EPYC Milan-X Linux 5.19 Benchmarks

2 x AMD EPYC 7773X 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 21.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2206135-NE-EPYCMILAN51
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 5.19 20220607
June 07 2022
  15 Hours, 38 Minutes
Linux 5.19 + AMD Patch
June 13 2022
  8 Hours, 37 Minutes
Invert Behavior (Only Show Selected Data)
  12 Hours, 8 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

Linux 5.19 20220607

Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 21.04, Kernel: 5.19.0-051900rc1daily20220607-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001229
Java Notes: OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.21.04)
Python Notes: Python 3.9.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Linux 5.19 + AMD Patch

OS: Ubuntu 21.04, Kernel: 5.19.0-rc2-amd-patch (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080

EPYC Milan-X Linux 5.19 BenchmarksOpenBenchmarking.orgPhoronix Test Suite2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RYM1009B BIOS)AMD Starship/Matisse512GB3841GB Micron_9300_MTFDHAL3T8TDPASPEEDVE2282 x Mellanox MT27710Ubuntu 21.045.19.0-051900rc1daily20220607-generic (x86_64)5.19.0-rc2-amd-patch (x86_64)GNOME Shell 3.38.4X Server 1.20.11GCC 10.3.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelsDesktopDisplay ServerCompilerFile-SystemScreen ResolutionEPYC Milan-X Linux 5.19 Benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - NONE / errors=remount-ro,relatime,rw / Block Size: 4096- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001229 - OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.21.04)- Python 3.9.5- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Linux 5.19 20220607 vs. Linux 5.19 + AMD Patch ComparisonPhoronix Test SuiteBaseline+7.3%+7.3%+14.6%+14.6%+21.9%+21.9%29.1%25.9%7.1%6.8%5.3%4.4%3.6%2.9%2.8%2.6%2.5%2.3%2.3%2.2%2.1%2.1%2.1%100 - 250 - Read Write - Average Latency100 - 250 - Read WriteNASNet Mobile8.7%Speed 10 Realtime - Bosphorus 4KInception V4Mobilenet Float6.5%100 - 500 - Read WriteDefault5.1%10 - Bosphorus 4K4.8%Mobilenet Quant4.7%19, Long Mode - D.SRand Write - IO_uring - Yes - No - 4KB4%Rand Write - IO_uring - Yes - No - 4KB4%3 - Compression Speed3.7%19 - Compression SpeedSqueezeNet3.3%16 - Thread3%100 - 500 - Read Write - Average LatencyBosphorus 4K619 - D.SRand Read - IO_uring - No - Yes - 4KBRand Write - IO_uring - No - Yes - 4KBRand Write - IO_uring - No - No - 4KBRand Write - IO_uring - No - No - 4KBRand Read - IO_uring - No - Yes - 4KBRand Write - IO_uring - No - Yes - 4KB32 - Process2%PostgreSQL pgbenchPostgreSQL pgbenchTensorFlow LiteAOM AV1TensorFlow LiteTensorFlow LitePostgreSQL pgbenchWebP2 Image EncodeSVT-HEVCTensorFlow LiteZstd CompressionFlexible IO TesterFlexible IO TesterZstd CompressionZstd CompressionTensorFlow LiteHackbenchPostgreSQL pgbenchx264libavif avifencZstd CompressionFlexible IO TesterFlexible IO TesterFlexible IO TesterFlexible IO TesterFlexible IO TesterFlexible IO TesterHackbenchLinux 5.19 20220607Linux 5.19 + AMD Patch

EPYC Milan-X Linux 5.19 Benchmarkswebp2: Defaultsvt-hevc: 10 - Bosphorus 4Kcompress-zstd: 19, Long Mode - Decompression Speedfio: Rand Write - IO_uring - Yes - No - 4KB - Default Test Directoryfio: Rand Write - IO_uring - Yes - No - 4KB - Default Test Directorycompress-zstd: 19 - Compression Speedhackbench: 16 - Threadavifenc: 6compress-zstd: 19 - Decompression Speedfio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - No - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - No - 4KB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directoryhackbench: 32 - Processgromacs: MPI CPU - water_GMX50_barepgbench: 100 - 250 - Read Onlygraph500: 26svt-av1: Preset 12 - Bosphorus 4Khackbench: 16 - Processcompress-7zip: Decompression Ratinggraph500: 26aom-av1: Speed 9 Realtime - Bosphorus 4Kcompress-zstd: 19, Long Mode - Compression Speedbuild-mplayer: Time To Compilefio: Rand Read - IO_uring - No - No - 4KB - Default Test Directorybuild-gem5: Time To Compilefio: Rand Read - IO_uring - No - No - 4KB - Default Test Directorypgbench: 100 - 250 - Read Only - Average Latencycompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionpgbench: 100 - 500 - Read Onlypgbench: 100 - 500 - Read Only - Average Latencygraph500: 26build-linux-kernel: defconfigfio: Rand Read - IO_uring - Yes - No - 4KB - Default Test Directorynettle: poly1305-aesnettle: sha512fio: Rand Read - IO_uring - Yes - No - 4KB - Default Test Directoryhpcg: fio: Rand Read - IO_uring - Yes - Yes - 4KB - Default Test Directorysimdjson: PartialTweetsetcpak: Multi-Threaded - ETC2compress-7zip: Compression Ratingnamd: ATPase Simulation - 327,506 Atomsavifenc: 6, Losslessfio: Rand Read - IO_uring - Yes - Yes - 4KB - Default Test Directorywebp2: Quality 75, Compression Effort 7ospray-studio: 3 - 1080p - 32 - Path Tracerpgbench: 1000 - 250 - Read Onlyospray-studio: 1 - 1080p - 32 - Path Tracergraph500: 26nettle: aes256ospray-studio: 2 - 1080p - 32 - Path Tracernettle: chachawebp2: Quality 95, Compression Effort 7compress-zstd: 3 - Decompression Speednginx: 1000nginx: 500nginx: 200blender: Pabellon Barcelona - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Classroom - CPU-Onlyblender: BMW27 - CPU-Onlyrocksdb: Read Rand Write Randrocksdb: Read While Writingrocksdb: Update Randrocksdb: Rand Readcassandra: Writesctx-clock: Context Switch Timestress-ng: System V Message Passingstress-ng: Socket Activitystress-ng: Memory Copyingstress-ng: Semaphoresstress-ng: CPU Cachestress-ng: SENDFILEstress-ng: IO_uringstress-ng: Forkingstress-ng: Mallocstress-ng: Cryptostress-ng: Atomicstress-ng: MEMFDstress-ng: Futexstress-ng: NUMAstress-ng: MMAPsqlite-speedtest: Timed Time - Size 1,000pgbench: 1000 - 500 - Read Write - Average Latencypgbench: 1000 - 500 - Read Writepgbench: 1000 - 250 - Read Write - Average Latencypgbench: 1000 - 250 - Read Writepgbench: 1000 - 250 - Read Only - Average Latencyrenaissance: In-Memory Database Shootoutrenaissance: Finagle HTTP Requestsrenaissance: Savina Reactors.IOsimdjson: DistinctUserIDsimdjson: LargeRandsimdjson: TopTweetsimdjson: Kostyastress-ng: Context Switchingredis: SETredis: GETpgbench: 1000 - 500 - Read Only - Average Latencypgbench: 1000 - 500 - Read Onlypgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 500 - Read Writepgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writetensorflow-lite: Inception ResNet V2tensorflow-lite: Mobilenet Quanttensorflow-lite: Mobilenet Floattensorflow-lite: NASNet Mobiletensorflow-lite: Inception V4tensorflow-lite: SqueezeNetx264: Bosphorus 4Ksvt-hevc: 7 - Bosphorus 4Ksvt-av1: Preset 10 - Bosphorus 4Kaom-av1: Speed 10 Realtime - Bosphorus 4Kcompress-zstd: 3 - Compression Speedrenaissance: Scala Dottyfio: Rand Write - IO_uring - Yes - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - Yes - Yes - 4KB - Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch2.463178.563184.31035265000102.612.5233.9903127.0277000219000852218000108385622.27610.9402516858292349000139.69912.50572348535447000041.8660.38.2371098182.8062810000.0992.25525299790.19857959600017.8807232513.98552.1518500038.27787283.663627.6475069570.222927.574186333111.7751035969748187345719400005400.758912887.73240.5773483.593150.0991300.0289622.0153.95136.4737.1035.8121.542473540161957452180455417871092156381347383539.9460982.1311663.5114458352.4016.972013711.499137377.7044455.03589340557.44166531.76121587.922136.381891191.74220.124685.1256.24629.7241682813.122191030.3598100.89565.312962.34.200.934.142.7418835617.111799548.941957662.310.70771193723.933209249.0652828116084928512.69516.7919925693947.615419.869.86142.24125.38344.745543.01009.025685710032.588170.423323.9995254800106.312.8943.8873204.0283333224000871222667110687422.71310.7502560940297410000142.06412.70173353635911800042.4061.08.3321110180.8582840000.0982.23325433200.19758239500017.7987262524.07550.1318566738.38567263.673636.4545081440.222447.558186000111.9321034669833087395721830005398.798914887.88240.5750.3594.200.934.142.7423.251220347.0213561015881429858.410131.3021651587983.415924.171.82142.82127.62147.905346.0255333997OpenBenchmarking.org

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: DefaultLinux 5.19 20220607Linux 5.19 + AMD Patch0.58231.16461.74692.32922.9115SE +/- 0.027, N = 3SE +/- 0.036, N = 152.4632.5881. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KLinux 5.19 20220607Linux 5.19 + AMD Patch4080120160200SE +/- 2.53, N = 15SE +/- 1.95, N = 3178.56170.421. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedLinux 5.19 20220607Linux 5.19 + AMD Patch7001400210028003500SE +/- 85.91, N = 3SE +/- 21.80, N = 53184.33323.91. (CC) gcc options: -O3 -pthread -lz -llzma

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.29Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch2004006008001000SE +/- 14.84, N = 3SE +/- 9.30, N = 1510359951. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.29Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch60K120K180K240K300KSE +/- 4000.00, N = 3SE +/- 2390.86, N = 152650002548001. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedLinux 5.19 20220607Linux 5.19 + AMD Patch20406080100SE +/- 1.06, N = 3SE +/- 1.28, N = 14102.6106.31. (CC) gcc options: -O3 -pthread -lz -llzma

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ThreadLinux 5.19 20220607Linux 5.19 + AMD Patch3691215SE +/- 0.12, N = 6SE +/- 0.17, N = 312.5212.891. (CC) gcc options: -lpthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6Linux 5.19 20220607Linux 5.19 + AMD Patch0.89781.79562.69343.59124.489SE +/- 0.057, N = 3SE +/- 0.042, N = 33.9903.8871. (CXX) g++ options: -O3 -fPIC -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedLinux 5.19 20220607Linux 5.19 + AMD Patch7001400210028003500SE +/- 56.07, N = 3SE +/- 11.31, N = 143127.03204.01. (CC) gcc options: -O3 -pthread -lz -llzma

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.29Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch60K120K180K240K300KSE +/- 3605.55, N = 3SE +/- 1201.85, N = 32770002833331. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.29Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch50K100K150K200K250KSE +/- 1154.70, N = 3SE +/- 1000.00, N = 32190002240001. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.29Type: Random Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch2004006008001000SE +/- 2.08, N = 3SE +/- 2.85, N = 38528711. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.29Type: Random Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch50K100K150K200K250KSE +/- 577.35, N = 3SE +/- 881.92, N = 32180002226671. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.29Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch2004006008001000SE +/- 14.33, N = 3SE +/- 4.16, N = 3108311061. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.29Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch2004006008001000SE +/- 5.51, N = 3SE +/- 4.67, N = 38568741. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: ProcessLinux 5.19 20220607Linux 5.19 + AMD Patch510152025SE +/- 0.06, N = 3SE +/- 0.25, N = 322.2822.711. (CC) gcc options: -lpthread

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_bareLinux 5.19 20220607Linux 5.19 + AMD Patch3691215SE +/- 0.08, N = 3SE +/- 0.08, N = 310.9410.751. (CXX) g++ options: -O3 -pthread

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyLinux 5.19 20220607Linux 5.19 + AMD Patch500K1000K1500K2000K2500KSE +/- 17315.79, N = 3SE +/- 32981.16, N = 3251685825609401. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26Linux 5.19 20220607Linux 5.19 + AMD Patch60M120M180M240M300M2923490002974100001. (CC) gcc options: -fcommon -O3 -lpthread -lm -pthread -lmpi

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 12 - Input: Bosphorus 4KLinux 5.19 20220607Linux 5.19 + AMD Patch306090120150SE +/- 1.97, N = 15SE +/- 2.08, N = 15139.70142.061. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ProcessLinux 5.19 20220607Linux 5.19 + AMD Patch3691215SE +/- 0.14, N = 4SE +/- 0.06, N = 312.5112.701. (CC) gcc options: -lpthread

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 21.06Test: Decompression RatingLinux 5.19 20220607Linux 5.19 + AMD Patch160K320K480K640K800KSE +/- 11361.01, N = 3SE +/- 1430.55, N = 37234857335361. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26Linux 5.19 20220607Linux 5.19 + AMD Patch80M160M240M320M400M3544700003591180001. (CC) gcc options: -fcommon -O3 -lpthread -lm -pthread -lmpi

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KLinux 5.19 20220607Linux 5.19 + AMD Patch1020304050SE +/- 0.57, N = 15SE +/- 0.51, N = 341.8642.401. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedLinux 5.19 20220607Linux 5.19 + AMD Patch1428425670SE +/- 0.23, N = 3SE +/- 0.60, N = 560.361.01. (CC) gcc options: -O3 -pthread -lz -llzma

Timed MPlayer Compilation

This test times how long it takes to build the MPlayer open-source media player program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompileLinux 5.19 20220607Linux 5.19 + AMD Patch246810SE +/- 0.056, N = 3SE +/- 0.036, N = 38.2378.332

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.29Type: Random Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch2004006008001000SE +/- 12.88, N = 3SE +/- 12.89, N = 4109811101. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To CompileLinux 5.19 20220607Linux 5.19 + AMD Patch4080120160200SE +/- 1.66, N = 3SE +/- 0.82, N = 3182.81180.86

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.29Type: Random Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch60K120K180K240K300KSE +/- 3055.05, N = 3SE +/- 3415.65, N = 42810002840001. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyLinux 5.19 20220607Linux 5.19 + AMD Patch0.02230.04460.06690.08920.1115SE +/- 0.001, N = 3SE +/- 0.001, N = 30.0990.0981. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Parallel BZIP2 Compression

This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionLinux 5.19 20220607Linux 5.19 + AMD Patch0.50741.01481.52222.02962.5372.2552.2331. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyLinux 5.19 20220607Linux 5.19 + AMD Patch500K1000K1500K2000K2500KSE +/- 11372.43, N = 3SE +/- 7217.73, N = 3252997925433201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyLinux 5.19 20220607Linux 5.19 + AMD Patch0.04460.08920.13380.17840.223SE +/- 0.001, N = 3SE +/- 0.001, N = 30.1980.1971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26Linux 5.19 20220607Linux 5.19 + AMD Patch120M240M360M480M600M5795960005823950001. (CC) gcc options: -fcommon -O3 -lpthread -lm -pthread -lmpi

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.16Build: defconfigLinux 5.19 20220607Linux 5.19 + AMD Patch48121620SE +/- 0.05, N = 3SE +/- 0.06, N = 317.8817.80

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.29Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch160320480640800SE +/- 8.34, N = 4SE +/- 8.65, N = 37237261. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Nettle

GNU Nettle is a low-level cryptographic library used by GnuTLS and other software. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: poly1305-aesLinux 5.19 20220607Linux 5.19 + AMD Patch5001000150020002500SE +/- 8.21, N = 3SE +/- 0.54, N = 32513.982524.071. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: sha512Linux 5.19 20220607Linux 5.19 + AMD Patch120240360480600SE +/- 0.02, N = 3SE +/- 1.49, N = 3552.15550.131. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.29Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch40K80K120K160K200KSE +/- 2160.25, N = 4SE +/- 2403.70, N = 31850001856671. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Linux 5.19 20220607Linux 5.19 + AMD Patch918273645SE +/- 0.05, N = 3SE +/- 0.05, N = 338.2838.391. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.29Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch160320480640800SE +/- 10.20, N = 37287261. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsLinux 5.19 20220607Linux 5.19 + AMD Patch0.82581.65162.47743.30324.129SE +/- 0.00, N = 3SE +/- 0.00, N = 33.663.671. (CXX) g++ options: -O3 -pthread

Etcpak

Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Multi-Threaded - Configuration: ETC2Linux 5.19 20220607Linux 5.19 + AMD Patch8001600240032004000SE +/- 30.94, N = 15SE +/- 8.14, N = 33627.653636.451. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 21.06Test: Compression RatingLinux 5.19 20220607Linux 5.19 + AMD Patch110K220K330K440K550KSE +/- 2658.66, N = 3SE +/- 3451.49, N = 35069575081441. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsLinux 5.19 20220607Linux 5.19 + AMD Patch0.05020.10040.15060.20080.251SE +/- 0.00184, N = 3SE +/- 0.00178, N = 30.222920.22244

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessLinux 5.19 20220607Linux 5.19 + AMD Patch246810SE +/- 0.053, N = 3SE +/- 0.054, N = 37.5747.5581. (CXX) g++ options: -O3 -fPIC -lm

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.29Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch40K80K120K160K200KSE +/- 881.92, N = 3SE +/- 2516.61, N = 31863331860001. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 75, Compression Effort 7Linux 5.19 20220607Linux 5.19 + AMD Patch306090120150SE +/- 0.03, N = 3SE +/- 0.10, N = 3111.78111.931. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread

OSPray Studio

Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerLinux 5.19 20220607Linux 5.19 + AMD Patch2K4K6K8K10KSE +/- 20.53, N = 3SE +/- 5.93, N = 310359103461. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read OnlyLinux 5.19 20220607Linux 5.19 + AMD Patch150K300K450K600K750KSE +/- 7402.83, N = 12SE +/- 10163.45, N = 126974816983301. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OSPray Studio

Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerLinux 5.19 20220607Linux 5.19 + AMD Patch2K4K6K8K10KSE +/- 8.33, N = 3SE +/- 3.48, N = 3873487391. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26Linux 5.19 20220607Linux 5.19 + AMD Patch120M240M360M480M600M5719400005721830001. (CC) gcc options: -fcommon -O3 -lpthread -lm -pthread -lmpi

Nettle

GNU Nettle is a low-level cryptographic library used by GnuTLS and other software. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: aes256Linux 5.19 20220607Linux 5.19 + AMD Patch12002400360048006000SE +/- 0.99, N = 3SE +/- 1.51, N = 35400.755398.79MIN: 4104.2 / MAX: 8000.83MIN: 4100.89 / MAX: 7999.631. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

OSPray Studio

Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerLinux 5.19 20220607Linux 5.19 + AMD Patch2K4K6K8K10KSE +/- 0.88, N = 3SE +/- 9.40, N = 3891289141. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread

Nettle

GNU Nettle is a low-level cryptographic library used by GnuTLS and other software. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: chachaLinux 5.19 20220607Linux 5.19 + AMD Patch2004006008001000SE +/- 0.15, N = 3SE +/- 0.25, N = 3887.73887.88MIN: 434.05 / MAX: 2525.12MIN: 433.77 / MAX: 2527.691. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 95, Compression Effort 7Linux 5.19 20220607Linux 5.19 + AMD Patch50100150200250SE +/- 0.35, N = 3SE +/- 0.92, N = 3240.58240.581. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Decompression SpeedLinux 5.19 2022060770014002100280035003483.51. (CC) gcc options: -O3 -pthread -lz -llzma

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000Linux 5.19 2022060720K40K60K80K100KSE +/- 122.64, N = 393150.091. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500Linux 5.19 2022060720K40K60K80K100KSE +/- 202.09, N = 391300.021. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200Linux 5.19 2022060720K40K60K80K100KSE +/- 243.15, N = 389622.011. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.83.5Blend File: Pabellon Barcelona - Compute: CPU-OnlyLinux 5.19 202206071224364860SE +/- 0.14, N = 353.95

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.83.5Blend File: Barbershop - Compute: CPU-OnlyLinux 5.19 20220607306090120150SE +/- 0.40, N = 3136.47

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.83.5Blend File: Fishy Cat - Compute: CPU-OnlyLinux 5.19 20220607918273645SE +/- 0.10, N = 337.10

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.83.5Blend File: Classroom - Compute: CPU-OnlyLinux 5.19 20220607816243240SE +/- 0.08, N = 335.81

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.83.5Blend File: BMW27 - Compute: CPU-OnlyLinux 5.19 20220607510152025SE +/- 0.18, N = 321.54

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Read Random Write RandomLinux 5.19 20220607500K1000K1500K2000K2500KSE +/- 15091.06, N = 324735401. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Read While WritingLinux 5.19 202206073M6M9M12M15MSE +/- 232074.13, N = 12161957451. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Update RandomLinux 5.19 2022060750K100K150K200K250KSE +/- 2031.90, N = 32180451. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Random ReadLinux 5.19 20220607120M240M360M480M600MSE +/- 590144.73, N = 35417871091. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: WritesLinux 5.19 2022060750K100K150K200K250KSE +/- 1874.36, N = 3215638

ctx_clock

Ctx_clock is a simple test program to measure the context switch time in clock cycles. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeLinux 5.19 20220607306090120150SE +/- 1.57, N = 14134

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: System V Message PassingLinux 5.19 202206071.6M3.2M4.8M6.4M8MSE +/- 6644.72, N = 37383539.941. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Socket ActivityLinux 5.19 2022060713K26K39K52K65KSE +/- 665.44, N = 1560982.131. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Memory CopyingLinux 5.19 202206072K4K6K8K10KSE +/- 109.56, N = 311663.511. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: SemaphoresLinux 5.19 202206073M6M9M12M15MSE +/- 29489.44, N = 314458352.401. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: CPU CacheLinux 5.19 2022060748121620SE +/- 0.02, N = 316.971. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: SENDFILELinux 5.19 20220607400K800K1200K1600K2000KSE +/- 5158.71, N = 32013711.491. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: IO_uringLinux 5.19 202206072M4M6M8M10MSE +/- 95013.84, N = 159137377.701. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: ForkingLinux 5.19 2022060710K20K30K40K50KSE +/- 136.67, N = 344455.031. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: MallocLinux 5.19 20220607130M260M390M520M650MSE +/- 2025129.07, N = 3589340557.441. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: CryptoLinux 5.19 2022060740K80K120K160K200KSE +/- 294.93, N = 3166531.761. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: AtomicLinux 5.19 2022060730K60K90K120K150KSE +/- 437.85, N = 3121587.921. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: MEMFDLinux 5.19 202206075001000150020002500SE +/- 2.11, N = 32136.381. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: FutexLinux 5.19 20220607400K800K1200K1600K2000KSE +/- 28813.94, N = 121891191.741. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: NUMALinux 5.19 2022060750100150200250SE +/- 0.12, N = 3220.121. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: MMAPLinux 5.19 2022060710002000300040005000SE +/- 10.81, N = 34685.121. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Linux 5.19 202206071326395265SE +/- 0.11, N = 356.251. (CC) gcc options: -O2 -ldl -lz -lpthread

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average LatencyLinux 5.19 20220607714212835SE +/- 0.30, N = 529.721. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read WriteLinux 5.19 202206074K8K12K16K20KSE +/- 172.65, N = 5168281. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average LatencyLinux 5.19 202206073691215SE +/- 0.20, N = 1213.121. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read WriteLinux 5.19 202206074K8K12K16K20KSE +/- 305.86, N = 12191031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average LatencyLinux 5.19 20220607Linux 5.19 + AMD Patch0.08080.16160.24240.32320.404SE +/- 0.004, N = 12SE +/- 0.005, N = 120.3590.3591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: In-Memory Database ShootoutLinux 5.19 202206072K4K6K8K10KSE +/- 59.72, N = 128100.8MIN: 7218.4 / MAX: 10092.45

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Finagle HTTP RequestsLinux 5.19 202206072K4K6K8K10KSE +/- 75.78, N = 39565.3MIN: 8755 / MAX: 9899.66

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Savina Reactors.IOLinux 5.19 202206073K6K9K12K15KSE +/- 142.46, N = 312962.3MIN: 12699.74 / MAX: 23396.29

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDLinux 5.19 20220607Linux 5.19 + AMD Patch0.9451.892.8353.784.725SE +/- 0.00, N = 3SE +/- 0.00, N = 34.204.201. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomLinux 5.19 20220607Linux 5.19 + AMD Patch0.20930.41860.62790.83721.0465SE +/- 0.00, N = 3SE +/- 0.00, N = 30.930.931. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetLinux 5.19 20220607Linux 5.19 + AMD Patch0.93151.8632.79453.7264.6575SE +/- 0.00, N = 3SE +/- 0.00, N = 34.144.141. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaLinux 5.19 20220607Linux 5.19 + AMD Patch0.61651.2331.84952.4663.0825SE +/- 0.01, N = 3SE +/- 0.00, N = 32.742.741. (CXX) g++ options: -O3 -pthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Context SwitchingLinux 5.19 202206074M8M12M16M20MSE +/- 1970197.83, N = 1518835617.111. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETLinux 5.19 20220607400K800K1200K1600K2000KSE +/- 60225.81, N = 121799548.941. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETLinux 5.19 20220607400K800K1200K1600K2000KSE +/- 38791.33, N = 121957662.311. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool. This current test profile currently just stresses the Redis protocol and basic options exposed wotj a 1:1 Set/Get ratio, 30 pipeline, 100 clients per thread, and thread count equal to the number of CPU cores/threads present. Patches to extend the test are welcome as always. Currently this test profile uses Memtier_benchmark 1.3 and Redis 6. Learn more via the OpenBenchmarking.org test page.

Protocol: Redis

Linux 5.19 20220607: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read Only - Average LatencyLinux 5.19 202206070.15910.31820.47730.63640.7955SE +/- 0.016, N = 120.7071. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read OnlyLinux 5.19 20220607150K300K450K600K750KSE +/- 18116.28, N = 127119371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyLinux 5.19 20220607Linux 5.19 + AMD Patch612182430SE +/- 0.28, N = 12SE +/- 0.93, N = 1223.9323.251. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WriteLinux 5.19 20220607Linux 5.19 + AMD Patch5K10K15K20K25KSE +/- 253.33, N = 12SE +/- 1210.62, N = 1220924220341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyLinux 5.19 20220607Linux 5.19 + AMD Patch3691215SE +/- 0.417, N = 12SE +/- 0.025, N = 39.0657.0211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteLinux 5.19 20220607Linux 5.19 + AMD Patch8K16K24K32K40KSE +/- 1401.39, N = 12SE +/- 124.76, N = 328281356101. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2Linux 5.19 20220607Linux 5.19 + AMD Patch30K60K90K120K150KSE +/- 4666.03, N = 15SE +/- 5408.96, N = 13160849158814

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet QuantLinux 5.19 20220607Linux 5.19 + AMD Patch6K12K18K24K30KSE +/- 679.05, N = 15SE +/- 771.86, N = 1528512.629858.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatLinux 5.19 20220607Linux 5.19 + AMD Patch2K4K6K8K10KSE +/- 375.59, N = 15SE +/- 378.50, N = 159516.7910131.30

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet MobileLinux 5.19 20220607Linux 5.19 + AMD Patch50K100K150K200K250KSE +/- 9562.38, N = 15SE +/- 13020.96, N = 15199256216515

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4Linux 5.19 20220607Linux 5.19 + AMD Patch20K40K60K80K100KSE +/- 3855.49, N = 15SE +/- 2495.14, N = 1293947.687983.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetLinux 5.19 20220607Linux 5.19 + AMD Patch3K6K9K12K15KSE +/- 515.90, N = 15SE +/- 533.69, N = 1515419.815924.1

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

Count: 32 - Type: Thread

Linux 5.19 20220607: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: Creating fdpair (error: Too many open files)

Linux 5.19 + AMD Patch: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: Creating fdpair (error: Too many open files)

Parallel BZIP2 Compression

This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.

Linux 5.19 20220607: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

x264

This is a multi-threaded test of the x264 video encoder run on the CPU with a choice of 1080p or 4K video input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2022-02-22Video Input: Bosphorus 4KLinux 5.19 20220607Linux 5.19 + AMD Patch1632486480SE +/- 1.15, N = 15SE +/- 1.41, N = 1569.8671.821. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K

Linux 5.19 20220607: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Linux 5.19 + AMD Patch: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Tuning: VMAF Optimized - Input: Bosphorus 4K

Linux 5.19 20220607: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Linux 5.19 + AMD Patch: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KLinux 5.19 20220607Linux 5.19 + AMD Patch306090120150SE +/- 7.39, N = 12SE +/- 7.51, N = 12142.24142.821. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 10 - Input: Bosphorus 4KLinux 5.19 20220607Linux 5.19 + AMD Patch306090120150SE +/- 5.40, N = 12SE +/- 5.61, N = 12125.38127.621. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KLinux 5.19 20220607Linux 5.19 + AMD Patch1122334455SE +/- 0.81, N = 15SE +/- 0.62, N = 344.7447.901. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression SpeedLinux 5.19 20220607Linux 5.19 + AMD Patch12002400360048006000SE +/- 90.25, N = 12SE +/- 82.95, N = 155543.05346.01. (CC) gcc options: -O3 -pthread -lz -llzma

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Scala DottyLinux 5.19 202206072004006008001000SE +/- 25.19, N = 121009.0MIN: 727.48 / MAX: 1571.33

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.29Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch60K120K180K240K300KSE +/- 4587.20, N = 14SE +/- 2668.45, N = 152568572553331. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.29Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.19 20220607Linux 5.19 + AMD Patch2004006008001000SE +/- 17.97, N = 14SE +/- 10.42, N = 1510039971. (CC) gcc options: -rdynamic -ltcmalloc -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

122 Results Shown

WebP2 Image Encode
SVT-HEVC
Zstd Compression
Flexible IO Tester:
  Rand Write - IO_uring - Yes - No - 4KB - Default Test Directory:
    MB/s
    IOPS
Zstd Compression
Hackbench
libavif avifenc
Zstd Compression
Flexible IO Tester:
  Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory
  Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory
  Rand Write - IO_uring - No - No - 4KB - Default Test Directory
  Rand Write - IO_uring - No - No - 4KB - Default Test Directory
  Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory
  Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory
Hackbench
GROMACS
PostgreSQL pgbench
Graph500
SVT-AV1
Hackbench
7-Zip Compression
Graph500
AOM AV1
Zstd Compression
Timed MPlayer Compilation
Flexible IO Tester
Timed Gem5 Compilation
Flexible IO Tester
PostgreSQL pgbench
Parallel BZIP2 Compression
PostgreSQL pgbench:
  100 - 500 - Read Only
  100 - 500 - Read Only - Average Latency
Graph500
Timed Linux Kernel Compilation
Flexible IO Tester
Nettle:
  poly1305-aes
  sha512
Flexible IO Tester
High Performance Conjugate Gradient
Flexible IO Tester
simdjson
Etcpak
7-Zip Compression
NAMD
libavif avifenc
Flexible IO Tester
WebP2 Image Encode
OSPray Studio
PostgreSQL pgbench
OSPray Studio
Graph500
Nettle
OSPray Studio
Nettle
WebP2 Image Encode
Zstd Compression
nginx:
  1000
  500
  200
Blender:
  Pabellon Barcelona - CPU-Only
  Barbershop - CPU-Only
  Fishy Cat - CPU-Only
  Classroom - CPU-Only
  BMW27 - CPU-Only
Facebook RocksDB:
  Read Rand Write Rand
  Read While Writing
  Update Rand
  Rand Read
Apache Cassandra
ctx_clock
Stress-NG:
  System V Message Passing
  Socket Activity
  Memory Copying
  Semaphores
  CPU Cache
  SENDFILE
  IO_uring
  Forking
  Malloc
  Crypto
  Atomic
  MEMFD
  Futex
  NUMA
  MMAP
SQLite Speedtest
PostgreSQL pgbench:
  1000 - 500 - Read Write - Average Latency
  1000 - 500 - Read Write
  1000 - 250 - Read Write - Average Latency
  1000 - 250 - Read Write
  1000 - 250 - Read Only - Average Latency
Renaissance:
  In-Memory Database Shootout
  Finagle HTTP Requests
  Savina Reactors.IO
simdjson:
  DistinctUserID
  LargeRand
  TopTweet
  Kostya
Stress-NG
Redis:
  SET
  GET
PostgreSQL pgbench:
  1000 - 500 - Read Only - Average Latency
  1000 - 500 - Read Only
  100 - 500 - Read Write - Average Latency
  100 - 500 - Read Write
  100 - 250 - Read Write - Average Latency
  100 - 250 - Read Write
TensorFlow Lite:
  Inception ResNet V2
  Mobilenet Quant
  Mobilenet Float
  NASNet Mobile
  Inception V4
  SqueezeNet
x264
SVT-HEVC
SVT-AV1
AOM AV1
Zstd Compression
Renaissance
Flexible IO Tester:
  Rand Write - IO_uring - Yes - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s

Linux 5.19 20220607

Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 21.04, Kernel: 5.19.0-051900rc1daily20220607-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001229
Java Notes: OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.21.04)
Python Notes: Python 3.9.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 7 June 2022 08:30 by user phoronix.

Linux 5.19 + AMD Patch

Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 21.04, Kernel: 5.19.0-rc2-amd-patch (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001229
Java Notes: OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.21.04)
Python Notes: Python 3.9.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 June 2022 14:07 by user phoronix.