Intel oneAPI

A collection of test profiles stressing either Intel oneAPI software components themselves (Open Image Denoise, OSPray, Embree) or benchmarks/programs leveraging these components.

See how your system performs with this suite using the Phoronix Test Suite. It's as easy as running the phoronix-test-suite benchmark oneapi command..

Tests In This Suite

  • Embree
        Binary: Pathtracer - Model: Asian Dragon
  • Embree
        Binary: Pathtracer - Model: Asian Dragon Obj
  • Embree
        Binary: Pathtracer - Model: Crown
  • Embree
        Binary: Pathtracer ISPC - Model: Asian Dragon
  • Embree
        Binary: Pathtracer ISPC - Model: Asian Dragon Obj
  • Embree
        Binary: Pathtracer ISPC - Model: Crown
  • oneDNN
        Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
  • oneDNN
        Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
  • oneDNN
        Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU
  • oneDNN
        Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU
  • oneDNN
        Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU
  • oneDNN
        Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 - Engine: CPU
  • oneDNN
        Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU
  • oneDNN
        Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU
  • oneDNN
        Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 - Engine: CPU
  • oneDNN
        Harness: IP Batch 1D - Data Type: f32 - Engine: CPU
  • oneDNN
        Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU
  • oneDNN
        Harness: IP Batch 1D - Data Type: bf16bf16bf16 - Engine: CPU
  • oneDNN
        Harness: IP Batch All - Data Type: f32 - Engine: CPU
  • oneDNN
        Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU
  • oneDNN
        Harness: IP Batch All - Data Type: bf16bf16bf16 - Engine: CPU
  • oneDNN
        Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
  • oneDNN
        Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
  • oneDNN
        Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU
  • oneDNN
        Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
  • oneDNN
        Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU
  • oneDNN
        Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU
  • oneDNN
        Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
  • oneDNN
        Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU
  • oneDNN
        Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU
  • Intel Open Image Denoise
        Scene: Memorial
  • OSPray
        Demo: Magnetic Reconnection - Renderer: SciVis
  • OSPray
        Demo: Magnetic Reconnection - Renderer: Path Tracer
  • OSPray
        Demo: XFrog Forest - Renderer: SciVis
  • OSPray
        Demo: XFrog Forest - Renderer: Path Tracer
  • OSPray
        Demo: NASA Streamlines - Renderer: SciVis
  • OSPray
        Demo: NASA Streamlines - Renderer: Path Tracer
  • OSPray
        Demo: San Miguel - Renderer: SciVis
  • OSPray
        Demo: San Miguel - Renderer: Path Tracer
  • Tungsten Renderer
        Scene: Hair
  • Tungsten Renderer
        Scene: Water Caustic
  • Tungsten Renderer
        Scene: Non-Exponential
  • Tungsten Renderer
        Scene: Volumetric Caustic
  • OpenVKL
        Benchmark: vklBenchmark
  • OpenVKL
        Benchmark: vklBenchmarkStructuredVolume
  • OpenVKL
        Benchmark: vklBenchmarkUnstructuredVolume
  • OpenVKL
        Benchmark: vklBenchmarkVdbVolume
  • oneAPI Level Zero Tests
        Test: Host-To-Device Bandwidth
  • oneAPI Level Zero Tests
        Test: Device-To-Host Bandwidth
  • oneAPI Level Zero Tests
        Test: Host-To-Device-To-Host Image Copy
  • oneAPI Level Zero Tests
        Test: Peak Float16 Global Memory Bandwidth
  • oneAPI Level Zero Tests
        Test: Peak Half-Precision Compute
  • oneAPI Level Zero Tests
        Test: Peak Single-Precision Compute
  • oneAPI Level Zero Tests
        Test: Peak Double-Precision Compute
  • oneAPI Level Zero Tests
        Test: Peak Integer Compute
  • oneAPI Level Zero Tests
        Test: Peak System Memory Copy to Shared Memory
  • oneAPI Level Zero Tests
        Test: Peak Kernel Launch Latency
  • OpenVINO
        Model: Face Detection 0106 FP16 - Device: CPU
  • OpenVINO
        Model: Face Detection 0106 FP16 - Device: Intel GPU
  • OpenVINO
        Model: Face Detection 0106 FP32 - Device: CPU
  • OpenVINO
        Model: Face Detection 0106 FP32 - Device: Intel GPU
  • OpenVINO
        Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
  • OpenVINO
        Model: Age Gender Recognition Retail 0013 FP16 - Device: Intel GPU
  • OpenVINO
        Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU
  • OpenVINO
        Model: Age Gender Recognition Retail 0013 FP32 - Device: Intel GPU
  • OpenVINO
        Model: Person Detection 0106 FP16 - Device: CPU
  • OpenVINO
        Model: Person Detection 0106 FP16 - Device: Intel GPU
  • OpenVINO
        Model: Person Detection 0106 FP32 - Device: CPU
  • OpenVINO
        Model: Person Detection 0106 FP32 - Device: Intel GPU

Revision History

pts/oneapi-1.3.2     08 Oct 2020 09:24 EDT
Add OpenVINO to oneAPI suite given all the Intel oneAPI components used.

pts/oneapi-1.3.1     17 Jun 2020 16:37 EDT
Rename mkl-dnn test profile to onednn to match current name.

pts/oneapi-1.3.0     09 Apr 2020 18:12 EDT
Add oneDNN (MKL-DNN) to oneAPI test suite.

pts/oneapi-1.2.0     07 Apr 2020 19:10 EDT
Add OpenVKL and oneAPI Level Zero tests to suite.

pts/oneapi-1.1.0     16 Feb 2020 19:10 EST
Update to use batch mode.

pts/oneapi-1.0.0     30 Sep 2019 11:07 EDT
Initial commit of oneAPI tests themselves and programs leveraging oneAPI components.


User Comments

Post A Comment