blender onednn

2 x AMD EPYC 7513 32-Core testing with a Supermicro H12DSi-N6 v1.02 (2.3 BIOS) and astdrmfb on AlmaLinux 9.1 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 2304021-NE-BLENDERON99
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

Limit displaying results to tests within:

CPU Massive 2 Tests
Creator Workloads 2 Tests
Multi-Core 2 Tests
Server CPU Tests 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
April 02 2023
  2 Hours, 26 Minutes
b
April 02 2023
  2 Hours, 8 Minutes
c
April 02 2023
  2 Hours, 17 Minutes
d
April 02 2023
  2 Hours, 1 Minute
Invert Hiding All Results Option
  2 Hours, 13 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):

a

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173
Security Notes: 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

b

c

d

Processor: 2 x AMD EPYC 7513 32-Core @ 2.60GHz (64 Cores / 128 Threads), Motherboard: Supermicro H12DSi-N6 v1.02 (2.3 BIOS), Memory: 512GB, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb

OS: AlmaLinux 9.1, Kernel: 5.14.0-162.18.1.el9_1.x86_64 (x86_64), Compiler: GCC 11.3.1 20220421, File-System: ext4, Screen Resolution: 1024x768

blender onednnOpenBenchmarking.orgPhoronix Test Suite2 x AMD EPYC 7513 32-Core @ 2.60GHz (64 Cores / 128 Threads)Supermicro H12DSi-N6 v1.02 (2.3 BIOS)512GB2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07astdrmfbAlmaLinux 9.15.14.0-162.18.1.el9_1.x86_64 (x86_64)GCC 11.3.1 20220421ext41024x768ProcessorMotherboardMemoryDiskGraphicsOSKernelCompilerFile-SystemScreen ResolutionBlender Onednn BenchmarksSystem Logs- Transparent Huge Pages: always- --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173 - 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

abcdResult OverviewPhoronix Test Suite100%103%106%109%112%oneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNIP Shapes 1D - f32 - CPUIP Shapes 1D - u8s8f32 - CPUR.N.N.I - u8s8f32 - CPUR.N.N.I - f32 - CPUD.B.s - f32 - CPUR.N.N.T - bf16bf16bf16 - CPUD.B.s - f32 - CPUR.N.N.T - u8s8f32 - CPUC.B.S.A - u8s8f32 - CPUIP Shapes 3D - f32 - CPUIP Shapes 3D - u8s8f32 - CPUC.B.S.A - f32 - CPUD.B.s - u8s8f32 - CPUD.B.s - u8s8f32 - CPUR.N.N.T - f32 - CPU

blender onednnonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUblender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyabcd3.066504.226683.675710.7345390.7689299.958822.037532.662601.969310.6537922608.021004.4012599.051000.7142622.671008.25825.4463.7032.14254.6680.973.404134.273133.768390.7311170.7746959.893222.015382.624741.973960.6612172585.07989.9902626.181010.5462671.08982.41925.4963.7032.08254.7581.073.151404.185483.513170.7357320.7724139.957331.959402.653411.953260.6561912601.271009.9272562.251050.0212572.50959.01025.5163.7432.25254.5880.793.043304.211003.432360.7418730.7796599.711212.011172.604961.979160.6611962612.25942.7832564.27962.8742626.09OpenBenchmarking.org

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUabcd0.76591.53182.29773.06363.8295SE +/- 0.14035, N = 12SE +/- 0.14621, N = 15SE +/- 0.16288, N = 12SE +/- 0.13183, N = 153.066503.404133.151403.04330MIN: 1.68MIN: 1.77MIN: 1.51MIN: 1.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUabcd246810Min: 2.37 / Avg: 3.07 / Max: 3.75Min: 2.58 / Avg: 3.4 / Max: 4.13Min: 2.02 / Avg: 3.15 / Max: 4Min: 2.25 / Avg: 3.04 / Max: 3.761. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUabcd0.96151.9232.88453.8464.8075SE +/- 0.03369, N = 15SE +/- 0.05055, N = 3SE +/- 0.04816, N = 3SE +/- 0.04935, N = 124.226684.273134.185484.21100MIN: 3.74MIN: 3.73MIN: 3.72MIN: 3.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUabcd246810Min: 4.02 / Avg: 4.23 / Max: 4.41Min: 4.21 / Avg: 4.27 / Max: 4.37Min: 4.1 / Avg: 4.19 / Max: 4.27Min: 3.94 / Avg: 4.21 / Max: 4.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabcd0.84791.69582.54373.39164.2395SE +/- 0.17871, N = 12SE +/- 0.13777, N = 15SE +/- 0.16441, N = 12SE +/- 0.19083, N = 123.675713.768393.513173.43236MIN: 1.91MIN: 1.64MIN: 1.57MIN: 1.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabcd246810Min: 2.71 / Avg: 3.68 / Max: 4.8Min: 2.34 / Avg: 3.77 / Max: 4.53Min: 2.63 / Avg: 3.51 / Max: 4.43Min: 2.19 / Avg: 3.43 / Max: 4.491. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUabcd0.16690.33380.50070.66760.8345SE +/- 0.009127, N = 4SE +/- 0.005445, N = 15SE +/- 0.005810, N = 15SE +/- 0.008286, N = 50.7345390.7311170.7357320.741873MIN: 0.64MIN: 0.63MIN: 0.63MIN: 0.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUabcd246810Min: 0.72 / Avg: 0.73 / Max: 0.76Min: 0.71 / Avg: 0.73 / Max: 0.77Min: 0.7 / Avg: 0.74 / Max: 0.79Min: 0.71 / Avg: 0.74 / Max: 0.761. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

c: The test run did not produce a result.

d: The test run did not produce a result.

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

c: The test run did not produce a result.

d: The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUabcd0.17540.35080.52620.70160.877SE +/- 0.000716, N = 3SE +/- 0.004528, N = 3SE +/- 0.004499, N = 3SE +/- 0.009937, N = 150.7689290.7746950.7724130.779659MIN: 0.7MIN: 0.69MIN: 0.69MIN: 0.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUabcd246810Min: 0.77 / Avg: 0.77 / Max: 0.77Min: 0.77 / Avg: 0.77 / Max: 0.78Min: 0.77 / Avg: 0.77 / Max: 0.78Min: 0.77 / Avg: 0.78 / Max: 0.921. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUabcd3691215SE +/- 0.08800, N = 3SE +/- 0.03302, N = 3SE +/- 0.11715, N = 3SE +/- 0.01444, N = 39.958829.893229.957339.71121MIN: 7.88MIN: 8.12MIN: 8.06MIN: 7.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUabcd3691215Min: 9.82 / Avg: 9.96 / Max: 10.12Min: 9.83 / Avg: 9.89 / Max: 9.94Min: 9.81 / Avg: 9.96 / Max: 10.19Min: 9.68 / Avg: 9.71 / Max: 9.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUabcd0.45840.91681.37521.83362.292SE +/- 0.01799, N = 3SE +/- 0.02767, N = 3SE +/- 0.00460, N = 3SE +/- 0.02491, N = 32.037532.015381.959402.01117MIN: 1.72MIN: 1.68MIN: 1.69MIN: 1.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUabcd246810Min: 2.01 / Avg: 2.04 / Max: 2.07Min: 1.96 / Avg: 2.02 / Max: 2.05Min: 1.95 / Avg: 1.96 / Max: 1.97Min: 1.96 / Avg: 2.01 / Max: 2.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUabcd0.59911.19821.79732.39642.9955SE +/- 0.04802, N = 12SE +/- 0.02263, N = 3SE +/- 0.04595, N = 15SE +/- 0.04509, N = 122.662602.624742.653412.60496MIN: 1.55MIN: 2.37MIN: 1.54MIN: 1.551. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUabcd246810Min: 2.24 / Avg: 2.66 / Max: 2.88Min: 2.58 / Avg: 2.62 / Max: 2.66Min: 2.16 / Avg: 2.65 / Max: 2.92Min: 2.23 / Avg: 2.6 / Max: 2.741. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUabcd0.44530.89061.33591.78122.2265SE +/- 0.01171, N = 3SE +/- 0.01997, N = 3SE +/- 0.00922, N = 3SE +/- 0.02166, N = 31.969311.973961.953261.97916MIN: 1.76MIN: 1.76MIN: 1.75MIN: 1.741. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUabcd246810Min: 1.95 / Avg: 1.97 / Max: 1.99Min: 1.95 / Avg: 1.97 / Max: 2.01Min: 1.94 / Avg: 1.95 / Max: 1.97Min: 1.94 / Avg: 1.98 / Max: 2.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUabcd0.14880.29760.44640.59520.744SE +/- 0.007768, N = 3SE +/- 0.001732, N = 3SE +/- 0.002860, N = 3SE +/- 0.001822, N = 30.6537920.6612170.6561910.661196MIN: 0.55MIN: 0.55MIN: 0.55MIN: 0.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUabcd246810Min: 0.64 / Avg: 0.65 / Max: 0.67Min: 0.66 / Avg: 0.66 / Max: 0.66Min: 0.65 / Avg: 0.66 / Max: 0.66Min: 0.66 / Avg: 0.66 / Max: 0.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUabcd6001200180024003000SE +/- 25.24, N = 15SE +/- 25.01, N = 15SE +/- 19.82, N = 15SE +/- 19.89, N = 152608.022585.072601.272612.25MIN: 2380.46MIN: 2316.48MIN: 2411.36MIN: 2424.871. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUabcd5001000150020002500Min: 2445.37 / Avg: 2608.02 / Max: 2772.45Min: 2419.46 / Avg: 2585.07 / Max: 2737.57Min: 2487.94 / Avg: 2601.27 / Max: 2752.98Min: 2467.06 / Avg: 2612.25 / Max: 2701.311. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUabcd2004006008001000SE +/- 19.95, N = 15SE +/- 20.58, N = 15SE +/- 15.43, N = 15SE +/- 25.28, N = 151004.40989.991009.93942.78MIN: 732.38MIN: 728.57MIN: 734.92MIN: 737.481. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUabcd2004006008001000Min: 859.33 / Avg: 1004.4 / Max: 1114.41Min: 832.54 / Avg: 989.99 / Max: 1068.99Min: 940.06 / Avg: 1009.93 / Max: 1148.7Min: 826.96 / Avg: 942.78 / Max: 1121.081. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabcd6001200180024003000SE +/- 27.68, N = 4SE +/- 30.07, N = 15SE +/- 4.75, N = 3SE +/- 28.18, N = 152599.052626.182562.252564.27MIN: 2477.38MIN: 2356.61MIN: 2475.81MIN: 2355.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabcd5001000150020002500Min: 2526.97 / Avg: 2599.05 / Max: 2659.17Min: 2408.35 / Avg: 2626.18 / Max: 2843.23Min: 2556.67 / Avg: 2562.25 / Max: 2571.7Min: 2411.15 / Avg: 2564.27 / Max: 2712.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

c: The test run did not produce a result.

d: The test run did not produce a result.

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

c: The test run did not produce a result.

d: The test run did not produce a result.

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

c: The test run did not produce a result.

d: The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUabcd2004006008001000SE +/- 15.41, N = 15SE +/- 21.48, N = 12SE +/- 21.25, N = 12SE +/- 20.54, N = 151000.711010.551050.02962.87MIN: 750.07MIN: 744.34MIN: 742.05MIN: 740.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUabcd2004006008001000Min: 910.15 / Avg: 1000.71 / Max: 1114.71Min: 869.87 / Avg: 1010.55 / Max: 1124.19Min: 902.04 / Avg: 1050.02 / Max: 1163.42Min: 820.37 / Avg: 962.87 / Max: 1074.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUabcd6001200180024003000SE +/- 39.05, N = 15SE +/- 28.05, N = 5SE +/- 32.84, N = 15SE +/- 27.52, N = 152622.672671.082572.502626.09MIN: 2182.27MIN: 2453.31MIN: 2236.3MIN: 2429.141. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUabcd5001000150020002500Min: 2258.04 / Avg: 2622.67 / Max: 2753.53Min: 2571.16 / Avg: 2671.08 / Max: 2735.17Min: 2302.6 / Avg: 2572.5 / Max: 2780.62Min: 2487.49 / Avg: 2626.09 / Max: 2825.121. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUabc2004006008001000SE +/- 21.48, N = 15SE +/- 13.23, N = 3SE +/- 24.66, N = 121008.26982.42959.01MIN: 724.13MIN: 755.65MIN: 712.871. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUabc2004006008001000Min: 848.92 / Avg: 1008.26 / Max: 1171.62Min: 962.38 / Avg: 982.42 / Max: 1007.39Min: 820.03 / Avg: 959.01 / Max: 1088.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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: BMW27 - Compute: CPU-Onlyabc612182430SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 325.4425.4925.51
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: BMW27 - Compute: CPU-Onlyabc612182430Min: 25.31 / Avg: 25.44 / Max: 25.57Min: 25.45 / Avg: 25.49 / Max: 25.57Min: 25.44 / Avg: 25.51 / Max: 25.6

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Classroom - Compute: CPU-Onlyabc1428425670SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 363.7063.7063.74
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Classroom - Compute: CPU-Onlyabc1224364860Min: 63.39 / Avg: 63.7 / Max: 63.88Min: 63.61 / Avg: 63.7 / Max: 63.78Min: 63.62 / Avg: 63.74 / Max: 63.93

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Fishy Cat - Compute: CPU-Onlyabc714212835SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 332.1432.0832.25
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Fishy Cat - Compute: CPU-Onlyabc714212835Min: 32.08 / Avg: 32.14 / Max: 32.26Min: 31.99 / Avg: 32.08 / Max: 32.19Min: 32.05 / Avg: 32.25 / Max: 32.52

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Barbershop - Compute: CPU-Onlyabc60120180240300SE +/- 0.31, N = 3SE +/- 0.29, N = 3SE +/- 0.45, N = 3254.66254.75254.58
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Barbershop - Compute: CPU-Onlyabc50100150200250Min: 254.04 / Avg: 254.66 / Max: 254.99Min: 254.24 / Avg: 254.75 / Max: 255.24Min: 254.11 / Avg: 254.58 / Max: 255.49

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Pabellon Barcelona - Compute: CPU-Onlyabc20406080100SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 380.9781.0780.79
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Pabellon Barcelona - Compute: CPU-Onlyabc1530456075Min: 80.86 / Avg: 80.97 / Max: 81.07Min: 81 / Avg: 81.07 / Max: 81.18Min: 80.64 / Avg: 80.79 / Max: 80.92

a

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173
Security Notes: 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

Testing initiated at 2 April 2023 12:42 by user .

b

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173
Security Notes: 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

Testing initiated at 2 April 2023 15:34 by user .

c

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173
Security Notes: 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

Testing initiated at 2 April 2023 19:30 by user .

d

Processor: 2 x AMD EPYC 7513 32-Core @ 2.60GHz (64 Cores / 128 Threads), Motherboard: Supermicro H12DSi-N6 v1.02 (2.3 BIOS), Memory: 512GB, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb

OS: AlmaLinux 9.1, Kernel: 5.14.0-162.18.1.el9_1.x86_64 (x86_64), Compiler: GCC 11.3.1 20220421, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173
Security Notes: 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

Testing initiated at 2 April 2023 23:01 by user .