extra tests

benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2310231-NE-EXTRATEST13
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

AV1 2 Tests
C/C++ Compiler Tests 2 Tests
CPU Massive 5 Tests
Creator Workloads 8 Tests
Database Test Suite 3 Tests
Encoding 3 Tests
Game Development 2 Tests
HPC - High Performance Computing 4 Tests
Java Tests 2 Tests
Machine Learning 2 Tests
Multi-Core 9 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 3 Tests
OpenMPI Tests 4 Tests
Renderers 2 Tests
Server 3 Tests
Server CPU Tests 4 Tests
Video Encoding 3 Tests
Common Workstation Benchmarks 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
RESET
October 23 2023
  6 Hours, 8 Minutes
RESET2
October 23 2023
  1 Hour, 18 Minutes
RESET3
October 23 2023
  5 Hours, 18 Minutes
Invert Hiding All Results Option
  4 Hours, 15 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

extra tests benchmarks for a future article. RESET: Processor: AMD EPYC 9124 16-Core @ 3.00GHz (16 Cores / 32 Threads), Motherboard: Supermicro H13SSW (1.1 BIOS), Memory: 12 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1024x768 RESET2: Processor: AMD EPYC 9124 16-Core @ 3.00GHz (16 Cores / 32 Threads), Motherboard: Supermicro H13SSW (1.1 BIOS), Memory: 12 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1024x768 RESET3: Processor: AMD EPYC 9334 32-Core @ 2.70GHz (32 Cores / 64 Threads), Motherboard: Supermicro H13SSW (1.1 BIOS), Memory: 12 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb, Monitor: DELL E207WFP OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1680x1050 Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:10 Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:100 Stress-NG 0.16.04 Test: IO_uring Stress-NG 0.16.04 Test: Hash Bogo Ops/s > Higher Is Better RESET .. 3622490.53 |=========================== RESET3 . 7756366.80 |========================================================== Stress-NG 0.16.04 Test: MMAP Bogo Ops/s > Higher Is Better RESET .. 297.29 |================================ RESET3 . 577.78 |============================================================== Stress-NG 0.16.04 Test: NUMA Bogo Ops/s > Higher Is Better RESET .. 664.87 |================================ RESET3 . 1272.74 |============================================================= Stress-NG 0.16.04 Test: Pipe Bogo Ops/s > Higher Is Better RESET .. 13860878.09 |=============================== RESET3 . 25368697.90 |========================================================= Stress-NG 0.16.04 Test: Poll Bogo Ops/s > Higher Is Better RESET .. 2214330.78 |============================ RESET3 . 4603498.17 |========================================================== Stress-NG 0.16.04 Test: Zlib Bogo Ops/s > Higher Is Better RESET .. 1466.40 |============================== RESET3 . 2988.69 |============================================================= Stress-NG 0.16.04 Test: Futex Bogo Ops/s > Higher Is Better RESET .. 4273978.26 |==================================================== RESET3 . 4747454.51 |========================================================== Stress-NG 0.16.04 Test: MEMFD Bogo Ops/s > Higher Is Better RESET .. 431.59 |====================================================== RESET3 . 495.03 |============================================================== Stress-NG 0.16.04 Test: Mutex Bogo Ops/s > Higher Is Better RESET .. 789472.50 |======================================================== RESET3 . 828974.29 |=========================================================== Stress-NG 0.16.04 Test: Atomic Bogo Ops/s > Higher Is Better RESET .. 246.62 |========================================================== RESET3 . 265.54 |============================================================== Stress-NG 0.16.04 Test: Crypto Bogo Ops/s > Higher Is Better RESET .. 39959.41 |============================== RESET3 . 79692.92 |============================================================ Stress-NG 0.16.04 Test: Malloc Bogo Ops/s > Higher Is Better RESET .. 31210490.91 |============= RESET3 . 137709065.86 |======================================================== Stress-NG 0.16.04 Test: Cloning Bogo Ops/s > Higher Is Better RESET .. 3317.10 |====================================================== RESET3 . 3751.82 |============================================================= Stress-NG 0.16.04 Test: Forking Bogo Ops/s > Higher Is Better RESET .. 32071.19 |==================================== RESET3 . 54137.34 |============================================================ Stress-NG 0.16.04 Test: AVL Tree Bogo Ops/s > Higher Is Better RESET .. 205.07 |=============================== RESET3 . 407.92 |============================================================== Stress-NG 0.16.04 Test: SENDFILE Bogo Ops/s > Higher Is Better RESET .. 419265.75 |===================================== RESET3 . 665723.58 |=========================================================== Stress-NG 0.16.04 Test: CPU Cache Bogo Ops/s > Higher Is Better RESET .. 1163806.08 |======================================================= RESET3 . 1221906.48 |========================================================== Stress-NG 0.16.04 Test: CPU Stress Bogo Ops/s > Higher Is Better RESET .. 41635.43 |============================ RESET3 . 87949.71 |============================================================ Stress-NG 0.16.04 Test: Semaphores Bogo Ops/s > Higher Is Better RESET .. 42481788.68 |========================== RESET3 . 92985304.75 |========================================================= Stress-NG 0.16.04 Test: Matrix Math Bogo Ops/s > Higher Is Better RESET .. 87537.46 |================================ RESET3 . 160597.83 |=========================================================== Stress-NG 0.16.04 Test: Vector Math Bogo Ops/s > Higher Is Better RESET .. 117532.19 |================================ RESET3 . 219207.68 |=========================================================== Stress-NG 0.16.04 Test: AVX-512 VNNI Bogo Ops/s > Higher Is Better RESET .. 1851108.77 |================================ RESET3 . 3384972.44 |========================================================== Stress-NG 0.16.04 Test: Function Call Bogo Ops/s > Higher Is Better RESET .. 13421.19 |============================= RESET3 . 27709.80 |============================================================ Stress-NG 0.16.04 Test: x86_64 RdRand Bogo Ops/s > Higher Is Better RESET .. 6022050.43 |=========================== RESET3 . 12951786.69 |========================================================= Stress-NG 0.16.04 Test: Floating Point Bogo Ops/s > Higher Is Better RESET .. 5845.74 |============================= RESET3 . 12241.13 |============================================================ Stress-NG 0.16.04 Test: Matrix 3D Math Bogo Ops/s > Higher Is Better RESET .. 5817.58 |======================================= RESET3 . 9028.11 |============================================================= Stress-NG 0.16.04 Test: Memory Copying Bogo Ops/s > Higher Is Better RESET .. 7269.20 |============================== RESET3 . 14537.11 |============================================================ Stress-NG 0.16.04 Test: Vector Shuffle Bogo Ops/s > Higher Is Better RESET .. 12554.84 |============================ RESET3 . 26692.66 |============================================================ Stress-NG 0.16.04 Test: Mixed Scheduler Bogo Ops/s > Higher Is Better RESET .. 39604.33 |============================================ RESET3 . 53630.31 |============================================================ Stress-NG 0.16.04 Test: Socket Activity Bogo Ops/s > Higher Is Better RESET .. 10472.15 |=============================== RESET3 . 20183.09 |============================================================ Stress-NG 0.16.04 Test: Wide Vector Math Bogo Ops/s > Higher Is Better RESET .. 772551.49 |=============================== RESET3 . 1424072.34 |========================================================== Stress-NG 0.16.04 Test: Context Switching Bogo Ops/s > Higher Is Better RESET .. 10072239.66 |============================= RESET3 . 20135718.92 |========================================================= Stress-NG 0.16.04 Test: Fused Multiply-Add Bogo Ops/s > Higher Is Better RESET .. 16158855.40 |=============================== RESET3 . 29786647.25 |========================================================= Stress-NG 0.16.04 Test: Vector Floating Point Bogo Ops/s > Higher Is Better RESET .. 53844.48 |=============================== RESET3 . 102433.04 |=========================================================== Stress-NG 0.16.04 Test: Glibc C String Functions Bogo Ops/s > Higher Is Better RESET .. 19957308.60 |============================= RESET3 . 39779508.19 |========================================================= Stress-NG 0.16.04 Test: Glibc Qsort Data Sorting Bogo Ops/s > Higher Is Better RESET .. 463.11 |================================= RESET3 . 858.22 |============================================================== Stress-NG 0.16.04 Test: System V Message Passing Bogo Ops/s > Higher Is Better RESET .. 7982733.22 |============================================= RESET3 . 10016615.70 |========================================================= Stress-NG 0.16.04 Test: Pthread Bogo Ops/s > Higher Is Better RESET .. 119839.68 |========================================================= RESET3 . 124853.18 |=========================================================== nekRS 23.0 Input: Kershaw flops/rank > Higher Is Better RESET .. 10295200000 |========================================================= RESET2 . 10068200000 |======================================================== RESET3 . 9111820000 |================================================== nekRS 23.0 Input: TurboPipe Periodic flops/rank > Higher Is Better RESET .. 7950340000 |========================================================== RESET2 . 7961240000 |========================================================== RESET3 . 6776830000 |================================================= Embree 4.1 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better RESET .. 21.58 |=============================== RESET2 . 21.43 |=============================== RESET3 . 43.40 |=============================================================== Embree 4.1 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better RESET .. 22.68 |=============================== RESET2 . 22.67 |=============================== RESET3 . 45.68 |=============================================================== Embree 4.1 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better RESET .. 24.81 |================================ RESET2 . 24.82 |================================ RESET3 . 48.15 |=============================================================== Embree 4.1 Binary: Pathtracer - Model: Asian Dragon Obj Frames Per Second > Higher Is Better RESET .. 22.25 |================================ RESET2 . 22.19 |================================ RESET3 . 43.51 |=============================================================== Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better RESET .. 28.29 |================================= RESET2 . 28.42 |================================= RESET3 . 54.50 |=============================================================== Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Frames Per Second > Higher Is Better RESET .. 23.83 |================================ RESET2 . 23.92 |================================ RESET3 . 46.46 |=============================================================== SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better RESET .. 4.502 |================================================== RESET2 . 4.528 |================================================== RESET3 . 5.719 |=============================================================== SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better RESET .. 59.64 |============================================== RESET2 . 59.06 |============================================== RESET3 . 81.06 |=============================================================== SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better RESET .. 165.65 |============================================ RESET2 . 164.10 |============================================ RESET3 . 231.17 |============================================================== SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better RESET .. 165.95 |============================================= RESET2 . 164.68 |============================================= RESET3 . 229.12 |============================================================== SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better RESET .. 14.21 |======================================================= RESET2 . 14.07 |====================================================== RESET3 . 16.40 |=============================================================== SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better RESET .. 128.58 |================================================== RESET2 . 128.47 |================================================== RESET3 . 160.67 |============================================================== SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better RESET .. 466.98 |================================================ RESET2 . 469.49 |================================================= RESET3 . 599.14 |============================================================== SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better RESET .. 600.20 |==================================================== RESET2 . 595.14 |=================================================== RESET3 . 721.70 |============================================================== VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better RESET .. 6.126 |===================================================== RESET2 . 6.147 |===================================================== RESET3 . 7.293 |=============================================================== VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better RESET .. 12.13 |======================================================= RESET2 . 12.23 |======================================================= RESET3 . 13.94 |=============================================================== VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better RESET .. 18.01 |======================================================= RESET2 . 18.09 |======================================================= RESET3 . 20.68 |=============================================================== VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better RESET .. 34.70 |========================================================= RESET2 . 34.69 |========================================================= RESET3 . 38.36 |=============================================================== SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better RESET .. 590.49 |============================================================== RESET3 . 558.19 |=========================================================== SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better RESET .. 161.60 |============================================================== RESET3 . 161.43 |============================================================== SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better RESET .. 528.29 |========================================================= RESET3 . 577.73 |============================================================== SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better RESET .. 162.29 |============================================== RESET3 . 216.63 |============================================================== SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better RESET .. 119.22 |================================================= RESET3 . 150.63 |============================================================== SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better RESET .. 67.60 |============================================ RESET3 . 97.76 |=============================================================== SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better RESET .. 10.73 |======================================================= RESET3 . 12.30 |=============================================================== SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better RESET .. 4.152 |=================================================== RESET3 . 5.089 |=============================================================== AOM AV1 3.7 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Frames Per Second > Higher Is Better AOM AV1 3.7 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Frames Per Second > Higher Is Better Intel Open Image Denoise 2.0 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better RESET .. 0.72 |================================== RESET2 . 0.72 |================================== RESET3 . 1.37 |================================================================ Intel Open Image Denoise 2.0 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better RESET .. 0.72 |================================= RESET2 . 0.72 |================================= RESET3 . 1.38 |================================================================ Intel Open Image Denoise 2.0 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only Images / Sec > Higher Is Better RESET .. 0.34 |================================= RESET2 . 0.34 |================================= RESET3 . 0.65 |================================================================ OSPRay 2.12 Benchmark: particle_volume/ao/real_time Items Per Second > Higher Is Better RESET .. 5.56770 |=============================== RESET2 . 5.57113 |=============================== RESET3 . 10.79350 |============================================================ OSPRay 2.12 Benchmark: particle_volume/scivis/real_time Items Per Second > Higher Is Better RESET .. 5.56275 |=============================== RESET2 . 5.55955 |=============================== RESET3 . 10.75420 |============================================================ OSPRay 2.12 Benchmark: particle_volume/pathtracer/real_time Items Per Second > Higher Is Better RESET .. 151.87 |================================================= RESET2 . 151.79 |================================================= RESET3 . 192.56 |============================================================== OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Items Per Second > Higher Is Better RESET .. 5.61038 |=============================== RESET2 . 5.60814 |=============================== RESET3 . 10.91530 |============================================================ OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Items Per Second > Higher Is Better RESET .. 5.46527 |=============================== RESET2 . 5.44882 |=============================== RESET3 . 10.59080 |============================================================ OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Items Per Second > Higher Is Better RESET .. 6.60071 |================================ RESET2 . 6.58666 |================================ RESET3 . 12.50750 |============================================================ Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 13.14 |================================ RESET2 . 13.03 |================================ RESET3 . 25.70 |=============================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 14.70 |===================================== RESET2 . 14.62 |==================================== RESET3 . 25.34 |=============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 505.28 |=============================== RESET2 . 505.41 |=============================== RESET3 . 999.06 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 202.75 |=========================================== RESET2 . 203.22 |=========================================== RESET3 . 291.47 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 257.57 |=============================== RESET2 . 257.40 |=============================== RESET3 . 508.34 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 141.09 |========================================== RESET2 . 143.56 |========================================== RESET3 . 210.21 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 70.92 |================================ RESET2 . 71.14 |================================ RESET3 . 136.89 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 48.75 |==================================== RESET2 . 48.82 |==================================== RESET3 . 86.41 |=============================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 163.18 |=============================== RESET2 . 162.95 |=============================== RESET3 . 327.97 |============================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 143.26 |======================================= RESET2 . 143.33 |======================================= RESET3 . 229.69 |============================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 1591.17 |============================= RESET2 . 1588.20 |============================= RESET3 . 3312.51 |============================================================= Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 916.58 |============================================= RESET2 . 922.36 |============================================= RESET3 . 1241.84 |============================================================= Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 71.84 |=============================== RESET2 . 72.16 |=============================== RESET3 . 143.77 |============================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 69.27 |=================================== RESET3 . 123.20 |============================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 16.16 |================================ RESET3 . 32.07 |=============================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 17.76 |===================================== RESET3 . 30.46 |=============================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 163.08 |=============================== RESET3 . 327.79 |============================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 143.69 |======================================= RESET3 . 229.15 |============================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 72.73 |=============================== RESET3 . 145.01 |============================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 69.63 |=================================== RESET3 . 124.37 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 109.08 |=============================== RESET3 . 215.92 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 101.91 |============================================ RESET3 . 143.87 |============================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 24.49 |================================= RESET3 . 47.15 |=============================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 25.92 |======================================= RESET3 . 41.67 |=============================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 240.38 |=============================== RESET3 . 486.73 |============================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 93.12 |========================================= RESET3 . 139.83 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 55.54 |================================ RESET3 . 109.28 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 54.81 |============================================= RESET3 . 75.92 |=============================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better RESET .. 13.10 |================================ RESET3 . 25.72 |=============================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better RESET .. 14.69 |==================================== RESET3 . 25.44 |=============================================================== Apache Cassandra 4.1.3 Test: Writes Op/s > Higher Is Better RESET .. 194642 |====================================== RESET3 . 318052 |============================================================== Apache Hadoop 3.3.6 Operation: Create - Threads: 20 - Files: 100000 Ops per sec > Higher Is Better RESET .. 59630 |=========================================================== RESET3 . 63492 |=============================================================== Apache Hadoop 3.3.6 Operation: Create - Threads: 20 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 72317 |========================================================== RESET3 . 78223 |=============================================================== Apache Hadoop 3.3.6 Operation: Create - Threads: 50 - Files: 100000 Ops per sec > Higher Is Better RESET .. 60314 |============================================================= RESET3 . 62189 |=============================================================== Apache Hadoop 3.3.6 Operation: Create - Threads: 50 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 71403 |============================================================ RESET3 . 74722 |=============================================================== Apache Hadoop 3.3.6 Operation: Create - Threads: 100 - Files: 100000 Ops per sec > Higher Is Better RESET .. 59242 |============================================================= RESET3 . 60790 |=============================================================== Apache Hadoop 3.3.6 Operation: Create - Threads: 100 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 69638 |============================================================ RESET3 . 73692 |=============================================================== Apache Hadoop 3.3.6 Operation: Create - Threads: 500 - Files: 100000 Ops per sec > Higher Is Better RESET .. 52383 |=========================================================== RESET3 . 55525 |=============================================================== Apache Hadoop 3.3.6 Operation: Create - Threads: 500 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 66037 |============================================================== RESET3 . 67087 |=============================================================== Apache Hadoop 3.3.6 Operation: Open - Threads: 20 - Files: 100000 Ops per sec > Higher Is Better RESET .. 636943 |============================================================== RESET3 . 595238 |========================================================== Apache Hadoop 3.3.6 Operation: Open - Threads: 20 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 1191895 |============================================================= RESET3 . 981354 |================================================== Apache Hadoop 3.3.6 Operation: Open - Threads: 50 - Files: 100000 Ops per sec > Higher Is Better RESET .. 537634 |=================================================== RESET3 . 653595 |============================================================== Apache Hadoop 3.3.6 Operation: Open - Threads: 50 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 264831 |============= RESET3 . 1256281 |============================================================= Apache Hadoop 3.3.6 Operation: Open - Threads: 100 - Files: 100000 Ops per sec > Higher Is Better RESET .. 305810 |===================================== RESET3 . 518135 |============================================================== Apache Hadoop 3.3.6 Operation: Open - Threads: 100 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 1256281 |============================================================= RESET3 . 805802 |======================================= Apache Hadoop 3.3.6 Operation: Open - Threads: 500 - Files: 100000 Ops per sec > Higher Is Better RESET .. 205761 |=========================================================== RESET3 . 217865 |============================================================== Apache Hadoop 3.3.6 Operation: Open - Threads: 500 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 1164144 |======================================================== RESET3 . 1257862 |============================================================= Apache Hadoop 3.3.6 Operation: Delete - Threads: 20 - Files: 100000 Ops per sec > Higher Is Better RESET .. 107875 |============================================================ RESET3 . 112233 |============================================================== Apache Hadoop 3.3.6 Operation: Delete - Threads: 20 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 116333 |========================================================== RESET3 . 124054 |============================================================== Apache Hadoop 3.3.6 Operation: Delete - Threads: 50 - Files: 100000 Ops per sec > Higher Is Better RESET .. 108696 |============================================================== RESET3 . 103950 |=========================================================== Apache Hadoop 3.3.6 Operation: Delete - Threads: 50 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 110963 |============================================================ RESET3 . 115022 |============================================================== Apache Hadoop 3.3.6 Operation: Delete - Threads: 100 - Files: 100000 Ops per sec > Higher Is Better RESET .. 99701 |========================================================== RESET3 . 107181 |============================================================== Apache Hadoop 3.3.6 Operation: Delete - Threads: 100 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 112587 |============================================================= RESET3 . 114732 |============================================================== Apache Hadoop 3.3.6 Operation: Delete - Threads: 500 - Files: 100000 Ops per sec > Higher Is Better RESET .. 93721 |======================================================== RESET3 . 103306 |============================================================== Apache Hadoop 3.3.6 Operation: Delete - Threads: 500 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 109673 |============================================================== RESET3 . 104362 |=========================================================== Apache Hadoop 3.3.6 Operation: File Status - Threads: 20 - Files: 100000 Ops per sec > Higher Is Better RESET .. 869565 |============================================================== RESET3 . 869565 |============================================================== Apache Hadoop 3.3.6 Operation: File Status - Threads: 20 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 1879699 |============================================================= RESET3 . 428816 |============== Apache Hadoop 3.3.6 Operation: File Status - Threads: 50 - Files: 100000 Ops per sec > Higher Is Better RESET .. 476190 |====================================== RESET3 . 769231 |============================================================== Apache Hadoop 3.3.6 Operation: File Status - Threads: 50 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 593120 |=================== RESET3 . 1890359 |============================================================= Apache Hadoop 3.3.6 Operation: File Status - Threads: 100 - Files: 100000 Ops per sec > Higher Is Better RESET .. 531915 |============================================= RESET3 . 740741 |============================================================== Apache Hadoop 3.3.6 Operation: File Status - Threads: 100 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 1828154 |================================================== RESET3 . 2252252 |============================================================= Apache Hadoop 3.3.6 Operation: File Status - Threads: 500 - Files: 100000 Ops per sec > Higher Is Better RESET .. 215517 |====================== RESET3 . 598802 |============================================================== Apache Hadoop 3.3.6 Operation: File Status - Threads: 500 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 1779359 |============================================================= RESET3 . 816327 |============================ Apache Hadoop 3.3.6 Operation: Rename - Threads: 20 - Files: 100000 Ops per sec > Higher Is Better RESET .. 87032 |============================================================= RESET3 . 90253 |=============================================================== Apache Hadoop 3.3.6 Operation: Rename - Threads: 20 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 89095 |=========================================================== RESET3 . 95293 |=============================================================== Apache Hadoop 3.3.6 Operation: Rename - Threads: 50 - Files: 100000 Ops per sec > Higher Is Better RESET .. 83333 |============================================================ RESET3 . 88183 |=============================================================== Apache Hadoop 3.3.6 Operation: Rename - Threads: 50 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 87912 |============================================================== RESET3 . 89985 |=============================================================== Apache Hadoop 3.3.6 Operation: Rename - Threads: 100 - Files: 100000 Ops per sec > Higher Is Better RESET .. 85616 |=============================================================== RESET3 . 83752 |============================================================== Apache Hadoop 3.3.6 Operation: Rename - Threads: 100 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 85800 |=============================================================== RESET3 . 84474 |============================================================== Apache Hadoop 3.3.6 Operation: Rename - Threads: 500 - Files: 100000 Ops per sec > Higher Is Better RESET .. 78555 |============================================================ RESET3 . 82305 |=============================================================== Apache Hadoop 3.3.6 Operation: Rename - Threads: 500 - Files: 1000000 Ops per sec > Higher Is Better RESET .. 76722 |=========================================================== RESET3 . 82529 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better RESET .. 8302009.42 |============================ RESET2 . 8584414.13 |============================= RESET3 . 16927170.48 |========================================================= Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better RESET .. 10162330.86 |============================== RESET2 . 9527420.80 |============================ RESET3 . 19505101.23 |========================================================= Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better RESET .. 12469755.60 |=============================== RESET2 . 11249348.91 |============================ RESET3 . 22835296.84 |========================================================= Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better RESET .. 8637294.18 |============================= RESET2 . 8951592.94 |============================== RESET3 . 17116522.17 |========================================================= Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better RESET .. 9932666.12 |=========================== RESET2 . 9367141.20 |========================= RESET3 . 21025616.30 |========================================================= Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better RESET .. 11746361.87 |============================ RESET2 . 12138788.95 |============================= RESET3 . 23607335.01 |========================================================= Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better RESET .. 12065388.34 |========================================================= RESET2 . 10983543.66 |==================================================== Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better RESET .. 11419293.83 |================================================ RESET2 . 13659195.83 |========================================================= TiDB Community Server 7.3 Test: oltp_read_write - Threads: 1 Queries Per Second > Higher Is Better RESET .. 3204 |================================================================ TiDB Community Server 7.3 Test: oltp_read_write - Threads: 16 Queries Per Second > Higher Is Better RESET .. 36124 |================================================ RESET3 . 47703 |=============================================================== TiDB Community Server 7.3 Test: oltp_read_write - Threads: 32 Queries Per Second > Higher Is Better RESET .. 46972 |======================================== RESET3 . 74741 |=============================================================== TiDB Community Server 7.3 Test: oltp_read_write - Threads: 64 Queries Per Second > Higher Is Better RESET3 . 94643 |=============================================================== TiDB Community Server 7.3 Test: oltp_read_write - Threads: 128 Queries Per Second > Higher Is Better RESET .. 59739 |=============================================================== TiDB Community Server 7.3 Test: oltp_read_write - Threads: 256 Queries Per Second > Higher Is Better RESET .. 62965 |=================================== RESET3 . 111354 |============================================================== TiDB Community Server 7.3 Test: oltp_point_select - Threads: 1 Queries Per Second > Higher Is Better RESET .. 5956 |=============================================================== RESET3 . 6080 |================================================================ TiDB Community Server 7.3 Test: oltp_point_select - Threads: 16 Queries Per Second > Higher Is Better RESET3 . 87667 |=============================================================== TiDB Community Server 7.3 Test: oltp_point_select - Threads: 32 Queries Per Second > Higher Is Better RESET .. 97200 |=============================================================== TiDB Community Server 7.3 Test: oltp_point_select - Threads: 64 Queries Per Second > Higher Is Better RESET .. 118850 |============================================================== TiDB Community Server 7.3 Test: oltp_point_select - Threads: 128 Queries Per Second > Higher Is Better RESET .. 131165 |========================================= RESET3 . 197386 |============================================================== TiDB Community Server 7.3 Test: oltp_point_select - Threads: 256 Queries Per Second > Higher Is Better RESET .. 143244 |========================================== RESET3 . 210553 |============================================================== TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 1 Queries Per Second > Higher Is Better RESET .. 1687 |=========================================================== RESET3 . 1843 |================================================================ TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 16 Queries Per Second > Higher Is Better RESET .. 18663 |================================================= RESET3 . 23758 |=============================================================== TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 32 Queries Per Second > Higher Is Better RESET .. 26459 |============================================== RESET3 . 36066 |=============================================================== TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 64 Queries Per Second > Higher Is Better RESET .. 34234 |========================================== RESET3 . 51897 |=============================================================== TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 128 Queries Per Second > Higher Is Better RESET .. 41635 |======================================== RESET3 . 65674 |=============================================================== Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better RESET .. 35186000 |========================================================= RESET2 . 35179000 |========================================================= RESET3 . 37083000 |============================================================ Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better RESET .. 52897000 |========================================================= RESET2 . 48803000 |===================================================== RESET3 . 55677000 |============================================================ Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better RESET .. 68854000 |========================================================= RESET2 . 68905000 |========================================================= RESET3 . 72570000 |============================================================ Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better RESET .. 105200000 |========================================================= RESET2 . 104020000 |========================================================= RESET3 . 108010000 |=========================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better RESET .. 138520000 |======================================================== RESET2 . 136520000 |======================================================= RESET3 . 145900000 |=========================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better RESET .. 190540000 |========================================================= RESET2 . 188640000 |======================================================== RESET3 . 197890000 |=========================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better RESET .. 277560000 |======================================================== RESET2 . 277780000 |======================================================== RESET3 . 292720000 |=========================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better RESET .. 337660000 |==================================================== RESET2 . 343950000 |===================================================== RESET3 . 380280000 |=========================================================== Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better RESET .. 12685000 |========================================================= RESET2 . 12264000 |======================================================= RESET3 . 13359000 |============================================================ Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better RESET .. 545570000 |======================================================= RESET2 . 544800000 |======================================================= RESET3 . 582930000 |=========================================================== Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better RESET .. 695920000 |========================================================= RESET2 . 686540000 |========================================================= RESET3 . 716650000 |=========================================================== Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better RESET .. 25206000 |========================================================== RESET2 . 25050000 |========================================================== RESET3 . 26065000 |============================================================ Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better RESET .. 1047500000 |==================================================== RESET2 . 1046500000 |==================================================== RESET3 . 1169700000 |========================================================== Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better RESET .. 1031700000 |=========================================== RESET2 . 1013800000 |========================================== RESET3 . 1397500000 |========================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better RESET .. 48886000 |======================================================== RESET2 . 49614000 |========================================================= RESET3 . 52587000 |============================================================ Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better RESET .. 1056400000 |============================== RESET2 . 1056700000 |============================== RESET3 . 2053800000 |========================================================== Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better RESET .. 1100900000 |================================= RESET2 . 1098600000 |================================= RESET3 . 1911400000 |========================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better RESET .. 97011000 |====================================================== RESET2 . 99404000 |======================================================== RESET3 . 105480000 |=========================================================== Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better RESET .. 196300000 |======================================================== RESET2 . 196070000 |======================================================= RESET3 . 208610000 |=========================================================== Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better RESET .. 273720000 |========================================= RESET2 . 274570000 |========================================= RESET3 . 393800000 |=========================================================== Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better RESET .. 282490000 |================================= RESET2 . 282060000 |================================= RESET3 . 510160000 |=========================================================== Kripke 1.2.6 Throughput FoM > Higher Is Better RESET .. 237641100 |======================================== RESET3 . 351062800 |=========================================================== BRL-CAD 7.36 VGR Performance Metric VGR Performance Metric > Higher Is Better RESET .. 295626 |================================ RESET3 . 569090 |============================================================== NCNN 20230517 Target: CPU - Model: mobilenet ms < Lower Is Better RESET .. 16.73 |=============================================================== RESET3 . 16.29 |============================================================= NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better RESET .. 7.36 |============================================================= RESET3 . 7.72 |================================================================ NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better RESET .. 7.55 |============================================================ RESET3 . 8.08 |================================================================ NCNN 20230517 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better RESET .. 8.67 |=========================================================== RESET3 . 9.38 |================================================================ NCNN 20230517 Target: CPU - Model: mnasnet ms < Lower Is Better RESET .. 7.47 |================================================================ RESET3 . 7.11 |============================================================= NCNN 20230517 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better RESET .. 9.35 |======================================================== RESET3 . 10.56 |=============================================================== NCNN 20230517 Target: CPU - Model: blazeface ms < Lower Is Better RESET .. 3.35 |======================================================== RESET3 . 3.86 |================================================================ NCNN 20230517 Target: CPU - Model: googlenet ms < Lower Is Better RESET .. 17.98 |=========================================================== RESET3 . 19.29 |=============================================================== NCNN 20230517 Target: CPU - Model: vgg16 ms < Lower Is Better RESET .. 22.59 |=============================================================== RESET3 . 20.62 |========================================================== NCNN 20230517 Target: CPU - Model: resnet18 ms < Lower Is Better RESET .. 9.13 |================================================================ RESET3 . 8.72 |============================================================= NCNN 20230517 Target: CPU - Model: alexnet ms < Lower Is Better RESET .. 6.01 |================================================================ RESET3 . 5.23 |======================================================== NCNN 20230517 Target: CPU - Model: resnet50 ms < Lower Is Better RESET .. 16.83 |============================================================== RESET3 . 17.19 |=============================================================== NCNN 20230517 Target: CPU - Model: yolov4-tiny ms < Lower Is Better RESET .. 25.42 |============================================================== RESET3 . 25.96 |=============================================================== NCNN 20230517 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better RESET .. 15.52 |============================================================ RESET3 . 16.20 |=============================================================== NCNN 20230517 Target: CPU - Model: regnety_400m ms < Lower Is Better RESET .. 17.13 |================================================ RESET3 . 22.32 |=============================================================== NCNN 20230517 Target: CPU - Model: vision_transformer ms < Lower Is Better RESET .. 55.73 |=============================================================== RESET3 . 44.06 |================================================== NCNN 20230517 Target: CPU - Model: FastestDet ms < Lower Is Better RESET .. 11.30 |============================================================ RESET3 . 11.81 |=============================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 607.03 |============================================================= RESET2 . 607.47 |============================================================= RESET3 . 613.03 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 68.03 |=============================================================== RESET2 . 68.38 |=============================================================== RESET3 . 39.46 |==================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 15.81 |============================================================== RESET2 . 15.80 |============================================================== RESET3 . 16.00 |=============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 4.9273 |============================================================== RESET2 . 4.9157 |============================================================== RESET3 . 3.4287 |=========================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 31.02 |============================================================== RESET2 . 31.05 |============================================================== RESET3 . 31.44 |=============================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 7.0815 |============================================================== RESET2 . 6.9594 |============================================================= RESET3 . 4.7514 |========================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 112.60 |============================================================ RESET2 . 112.25 |============================================================ RESET3 . 116.56 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 20.51 |=============================================================== RESET2 . 20.47 |=============================================================== RESET3 . 11.57 |==================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 49.00 |=============================================================== RESET2 . 49.06 |=============================================================== RESET3 . 48.74 |=============================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 6.9730 |============================================================== RESET2 . 6.9693 |============================================================== RESET3 . 4.3494 |======================================= Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 5.0159 |============================================================== RESET2 . 5.0233 |============================================================== RESET3 . 4.8202 |=========================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 1.0875 |============================================================== RESET2 . 1.0807 |============================================================== RESET3 . 0.8023 |============================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 111.10 |============================================================== RESET2 . 110.74 |============================================================== RESET3 . 111.08 |============================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 14.4253 |============================================================= RESET3 . 8.1111 |================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 493.61 |============================================================== RESET3 . 494.30 |============================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 56.29 |=============================================================== RESET3 . 32.83 |===================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 49.00 |=============================================================== RESET3 . 48.77 |=============================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 6.9520 |============================================================== RESET3 . 4.3595 |======================================= Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 109.89 |============================================================== RESET3 . 110.13 |============================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 14.3550 |============================================================= RESET3 . 8.0375 |================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 73.20 |============================================================== RESET3 . 73.98 |=============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 9.8064 |============================================================== RESET3 . 6.9453 |============================================ Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 325.02 |============================================================ RESET3 . 336.76 |============================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 38.57 |=============================================================== RESET3 . 23.98 |======================================= Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 33.25 |=============================================================== RESET3 . 32.83 |============================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 10.7278 |============================================================= RESET3 . 7.1439 |========================================= Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 143.84 |============================================================= RESET3 . 146.00 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 18.24 |=============================================================== RESET3 . 13.17 |============================================= Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better RESET .. 608.16 |============================================================= RESET3 . 614.02 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better RESET .. 68.08 |=============================================================== RESET3 . 39.31 |==================================== Remhos 1.0 Test: Sample Remap Example Seconds < Lower Is Better RESET .. 31.02 |=============================================================== RESET2 . 30.94 |=============================================================== RESET3 . 20.69 |========================================== SPECFEM3D 4.0 Model: Mount St. Helens Seconds < Lower Is Better RESET .. 27.11 |=============================================================== RESET2 . 26.34 |============================================================= RESET3 . 14.86 |=================================== SPECFEM3D 4.0 Model: Layered Halfspace Seconds < Lower Is Better RESET .. 69.74 |=============================================================== RESET2 . 69.18 |============================================================== RESET3 . 39.28 |=================================== SPECFEM3D 4.0 Model: Tomographic Model Seconds < Lower Is Better RESET .. 27.09 |============================================================== RESET2 . 27.37 |=============================================================== RESET3 . 15.28 |=================================== SPECFEM3D 4.0 Model: Homogeneous Halfspace Seconds < Lower Is Better RESET .. 35.68 |=============================================================== RESET2 . 35.32 |============================================================== RESET3 . 20.01 |=================================== SPECFEM3D 4.0 Model: Water-layered Halfspace Seconds < Lower Is Better RESET .. 64.32 |=============================================================== RESET2 . 63.20 |============================================================== RESET3 . 37.55 |===================================== Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better RESET .. 55.16 |=============================================================== RESET2 . 55.21 |=============================================================== RESET3 . 33.90 |======================================= Timed Linux Kernel Compilation 6.1 Build: allmodconfig Seconds < Lower Is Better Blender 3.6 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better RESET .. 71.89 |=============================================================== RESET3 . 38.91 |================================== Blender 3.6 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better RESET .. 183.11 |============================================================== RESET3 . 99.35 |================================== Blender 3.6 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better RESET .. 90.46 |=============================================================== RESET3 . 48.68 |================================== Blender 3.6 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better RESET .. 670.71 |============================================================== RESET3 . 351.79 |================================= Blender 3.6 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better RESET .. 223.60 |============================================================== RESET3 . 119.19 |=================================