extra tests 2 x AMD EPYC 9754 128-Core testing with a Supermicro H13DSH (1.5 BIOS) and astdrmfb on AlmaLinux 9.2 via the Phoronix Test Suite. d: Processor: 2 x AMD EPYC 9124 16-Core @ 3.00GHz (32 Cores / 64 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 24 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, 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 e: Processor: 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 23 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, 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 f: Processor: 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 23 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, 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 g: Processor: 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 23 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, 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 h: Processor: 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 23 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, 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 Laghos 3.1 Test: Triple Point Problem Major Kernels Total Rate > Higher Is Better d . 195.40 |=================================================================== Laghos 3.1 Test: Sedov Blast Wave, ube_922_hex.mesh Major Kernels Total Rate > Higher Is Better d . 263.85 |=================================================================== Remhos 1.0 Test: Sample Remap Example Seconds < Lower Is Better d . 20.90 |==================================================================== SPECFEM3D 4.0 Model: Mount St. Helens Seconds < Lower Is Better d . 14.51 |==================================================================== SPECFEM3D 4.0 Model: Layered Halfspace Seconds < Lower Is Better d . 38.49 |==================================================================== SPECFEM3D 4.0 Model: Tomographic Model Seconds < Lower Is Better d . 14.88 |==================================================================== SPECFEM3D 4.0 Model: Homogeneous Halfspace Seconds < Lower Is Better d . 18.85 |==================================================================== SPECFEM3D 4.0 Model: Water-layered Halfspace Seconds < Lower Is Better d . 34.82 |==================================================================== nekRS 23.0 Input: Kershaw flops/rank > Higher Is Better d . 11520900000 |============================================================== nekRS 23.0 Input: TurboPipe Periodic flops/rank > Higher Is Better d . 7470490000 |=============================================================== Embree 4.1 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better d . 37.68 |============= e . 189.44 |=================================================================== f . 185.36 |================================================================== g . 183.40 |================================================================= h . 187.42 |================================================================== Embree 4.1 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better d . 39.38 |============== e . 189.19 |================================================================= f . 189.32 |================================================================= g . 193.60 |=================================================================== h . 194.27 |=================================================================== Embree 4.1 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better d . 42.76 |============= e . 205.71 |=============================================================== f . 206.17 |=============================================================== g . 217.59 |=================================================================== h . 207.25 |================================================================ Embree 4.1 Binary: Pathtracer - Model: Asian Dragon Obj Frames Per Second > Higher Is Better d . 37.99 |============= e . 184.11 |================================================================ f . 180.14 |=============================================================== g . 193.05 |=================================================================== h . 172.21 |============================================================ Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better d . 48.47 |============== e . 227.03 |================================================================ f . 224.90 |=============================================================== g . 239.42 |=================================================================== h . 225.83 |=============================================================== Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Frames Per Second > Higher Is Better d . 40.57 |============== e . 187.01 |================================================================= f . 184.24 |================================================================ g . 193.43 |=================================================================== h . 184.45 |================================================================ SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better d . 5.053 |==================================================================== e . 4.580 |============================================================== f . 4.646 |=============================================================== g . 4.615 |============================================================== h . 4.593 |============================================================== SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better d . 72.35 |================================================================= e . 73.62 |=================================================================== f . 71.71 |================================================================= g . 75.15 |==================================================================== h . 73.25 |================================================================== SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better d . 199.52 |=================================================================== e . 169.89 |========================================================= f . 183.47 |============================================================== g . 189.16 |================================================================ h . 194.86 |================================================================= SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better d . 195.83 |=================================================================== e . 188.74 |================================================================= f . 161.82 |======================================================= g . 191.67 |================================================================== h . 177.36 |============================================================= SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better d . 14.97 |==================================================================== e . 13.19 |============================================================ f . 13.45 |============================================================= g . 13.58 |============================================================== h . 12.91 |=========================================================== SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better d . 136.07 |=================================================================== e . 133.87 |================================================================== f . 134.06 |================================================================== g . 134.88 |================================================================== h . 134.38 |================================================================== SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better d . 419.85 |======================================================== e . 490.98 |================================================================= f . 503.08 |=================================================================== g . 490.15 |================================================================= h . 485.59 |================================================================= SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better d . 545.20 |============================================================= e . 594.84 |================================================================== f . 588.81 |================================================================== g . 600.23 |=================================================================== h . 581.07 |================================================================= VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better d . 6.768 |==================================================================== VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better d . 12.68 |==================================================================== VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better d . 19.17 |==================================================================== VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better d . 33.57 |==================================================================== Intel Open Image Denoise 2.0 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better d . 1.36 |=========================== e . 3.24 |=============================================================== f . 3.25 |================================================================ g . 3.40 |================================================================== h . 3.53 |===================================================================== Intel Open Image Denoise 2.0 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better d . 1.37 |=========================== e . 3.18 |=============================================================== f . 3.07 |============================================================= g . 3.28 |================================================================= h . 3.46 |===================================================================== Intel Open Image Denoise 2.0 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only Images / Sec > Higher Is Better d . 0.65 |============================= e . 1.50 |=================================================================== f . 1.47 |================================================================== g . 1.50 |=================================================================== h . 1.54 |===================================================================== OSPRay 2.12 Benchmark: particle_volume/ao/real_time Items Per Second > Higher Is Better d . 10.86 |================ e . 46.66 |==================================================================== f . 46.56 |==================================================================== g . 46.66 |==================================================================== h . 46.76 |==================================================================== OSPRay 2.12 Benchmark: particle_volume/scivis/real_time Items Per Second > Higher Is Better d . 10.85 |================ e . 46.60 |==================================================================== f . 46.59 |==================================================================== g . 46.61 |==================================================================== h . 46.55 |==================================================================== OSPRay 2.12 Benchmark: particle_volume/pathtracer/real_time Items Per Second > Higher Is Better d . 176.61 |=================================================================== e . 161.20 |============================================================= f . 160.91 |============================================================= g . 161.17 |============================================================= h . 160.87 |============================================================= OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Items Per Second > Higher Is Better d . 10.08 |============= e . 50.39 |=================================================================== f . 50.09 |=================================================================== g . 50.40 |=================================================================== h . 50.96 |==================================================================== OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Items Per Second > Higher Is Better d . 9.81318 |============= e . 49.08320 |================================================================ f . 48.90060 |=============================================================== g . 49.51230 |================================================================ h . 50.08790 |================================================================= OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Items Per Second > Higher Is Better d . 11.90 |============================= e . 28.17 |==================================================================== f . 28.27 |==================================================================== g . 28.35 |==================================================================== h . 28.25 |==================================================================== Timed Linux Kernel Compilation 6.1 Build: defconfig Seconds < Lower Is Better d . 35.28 |==================================================================== e . 22.77 |============================================ f . 23.47 |============================================= g . 23.06 |============================================ h . 23.05 |============================================ Timed Linux Kernel Compilation 6.1 Build: allmodconfig Seconds < Lower Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better d . 35195000 |================================================================= e . 29190000 |====================================================== f . 29214000 |====================================================== g . 29219000 |====================================================== h . 29200000 |====================================================== Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better d . 52765000 |================================================================= e . 44113000 |====================================================== f . 44144000 |====================================================== g . 44187000 |====================================================== h . 44183000 |====================================================== Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better d . 68834000 |================================================================= e . 57284000 |====================================================== f . 57194000 |====================================================== g . 55708000 |===================================================== h . 55923000 |===================================================== Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better d . 105630000 |================================================================ e . 88038000 |===================================================== f . 88120000 |===================================================== g . 88109000 |===================================================== h . 88042000 |===================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better d . 136500000 |================================================================ e . 113830000 |===================================================== f . 114360000 |====================================================== g . 114550000 |====================================================== h . 114390000 |====================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better d . 174280000 |================================================================ e . 150930000 |======================================================= f . 146510000 |====================================================== g . 151010000 |======================================================= h . 155360000 |========================================================= Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better d . 271730000 |================================================================ e . 228660000 |====================================================== f . 223690000 |===================================================== g . 228520000 |====================================================== h . 228090000 |====================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better d . 331200000 |================================================================ e . 276890000 |====================================================== f . 278140000 |====================================================== g . 279840000 |====================================================== h . 277250000 |====================================================== Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better d . 12652000 |================================================================= e . 10553000 |====================================================== f . 10563000 |====================================================== g . 10576000 |====================================================== h . 10567000 |====================================================== Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better d . 549390000 |================================================================ e . 456980000 |===================================================== f . 458140000 |===================================================== g . 457820000 |===================================================== h . 457420000 |===================================================== Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better d . 650410000 |================================================================ e . 534940000 |===================================================== f . 553290000 |====================================================== g . 542300000 |===================================================== h . 546690000 |====================================================== Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better d . 24900000 |================================================================= e . 20808000 |====================================================== f . 20873000 |====================================================== g . 20660000 |====================================================== h . 20837000 |====================================================== Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better d . 1073800000 |=============================================================== e . 916020000 |====================================================== f . 913640000 |====================================================== g . 914570000 |====================================================== h . 911870000 |===================================================== Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better d . 1234500000 |=============================================================== e . 1071100000 |======================================================= f . 1055200000 |====================================================== g . 1057300000 |====================================================== h . 1065000000 |====================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better d . 49884000 |================================================================= e . 41506000 |====================================================== f . 41015000 |===================================================== g . 41641000 |====================================================== h . 41052000 |===================================================== Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better d . 2045600000 |=============================================================== e . 1827100000 |======================================================== f . 1827900000 |======================================================== g . 1827600000 |======================================================== h . 1822100000 |======================================================== Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better d . 1778600000 |====================================================== e . 2066300000 |=============================================================== f . 2081700000 |=============================================================== g . 2076600000 |=============================================================== h . 2072000000 |=============================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better d . 96449000 |================================================================= e . 81715000 |======================================================= f . 82343000 |======================================================= g . 83090000 |======================================================== h . 82749000 |======================================================== Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better d . 195510000 |================================================================ e . 164350000 |====================================================== f . 166500000 |======================================================= g . 165180000 |====================================================== h . 165390000 |====================================================== Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better d . 387460000 |================================================================ e . 330490000 |======================================================= f . 330090000 |======================================================= g . 331240000 |======================================================= h . 329210000 |====================================================== Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better d . 504660000 |================================================= e . 659610000 |================================================================ f . 659970000 |================================================================ g . 659140000 |================================================================ h . 652820000 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better d . 11686474.26 |============================================================== Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better d . 15179164.86 |============================================================== Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better d . 15253621.53 |============================================================== Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:10 Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better d . 11860591.65 |============================================================== Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better d . 14250093.71 |============================================================== Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better d . 17583489.38 |============================================================== Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:100 Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 19.81 |========== e . 128.44 |================================================================== f . 129.13 |================================================================== g . 129.38 |================================================================== h . 131.10 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 795.85 |======================================================= e . 972.75 |=================================================================== f . 969.17 |=================================================================== g . 969.88 |=================================================================== h . 954.94 |================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 13.92 |============================= e . 28.72 |============================================================ f . 28.95 |============================================================ g . 31.79 |================================================================== h . 32.54 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 71.84 |==================================================================== e . 34.82 |================================= f . 34.54 |================================= g . 31.45 |============================== h . 30.72 |============================= Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 757.48 |========== e . 5158.66 |================================================================== f . 5181.36 |================================================================== g . 5150.43 |================================================================== h . 5175.49 |================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 21.09 |========================================================== e . 24.76 |==================================================================== f . 24.65 |==================================================================== g . 24.79 |==================================================================== h . 24.68 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 202.50 |=================================================================== e . 135.64 |============================================= f . 134.57 |============================================= g . 135.40 |============================================= h . 134.02 |============================================ Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 4.9317 |============================================ e . 7.3697 |================================================================== f . 7.4283 |=================================================================== g . 7.3831 |================================================================== h . 7.4589 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 355.89 |========== e . 2319.88 |=============================================================== f . 2295.61 |============================================================== g . 2405.88 |================================================================= h . 2429.74 |================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 44.91 |======================================================= e . 55.06 |=================================================================== f . 55.65 |==================================================================== g . 53.12 |================================================================= h . 52.58 |================================================================ Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 139.79 |=================================================================== e . 111.08 |===================================================== f . 112.42 |====================================================== g . 114.38 |======================================================= h . 116.19 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 7.1456 |===================================================== e . 8.9987 |=================================================================== f . 8.8905 |================================================================== g . 8.7387 |================================================================= h . 8.6016 |================================================================ Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 106.15 |============= e . 447.14 |======================================================== f . 446.50 |======================================================== g . 497.90 |=============================================================== h . 532.46 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 150.28 |=================================== e . 285.13 |=================================================================== f . 285.52 |=================================================================== g . 256.16 |============================================================ h . 239.19 |======================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 48.25 |================================================ e . 60.51 |============================================================ f . 61.86 |============================================================= g . 66.52 |================================================================== h . 68.61 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 20.71 |==================================================================== e . 16.52 |====================================================== f . 16.16 |===================================================== g . 15.02 |================================================= h . 14.56 |================================================ Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 257.42 |========== e . 1773.17 |================================================================== f . 1774.44 |================================================================== g . 1780.24 |================================================================== h . 1784.36 |================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 62.10 |=========================================================== e . 72.05 |==================================================================== f . 71.98 |==================================================================== g . 71.76 |==================================================================== h . 71.58 |==================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 140.46 |=================================================================== e . 137.53 |================================================================== f . 138.36 |================================================================== g . 138.76 |================================================================== h . 139.21 |================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 7.1102 |================================================================== e . 7.2672 |=================================================================== f . 7.2233 |=================================================================== g . 7.2026 |================================================================== h . 7.1792 |================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 2661.23 |=========== e . 14145.43 |============================================================ f . 15229.27 |================================================================= g . 14854.86 |=============================================================== h . 13153.50 |======================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 5.9947 |========================================= e . 9.0162 |============================================================== f . 8.3725 |========================================================== g . 8.5843 |=========================================================== h . 9.6974 |=================================================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 890.94 |=================================================================== e . 600.57 |============================================= f . 597.37 |============================================= g . 605.47 |============================================== h . 608.16 |============================================== Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 1.1189 |============================================= e . 1.6625 |=================================================================== f . 1.6716 |=================================================================== g . 1.6492 |================================================================== h . 1.6419 |================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 113.66 |========== e . 755.22 |================================================================== f . 755.35 |================================================================== g . 761.87 |=================================================================== h . 764.74 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 140.58 |======================================================== e . 168.90 |=================================================================== f . 169.05 |=================================================================== g . 167.42 |================================================================== h . 166.76 |================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 67.77 |========================= e . 180.50 |================================================================== f . 179.78 |================================================================== g . 182.64 |=================================================================== h . 183.24 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 14.7454 |================================================================== e . 5.5308 |========================= f . 5.5536 |========================= g . 5.4661 |======================== h . 5.4481 |======================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 24.72 |========== e . 163.82 |================================================================= f . 168.09 |=================================================================== g . 166.73 |================================================================== h . 168.75 |=================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 641.61 |======================================================== e . 772.28 |=================================================================== f . 752.58 |================================================================= g . 756.62 |================================================================== h . 751.72 |================================================================= Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 17.00 |========================================= e . 24.33 |=========================================================== f . 22.65 |======================================================= g . 23.78 |========================================================== h . 27.88 |==================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 58.83 |==================================================================== e . 41.09 |=============================================== f . 44.15 |=================================================== g . 42.04 |================================================= h . 35.85 |========================================= Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 258.56 |========== e . 1776.22 |================================================================== f . 1775.04 |================================================================== g . 1778.36 |================================================================== h . 1786.18 |================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 61.81 |========================================================== e . 71.90 |==================================================================== f . 71.98 |==================================================================== g . 71.82 |==================================================================== h . 71.54 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 140.20 |=================================================================== f . 137.94 |================================================================== e . 137.36 |================================================================== g . 138.59 |================================================================== h . 140.44 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 7.1228 |================================================================== f . 7.2453 |=================================================================== e . 7.2759 |=================================================================== g . 7.2111 |================================================================== h . 7.1163 |================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 114.28 |========== f . 765.85 |================================================================== e . 767.63 |================================================================== g . 770.51 |=================================================================== h . 774.41 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 139.61 |======================================================== f . 166.52 |=================================================================== e . 166.16 |=================================================================== g . 165.51 |=================================================================== h . 164.66 |================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 68.16 |========================= f . 182.14 |================================================================== e . 182.80 |=================================================================== g . 183.37 |=================================================================== h . 184.09 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 14.6632 |================================================================== f . 5.4849 |========================= e . 5.4651 |========================= g . 5.4478 |========================= h . 5.4268 |======================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 168.72 |========== f . 1127.39 |================================================================== e . 1125.03 |================================================================== g . 1128.88 |================================================================== h . 1127.79 |================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 94.62 |======================================================== f . 113.24 |=================================================================== e . 113.46 |=================================================================== g . 113.02 |=================================================================== h . 113.20 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 99.12 |=================================================== f . 111.26 |========================================================= e . 122.25 |=============================================================== g . 124.41 |================================================================ h . 130.19 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 10.0813 |================================================================== f . 8.9799 |=========================================================== e . 8.1721 |====================================================== g . 8.0302 |===================================================== h . 7.6734 |================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 36.38 |=========== f . 215.66 |================================================================= e . 216.86 |================================================================= g . 220.91 |================================================================== h . 222.86 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 436.97 |================================================== f . 585.34 |=================================================================== e . 584.60 |=================================================================== g . 573.36 |================================================================== h . 567.86 |================================================================= Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 24.54 |================================= f . 43.75 |=========================================================== e . 43.90 |=========================================================== g . 48.50 |================================================================= h . 50.60 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 40.73 |==================================================================== f . 22.83 |====================================== e . 22.76 |====================================== g . 20.60 |================================== h . 19.74 |================================= Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 373.03 |========= f . 2593.45 |================================================================= e . 2584.39 |================================================================= g . 2613.09 |================================================================= h . 2633.59 |================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 42.83 |=========================================================== f . 49.26 |==================================================================== e . 49.42 |==================================================================== g . 48.88 |=================================================================== h . 48.51 |=================================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 90.08 |==================================================================== f . 71.05 |====================================================== e . 71.41 |====================================================== g . 72.18 |====================================================== h . 77.92 |=========================================================== Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 11.09 |====================================================== f . 14.07 |==================================================================== e . 14.00 |==================================================================== g . 13.85 |=================================================================== h . 12.83 |============================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 85.49 |========== f . 570.63 |=================================================================== e . 567.94 |=================================================================== g . 566.73 |=================================================================== h . 569.32 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 186.65 |======================================================== f . 222.96 |================================================================== e . 224.25 |=================================================================== g . 224.65 |=================================================================== h . 223.85 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 50.91 |================================================ f . 60.08 |========================================================= e . 68.51 |================================================================= g . 69.33 |================================================================== h . 71.57 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 19.64 |==================================================================== f . 16.64 |========================================================== e . 14.59 |=================================================== g . 14.42 |================================================== h . 13.97 |================================================ Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better d . 19.88 |========== f . 128.97 |================================================================== e . 129.86 |================================================================== g . 129.44 |================================================================== h . 131.54 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better d . 794.04 |======================================================= f . 972.50 |=================================================================== e . 963.86 |================================================================== g . 969.24 |=================================================================== h . 952.87 |================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better d . 14.01 |============================= f . 30.56 |=============================================================== e . 30.31 |============================================================== g . 33.08 |==================================================================== h . 32.92 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better d . 71.35 |==================================================================== f . 32.72 |=============================== e . 32.98 |=============================== g . 30.22 |============================= h . 30.37 |============================= Stress-NG 0.16.04 Test: Hash Bogo Ops/s > Higher Is Better d . 7218607.12 |========== f . 45263381.84 |============================================================== e . 45096278.13 |============================================================== g . 45298625.91 |============================================================== h . 45265797.34 |============================================================== Stress-NG 0.16.04 Test: MMAP Bogo Ops/s > Higher Is Better d . 1131.55 |================== f . 2268.34 |==================================== e . 4118.19 |================================================================== g . 3664.34 |=========================================================== h . 3749.47 |============================================================ Stress-NG 0.16.04 Test: NUMA Bogo Ops/s > Higher Is Better d . 18.35 |==================================================================== f . 14.09 |==================================================== e . 14.26 |===================================================== g . 14.38 |===================================================== h . 14.46 |====================================================== Stress-NG 0.16.04 Test: Pipe Bogo Ops/s > Higher Is Better d . 20249488.61 |======= f . 168142512.00 |=========================================================== e . 157840183.63 |======================================================= g . 173499514.94 |============================================================= h . 159491222.34 |======================================================== Stress-NG 0.16.04 Test: Poll Bogo Ops/s > Higher Is Better d . 4337787.72 |============= f . 21392880.41 |============================================================== e . 21326879.36 |============================================================== g . 21346079.30 |============================================================== h . 20251576.33 |=========================================================== Stress-NG 0.16.04 Test: Zlib Bogo Ops/s > Higher Is Better d . 2944.54 |============ f . 16624.07 |================================================================= e . 16620.95 |================================================================= g . 16624.07 |================================================================= h . 16625.57 |================================================================= Stress-NG 0.16.04 Test: Futex Bogo Ops/s > Higher Is Better d . 4022496.07 |=============================================================== f . 2722241.67 |=========================================== e . 2781554.43 |============================================ g . 2951631.96 |============================================== h . 2880825.11 |============================================= Stress-NG 0.16.04 Test: MEMFD Bogo Ops/s > Higher Is Better d . 912.62 |=================================================================== f . 116.44 |========= e . 120.85 |========= g . 97.94 |======= h . 115.83 |========= Stress-NG 0.16.04 Test: Mutex Bogo Ops/s > Higher Is Better d . 438280.16 |================================================================ f . 363091.11 |===================================================== e . 363805.32 |===================================================== g . 364035.57 |===================================================== h . 363892.10 |===================================================== Stress-NG 0.16.04 Test: Atomic Bogo Ops/s > Higher Is Better d . 236.99 |=================================================================== f . 204.56 |========================================================== e . 205.09 |========================================================== g . 204.44 |========================================================== h . 203.49 |========================================================== Stress-NG 0.16.04 Test: Crypto Bogo Ops/s > Higher Is Better d . 107643.49 |=============== f . 457992.62 |=============================================================== e . 464310.66 |================================================================ g . 462528.73 |================================================================ h . 461785.36 |================================================================ Stress-NG 0.16.04 Test: Malloc Bogo Ops/s > Higher Is Better d . 137476652.93 |============ f . 714509917.70 |============================================================ e . 712254498.06 |============================================================ g . 719479964.33 |============================================================ h . 725705488.15 |============================================================= Stress-NG 0.16.04 Test: Cloning Bogo Ops/s > Higher Is Better d . 1170.31 |================================================================ f . 1158.86 |=============================================================== e . 1161.56 |=============================================================== g . 1139.87 |============================================================== h . 1209.53 |================================================================== Stress-NG 0.16.04 Test: Forking Bogo Ops/s > Higher Is Better d . 1007.46 |== f . 30923.93 |================================================================= e . 30826.86 |================================================================= g . 31064.95 |================================================================= h . 30591.67 |================================================================ Stress-NG 0.16.04 Test: AVL Tree Bogo Ops/s > Higher Is Better d . 410.89 |================= f . 1444.96 |=========================================================== e . 1473.15 |============================================================ g . 1564.42 |=============================================================== h . 1628.91 |================================================================== Stress-NG 0.16.04 Test: IO_uring Stress-NG 0.16.04 Test: SENDFILE Bogo Ops/s > Higher Is Better d . 857324.89 |============== f . 3224251.14 |====================================================== e . 3678593.69 |============================================================== g . 3761786.29 |=============================================================== h . 3745995.16 |=============================================================== Stress-NG 0.16.04 Test: CPU Cache Bogo Ops/s > Higher Is Better d . 776708.72 |================================================================ f . 352745.53 |============================= e . 348317.23 |============================= g . 334039.11 |============================ h . 361173.71 |============================== Stress-NG 0.16.04 Test: CPU Stress Bogo Ops/s > Higher Is Better d . 88466.54 |=========== f . 516299.64 |=============================================================== e . 517736.81 |=============================================================== g . 523898.45 |================================================================ h . 518600.85 |=============================================================== Stress-NG 0.16.04 Test: Semaphores Bogo Ops/s > Higher Is Better d . 92019395.13 |====== f . 775690998.40 |======================================================= e . 866657136.27 |============================================================= g . 800762640.11 |======================================================== h . 786069338.66 |======================================================= Stress-NG 0.16.04 Test: Matrix Math Bogo Ops/s > Higher Is Better d . 173878.70 |=========== f . 990014.15 |================================================================ e . 989961.32 |================================================================ g . 989553.80 |================================================================ h . 990104.85 |================================================================ Stress-NG 0.16.04 Test: Vector Math Bogo Ops/s > Higher Is Better d . 234239.60 |=========== f . 1284285.09 |=============================================================== e . 1287349.02 |=============================================================== g . 1288008.26 |=============================================================== h . 1285121.40 |=============================================================== Stress-NG 0.16.04 Test: AVX-512 VNNI Bogo Ops/s > Higher Is Better d . 3667964.15 |=========== f . 20046142.67 |============================================================== e . 20114751.56 |============================================================== g . 20133541.11 |============================================================== h . 20123210.14 |============================================================== Stress-NG 0.16.04 Test: Function Call Bogo Ops/s > Higher Is Better d . 27731.16 |=========== f . 159300.62 |================================================================ e . 159228.55 |================================================================ g . 156381.63 |=============================================================== h . 158994.25 |================================================================ Stress-NG 0.16.04 Test: x86_64 RdRand Bogo Ops/s > Higher Is Better d . 12013602.06 |========= f . 78670864.07 |============================================================== e . 78670488.15 |============================================================== g . 78673620.14 |============================================================== h . 78690548.49 |============================================================== Stress-NG 0.16.04 Test: Floating Point Bogo Ops/s > Higher Is Better d . 11939.41 |=========== f . 71775.48 |================================================================= e . 71642.41 |================================================================= g . 71782.95 |================================================================= h . 71790.06 |================================================================= Stress-NG 0.16.04 Test: Matrix 3D Math Bogo Ops/s > Higher Is Better d . 10869.49 |============================================= f . 13014.81 |====================================================== e . 13265.67 |======================================================= g . 14658.75 |============================================================ h . 15802.86 |================================================================= Stress-NG 0.16.04 Test: Memory Copying Bogo Ops/s > Higher Is Better d . 13428.64 |============ f . 72822.86 |================================================================= e . 72762.67 |================================================================= g . 72825.56 |================================================================= h . 72800.74 |================================================================= Stress-NG 0.16.04 Test: Vector Shuffle Bogo Ops/s > Higher Is Better d . 25006.73 |========== f . 154301.84 |================================================================ e . 153882.19 |================================================================ g . 154267.34 |================================================================ h . 154293.33 |================================================================ Stress-NG 0.16.04 Test: Mixed Scheduler Bogo Ops/s > Higher Is Better d . 35640.36 |================================================================= f . 29475.62 |====================================================== e . 29901.53 |======================================================= g . 29932.20 |======================================================= h . 29481.45 |====================================================== Stress-NG 0.16.04 Test: Socket Activity Bogo Ops/s > Higher Is Better d . 9504.38 |===== f . 109282.45 |============================================================== e . 111104.17 |=============================================================== g . 110254.19 |============================================================== h . 113347.77 |================================================================ Stress-NG 0.16.04 Test: Wide Vector Math Bogo Ops/s > Higher Is Better d . 1543291.91 |============ f . 8234696.93 |=============================================================== e . 8239176.31 |=============================================================== g . 8237581.37 |=============================================================== h . 8234456.23 |=============================================================== Stress-NG 0.16.04 Test: Context Switching Bogo Ops/s > Higher Is Better d . 17931974.92 |========== f . 96067858.09 |===================================================== e . 79639504.69 |============================================ g . 110432440.32 |============================================================= h . 110991931.60 |============================================================= Stress-NG 0.16.04 Test: Fused Multiply-Add Bogo Ops/s > Higher Is Better d . 32151217.03 |=========== f . 183254707.86 |============================================================= e . 179841973.66 |============================================================ g . 180789739.08 |============================================================ h . 181626937.85 |============================================================ Stress-NG 0.16.04 Test: Vector Floating Point Bogo Ops/s > Higher Is Better d . 106715.85 |=========== f . 606558.87 |================================================================ e . 605694.40 |================================================================ g . 604724.84 |================================================================ h . 605340.53 |================================================================ Stress-NG 0.16.04 Test: Glibc C String Functions Bogo Ops/s > Higher Is Better d . 40991307.95 |============ f . 215059237.87 |============================================================= e . 215179957.06 |============================================================= g . 215429087.61 |============================================================= h . 215308424.81 |============================================================= Stress-NG 0.16.04 Test: Glibc Qsort Data Sorting Bogo Ops/s > Higher Is Better d . 916.74 |============ f . 4847.93 |================================================================== e . 4849.60 |================================================================== g . 4846.22 |================================================================== h . 4850.99 |================================================================== Stress-NG 0.16.04 Test: System V Message Passing Bogo Ops/s > Higher Is Better d . 6851573.20 |======================================================== f . 7746308.69 |=============================================================== e . 7717311.24 |=============================================================== g . 7729966.17 |=============================================================== h . 7761412.61 |=============================================================== NCNN 20230517 Target: CPU - Model: mobilenet ms < Lower Is Better d . 23.97 |===================================== d . 23.55 |==================================== f . 42.54 |================================================================== e . 43.04 |================================================================== g . 41.21 |=============================================================== h . 44.14 |==================================================================== NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better d . 11.83 |========================= d . 11.29 |======================== f . 30.70 |================================================================= e . 31.88 |==================================================================== g . 31.24 |=================================================================== h . 30.89 |================================================================== NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better d . 12.01 |====================== d . 11.64 |===================== f . 34.29 |============================================================== e . 34.75 |=============================================================== g . 35.96 |================================================================= h . 37.56 |==================================================================== NCNN 20230517 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better d . 15.46 |================== d . 13.96 |================ f . 47.09 |======================================================== e . 43.73 |==================================================== g . 57.67 |==================================================================== h . 45.22 |===================================================== NCNN 20230517 Target: CPU - Model: mnasnet ms < Lower Is Better d . 10.83 |======================== d . 10.70 |======================= f . 30.98 |==================================================================== e . 29.33 |================================================================ g . 29.92 |================================================================== h . 29.55 |================================================================= NCNN 20230517 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better d . 15.43 |====================== d . 14.76 |===================== f . 48.73 |==================================================================== e . 48.52 |==================================================================== g . 47.67 |================================================================== h . 48.76 |==================================================================== NCNN 20230517 Target: CPU - Model: blazeface ms < Lower Is Better d . 5.84 |=============== d . 5.63 |============== f . 22.12 |======================================================== e . 21.74 |======================================================= g . 26.90 |==================================================================== h . 23.63 |============================================================ NCNN 20230517 Target: CPU - Model: googlenet ms < Lower Is Better d . 30.11 |=================================== d . 29.03 |================================== f . 56.15 |================================================================== e . 55.30 |================================================================= g . 57.72 |==================================================================== h . 55.36 |================================================================= NCNN 20230517 Target: CPU - Model: vgg16 ms < Lower Is Better d . 28.57 |================================ d . 28.69 |================================ f . 61.01 |==================================================================== e . 55.52 |============================================================== g . 56.34 |=============================================================== h . 58.85 |================================================================== NCNN 20230517 Target: CPU - Model: resnet18 ms < Lower Is Better d . 13.75 |=============================== d . 13.65 |=============================== f . 30.31 |==================================================================== e . 28.75 |================================================================= g . 29.26 |================================================================== h . 29.56 |================================================================== NCNN 20230517 Target: CPU - Model: alexnet ms < Lower Is Better d . 8.14 |================================ d . 8.13 |================================ f . 16.54 |================================================================= e . 16.70 |================================================================= g . 15.10 |=========================================================== h . 17.39 |==================================================================== NCNN 20230517 Target: CPU - Model: resnet50 ms < Lower Is Better d . 26.68 |================================= d . 26.53 |================================= f . 55.26 |==================================================================== e . 50.48 |============================================================== g . 53.62 |================================================================== h . 54.47 |=================================================================== NCNN 20230517 Target: CPU - Model: yolov4-tiny ms < Lower Is Better d . 40.34 |====================================================== d . 35.75 |================================================ f . 50.39 |==================================================================== e . 48.09 |================================================================= g . 48.08 |================================================================= h . 48.82 |================================================================== NCNN 20230517 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better d . 25.61 |============================= d . 24.22 |=========================== f . 60.52 |==================================================================== e . 56.85 |================================================================ g . 58.66 |================================================================== h . 58.41 |================================================================== NCNN 20230517 Target: CPU - Model: regnety_400m ms < Lower Is Better d . 34.57 |=========== d . 33.50 |=========== f . 197.20 |================================================================= e . 191.23 |=============================================================== g . 202.34 |=================================================================== h . 201.59 |=================================================================== NCNN 20230517 Target: CPU - Model: vision_transformer ms < Lower Is Better d . 55.81 |================================== d . 55.05 |================================== f . 98.31 |============================================================= e . 102.96 |=============================================================== g . 108.73 |=================================================================== h . 93.15 |========================================================= NCNN 20230517 Target: CPU - Model: FastestDet ms < Lower Is Better d . 16.00 |========================= f . 44.07 |==================================================================== e . 43.01 |================================================================== g . 44.27 |==================================================================== h . 42.30 |================================================================= Blender 3.6 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better d . 37.93 |==================================================================== f . 7.52 |============= e . 7.44 |============= g . 7.51 |============= h . 7.40 |============= Blender 3.6 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better d . 94.88 |==================================================================== f . 17.21 |============ e . 17.16 |============ g . 17.31 |============ h . 17.12 |============ Blender 3.6 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better d . 48.95 |==================================================================== f . 10.11 |============== e . 10.05 |============== g . 10.02 |============== h . 10.02 |============== Blender 3.6 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better d . 372.72 |=================================================================== f . 71.04 |============= e . 71.23 |============= g . 71.97 |============= h . 71.39 |============= Blender 3.6 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better d . 122.70 |=================================================================== f . 22.64 |============ e . 22.26 |============ g . 22.40 |============ h . 22.35 |============ Apache Cassandra 4.1.3 Test: Writes Op/s > Higher Is Better d . 230402 |=================================================================== f . 198090 |========================================================== e . 185913 |====================================================== g . 185134 |====================================================== h . 190955 |======================================================== Kripke 1.2.6 Throughput FoM > Higher Is Better d . 372072000 |================================================================ BRL-CAD 7.36 VGR Performance Metric VGR Performance Metric > Higher Is Better d . 544648 |====== f . 6353682 |================================================================= e . 6434651 |================================================================== g . 6398404 |================================================================== h . 6270577 |================================================================ Stress-NG 0.16.04 Test: Pthread Bogo Ops/s > Higher Is Better d . 70043.78 |================================================================= f . 54748.85 |=================================================== e . 54645.35 |=================================================== g . 54906.43 |=================================================== h . 55328.71 |=================================================== SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better f . 602.99 |=================================================================== e . 602.21 |=================================================================== g . 599.57 |=================================================================== h . 600.76 |=================================================================== SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better f . 202.49 |=================================================================== e . 195.36 |================================================================ g . 203.01 |=================================================================== h . 197.03 |================================================================= SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better f . 483.01 |=============================================================== e . 495.83 |================================================================= g . 511.80 |=================================================================== h . 507.02 |================================================================== SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better f . 196.32 |=================================================================== e . 169.93 |========================================================== g . 179.41 |============================================================= h . 187.68 |================================================================ SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better f . 124.81 |=================================================================== e . 123.52 |================================================================== g . 125.22 |=================================================================== h . 124.70 |=================================================================== SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better f . 93.66 |=================================================================== e . 93.28 |=================================================================== g . 92.64 |================================================================== h . 94.83 |==================================================================== SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better f . 9.873 |==================================================================== e . 9.731 |=================================================================== g . 9.831 |==================================================================== h . 9.901 |==================================================================== SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better f . 4.179 |==================================================================== e . 4.135 |=================================================================== g . 4.124 |=================================================================== h . 4.204 |====================================================================