hh

Intel Xeon E3-1505M v6 testing with a Dell 06X96V (1.31.0 BIOS) and NVIDIA Quadro M1200 4GB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2302026-NE-HH568983576&grw.

hhProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionhhyIntel Xeon E3-1505M v6 @ 3.00GHz (4 Cores / 8 Threads)Dell 06X96V (1.31.0 BIOS)Intel Xeon E3-1200 v6/7th32GB1000GB Samsung SSD 970 EVO 1TBNVIDIA Quadro M1200 4GBRealtek ALC3266Intel 8265 / 8275Ubuntu 22.045.15.0-58-generic (x86_64)GNOME Shell 42.5X ServerNVIDIA 525.78.014.6.0OpenCL 3.0 CUDA 12.0.1331.3.224GCC 11.3.0zfs1920x1080OpenBenchmarking.org- Transparent Huge Pages: madvise- Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 - Thermald 2.4.9 - Python 3.10.6- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of IBRS + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of TSX disabled

hhdeepsparse: 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-Streamhhy9.1641218.06978.2956120.5414OpenBenchmarking.org

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamhhy3691215SE +/- 0.0965, N = 39.1641

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamhhy50100150200250SE +/- 2.37, N = 3218.07

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamhhy246810SE +/- 0.0363, N = 38.2956

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamhhy306090120150SE +/- 0.53, N = 3120.54

Phoronix Test Suite v10.8.4