Ryzen 9 5900X Znver3 GCC 11 Tuned

AMD Ryzen 9 5900X compiler tests for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2103153-PTS-RYZEN95939&grs.

Ryzen 9 5900X Znver3 GCC 11 TunedProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads)ASUS ROG CROSSHAIR VIII HERO (3202 BIOS)AMD Starship/Matisse16GB1000GB Sabrent Rocket 4.0 PlusSapphire AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB (1780/875MHz)AMD Navi 10 HDMI AudioASUS VP28URealtek RTL8125 2.5GbE + Intel I211Ubuntu 20.105.12.0-051200rc2-generic (x86_64) 20210306GNOME Shell 3.38.1X Server 1.20.94.6 Mesa 20.2.1 (LLVM 11.0.0)1.2.131GCC 11.0.1 20210315ext43840x2160OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseEnvironment Details- GCC 11 Znver2: CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2"- GCC 11 Pre-Tuned Znver3: CXXFLAGS="-O3 -march=znver3" CFLAGS="-O3 -march=znver3"- GCC 11 Tuned Znver3: CXXFLAGS="-O3 -march=znver3" CFLAGS="-O3 -march=znver3"Compiler Details- --disable-multilib --enable-checking=releaseProcessor Details- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201009Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 9 5900X Znver3 GCC 11 Tunedfftw: Float + SSE - 2D FFT Size 2048rnnoise: graphics-magick: HWB Color Spaceaom-av1: Speed 8 Realtimecompress-zstd: 3, Long Mode - Compression Speedliquid-dsp: 1 - 256 - 57encode-wavpack: WAV To WavPackngspice: C2670compress-zstd: 8 - Compression Speedgraphics-magick: Rotategraphics-magick: Noise-Gaussiancoremark: CoreMark Size 666 - Iterations Per Secondredis: GETsvt-vp9: VMAF Optimized - Bosphorus 1080pfftw: Stock - 1D FFT Size 4096libraw: Post-Processing Benchmarkaom-av1: Speed 6 Realtimex265: Bosphorus 4Kwebp: Quality 100, Highest Compressionwebp: Quality 100, Losslesssvt-vp9: Visual Quality Optimized - Bosphorus 1080paom-av1: Speed 4 Two-Passencode-mp3: WAV To MP3aom-av1: Speed 6 Two-Passliquid-dsp: 24 - 256 - 57graphics-magick: Resizingngspice: C7552redis: SETcompress-zstd: 19 - Compression Speedhmmer: Pfam Database Searchwebp: Quality 100, Lossless, Highest Compressiongraphics-magick: Swirlsmallpt: Global Illumination Renderer; 128 Samplesastcenc: Exhaustivec-ray: Total Time - 4K, 16 Rays Per PixelGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver34288914.32893298.101015.38081760010.38677.6961072.4920373645138.9228873381005.53214.361326373.3132.5422.725.37613.641201.278.225.58826.17964846667175866.0162685028.4244.879.80928.6099525.85164.099031.6904333014.51197096.62982.87864366710.10776.8651068.0936379642080.7633403356812.88217.521333873.1632.9523.005.36113.519203.418.145.53625.97970606667176666.0662695791.5544.679.95528.6019515.86064.171131.7044531713.90497194.701014.28011800010.30878.3921089.0934379635188.0398093330130.95217.231344974.1532.9222.795.31113.490203.118.205.58926.17970783333176865.7272697891.7544.879.60128.5119545.86964.177831.686OpenBenchmarking.org

FFTW

Build: Float + SSE - Size: 2D FFT Size 2048

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 2048GCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver310K20K30K40K50KSE +/- 327.67, N = 3SE +/- 529.09, N = 3SE +/- 429.31, N = 3428894333045317-march=znver2-march=znver3-march=znver31. (CC) gcc options: -pthread -O3 -lm

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28GCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver348121620SE +/- 0.08, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 314.3314.5113.90-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -pedantic -fvisibility=hidden

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver32004006008001000SE +/- 5.33, N = 3SE +/- 1.45, N = 3SE +/- 4.51, N = 3932970971-march=znver2-march=znver3-march=znver31. (CC) gcc options: -fopenmp -O3 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

AOM AV1

Encoder Mode: Speed 8 Realtime

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 8 RealtimeGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver320406080100SE +/- 0.50, N = 3SE +/- 0.94, N = 3SE +/- 0.84, N = 398.1096.6294.70-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Zstd Compression

Compression Level: 3, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Compression SpeedGCC 11 Pre-Tuned Znver3GCC 11 Znver2GCC 11 Tuned Znver32004006008001000SE +/- 4.29, N = 3SE +/- 12.26, N = 4SE +/- 9.38, N = 151004.61015.31014.2-march=znver3-march=znver2-march=znver31. (CC) gcc options: -O3 -pthread -lz

Liquid-DSP

Threads: 1 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 57GCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver320M40M60M80M100MSE +/- 894548.63, N = 5SE +/- 700170.53, N = 3SE +/- 1031315.83, N = 3808176007864366780118000-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

WavPack Audio Encoding

WAV To WavPack

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver33691215SE +/- 0.08, N = 5SE +/- 0.06, N = 5SE +/- 0.08, N = 510.3910.1110.31-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -O3 -rdynamic

Ngspice

Circuit: C2670

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670GCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver320406080100SE +/- 0.51, N = 15SE +/- 0.85, N = 3SE +/- 0.52, N = 1577.7076.8778.39-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -fopenmp -lm -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE

Zstd Compression

Compression Level: 8 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression SpeedGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver32004006008001000SE +/- 13.07, N = 4SE +/- 10.96, N = 5SE +/- 7.42, N = 31072.41068.01089.0-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -pthread -lz

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver32004006008001000SE +/- 9.54, N = 3SE +/- 9.74, N = 3SE +/- 5.57, N = 3920936934-march=znver2-march=znver3-march=znver31. (CC) gcc options: -fopenmp -O3 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver380160240320400SE +/- 0.33, N = 3SE +/- 0.67, N = 3373379379-march=znver2-march=znver3-march=znver31. (CC) gcc options: -fopenmp -O3 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3140K280K420K560K700KSE +/- 1451.16, N = 3SE +/- 2904.70, N = 3SE +/- 7601.44, N = 3645138.92642080.76635188.04-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O2 -O3 -lrt" -lrt

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3700K1400K2100K2800K3500KSE +/- 36473.74, N = 15SE +/- 39558.07, N = 15SE +/- 34194.49, N = 53381005.533356812.883330130.95-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver350100150200250SE +/- 1.85, N = 3SE +/- 2.21, N = 3SE +/- 2.16, N = 3214.36217.52217.23-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

FFTW

Build: Stock - Size: 1D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 4096GCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver33K6K9K12K15KSE +/- 137.60, N = 3SE +/- 84.45, N = 3SE +/- 63.19, N = 3132631333813449-march=znver2-march=znver3-march=znver31. (CC) gcc options: -pthread -O3 -lm

LibRaw

Post-Processing Benchmark

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver31632486480SE +/- 0.53, N = 3SE +/- 0.97, N = 3SE +/- 0.26, N = 373.3173.1674.15-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -O3 -fopenmp -ljpeg -lz -lm

AOM AV1

Encoder Mode: Speed 6 Realtime

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 6 RealtimeGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3816243240SE +/- 0.17, N = 3SE +/- 0.21, N = 3SE +/- 0.26, N = 332.5432.9532.92-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

x265

Video Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3612182430SE +/- 0.04, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 322.7223.0022.79-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver31.20962.41923.62884.83846.048SE +/- 0.004, N = 3SE +/- 0.027, N = 3SE +/- 0.042, N = 35.3765.3615.311-march=znver2-march=znver3-march=znver31. (CC) gcc options: -fvisibility=hidden -O3 -pthread -lm -ljpeg -lpng16

WebP Image Encode

Encode Settings: Quality 100, Lossless

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver348121620SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 313.6413.5213.49-march=znver2-march=znver3-march=znver31. (CC) gcc options: -fvisibility=hidden -O3 -pthread -lm -ljpeg -lpng16

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver34080120160200SE +/- 0.41, N = 3SE +/- 0.50, N = 3SE +/- 0.68, N = 3201.27203.41203.11-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

AOM AV1

Encoder Mode: Speed 4 Two-Pass

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 4 Two-PassGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3246810SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 38.228.148.20-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3GCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver31.25752.5153.77255.036.2875SE +/- 0.049, N = 3SE +/- 0.059, N = 5SE +/- 0.012, N = 35.5885.5365.589-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm

AOM AV1

Encoder Mode: Speed 6 Two-Pass

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 6 Two-PassGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3612182430SE +/- 0.05, N = 3SE +/- 0.34, N = 3SE +/- 0.08, N = 326.1725.9726.17-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Liquid-DSP

Threads: 24 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 24 - Buffer Length: 256 - Filter Length: 57GCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3200M400M600M800M1000MSE +/- 6356283.14, N = 12SE +/- 1844354.75, N = 3SE +/- 1700807.00, N = 3964846667970606667970783333-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3400800120016002000SE +/- 0.58, N = 3SE +/- 3.21, N = 3SE +/- 3.93, N = 3175817661768-march=znver2-march=znver3-march=znver31. (CC) gcc options: -fopenmp -O3 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

Ngspice

Circuit: C7552

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552GCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver31530456075SE +/- 0.42, N = 3SE +/- 0.65, N = 3SE +/- 0.77, N = 366.0266.0765.73-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -fopenmp -lm -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3600K1200K1800K2400K3000KSE +/- 16069.57, N = 3SE +/- 35424.76, N = 15SE +/- 31559.14, N = 122685028.422695791.552697891.75-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression SpeedGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver31020304050SE +/- 0.07, N = 3SE +/- 0.22, N = 3SE +/- 0.18, N = 344.844.644.8-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -pthread -lz

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver320406080100SE +/- 0.10, N = 3SE +/- 0.41, N = 3SE +/- 0.07, N = 379.8179.9679.60-march=znver2-march=znver3-march=znver31. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

WebP Image Encode

Encode Settings: Quality 100, Lossless, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3714212835SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 328.6128.6028.51-march=znver2-march=znver3-march=znver31. (CC) gcc options: -fvisibility=hidden -O3 -pthread -lm -ljpeg -lpng16

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver32004006008001000SE +/- 1.45, N = 3SE +/- 0.67, N = 3SE +/- 2.60, N = 3952951954-march=znver2-march=znver3-march=znver31. (CC) gcc options: -fopenmp -O3 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

Smallpt

Global Illumination Renderer; 128 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver31.32052.6413.96155.2826.6025SE +/- 0.006, N = 3SE +/- 0.007, N = 3SE +/- 0.017, N = 35.8515.8605.869-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -fopenmp -O3

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: ExhaustiveGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver31428425670SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 364.1064.1764.18-march=znver2-march=znver3-march=znver31. (CXX) g++ options: -O3 -flto -pthread

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelGCC 11 Znver2GCC 11 Pre-Tuned Znver3GCC 11 Tuned Znver3714212835SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 331.6931.7031.69-march=znver2-march=znver3-march=znver31. (CC) gcc options: -lm -lpthread -O3

Phoronix Test Suite v10.8.4