OpenVINO GenAI

This is a benchmark of OpenVINO GenAI that makes use of Intel OpenVINO, a toolkit around neural networks / AI. Complementing the pts/openvino test profile, pts/openvino-genai is focused on Generative AI (GenAI) LLM performance.

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

Project Site

docs.openvino.ai

Source Repository

github.com

Test Created

23 November 2024

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

23 Minutes, 16 Seconds

Average Run Time

1 Minute, 43 Seconds

Test Dependencies

Python + C/C++ Compiler Toolchain + CMake

Accolades

Recently Created Test Profile

Supported Platforms


Phi-3-mini-128k-instruct-int4-ov25.4%TinyLlama-1.1B-Chat-v1.024.3%Falcon-7b-instruct-int4-ov25.4%Gemma-7b-int4-ov24.9%Model Option PopularityOpenBenchmarking.org

Revision History

pts/openvino-genai-1.0.0   [View Source]   Sat, 23 Nov 2024 10:44:39 GMT
Add OpenVINO GenAI benchmark complement to pts/openvino.

Suites Using This Test

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

OpenVINO GenAI 2024.5

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU

OpenBenchmarking.org metrics for this test profile configuration based on 44 public results since 24 November 2024 with the latest data as of 29 November 2024.

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
tokens/s (Average)
Mid-Tier
75th
< 56
Median
50th
22
Low-Tier
25th
< 17
OpenBenchmarking.orgDistribution Of Public Results - Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU44 Results Range From 8 To 106 tokens/s81726354453627180899810711648121620

Based on OpenBenchmarking.org data, the selected test / test configuration (OpenVINO GenAI 2024.5 - Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU) has an average run-time of 2 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: Phi-3-mini-128k-instruct-int4-ov - Device: CPURun-Time3691215Min: 1 / Avg: 2 / Max: 7

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: Phi-3-mini-128k-instruct-int4-ov - Device: CPUDeviation246810Min: 0 / Avg: 0.07 / Max: 1

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)
ARMv8 64-bit
aarch64
ARMv8 Neoverse-N1 128-Core, ARMv8 Neoverse-V2 72-Core

Recent Test Results

OpenBenchmarking.org Results Compare

2 Systems - 116 Benchmark Results

AMD EPYC 9575F 64-Core - Supermicro Super Server H13SSL-N v1.01 - AMD 1Ah

Ubuntu 24.10 - 6.12.0-rc7-linux-pm-next-phx - GNOME Shell 47.0

4 Systems - 110 Benchmark Results

Intel Core i7-1280P - MSI Prestige 14Evo A12M MS-14C6 - Intel Alder Lake PCH

Ubuntu 24.10 - 6.11.0-rc6-phx - GNOME Shell 47.0

2 Systems - 66 Benchmark Results

AMD EPYC 9655P 96-Core - Supermicro Super Server H13SSL-N v1.01 - AMD 1Ah

Ubuntu 24.10 - 6.12.0-rc7-linux-pm-next-phx - GNOME Shell 47.0

2 Systems - 90 Benchmark Results

AMD Ryzen 7 9800X3D 8-Core - ASRock X870E Taichi - AMD Device 14d8

Ubuntu 24.04 - 6.8.0-49-generic - GNOME Shell 46.0

4 Systems - 94 Benchmark Results

Intel Core Ultra 9 285K - ASUS ROG MAXIMUS Z890 HERO - Intel Device ae7f

Ubuntu 24.10 - 6.11.0-9-generic - GNOME Shell 47.0

5 Systems - 64 Benchmark Results

AMD Ryzen AI 9 HX 370 - ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 - AMD Device 1507

Ubuntu 24.10 - 6.11.0-rc6-phx - GNOME Shell 47.0

4 Systems - 64 Benchmark Results

AMD Ryzen 7 7840HS - Framework Laptop 16 - AMD Device 14e8

Ubuntu 24.04 - 6.8.0-48-generic - GNOME Shell 46.0

1 System - 52 Benchmark Results

ARMv8 Neoverse-N1 - System76 Thelio Astra - Ampere Computing LLC Altra PCI Root Complex A

Ubuntu 24.04 - 6.8.0-48-generic-64k - GNOME Shell 46.0

2 Systems - 77 Benchmark Results

ARMv8 Neoverse-N1 - System76 Thelio Astra - Ampere Computing LLC Altra PCI Root Complex A

Ubuntu 24.04 - 6.8.0-48-generic-64k - GNOME Shell 46.0

3 Systems - 16 Benchmark Results

Intel Core Ultra 7 155H - MTL Swift SFG14-72T Coral_MTH - Intel Device 7e7f

Ubuntu 24.10 - 6.11.0-rc6-phx - GNOME Shell 47.0

3 Systems - 52 Benchmark Results

AMD Ryzen Threadripper 7980X 64-Cores - System76 Thelio Major - AMD Device 14a4

Ubuntu 24.04 - 6.8.0-48-generic - GNOME Shell 46.0

4 Systems - 52 Benchmark Results

ARMv8 Neoverse-V2 - Pegatron JIMBO P4352 - 1 x 480GB LPDDR5-6400MT

Ubuntu 24.04 - 6.8.0-49-generic-64k - GCC 13.2.0 + Clang 18.1.3 + CUDA 11.8

2 Systems - 52 Benchmark Results

AMD EPYC 9655P 96-Core - Supermicro Super Server H13SSL-N v1.01 - AMD 1Ah

Ubuntu 24.10 - 6.12.0-rc7-linux-pm-next-phx - GNOME Shell 47.0

Find More Test Results