dddxxx
Intel Core i7-8565U testing with a Dell 0KTW76 (1.17.0 BIOS) and Intel UHD 620 WHL GT2 15GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2308067-NE-DDDXXX42317&grs&rdt.
SQLite
Threads / Copies: 1
Neural Magic DeepSparse
Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream
NCNN
Target: CPU - Model: shufflenet-v2
Redis 7.0.12 + memtier_benchmark
Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:5
SQLite
Threads / Copies: 2
SQLite
Threads / Copies: 4
Redis 7.0.12 + memtier_benchmark
Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:10
Stress-NG
Test: MMAP
Redis 7.0.12 + memtier_benchmark
Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5
Redis 7.0.12 + memtier_benchmark
Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5
NCNN
Target: CPU - Model: mnasnet
Redis 7.0.12 + memtier_benchmark
Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10
Stress-NG
Test: MEMFD
Redis 7.0.12 + memtier_benchmark
Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10
Stress-NG
Test: Futex
Stress-NG
Test: Forking
Neural Magic DeepSparse
Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream
Stress-NG
Test: CPU Cache
Stress-NG
Test: Crypto
Stress-NG
Test: Zlib
SVT-AV1
Encoder Mode: Preset 12 - Input: Bosphorus 4K
Stress-NG
Test: Hash
Neural Magic DeepSparse
Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream
Stress-NG
Test: Pthread
NCNN
Target: CPU-v3-v3 - Model: mobilenet-v3
Stress-NG
Test: SENDFILE
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
Stress-NG
Test: AVL Tree
Neural Magic DeepSparse
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
Stress-NG
Test: Malloc
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 1080p
SVT-AV1
Encoder Mode: Preset 4 - Input: Bosphorus 4K
Stress-NG
Test: Mutex
OSPRay
Benchmark: gravity_spheres_volume/dim_512/scivis/real_time
dav1d
Video Input: Summer Nature 1080p
Apache IoTDB
Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 500
Apache IoTDB
Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 500
Apache IoTDB
Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 500
Stress-NG
Test: NUMA
SVT-AV1
Encoder Mode: Preset 4 - Input: Bosphorus 1080p
Stress-NG
Test: Poll
Stress-NG
Test: Atomic
SVT-AV1
Encoder Mode: Preset 13 - Input: Bosphorus 4K
Apache IoTDB
Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 500
OSPRay
Benchmark: particle_volume/ao/real_time
Stress-NG
Test: Fused Multiply-Add
NCNN
Target: CPU-v2-v2 - Model: mobilenet-v2
Neural Magic DeepSparse
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream
Stress-NG
Test: Vector Floating Point
Stress-NG
Test: Pipe
Stress-NG
Test: CPU Stress
Stress-NG
Test: IO_uring
Stress-NG
Test: Glibc Qsort Data Sorting
Apache IoTDB
Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200
Apache IoTDB
Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 500
Apache IoTDB
Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500
Stress-NG
Test: Cloning
NCNN
Target: CPU - Model: mobilenet
Liquid-DSP
Threads: 4 - Buffer Length: 256 - Filter Length: 57
Neural Magic DeepSparse
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream
NCNN
Target: Vulkan GPU - Model: regnety_400m
Liquid-DSP
Threads: 8 - Buffer Length: 256 - Filter Length: 57
Stress-NG
Test: Glibc C String Functions
Stress-NG
Test: System V Message Passing
Neural Magic DeepSparse
Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Stress-NG
Test: Function Call
OSPRay
Benchmark: particle_volume/pathtracer/real_time
NCNN
Target: CPU - Model: resnet50
OSPRay
Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time
libxsmm
M N K: 128
NCNN
Target: CPU - Model: squeezenet_ssd
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
Apache IoTDB
Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500
Liquid-DSP
Threads: 8 - Buffer Length: 256 - Filter Length: 32
Stress-NG
Test: x86_64 RdRand
Apache IoTDB
Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 200
Apache IoTDB
Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 500
Stress-NG
Test: Context Switching
Apache IoTDB
Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 200
Apache IoTDB
Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200
NCNN
Target: CPU - Model: efficientnet-b0
NCNN
Target: Vulkan GPU - Model: FastestDet
Apache IoTDB
Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 200
Stress-NG
Test: Matrix 3D Math
Apache IoTDB
Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 200
Neural Magic DeepSparse
Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream
NCNN
Target: Vulkan GPU - Model: squeezenet_ssd
Memcached
Set To Get Ratio: 1:10
Neural Magic DeepSparse
Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream
VVenC
Video Input: Bosphorus 1080p - Video Preset: Fast
NCNN
Target: CPU - Model: FastestDet
NCNN
Target: Vulkan GPU - Model: mobilenet
Neural Magic DeepSparse
Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream
Apache IoTDB
Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 500
Stress-NG
Test: Floating Point
Build2
Time To Compile
NCNN
Target: CPU - Model: yolov4-tiny
Neural Magic DeepSparse
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
dav1d
Video Input: Chimera 1080p
Liquid-DSP
Threads: 8 - Buffer Length: 256 - Filter Length: 512
NCNN
Target: CPU - Model: blazeface
OSPRay
Benchmark: particle_volume/scivis/real_time
Memcached
Set To Get Ratio: 1:100
NCNN
Target: Vulkan GPU - Model: blazeface
SVT-AV1
Encoder Mode: Preset 12 - Input: Bosphorus 1080p
Embree
Binary: Pathtracer - Model: Crown
SVT-AV1
Encoder Mode: Preset 13 - Input: Bosphorus 1080p
NCNN
Target: Vulkan GPU - Model: vision_transformer
Neural Magic DeepSparse
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream
Stress-NG
Test: Vector Math
Neural Magic DeepSparse
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream
NCNN
Target: Vulkan GPU - Model: vgg16
OSPRay
Benchmark: gravity_spheres_volume/dim_512/ao/real_time
Apache IoTDB
Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 200
NCNN
Target: CPU - Model: vgg16
Apache IoTDB
Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 500
Memcached
Set To Get Ratio: 1:5
NCNN
Target: Vulkan GPU - Model: resnet18
NCNN
Target: Vulkan GPU - Model: efficientnet-b0
Timed LLVM Compilation
Build System: Unix Makefiles
Z3 Theorem Prover
SMT File: 1.smt2
NCNN
Target: Vulkan GPU - Model: resnet50
Apache IoTDB
Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 200
Stress-NG
Test: Matrix Math
Embree
Binary: Pathtracer ISPC - Model: Crown
Neural Magic DeepSparse
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
QuantLib
Liquid-DSP
Threads: 2 - Buffer Length: 256 - Filter Length: 512
Apache IoTDB
Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 500
dav1d
Video Input: Summer Nature 4K
Apache IoTDB
Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 200
Stress-NG
Test: Memory Copying
Apache IoTDB
Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 200
NCNN
Target: CPU - Model: regnety_400m
Timed Godot Game Engine Compilation
Time To Compile
Neural Magic DeepSparse
Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream
VVenC
Video Input: Bosphorus 4K - Video Preset: Fast
Neural Magic DeepSparse
Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
VVenC
Video Input: Bosphorus 4K - Video Preset: Faster
NCNN
Target: CPU - Model: vision_transformer
Neural Magic DeepSparse
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
Stress-NG
Test: Wide Vector Math
Embree
Binary: Pathtracer - Model: Asian Dragon Obj
Stress-NG
Test: Semaphores
Neural Magic DeepSparse
Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Liquid-DSP
Threads: 1 - Buffer Length: 256 - Filter Length: 32
libxsmm
M N K: 32
NCNN
Target: Vulkan GPU - Model: googlenet
Timed LLVM Compilation
Build System: Ninja
NCNN
Target: Vulkan GPU - Model: mnasnet
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 4K
NCNN
Target: Vulkan GPU - Model: yolov4-tiny
Xonotic
Resolution: 1920 x 1080 - Effects Quality: Ultra
Stress-NG
Test: Socket Activity
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
Apache IoTDB
Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 200
Neural Magic DeepSparse
Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
Embree
Binary: Pathtracer - Model: Asian Dragon
Apache IoTDB
Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 200
Xonotic
Resolution: 1920 x 1080 - Effects Quality: Ultimate
Z3 Theorem Prover
SMT File: 2.smt2
NCNN
Target: CPU - Model: alexnet
Apache IoTDB
Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 500
NCNN
Target: Vulkan GPU - Model: shufflenet-v2
NCNN
Target: CPU - Model: googlenet
Liquid-DSP
Threads: 2 - Buffer Length: 256 - Filter Length: 57
Liquid-DSP
Threads: 4 - Buffer Length: 256 - Filter Length: 32
Xonotic
Resolution: 1920 x 1080 - Effects Quality: High
dav1d
Video Input: Chimera 1080p 10-bit
Neural Magic DeepSparse
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
NCNN
Target: Vulkan GPU - Model: alexnet
Liquid-DSP
Threads: 1 - Buffer Length: 256 - Filter Length: 512
VVenC
Video Input: Bosphorus 1080p - Video Preset: Faster
Liquid-DSP
Threads: 2 - Buffer Length: 256 - Filter Length: 32
libxsmm
M N K: 64
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Opus Codec Encoding
WAV To Opus Encode
NCNN
Target: CPU - Model: resnet18
Xonotic
Resolution: 1920 x 1080 - Effects Quality: Low
Liquid-DSP
Threads: 4 - Buffer Length: 256 - Filter Length: 512
Apache Cassandra
Test: Writes
Stress-NG
Test: Vector Shuffle
Liquid-DSP
Threads: 1 - Buffer Length: 256 - Filter Length: 57
NCNN
Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3
NCNN
Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2
Intel Open Image Denoise
Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only
Intel Open Image Denoise
Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only
Intel Open Image Denoise
Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only
vkpeak
fp32-scalar
Phoronix Test Suite v10.8.5