merge-2460 2 x AMD Opteron 4386 testing with a ASUS KCMA-D8 v1.0 (4.11-56-g6ffb50080a BIOS) and ASPEED on Debian via the Phoronix Test Suite. NOTE! By putting ram in slots furthest from CPU it crashed less (my motherboard has issues or?) but only runs in 1066Mhz!
HTML result view exported from: https://openbenchmarking.org/result/2411215-EROX-MERGE2449&sor&grs .
Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenCL Compiler File-System Screen Resolution OpenGL 9020 SFF KCMA-D8 KGPE-D16 i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB Intel Core i7-4790K @ 4.40GHz (4 Cores) Dell OptiPlex 7020/9020 SFF [OptiPlex v1.0] (20241008 BIOS) Intel 4th Gen Core DRAM 32GB Western Digital WD_BLACK SN770 250GB Intel Xeon E3-1200 v3/4th Gen Core IGP (1250MHz) Intel Xeon E3-1200 v3/4th DELL U2520D Intel I217-LM Debian 6.11.5-amd64 (x86_64) GNOME Shell 47.0 X Server OpenCL 2.1 AMD-APP (3590.0) GCC 14.2.0 ext4 2560x1440 Intel Core i7-4790K @ 4.40GHz (4 Cores / 8 Threads) Intel HD 4600 HSW GT2 2GB (1250MHz) 6.11.4-amd64 (x86_64) 4.6 Mesa 24.2.4-1 2 x AMD Opteron 4256 EE @ 1.60GHz (16 Cores) ASUS KCMA-D8 v1.0 (4.11-56-g6ffb50080a BIOS) AMD RD890 + SB7x0/SB8x0/SB9x0 4 x 8 GB DDR3-800MT/s Crucial ASPEED AMD SBx00 Azalia BenQ GL2440H 2 x Intel 82574L Debian 13 6.11.5-amd64 (x86_64) GCC 14.2.0 + Clang 16.0.6 1600x900 8 x GB DDR3-533MT/s Kingston 2 x AMD Opteron 4386 @ 3.10GHz (16 Cores) 4 x 8 GB DDR3-533MT/s Crucial Debian GCC 14.2.0 2 x AMD Opteron 6276 @ 2.30GHz (32 Cores) ASUS KGPE-D16 v1.0 (Dasharo coreboot+SeaBIOS v0.4.0 BIOS) 32GB Debian 13 GCC 14.2.0 + Clang 16.0.6 ASUS KGPE-D16 v1.0 (20241008 BIOS) 4 x 16 GB DDR3-800MT/s Samsung M393B2G70QH0-YK0 1280x800 2 x AMD Opteron 6380 @ 2.50GHz (32 Cores) ASUS KGPE-D16 v1.0 (Dasharo coreboot+SeaBIOS v0.4.0 BIOS) 256GB 1600x900 ASUS KGPE-D16 v1.0 (20241008 BIOS) 4 x 16 GB DDR3-800MT/s Samsung M393B2G70QH0-YK0 1280x800 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=3 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/reproducible-path/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/reproducible-path/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details - 9020 SFF: i7-4790k no-smt, 32GB-1600CL9 4x8GB, 9020 SFF: i7-4790k, 32GB-1600CL9 4x8GB, KCMA-D8: 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB, KCMA-D8: 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz, KCMA-D8: 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz, KGPE-D16: 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo, KGPE-D16: 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB, KGPE-D16: 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo, KGPE-D16: 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB: NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - 9020 SFF: i7-4790k no-smt, 32GB-1600CL9 4x8GB: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x28 - 9020 SFF: i7-4790k, 32GB-1600CL9 4x8GB: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x28 - KCMA-D8: 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x600063e - KCMA-D8: 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x600063e - KCMA-D8: 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!): Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x6000852 - KCMA-D8: 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x6000852 - KGPE-D16: 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x600063e - KGPE-D16: 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x600063e - KGPE-D16: 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x6000852 - KGPE-D16: 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x6000852 Security Details - 9020 SFF: i7-4790k no-smt, 32GB-1600CL9 4x8GB: gather_data_sampling: Not affected + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + mmio_stale_data: Unknown: No mitigations + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Mitigation of Microcode + tsx_async_abort: Not affected - 9020 SFF: i7-4790k, 32GB-1600CL9 4x8GB: gather_data_sampling: Not affected + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Unknown: No mitigations + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Mitigation of Microcode + tsx_async_abort: Not affected - KCMA-D8: 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_rstack_overflow: 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; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - KCMA-D8: 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_rstack_overflow: 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; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - KCMA-D8: 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!): gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_rstack_overflow: 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; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - KCMA-D8: 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_rstack_overflow: 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; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - KGPE-D16: 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_rstack_overflow: 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; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - KGPE-D16: 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_rstack_overflow: 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; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - KGPE-D16: 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_rstack_overflow: 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; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - KGPE-D16: 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Mitigation of untrained return thunk; SMT disabled + spec_rstack_overflow: 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; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
kvazaar: Bosphorus 1080p - Very Fast kvazaar: Bosphorus 1080p - Super Fast kvazaar: Bosphorus 1080p - Medium kvazaar: Bosphorus 4K - Medium kvazaar: Bosphorus 1080p - Ultra Fast kvazaar: Bosphorus 4K - Super Fast kvazaar: Bosphorus 4K - Very Fast kvazaar: Bosphorus 1080p - Slow tinymembench: Standard Memset sysbench: CPU sysbench: RAM / Memory kvazaar: Bosphorus 4K - Slow kvazaar: Bosphorus 4K - Ultra Fast deepspeech: CPU wireguard: t-test1: 1 t-test1: 2 asmfish: 1024 Hash Memory, 26 Depth compress-7zip: Decompression Rating x264: Bosphorus 4K build-linux-kernel: defconfig radiance: Serial tinymembench: Standard Memcpy radiance: SMP Parallel x264: Bosphorus 1080p compress-7zip: Compression Rating openssl: SHA512 openssl: RSA4096 openssl: SHA256 openssl: RSA4096 povray: Trace Time git: Time To Complete Common Git Commands build-linux-kernel: allmodconfig ctx-clock: Context Switch Time dbench: 1 nginx: 1000 nginx: 500 openssl: ChaCha20 nginx: 200 nginx: 100 openssl: ChaCha20-Poly1305 whisper-cpp: ggml-base.en - 2016 State of the Union dbench: 12 ramspeed: Triad - Integer ramspeed: Triad - Floating Point dbench: 6 sqlite: 8 ramspeed: Add - Floating Point ramspeed: Add - Integer ramspeed: Average - Integer ramspeed: Average - Floating Point ramspeed: Scale - Integer sqlite: 1 sqlite: 4 ramspeed: Copy - Floating Point ramspeed: Scale - Floating Point ramspeed: Copy - Integer openssl: AES-256-GCM openssl: AES-128-GCM sqlite: 2 nginx: 4000 nginx: 20 dbench: 256 dbench: 128 dbench: 48 stockfish: Chess Benchmark nginx: 1 9020 SFF KCMA-D8 KGPE-D16 i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 33.72 39.55 16.44 2.97 54.62 8.72 7.31 15.83 25230.7 4379.29 13322.26 2.86 12.11 94.34025 190.933 20.943 6.826 10104729 17807 8.99 362.158 686.637 11281.2 226.641 39.73 22961 1477501870 48176.6 1345337453 739.9 133.776 52.206 5231.802 1181 418.650 15627.00 16162.63 13514159173 16895.10 17154.22 8779193183 343.96800 2119.08 14299.97 14479.63 961.692 34.922 14440.88 14365.29 13628.35 13719.81 12861.90 6.473 21.984 12932.00 13014.23 12951.42 12494812137 15981019683 13.462 15176.60 17773.82 1492.48 1671.44 2201.27 3713939 38.28 46.14 18.17 3.37 62.95 10.24 8.48 17.55 24076.9 7953.55 20035.88 3.28 14.20 114.01644 195.720 22.298 7.140 12652496 24663 10.99 306.983 690.914 10846.2 224.772 46.56 29617 1407249223 49904.6 1325963630 746.5 112.801 50.457 4382.301 1177 452.392 19217.18 19865.14 15444836350 20677.58 20941.00 9980068387 342.01067 2110.69 13751.74 13852.47 1089.76 30.798 13861.36 13771.52 13047.48 13132.73 12372.61 6.422 19.681 12393.24 12448.52 12375.81 12490032380 16225235033 11.417 19198.77 20716.89 1775.11 2424.98 2238.34 4260414 4.59 5.63 2.37 0.45 8.41 1.37 1.14 2.36 3932.1 0.46 2.09 1030.615 99.159 31.028 6302112 16269 5.27 622.242 4028.9 21.46 20510 208.030 1126.45 9038.22 9134.12 785.194 23.750 9402.75 9353.29 9070.31 9359.15 8354.26 9.635 16.234 9504.50 9379.78 9523.40 10.810 1177.89 1162.34 1214.05 5.23 6.58 2.71 0.54 10.02 1.63 1.36 2.69 3948.7 0.55 2.53 909.329 89.031 27.420 8207387 20796 6.53 505.736 4200.6 27.03 23399 208.138 1390.65 8462.03 8376.62 939.745 23.930 8799.64 8733.15 8514.69 8756.49 7875.36 9.758 16.656 8966.66 8889.02 8959.58 11.251 1869.00 1901.33 1962.32 4025830 10.76 13.58 5.51 1.11 20.65 3.35 2.79 5.46 3401.3 19569.17 3001.97 1.12 5.18 530.737 51.124 15.075 16358925 40534 11.97 272.733 1979.935 3609.7 584.323 49.05 34440 2481919357 74603.5 1993584610 1109.0 87.143 105.507 809 332.549 17963.18 19543.06 17179723820 20849.91 21415.16 10936636483 1619.24749 1826.37 7905.14 8078.08 1216.09 26.162 8245.26 8270.63 7880.98 8009.08 7522.25 7.228 14.858 7824.11 7898.93 7931.71 10969188487 12231015810 10.441 15916.97 18965.99 5790861 3714.558 2407.34 1978.95 1586.84 12.54 16.14 5.74 1.41 24.48 3.86 3.10 5.68 5286.5 23599.40 2814.57 1.43 5.86 518.38446 674.661 62.597 18.579 22429428 56514 15.81 215.898 2185.7 5737.6 700.088 57.30 53003 3572458597 103162.4 2864350503 1534.7 66.725 117.061 2794.560 532 260.633 27382.61 28584.46 24760358277 29057.65 29208.74 15967123957 3665.99808 1516.39 8742.23 9024.95 1034.72 25.878 9205.39 9000.26 8604.11 8901.08 7595.49 10.664 17.039 8838.26 8752.19 8793.11 16305372890 18188798270 12.659 2520.73 2309.96 2618.90 8434024 12.59 16.28 5.73 1.42 24.79 3.89 3.11 5.67 4991.6 23587.31 2797.87 1.43 5.89 413.78754 689.511 63.253 19.894 22341314 56554 15.82 211.612 2193.238 5642.8 687.702 57.03 54823 3566379557 103147.0 2850172400 1534.0 66.514 116.500 2694.740 532 254.507 28765.21 29341.51 24758972870 29832.02 29876.69 15987696800 3903.89217 1262.19 11604.30 9006.51 854.691 36.649 12211.77 12119.88 11436.77 8989.05 7557.33 10.652 17.627 8916.05 12204.42 9487.26 16306141410 18192103857 12.605 2074.96 2334.00 1907.46 9360380 14.32 18.48 6.47 1.61 28.17 4.44 3.54 6.40 5215.6 31647.06 3000.22 1.62 6.76 370.63305 601.293 55.104 15.908 25498939 60989 17.40 232.002 1970.48 5770.6 620.291 62.34 31226 4012481460 120343.0 3170828890 1788.7 55.471 102.955 2865.739 650 290.357 23398.99 26105.30 27691229820 30046.83 31647.95 17685267707 1906.93697 1622.98 8718.48 9143.9 1091.22 24.016 9340.12 9389.00 8725.36 9031.33 7935.45 9.972 16.255 8736.61 8870.80 8745.12 17762825830 19811270380 11.785 2617.92 2371.45 2138.06 5044238 14.48 18.80 6.51 1.62 28.83 4.51 3.59 6.44 5524.3 31660.63 2996.26 1.64 6.91 416.41616 558.276 55.542 17.229 26060061 63081 17.85 184.096 1958.181 5685.6 626.799 65.69 60240 4013246317 120430.5 3218093157 1788.9 55.494 104.445 2353.610 652 258.874 32488.65 33514.92 27723977703 34221.36 34596.13 17657219300 1975.35904 1432.71 11183.93 11689.12 681.124 41.778 12366.95 12333.43 11567.83 12131.26 10567.86 10.450 24.605 12288.54 12295.85 12228.01 17767864910 19811117103 14.403 1563.72 1817.29 1680.32 11090670 OpenBenchmarking.org
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Very Fast i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 9 18 27 36 45 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, 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 SE +/- 0.02, N = 3 38.28 33.72 14.48 14.32 12.59 12.54 10.76 5.23 4.59 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Super Fast 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Super Fast i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 10 20 30 40 50 SE +/- 0.11, N = 3 SE +/- 0.09, 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 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 46.14 39.55 18.80 18.48 16.28 16.14 13.58 6.58 5.63 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Medium i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, 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 SE +/- 0.00, N = 3 18.17 16.44 6.51 6.47 5.74 5.73 5.51 2.71 2.37 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 0.7583 1.5166 2.2749 3.0332 3.7915 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 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.37 2.97 1.62 1.61 1.42 1.41 1.11 0.54 0.45 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 14 28 42 56 70 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 62.95 54.62 28.83 28.17 24.79 24.48 20.65 10.02 8.41 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Super Fast 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 10.24 8.72 4.51 4.44 3.89 3.86 3.35 1.63 1.37 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2 4 6 8 10 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 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 8.48 7.31 3.59 3.54 3.11 3.10 2.79 1.36 1.14 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Slow 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Slow i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 4 8 12 16 20 SE +/- 0.02, N = 3 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 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 17.55 15.83 6.44 6.40 5.68 5.67 5.46 2.69 2.36 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Tinymembench Standard Memset 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 5K 10K 15K 20K 25K SE +/- 0.55, N = 3 SE +/- 19.95, N = 3 SE +/- 54.62, N = 3 SE +/- 17.55, N = 3 SE +/- 19.04, N = 3 SE +/- 44.23, N = 3 SE +/- 16.12, N = 3 SE +/- 18.77, N = 3 SE +/- 11.66, N = 3 25230.7 24076.9 5524.3 5286.5 5215.6 4991.6 3948.7 3932.1 3401.3 1. (CC) gcc options: -O2 -lm
Sysbench Test: CPU KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 7K 14K 21K 28K 35K SE +/- 5.55, N = 3 SE +/- 12.25, N = 3 SE +/- 6.37, N = 3 SE +/- 2.32, N = 3 SE +/- 0.65, N = 3 SE +/- 0.54, N = 3 SE +/- 0.23, N = 3 31660.63 31647.06 23599.40 23587.31 19569.17 7953.55 4379.29 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
Sysbench Test: RAM / Memory 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org MiB/sec, More Is Better Sysbench 1.0.20 Test: RAM / Memory i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 4K 8K 12K 16K 20K SE +/- 93.36, N = 3 SE +/- 118.85, N = 7 SE +/- 27.74, N = 3 SE +/- 15.15, N = 3 SE +/- 5.82, N = 3 SE +/- 1.48, N = 3 SE +/- 7.52, N = 3 20035.88 13322.26 3001.97 3000.22 2996.26 2814.57 2797.87 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 0.738 1.476 2.214 2.952 3.69 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 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.28 2.86 1.64 1.62 1.43 1.43 1.12 0.55 0.46 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 14.20 12.11 6.91 6.76 5.89 5.86 5.18 2.53 2.09 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
DeepSpeech Acceleration: CPU 9020 SFF KGPE-D16 OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 110 220 330 440 550 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 1.26, N = 3 SE +/- 17.85, N = 9 SE +/- 17.42, N = 9 SE +/- 4.98, N = 3 94.34 114.02 370.63 413.79 416.42 518.38
WireGuard + Linux Networking Stack Stress Test 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 200 400 600 800 1000 SE +/- 0.99, N = 3 SE +/- 0.35, N = 3 SE +/- 1.32, N = 3 SE +/- 2.26, N = 3 SE +/- 3.73, N = 3 SE +/- 0.86, N = 3 SE +/- 1.74, N = 3 SE +/- 1.35, N = 3 SE +/- 4.67, N = 3 190.93 195.72 530.74 909.33 1030.62 558.28 601.29 674.66 689.51
t-test1 Threads: 1 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 1 i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.27, N = 3 SE +/- 0.09, N = 3 SE +/- 0.34, N = 3 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.40, N = 3 SE +/- 0.36, N = 3 20.94 22.30 51.12 89.03 99.16 55.10 55.54 62.60 63.25 1. (CC) gcc options: -pthread
t-test1 Threads: 2 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 2 i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 7 14 21 28 35 SE +/- 0.008, N = 3 SE +/- 0.005, N = 3 SE +/- 0.026, N = 3 SE +/- 0.017, N = 3 SE +/- 0.095, N = 3 SE +/- 0.001, N = 3 SE +/- 0.031, N = 3 SE +/- 0.158, N = 3 SE +/- 0.158, N = 3 6.826 7.140 15.075 27.420 31.028 15.908 17.229 18.579 19.894 1. (CC) gcc options: -pthread
asmFish 1024 Hash Memory, 26 Depth KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 6M 12M 18M 24M 30M SE +/- 356749.39, N = 3 SE +/- 116206.47, N = 3 SE +/- 141056.03, N = 3 SE +/- 252856.43, N = 4 SE +/- 171336.12, N = 5 SE +/- 71335.10, N = 3 SE +/- 65774.81, N = 3 SE +/- 111781.56, N = 8 SE +/- 26691.50, N = 3 26060061 25498939 22429428 22341314 16358925 8207387 6302112 12652496 10104729
7-Zip Compression Test: Decompression Rating KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Decompression Rating 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 14K 28K 42K 56K 70K SE +/- 119.84, N = 4 SE +/- 250.64, N = 3 SE +/- 136.07, N = 3 SE +/- 84.07, N = 5 SE +/- 42.75, N = 3 SE +/- 28.29, N = 3 SE +/- 139.55, N = 3 SE +/- 11.46, N = 3 SE +/- 24.74, N = 3 63081 60989 56554 56514 40534 20796 16269 24663 17807 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
x264 Video Input: Bosphorus 4K KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 4K 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 9 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 17.85 17.40 15.82 15.81 11.97 6.53 5.27 10.99 8.99 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto
Timed Linux Kernel Compilation Build: defconfig KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: defconfig 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 130 260 390 520 650 SE +/- 0.68, N = 3 SE +/- 1.78, N = 3 SE +/- 1.75, N = 3 SE +/- 1.86, N = 3 SE +/- 1.16, N = 3 SE +/- 1.98, N = 3 SE +/- 2.87, N = 3 SE +/- 0.82, N = 3 SE +/- 0.49, N = 3 184.10 211.61 215.90 232.00 272.73 505.74 622.24 306.98 362.16
Radiance Benchmark Test: Serial 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: Serial i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 500 1000 1500 2000 2500 686.64 690.91 1958.18 1970.48 2185.70 2193.24 1979.94
Tinymembench Standard Memcpy 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memcpy i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2K 4K 6K 8K 10K SE +/- 10.81, N = 3 SE +/- 13.70, N = 3 SE +/- 15.37, N = 3 SE +/- 61.22, N = 3 SE +/- 50.74, N = 3 SE +/- 5.60, N = 3 SE +/- 10.25, N = 3 SE +/- 35.35, N = 3 SE +/- 21.99, N = 3 11281.2 10846.2 5770.6 5737.6 5685.6 5642.8 4200.6 4028.9 3609.7 1. (CC) gcc options: -O2 -lm
Radiance Benchmark Test: SMP Parallel 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: SMP Parallel i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 150 300 450 600 750 224.77 226.64 584.32 620.29 626.80 687.70 700.09
x264 Video Input: Bosphorus 1080p KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 1080p 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 15 30 45 60 75 SE +/- 0.30, N = 3 SE +/- 0.29, N = 3 SE +/- 0.45, N = 3 SE +/- 0.16, N = 3 SE +/- 0.33, N = 3 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 SE +/- 0.21, N = 3 SE +/- 0.14, N = 3 65.69 62.34 57.30 57.03 49.05 27.03 21.46 46.56 39.73 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto
7-Zip Compression Test: Compression Rating KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 24.05 Test: Compression Rating 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 13K 26K 39K 52K 65K SE +/- 637.28, N = 4 SE +/- 390.42, N = 3 SE +/- 547.18, N = 5 SE +/- 373.45, N = 3 SE +/- 322.27, N = 3 SE +/- 106.27, N = 3 SE +/- 224.69, N = 3 SE +/- 401.08, N = 3 SE +/- 26.95, N = 3 60240 54823 53003 31226 34440 23399 20510 29617 22961 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenSSL Algorithm: SHA512 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA512 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 900M 1800M 2700M 3600M 4500M SE +/- 4654728.50, N = 3 SE +/- 2423345.15, N = 3 SE +/- 8781691.42, N = 3 SE +/- 22409409.90, N = 3 SE +/- 1520122.92, N = 3 SE +/- 71344.33, N = 3 SE +/- 102089.00, N = 3 4013246317 4012481460 3572458597 3566379557 2481919357 1477501870 1407249223 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: RSA4096 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 30K 60K 90K 120K 150K SE +/- 23.11, N = 3 SE +/- 75.26, N = 3 SE +/- 50.45, N = 3 SE +/- 27.41, N = 3 SE +/- 37.78, N = 3 SE +/- 427.54, N = 3 SE +/- 9.02, N = 3 120430.5 120343.0 103162.4 103147.0 74603.5 49904.6 48176.6 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: SHA256 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA256 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 700M 1400M 2100M 2800M 3500M SE +/- 1143320.47, N = 3 SE +/- 2408380.99, N = 3 SE +/- 10211336.02, N = 3 SE +/- 6697625.80, N = 3 SE +/- 490630.42, N = 3 SE +/- 355688.20, N = 3 SE +/- 1734454.85, N = 3 3218093157 3170828890 2864350503 2850172400 1993584610 1345337453 1325963630 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: RSA4096 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 400 800 1200 1600 2000 SE +/- 1.17, N = 3 SE +/- 1.45, N = 3 SE +/- 1.34, N = 3 SE +/- 1.38, N = 3 SE +/- 0.37, N = 3 SE +/- 0.00, N = 3 SE +/- 0.29, N = 3 1788.9 1788.7 1534.7 1534.0 1109.0 746.5 739.9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
POV-Ray Trace Time KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 30 60 90 120 150 SE +/- 0.18, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.26, N = 3 SE +/- 0.45, N = 3 SE +/- 0.14, N = 3 SE +/- 0.10, N = 3 55.47 55.49 66.51 66.73 87.14 112.80 133.78 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Git Time To Complete Common Git Commands 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 30 60 90 120 150 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.15, N = 3 SE +/- 0.30, N = 3 SE +/- 0.38, N = 3 SE +/- 0.27, N = 3 SE +/- 0.07, N = 3 50.46 52.21 102.96 104.45 116.50 117.06 105.51 1. git version 2.45.2
Timed Linux Kernel Compilation Build: allmodconfig KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: allmodconfig 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 1100 2200 3300 4400 5500 SE +/- 1.93, N = 3 SE +/- 0.30, N = 3 SE +/- 11.58, N = 3 SE +/- 39.45, N = 3 SE +/- 19.03, N = 3 SE +/- 2.95, N = 3 SE +/- 14.82, N = 3 2353.61 2694.74 2794.56 2865.74 3714.56 4382.30 5231.80
ctx_clock Context Switch Time KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Clocks, Fewer Is Better ctx_clock Context Switch Time 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 300 600 900 1200 1500 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 1.45, N = 3 SE +/- 1.53, N = 3 SE +/- 2.67, N = 3 SE +/- 1.00, N = 3 SE +/- 0.00, N = 3 532 532 650 652 809 1177 1181
Dbench Client Count: 1 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 1 i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 100 200 300 400 500 SE +/- 0.80, N = 3 SE +/- 5.06, N = 3 SE +/- 2.87, N = 3 SE +/- 0.70, N = 3 SE +/- 0.53, N = 3 SE +/- 0.80, N = 3 SE +/- 3.76, N = 3 SE +/- 0.25, N = 3 SE +/- 0.74, N = 3 452.39 418.65 332.55 208.14 208.03 290.36 260.63 258.87 254.51 1. (CC) gcc options: -lpopt -O2
nginx Connections: 1000 KGPE-D16 9020 SFF KCMA-D8 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 1000 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k no-smt, 32GB-1600CL9 4x8GB 7K 14K 21K 28K 35K SE +/- 15.35, N = 3 SE +/- 18.61, N = 3 SE +/- 173.39, N = 3 SE +/- 243.76, N = 3 SE +/- 148.36, N = 3 SE +/- 116.30, N = 3 SE +/- 192.86, N = 3 32488.65 28765.21 27382.61 23398.99 19217.18 15627.00 17963.18 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
nginx Connections: 500 KGPE-D16 9020 SFF KCMA-D8 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k no-smt, 32GB-1600CL9 4x8GB 7K 14K 21K 28K 35K SE +/- 46.93, N = 3 SE +/- 30.25, N = 3 SE +/- 36.59, N = 3 SE +/- 25.35, N = 3 SE +/- 108.52, N = 3 SE +/- 149.54, N = 3 SE +/- 36.16, N = 3 33514.92 29341.51 28584.46 26105.30 19865.14 16162.63 19543.06 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenSSL Algorithm: ChaCha20 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 6000M 12000M 18000M 24000M 30000M SE +/- 17301433.61, N = 3 SE +/- 14720251.75, N = 3 SE +/- 4981271.48, N = 3 SE +/- 1828076.21, N = 3 SE +/- 4777740.30, N = 3 SE +/- 1096898.59, N = 3 SE +/- 19359459.21, N = 3 27723977703 27691229820 24760358277 24758972870 17179723820 15444836350 13514159173 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
nginx Connections: 200 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 200 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 7K 14K 21K 28K 35K SE +/- 44.64, N = 3 SE +/- 17.76, N = 3 SE +/- 16.79, N = 3 SE +/- 8.01, N = 3 SE +/- 21.18, N = 3 SE +/- 67.37, N = 3 SE +/- 22.95, N = 3 34221.36 30046.83 29832.02 29057.65 20849.91 20677.58 16895.10 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
nginx Connections: 100 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 100 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 7K 14K 21K 28K 35K SE +/- 21.61, N = 3 SE +/- 14.25, N = 3 SE +/- 30.55, N = 3 SE +/- 29.14, N = 3 SE +/- 18.65, N = 3 SE +/- 11.59, N = 3 SE +/- 15.58, N = 3 34596.13 31647.95 29876.69 29208.74 21415.16 20941.00 17154.22 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenSSL Algorithm: ChaCha20-Poly1305 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 4000M 8000M 12000M 16000M 20000M SE +/- 20654805.46, N = 3 SE +/- 21796818.40, N = 3 SE +/- 4839410.04, N = 3 SE +/- 30369902.26, N = 3 SE +/- 14057824.98, N = 3 SE +/- 870394.40, N = 3 SE +/- 1923758.63, N = 3 17685267707 17657219300 15987696800 15967123957 10936636483 9980068387 8779193183 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Whisper.cpp Model: ggml-base.en - Input: 2016 State of the Union 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.6.2 Model: ggml-base.en - Input: 2016 State of the Union i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 800 1600 2400 3200 4000 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 19.44, N = 9 SE +/- 185.13, N = 8 SE +/- 147.27, N = 6 SE +/- 96.94, N = 3 SE +/- 78.69, N = 3 342.01 343.97 1619.25 1906.94 1975.36 3666.00 3903.89 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx
Dbench Client Count: 12 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 12 i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 500 1000 1500 2000 2500 SE +/- 6.67, N = 3 SE +/- 23.54, N = 3 SE +/- 25.29, N = 9 SE +/- 0.33, N = 3 SE +/- 2.45, N = 3 SE +/- 8.27, N = 3 SE +/- 2.21, N = 3 SE +/- 2.39, N = 3 SE +/- 11.73, N = 3 2119.08 2110.69 1826.37 1390.65 1126.45 1622.98 1516.39 1432.71 1262.19 1. (CC) gcc options: -lpopt -O2
RAMspeed SMP Type: Triad - Benchmark: Integer 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Integer i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 10.87, N = 3 SE +/- 12.01, N = 3 SE +/- 31.33, N = 3 SE +/- 23.64, N = 3 SE +/- 59.49, N = 3 SE +/- 28.35, N = 3 SE +/- 14.20, N = 3 SE +/- 18.86, N = 3 SE +/- 55.36, N = 3 14299.97 13751.74 11604.30 11183.93 8742.23 8718.48 9038.22 8462.03 7905.14 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Triad - Benchmark: Floating Point 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Floating Point i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 6.26, N = 3 SE +/- 16.99, N = 3 SE +/- 114.35, N = 6 SE +/- 33.20, N = 3 SE +/- 24.74, N = 3 SE +/- 17.52, N = 3 SE +/- 6.23, N = 3 SE +/- 147.33, N = 11 SE +/- 28.96, N = 3 14479.63 13852.47 11689.12 9143.90 9024.95 9006.51 9134.12 8376.62 8078.08 1. (CC) gcc options: -O3 -march=native
Dbench Client Count: 6 KCMA-D8 KGPE-D16 9020 SFF OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 6 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 300 600 900 1200 1500 SE +/- 12.27, N = 3 SE +/- 0.42, N = 3 SE +/- 6.27, N = 3 SE +/- 4.18, N = 3 SE +/- 2.32, N = 3 SE +/- 8.52, N = 3 SE +/- 2.28, N = 3 SE +/- 2.23, N = 3 SE +/- 6.30, N = 3 1216.09 939.75 785.19 1091.22 1034.72 854.69 681.12 1089.76 961.69 1. (CC) gcc options: -lpopt -O2
SQLite Threads / Copies: 8 KCMA-D8 KGPE-D16 9020 SFF OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 8 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 10 20 30 40 50 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 1.02, N = 12 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 1.57, N = 12 SE +/- 0.46, N = 3 SE +/- 0.36, N = 4 SE +/- 0.25, N = 3 23.75 23.93 26.16 24.02 25.88 36.65 41.78 30.80 34.92 1. (CC) gcc options: -O2 -lz -lm
RAMspeed SMP Type: Add - Benchmark: Floating Point 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Floating Point i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 15.45, N = 3 SE +/- 8.22, N = 3 SE +/- 15.55, N = 3 SE +/- 3.65, N = 3 SE +/- 41.34, N = 3 SE +/- 20.74, N = 3 SE +/- 13.19, N = 3 SE +/- 16.93, N = 3 SE +/- 18.00, N = 3 14440.88 13861.36 12366.95 12211.77 9340.12 9205.39 9402.75 8799.64 8245.26 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Add - Benchmark: Integer 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Integer i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 4.54, N = 3 SE +/- 14.02, N = 3 SE +/- 21.49, N = 3 SE +/- 13.85, N = 3 SE +/- 11.45, N = 3 SE +/- 44.71, N = 3 SE +/- 9.38, N = 3 SE +/- 14.05, N = 3 SE +/- 28.35, N = 3 14365.29 13771.52 12333.43 12119.88 9389.00 9000.26 9353.29 8733.15 8270.63 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Average - Benchmark: Integer 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Integer i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 1.70, N = 3 SE +/- 1.39, N = 3 SE +/- 10.66, N = 3 SE +/- 106.55, N = 3 SE +/- 15.43, N = 3 SE +/- 20.36, N = 3 SE +/- 14.65, N = 3 SE +/- 9.13, N = 3 SE +/- 6.48, N = 3 13628.35 13047.48 11567.83 11436.77 8725.36 8604.11 9070.31 8514.69 7880.98 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Average - Benchmark: Floating Point 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Floating Point i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 3.99, N = 3 SE +/- 3.67, N = 3 SE +/- 9.21, N = 3 SE +/- 26.15, N = 3 SE +/- 9.99, N = 3 SE +/- 29.78, N = 3 SE +/- 13.19, N = 3 SE +/- 4.50, N = 3 SE +/- 10.46, N = 3 13719.81 13132.73 12131.26 9031.33 8989.05 8901.08 9359.15 8756.49 8009.08 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Scale - Benchmark: Integer 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Integer i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 5.89, N = 3 SE +/- 3.50, N = 3 SE +/- 9.12, N = 3 SE +/- 31.25, N = 3 SE +/- 69.60, N = 3 SE +/- 7.40, N = 3 SE +/- 26.66, N = 3 SE +/- 15.26, N = 3 SE +/- 47.36, N = 3 12861.90 12372.61 10567.86 7935.45 7595.49 7557.33 8354.26 7875.36 7522.25 1. (CC) gcc options: -O3 -march=native
SQLite Threads / Copies: 1 9020 SFF KCMA-D8 KGPE-D16 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 1 i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 3 6 9 12 15 SE +/- 0.062, N = 6 SE +/- 0.042, N = 3 SE +/- 0.009, N = 3 SE +/- 0.017, N = 3 SE +/- 0.120, N = 12 SE +/- 0.087, N = 7 SE +/- 0.291, N = 15 SE +/- 0.029, N = 3 SE +/- 0.109, N = 15 6.422 6.473 7.228 9.635 9.758 9.972 10.450 10.652 10.664 1. (CC) gcc options: -O2 -lz -lm
SQLite Threads / Copies: 4 KCMA-D8 KGPE-D16 9020 SFF OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 4 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.15, N = 15 SE +/- 0.24, N = 3 14.86 16.23 16.66 16.26 17.04 17.63 24.61 19.68 21.98 1. (CC) gcc options: -O2 -lz -lm
RAMspeed SMP Type: Copy - Benchmark: Floating Point 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Floating Point i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 16.16, N = 3 SE +/- 17.42, N = 3 SE +/- 8.91, N = 3 SE +/- 17.08, N = 3 SE +/- 70.34, N = 3 SE +/- 35.36, N = 3 SE +/- 25.40, N = 3 SE +/- 32.90, N = 3 SE +/- 9.82, N = 3 12932.00 12393.24 12288.54 8916.05 8838.26 8736.61 9504.50 8966.66 7824.11 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Scale - Benchmark: Floating Point 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Floating Point i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 15.59, N = 3 SE +/- 14.78, N = 3 SE +/- 37.56, N = 3 SE +/- 34.40, N = 3 SE +/- 43.31, N = 3 SE +/- 64.42, N = 3 SE +/- 33.26, N = 3 SE +/- 5.08, N = 3 SE +/- 2.02, N = 3 13014.23 12448.52 12295.85 12204.42 8870.80 8752.19 9379.78 8889.02 7898.93 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Copy - Benchmark: Integer 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Integer i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 3K 6K 9K 12K 15K SE +/- 7.05, N = 3 SE +/- 4.32, N = 3 SE +/- 16.02, N = 3 SE +/- 406.70, N = 12 SE +/- 20.03, N = 3 SE +/- 14.42, N = 3 SE +/- 12.40, N = 3 SE +/- 1.02, N = 3 SE +/- 37.23, N = 3 12951.42 12375.81 12228.01 9487.26 8793.11 8745.12 9523.40 8959.58 7931.71 1. (CC) gcc options: -O3 -march=native
OpenSSL Algorithm: AES-256-GCM KGPE-D16 9020 SFF KCMA-D8 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo i7-4790k no-smt, 32GB-1600CL9 4x8GB i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 4000M 8000M 12000M 16000M 20000M SE +/- 2606299.33, N = 3 SE +/- 1188969.89, N = 3 SE +/- 2030091.40, N = 3 SE +/- 3552540.47, N = 3 SE +/- 22158747.24, N = 3 SE +/- 2338047.82, N = 3 SE +/- 998537.42, N = 3 17767864910 17762825830 16306141410 16305372890 12494812137 12490032380 10969188487 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: AES-128-GCM KGPE-D16 9020 SFF KCMA-D8 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 4000M 8000M 12000M 16000M 20000M SE +/- 2646506.76, N = 3 SE +/- 3808261.27, N = 3 SE +/- 424284.34, N = 3 SE +/- 835147.75, N = 3 SE +/- 9986258.77, N = 3 SE +/- 2588088.69, N = 3 SE +/- 3858436.83, N = 3 19811270380 19811117103 18192103857 18188798270 16225235033 15981019683 12231015810 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
SQLite Threads / Copies: 2 KCMA-D8 9020 SFF KGPE-D16 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 2 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.13, N = 5 SE +/- 0.17, N = 3 SE +/- 0.12, N = 15 10.44 10.81 11.25 11.42 13.46 11.79 12.61 12.66 14.40 1. (CC) gcc options: -O2 -lz -lm
nginx Connections: 4000 9020 SFF KCMA-D8 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 4000 i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k no-smt, 32GB-1600CL9 4x8GB 4K 8K 12K 16K 20K SE +/- 169.93, N = 3 SE +/- 195.12, N = 3 SE +/- 144.64, N = 15 19198.77 15176.60 15916.97 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
nginx Connections: 20 9020 SFF KCMA-D8 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 20 i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) i7-4790k no-smt, 32GB-1600CL9 4x8GB 4K 8K 12K 16K 20K SE +/- 6.68, N = 3 SE +/- 12.00, N = 3 SE +/- 13.30, N = 3 20716.89 17773.82 18965.99 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Dbench Client Count: 256 KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 256 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 600 1200 1800 2400 3000 SE +/- 13.33, N = 3 SE +/- 11.72, N = 3 SE +/- 167.59, N = 6 SE +/- 6.08, N = 3 SE +/- 19.78, N = 3 SE +/- 0.42, N = 3 SE +/- 12.86, N = 4 SE +/- 100.50, N = 9 SE +/- 38.10, N = 9 2617.92 2520.73 2074.96 1563.72 2407.34 1869.00 1177.89 1775.11 1492.48 1. (CC) gcc options: -lpopt -O2
Dbench Client Count: 128 9020 SFF KGPE-D16 KCMA-D8 OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 128 i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 500 1000 1500 2000 2500 SE +/- 20.81, N = 3 SE +/- 71.14, N = 9 SE +/- 46.04, N = 9 SE +/- 21.23, N = 3 SE +/- 21.05, N = 7 SE +/- 52.60, N = 9 SE +/- 75.91, N = 9 SE +/- 16.99, N = 9 SE +/- 27.89, N = 9 2424.98 1671.44 2371.45 2334.00 2309.96 1817.29 1978.95 1901.33 1162.34 1. (CC) gcc options: -lpopt -O2
Dbench Client Count: 48 KGPE-D16 9020 SFF KCMA-D8 OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 48 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo i7-4790k, 32GB-1600CL9 4x8GB i7-4790k no-smt, 32GB-1600CL9 4x8GB 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 4386, 32GB-1600CL9 4x8GB in 1066Mhz 2x Opteron 4256 EE, 32GB-1600CL9 4x8GB 600 1200 1800 2400 3000 SE +/- 30.70, N = 3 SE +/- 29.50, N = 9 SE +/- 11.74, N = 3 SE +/- 50.35, N = 6 SE +/- 24.97, N = 4 SE +/- 67.65, N = 9 SE +/- 7.64, N = 3 SE +/- 18.14, N = 3 SE +/- 52.21, N = 7 2618.90 2138.06 1907.46 1680.32 2238.34 2201.27 1962.32 1586.84 1214.05 1. (CC) gcc options: -lpopt -O2
Stockfish Chess Benchmark KGPE-D16 KCMA-D8 9020 SFF OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 17 Chess Benchmark 2x Opteron 6380, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 64GB-1600CL11 ECC 4x16GB 2x Opteron 6276, 32GB-1600CL11 4x8GB Dasharo 2x Opteron 4386, 32GB-1600CL9 4x8GB (in 1066Mhz!) 2x Opteron 6380, 256GB-1600CL11 ECC 16x16GB Dasharo i7-4790k, 32GB-1600CL9 4x8GB 2x Opteron 4256 EE, 64GB-1600CL11 ECC 8x8GB unreg, reports as 1066Mhz i7-4790k no-smt, 32GB-1600CL9 4x8GB 2M 4M 6M 8M 10M SE +/- 377078.05, N = 9 SE +/- 324914.59, N = 9 SE +/- 440460.64, N = 9 SE +/- 353903.21, N = 6 SE +/- 353022.06, N = 9 SE +/- 125889.26, N = 9 SE +/- 328647.22, N = 9 SE +/- 9836.51, N = 3 11090670 9360380 8434024 5044238 5790861 4025830 4260414 3713939 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto-partition=one -flto=jobserver
Phoronix Test Suite v10.8.5