Microsoft Azure EPYC 7003 HPC HBv3 Benchmarks

Azure HBv3 benchmarks against other Microsoft Azure HPC instance types. Benchmarks by Michael Larabel for a future article on phoronix.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2104153-PTS-AZUREHPC42
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:

Timed Code Compilation 3 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 14 Tests
Creator Workloads 4 Tests
Encoding 3 Tests
Finance 2 Tests
Fortran Tests 4 Tests
HPC - High Performance Computing 14 Tests
Machine Learning 5 Tests
Molecular Dynamics 6 Tests
MPI Benchmarks 5 Tests
Multi-Core 14 Tests
NVIDIA GPU Compute 4 Tests
OpenMPI Tests 8 Tests
Programmer / Developer System Benchmarks 4 Tests
Python Tests 3 Tests
Scientific Computing 6 Tests
Server CPU Tests 10 Tests
Single-Threaded 2 Tests
Video Encoding 3 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
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread 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
Azure HBv3 - EPYC 7V13
April 09 2021
  7 Hours, 20 Minutes
Azure HBv2 - EPYC 7V12
April 10 2021
  7 Hours, 28 Minutes
Azure HBv1 - EPYC 7551
April 11 2021
  9 Hours, 51 Minutes
Azure HC - Xeon 8168
April 12 2021
  4 Hours, 24 Minutes
Azure H - Xeon E5-2667 v3
April 14 2021
  9 Hours, 51 Minutes
Invert Hiding All Results Option
  7 Hours, 47 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):

Microsoft Azure EPYC 7003 HPC HBv3 Benchmarks Suite 1.0.0 System Test suite extracted from Microsoft Azure EPYC 7003 HPC HBv3 Benchmarks. pts/botan-1.6.0 KASUMI Test: KASUMI pts/botan-1.6.0 KASUMI Test: KASUMI - Decrypt pts/botan-1.6.0 AES-256 Test: AES-256 pts/botan-1.6.0 AES-256 Test: AES-256 - Decrypt pts/botan-1.6.0 Twofish Test: Twofish pts/botan-1.6.0 Twofish Test: Twofish - Decrypt pts/botan-1.6.0 Blowfish Test: Blowfish pts/botan-1.6.0 Blowfish Test: Blowfish - Decrypt pts/botan-1.6.0 CAST-256 Test: CAST-256 pts/botan-1.6.0 CAST-256 Test: CAST-256 - Decrypt pts/botan-1.6.0 ChaCha20Poly1305 Test: ChaCha20Poly1305 pts/botan-1.6.0 ChaCha20Poly1305 Test: ChaCha20Poly1305 - Decrypt pts/quantlib-1.0.0 pts/plaidml-1.0.4 --no-fp16 --no-train vgg16 CPU FP16: No - Mode: Inference - Network: VGG16 - Device: CPU pts/plaidml-1.0.4 --no-fp16 --no-train vgg19 CPU FP16: No - Mode: Inference - Network: VGG19 - Device: CPU pts/plaidml-1.0.4 --no-fp16 --no-train resnet50 CPU FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU pts/cloverleaf-1.1.0 Lagrangian-Eulerian Hydrodynamics pts/mnn-1.2.0 Model: SqueezeNetV1.0 pts/mnn-1.2.0 Model: resnet-v2-50 pts/mnn-1.2.0 Model: inception-v3 pts/tensorflow-lite-1.0.0 --graph=squeezenet.tflite Model: SqueezeNet pts/tnn-1.0.1 -dt NAIVE -mp ../benchmark/benchmark-model/squeezenet_v1.1.tnnproto Target: CPU - Model: SqueezeNet v1.1 pts/gromacs-1.4.1 Water Benchmark pts/hpcg-1.2.1 pts/npb-1.4.2 lu.C Test / Class: LU.C pts/rodinia-1.3.1 OMP_LAVAMD Test: OpenMP LavaMD pts/rodinia-1.3.1 OMP_HOTSPOT3D Test: OpenMP HotSpot3D pts/namd-1.2.1 ATPase Simulation - 327,506 Atoms pts/onednn-1.7.0 --ip --batch=inputs/ip/shapes_3d --cfg=f32 --engine=cpu Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU pts/onednn-1.7.0 --ip --batch=inputs/ip/shapes_3d --cfg=u8s8f32 --engine=cpu Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU pts/onednn-1.7.0 --deconv --batch=inputs/deconv/shapes_1d --cfg=u8s8f32 --engine=cpu Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU pts/onednn-1.7.0 --deconv --batch=inputs/deconv/shapes_3d --cfg=u8s8f32 --engine=cpu Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU pts/onednn-1.7.0 --rnn --batch=inputs/rnn/perf_rnn_training --cfg=f32 --engine=cpu Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU pts/onednn-1.7.0 --rnn --batch=inputs/rnn/perf_rnn_inference_lb --cfg=f32 --engine=cpu Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU pts/onednn-1.7.0 --rnn --batch=inputs/rnn/perf_rnn_training --cfg=u8s8f32 --engine=cpu Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU pts/onednn-1.7.0 --rnn --batch=inputs/rnn/perf_rnn_inference_lb --cfg=u8s8f32 --engine=cpu Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU pts/onednn-1.7.0 --matmul --batch=inputs/matmul/shapes_transformer --cfg=f32 --engine=cpu Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU pts/onednn-1.7.0 --rnn --batch=inputs/rnn/perf_rnn_training --cfg=bf16bf16bf16 --engine=cpu Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU pts/onednn-1.7.0 --rnn --batch=inputs/rnn/perf_rnn_inference_lb --cfg=bf16bf16bf16 --engine=cpu Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU pts/onednn-1.7.0 --matmul --batch=inputs/matmul/shapes_transformer --cfg=u8s8f32 --engine=cpu Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU pts/pennant-1.1.0 sedovbig/sedovbig.pnt Test: sedovbig pts/pennant-1.1.0 leblancbig/leblancbig.pnt Test: leblancbig pts/lulesh-1.1.1 pts/incompact3d-2.0.2 input.i3d Input: X3D-benchmarking input.i3d pts/build-llvm-1.2.1 Time To Compile pts/compress-zstd-1.3.0 -b8 Compression Level: 8 - Compression Speed pts/compress-zstd-1.3.0 -b19 Compression Level: 19 - Compression Speed pts/compress-zstd-1.3.0 -b19 Compression Level: 19 - Decompression Speed pts/compress-zstd-1.3.0 -b8 --long Compression Level: 8, Long Mode - Compression Speed pts/compress-zstd-1.3.0 -b8 --long Compression Level: 8, Long Mode - Decompression Speed pts/compress-zstd-1.3.0 -b19 --long Compression Level: 19, Long Mode - Decompression Speed pts/build-linux-kernel-1.11.0 Time To Compile pts/svt-vp9-1.3.0 -tune 0 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p pts/svt-av1-2.2.1 -enc-mode 0 -n 20 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Enc Mode 0 - Input: 1080p pts/svt-av1-2.2.1 -enc-mode 4 -n 80 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Enc Mode 4 - Input: 1080p pts/svt-av1-2.2.1 -enc-mode 8 -n 320 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Enc Mode 8 - Input: 1080p pts/svt-hevc-1.2.0 -encMode 1 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Tuning: 1 - Input: Bosphorus 1080p pts/svt-hevc-1.2.0 -encMode 7 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Tuning: 7 - Input: Bosphorus 1080p pts/svt-hevc-1.2.0 -encMode 10 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Tuning: 10 - Input: Bosphorus 1080p pts/build-nodejs-1.0.0 Time To Compile pts/financebench-1.1.1 Repo/OpenMP/repoEngine.exe Benchmark: Repo OpenMP pts/financebench-1.1.1 Bonds/OpenMP/bondsEngine.exe Benchmark: Bonds OpenMP pts/gmpbench-1.3.0 Total Time