tensorflow ryzen zen 4

Tests for a future article. AMD Ryzen 9 7950X3D 16-Core testing with a ASUS ROG CROSSHAIR X670E HERO (9927 BIOS) and AMD Radeon RX 7900 XTX on Ubuntu 23.04 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 2303294-PTS-TENSORFL34
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

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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
7600x a
March 29 2023
  1 Hour, 32 Minutes
7600x b
March 29 2023
  2 Hours, 22 Minutes
7950x3d a
March 29 2023
  48 Minutes
7950x3d b
March 29 2023
  48 Minutes
Invert Hiding All Results Option
  1 Hour, 22 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):


tensorflow ryzen zen 4OpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 5 7600X 6-Core @ 4.70GHz (6 Cores / 12 Threads)AMD Ryzen 9 7950X3D 16-Core @ 4.20GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR X670E HERO (9927 BIOS)AMD Device 14d832GBWestern Digital WD_BLACK SN850X 1000GB + 2000GBAMD Radeon RX 7900 XTX (2304/1249MHz)AMD Device ab30ASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.046.2.8-060208-generic (x86_64)GNOME Shell 44.0X Server 1.21.1.7 + Wayland4.6 Mesa 23.1.0-devel (git-de8b14f 2023-03-24 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.49)OpenCL 2.1 AMD-APP (3513.0)GCC 12.2.0ext43840x2160ProcessorsMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionTensorflow Ryzen Zen 4 BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- Python 3.11.2- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

7600x a7600x b7950x3d a7950x3d bResult OverviewPhoronix Test Suite100%138%175%213%250%BlenderBlenderBlenderBlenderBlenderTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowTensorFlowBarbershop - CPU-OnlyPabellon Barcelona - CPU-OnlyBMW27 - CPU-OnlyFishy Cat - CPU-OnlyClassroom - CPU-OnlyCPU - 512 - AlexNetCPU - 256 - AlexNetCPU - 64 - AlexNetCPU - 32 - GoogLeNetCPU - 64 - GoogLeNetCPU - 16 - GoogLeNetCPU - 32 - AlexNetCPU - 256 - GoogLeNetCPU - 512 - GoogLeNetCPU - 64 - ResNet-50CPU - 32 - ResNet-50CPU - 256 - ResNet-50CPU - 16 - ResNet-50CPU - 16 - AlexNet

tensorflow ryzen zen 4blender: Barbershop - CPU-Onlytensorflow: CPU - 256 - ResNet-50tensorflow: CPU - 512 - GoogLeNettensorflow: CPU - 256 - GoogLeNettensorflow: CPU - 512 - AlexNettensorflow: CPU - 64 - ResNet-50blender: Pabellon Barcelona - CPU-Onlyblender: Classroom - CPU-Onlytensorflow: CPU - 256 - AlexNettensorflow: CPU - 32 - ResNet-50tensorflow: CPU - 64 - GoogLeNetblender: Fishy Cat - CPU-Onlyblender: BMW27 - CPU-Onlytensorflow: CPU - 16 - ResNet-50tensorflow: CPU - 32 - GoogLeNettensorflow: CPU - 64 - AlexNettensorflow: CPU - 32 - AlexNettensorflow: CPU - 16 - GoogLeNettensorflow: CPU - 16 - AlexNettensorflow: CPU - 512 - ResNet-507600x a7600x b7950x3d a7950x3d b1202.8527.5379.7779.54188.727.63411.84333.15186.2327.8180.05163.19127.8727.8680.73166.15145.5482.08114.421202.6727.5479.7779.61190.3027.66410.66333.68186.3127.8079.92162.92128.2627.8580.76164.76145.4581.95114.73480.8843.85136.9137.95430.5744.16167.38136419.2844.34145.166.5652.143.14149.5340.13259.68146.69176480.3443.9136.97137.75430.5844.24166.53135.8418.8544.32145.1966.1651.9643.24149.66339.62258.45146.43176.37OpenBenchmarking.org

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Barbershop - Compute: CPU-Only7600x a7600x b7950x3d a7950x3d b300600900120015001202.851202.67480.88480.34

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-507600x a7600x b7950x3d a7950x3d b102030405027.5327.5443.8543.90

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNet7600x a7600x b7950x3d a7950x3d b30609012015079.7779.77136.90136.97

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNet7600x a7600x b7950x3d b7950x3d a306090120150SE +/- 0.05, N = 379.5479.61137.75137.95

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNet7600x a7600x b7950x3d a7950x3d b90180270360450SE +/- 1.32, N = 3188.70190.30430.57430.58

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-507600x a7600x b7950x3d a7950x3d b1020304050SE +/- 0.00, N = 327.6327.6644.1644.24

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Pabellon Barcelona - Compute: CPU-Only7600x a7600x b7950x3d a7950x3d b90180270360450411.84410.66167.38166.53

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Classroom - Compute: CPU-Only7600x b7600x a7950x3d a7950x3d b70140210280350333.68333.15136.00135.80

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNet7600x a7600x b7950x3d b7950x3d a90180270360450SE +/- 0.42, N = 3186.23186.31418.85419.28

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-507600x b7600x a7950x3d b7950x3d a1020304050SE +/- 0.01, N = 327.8027.8144.3244.34

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNet7600x b7600x a7950x3d a7950x3d b306090120150SE +/- 0.04, N = 379.9280.05145.10145.19

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Fishy Cat - Compute: CPU-Only7600x a7600x b7950x3d a7950x3d b4080120160200163.19162.9266.5666.16

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: BMW27 - Compute: CPU-Only7600x b7600x a7950x3d a7950x3d b306090120150128.26127.8752.1051.96

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-507600x b7600x a7950x3d a7950x3d b1020304050SE +/- 0.01, N = 327.8527.8643.1443.24

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNet7600x a7600x b7950x3d a7950x3d b306090120150SE +/- 0.02, N = 380.7380.76149.50149.66

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNet7600x b7600x a7950x3d b7950x3d a70140210280350SE +/- 0.14, N = 3164.76166.15339.62340.13

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNet7600x b7600x a7950x3d b7950x3d a60120180240300SE +/- 0.21, N = 3145.45145.54258.45259.68

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNet7600x b7600x a7950x3d b7950x3d a306090120150SE +/- 0.08, N = 381.9582.08146.43146.69

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNet7600x a7600x b7950x3d a7950x3d b4080120160200SE +/- 0.04, N = 3114.42114.73176.00176.37

Device: CPU - Batch Size: 512 - Model: ResNet-50

7600x a: The test quit with a non-zero exit status.

7600x b: The test quit with a non-zero exit status.

7950x3d a: The test quit with a non-zero exit status. E: Fatal Python error: Segmentation fault

7950x3d b: The test quit with a non-zero exit status. E: Fatal Python error: Segmentation fault