june Intel Core i9-10980XE testing with a ASRock X299 Steel Legend (P1.30 BIOS) and llvmpipe on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: llvmpipe, Audio: Realtek ALC1220, Network: Intel I219-V + Intel I211 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc7-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, OpenGL: 4.5 Mesa 22.0.1 (LLVM 13.0.1 256 bits), Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1024x768 b: Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: llvmpipe, Audio: Realtek ALC1220, Network: Intel I219-V + Intel I211 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc7-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, OpenGL: 4.5 Mesa 22.0.1 (LLVM 13.0.1 256 bits), Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1024x768 c: Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: llvmpipe, Audio: Realtek ALC1220, Network: Intel I219-V + Intel I211 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc7-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, OpenGL: 4.5 Mesa 22.0.1 (LLVM 13.0.1 256 bits), Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1024x768 SQLite 3.41.2 Threads / Copies: 1 Seconds < Lower Is Better a . 48.86 |==================================================================== b . 47.95 |=================================================================== c . 48.01 |=================================================================== SQLite 3.41.2 Threads / Copies: 2 Seconds < Lower Is Better a . 114.62 |=================================================================== b . 115.27 |=================================================================== c . 115.04 |=================================================================== SQLite 3.41.2 Threads / Copies: 4 Seconds < Lower Is Better a . 138.51 |=================================================================== b . 137.37 |================================================================== c . 137.41 |================================================================== SQLite 3.41.2 Threads / Copies: 8 Seconds < Lower Is Better a . 177.00 |================================================================= b . 182.14 |=================================================================== c . 179.77 |================================================================== QuantLib 1.30 MFLOPS > Higher Is Better a . 2297.4 |================================================================ b . 2386.9 |=================================================================== c . 2365.5 |================================================================== High Performance Conjugate Gradient 3.1 X Y Z: 104 104 104 - RT: 60 GFLOP/s > Higher Is Better a . 7.56073 |================================================================== b . 7.54527 |================================================================== c . 7.54020 |================================================================== High Performance Conjugate Gradient 3.1 X Y Z: 144 144 144 - RT: 60 GFLOP/s > Higher Is Better High Performance Conjugate Gradient 3.1 X Y Z: 160 160 160 - RT: 60 GFLOP/s > Higher Is Better libxsmm 2-1.17-3645 M N K: 128 GFLOPS/s > Higher Is Better a . 392.9 |=================================================================== b . 397.3 |==================================================================== c . 398.6 |==================================================================== libxsmm 2-1.17-3645 M N K: 256 GFLOPS/s > Higher Is Better a . 156.6 |==================================================================== b . 156.8 |==================================================================== c . 156.9 |==================================================================== libxsmm 2-1.17-3645 M N K: 32 GFLOPS/s > Higher Is Better a . 107.2 |==================================================================== b . 107.2 |==================================================================== c . 107.5 |==================================================================== libxsmm 2-1.17-3645 M N K: 64 GFLOPS/s > Higher Is Better a . 222.1 |==================================================================== b . 222.8 |==================================================================== c . 223.2 |==================================================================== Monte Carlo Simulations of Ionised Nebulae 2.02.73.3 Input: Gas HII40 Seconds < Lower Is Better a . 18.28 |================================================================ b . 19.26 |==================================================================== c . 19.32 |==================================================================== Monte Carlo Simulations of Ionised Nebulae 2.02.73.3 Input: Dust 2D tau100.0 Seconds < Lower Is Better a . 195.53 |=================================================================== b . 195.67 |=================================================================== c . 195.37 |=================================================================== RELION 4.0.1 Test: Basic - Device: CPU Seconds < Lower Is Better a . 1354.22 |============================================================= b . 1458.82 |================================================================= c . 1470.98 |================================================================== Z3 Theorem Prover 4.12.1 SMT File: 1.smt2 Seconds < Lower Is Better a . 37.59 |=================================================================== b . 37.58 |=================================================================== c . 38.07 |==================================================================== Z3 Theorem Prover 4.12.1 SMT File: 2.smt2 Seconds < Lower Is Better a . 136.37 |================================================================== b . 138.13 |=================================================================== c . 138.13 |=================================================================== srsRAN Project 23.5 Test: Downlink Processor Benchmark Mbps > Higher Is Better a . 413.6 |==================================================================== b . 416.0 |==================================================================== c . 413.5 |==================================================================== srsRAN Project 23.5 Test: PUSCH Processor Benchmark, Throughput Total Mbps > Higher Is Better a . 2199.7 |=================================================================== b . 2159.6 |================================================================== c . 2203.9 |=================================================================== srsRAN Project 23.5 Test: PUSCH Processor Benchmark, Throughput Thread Mbps > Higher Is Better a . 164.4 |==================================================================== b . 163.8 |==================================================================== c . 161.0 |=================================================================== dav1d 1.2.1 Video Input: Chimera 1080p FPS > Higher Is Better a . 230.12 |=================================================================== b . 230.26 |=================================================================== c . 230.84 |=================================================================== dav1d 1.2.1 Video Input: Summer Nature 4K FPS > Higher Is Better a . 224.08 |================================================================== b . 225.15 |================================================================== c . 227.44 |=================================================================== dav1d 1.2.1 Video Input: Summer Nature 1080p FPS > Higher Is Better a . 596.16 |================================================================= b . 602.88 |================================================================= c . 618.43 |=================================================================== dav1d 1.2.1 Video Input: Chimera 1080p 10-bit FPS > Higher Is Better a . 205.71 |=================================================================== b . 205.66 |=================================================================== c . 204.78 |=================================================================== Embree 4.1 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better a . 19.34 |==================================================================== b . 19.18 |=================================================================== c . 19.32 |==================================================================== Embree 4.1 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better a . 17.62 |==================================================================== b . 17.62 |==================================================================== c . 17.68 |==================================================================== Embree 4.1 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better a . 22.27 |==================================================================== b . 22.24 |==================================================================== c . 22.19 |==================================================================== Embree 4.1 Binary: Pathtracer - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 20.12 |==================================================================== b . 19.95 |=================================================================== c . 20.09 |==================================================================== Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better a . 22.97 |==================================================================== b . 22.92 |==================================================================== c . 23.06 |==================================================================== Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 19.73 |==================================================================== b . 19.73 |==================================================================== c . 19.77 |==================================================================== SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 2.670 |==================================================================== b . 2.668 |==================================================================== c . 2.665 |==================================================================== SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 35.93 |==================================================================== b . 36.10 |==================================================================== c . 35.77 |=================================================================== SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 98.96 |==================================================================== b . 98.19 |=================================================================== c . 99.18 |==================================================================== SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 100.18 |=================================================================== b . 99.42 |================================================================== c . 99.11 |================================================================== SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 7.817 |==================================================================== b . 7.680 |=================================================================== c . 7.839 |==================================================================== SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 50.51 |==================================================================== b . 49.28 |================================================================== c . 49.22 |================================================================== SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 157.71 |================================================================== b . 160.45 |=================================================================== c . 154.21 |================================================================ SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 189.51 |=================================================================== b . 188.50 |=================================================================== c . 179.15 |=============================================================== VVenC 1.8 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 4.200 |==================================================================== b . 4.198 |==================================================================== c . 4.209 |==================================================================== VVenC 1.8 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 8.083 |==================================================================== b . 8.086 |==================================================================== c . 8.083 |==================================================================== VVenC 1.8 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 11.36 |==================================================================== b . 11.43 |==================================================================== c . 11.30 |=================================================================== VVenC 1.8 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 21.78 |==================================================================== b . 21.79 |==================================================================== c . 21.79 |==================================================================== Opus Codec Encoding 1.4 WAV To Opus Encode Seconds < Lower Is Better a . 39.97 |==================================================================== b . 39.91 |==================================================================== c . 39.83 |==================================================================== eSpeak-NG Speech Engine 1.51 Text-To-Speech Synthesis Seconds < Lower Is Better a . 36.85 |=================================================================== b . 37.00 |=================================================================== c . 37.61 |==================================================================== Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 38047000 |================================================================= b . 37991000 |================================================================= c . 37996000 |================================================================= Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 47089000 |================================================================= b . 47036000 |================================================================= c . 46996000 |================================================================= Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 74320000 |================================================================= b . 74473000 |================================================================= c . 73914000 |================================================================= Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 83707000 |================================================================= b . 83589000 |================================================================= c . 83637000 |================================================================= Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 143830000 |================================================================ b . 143510000 |================================================================ c . 142900000 |================================================================ Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 147040000 |================================================================ b . 144900000 |=============================================================== c . 145610000 |=============================================================== Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 281500000 |================================================================ b . 283260000 |================================================================ c . 281220000 |================================================================ Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 262290000 |=============================================================== b . 264750000 |================================================================ c . 264540000 |================================================================ Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 12299000 |================================================================= b . 12292000 |================================================================= c . 12273000 |================================================================= Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 528520000 |================================================================ b . 527920000 |================================================================ c . 527780000 |================================================================ Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 472070000 |================================================================ b . 471920000 |================================================================ c . 468410000 |================================================================ Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 25027000 |================================================================= b . 24980000 |================================================================= c . 25043000 |================================================================= Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 973050000 |================================================================ b . 973270000 |================================================================ c . 976240000 |================================================================ Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 700150000 |=============================================================== b . 707420000 |================================================================ c . 697890000 |=============================================================== Liquid-DSP 1.6 Threads: 36 - Buffer Length: 256 - Filter Length: 32 samples/s > Higher Is Better a . 1070600000 |=============================================================== b . 1057600000 |============================================================== c . 1063900000 |=============================================================== Liquid-DSP 1.6 Threads: 36 - Buffer Length: 256 - Filter Length: 57 samples/s > Higher Is Better a . 736850000 |=============================================================== b . 750100000 |================================================================ c . 742360000 |=============================================================== Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 49144000 |================================================================= b . 49260000 |================================================================= c . 49141000 |================================================================= Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 95954000 |================================================================= b . 96260000 |================================================================= c . 96340000 |================================================================= Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 179950000 |================================================================ b . 180140000 |================================================================ c . 180230000 |================================================================ Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 257910000 |================================================================ b . 257140000 |================================================================ c . 258540000 |================================================================ Liquid-DSP 1.6 Threads: 36 - Buffer Length: 256 - Filter Length: 512 samples/s > Higher Is Better a . 273040000 |================================================================ b . 273140000 |================================================================ c . 272650000 |================================================================ Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 17.97 |==================================================================== b . 17.96 |==================================================================== c . 17.82 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 497.58 |=================================================================== b . 498.40 |=================================================================== c . 501.26 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 16.52 |==================================================================== b . 16.55 |==================================================================== c . 16.57 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 60.51 |==================================================================== b . 60.42 |==================================================================== c . 60.35 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 232.45 |=================================================================== b . 233.56 |=================================================================== c . 233.84 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 38.70 |==================================================================== b . 38.51 |==================================================================== c . 38.46 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 123.43 |=================================================================== b . 122.66 |=================================================================== c . 123.45 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 8.0921 |=================================================================== b . 8.1430 |=================================================================== c . 8.0913 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 52.82 |==================================================================== b . 53.19 |==================================================================== c . 52.91 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 170.12 |=================================================================== b . 169.04 |=================================================================== c . 169.81 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 49.30 |==================================================================== b . 49.31 |==================================================================== c . 49.08 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 20.27 |==================================================================== b . 20.27 |==================================================================== c . 20.36 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 103.33 |=================================================================== b . 102.80 |=================================================================== c . 103.29 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 87.06 |==================================================================== b . 87.51 |==================================================================== c . 87.05 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 79.83 |==================================================================== b . 79.95 |==================================================================== c . 79.65 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 12.51 |==================================================================== b . 12.49 |==================================================================== c . 12.54 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 257.95 |=================================================================== b . 257.42 |=================================================================== c . 258.11 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 34.86 |==================================================================== b . 34.93 |==================================================================== c . 34.84 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 137.72 |=================================================================== b . 135.69 |================================================================== c . 137.94 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 7.2500 |================================================================== b . 7.3587 |=================================================================== c . 7.2377 |================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 144.10 |================================================================= b . 144.71 |================================================================= c . 148.40 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 62.38 |==================================================================== b . 62.16 |==================================================================== c . 60.63 |================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 96.64 |==================================================================== b . 94.97 |=================================================================== c . 95.81 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 10.34 |=================================================================== b . 10.52 |==================================================================== c . 10.43 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 22.83 |==================================================================== b . 22.71 |==================================================================== c . 22.67 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 393.76 |=================================================================== b . 395.87 |=================================================================== c . 394.44 |=================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 21.95 |==================================================================== b . 22.00 |==================================================================== c . 21.96 |==================================================================== Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 45.54 |==================================================================== b . 45.44 |==================================================================== c . 45.51 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 71.96 |=================================================================== b . 73.10 |==================================================================== c . 71.89 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 125.04 |=================================================================== b . 123.09 |================================================================== c . 125.17 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 48.65 |==================================================================== b . 48.94 |==================================================================== c . 48.95 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 20.55 |==================================================================== b . 20.42 |==================================================================== c . 20.42 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 17.65 |==================================================================== b . 17.74 |==================================================================== c . 17.69 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 506.53 |=================================================================== b . 505.34 |=================================================================== c . 506.70 |=================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 16.10 |=================================================================== b . 16.32 |==================================================================== c . 16.23 |==================================================================== Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 62.10 |==================================================================== b . 61.27 |=================================================================== c . 61.62 |=================================================================== Stress-NG 0.15.10 Test: Hash Bogo Ops/s > Higher Is Better a . 3160968.94 |============================================================ b . 3293772.69 |=============================================================== c . 3269490.82 |=============================================================== Stress-NG 0.15.10 Test: MMAP Bogo Ops/s > Higher Is Better a . 377.69 |================================================================== b . 381.37 |=================================================================== c . 378.29 |================================================================== Stress-NG 0.15.10 Test: NUMA Bogo Ops/s > Higher Is Better a . 383.40 |================================================================== b . 388.63 |=================================================================== c . 385.82 |=================================================================== Stress-NG 0.15.10 Test: Pipe Bogo Ops/s > Higher Is Better a . 9319148.71 |=============================================================== b . 9374931.95 |=============================================================== c . 9360534.19 |=============================================================== Stress-NG 0.15.10 Test: Poll Bogo Ops/s > Higher Is Better a . 2356731.34 |=============================================================== b . 2357112.22 |=============================================================== c . 2355403.88 |=============================================================== Stress-NG 0.15.10 Test: Zlib Bogo Ops/s > Higher Is Better a . 1926.82 |================================================================== b . 1923.67 |================================================================== c . 1917.90 |================================================================== Stress-NG 0.15.10 Test: Futex Bogo Ops/s > Higher Is Better a . 2450295.89 |=============================================================== b . 2257619.63 |========================================================== c . 2364953.68 |============================================================= Stress-NG 0.15.10 Test: MEMFD Bogo Ops/s > Higher Is Better a . 356.35 |================================================================== b . 362.51 |=================================================================== c . 359.02 |================================================================== Stress-NG 0.15.10 Test: Mutex Bogo Ops/s > Higher Is Better a . 11151019.20 |============================================================== b . 11163728.77 |============================================================== Stress-NG 0.15.10 Test: Atomic Bogo Ops/s > Higher Is Better a . 268.45 |=================================================================== b . 266.98 |=================================================================== Stress-NG 0.15.10 Test: Crypto Bogo Ops/s > Higher Is Better a . 30778.89 |================================================================= b . 30768.49 |================================================================= Stress-NG 0.15.10 Test: Malloc Bogo Ops/s > Higher Is Better a . 27513666.08 |============================================================== b . 27457307.30 |============================================================== Stress-NG 0.15.10 Test: Cloning Bogo Ops/s > Higher Is Better a . 1657.21 |================================================================== b . 1666.79 |================================================================== Stress-NG 0.15.10 Test: Forking Bogo Ops/s > Higher Is Better a . 54709.75 |================================================================ b . 55280.88 |================================================================= Stress-NG 0.15.10 Test: Pthread Bogo Ops/s > Higher Is Better a . 139152.26 |================================================================ b . 138545.44 |================================================================ Stress-NG 0.15.10 Test: AVL Tree Bogo Ops/s > Higher Is Better a . 111.01 |=================================================================== b . 111.05 |=================================================================== Stress-NG 0.15.10 Test: IO_uring Bogo Ops/s > Higher Is Better a . 238314.47 |================================================================ b . 239747.21 |================================================================ Stress-NG 0.15.10 Test: SENDFILE Bogo Ops/s > Higher Is Better a . 325600.51 |================================================================ b . 325816.87 |================================================================ Stress-NG 0.15.10 Test: CPU Cache Bogo Ops/s > Higher Is Better a . 2923392.1 |================================================================ b . 2576358.0 |======================================================== Stress-NG 0.15.10 Test: CPU Stress Bogo Ops/s > Higher Is Better a . 42674.60 |================================================================= b . 42701.63 |================================================================= Stress-NG 0.15.10 Test: Semaphores Bogo Ops/s > Higher Is Better a . 41039242.26 |============================================================== b . 41174375.79 |============================================================== Stress-NG 0.15.10 Test: Matrix Math Bogo Ops/s > Higher Is Better a . 99971.52 |================================================================= b . 98339.79 |================================================================ Stress-NG 0.15.10 Test: Vector Math Bogo Ops/s > Higher Is Better a . 69200.14 |================================================================= b . 69079.55 |================================================================= Stress-NG 0.15.10 Test: Function Call Bogo Ops/s > Higher Is Better a . 10795.42 |================================================================= b . 10785.12 |================================================================= Stress-NG 0.15.10 Test: x86_64 RdRand Bogo Ops/s > Higher Is Better a . 182253.68 |================================================================ b . 182243.26 |================================================================ Stress-NG 0.15.10 Test: Floating Point Bogo Ops/s > Higher Is Better a . 3901.00 |================================================================== b . 3892.41 |================================================================== Stress-NG 0.15.10 Test: Matrix 3D Math Bogo Ops/s > Higher Is Better a . 1403.77 |================================================================== b . 1404.98 |================================================================== Stress-NG 0.15.10 Test: Memory Copying Bogo Ops/s > Higher Is Better a . 4840.85 |================================================================== b . 4835.24 |================================================================== Stress-NG 0.15.10 Test: Vector Shuffle Bogo Ops/s > Higher Is Better a . 12117.87 |================================================================= b . 12090.17 |================================================================= Stress-NG 0.15.10 Test: Socket Activity Bogo Ops/s > Higher Is Better a . 11498.67 |=============================================================== b . 11930.75 |================================================================= Stress-NG 0.15.10 Test: Wide Vector Math Bogo Ops/s > Higher Is Better a . 726737.43 |================================================================ b . 730513.78 |================================================================ Stress-NG 0.15.10 Test: Context Switching Bogo Ops/s > Higher Is Better a . 2769182.16 |============================================================= b . 2862261.77 |=============================================================== Stress-NG 0.15.10 Test: Fused Multiply-Add Bogo Ops/s > Higher Is Better a . 17168287.23 |============================================================== b . 17113542.40 |============================================================== Stress-NG 0.15.10 Test: Vector Floating Point Bogo Ops/s > Higher Is Better a . 39425.24 |================================================================= b . 37514.93 |============================================================== Stress-NG 0.15.10 Test: Glibc C String Functions Bogo Ops/s > Higher Is Better a . 6643031.84 |=============================================================== b . 6629878.42 |=============================================================== Stress-NG 0.15.10 Test: Glibc Qsort Data Sorting Bogo Ops/s > Higher Is Better a . 427.85 |=================================================================== b . 426.51 |=================================================================== Stress-NG 0.15.10 Test: System V Message Passing Bogo Ops/s > Higher Is Better a . 7183098.54 |=============================================================== b . 7136960.22 |=============================================================== GPAW 23.6 Input: Carbon Nanotube Seconds < Lower Is Better a . 207.78 |=================================================================== b . 207.09 |=================================================================== Whisper.cpp 1.4 Model: ggml-base.en - Input: 2016 State of the Union Seconds < Lower Is Better a . 173.92 |=================================================================== b . 173.15 |=================================================================== Whisper.cpp 1.4 Model: ggml-small.en - Input: 2016 State of the Union Seconds < Lower Is Better a . 488.90 |=================================================================== b . 481.10 |================================================================== Whisper.cpp 1.4 Model: ggml-medium.en - Input: 2016 State of the Union Seconds < Lower Is Better a . 1343.53 |================================================================= b . 1366.65 |================================================================== Kripke 1.2.6 Throughput FoM > Higher Is Better