Intel Core i7-1185G7 testing with a Dell 0DXP1F (3.7.0 BIOS) and Intel Xe TGL GT2 15GB 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 2311135-PTS-TGLS547809
tgls
Intel Core i7-1185G7 testing with a Dell 0DXP1F (3.7.0 BIOS) and Intel Xe TGL GT2 15GB on Ubuntu 22.04 via the Phoronix Test Suite.
a:
Processor: Intel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads), Motherboard: Dell 0DXP1F (3.7.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Micron 2300 NVMe 512GB, Graphics: Intel Xe TGL GT2 15GB (1350MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201
OS: Ubuntu 22.04, Kernel: 5.19.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.3.204, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 1920x1200
b:
Processor: Intel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads), Motherboard: Dell 0DXP1F (3.7.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Micron 2300 NVMe 512GB, Graphics: Intel Xe TGL GT2 15GB (1350MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201
OS: Ubuntu 22.04, Kernel: 5.19.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.3.204, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 1920x1200
c:
Processor: Intel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads), Motherboard: Dell 0DXP1F (3.7.0 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Micron 2300 NVMe 512GB, Graphics: Intel Xe TGL GT2 15GB (1350MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201
OS: Ubuntu 22.04, Kernel: 6.2.0-36-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1, OpenCL: OpenCL 3.0, Vulkan: 1.3.204, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 1920x1200
Stress-NG 0.16.04
Test: Hash
Bogo Ops/s > Higher Is Better
a . 814204.59 |================================================================
b . 761130.78 |============================================================
c . 808351.87 |================================================================
Stress-NG 0.16.04
Test: MMAP
Bogo Ops/s > Higher Is Better
a . 69.50 |====================================================================
b . 69.31 |====================================================================
c . 36.33 |====================================
Stress-NG 0.16.04
Test: NUMA
Bogo Ops/s > Higher Is Better
a . 91.38 |====================================================================
b . 90.40 |===================================================================
c . 67.68 |==================================================
Stress-NG 0.16.04
Test: Pipe
Bogo Ops/s > Higher Is Better
a . 3286500.94 |===============================================================
b . 2941192.56 |========================================================
c . 2989197.58 |=========================================================
Stress-NG 0.16.04
Test: Poll
Bogo Ops/s > Higher Is Better
a . 583755.41 |================================================================
b . 577995.91 |===============================================================
c . 577081.19 |===============================================================
Stress-NG 0.16.04
Test: Zlib
Bogo Ops/s > Higher Is Better
a . 339.75 |===================================================================
b . 328.60 |=================================================================
c . 327.19 |=================================================================
Stress-NG 0.16.04
Test: Futex
Bogo Ops/s > Higher Is Better
a . 1556806.04 |==============================================================
b . 1573811.12 |===============================================================
c . 1409614.10 |========================================================
Stress-NG 0.16.04
Test: MEMFD
Bogo Ops/s > Higher Is Better
a . 151.83 |==============================================================
b . 163.56 |===================================================================
c . 155.80 |================================================================
Stress-NG 0.16.04
Test: Mutex
Bogo Ops/s > Higher Is Better
a . 1800239.74 |===============================================================
b . 1732350.97 |=============================================================
c . 1454355.06 |===================================================
Stress-NG 0.16.04
Test: Atomic
Bogo Ops/s > Higher Is Better
a . 297.71 |=============================================================
b . 298.85 |==============================================================
c . 325.29 |===================================================================
Stress-NG 0.16.04
Test: Crypto
Bogo Ops/s > Higher Is Better
a . 7870.33 |==================================================================
b . 7909.16 |==================================================================
c . 7843.28 |=================================================================
Stress-NG 0.16.04
Test: Malloc
Bogo Ops/s > Higher Is Better
a . 1275453.62 |===============================================================
b . 1281240.89 |===============================================================
c . 1028677.94 |===================================================
Stress-NG 0.16.04
Test: Cloning
Bogo Ops/s > Higher Is Better
a . 773.96 |=================================================================
b . 801.63 |===================================================================
c . 773.35 |=================================================================
Stress-NG 0.16.04
Test: Forking
Bogo Ops/s > Higher Is Better
a . 19571.06 |=================================================================
b . 17963.97 |============================================================
c . 15226.03 |===================================================
Stress-NG 0.16.04
Test: Pthread
Bogo Ops/s > Higher Is Better
a . 87060.44 |=================================================================
b . 83444.87 |==============================================================
c . 77712.52 |==========================================================
Stress-NG 0.16.04
Test: AVL Tree
Bogo Ops/s > Higher Is Better
a . 38.00 |===================================================================
b . 38.26 |===================================================================
c . 38.60 |====================================================================
Stress-NG 0.16.04
Test: IO_uring
Bogo Ops/s > Higher Is Better
a . 335053.51 |=============================================================
b . 350882.75 |================================================================
c . 335942.42 |=============================================================
Stress-NG 0.16.04
Test: SENDFILE
Bogo Ops/s > Higher Is Better
a . 74606.13 |=================================================================
b . 58965.05 |===================================================
c . 60163.92 |====================================================
Stress-NG 0.16.04
Test: CPU Cache
Bogo Ops/s > Higher Is Better
a . 788775.98 |================================================================
b . 614301.31 |==================================================
c . 541147.88 |============================================
Stress-NG 0.16.04
Test: CPU Stress
Bogo Ops/s > Higher Is Better
a . 8190.18 |==================================================================
b . 7691.29 |==============================================================
c . 6915.21 |========================================================
Stress-NG 0.16.04
Test: Semaphores
Bogo Ops/s > Higher Is Better
a . 8568428.80 |============================================================
b . 7131559.06 |==================================================
c . 9046086.62 |===============================================================
Stress-NG 0.16.04
Test: Matrix Math
Bogo Ops/s > Higher Is Better
a . 19810.07 |=================================================================
b . 18411.16 |============================================================
c . 16983.95 |========================================================
Stress-NG 0.16.04
Test: Vector Math
Bogo Ops/s > Higher Is Better
a . 19001.52 |=================================================================
b . 15774.03 |======================================================
c . 15404.09 |=====================================================
Stress-NG 0.16.04
Test: AVX-512 VNNI
Bogo Ops/s > Higher Is Better
a . 575521.32 |================================================================
b . 467858.43 |====================================================
c . 497416.91 |=======================================================
Stress-NG 0.16.04
Test: Function Call
Bogo Ops/s > Higher Is Better
a . 2533.58 |==================================================================
b . 2144.47 |========================================================
c . 2126.84 |=======================================================
Stress-NG 0.16.04
Test: x86_64 RdRand
Bogo Ops/s > Higher Is Better
a . 1190.72 |==================================================================
b . 1175.31 |=================================================================
c . 1107.03 |=============================================================
Stress-NG 0.16.04
Test: Floating Point
Bogo Ops/s > Higher Is Better
a . 1644.27 |==================================================================
b . 1377.23 |=======================================================
c . 1350.58 |======================================================
Stress-NG 0.16.04
Test: Matrix 3D Math
Bogo Ops/s > Higher Is Better
a . 1503.69 |==================================================================
b . 1497.30 |==================================================================
c . 1479.59 |=================================================================
Stress-NG 0.16.04
Test: Memory Copying
Bogo Ops/s > Higher Is Better
a . 1450.68 |==================================================================
b . 1175.93 |======================================================
c . 1179.30 |======================================================
Stress-NG 0.16.04
Test: Vector Shuffle
Bogo Ops/s > Higher Is Better
a . 40150.80 |=================================================================
b . 34114.33 |=======================================================
c . 33753.34 |=======================================================
Stress-NG 0.16.04
Test: Mixed Scheduler
Bogo Ops/s > Higher Is Better
a . 3933.30 |==================================================================
b . 3841.89 |================================================================
c . 3666.05 |==============================================================
Stress-NG 0.16.04
Test: Socket Activity
Bogo Ops/s > Higher Is Better
a . 6702.46 |==================================================================
b . 4404.68 |===========================================
c . 5819.48 |=========================================================
Stress-NG 0.16.04
Test: Wide Vector Math
Bogo Ops/s > Higher Is Better
a . 259593.94 |================================================================
b . 230331.68 |=========================================================
c . 230559.53 |=========================================================
Stress-NG 0.16.04
Test: Context Switching
Bogo Ops/s > Higher Is Better
a . 1325769.49 |===============================================================
b . 1291162.21 |=============================================================
c . 1089870.73 |====================================================
Stress-NG 0.16.04
Test: Fused Multiply-Add
Bogo Ops/s > Higher Is Better
a . 4206478.30 |==============================================================
b . 3753786.13 |=======================================================
c . 4280472.18 |===============================================================
Stress-NG 0.16.04
Test: Vector Floating Point
Bogo Ops/s > Higher Is Better
a . 11875.81 |=================================================================
b . 9743.95 |=====================================================
c . 8453.72 |==============================================
Stress-NG 0.16.04
Test: Glibc C String Functions
Bogo Ops/s > Higher Is Better
a . 3597888.50 |===============================================================
b . 3169430.98 |=======================================================
c . 2687720.74 |===============================================
Stress-NG 0.16.04
Test: Glibc Qsort Data Sorting
Bogo Ops/s > Higher Is Better
a . 104.16 |===================================================================
b . 85.03 |=======================================================
c . 85.43 |=======================================================
Stress-NG 0.16.04
Test: System V Message Passing
Bogo Ops/s > Higher Is Better
a . 6382311.82 |===============================================================
b . 5221036.03 |====================================================
c . 4574104.46 |=============================================
FFmpeg 6.1
Encoder: libx264 - Scenario: Live
FPS > Higher Is Better
a . 189.77 |===================================================================
b . 185.32 |=================================================================
c . 177.32 |===============================================================
FFmpeg 6.1
Encoder: libx265 - Scenario: Live
FPS > Higher Is Better
a . 79.05 |====================================================================
b . 79.50 |====================================================================
c . 79.15 |====================================================================
FFmpeg 6.1
Encoder: libx264 - Scenario: Upload
FPS > Higher Is Better
a . 13.29 |====================================================================
b . 13.26 |====================================================================
c . 13.11 |===================================================================
FFmpeg 6.1
Encoder: libx265 - Scenario: Upload
FPS > Higher Is Better
a . 12.63 |===================================================================
b . 12.69 |====================================================================
c . 12.76 |====================================================================
FFmpeg 6.1
Encoder: libx264 - Scenario: Platform
FPS > Higher Is Better
a . 50.35 |===================================================================
b . 51.03 |====================================================================
c . 49.38 |==================================================================
FFmpeg 6.1
Encoder: libx265 - Scenario: Platform
FPS > Higher Is Better
a . 26.42 |====================================================================
b . 26.40 |====================================================================
c . 25.93 |===================================================================
FFmpeg 6.1
Encoder: libx264 - Scenario: Video On Demand
FPS > Higher Is Better
a . 49.70 |====================================================================
b . 50.01 |====================================================================
c . 49.79 |====================================================================
FFmpeg 6.1
Encoder: libx265 - Scenario: Video On Demand
FPS > Higher Is Better
a . 26.42 |====================================================================
b . 26.43 |====================================================================
c . 25.88 |===================================================================
OpenVINO 2023.2.dev
Model: Face Detection FP16 - Device: CPU
FPS > Higher Is Better
a . 1.11 |=====================================================================
b . 1.07 |===================================================================
c . 1.01 |===============================================================
OpenVINO 2023.2.dev
Model: Person Detection FP16 - Device: CPU
FPS > Higher Is Better
a . 11.52 |====================================================================
b . 10.81 |================================================================
c . 10.77 |================================================================
OpenVINO 2023.2.dev
Model: Person Detection FP32 - Device: CPU
FPS > Higher Is Better
a . 11.59 |====================================================================
b . 10.78 |===============================================================
c . 10.72 |===============================================================
OpenVINO 2023.2.dev
Model: Vehicle Detection FP16 - Device: CPU
FPS > Higher Is Better
a . 83.21 |====================================================================
b . 77.29 |===============================================================
c . 77.19 |===============================================================
OpenVINO 2023.2.dev
Model: Face Detection FP16-INT8 - Device: CPU
FPS > Higher Is Better
a . 4.05 |=====================================================================
b . 3.75 |================================================================
c . 3.75 |================================================================
OpenVINO 2023.2.dev
Model: Face Detection Retail FP16 - Device: CPU
FPS > Higher Is Better
a . 271.08 |===================================================================
b . 261.21 |=================================================================
c . 263.43 |=================================================================
OpenVINO 2023.2.dev
Model: Road Segmentation ADAS FP16 - Device: CPU
FPS > Higher Is Better
a . 41.06 |====================================================================
b . 38.82 |================================================================
c . 38.72 |================================================================
OpenVINO 2023.2.dev
Model: Vehicle Detection FP16-INT8 - Device: CPU
FPS > Higher Is Better
a . 222.27 |===================================================================
b . 211.09 |================================================================
c . 211.63 |================================================================
OpenVINO 2023.2.dev
Model: Weld Porosity Detection FP16 - Device: CPU
FPS > Higher Is Better
a . 105.49 |===================================================================
b . 97.09 |==============================================================
c . 97.33 |==============================================================
OpenVINO 2023.2.dev
Model: Face Detection Retail FP16-INT8 - Device: CPU
FPS > Higher Is Better
a . 660.54 |===================================================================
b . 606.16 |=============================================================
c . 608.75 |==============================================================
OpenVINO 2023.2.dev
Model: Road Segmentation ADAS FP16-INT8 - Device: CPU
FPS > Higher Is Better
a . 81.00 |====================================================================
b . 75.63 |===============================================================
c . 75.52 |===============================================================
OpenVINO 2023.2.dev
Model: Machine Translation EN To DE FP16 - Device: CPU
FPS > Higher Is Better
a . 13.90 |====================================================================
b . 12.79 |===============================================================
c . 12.79 |===============================================================
OpenVINO 2023.2.dev
Model: Weld Porosity Detection FP16-INT8 - Device: CPU
FPS > Higher Is Better
a . 384.36 |===================================================================
b . 366.17 |================================================================
c . 368.00 |================================================================
OpenVINO 2023.2.dev
Model: Person Vehicle Bike Detection FP16 - Device: CPU
FPS > Higher Is Better
a . 145.83 |===================================================================
b . 137.20 |===============================================================
c . 136.61 |===============================================================
OpenVINO 2023.2.dev
Model: Handwritten English Recognition FP16 - Device: CPU
FPS > Higher Is Better
a . 53.07 |====================================================================
b . 47.86 |=============================================================
c . 47.69 |=============================================================
OpenVINO 2023.2.dev
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
FPS > Higher Is Better
a . 2874.25 |==================================================================
b . 2834.17 |=================================================================
c . 2763.40 |===============================================================
OpenVINO 2023.2.dev
Model: Handwritten English Recognition FP16-INT8 - Device: CPU
FPS > Higher Is Better
a . 61.12 |====================================================================
b . 54.46 |=============================================================
c . 55.20 |=============================================================
OpenVINO 2023.2.dev
Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU
FPS > Higher Is Better
a . 8360.99 |==================================================================
b . 7457.91 |===========================================================
c . 7460.73 |===========================================================
Embree 4.3
Binary: Pathtracer - Model: Crown
Frames Per Second > Higher Is Better
a . 4.1966 |===================================================================
b . 4.2047 |===================================================================
c . 4.2112 |===================================================================
Embree 4.3
Binary: Pathtracer ISPC - Model: Crown
Frames Per Second > Higher Is Better
a . 4.9067 |===================================================================
b . 4.9376 |===================================================================
c . 4.6745 |===============================================================
Embree 4.3
Binary: Pathtracer - Model: Asian Dragon
Frames Per Second > Higher Is Better
a . 4.8695 |===================================================================
b . 4.8785 |===================================================================
c . 4.8776 |===================================================================
Embree 4.3
Binary: Pathtracer - Model: Asian Dragon Obj
Frames Per Second > Higher Is Better
a . 4.4332 |===================================================================
b . 4.4038 |===================================================================
c . 4.4308 |===================================================================
Embree 4.3
Binary: Pathtracer ISPC - Model: Asian Dragon
Frames Per Second > Higher Is Better
a . 6.1486 |===================================================================
b . 6.1218 |===================================================================
c . 5.8890 |================================================================
Embree 4.3
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
Frames Per Second > Higher Is Better
a . 5.2742 |===================================================================
b . 5.2679 |===================================================================
c . 5.0433 |================================================================
SVT-AV1 1.7
Encoder Mode: Preset 4 - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
a . 1.209 |====================================================================
b . 1.211 |====================================================================
c . 1.175 |==================================================================
SVT-AV1 1.7
Encoder Mode: Preset 8 - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
a . 14.86 |====================================================================
b . 14.84 |====================================================================
c . 14.76 |====================================================================
SVT-AV1 1.7
Encoder Mode: Preset 12 - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
a . 37.70 |====================================================================
b . 37.90 |====================================================================
c . 33.44 |============================================================
SVT-AV1 1.7
Encoder Mode: Preset 13 - Input: Bosphorus 4K
Frames Per Second > Higher Is Better
a . 42.30 |===================================================================
b . 42.44 |===================================================================
c . 43.14 |====================================================================
SVT-AV1 1.7
Encoder Mode: Preset 4 - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
a . 4.593 |=================================================================
b . 4.801 |====================================================================
c . 4.250 |============================================================
SVT-AV1 1.7
Encoder Mode: Preset 8 - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
a . 42.13 |====================================================================
b . 41.54 |===================================================================
c . 38.79 |===============================================================
SVT-AV1 1.7
Encoder Mode: Preset 12 - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
a . 191.61 |==========================================================
b . 189.29 |=========================================================
c . 221.84 |===================================================================
SVT-AV1 1.7
Encoder Mode: Preset 13 - Input: Bosphorus 1080p
Frames Per Second > Higher Is Better
a . 290.54 |===================================================================
b . 289.78 |===================================================================
c . 288.16 |==================================================================
VVenC 1.9
Video Input: Bosphorus 4K - Video Preset: Fast
Frames Per Second > Higher Is Better
a . 1.738 |====================================================================
b . 1.733 |====================================================================
c . 1.679 |==================================================================
VVenC 1.9
Video Input: Bosphorus 4K - Video Preset: Faster
Frames Per Second > Higher Is Better
a . 3.843 |====================================================================
b . 3.858 |====================================================================
c . 3.711 |=================================================================
VVenC 1.9
Video Input: Bosphorus 1080p - Video Preset: Fast
Frames Per Second > Higher Is Better
a . 5.428 |====================================================================
b . 5.415 |====================================================================
c . 5.343 |===================================================================
VVenC 1.9
Video Input: Bosphorus 1080p - Video Preset: Faster
Frames Per Second > Higher Is Better
a . 13.20 |====================================================================
b . 13.21 |====================================================================
c . 13.17 |====================================================================
Intel Open Image Denoise 2.1
Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only
Images / Sec > Higher Is Better
a . 0.15 |=====================================================================
b . 0.15 |=====================================================================
c . 0.15 |=====================================================================
Intel Open Image Denoise 2.1
Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only
Images / Sec > Higher Is Better
a . 0.15 |=====================================================================
b . 0.15 |=====================================================================
c . 0.15 |=====================================================================
Intel Open Image Denoise 2.1
Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only
Images / Sec > Higher Is Better
a . 0.07 |=====================================================================
b . 0.07 |=====================================================================
c . 0.07 |=====================================================================
OpenVKL 2.0.0
Benchmark: vklBenchmarkCPU ISPC
Items / Sec > Higher Is Better
a . 124 |======================================================================
b . 124 |======================================================================
c . 105 |===========================================================
OpenVKL 2.0.0
Benchmark: vklBenchmarkCPU Scalar
Items / Sec > Higher Is Better
a . 41 |=======================================================================
b . 40 |=====================================================================
c . 37 |================================================================
Neural Magic DeepSparse 1.5
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 3.9794 |===================================================================
b . 3.9535 |===================================================================
c . 3.8837 |=================================================================
Neural Magic DeepSparse 1.5
Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 164.34 |===================================================================
b . 157.58 |================================================================
c . 140.06 |=========================================================
Neural Magic DeepSparse 1.5
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 63.85 |====================================================================
b . 63.89 |====================================================================
c . 61.01 |=================================================================
Neural Magic DeepSparse 1.5
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 16.44 |====================================================================
b . 16.31 |===================================================================
c . 16.08 |===================================================================
Neural Magic DeepSparse 1.5
Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 54.41 |====================================================================
b . 54.31 |====================================================================
c . 53.99 |===================================================================
Neural Magic DeepSparse 1.5
Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 423.50 |===================================================================
b . 391.97 |==============================================================
c . 367.11 |==========================================================
Neural Magic DeepSparse 1.5
Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 21.35 |================================================================
b . 22.59 |====================================================================
c . 21.62 |=================================================================
Neural Magic DeepSparse 1.5
Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 4.2577 |===================================================================
b . 4.2784 |===================================================================
c . 4.1156 |================================================================
Neural Magic DeepSparse 1.5
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 53.89 |====================================================================
b . 53.77 |====================================================================
c . 53.66 |====================================================================
Neural Magic DeepSparse 1.5
Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 23.01 |====================================================================
b . 21.57 |================================================================
c . 21.13 |==============================================================
Neural Magic DeepSparse 1.5
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 27.66 |==============================================================
b . 30.16 |====================================================================
c . 27.97 |===============================================================
Neural Magic DeepSparse 1.5
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 6.8296 |===================================================================
b . 6.7467 |==================================================================
c . 6.6347 |=================================================================
Neural Magic DeepSparse 1.5
Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 68.74 |=================================================================
b . 71.43 |====================================================================
c . 56.86 |======================================================
Neural Magic DeepSparse 1.5
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 14.68 |====================================================================
b . 13.77 |================================================================
c . 14.70 |====================================================================
Neural Magic DeepSparse 1.5
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
items/sec > Higher Is Better
a . 3.3887 |================================================================
b . 3.5666 |===================================================================
c . 3.3874 |================================================================
Cpuminer-Opt 23.5
Algorithm: Magi
kH/s > Higher Is Better
a . 79.32 |====================================================================
b . 78.74 |====================================================================
c . 78.68 |===================================================================
Cpuminer-Opt 23.5
Algorithm: scrypt
kH/s > Higher Is Better
a . 44.52 |====================================================================
b . 36.67 |========================================================
c . 36.39 |========================================================
Cpuminer-Opt 23.5
Algorithm: Deepcoin
kH/s > Higher Is Better
a . 992.85 |=====================================================
b . 1232.90 |==================================================================
c . 1185.50 |===============================================================
Cpuminer-Opt 23.5
Algorithm: Ringcoin
kH/s > Higher Is Better
a . 526.74 |===================================================================
b . 436.98 |========================================================
c . 436.97 |========================================================
Cpuminer-Opt 23.5
Algorithm: Blake-2 S
kH/s > Higher Is Better
a . 18920 |=======================================================
b . 23420 |====================================================================
c . 22910 |===================================================================
Cpuminer-Opt 23.5
Algorithm: Garlicoin
kH/s > Higher Is Better
a . 530.61 |===================================================================
b . 451.17 |=========================================================
c . 456.13 |==========================================================
Cpuminer-Opt 23.5
Algorithm: Skeincoin
kH/s > Higher Is Better
a . 3997.83 |==================================================
b . 5234.04 |==================================================================
c . 4034.91 |===================================================
Cpuminer-Opt 23.5
Algorithm: Myriad-Groestl
kH/s > Higher Is Better
a . 1627.74 |=================================================================
b . 1337.88 |======================================================
c . 1647.77 |==================================================================
Cpuminer-Opt 23.5
Algorithm: LBC, LBRY Credits
kH/s > Higher Is Better
a . 1723.39 |=======================================================
b . 2080.34 |==================================================================
c . 1755.69 |========================================================
Cpuminer-Opt 23.5
Algorithm: Quad SHA-256, Pyrite
kH/s > Higher Is Better
a . 8552.11 |==================================================================
b . 7883.39 |=============================================================
c . 7888.21 |=============================================================
Cpuminer-Opt 23.5
Algorithm: Triple SHA-256, Onecoin
kH/s > Higher Is Better
a . 9651.39 |==================================================================
b . 9651.58 |==================================================================
c . 9653.77 |==================================================================
C-Blosc 2.11
Test: blosclz shuffle - Buffer Size: 8MB
MB/s > Higher Is Better
a . 10149.8 |==============================================================
b . 10851.9 |==================================================================
c . 9898.3 |============================================================
C-Blosc 2.11
Test: blosclz shuffle - Buffer Size: 16MB
MB/s > Higher Is Better
a . 8877.9 |=================================================================
b . 9133.5 |===================================================================
c . 8841.6 |=================================================================
C-Blosc 2.11
Test: blosclz shuffle - Buffer Size: 32MB
MB/s > Higher Is Better
a . 8499.9 |=================================================================
b . 8751.4 |===================================================================
c . 8437.5 |=================================================================
C-Blosc 2.11
Test: blosclz shuffle - Buffer Size: 64MB
MB/s > Higher Is Better
a . 7801.5 |=================================================================
b . 8005.2 |===================================================================
c . 7884.2 |==================================================================
C-Blosc 2.11
Test: blosclz noshuffle - Buffer Size: 8MB
MB/s > Higher Is Better
a . 9850.2 |================================================================
b . 10107.7 |==================================================================
c . 9885.9 |=================================================================
C-Blosc 2.11
Test: blosclz shuffle - Buffer Size: 128MB
MB/s > Higher Is Better
a . 6629.3 |==================================================================
b . 6779.3 |===================================================================
c . 6665.5 |==================================================================
C-Blosc 2.11
Test: blosclz shuffle - Buffer Size: 256MB
MB/s > Higher Is Better
a . 5080.8 |==================================================================
b . 5182.4 |===================================================================
c . 5107.4 |==================================================================
C-Blosc 2.11
Test: blosclz bitshuffle - Buffer Size: 8MB
MB/s > Higher Is Better
a . 9769.5 |================================================================
b . 10085.2 |==================================================================
c . 10073.9 |==================================================================
C-Blosc 2.11
Test: blosclz noshuffle - Buffer Size: 16MB
MB/s > Higher Is Better
a . 8558.6 |=================================================================
b . 8842.0 |===================================================================
c . 8780.8 |===================================================================
C-Blosc 2.11
Test: blosclz noshuffle - Buffer Size: 32MB
MB/s > Higher Is Better
a . 8124.8 |==================================================================
b . 8273.4 |===================================================================
c . 8221.1 |===================================================================
C-Blosc 2.11
Test: blosclz noshuffle - Buffer Size: 64MB
MB/s > Higher Is Better
a . 7456.9 |===================================================================
b . 7472.9 |===================================================================
c . 7452.8 |===================================================================
C-Blosc 2.11
Test: blosclz bitshuffle - Buffer Size: 16MB
MB/s > Higher Is Better
a . 9000.6 |=================================================================
b . 9267.8 |===================================================================
c . 9052.0 |=================================================================
C-Blosc 2.11
Test: blosclz bitshuffle - Buffer Size: 32MB
MB/s > Higher Is Better
a . 8299.4 |================================================================
b . 8646.1 |===================================================================
c . 8660.0 |===================================================================
C-Blosc 2.11
Test: blosclz bitshuffle - Buffer Size: 64MB
MB/s > Higher Is Better
a . 7691.6 |==================================================================
b . 7799.7 |===================================================================
c . 7839.9 |===================================================================
C-Blosc 2.11
Test: blosclz noshuffle - Buffer Size: 128MB
MB/s > Higher Is Better
a . 6398.4 |===================================================================
b . 6413.8 |===================================================================
c . 6391.1 |===================================================================
C-Blosc 2.11
Test: blosclz noshuffle - Buffer Size: 256MB
MB/s > Higher Is Better
a . 4883.8 |=================================================================
b . 5007.6 |===================================================================
c . 4922.9 |==================================================================
C-Blosc 2.11
Test: blosclz bitshuffle - Buffer Size: 128MB
MB/s > Higher Is Better
a . 6601.2 |==================================================================
b . 6738.5 |===================================================================
c . 6470.2 |================================================================
C-Blosc 2.11
Test: blosclz bitshuffle - Buffer Size: 256MB
MB/s > Higher Is Better
a . 5086.8 |===================================================================
b . 5087.2 |===================================================================
c . 5010.3 |==================================================================
RabbitMQ 3.12.7
Scenario: Simple 2 Publishers + 4 Consumers
Messages/s > Higher Is Better
RabbitMQ 3.12.7
Scenario: 10 Queues, 100 Producers, 100 Consumers
Messages/s > Higher Is Better
RabbitMQ 3.12.7
Scenario: 60 Queues, 100 Producers, 100 Consumers
Messages/s > Higher Is Better
RabbitMQ 3.12.7
Scenario: 120 Queues, 400 Producers, 400 Consumers
Messages/s > Higher Is Better
RabbitMQ 3.12.7
Scenario: 200 Queues, 400 Producers, 400 Consumers
Messages/s > Higher Is Better
QuantLib 1.32
Configuration: Multi-Threaded
MFLOPS > Higher Is Better
a . 13707.0 |==================================================================
b . 13689.3 |==================================================================
c . 13287.0 |================================================================
QuantLib 1.32
Configuration: Single-Threaded
MFLOPS > Higher Is Better
a . 3489.3 |===================================================================
b . 3488.1 |===================================================================
c . 3375.6 |=================================================================
Apache Cassandra 4.1.3
Test: Writes
Op/s > Higher Is Better
a . 43984 |====================================================================
b . 37649 |==========================================================
c . 37916 |===========================================================
BRL-CAD 7.36
VGR Performance Metric
VGR Performance Metric > Higher Is Better
a . 54646 |====================================================================
b . 54938 |====================================================================
c . 53711 |==================================================================
oneDNN 3.3
Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 6.76989 |============================================================
b . 6.76791 |============================================================
c . 7.39175 |==================================================================
oneDNN 3.3
Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 6.08399 |==================================================================
b . 6.09457 |==================================================================
c . 6.07427 |==================================================================
oneDNN 3.3
Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 1.58930 |==================================================================
b . 1.59378 |==================================================================
c . 1.59090 |==================================================================
oneDNN 3.3
Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 2.40204 |=================================================================
b . 2.44303 |==================================================================
c . 2.40573 |=================================================================
oneDNN 3.3
Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 21.44 |============================================================
b . 24.37 |====================================================================
c . 22.28 |==============================================================
oneDNN 3.3
Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 5.96832 |==================================================================
b . 5.92005 |=================================================================
c . 5.93496 |==================================================================
oneDNN 3.3
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 8.49762 |==================================================================
b . 8.44523 |==================================================================
c . 8.47369 |==================================================================
oneDNN 3.3
Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 11.33250 |=================================================================
b . 10.26470 |===========================================================
c . 9.93517 |=========================================================
oneDNN 3.3
Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 9.87897 |================================================================
b . 10.07040 |=================================================================
c . 10.03890 |=================================================================
oneDNN 3.3
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 7.88294 |=================================================================
b . 8.05175 |==================================================================
c . 7.95953 |=================================================================
oneDNN 3.3
Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 2.15486 |================================================================
b . 2.22896 |==================================================================
c . 2.18576 |=================================================================
oneDNN 3.3
Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 2.45216 |=================================================================
b . 2.44729 |=================================================================
c . 2.47290 |==================================================================
oneDNN 3.3
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 7128.22 |==================================================================
b . 7138.73 |==================================================================
c . 7174.36 |==================================================================
oneDNN 3.3
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
ms < Lower Is Better
a . 3701.08 |==================================================================
b . 3699.05 |==================================================================
c . 3703.50 |==================================================================
oneDNN 3.3
Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 7179.51 |==================================================================
b . 7178.23 |==================================================================
c . 7176.24 |==================================================================
oneDNN 3.3
Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 50.88 |====================================================================
b . 51.01 |====================================================================
c . 50.97 |====================================================================
oneDNN 3.3
Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 42.98 |===================================================================
b . 43.39 |====================================================================
c . 43.16 |====================================================================
oneDNN 3.3
Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 35.72 |====================================================================
b . 35.78 |====================================================================
c . 35.73 |====================================================================
oneDNN 3.3
Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU
ms < Lower Is Better
a . 3671.69 |==================================================================
b . 3680.74 |==================================================================
c . 3680.01 |==================================================================
oneDNN 3.3
Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 7189.12 |==================================================================
b . 7178.37 |==================================================================
c . 7178.94 |==================================================================
oneDNN 3.3
Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU
ms < Lower Is Better
a . 3703.86 |==================================================================
b . 3697.25 |==================================================================
c . 3699.85 |==================================================================
OSPRay Studio 0.13
Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 26473 |=====================================================
b . 26522 |=====================================================
c . 33836 |====================================================================
OSPRay Studio 0.13
Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 31575 |====================================================================
b . 31507 |====================================================================
c . 31324 |===================================================================
OSPRay Studio 0.13
Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 33081 |==========================================================
b . 33073 |==========================================================
c . 39043 |====================================================================
OSPRay Studio 0.13
Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 429631 |=============================================================
b . 429276 |=============================================================
c . 470269 |===================================================================
OSPRay Studio 0.13
Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 858149 |=============================================================
b . 856610 |=============================================================
c . 943953 |===================================================================
OSPRay Studio 0.13
Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 436532 |=============================================================
b . 438395 |==============================================================
c . 476659 |===================================================================
OSPRay Studio 0.13
Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 869726 |=============================================================
b . 870122 |=============================================================
c . 951381 |===================================================================
OSPRay Studio 0.13
Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 514920 |=============================================================
b . 514145 |=============================================================
c . 561556 |===================================================================
OSPRay Studio 0.13
Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 1025430 |============================================================
b . 1024292 |============================================================
c . 1119430 |==================================================================
OSPRay Studio 0.13
Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 6673 |===============================================================
b . 6704 |===============================================================
c . 7343 |=====================================================================
OSPRay Studio 0.13
Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 6768 |===============================================================
b . 6786 |===============================================================
c . 7425 |=====================================================================
OSPRay Studio 0.13
Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 7982 |===============================================================
b . 7987 |===============================================================
c . 8722 |=====================================================================
OSPRay Studio 0.13
Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 111136 |=============================================================
b . 111078 |=============================================================
c . 122118 |===================================================================
OSPRay Studio 0.13
Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 217399 |=============================================================
b . 218393 |=============================================================
c . 239831 |===================================================================
OSPRay Studio 0.13
Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 112613 |=============================================================
b . 113201 |=============================================================
c . 123787 |===================================================================
OSPRay Studio 0.13
Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 221087 |=============================================================
b . 222412 |=============================================================
c . 242527 |===================================================================
OSPRay Studio 0.13
Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 132433 |=============================================================
b . 132979 |=============================================================
c . 145066 |===================================================================
OSPRay Studio 0.13
Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU
ms < Lower Is Better
a . 260252 |=============================================================
b . 261073 |=============================================================
c . 285007 |===================================================================
NCNN 20230517
Target: CPU - Model: mobilenet
ms < Lower Is Better
a . 18.82 |=====
b . 273.80 |===================================================================
c . 265.17 |=================================================================
NCNN 20230517
Target: CPU-v2-v2 - Model: mobilenet-v2
ms < Lower Is Better
a . 4.42 |====
b . 76.64 |====================================================================
c . 71.04 |===============================================================
NCNN 20230517
Target: CPU-v3-v3 - Model: mobilenet-v3
ms < Lower Is Better
a . 3.50 |====
b . 54.67 |==================================================================
c . 56.24 |====================================================================
NCNN 20230517
Target: CPU - Model: shufflenet-v2
ms < Lower Is Better
a . 3.45 |====
b . 55.66 |===============================================================
c . 59.68 |====================================================================
NCNN 20230517
Target: CPU - Model: mnasnet
ms < Lower Is Better
a . 3.77 |====
b . 59.72 |================================================================
c . 63.80 |====================================================================
NCNN 20230517
Target: CPU - Model: efficientnet-b0
ms < Lower Is Better
a . 7.17 |=====
b . 88.38 |==================================================================
c . 91.44 |====================================================================
NCNN 20230517
Target: CPU - Model: blazeface
ms < Lower Is Better
a . 1.29 |=====
b . 13.67 |====================================================
c . 17.89 |====================================================================
NCNN 20230517
Target: CPU - Model: googlenet
ms < Lower Is Better
a . 13.84 |=====
b . 196.54 |===================================================================
c . 180.35 |=============================================================
NCNN 20230517
Target: CPU - Model: vgg16
ms < Lower Is Better
a . 49.76 |======
b . 563.22 |===================================================================
c . 534.25 |================================================================
NCNN 20230517
Target: CPU - Model: resnet18
ms < Lower Is Better
a . 9.44 |====
b . 132.13 |===========================================================
c . 149.31 |===================================================================
NCNN 20230517
Target: CPU - Model: alexnet
ms < Lower Is Better
a . 7.44 |====
b . 119.06 |========================================================
c . 141.51 |===================================================================
NCNN 20230517
Target: CPU - Model: resnet50
ms < Lower Is Better
a . 23.94 |====
b . 372.91 |===================================================================
c . 349.97 |===============================================================
NCNN 20230517
Target: CPU - Model: yolov4-tiny
ms < Lower Is Better
a . 26.69 |=====
b . 354.78 |===================================================================
c . 336.66 |================================================================
NCNN 20230517
Target: CPU - Model: squeezenet_ssd
ms < Lower Is Better
a . 11.91 |=====
b . 174.87 |===================================================================
c . 174.48 |===================================================================
NCNN 20230517
Target: CPU - Model: regnety_400m
ms < Lower Is Better
a . 10.75 |=====
b . 143.48 |===================================================================
c . 127.58 |============================================================
NCNN 20230517
Target: CPU - Model: vision_transformer
ms < Lower Is Better
a . 185.96 |======
b . 2056.91 |==================================================================
c . 1952.08 |===============================================================
NCNN 20230517
Target: CPU - Model: FastestDet
ms < Lower Is Better
a . 5.05 |=====
b . 57.01 |============================================================
c . 64.89 |====================================================================
NCNN 20230517
Target: Vulkan GPU - Model: mobilenet
ms < Lower Is Better
a . 18.97 |=====
b . 282.29 |===================================================================
c . 266.51 |===============================================================
NCNN 20230517
Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2
ms < Lower Is Better
a . 4.39 |====
b . 75.30 |====================================================================
c . 66.65 |============================================================
NCNN 20230517
Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3
ms < Lower Is Better
a . 3.48 |====
b . 66.64 |====================================================================
c . 54.85 |========================================================
NCNN 20230517
Target: Vulkan GPU - Model: shufflenet-v2
ms < Lower Is Better
a . 3.40 |====
b . 54.38 |=================================================================
c . 56.62 |====================================================================
NCNN 20230517
Target: Vulkan GPU - Model: mnasnet
ms < Lower Is Better
a . 3.77 |====
b . 62.71 |===================================================================
c . 63.33 |====================================================================
NCNN 20230517
Target: Vulkan GPU - Model: efficientnet-b0
ms < Lower Is Better
a . 5.61 |====
b . 86.30 |============================================================
c . 97.95 |====================================================================
NCNN 20230517
Target: Vulkan GPU - Model: blazeface
ms < Lower Is Better
a . 0.92 |===
b . 21.67 |====================================================================
c . 15.59 |=================================================
NCNN 20230517
Target: Vulkan GPU - Model: googlenet
ms < Lower Is Better
a . 11.36 |====
b . 184.62 |===================================================================
c . 178.40 |=================================================================
NCNN 20230517
Target: Vulkan GPU - Model: vgg16
ms < Lower Is Better
a . 47.81 |======
b . 542.46 |===================================================================
c . 541.65 |===================================================================
NCNN 20230517
Target: Vulkan GPU - Model: resnet18
ms < Lower Is Better
a . 8.36 |====
b . 130.84 |=================================================================
c . 134.78 |===================================================================
NCNN 20230517
Target: Vulkan GPU - Model: alexnet
ms < Lower Is Better
a . 6.81 |====
b . 122.08 |=================================================================
c . 124.98 |===================================================================
NCNN 20230517
Target: Vulkan GPU - Model: resnet50
ms < Lower Is Better
a . 23.98 |=====
b . 354.34 |===================================================================
c . 328.87 |==============================================================
NCNN 20230517
Target: Vulkan GPU - Model: yolov4-tiny
ms < Lower Is Better
a . 26.68 |=====
b . 347.17 |===================================================================
c . 341.71 |==================================================================
NCNN 20230517
Target: Vulkan GPU - Model: squeezenet_ssd
ms < Lower Is Better
a . 11.90 |====
b . 177.20 |===================================================================
c . 164.33 |==============================================================
NCNN 20230517
Target: Vulkan GPU - Model: regnety_400m
ms < Lower Is Better
a . 8.05 |====
b . 132.95 |===================================================================
c . 133.77 |===================================================================
NCNN 20230517
Target: Vulkan GPU - Model: vision_transformer
ms < Lower Is Better
a . 182.09 |======
b . 2069.02 |==================================================================
c . 1933.05 |==============================================================
NCNN 20230517
Target: Vulkan GPU - Model: FastestDet
ms < Lower Is Better
a . 4.83 |=====
b . 62.98 |====================================================================
c . 55.01 |===========================================================
OpenVINO 2023.2.dev
Model: Face Detection FP16 - Device: CPU
ms < Lower Is Better
a . 3600.29 |=============================================================
b . 3719.15 |===============================================================
c . 3922.05 |==================================================================
OpenVINO 2023.2.dev
Model: Person Detection FP16 - Device: CPU
ms < Lower Is Better
a . 346.37 |===============================================================
b . 369.62 |===================================================================
c . 370.61 |===================================================================
OpenVINO 2023.2.dev
Model: Person Detection FP32 - Device: CPU
ms < Lower Is Better
a . 344.94 |==============================================================
b . 370.73 |===================================================================
c . 372.34 |===================================================================
OpenVINO 2023.2.dev
Model: Vehicle Detection FP16 - Device: CPU
ms < Lower Is Better
a . 48.04 |===============================================================
b . 51.72 |====================================================================
c . 51.79 |====================================================================
OpenVINO 2023.2.dev
Model: Face Detection FP16-INT8 - Device: CPU
ms < Lower Is Better
a . 985.39 |=============================================================
b . 1059.61 |==================================================================
c . 1061.06 |==================================================================
OpenVINO 2023.2.dev
Model: Face Detection Retail FP16 - Device: CPU
ms < Lower Is Better
a . 14.73 |==================================================================
b . 15.29 |====================================================================
c . 15.17 |===================================================================
OpenVINO 2023.2.dev
Model: Road Segmentation ADAS FP16 - Device: CPU
ms < Lower Is Better
a . 97.39 |===============================================================
b . 103.02 |===================================================================
c . 103.24 |===================================================================
OpenVINO 2023.2.dev
Model: Vehicle Detection FP16-INT8 - Device: CPU
ms < Lower Is Better
a . 17.97 |=================================================================
b . 18.93 |====================================================================
c . 18.88 |====================================================================
OpenVINO 2023.2.dev
Model: Weld Porosity Detection FP16 - Device: CPU
ms < Lower Is Better
a . 37.89 |===============================================================
b . 41.18 |====================================================================
c . 41.07 |====================================================================
OpenVINO 2023.2.dev
Model: Face Detection Retail FP16-INT8 - Device: CPU
ms < Lower Is Better
a . 6.04 |===============================================================
b . 6.59 |=====================================================================
c . 6.56 |=====================================================================
OpenVINO 2023.2.dev
Model: Road Segmentation ADAS FP16-INT8 - Device: CPU
ms < Lower Is Better
a . 49.36 |===============================================================
b . 52.86 |====================================================================
c . 52.94 |====================================================================
OpenVINO 2023.2.dev
Model: Machine Translation EN To DE FP16 - Device: CPU
ms < Lower Is Better
a . 287.28 |==============================================================
b . 312.41 |===================================================================
c . 312.33 |===================================================================
OpenVINO 2023.2.dev
Model: Weld Porosity Detection FP16-INT8 - Device: CPU
ms < Lower Is Better
a . 10.38 |=================================================================
b . 10.91 |====================================================================
c . 10.86 |====================================================================
OpenVINO 2023.2.dev
Model: Person Vehicle Bike Detection FP16 - Device: CPU
ms < Lower Is Better
a . 27.41 |================================================================
b . 29.13 |====================================================================
c . 29.26 |====================================================================
OpenVINO 2023.2.dev
Model: Handwritten English Recognition FP16 - Device: CPU
ms < Lower Is Better
a . 75.35 |=============================================================
b . 83.53 |====================================================================
c . 83.82 |====================================================================
OpenVINO 2023.2.dev
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
ms < Lower Is Better
a . 1.37 |==================================================================
b . 1.40 |====================================================================
c . 1.43 |=====================================================================
OpenVINO 2023.2.dev
Model: Handwritten English Recognition FP16-INT8 - Device: CPU
ms < Lower Is Better
a . 65.40 |=============================================================
b . 73.40 |====================================================================
c . 72.42 |===================================================================
OpenVINO 2023.2.dev
Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU
ms < Lower Is Better
a . 0.47 |=============================================================
b . 0.53 |=====================================================================
c . 0.53 |=====================================================================
Neural Magic DeepSparse 1.5
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 501.90 |=================================================================
b . 504.86 |==================================================================
c . 514.94 |===================================================================
Neural Magic DeepSparse 1.5
Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 12.14 |==========================================================
b . 12.66 |============================================================
c . 14.25 |====================================================================
Neural Magic DeepSparse 1.5
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 31.29 |=================================================================
b . 31.27 |=================================================================
c . 32.75 |====================================================================
Neural Magic DeepSparse 1.5
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 121.50 |==================================================================
b . 122.59 |==================================================================
c . 124.18 |===================================================================
Neural Magic DeepSparse 1.5
Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 36.73 |===================================================================
b . 36.80 |====================================================================
c . 37.01 |====================================================================
Neural Magic DeepSparse 1.5
Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 4.6989 |==========================================================
b . 5.0779 |===============================================================
c . 5.4230 |===================================================================
Neural Magic DeepSparse 1.5
Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 93.65 |====================================================================
b . 88.48 |================================================================
c . 92.45 |===================================================================
Neural Magic DeepSparse 1.5
Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 469.68 |=================================================================
b . 466.25 |================================================================
c . 485.92 |===================================================================
Neural Magic DeepSparse 1.5
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 37.08 |====================================================================
b . 37.15 |====================================================================
c . 37.24 |====================================================================
Neural Magic DeepSparse 1.5
Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 86.90 |==============================================================
b . 92.70 |===================================================================
c . 94.63 |====================================================================
Neural Magic DeepSparse 1.5
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 72.27 |====================================================================
b . 66.28 |==============================================================
c . 71.47 |===================================================================
Neural Magic DeepSparse 1.5
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 292.80 |=================================================================
b . 296.40 |==================================================================
c . 301.40 |===================================================================
Neural Magic DeepSparse 1.5
Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 29.05 |========================================================
b . 27.95 |======================================================
c . 35.13 |====================================================================
Neural Magic DeepSparse 1.5
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 136.21 |===============================================================
b . 145.16 |===================================================================
c . 136.01 |===============================================================
Neural Magic DeepSparse 1.5
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
ms/batch < Lower Is Better
a . 590.17 |===================================================================
b . 560.72 |================================================================
c . 590.37 |===================================================================
DaCapo Benchmark 23.11
Java Test: Jython
msec < Lower Is Better
a . 4755 |=====================================================================
b . 4585 |===================================================================
c . 4654 |====================================================================
DaCapo Benchmark 23.11
Java Test: Eclipse
msec < Lower Is Better
a . 14549 |====================================================================
b . 14537 |====================================================================
c . 14307 |===================================================================
DaCapo Benchmark 23.11
Java Test: GraphChi
msec < Lower Is Better
a . 4418 |=====================================================================
b . 4400 |=====================================================================
c . 4428 |=====================================================================
DaCapo Benchmark 23.11
Java Test: Tradesoap
msec < Lower Is Better
a . 2943 |=====================================================================
b . 2939 |=====================================================================
c . 2947 |=====================================================================
DaCapo Benchmark 23.11
Java Test: Tradebeans
msec < Lower Is Better
a . 7683 |================================================
b . 7183 |=============================================
c . 10909 |====================================================================
DaCapo Benchmark 23.11
Java Test: Spring Boot
msec < Lower Is Better
a . 5151 |=================================================================
b . 5416 |=====================================================================
c . 5444 |=====================================================================
DaCapo Benchmark 23.11
Java Test: Apache Kafka
msec < Lower Is Better
a . 5346 |=====================================================================
b . 5341 |=====================================================================
c . 5351 |=====================================================================
DaCapo Benchmark 23.11
Java Test: Apache Tomcat
msec < Lower Is Better
a . 14326 |===================================================================
b . 14327 |===================================================================
c . 14456 |====================================================================
DaCapo Benchmark 23.11
Java Test: jMonkeyEngine
msec < Lower Is Better
a . 6914 |=====================================================================
b . 6893 |=====================================================================
c . 6876 |=====================================================================
DaCapo Benchmark 23.11
Java Test: Apache Cassandra
msec < Lower Is Better
a . 7845 |=====================================================================
b . 7797 |=====================================================================
c . 7848 |=====================================================================
DaCapo Benchmark 23.11
Java Test: Apache Xalan XSLT
msec < Lower Is Better
a . 1248 |============================================================
b . 1438 |=====================================================================
c . 1264 |=============================================================
DaCapo Benchmark 23.11
Java Test: Batik SVG Toolkit
msec < Lower Is Better
a . 1392 |=====================================================================
b . 1321 |=================================================================
c . 1362 |====================================================================
DaCapo Benchmark 23.11
Java Test: H2 Database Engine
msec < Lower Is Better
a . 5250 |===================================================================
b . 5440 |=====================================================================
c . 5419 |=====================================================================
DaCapo Benchmark 23.11
Java Test: FOP Print Formatter
msec < Lower Is Better
a . 709 |======================================================================
b . 702 |=====================================================================
c . 690 |====================================================================
DaCapo Benchmark 23.11
Java Test: PMD Source Code Analyzer
msec < Lower Is Better
a . 3315 |===============================================================
b . 3645 |=====================================================================
c . 3187 |============================================================
DaCapo Benchmark 23.11
Java Test: Apache Lucene Search Index
msec < Lower Is Better
a . 3397 |================================================================
b . 3655 |=====================================================================
c . 3541 |===================================================================
DaCapo Benchmark 23.11
Java Test: Apache Lucene Search Engine
msec < Lower Is Better
a . 6558 |====================================================================
b . 6472 |===================================================================
c . 6687 |=====================================================================
DaCapo Benchmark 23.11
Java Test: Avrora AVR Simulation Framework
msec < Lower Is Better
a . 2554 |===================================================================
b . 2524 |===================================================================
c . 2612 |=====================================================================
DaCapo Benchmark 23.11
Java Test: BioJava Biological Data Framework
msec < Lower Is Better
a . 6163 |====================================================================
b . 6160 |====================================================================
c . 6249 |=====================================================================
DaCapo Benchmark 23.11
Java Test: Zxing 1D/2D Barcode Image Processing
msec < Lower Is Better
a . 3123 |===================================================================
b . 3195 |=====================================================================
c . 3198 |=====================================================================
DaCapo Benchmark 23.11
Java Test: H2O In-Memory Platform For Machine Learning
msec < Lower Is Better
a . 3223 |===========================================================
b . 3772 |=====================================================================
c . 3335 |=============================================================
CloverLeaf 1.3
Input: clover_bm
Seconds < Lower Is Better
a . 117.10 |===================================================================
b . 116.20 |==================================================================
c . 117.62 |===================================================================
CloverLeaf 1.3
Input: clover_bm64_short
Seconds < Lower Is Better
a . 206.97 |===================================================================
b . 203.68 |==================================================================
c . 203.49 |==================================================================
OpenRadioss 2023.09.15
Model: Cell Phone Drop Test
Seconds < Lower Is Better
a . 245.14 |===================================================================
b . 243.36 |===================================================================
c . 241.64 |==================================================================
OpenRadioss 2023.09.15
Model: Bird Strike on Windshield
Seconds < Lower Is Better
a . 653.24 |===================================================================
b . 650.51 |==================================================================
c . 657.96 |===================================================================
OpenRadioss 2023.09.15
Model: Rubber O-Ring Seal Installation
Seconds < Lower Is Better
a . 482.80 |===================================================================
b . 479.06 |==================================================================
c . 480.70 |===================================================================
easyWave r34
Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240
Seconds < Lower Is Better
a . 10.613 |===================================================================
b . 9.924 |===============================================================
c . 9.620 |=============================================================
easyWave r34
Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200
Seconds < Lower Is Better
a . 189.03 |===================================================================
b . 188.68 |===================================================================
c . 188.52 |===================================================================
libavif avifenc 1.0
Encoder Speed: 0
Seconds < Lower Is Better
a . 381.27 |=================================================================
b . 383.21 |=================================================================
c . 392.47 |===================================================================
libavif avifenc 1.0
Encoder Speed: 2
Seconds < Lower Is Better
a . 168.17 |=================================================================
b . 168.56 |=================================================================
c . 172.81 |===================================================================
libavif avifenc 1.0
Encoder Speed: 6
Seconds < Lower Is Better
a . 14.73 |===================================================================
b . 14.83 |===================================================================
c . 14.95 |====================================================================
libavif avifenc 1.0
Encoder Speed: 6, Lossless
Seconds < Lower Is Better
a . 22.31 |====================================================================
b . 22.19 |===================================================================
c . 22.45 |====================================================================
libavif avifenc 1.0
Encoder Speed: 10, Lossless
Seconds < Lower Is Better
a . 9.678 |====================================================================
b . 9.506 |===================================================================
c . 9.597 |===================================================================
Timed FFmpeg Compilation 6.1
Time To Compile
Seconds < Lower Is Better
a . 128.96 |==================================================================
b . 128.75 |==================================================================
c . 130.59 |===================================================================
Timed GCC Compilation 13.2
Time To Compile
Seconds < Lower Is Better
a . 2337.79 |=================================================================
b . 2342.49 |=================================================================
c . 2374.92 |==================================================================
Timed Gem5 Compilation 23.0.1
Time To Compile
Seconds < Lower Is Better
a . 1296.13 |=================================================================
b . 1299.28 |==================================================================
c . 1309.17 |==================================================================
QMCPACK 3.17.1
Input: H4_ae
Total Execution Time - Seconds < Lower Is Better
a . 76.19 |====================================================================
b . 69.78 |==============================================================
c . 75.96 |====================================================================
QMCPACK 3.17.1
Input: Li2_STO_ae
Total Execution Time - Seconds < Lower Is Better
a . 687.22 |===================================================================
b . 653.08 |================================================================
c . 675.81 |==================================================================
QMCPACK 3.17.1
Input: LiH_ae_MSD
Total Execution Time - Seconds < Lower Is Better
a . 83.22 |=================================================================
b . 83.17 |=================================================================
c . 87.02 |====================================================================
QMCPACK 3.17.1
Input: simple-H2O
Total Execution Time - Seconds < Lower Is Better
a . 31.22 |===================================================================
b . 31.76 |====================================================================
c . 31.75 |====================================================================
QMCPACK 3.17.1
Input: O_ae_pyscf_UHF
Total Execution Time - Seconds < Lower Is Better
a . 222.05 |==============================================================
b . 222.61 |==============================================================
c . 239.07 |===================================================================
QMCPACK 3.17.1
Input: FeCO6_b3lyp_gms
Total Execution Time - Seconds < Lower Is Better
a . 110.52 |====================================================
b . 110.13 |====================================================
c . 141.41 |===================================================================