Rocket Lake Core i9 11900K
Benchmarks for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2103298-IB-ROCKETLAK21&grs.
ACES DGEMM
Sustained Floating-Point Rate
oneDNN
Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU
oneDNN
Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU
AOM AV1
Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K
OpenVKL
Benchmark: vklBenchmarkStructuredVolume
Stress-NG
Test: Context Switching
CloverLeaf
Lagrangian-Eulerian Hydrodynamics
ViennaCL
Test: CPU BLAS - dGEMM-NN
NCNN
Target: CPU - Model: googlenet
NCNN
Target: CPU - Model: blazeface
oneDNN
Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU
GraphicsMagick
Operation: Rotate
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU
Selenium
Benchmark: Jetstream 2 - Browser: Firefox
oneDNN
Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU
Swet
Average
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
Selenium
Benchmark: Speedometer - Browser: Firefox
AOM AV1
Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p
FFTW
Build: Float + SSE - Size: 2D FFT Size 4096
NCNN
Target: CPU - Model: vgg16
NCNN
Target: CPU - Model: resnet18
Radiance Benchmark
Test: SMP Parallel
NCNN
Target: CPU - Model: mnasnet
NCNN
Target: CPU - Model: resnet50
Embree
Binary: Pathtracer - Model: Asian Dragon Obj
Stress-NG
Test: CPU Cache
Stress-NG
Test: Atomic
Stockfish
Total Time
x265
Video Input: Bosphorus 4K
simdjson
Throughput Test: DistinctUserID
TTSIOD 3D Renderer
Phong Rendering With Soft-Shadow Mapping
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
AOM AV1
Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU
ASKAP
Test: tConvolve OpenMP - Gridding
GNU Radio
Test: Five Back to Back FIR Filters
TensorFlow Lite
Model: NASNet Mobile
Java Gradle Build
Gradle Build: Reactor
NCNN
Target: CPU - Model: mobilenet
NCNN
Target: CPU - Model: efficientnet-b0
AOM AV1
Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p
NAS Parallel Benchmarks
Test / Class: EP.C
Zstd Compression
Compression Level: 8, Long Mode - Compression Speed
DaCapo Benchmark
Java Test: Tradesoap
John The Ripper
Test: MD5
Selenium
Benchmark: WASM imageConvolute - Browser: Firefox
NCNN
Target: CPU-v2-v2 - Model: mobilenet-v2
ViennaCL
Test: CPU BLAS - dGEMM-NT
Stockfish
Total Time
NAS Parallel Benchmarks
Test / Class: LU.C
OpenVKL
Benchmark: vklBenchmark
OpenVKL
Benchmark: vklBenchmarkVdbVolume
DaCapo Benchmark
Java Test: Jython
NCNN
Target: CPU - Model: alexnet
GraphicsMagick
Operation: HWB Color Space
ViennaCL
Test: CPU BLAS - dGEMM-TT
Zstd Compression
Compression Level: 19, Long Mode - Decompression Speed
DeepSpeech
Acceleration: CPU
OSPray
Demo: San Miguel - Renderer: SciVis
Liquid-DSP
Threads: 2 - Buffer Length: 256 - Filter Length: 57
Numpy Benchmark
Stress-NG
Test: Vector Math
Rodinia
Test: OpenMP Leukocyte
Liquid-DSP
Threads: 8 - Buffer Length: 256 - Filter Length: 57
Selenium
Benchmark: WASM imageConvolute - Browser: Google Chrome
NCNN
Target: CPU-v3-v3 - Model: mobilenet-v3
Zstd Compression
Compression Level: 8 - Compression Speed
Ngspice
Circuit: C2670
BLAKE2
libavif avifenc
Encoder Speed: 6, Lossless
Ngspice
Circuit: C7552
SVT-VP9
Tuning: VMAF Optimized - Input: Bosphorus 1080p
Tachyon
Total Time
SVT-HEVC
Tuning: 10 - Input: Bosphorus 1080p
LeelaChessZero
Backend: BLAS
Xcompact3d Incompact3d
Input: input.i3d 129 Cells Per Direction
GraphicsMagick
Operation: Resizing
Mobile Neural Network
Model: inception-v3
Timed MAFFT Alignment
Multiple Sequence Alignment - LSU RNA
ViennaCL
Test: CPU BLAS - dGEMM-TN
asmFish
1024 Hash Memory, 26 Depth
Darktable
Test: Server Rack - Acceleration: CPU-only
Liquid-DSP
Threads: 1 - Buffer Length: 256 - Filter Length: 57
LeelaChessZero
Backend: Eigen
ONNX Runtime
Model: fcn-resnet101-11 - Device: OpenMP CPU
Perl Benchmarks
Test: Interpreter
Embree
Binary: Pathtracer ISPC - Model: Crown
JPEG XL
Input: JPEG - Encode Speed: 7
OSPray
Demo: XFrog Forest - Renderer: Path Tracer
LibreOffice
Test: 20 Documents To PDF
ASKAP
Test: Hogbom Clean OpenMP
PyPerformance
Benchmark: python_startup
Rodinia
Test: OpenMP CFD Solver
JPEG XL Decoding
CPU Threads: All
ViennaCL
Test: CPU BLAS - sAXPY
LuxCoreRender
Scene: DLSC
Hugin
Panorama Photo Assistant + Stitching Time
Sysbench
Test: RAM / Memory
LuaJIT
Test: Composite
Botan
Test: AES-256 - Decrypt
Selenium
Benchmark: Kraken - Browser: Google Chrome
Mobile Neural Network
Model: MobileNetV2_224
Mobile Neural Network
Model: SqueezeNetV1.0
Botan
Test: AES-256
AOM AV1
Encoder Mode: Speed 8 Realtime
ViennaCL
Test: CPU BLAS - sDOT
librsvg
Operation: SVG Files To PNG
PHPBench
PHP Benchmark Suite
Optcarrot
Optimized Benchmark
FinanceBench
Benchmark: Repo OpenMP
AOM AV1
Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K
WebP2 Image Encode
Encode Settings: Default
Selenium
Benchmark: StyleBench - Browser: Google Chrome
Appleseed
Scene: Disney Material
OpenSCAD
Render: Leonardo Phone Case Slim
AOM AV1
Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p
Embree
Binary: Pathtracer - Model: Crown
ViennaCL
Test: CPU BLAS - dCOPY
LuaRadio
Test: Five Back to Back FIR Filters
Build2
Time To Compile
ViennaCL
Test: CPU BLAS - dAXPY
Appleseed
Scene: Material Tester
John The Ripper
Test: Blowfish
Timed Linux Kernel Compilation
Time To Compile
NCNN
Target: CPU - Model: shufflenet-v2
ViennaCL
Test: CPU BLAS - sCOPY
Mobile Neural Network
Model: mobilenet-v1-1.0
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Ultra Fast
PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: CPU
Stress-NG
Test: CPU Stress
SVT-VP9
Tuning: Visual Quality Optimized - Input: Bosphorus 1080p
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU
PyBench
Total For Average Test Times
LZ4 Compression
Compression Level: 1 - Decompression Speed
srsLTE
Test: OFDM_Test
Stress-NG
Test: Matrix Math
Selenium
Benchmark: ARES-6 - Browser: Firefox
Intel Open Image Denoise
Scene: Memorial
Timed MrBayes Analysis
Primate Phylogeny Analysis
libavif avifenc
Encoder Speed: 10
AOM AV1
Encoder Mode: Speed 4 Two-Pass
Embree
Binary: Pathtracer - Model: Asian Dragon
SVT-VP9
Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
SVT-AV1
Encoder Mode: Enc Mode 8 - Input: 1080p
Timed LLVM Compilation
Time To Compile
Timed GDB GNU Debugger Compilation
Time To Compile
FinanceBench
Benchmark: Bonds OpenMP
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
ctx_clock
Context Switch Time
JPEG XL Decoding
CPU Threads: 1
OSPray
Demo: XFrog Forest - Renderer: SciVis
Liquid-DSP
Threads: 4 - Buffer Length: 256 - Filter Length: 57
G'MIC
Test: 2D Function Plotting, 1000 Times
Rodinia
Test: OpenMP LavaMD
Zstd Compression
Compression Level: 8, Long Mode - Decompression Speed
Monte Carlo Simulations of Ionised Nebulae
Input: Dust 2D tau100.0
simdjson
Throughput Test: PartialTweets
Cryptsetup
PBKDF2-sha512
NeatBench
Acceleration: CPU
PyPerformance
Benchmark: json_loads
BRL-CAD
VGR Performance Metric
GNU Octave Benchmark
libjpeg-turbo tjbench
Test: Decompression Throughput
eSpeak-NG Speech Engine
Text-To-Speech Synthesis
Timed Erlang/OTP Compilation
Time To Compile
Chaos Group V-RAY
Mode: CPU
SVT-AV1
Encoder Mode: Enc Mode 4 - Input: 1080p
7-Zip Compression
Compress Speed Test
WebP2 Image Encode
Encode Settings: Quality 75, Compression Effort 7
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
libavif avifenc
Encoder Speed: 10, Lossless
AOM AV1
Encoder Mode: Speed 6 Two-Pass
ViennaCL
Test: CPU BLAS - dDOT
Liquid-DSP
Threads: 12 - Buffer Length: 256 - Filter Length: 57
C-Blosc
Compressor: blosclz
AOM AV1
Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K
GNU Radio
Test: Hilbert Transform
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
WireGuard + Linux Networking Stack Stress Test
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Very Fast
LuaRadio
Test: Complex Phase
Cryptsetup
AES-XTS 256b Decryption
Stress-NG
Test: Memory Copying
OpenSCAD
Render: Pistol
Mobile Neural Network
Model: resnet-v2-50
LuxCoreRender
Scene: Rainbow Colors and Prism
SQLite Speedtest
Timed Time - Size 1,000
GraphicsMagick
Operation: Enhanced
libavif avifenc
Encoder Speed: 0
SVT-HEVC
Tuning: 7 - Input: Bosphorus 1080p
OpenSCAD
Render: Mini-ITX Case
NCNN
Target: CPU - Model: regnety_400m
ONNX Runtime
Model: super-resolution-10 - Device: OpenMP CPU
JPEG XL
Input: JPEG - Encode Speed: 5
NCNN
Target: CPU - Model: squeezenet_ssd
OSPray
Demo: NASA Streamlines - Renderer: Path Tracer
Cryptsetup
PBKDF2-whirlpool
Darktable
Test: Server Room - Acceleration: CPU-only
Selenium
Benchmark: PSPDFKit WASM - Browser: Firefox
Cryptsetup
AES-XTS 512b Encryption
Selenium
Benchmark: PSPDFKit WASM - Browser: Google Chrome
OCRMyPDF
Processing 60 Page PDF Document
POV-Ray
Trace Time
PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
ViennaCL
Test: CPU BLAS - dGEMV-T
PyPerformance
Benchmark: crypto_pyaes
Timed Mesa Compilation
Time To Compile
Cryptsetup
AES-XTS 256b Encryption
libavif avifenc
Encoder Speed: 2
OpenFOAM
Input: Motorbike 30M
TNN
Target: CPU - Model: SqueezeNet v1.1
Basis Universal
Settings: ETC1S
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Very Fast
AOM AV1
Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K
RawTherapee
Total Benchmark Time
LULESH
Timed Wasmer Compilation
Time To Compile
ASKAP
Test: tConvolve OpenMP - Degridding
FFTW
Build: Stock - Size: 2D FFT Size 4096
Cryptsetup
AES-XTS 512b Decryption
PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU
JPEG XL
Input: PNG - Encode Speed: 5
Coremark
CoreMark Size 666 - Iterations Per Second
GIMP
Test: unsharp-mask
srsLTE
Test: PHY_DL_Test
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU
Timed ImageMagick Compilation
Time To Compile
QuantLib
Timed Eigen Compilation
Time To Compile
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU
NCNN
Target: CPU - Model: yolov4-tiny
OpenSCAD
Render: Projector Mount Swivel
ONNX Runtime
Model: shufflenet-v2-10 - Device: OpenMP CPU
AOM AV1
Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p
Botan
Test: AES-256
Perl Benchmarks
Test: Pod2html
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Ultra Fast
Etcpak
Configuration: DXT1
Darktable
Test: Masskrug - Acceleration: CPU-only
PyPerformance
Benchmark: pickle_pure_python
SVT-HEVC
Tuning: 1 - Input: Bosphorus 1080p
GraphicsMagick
Operation: Noise-Gaussian
GIMP
Test: auto-levels
Appleseed
Scene: Emily
Zstd Compression
Compression Level: 19, Long Mode - Compression Speed
GEGL
Operation: Scale
Zstd Compression
Compression Level: 19 - Compression Speed
Botan
Test: Twofish
libavif avifenc
Encoder Speed: 6
IndigoBench
Acceleration: CPU - Scene: Supercar
LibRaw
Post-Processing Benchmark
Botan
Test: ChaCha20Poly1305
Timed Apache Compilation
Time To Compile
Nebular Empirical Analysis Tool
PyPerformance
Benchmark: django_template
NAMD
ATPase Simulation - 327,506 Atoms
Zstd Compression
Compression Level: 8 - Decompression Speed
Cryptsetup
Twofish-XTS 256b Encryption
Selenium
Benchmark: Kraken - Browser: Firefox
Git
Time To Complete Common Git Commands
simdjson
Throughput Test: Kostya
Cryptsetup
Serpent-XTS 256b Encryption
oneDNN
Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU
PyPerformance
Benchmark: chaos
Cryptsetup
Twofish-XTS 512b Encryption
Timed FFmpeg Compilation
Time To Compile
Crafty
Elapsed Time
GNU GMP GMPbench
Total Time
AOM AV1
Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p
Darktable
Test: Boat - Acceleration: CPU-only
Zstd Compression
Compression Level: 19 - Decompression Speed
Timed Node.js Compilation
Time To Compile
WebP Image Encode
Encode Settings: Quality 100, Highest Compression
PyPerformance
Benchmark: float
Timed PHP Compilation
Time To Compile
x265
Video Input: Bosphorus 1080p
ONNX Runtime
Model: bertsquad-10 - Device: OpenMP CPU
Xcompact3d Incompact3d
Input: input.i3d 193 Cells Per Direction
WebP2 Image Encode
Encode Settings: Quality 100, Compression Effort 5
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU
Tesseract OCR
Time To OCR 7 Images
Primesieve
1e12 Prime Number Generation
srsLTE
Test: PHY_DL_Test
Timed Godot Game Engine Compilation
Time To Compile
Zstd Compression
Compression Level: 3, Long Mode - Decompression Speed
ONNX Runtime
Model: yolov4 - Device: OpenMP CPU
dav1d
Video Input: Summer Nature 1080p
XZ Compression
Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9
ViennaCL
Test: CPU BLAS - dGEMV-N
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 100
VP9 libvpx Encoding
Speed: Speed 5
Dolfyn
Computational Fluid Dynamics
oneDNN
Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU
Google SynthMark
Test: VoiceMark_100
AOM AV1
Encoder Mode: Speed 6 Realtime
GNU Radio
Test: FM Deemphasis Filter
JPEG XL
Input: PNG - Encode Speed: 7
GIMP
Test: rotate
TSCP
AI Chess Performance
Monkey Audio Encoding
WAV To APE
Cython Benchmark
Test: N-Queens
rays1bench
Large Scene
YafaRay
Total Time For Sample Scene
GNU Radio
Test: Signal Source (Cosine)
GEGL
Operation: Rotate 90 Degrees
LAME MP3 Encoding
WAV To MP3
x264
H.264 Video Encoding
Cryptsetup
Serpent-XTS 512b Decryption
OpenSCAD
Render: Retro Car
LZ4 Compression
Compression Level: 1 - Compression Speed
GIMP
Test: resize
LZ4 Compression
Compression Level: 3 - Decompression Speed
dav1d
Video Input: Summer Nature 4K
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Medium
Botan
Test: ChaCha20Poly1305 - Decrypt
Rodinia
Test: OpenMP Streamcluster
Botan
Test: KASUMI - Decrypt
GEGL
Operation: Color Enhance
Unpacking Firefox
Extracting: firefox-84.0.source.tar.xz
Selenium
Benchmark: WASM collisionDetection - Browser: Google Chrome
ASTC Encoder
Preset: Medium
IndigoBench
Acceleration: CPU - Scene: Bedroom
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU
Basis Universal
Settings: UASTC Level 0
Opus Codec Encoding
WAV To Opus Encode
Etcpak
Configuration: ETC2
Botan
Test: Twofish
N-Queens
Elapsed Time
Cryptsetup
Serpent-XTS 512b Encryption
Botan
Test: Blowfish
OpenVKL
Benchmark: vklBenchmarkUnstructuredVolume
WebP Image Encode
Encode Settings: Quality 100, Lossless
Botan
Test: Blowfish - Decrypt
ASKAP
Test: tConvolve MT - Degridding
PyPerformance
Benchmark: nbody
dcraw
RAW To PPM Image Conversion
Timed HMMer Search
Pfam Database Search
Algebraic Multi-Grid Benchmark
Blender
Blend File: BMW27 - Compute: CPU-Only
Cryptsetup
Serpent-XTS 256b Decryption
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Medium
VP9 libvpx Encoding
Speed: Speed 0
Cryptsetup
Twofish-XTS 512b Decryption
Cryptsetup
Twofish-XTS 256b Decryption
TNN
Target: CPU - Model: MobileNet v2
RAR Compression
Linux Source Tree Archiving To RAR
LuaRadio
Test: Hilbert Transform
Radiance Benchmark
Test: Serial
GEGL
Operation: Crop
WavPack Audio Encoding
WAV To WavPack
Crypto++
Test: Unkeyed Algorithms
Polyhedron Fortran Benchmarks
Benchmark: rnflow
GNU Radio
Test: FIR Filter
LZ4 Compression
Compression Level: 9 - Compression Speed
LZ4 Compression
Compression Level: 3 - Compression Speed
TensorFlow Lite
Model: Mobilenet Float
LZ4 Compression
Compression Level: 9 - Decompression Speed
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU
Botan
Test: Twofish - Decrypt
Himeno Benchmark
Poisson Pressure Solver
Botan
Test: KASUMI
oneDNN
Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU
ASTC Encoder
Preset: Exhaustive
RNNoise
Basis Universal
Settings: UASTC Level 2
ASTC Encoder
Preset: Thorough
Botan
Test: KASUMI
TensorFlow Lite
Model: Mobilenet Quant
Basis Universal
Settings: UASTC Level 3
TensorFlow Lite
Model: Inception V4
Stress-NG
Test: Crypto
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU
ASKAP
Test: tConvolve MT - Gridding
GNU Radio
Test: IIR Filter
Smallpt
Global Illumination Renderer; 128 Samples
TensorFlow Lite
Model: SqueezeNet
Selenium
Benchmark: WASM collisionDetection - Browser: Firefox
m-queens
Time To Solve
FLAC Audio Encoding
WAV To FLAC
Sysbench
Test: CPU
Botan
Test: Blowfish
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 100
C-Ray
Total Time - 4K, 16 Rays Per Pixel
TensorFlow Lite
Model: Inception ResNet V2
Etcpak
Configuration: ETC1
Botan
Test: CAST-256
LuaRadio
Test: FM Deemphasis Filter
Aircrack-ng
Botan
Test: CAST-256 - Decrypt
Botan
Test: CAST-256
PyPerformance
Benchmark: regex_compile
PyPerformance
Benchmark: raytrace
PyPerformance
Benchmark: pathlib
PyPerformance
Benchmark: 2to3
PyPerformance
Benchmark: go
AOM AV1
Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p
AOM AV1
Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K
OSPray
Demo: Magnetic Reconnection - Renderer: Path Tracer
OSPray
Demo: Magnetic Reconnection - Renderer: SciVis
OSPray
Demo: NASA Streamlines - Renderer: SciVis
OSPray
Demo: San Miguel - Renderer: Path Tracer
GraphicsMagick
Operation: Sharpen
simdjson
Throughput Test: LargeRandom
Polyhedron Fortran Benchmarks
Benchmark: linpk
Selenium
Benchmark: StyleBench - Browser: Firefox
Zstd Compression
Compression Level: 3, Long Mode - Compression Speed
Rodinia
Test: OpenMP HotSpot3D
Phoronix Test Suite v10.8.5