18912.24 13329232.97 2179 83138 2178 2606 352912.32 162.03 1812 1071852 32.01 13933.94 803664.96 4984809.43 7.60 1376.46 29.18 788.33 940.67 941.20 961.69 375 380 207.09 3413.08 241176.07 45411.65 919106.95 1143321.88 1026789.50 832909.06 17.22 1124203 365.43 397.55 1539.24 6.28 298 115.20 2162 36813 8375392.54 144 41985 192 252 2444 1686908 39.20 936269.56 4525754.96 7.93 25.21 4557 76 9337.64 373271.38 77255.48 1091377.62 1437054.88 1202903.54 1487480.25 24.47 494409 225.54 OpenBenchmarking.org
Flexible IO Tester Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory No Mitigation Default OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC Xeon C240M4-E52650v4 600 1200 1800 2400 3000 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 2617 533 2616 534 298 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lrt -laio -lm -lpthread -ldl
IOzone Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance No Mitigation Default OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance EPYC Xeon C240M4-E52650v4 200 400 600 800 1000 SE +/- 17.05, N = 3 SE +/- 5.52, N = 3 SE +/- 14.27, N = 4 SE +/- 0.82, N = 3 SE +/- 0.88, N = 3 851.68 379.23 815.37 366.83 115.20 1. (CC) gcc options: -O3
BlogBench Test: Write No Mitigation Default OpenBenchmarking.org Final Score, More Is Better BlogBench 1.0 Test: Write EPYC Xeon C240M4-E52650v4 3K 6K 9K 12K 15K SE +/- 31.67, N = 3 SE +/- 87.79, N = 3 SE +/- 105.36, N = 3 SE +/- 11.53, N = 3 SE +/- 14.77, N = 3 13165 10960 12734 10718 2162 1. (CC) gcc options: -O2 -pthread
Systemd Total Boot Time Test: Firmware Default No Mitigation OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Firmware EPYC Xeon 500K 1000K 1500K 2000K 2500K 44496 2487421 46473
Systemd Total Boot Time Test: Loader Default No Mitigation OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Loader Xeon EPYC 3K 6K 9K 12K 15K 2310 5492 13432
PostgreSQL pgbench Scaling: Buffer Test - Test: Single Thread - Mode: Read Write No Mitigation Default OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Single Thread - Mode: Read Write EPYC Xeon 400 800 1200 1600 2000 SE +/- 29.73, N = 6 SE +/- 3.76, N = 3 SE +/- 35.02, N = 3 SE +/- 3.02, N = 3 2056.96 463.33 2035.47 454.83 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Systemd Total Boot Time Test: Userspace No Mitigation Default OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Userspace Xeon EPYC C240M4-E52650v4 11K 22K 33K 44K 55K 18428 20117 36813 44463 52882
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Default No Mitigation OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write EPYC Xeon 4K 8K 12K 16K 20K SE +/- 273.59, N = 5 SE +/- 8.89, N = 3 SE +/- 355.75, N = 3 SE +/- 37.58, N = 3 19123.50 8904.44 18912.24 8863.35 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Stress-NG Test: Context Switching No Mitigation Default OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Xeon EPYC C240M4-E52650v4 4M 8M 12M 16M 20M SE +/- 278249.11, N = 3 SE +/- 88330.28, N = 3 SE +/- 285738.13, N = 6 SE +/- 214794.01, N = 3 SE +/- 145783.18, N = 6 17854342.78 13329232.97 15540101.78 14023842.08 8375392.54 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lpthread -laio -lc
Flexible IO Tester Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory No Mitigation Default OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC Xeon C240M4-E52650v4 500 1000 1500 2000 2500 SE +/- 1.53, N = 3 2179 515 2179 516 144 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lrt -laio -lm -lpthread -ldl
Systemd Total Boot Time Test: Total No Mitigation Default OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Total Xeon C240M4-E52650v4 EPYC 500K 1000K 1500K 2000K 2500K 23018 83138 41985 106009 2538816
Flexible IO Tester Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory No Mitigation Default OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC Xeon C240M4-E52650v4 500 1000 1500 2000 2500 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 2178 516 2178 516 192 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lrt -laio -lm -lpthread -ldl
Flexible IO Tester Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory Default No Mitigation OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.1 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC Xeon C240M4-E52650v4 600 1200 1800 2400 3000 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 9.33, N = 3 2614 534 252 2606 533 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -lrt -laio -lm -lpthread -ldl
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only No Mitigation Default OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only Xeon EPYC 130K 260K 390K 520K 650K SE +/- 10702.56, N = 6 SE +/- 2073.02, N = 3 SE +/- 3440.47, N = 3 SE +/- 379.13, N = 3 606672.77 352912.32 589604.88 350860.98 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Compile Bench Test: Initial Create No Mitigation Default OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Xeon EPYC 60 120 180 240 300 SE +/- 3.53, N = 3 SE +/- 1.94, N = 3 SE +/- 1.38, N = 3 SE +/- 0.64, N = 3 253.30 162.03 222.55 155.50
Systemd Total Boot Time Test: Kernel No Mitigation Default OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Kernel EPYC C240M4-E52650v4 Xeon 600 1200 1800 2400 3000 1812 2791 1826 2444 2948
BlogBench Test: Read Default No Mitigation OpenBenchmarking.org Final Score, More Is Better BlogBench 1.0 Test: Read C240M4-E52650v4 Xeon EPYC 400K 800K 1200K 1600K 2000K SE +/- 10749.52, N = 3 SE +/- 12522.98, N = 3 SE +/- 9564.08, N = 3 SE +/- 23638.75, N = 4 SE +/- 5471.69, N = 3 1686908 1347194 1077180 1419432 1071852 1. (CC) gcc options: -O2 -pthread
Timed Linux Kernel Compilation Time To Compile No Mitigation Default OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.13 Time To Compile Xeon EPYC C240M4-E52650v4 9 18 27 36 45 SE +/- 0.51, N = 6 SE +/- 0.61, N = 6 SE +/- 0.60, N = 6 SE +/- 0.68, N = 6 SE +/- 0.65, N = 6 24.94 32.01 25.82 31.86 39.20
PostgreSQL pgbench Scaling: Buffer Test - Test: Single Thread - Mode: Read Only No Mitigation Default OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Single Thread - Mode: Read Only Xeon EPYC 4K 8K 12K 16K 20K SE +/- 47.53, N = 3 SE +/- 159.76, N = 3 SE +/- 152.63, N = 3 SE +/- 64.88, N = 3 20927.92 13933.94 19183.95 13418.48 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Redis Test: LPUSH No Mitigation Default OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: LPUSH Xeon C240M4-E52650v4 EPYC 200K 400K 600K 800K 1000K SE +/- 445.00, N = 3 SE +/- 13536.05, N = 3 SE +/- 8460.85, N = 3 SE +/- 15555.64, N = 3 SE +/- 11432.55, N = 5 1155179.38 803664.96 1105101.92 936269.56 790912.27 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Stress-NG Test: System V Message Passing No Mitigation Default OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing Xeon EPYC C240M4-E52650v4 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 23577.80, N = 3 SE +/- 17091.59, N = 3 SE +/- 40096.53, N = 3 SE +/- 5394.60, N = 3 SE +/- 44382.75, N = 3 5877638.95 4984809.43 5535241.82 4828921.70 4525754.96 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lpthread -laio -lc
Git Time To Complete Common Git Commands Default No Mitigation OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Xeon EPYC C240M4-E52650v4 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.12, N = 4 SE +/- 0.06, N = 3 SE +/- 0.09, N = 6 SE +/- 0.10, N = 3 6.23 7.52 7.93 6.24 7.60 1. git version 1.8.3.1
Compile Bench Test: Compile No Mitigation Default OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile Xeon EPYC 300 600 900 1200 1500 SE +/- 2.50, N = 3 SE +/- 13.70, N = 3 SE +/- 22.10, N = 3 SE +/- 3.80, N = 3 1536.84 1376.46 1460.15 1275.37
Hackbench Count: 16 - Type: Thread Default No Mitigation OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread C240M4-E52650v4 Xeon EPYC 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.44, N = 3 SE +/- 0.58, N = 6 SE +/- 0.43, N = 6 SE +/- 0.49, N = 3 25.21 29.23 30.36 25.81 29.18 1. (CC) gcc options: -lpthread
Netperf Server: 192.168.1.55 - Test: TCP Stream - Client To Server - Duration: 60 Seconds No Mitigation Default OpenBenchmarking.org Megabits/sec Throughput, More Is Better Netperf 2.7.0 Server: 192.168.1.55 - Test: TCP Stream - Client To Server - Duration: 60 Seconds EPYC Xeon 200 400 600 800 1000 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 0.10, N = 3 SE +/- 1.43, N = 3 788.33 788.10 788.06 786.77 1. (CC) gcc options: -O3 -march=native -lm
Netperf Server: 192.168.1.55 - Test: TCP Stream - Server To Client - Duration: 60 Seconds Default No Mitigation OpenBenchmarking.org Megabits/sec Throughput, More Is Better Netperf 2.7.0 Server: 192.168.1.55 - Test: TCP Stream - Server To Client - Duration: 60 Seconds Xeon EPYC 200 400 600 800 1000 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.36, N = 3 941.35 940.85 941.27 940.67 1. (CC) gcc options: -O3 -march=native -lm
Netperf Server: 192.168.1.55 - Test: TCP Send File - Duration: 60 Seconds Default No Mitigation OpenBenchmarking.org Megabits/sec Throughput, More Is Better Netperf 2.7.0 Server: 192.168.1.55 - Test: TCP Send File - Duration: 60 Seconds Xeon EPYC 200 400 600 800 1000 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 941.44 941.15 941.38 941.20 1. (CC) gcc options: -O3 -march=native -lm
Netperf Server: 192.168.1.55 - Test: UDP Stream - Server To Client - 10G - Duration: 60 Seconds Default No Mitigation OpenBenchmarking.org Megabits/sec Throughput, More Is Better Netperf 2.7.0 Server: 192.168.1.55 - Test: UDP Stream - Server To Client - 10G - Duration: 60 Seconds Xeon EPYC 200 400 600 800 1000 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 961.78 961.65 961.71 961.69 1. (CC) gcc options: -O3 -march=native -lm
Schbench Message Threads: 8 - Workers Per Message Thread: 6 Default No Mitigation OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 8 - Workers Per Message Thread: 6 Xeon EPYC C240M4-E52650v4 1000 2000 3000 4000 5000 SE +/- 3.22, N = 6 SE +/- 18.94, N = 6 SE +/- 243.84, N = 6 SE +/- 4.09, N = 6 SE +/- 4.06, N = 3 119 394 4557 122 375 1. (CC) gcc options: -O2 -lpthread
Schbench Message Threads: 8 - Workers Per Message Thread: 4 Default No Mitigation OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 8 - Workers Per Message Thread: 4 C240M4-E52650v4 Xeon EPYC 80 160 240 320 400 SE +/- 1.78, N = 6 SE +/- 15.02, N = 6 SE +/- 2.00, N = 3 SE +/- 1.20, N = 3 SE +/- 3.38, N = 3 76 131 379 107 380 1. (CC) gcc options: -O2 -lpthread
RAR Compression Linux Source Tree Archiving To RAR Default No Mitigation OpenBenchmarking.org Seconds, Fewer Is Better RAR Compression 5.6.b1 Linux Source Tree Archiving To RAR Xeon EPYC 50 100 150 200 250 SE +/- 4.56, N = 6 SE +/- 3.34, N = 6 SE +/- 1.73, N = 3 SE +/- 2.52, N = 3 163.79 212.20 169.81 207.09
Stress-NG Test: Socket Activity Default No Mitigation OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity C240M4-E52650v4 EPYC Xeon 2K 4K 6K 8K 10K SE +/- 169.85, N = 3 SE +/- 2153.81, N = 6 SE +/- 2085.05, N = 6 SE +/- 2156.28, N = 6 SE +/- 2083.35, N = 6 9337.64 3409.01 3300.35 3413.08 3297.64 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Semaphores Default No Mitigation OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores C240M4-E52650v4 Xeon EPYC 80K 160K 240K 320K 400K SE +/- 9167.64, N = 6 SE +/- 493.46, N = 3 SE +/- 1445.04, N = 3 SE +/- 2801.19, N = 3 SE +/- 2408.75, N = 3 373271.38 237838.14 229301.54 247476.16 241176.07 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Forking Default No Mitigation OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Forking C240M4-E52650v4 Xeon EPYC 17K 34K 51K 68K 85K SE +/- 582.49, N = 3 SE +/- 1408.35, N = 6 SE +/- 1430.46, N = 6 SE +/- 863.59, N = 6 SE +/- 1321.55, N = 6 77255.48 64139.63 42635.50 64683.94 45411.65 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lpthread -laio -lc
Redis Test: SET No Mitigation Default OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SET Xeon C240M4-E52650v4 EPYC 300K 600K 900K 1200K 1500K SE +/- 19675.61, N = 3 SE +/- 22849.80, N = 6 SE +/- 6232.77, N = 3 SE +/- 6271.05, N = 3 SE +/- 15054.31, N = 4 1308916.96 919106.95 1232095.75 1091377.62 899226.97 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Redis Test: GET Default No Mitigation OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: GET Xeon C240M4-E52650v4 EPYC 300K 600K 900K 1200K 1500K SE +/- 54335.61, N = 6 SE +/- 13971.13, N = 3 SE +/- 33824.99, N = 6 SE +/- 18583.91, N = 3 SE +/- 17368.61, N = 4 1610474.09 1437054.88 1153713.90 1609005.09 1143321.88 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Redis Test: SADD No Mitigation Default OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SADD Xeon C240M4-E52650v4 EPYC 300K 600K 900K 1200K 1500K SE +/- 2935.21, N = 3 SE +/- 6981.54, N = 3 SE +/- 34509.71, N = 6 SE +/- 3170.45, N = 3 SE +/- 14784.29, N = 3 1421813.12 1026789.50 1360277.75 1202903.54 1000430.87 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Redis Test: LPOP Default No Mitigation OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: LPOP Xeon C240M4-E52650v4 EPYC 300K 600K 900K 1200K 1500K SE +/- 30273.65, N = 6 SE +/- 9525.75, N = 3 SE +/- 14874.04, N = 3 SE +/- 118496.65, N = 6 SE +/- 14323.78, N = 3 1605734.42 1487480.25 1167236.62 1449609.17 832909.06 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Hackbench Count: 16 - Type: Process No Mitigation Default OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process EPYC Xeon C240M4-E52650v4 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.35, N = 3 SE +/- 0.35, N = 6 SE +/- 0.05, N = 3 SE +/- 0.63, N = 6 17.22 24.07 17.74 24.47 25.31 1. (CC) gcc options: -lpthread
ebizzy Default No Mitigation OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 EPYC Xeon C240M4-E52650v4 200K 400K 600K 800K 1000K SE +/- 18137.48, N = 3 SE +/- 6186.16, N = 3 SE +/- 6605.90, N = 3 SE +/- 30623.06, N = 6 SE +/- 7014.28, N = 3 1128609 496979 494409 1124203 488760 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
Netperf Server: 192.168.1.55 - Test: UDP Request Response - Duration: 60 Seconds No Mitigation Default OpenBenchmarking.org Transaction Rate Per Second, More Is Better Netperf 2.7.0 Server: 192.168.1.55 - Test: UDP Request Response - Duration: 60 Seconds Xeon EPYC 200 400 600 800 1000 SE +/- 16.23, N = 3 SE +/- 120.58, N = 6 SE +/- 10.22, N = 3 SE +/- 131.22, N = 6 835.27 365.43 748.07 325.74 1. (CC) gcc options: -O3 -march=native -lm
Netperf Server: 192.168.1.55 - Test: TCP Request Response - Duration: 60 Seconds No Mitigation Default OpenBenchmarking.org Transaction Rate Per Second, More Is Better Netperf 2.7.0 Server: 192.168.1.55 - Test: TCP Request Response - Duration: 60 Seconds Xeon EPYC 200 400 600 800 1000 SE +/- 4.51, N = 3 SE +/- 100.88, N = 6 SE +/- 10.77, N = 4 SE +/- 114.08, N = 6 795.77 397.55 715.57 528.16 1. (CC) gcc options: -O3 -march=native -lm
Compile Bench Test: Read Compiled Tree No Mitigation Default OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree Xeon EPYC 500 1000 1500 2000 2500 SE +/- 53.11, N = 3 SE +/- 25.56, N = 3 SE +/- 67.36, N = 3 SE +/- 42.62, N = 3 2097.64 1539.24 1786.12 1461.13
SQLite Timed SQLite Insertions No Mitigation Default OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.22 Timed SQLite Insertions EPYC Xeon C240M4-E52650v4 50 100 150 200 250 SE +/- 0.32, N = 6 SE +/- 0.12, N = 3 SE +/- 0.36, N = 6 SE +/- 0.09, N = 3 SE +/- 2.75, N = 3 6.28 47.01 6.56 47.17 225.54 1. (CC) gcc options: -O2 -ldl -lpthread
Phoronix Test Suite v10.8.4