Xeon Platinum 8380 DODT Mitigation Impact

Benchmarks for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2301271-NE-XEONPLATI60&sro&grs.

Xeon Platinum 8380 DODT Mitigation ImpactProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionLinux w DODTdoitm=off2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Ice Lake IEH512GB7682GB INTEL SSDPF2KX076TZASPEEDVE2282 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFPUbuntu 22.106.2.0-rc5-phx-dodt (x86_64)GNOME ShellX Server 1.21.1.31.3.211GCC 12.2.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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-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 Processor Details- Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd000375 Python Details- Python 3.10.6Security Details- Linux w DODT: dodt: Mitigation of DOITM + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - doitm=off: dodt: Vulnerable + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Xeon Platinum 8380 DODT Mitigation Impactstress-ng: Mallocspacy: en_core_web_trfclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachestress-ng: SENDFILEstress-ng: Mutexkvazaar: Bosphorus 4K - Super Fastdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamnekrs: TurboPipe Periodicstress-ng: MEMFDspacy: en_core_web_lgbuild-godot: Time To Compilestress-ng: Cryptorocksdb: Update Randblender: BMW27 - CPU-Onlyopenradioss: Bumper Beamclickhouse: 100M Rows Hits Dataset, Third Runavifenc: 6xmrig: Monero - 1Mkvazaar: Bosphorus 4K - Ultra Fastopenradioss: Bird Strike on Windshieldclickhouse: 100M Rows Hits Dataset, Second Runpgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writecryptsetup: AES-XTS 512b Encryptiondeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streambuild-linux-kernel: defconfigbuild-nodejs: Time To Compilexmrig: Wownero - 1Mopenssl: cryptsetup: PBKDF2-sha512cryptsetup: AES-XTS 256b Encryptiondeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streambuild-llvm: Ninjaavifenc: 0deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamminibude: OpenMP - BM1minibude: OpenMP - BM1cryptsetup: Twofish-XTS 256b Decryptiondeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamcryptsetup: Twofish-XTS 512b Decryptionbuild-linux-kernel: allmodconfigpgbench: 100 - 800 - Read Write - Average Latencycryptsetup: AES-XTS 256b Decryptionpgbench: 100 - 800 - Read Writedeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamwebp: Quality 100cryptsetup: PBKDF2-whirlpoolcryptsetup: AES-XTS 512b Decryptionavifenc: 2uvg266: Bosphorus 4K - Super Faststress-ng: IO_uringcryptsetup: Serpent-XTS 512b Encryptionopenradioss: Rubber O-Ring Seal Installationcryptsetup: Serpent-XTS 256b Encryptiondeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamcryptopp: Keyed Algorithmscryptopp: Unkeyed Algorithmscryptsetup: Serpent-XTS 256b Decryptiondeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamblender: Classroom - CPU-Onlyopenssl: deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamcryptsetup: Twofish-XTS 256b Encryptionuvg266: Bosphorus 4K - Ultra Fastcryptsetup: Serpent-XTS 512b Decryptiondeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamrocksdb: Rand Readdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamstress-ng: x86_64 RdRandcryptsetup: Twofish-XTS 512b Encryptioncockroach: KV, 10% Reads - 256cockroach: MoVR - 256webp: Quality 100, Highest Compressionwebp: Defaultstress-ng: Futexpgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Onlycockroach: KV, 95% Reads - 256cockroach: KV, 60% Reads - 256Linux w DODTdoitm=off195951844.813169398.751128077.9141364067.7547.06890.948644.8577487.361081.88022956216666673592.881097144.64685533.0259257623.4485.13427.423.51926451.347.95138.61423.1314.635683283445.4821.211234.515170.92941450.117781.613925463864.3182.2006146.95679.482219.3059823.502348.123494.7252368.116357.7830.5710178.6233223.6458357.5261.02810.6353891.57522348.51238.425831953449.844.03842.6826508.09561.078.06559.548.4603565.089482361.672421527.6125.912662.711188255.4454.9543351.442.61527.287.8377278841535316.8622669198.10352.281359.8974.82.8113.09699147.730.5062021337119187.4102448.9201328390.343225392.391146358.1641978074.4146.47902.056344.3071481.386482.70512983103333333624.421088844.95184975.8458878723.3084.63424.963.49926578.047.75139.19421.3914.695680553458.6818.301734.393170.36141317.217837.913968663876.2182.6993147.34079.684218.7781821.523948.013994.9402373.489358.5832.3903178.2763224.0542358.1261.45410.6503886.17512348.44858.435825513446.343.99542.7226532.30560.578.00559.148.4895564.749237361.884748527.3125.973662.681188684.8455.1038351.542.62527.387.8216278886510316.8167669178.00352.22.8113.09958957.410.5042020130OpenBenchmarking.org

Stress-NG

Test: Malloc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: MallocLinux w DODTdoitm=off40M80M120M160M200MSE +/- 655475.74, N = 3SE +/- 454146.57, N = 3195951844.81201328390.341. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

spaCy

Model: en_core_web_trf

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_trfLinux w DODTdoitm=off7001400210028003500SE +/- 30.17, N = 3SE +/- 48.89, N = 331693225

ClickHouse

100M Rows Hits Dataset, First Run / Cold Cache

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheLinux w DODTdoitm=off90180270360450SE +/- 3.64, N = 3SE +/- 1.76, N = 3398.75392.39MIN: 34.82 / MAX: 4615.38MIN: 33.75 / MAX: 5000

Stress-NG

Test: SENDFILE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: SENDFILELinux w DODTdoitm=off200K400K600K800K1000KSE +/- 8091.69, N = 3SE +/- 8323.86, N = 31128077.911146358.161. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Stress-NG

Test: Mutex

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: MutexLinux w DODTdoitm=off9M18M27M36M45MSE +/- 162165.00, N = 3SE +/- 34997.86, N = 341364067.7541978074.411. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastLinux w DODTdoitm=off1122334455SE +/- 0.46, N = 15SE +/- 0.63, N = 347.0646.471. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off2004006008001000SE +/- 2.39, N = 3SE +/- 3.12, N = 3890.95902.06

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off1020304050SE +/- 0.12, N = 3SE +/- 0.16, N = 344.8644.31

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off110220330440550SE +/- 0.57, N = 3SE +/- 3.55, N = 3487.36481.39

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off20406080100SE +/- 0.12, N = 3SE +/- 0.60, N = 381.8882.71

nekRS

Input: TurboPipe Periodic

OpenBenchmarking.orgFLOP/s, More Is BetternekRS 22.0Input: TurboPipe PeriodicLinux w DODTdoitm=off60000M120000M180000M240000M300000MSE +/- 500223394.54, N = 3SE +/- 1474277940.03, N = 32956216666672983103333331. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -lmpi_cxx -lmpi

Stress-NG

Test: MEMFD

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: MEMFDLinux w DODTdoitm=off8001600240032004000SE +/- 2.24, N = 3SE +/- 1.55, N = 33592.883624.421. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

spaCy

Model: en_core_web_lg

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_lgLinux w DODTdoitm=off2K4K6K8K10KSE +/- 10.12, N = 3SE +/- 69.82, N = 31097110888

Timed Godot Game Engine Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileLinux w DODTdoitm=off1020304050SE +/- 0.20, N = 3SE +/- 0.31, N = 344.6544.95

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: CryptoLinux w DODTdoitm=off20K40K60K80K100KSE +/- 445.46, N = 3SE +/- 991.74, N = 385533.0284975.841. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

RocksDB

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Update RandomLinux w DODTdoitm=off130K260K390K520K650KSE +/- 1503.74, N = 3SE +/- 3603.95, N = 35925765887871. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: CPU-OnlyLinux w DODTdoitm=off612182430SE +/- 0.07, N = 3SE +/- 0.04, N = 323.4423.30

OpenRadioss

Model: Bumper Beam

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bumper BeamLinux w DODTdoitm=off20406080100SE +/- 0.28, N = 3SE +/- 0.06, N = 385.1384.63

ClickHouse

100M Rows Hits Dataset, Third Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunLinux w DODTdoitm=off90180270360450SE +/- 3.25, N = 3SE +/- 0.79, N = 3427.42424.96MIN: 35.99 / MAX: 5454.55MIN: 36.19 / MAX: 5454.55

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6Linux w DODTdoitm=off0.79181.58362.37543.16723.959SE +/- 0.031, N = 15SE +/- 0.014, N = 33.5193.4991. (CXX) g++ options: -O3 -fPIC -lm

Xmrig

Variant: Monero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Monero - Hash Count: 1MLinux w DODTdoitm=off6K12K18K24K30KSE +/- 76.73, N = 3SE +/- 48.01, N = 326451.326578.01. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastLinux w DODTdoitm=off1122334455SE +/- 0.37, N = 10SE +/- 0.60, N = 347.9547.751. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenRadioss

Model: Bird Strike on Windshield

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bird Strike on WindshieldLinux w DODTdoitm=off306090120150SE +/- 0.54, N = 3SE +/- 0.51, N = 3138.61139.19

ClickHouse

100M Rows Hits Dataset, Second Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunLinux w DODTdoitm=off90180270360450SE +/- 1.99, N = 3SE +/- 1.56, N = 3423.13421.39MIN: 35.89 / MAX: 5000MIN: 34.86 / MAX: 5454.55

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyLinux w DODTdoitm=off48121620SE +/- 0.02, N = 3SE +/- 0.06, N = 314.6414.701. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteLinux w DODTdoitm=off15K30K45K60K75KSE +/- 95.69, N = 3SE +/- 295.57, N = 368328680551. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Cryptsetup

AES-XTS 512b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 512b EncryptionLinux w DODTdoitm=off7001400210028003500SE +/- 13.51, N = 3SE +/- 3.15, N = 33445.43458.6

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off2004006008001000SE +/- 0.79, N = 3SE +/- 2.36, N = 3821.21818.30

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigLinux w DODTdoitm=off816243240SE +/- 0.39, N = 4SE +/- 0.40, N = 434.5234.39

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 18.8Time To CompileLinux w DODTdoitm=off4080120160200SE +/- 1.24, N = 3SE +/- 0.77, N = 3170.93170.36

Xmrig

Variant: Wownero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Wownero - Hash Count: 1MLinux w DODTdoitm=off9K18K27K36K45KSE +/- 149.86, N = 3SE +/- 35.05, N = 341450.141317.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenSSL

OpenBenchmarking.orgsign/s, More Is BetterOpenSSLLinux w DODTdoitm=off4K8K12K16K20KSE +/- 63.70, N = 3SE +/- 20.72, N = 317781.617837.91. OpenSSL 3.0.5 5 Jul 2022 (Library: OpenSSL 3.0.5 5 Jul 2022)

Cryptsetup

PBKDF2-sha512

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-sha512Linux w DODTdoitm=off300K600K900K1200K1500KSE +/- 3203.15, N = 3SE +/- 2233.59, N = 313925461396866

Cryptsetup

AES-XTS 256b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 256b EncryptionLinux w DODTdoitm=off8001600240032004000SE +/- 16.70, N = 3SE +/- 7.45, N = 33864.33876.2

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off4080120160200SE +/- 0.39, N = 3SE +/- 2.12, N = 3182.20182.70

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaLinux w DODTdoitm=off306090120150SE +/- 0.07, N = 3SE +/- 0.50, N = 3146.96147.34

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 0Linux w DODTdoitm=off20406080100SE +/- 0.33, N = 3SE +/- 0.31, N = 379.4879.681. (CXX) g++ options: -O3 -fPIC -lm

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off50100150200250SE +/- 0.42, N = 3SE +/- 2.51, N = 3219.31218.78

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off2004006008001000SE +/- 0.30, N = 3SE +/- 0.15, N = 3823.50821.52

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off1122334455SE +/- 0.06, N = 3SE +/- 0.03, N = 348.1248.01

miniBUDE

Implementation: OpenMP - Input Deck: BM1

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Linux w DODTdoitm=off20406080100SE +/- 0.72, N = 3SE +/- 0.43, N = 394.7394.941. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

miniBUDE

Implementation: OpenMP - Input Deck: BM1

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Linux w DODTdoitm=off5001000150020002500SE +/- 17.94, N = 3SE +/- 10.72, N = 32368.122373.491. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

Cryptsetup

Twofish-XTS 256b Decryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 256b DecryptionLinux w DODTdoitm=off80160240320400SE +/- 0.17, N = 3SE +/- 0.21, N = 3357.7358.5

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off2004006008001000SE +/- 0.98, N = 3SE +/- 0.57, N = 3830.57832.39

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off4080120160200SE +/- 0.19, N = 3SE +/- 0.20, N = 3178.62178.28

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off50100150200250SE +/- 0.20, N = 3SE +/- 0.28, N = 3223.65224.05

Cryptsetup

Twofish-XTS 512b Decryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 512b DecryptionLinux w DODTdoitm=off80160240320400SE +/- 0.25, N = 2SE +/- 0.23, N = 3357.5358.1

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigLinux w DODTdoitm=off60120180240300SE +/- 0.63, N = 3SE +/- 0.84, N = 3261.03261.45

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average LatencyLinux w DODTdoitm=off3691215SE +/- 0.03, N = 3SE +/- 0.04, N = 310.6410.651. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Cryptsetup

AES-XTS 256b Decryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 256b DecryptionLinux w DODTdoitm=off8001600240032004000SE +/- 17.78, N = 3SE +/- 3.34, N = 33891.53886.1

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read WriteLinux w DODTdoitm=off16K32K48K64K80KSE +/- 197.73, N = 3SE +/- 295.95, N = 375223751231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off1122334455SE +/- 0.01, N = 3SE +/- 0.02, N = 348.5148.45

WebP Image Encode

Encode Settings: Quality 100

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100Linux w DODTdoitm=off246810SE +/- 0.00, N = 3SE +/- 0.01, N = 38.428.431. (CC) gcc options: -fvisibility=hidden -O2 -lm

Cryptsetup

PBKDF2-whirlpool

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-whirlpoolLinux w DODTdoitm=off120K240K360K480K600KSE +/- 1294.67, N = 3SE +/- 1624.74, N = 3583195582551

Cryptsetup

AES-XTS 512b Decryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 512b DecryptionLinux w DODTdoitm=off7001400210028003500SE +/- 13.35, N = 3SE +/- 2.54, N = 33449.83446.3

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 2Linux w DODTdoitm=off1020304050SE +/- 0.03, N = 3SE +/- 0.23, N = 344.0444.001. (CXX) g++ options: -O3 -fPIC -lm

uvg266

Video Input: Bosphorus 4K - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastLinux w DODTdoitm=off1020304050SE +/- 0.33, N = 10SE +/- 0.36, N = 842.6842.72

Stress-NG

Test: IO_uring

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: IO_uringLinux w DODTdoitm=off6K12K18K24K30KSE +/- 16.56, N = 3SE +/- 1.30, N = 326508.0926532.301. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Cryptsetup

Serpent-XTS 512b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 512b EncryptionLinux w DODTdoitm=off120240360480600SE +/- 0.45, N = 2SE +/- 0.06, N = 3561.0560.5

OpenRadioss

Model: Rubber O-Ring Seal Installation

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Rubber O-Ring Seal InstallationLinux w DODTdoitm=off20406080100SE +/- 0.01, N = 3SE +/- 0.08, N = 378.0678.00

Cryptsetup

Serpent-XTS 256b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 256b EncryptionLinux w DODTdoitm=off120240360480600SE +/- 1.27, N = 3SE +/- 1.35, N = 3559.5559.1

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off1122334455SE +/- 0.18, N = 3SE +/- 0.03, N = 348.4648.49

Crypto++

Test: Keyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Keyed AlgorithmsLinux w DODTdoitm=off120240360480600SE +/- 0.07, N = 3SE +/- 0.20, N = 3565.09564.751. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

Crypto++

Test: Unkeyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed AlgorithmsLinux w DODTdoitm=off80160240320400SE +/- 0.04, N = 3SE +/- 0.02, N = 3361.67361.881. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

Cryptsetup

Serpent-XTS 256b Decryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 256b DecryptionLinux w DODTdoitm=off110220330440550SE +/- 0.27, N = 3SE +/- 0.09, N = 3527.6527.3

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off306090120150SE +/- 0.09, N = 3SE +/- 0.38, N = 3125.91125.97

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: CPU-OnlyLinux w DODTdoitm=off1428425670SE +/- 0.10, N = 3SE +/- 0.06, N = 362.7162.68

OpenSSL

OpenBenchmarking.orgverify/s, More Is BetterOpenSSLLinux w DODTdoitm=off300K600K900K1200K1500KSE +/- 1656.25, N = 3SE +/- 1026.50, N = 31188255.41188684.81. OpenSSL 3.0.5 5 Jul 2022 (Library: OpenSSL 3.0.5 5 Jul 2022)

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off100200300400500SE +/- 0.28, N = 3SE +/- 0.57, N = 3454.95455.10

Cryptsetup

Twofish-XTS 256b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 256b EncryptionLinux w DODTdoitm=off80160240320400SE +/- 0.92, N = 3SE +/- 0.88, N = 3351.4351.5

uvg266

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastLinux w DODTdoitm=off1020304050SE +/- 0.45, N = 3SE +/- 0.18, N = 342.6142.62

Cryptsetup

Serpent-XTS 512b Decryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 512b DecryptionLinux w DODTdoitm=off110220330440550527.2527.3

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off20406080100SE +/- 0.05, N = 3SE +/- 0.10, N = 387.8487.82

RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Random ReadLinux w DODTdoitm=off60M120M180M240M300MSE +/- 2251545.82, N = 3SE +/- 2757403.57, N = 32788415352788865101. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamLinux w DODTdoitm=off70140210280350SE +/- 0.14, N = 3SE +/- 1.00, N = 3316.86316.82

Stress-NG

Test: x86_64 RdRand

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: x86_64 RdRandLinux w DODTdoitm=off140K280K420K560K700KSE +/- 68.80, N = 3SE +/- 67.49, N = 3669198.10669178.001. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Cryptsetup

Twofish-XTS 512b Encryption

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 512b EncryptionLinux w DODTdoitm=off80160240320400SE +/- 0.12, N = 3SE +/- 0.03, N = 3352.2352.2

CockroachDB

Workload: KV, 10% Reads - Concurrency: 256

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 10% Reads - Concurrency: 256Linux w DODT20K40K60K80K100KSE +/- 849.68, N = 1581359.8

CockroachDB

Workload: MoVR - Concurrency: 256

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: MoVR - Concurrency: 256Linux w DODT2004006008001000SE +/- 3.64, N = 3974.8

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionLinux w DODTdoitm=off0.63231.26461.89692.52923.1615SE +/- 0.00, N = 3SE +/- 0.00, N = 32.812.811. (CC) gcc options: -fvisibility=hidden -O2 -lm

WebP Image Encode

Encode Settings: Default

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultLinux w DODTdoitm=off3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 313.0913.091. (CC) gcc options: -fvisibility=hidden -O2 -lm

Stress-NG

Test: Futex

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: FutexLinux w DODTdoitm=off200K400K600K800K1000KSE +/- 6957.32, N = 3SE +/- 56672.45, N = 15699147.73958957.411. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyLinux w DODTdoitm=off0.11390.22780.34170.45560.5695SE +/- 0.024, N = 12SE +/- 0.021, N = 120.5060.5041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyLinux w DODTdoitm=off400K800K1200K1600K2000KSE +/- 89751.30, N = 12SE +/- 80874.14, N = 12202133720201301. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

CockroachDB

Workload: KV, 95% Reads - Concurrency: 256

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 256Linux w DODT30K60K90K120K150KSE +/- 2483.59, N = 15119187.4

CockroachDB

Workload: KV, 60% Reads - Concurrency: 256

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 256Linux w DODT20K40K60K80K100KSE +/- 1847.96, N = 15102448.9

Phoronix Test Suite v10.8.5