xeon-8480-deepsparse

2 x Intel Xeon Platinum 8480+ testing with a Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) and ASPEED on Ubuntu 22.04 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 2307130-NE-XEON8480D61
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
bert-all
July 13 2023
  11 Minutes
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):


xeon-8480-deepsparseOpenBenchmarking.orgPhoronix Test Suite2 x Intel Xeon Platinum 8480+ @ 3.80GHz (112 Cores / 224 Threads)Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS)Intel Device 1bce1008GB8 x 1920GB Dell Ent NVMe AGN RI U.2 1.92TB + 1920GB INTEL SSDSC2KG01 + 800GB INTEL SSDSC2BA80 + 800GB INTEL SSDSC2BB80ASPEED4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-TUbuntu 22.045.15.0-76-generic (x86_64)X Server1.3.224GCC 11.3.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDisplay ServerVulkanCompilerFile-SystemScreen ResolutionXeon-8480-deepsparse BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000181- Python 3.10.6- 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 and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

xeon-8480-deepsparsedeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streambert-all128.0829436.107915.956662.6375OpenBenchmarking.org

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streambert-all306090120150SE +/- 0.44, N = 3128.08

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streambert-all90180270360450SE +/- 1.55, N = 3436.11

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streambert-all48121620SE +/- 0.01, N = 315.96

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streambert-all1428425670SE +/- 0.03, N = 362.64