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/).

To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark deepsparse.

Project Site

neuralmagic.com

Source Repository

github.com

Test Created

13 October 2022

Last Updated

26 July 2023

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

14 Minutes, 51 Seconds

Average Run Time

2 Minutes, 19 Seconds

Test Dependencies

Python

Accolades

20k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page ViewsOpenBenchmarking.orgEventsNeural Magic DeepSparse Popularity Statisticspts/deepsparse2022.102022.112022.122023.012023.022023.032023.042023.052023.062023.072023.082023.092023.102023.114K8K12K16K20K
* Uploading of benchmark result data to OpenBenchmarking.org is always optional (opt-in) via the Phoronix Test Suite for users wishing to share their results publicly.
** Data based on those opting to upload their test results to OpenBenchmarking.org and users enabling the opt-in anonymous statistics reporting while running benchmarks from an Internet-connected platform.
Data updated weekly as of 28 November 2023.
BERT-Large, NLP Question Answering, Sparse INT85.5%NLP Text Classification, DistilBERT mnli7.3%CV Detection, YOLOv5s COCO, Sparse INT85.4%ResNet-50, Baseline5.4%ResNet-50, Sparse INT85.5%NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased7.6%NLP Question Answering, BERT base uncased SQuaD 12layer Pruned907.5%NLP Text Classification, BERT base uncased SST27.4%BERT-Large, NLP Question Answering5.5%CV Detection, YOLOv5s COCO7.5%NLP Document Classification, oBERT base uncased on IMDB7.6%NLP Token Classification, BERT base uncased conll20037.3%CV Classification, ResNet-50 ImageNet7.4%NLP Text Classification, BERT base uncased SST2, Sparse INT85.4%CV Segmentation, 90% Pruned YOLACT Pruned7.7%Model Option PopularityOpenBenchmarking.org
Asynchronous Multi-Stream66.1%Synchronous Single-Stream33.9%Scenario Option PopularityOpenBenchmarking.org

Revision History

pts/deepsparse-1.5.2   [View Source]   Wed, 26 Jul 2023 15:52:28 GMT
Update against 1.5.2 point release, add more models.

pts/deepsparse-1.5.0   [View Source]   Wed, 07 Jun 2023 07:51:58 GMT
Update against Deepsparse 1.5 upstream.

pts/deepsparse-1.3.2   [View Source]   Sun, 22 Jan 2023 19:05:03 GMT
Update against DeepSparse 1.3.2 upstream.

pts/deepsparse-1.0.1   [View Source]   Thu, 13 Oct 2022 13:47:39 GMT
Initial commit of DeepSparse benchmark.

Suites Using This Test

Machine Learning

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

Neural Magic DeepSparse 1.5

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.org metrics for this test profile configuration based on 153 public results since 7 June 2023 with the latest data as of 13 November 2023.

Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.

Component
Percentile Rank
# Compatible Public Results
ms/batch (Average)
90th
6
297 +/- 4
87th
5
320 +/- 5
80th
4
337 +/- 1
78th
5
345 +/- 1
Mid-Tier
75th
> 347
65th
9
395 +/- 1
53rd
3
439 +/- 25
Median
50th
449
44th
6
466 +/- 3
40th
4
476 +/- 4
Low-Tier
25th
> 564
21st
5
585 +/- 45
16th
8
597 +/- 1
14th
4
610 +/- 4
12th
4
649 +/- 24
8th
3
720 +/- 4
6th
3
806 +/- 63
4th
4
1193 +/- 1
1st
3
1820 +/- 255
OpenBenchmarking.orgDistribution Of Public Results - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream153 Results Range From 183 To 2115 ms/batch18322727131535940344749153557962366771175579984388793197510191063110711511195123912831327137114151459150315471591163516791723176718111855189919431987203120752119714212835

Based on OpenBenchmarking.org data, the selected test / test configuration (Neural Magic DeepSparse 1.5 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream) has an average run-time of 3 minutes. By default this test profile is set to run at least 3 times but may increase if the standard deviation exceeds pre-defined defaults or other calculations deem additional runs necessary for greater statistical accuracy of the result.

OpenBenchmarking.orgMinutesTime Required To Complete BenchmarkModel: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamRun-Time246810Min: 2 / Avg: 2.67 / Max: 5

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.1%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsModel: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamDeviation246810Min: 0 / Avg: 0.05 / Max: 2

Tested CPU Architectures

This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.

CPU Architecture
Kernel Identifier
Verified On
Intel / AMD x86 64-bit
x86_64
(Many Processors)

Recent Test Results

OpenBenchmarking.org Results Compare

1 System - 264 Benchmark Results

Intel Pentium Gold G6405 - ASRock H510M-HDV/M.2 SE - Intel Comet Lake PCH

Ubuntu 20.04 - 5.15.0-88-generic - GNOME Shell 3.36.9

1 System - 264 Benchmark Results

Intel Pentium Gold G6400 - ASRock H510M-HDV/M.2 SE - Intel Comet Lake PCH

Ubuntu 20.04 - 5.15.0-86-generic - GNOME Shell 3.36.9

2 Systems - 358 Benchmark Results

AMD Ryzen 9 3900XT 12-Core - MSI MEG X570 GODLIKE - AMD Starship

Ubuntu 22.04 - 6.2.0-35-generic - GNOME Shell 42.2

2 Systems - 246 Benchmark Results

Intel Core i5-12600K - ASUS PRIME Z690-P WIFI D4 - Intel Device 7aa7

Ubuntu 22.04 - 5.19.0-051900rc6daily20220716-generic - GNOME Shell 42.1

10 Systems - 214 Benchmark Results

2 x AMD EPYC 9254 24-Core - Supermicro H13DSH - 24 x 32 GB DDR5-4800MT

AlmaLinux 9.2 - 5.14.0-284.25.1.el9_2.x86_64 - GCC 11.3.1 20221121

1 System - 279 Benchmark Results

Intel Core i3-10105 - ASRock H510M-HDV/M.2 SE - Intel Comet Lake PCH

Ubuntu 20.04 - 5.15.0-83-generic - GNOME Shell 3.36.9

1 System - 29 Benchmark Results

AMD Ryzen 7 3700X 8-Core - ASUS PRIME B450M-A - AMD Starship

Linuxmint 21.2 - 6.2.0-34-generic - MATE 1.26.0

1 System - 279 Benchmark Results

Intel Core i3-10105 - ASRock H510M-HDV/M.2 SE - Intel Comet Lake PCH

Ubuntu 20.04 - 5.15.0-83-generic - GNOME Shell 3.36.9

1 System - 279 Benchmark Results

Intel Core i3-10105 - ASRock H510M-HDV/M.2 SE - Intel Comet Lake PCH

Ubuntu 20.04 - 5.15.0-83-generic - GNOME Shell 3.36.9

1 System - 543 Benchmark Results

AMD Ryzen Threadripper PRO 5995WX 64-Cores - ASRock WRX80 Creator - AMD Starship

Ubuntu 22.04 - 6.2.0-33-generic - GNOME Shell 42.9

1 System - 332 Benchmark Results

AMD Ryzen Threadripper 3970X 32-Core - ASUS ROG ZENITH II EXTREME - AMD Starship

Ubuntu 22.04 - 5.19.0-051900rc7-generic - GNOME Shell 42.2

3 Systems - 190 Benchmark Results

Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

Ubuntu 22.04 - 6.6.0-060600rc1-generic - GNOME Shell 42.9

2 Systems - 191 Benchmark Results

AMD Ryzen 7 PRO 5850U - HP 8A78 - AMD Renoir

Pop 22.04 - 6.2.6-76060206-generic - GNOME Shell 42.5

1 System - 60 Benchmark Results

2 x Intel Xeon Platinum 8280 - Intel PURLEY - Intel Sky Lake-E DMI3 Registers

Ubuntu 22.04 - 6.2.0-26-generic - GNOME Shell 42.9

Most Popular Test Results

OpenBenchmarking.org Results Compare

2 Systems - 234 Benchmark Results

AMD Ryzen Threadripper 3970X 32-Core - ASUS ROG ZENITH II EXTREME - AMD Starship

Ubuntu 22.04 - 5.19.0-051900rc7-generic - GNOME Shell 42.2

2 Systems - 234 Benchmark Results

AMD Ryzen Threadripper 3970X 32-Core - ASUS ROG ZENITH II EXTREME - AMD Starship

Ubuntu 22.04 - 5.19.0-051900rc7-generic - GNOME Shell 42.2

2 Systems - 166 Benchmark Results

3 Systems - 153 Benchmark Results

AMD Ryzen 5 5500U - NB01 NL5xNU - AMD Renoir

Tuxedo 22.04 - 6.0.0-1010-oem - KDE Plasma 5.26.5

3 Systems - 122 Benchmark Results

AMD EPYC 7763 64-Core - AMD DAYTONA_X - AMD Starship

Ubuntu 22.04 - 6.2.0-phx - GNOME Shell 42.5

2 Systems - 127 Benchmark Results

AMD EPYC 9684X 96-Core - AMD Titanite_4G - AMD Device 14a4

Ubuntu 22.04 - 5.19.0-41-generic - GNOME Shell 42.5

5 Systems - 85 Benchmark Results

Intel Xeon Platinum 8490H - Quanta Cloud S6Q-MB-MPS - Intel Device 1bce

Ubuntu 22.04 - 5.15.0-47-generic - GNOME Shell 42.4

4 Systems - 193 Benchmark Results

2 x AMD EPYC 9124 16-Core - Supermicro H13DSH - 24 x 32 GB DDR5-4800MT

AlmaLinux 9.2 - 5.14.0-284.25.1.el9_2.x86_64 - GCC 11.3.1 20221121

5 Systems - 200 Benchmark Results

2 x AMD EPYC 9124 16-Core - Supermicro H13DSH - 24 x 32 GB DDR5-4800MT

AlmaLinux 9.2 - 5.14.0-284.25.1.el9_2.x86_64 - GCC 11.3.1 20221121

3 Systems - 60 Benchmark Results

AMD Ryzen 9 5900HX - ASUS G513QY v1.0 - AMD Renoir

Ubuntu 22.10 - 5.19.0-46-generic - GNOME Shell 43.0

3 Systems - 143 Benchmark Results

Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers

Ubuntu 22.04 - 5.19.0-051900rc7-generic - GNOME Shell 42.2

3 Systems - 55 Benchmark Results

Intel Core i7-1065G7 - Dell 06CDVY - Intel Ice Lake-LP DRAM

Ubuntu 22.04 - 5.19.0-41-generic - GNOME Shell 42.2

Find More Test Results