new 2025

AMD EPYC 9655P 96-Core testing with a Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS) and ASPEED on Ubuntu 24.10 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 2501190-NE-NEW20253068
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
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
a
January 19
  1 Hour
b
January 19
  2 Hours, 9 Minutes
c
January 19
  1 Hour, 1 Minute
d
January 19
  1 Hour, 1 Minute
e
January 19
  8 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 4 Minutes

Only show results where is faster than
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):


new 2025OpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads)Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS)AMD 1Ah12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF3201GB Micron_7450_MTFDKCB3T2TFSASPEED2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 24.106.13.0-rc4-phx-stock (x86_64)GNOME Shell 47.0X ServerGCC 14.2.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionNew 2025 BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcdeLogarithmic Result OverviewPhoronix Test SuiteStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGStress-NGCryptoPipeCloningMMAPPollMutexFutexForkingMEMFDMallocNUMAPthreadAtomicHashZlib

new 2025ncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - vision_transformerstress-ng: Pipencnn: CPU - resnet50ncnn: CPU-v3-v3 - mobilenet-v3stress-ng: Glibc C String Functionsncnn: CPU - shufflenet-v2llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512stress-ng: Cloningstress-ng: MMAPllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024stress-ng: Exponential Mathncnn: CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: CPU - mobilenetstress-ng: Pollncnn: CPU - FastestDetstress-ng: SENDFILEstress-ng: Semaphoresstress-ng: Mutexncnn: CPU - yolov4-tinyllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512stress-ng: Futexncnn: CPU - efficientnet-b0stress-ng: System V Message Passingllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024stress-ng: Mixed Schedulerncnn: CPU - regnety_400mllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512stress-ng: Forkingllama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048stress-ng: IO_uringncnn: CPU - mnasnetncnn: CPU - blazefacencnn: CPU - alexnetllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048stress-ng: Context Switchingstress-ng: MEMFDncnn: CPU - squeezenet_ssdstress-ng: Memory Copyingstress-ng: Jpeg Compressionstress-ng: Fractal Generatorstress-ng: Mallocstress-ng: Integer Bit Operationsstress-ng: NUMAllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128stress-ng: Glibc Qsort Data Sortingstress-ng: Trigonometric Mathstress-ng: CPU Stressstress-ng: Vector Shufflencnn: CPU-v2-v2 - mobilenet-v2stress-ng: AVX-512 VNNIllama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128stress-ng: Integer Mathllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128stress-ng: POSIX Regular Expressionsstress-ng: Logarithmic Mathstress-ng: Vector Floating Pointstress-ng: Floating Pointstress-ng: Power Mathstress-ng: AVL Treestress-ng: Function Callstress-ng: Pthreadstress-ng: Bitonic Integer Sortstress-ng: Socket Activitystress-ng: Atomicstress-ng: Radix String Sortstress-ng: Fused Multiply-Addstress-ng: Hashstress-ng: Matrix Mathstress-ng: Bessel Math Operationsstress-ng: Matrix 3D Mathstress-ng: Hyperbolic Trigonometric Mathstress-ng: Vector Mathstress-ng: Wide Vector Mathstress-ng: x86_64 RdRandstress-ng: Zlibstress-ng: CPU Cachestress-ng: Cryptoabcde6.7825.312.7128.8393409969.8413.596.27107612437.816.51111.8317095.9610428.33105.26383630.4411.6611.6610784198.18.352154952.69308990236.8353532986.4715.57109.123638855.988.7847541326.12351.86110.17122963.0830.93373.19371.1108842.42112.551174584.735.563.663.65111.4363915053.031919.7913.1431375.3288326.04693.4284239015.2623056228.012481.5193.232548.19244291.11248390.7584138.455.7514960065.5647.438891028.4945.72661780.5716302.05379135.3419070.57224273.321160.2286214.78302128.671044.440702.33309.281564.7138497783.1124396187.67502535.3860411.4717150.13593312.686729506924089.9643519846.0911768.971692665.99899403404.9910.4228.3611.4931.1586342322.2314.467.05116765511.696.42115.3917134.679912.94112.48398930.7412.2612.2610723492.788.372246589.22316698667.9352886531.7516.11113.293760562.788.8247921020.68358.35107.87119811.3630.11363.38373.68107808.84110.411158950.965.633.653.63111.2264954321.281900.4213.3131364.5489241.18688.12286876085.5622934130.222497.5893.092568.76243089.84250283.9884762.105.7215009286.8647.68864583.1645.58658699.92715277.29379291.1519039.70224447.951162.5386322.56302585.291046.9740726.66309.501568.14138796151.4124359044.61502617.4260356.6217168.28593034.23672523.576924707.0643509192.0611766.101628433.01770723548.748.0829.8511.2235.0794350773.0712.436.23121505178.266.41112.6717504.839853.41112.48389486.0511.7111.7110308236.168.022197431.31304269865.5753398638.8215.51113.243709094.168.6846473032.42358.79109.42119458.9130.5370.94364.03108924.02109.761159544.855.553.593.69113.3463768508.751901.1113.231565.7188010.39684.29286437650.0522766908.872489.4793.52554.43242366.63249308.7884482.65.7614917255.9947.618841688.145.81660034.85716894.75378253.219000.24223750.111161.9786162.29302063.591045.5340788.38308.811567.3138579068.0924386852.13501693.4260345.117161.93593368.41672908.816921682.4943497875.2311767.971758101.66904442086.589.0137.1514.3427.680625187.9512.536.24121109562.77.18107.1618352.089889.77106.51404064.5311.7211.7210651633.768.062168580.67311249205.7953247347.7815.99109.23675306.138.9747987577.93363.16111.1119549.1230.17366.93373.62110596.05111.81151684.35.663.613.7111.2964355743.861902.3713.131095.3589337.3691.63285984682.2323049501.322499.3194.082568.33242558.25250245.1984525.315.7614905295.147.758897966.8245.85660725.51718105.01379655.6919014.27223675.371158.9986399.13301801.151045.9640689.5309.491567.32138573633.5524350902.07501990.1360304.1317176.65593440.18672816.396926027.0943522600.1111769.341685503.52904135820.1677385407.3317774.049716.7110421659.7251459083.93676509.08109992.731888.5288021758.692511.91302111.18309.3424400600.1211768.36276965.13OpenBenchmarking.org

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: resnet18dcba36912159.018.0810.426.78MIN: 6.6 / MAX: 197.68MIN: 6.59 / MAX: 143.39MIN: 6.5 / MAX: 500.3MIN: 6.57 / MAX: 7.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: vgg16dcba91827364537.1529.8528.3625.30MIN: 19 / MAX: 553.55MIN: 18.57 / MAX: 491.56MIN: 18.62 / MAX: 395.65MIN: 18.81 / MAX: 398.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: googlenetdcba4812162014.3411.2211.4912.71MIN: 11.33 / MAX: 392.85MIN: 10.84 / MAX: 13.82MIN: 11.27 / MAX: 11.81MIN: 10.95 / MAX: 204.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: vision_transformerdcba81624324027.6035.0731.1528.83MIN: 27.29 / MAX: 30.05MIN: 27.34 / MAX: 470.93MIN: 27.65 / MAX: 419.66MIN: 27.44 / MAX: 145.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Pipeedcba20M40M60M80M100MSE +/- 1320514.40, N = 1277385407.3380625187.9594350773.0786342322.2393409969.841. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: resnet50dcba4812162012.5312.4314.4613.59MIN: 12.27 / MAX: 14.64MIN: 12.07 / MAX: 13.04MIN: 12.6 / MAX: 236.39MIN: 12.47 / MAX: 203.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU-v3-v3 - Model: mobilenet-v3dcba2468106.246.237.056.27MIN: 6.16 / MAX: 6.65MIN: 6.15 / MAX: 6.61MIN: 6.19 / MAX: 157.63MIN: 6.19 / MAX: 6.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Glibc C String Functionsdcba30M60M90M120M150M121109562.70121505178.26116765511.69107612437.811. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: shufflenet-v2dcba2468107.186.416.426.51MIN: 6.33 / MAX: 199.41MIN: 6.34 / MAX: 6.7MIN: 6.37 / MAX: 6.67MIN: 6.43 / MAX: 8.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512dcba306090120150107.16112.67115.39111.831. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Cloningedcba4K8K12K16K20KSE +/- 172.38, N = 617774.0418352.0817504.8317134.6717095.961. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: MMAPedcba2K4K6K8K10KSE +/- 9.81, N = 39716.719889.779853.419912.9410428.331. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024dcba306090120150106.51112.48112.48105.261. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Exponential Mathdcba90K180K270K360K450KSE +/- 3969.34, N = 6404064.53389486.05398930.74383630.441. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3dcba369121511.7211.7112.2611.66MIN: 11.52 / MAX: 12.06MIN: 11.51 / MAX: 11.88MIN: 11.83 / MAX: 38.58MIN: 11.45 / MAX: 12.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: mobilenetdcba369121511.7211.7112.2611.66MIN: 11.52 / MAX: 12.06MIN: 11.51 / MAX: 11.88MIN: 11.83 / MAX: 38.58MIN: 11.45 / MAX: 12.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Polledcba2M4M6M8M10MSE +/- 81527.82, N = 310421659.7210651633.7610308236.1610723492.7810784198.101. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: FastestDetdcba2468108.068.028.378.35MIN: 7.94 / MAX: 8.64MIN: 7.85 / MAX: 8.91MIN: 8.21 / MAX: 10.94MIN: 8.22 / MAX: 9.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: SENDFILEdcba500K1000K1500K2000K2500KSE +/- 12520.19, N = 32168580.672197431.312246589.222154952.691. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Semaphoresdcba70M140M210M280M350MSE +/- 3510501.49, N = 5311249205.79304269865.57316698667.93308990236.831. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Mutexedcba11M22M33M44M55MSE +/- 30126.63, N = 351459083.9053247347.7853398638.8252886531.7553532986.471. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: yolov4-tinydcba4812162015.9915.5116.1115.57MIN: 15.01 / MAX: 205MIN: 15.32 / MAX: 20.25MIN: 15.6 / MAX: 79.48MIN: 15.34 / MAX: 17.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512dcba306090120150109.20113.24113.29109.121. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Futexedcba800K1600K2400K3200K4000KSE +/- 30393.34, N = 33676509.083675306.133709094.163760562.783638855.981. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: efficientnet-b0dcba36912158.978.688.828.78MIN: 8.79 / MAX: 9.27MIN: 8.54 / MAX: 8.97MIN: 8.63 / MAX: 15.62MIN: 8.63 / MAX: 9.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: System V Message Passingdcba10M20M30M40M50M47987577.9346473032.4247921020.6847541326.121. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048dcba80160240320400363.16358.79358.35351.861. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024dcba20406080100111.10109.42107.87110.171. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Mixed Schedulerdcba30K60K90K120K150KSE +/- 60.64, N = 3119549.12119458.91119811.36122963.081. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: regnety_400mdcba71421283530.1730.5030.1130.93MIN: 29.93 / MAX: 32.92MIN: 30.05 / MAX: 66.6MIN: 29.92 / MAX: 32.78MIN: 30.33 / MAX: 129.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024dcba80160240320400366.93370.94363.38373.191. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512dcba80160240320400373.62364.03373.68371.101. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Forkingedcba20K40K60K80K100KSE +/- 1165.09, N = 3109992.73110596.05108924.02107808.84108842.421. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048dcba306090120150111.80109.76110.41112.551. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: IO_uringdcba300K600K900K1200K1500KSE +/- 7669.66, N = 31151684.301159544.851158950.961174584.731. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: mnasnetdcba1.27352.5473.82055.0946.36755.665.555.635.56MIN: 5.57 / MAX: 5.92MIN: 5.46 / MAX: 7.51MIN: 5.56 / MAX: 5.81MIN: 5.45 / MAX: 5.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: blazefacedcba0.82351.6472.47053.2944.11753.613.593.653.66MIN: 3.54 / MAX: 4.58MIN: 3.52 / MAX: 3.72MIN: 3.55 / MAX: 3.8MIN: 3.58 / MAX: 3.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: alexnetdcba0.83251.6652.49753.334.16253.703.693.633.65MIN: 3.6 / MAX: 3.96MIN: 3.57 / MAX: 5.69MIN: 3.56 / MAX: 3.96MIN: 3.56 / MAX: 4.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048dcba306090120150111.29113.34111.22111.431. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Context Switchingdcba14M28M42M56M70MSE +/- 279870.92, N = 364355743.8663768508.7564954321.2863915053.031. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: MEMFDedcba400800120016002000SE +/- 2.61, N = 31888.501902.371901.111900.421919.791. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: squeezenet_ssddcba369121513.1013.2013.3113.14MIN: 12.73 / MAX: 22.51MIN: 12.76 / MAX: 15.13MIN: 13.17 / MAX: 15.89MIN: 12.98 / MAX: 13.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Memory Copyingdcba7K14K21K28K35KSE +/- 50.08, N = 331095.3531565.7131364.5431375.321. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Jpeg Compressiondcba20K40K60K80K100KSE +/- 336.69, N = 389337.3088010.3989241.1888326.041. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Fractal Generatordcba150300450600750SE +/- 2.15, N = 3691.63684.29688.12693.401. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Mallocedcba60M120M180M240M300MSE +/- 2355922.46, N = 3288021758.69285984682.23286437650.05286876085.56284239015.261. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Integer Bit Operationsdcba5M10M15M20M25MSE +/- 79034.91, N = 323049501.3222766908.8722934130.2223056228.011. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: NUMAedcba5001000150020002500SE +/- 10.73, N = 32511.912499.312489.472497.582481.511. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128dcba2040608010094.0893.5093.0993.231. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Glibc Qsort Data Sortingdcba60012001800240030002568.332554.432568.762548.191. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Trigonometric Mathdcba50K100K150K200K250KSE +/- 407.29, N = 3242558.25242366.63243089.84244291.111. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: CPU Stressdcba50K100K150K200K250KSE +/- 717.08, N = 3250245.19249308.78250283.98248390.751. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Vector Shuffledcba20K40K60K80K100KSE +/- 192.26, N = 384525.3184482.6084762.1084138.451. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU-v2-v2 - Model: mobilenet-v2dcba1.2962.5923.8885.1846.485.765.765.725.75MIN: 5.65 / MAX: 7.3MIN: 5.66 / MAX: 5.97MIN: 5.61 / MAX: 6.14MIN: 5.65 / MAX: 6.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: AVX-512 VNNIdcba3M6M9M12M15MSE +/- 15958.95, N = 314905295.1014917255.9915009286.8614960065.561. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128dcba112233445547.7547.6147.6047.431. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Integer Mathdcba2M4M6M8M10MSE +/- 12411.99, N = 38897966.828841688.108864583.168891028.491. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128dcba102030405045.8545.8145.5845.721. (CXX) g++ options: -O3

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: POSIX Regular Expressionsdcba140K280K420K560K700K660725.51660034.85658699.92661780.501. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Logarithmic Mathdcba150K300K450K600K750KSE +/- 1549.57, N = 3718105.01716894.75715277.29716302.051. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Vector Floating Pointdcba80K160K240K320K400KSE +/- 955.04, N = 3379655.69378253.20379291.15379135.341. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Floating Pointdcba4K8K12K16K20KSE +/- 30.59, N = 319014.2719000.2419039.7019070.571. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Power Mathdcba50K100K150K200K250KSE +/- 36.82, N = 3223675.37223750.11224447.95224273.321. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: AVL Treedcba30060090012001500SE +/- 2.09, N = 31158.991161.971162.531160.221. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Function Calldcba20K40K60K80K100KSE +/- 75.87, N = 386399.1386162.2986322.5686214.781. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Pthreadedcba60K120K180K240K300KSE +/- 570.54, N = 3302111.18301801.15302063.59302585.29302128.671. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Bitonic Integer Sortdcba2004006008001000SE +/- 1.18, N = 31045.961045.531046.971044.401. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Socket Activitydcba9K18K27K36K45KSE +/- 40.26, N = 340689.5040788.3840726.6640702.331. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Atomicedcba70140210280350SE +/- 0.10, N = 3309.34309.49308.81309.50309.281. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Radix String Sortdcba30060090012001500SE +/- 0.60, N = 31567.321567.301568.141564.701. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Fused Multiply-Adddcba30M60M90M120M150MSE +/- 40538.03, N = 3138573633.55138579068.09138796151.41138497783.111. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Hashedcba5M10M15M20M25MSE +/- 21888.88, N = 324400600.1224350902.0724386852.1324359044.6124396187.671. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Matrix Mathdcba110K220K330K440K550KSE +/- 182.19, N = 3501990.13501693.42502617.42502535.381. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Bessel Math Operationsdcba13K26K39K52K65KSE +/- 3.51, N = 360304.1360345.1060356.6260411.471. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Matrix 3D Mathdcba4K8K12K16K20KSE +/- 5.61, N = 317176.6517161.9317168.2817150.131. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Hyperbolic Trigonometric Mathdcba130K260K390K520K650K593440.18593368.41593034.23593312.681. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Vector Mathdcba140K280K420K560K700KSE +/- 131.15, N = 3672816.39672908.81672523.57672950.001. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Wide Vector Mathdcba1.5M3M4.5M6M7.5MSE +/- 1026.05, N = 36926027.096921682.496924707.066924089.961. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: x86_64 RdRanddcba9M18M27M36M45MSE +/- 8715.59, N = 343522600.1143497875.2343509192.0643519846.091. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Zlibedcba3K6K9K12K15KSE +/- 5.26, N = 311768.3611769.3411767.9711766.1011768.971. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: CPU Cachedcba400K800K1200K1600K2000KSE +/- 34826.19, N = 151685503.521758101.661628433.011692665.991. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.18.09Test: Cryptoedcba200M400M600M800M1000MSE +/- 108830554.05, N = 15276965.13904135820.16904442086.58770723548.74899403404.991. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lGLESv2 -lmpfr -lgmp -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -fipa-pta -fivopts -fmodulo-sched

82 Results Shown

NCNN:
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - vision_transformer
Stress-NG
NCNN:
  CPU - resnet50
  CPU-v3-v3 - mobilenet-v3
Stress-NG
NCNN
Llama.cpp
Stress-NG:
  Cloning
  MMAP
Llama.cpp
Stress-NG
NCNN:
  CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3
  CPU - mobilenet
Stress-NG
NCNN
Stress-NG:
  SENDFILE
  Semaphores
  Mutex
NCNN
Llama.cpp
Stress-NG
NCNN
Stress-NG
Llama.cpp:
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024
Stress-NG
NCNN
Llama.cpp:
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512
Stress-NG
Llama.cpp
Stress-NG
NCNN:
  CPU - mnasnet
  CPU - blazeface
  CPU - alexnet
Llama.cpp
Stress-NG:
  Context Switching
  MEMFD
NCNN
Stress-NG:
  Memory Copying
  Jpeg Compression
  Fractal Generator
  Malloc
  Integer Bit Operations
  NUMA
Llama.cpp
Stress-NG:
  Glibc Qsort Data Sorting
  Trigonometric Math
  CPU Stress
  Vector Shuffle
NCNN
Stress-NG
Llama.cpp
Stress-NG
Llama.cpp
Stress-NG:
  POSIX Regular Expressions
  Logarithmic Math
  Vector Floating Point
  Floating Point
  Power Math
  AVL Tree
  Function Call
  Pthread
  Bitonic Integer Sort
  Socket Activity
  Atomic
  Radix String Sort
  Fused Multiply-Add
  Hash
  Matrix Math
  Bessel Math Operations
  Matrix 3D Math
  Hyperbolic Trigonometric Math
  Vector Math
  Wide Vector Math
  x86_64 RdRand
  Zlib
  CPU Cache
  Crypto