2023 ryzen 5 AMD Ryzen 5 4500U testing with a LENOVO LNVNB161216 (EECN20WW BIOS) and AMD Renoir 512MB on Pop 22.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 5 4500U @ 2.38GHz (6 Cores), Motherboard: LENOVO LNVNB161216 (EECN20WW BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 256GB SK hynix HFM256GDHTNI-87A0B, Graphics: AMD Renoir 512MB (1500/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Realtek RTL8822CE 802.11ac PCIe OS: Pop 22.04, Kernel: 5.17.5-76051705-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.44), Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: AMD Ryzen 5 4500U @ 2.38GHz (6 Cores), Motherboard: LENOVO LNVNB161216 (EECN20WW BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 256GB SK hynix HFM256GDHTNI-87A0B, Graphics: AMD Renoir 512MB (1500/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Realtek RTL8822CE 802.11ac PCIe OS: Pop 22.04, Kernel: 5.17.5-76051705-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.44), Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: AMD Ryzen 5 4500U @ 2.38GHz (6 Cores), Motherboard: LENOVO LNVNB161216 (EECN20WW BIOS), Chipset: AMD Renoir/Cezanne, Memory: 16GB, Disk: 256GB SK hynix HFM256GDHTNI-87A0B, Graphics: AMD Renoir 512MB (1500/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Realtek RTL8822CE 802.11ac PCIe OS: Pop 22.04, Kernel: 5.17.5-76051705-generic (x86_64), Desktop: GNOME Shell 42.1, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.44), Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080 ET: Legacy 2.81 Resolution: 1920 x 1080 Frames Per Second > Higher Is Better a . 125.9 |==================================================================== b . 104.0 |======================================================== c . 104.2 |======================================================== Unvanquished 0.54 Resolution: 1920 x 1080 - Effects Quality: High Frames Per Second > Higher Is Better a . 162.2 |==================================================================== b . 130.4 |======================================================= c . 123.8 |==================================================== Unvanquished 0.54 Resolution: 1920 x 1080 - Effects Quality: Ultra Frames Per Second > Higher Is Better a . 126.7 |==================================================================== b . 90.7 |================================================= c . 86.6 |============================================== Unvanquished 0.54 Resolution: 1920 x 1080 - Effects Quality: Medium Frames Per Second > Higher Is Better a . 146.3 |==================================================================== b . 120.1 |======================================================== c . 124.1 |========================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 1.591 |================================================================== b . 1.648 |==================================================================== c . 1.621 |=================================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 3.580 |=================================================================== b . 3.644 |==================================================================== c . 3.601 |=================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 5.335 |=================================================================== b . 5.445 |==================================================================== c . 5.400 |=================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 13.07 |=================================================================== b . 13.29 |==================================================================== c . 13.07 |=================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Queries Per Minute, Geo Mean > Higher Is Better a . 62.09 |==================================================================== b . 61.80 |==================================================================== c . 60.32 |================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Queries Per Minute, Geo Mean > Higher Is Better a . 66.77 |================================================================== b . 67.00 |================================================================== c . 69.10 |==================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Queries Per Minute, Geo Mean > Higher Is Better a . 68.21 |================================================================== b . 67.68 |================================================================== c . 70.22 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 6.20 |===================================================================== b . 6.09 |==================================================================== c . 6.18 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 382.94 |=================================================================== b . 376.45 |================================================================== c . 379.30 |================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 27.82 |==================================================================== b . 27.29 |=================================================================== c . 27.47 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 5.41 |=================================================================== b . 5.59 |===================================================================== c . 5.38 |================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 5.31 |==================================================================== b . 5.40 |===================================================================== c . 5.38 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 3.569670803 |========================================================= b . 3.880000000 |============================================================== c . 3.770000000 |============================================================ Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 3.19 |===================================================================== b . 3.10 |=================================================================== c . 3.15 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 6.60 |================================================================= b . 6.96 |===================================================================== c . 6.88 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Calculate Pi Benchmark Seconds < Lower Is Better a . 380.63 |=================================================================== b . 376.19 |================================================================== c . 377.48 |================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 27.70 |==================================================================== b . 26.91 |================================================================== c . 27.50 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Group By Test Time Seconds < Lower Is Better a . 6.30 |================================================================= b . 6.53 |==================================================================== c . 6.65 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Repartition Test Time Seconds < Lower Is Better a . 5.41 |==================================================================== b . 5.46 |===================================================================== c . 5.48 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Inner Join Test Time Seconds < Lower Is Better a . 4.36 |================================================================== b . 4.53 |===================================================================== c . 4.47 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 3.84 |===================================================================== b . 3.84 |===================================================================== c . 3.80 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 7.25 |================================================================= b . 7.75 |===================================================================== c . 7.27 |================================================================= Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 380.69 |=================================================================== b . 379.89 |=================================================================== c . 378.64 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 27.39 |==================================================================== b . 27.36 |==================================================================== c . 27.33 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Group By Test Time Seconds < Lower Is Better a . 7.04 |===================================================================== b . 6.80 |=================================================================== c . 6.93 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Repartition Test Time Seconds < Lower Is Better a . 6.14 |=================================================================== b . 5.86 |================================================================ c . 6.31 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Inner Join Test Time Seconds < Lower Is Better a . 5.41 |==================================================================== b . 5.44 |==================================================================== c . 5.52 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 4.57 |===================================================================== b . 4.60 |===================================================================== c . 4.60 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 7.89 |===================================================================== b . 7.93 |===================================================================== c . 7.88 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 379.06 |=================================================================== b . 378.35 |=================================================================== c . 379.19 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 27.35 |=================================================================== b . 27.62 |==================================================================== c . 27.22 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Group By Test Time Seconds < Lower Is Better a . 8.09 |===================================================================== b . 8.02 |==================================================================== c . 8.05 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Repartition Test Time Seconds < Lower Is Better a . 7.20 |===================================================================== b . 7.03 |=================================================================== c . 7.03 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Inner Join Test Time Seconds < Lower Is Better a . 6.90 |================================================================= b . 7.35 |===================================================================== c . 7.36 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 5.57 |=============================================================== b . 6.12 |===================================================================== c . 5.54 |============================================================== Memcached 1.6.18 Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 686914.92 |================================================================ b . 680062.15 |=============================================================== c . 673400.06 |=============================================================== Memcached 1.6.18 Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 647418.98 |=============================================================== b . 661606.77 |================================================================ c . 652041.20 |=============================================================== Memcached 1.6.18 Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 646102.05 |============================================================== b . 604441.11 |========================================================== c . 664570.89 |================================================================ PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only TPS > Higher Is Better a . 18849 |==================================================================== b . 18350 |================================================================== c . 18694 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.053 |=================================================================== b . 0.054 |==================================================================== c . 0.053 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write TPS > Higher Is Better a . 568 |===================================================================== b . 574 |====================================================================== c . 564 |===================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency ms < Lower Is Better a . 1.759 |=================================================================== b . 1.743 |=================================================================== c . 1.773 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only TPS > Higher Is Better a . 189855 |=================================================================== b . 190735 |=================================================================== c . 187167 |================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.263 |=================================================================== b . 0.262 |=================================================================== c . 0.267 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only TPS > Higher Is Better a . 188986 |=================================================================== b . 172730 |============================================================= c . 187969 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.529 |============================================================== b . 0.579 |==================================================================== c . 0.532 |============================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only TPS > Higher Is Better a . 183892 |=================================================================== b . 178424 |================================================================= c . 184157 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better a . 1.359 |================================================================== b . 1.401 |==================================================================== c . 1.358 |================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Write TPS > Higher Is Better a . 557 |====================================================================== b . 551 |===================================================================== c . 555 |====================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better a . 89.70 |=================================================================== b . 90.76 |==================================================================== c . 90.04 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only TPS > Higher Is Better a . 180688 |=================================================================== b . 164072 |============================================================= c . 176550 |================================================================= PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency ms < Lower Is Better a . 2.767 |============================================================== b . 3.047 |==================================================================== c . 2.832 |=============================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Only TPS > Higher Is Better a . 137557 |=================================================================== b . 110229 |====================================================== c . 120638 |=========================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Only - Average Latency ms < Lower Is Better a . 5.816 |====================================================== b . 7.258 |==================================================================== c . 6.631 |============================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Only TPS > Higher Is Better a . 19549 |================================================================== b . 16747 |======================================================== c . 20223 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.051 |========================================================== b . 0.060 |==================================================================== c . 0.049 |======================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write TPS > Higher Is Better a . 418 |====================================================== b . 545 |====================================================================== c . 474 |============================================================= PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better a . 239.14 |=================================================================== b . 183.36 |=================================================== c . 210.77 |=========================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Write TPS > Higher Is Better a . 500 |====================================================================== b . 497 |====================================================================== c . 489 |==================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency ms < Lower Is Better a . 499.81 |================================================================== b . 503.30 |================================================================== c . 510.90 |=================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write TPS > Higher Is Better a . 388 |================================================================= b . 421 |====================================================================== c . 387 |================================================================ PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write - Average Latency ms < Lower Is Better a . 1288.17 |================================================================== b . 1188.78 |============================================================= c . 1293.04 |================================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Write TPS > Higher Is Better a . 338 |====================================================================== b . 329 |==================================================================== c . 306 |=============================================================== PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Write - Average Latency ms < Lower Is Better a . 2368.33 |============================================================ b . 2434.47 |============================================================= c . 2613.03 |================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Write TPS > Higher Is Better a . 339 |==================================================================== b . 350 |====================================================================== c . 340 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency ms < Lower Is Better a . 2.946 |==================================================================== b . 2.856 |================================================================== c . 2.939 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Only TPS > Higher Is Better a . 185082 |=================================================================== b . 175404 |=============================================================== c . 174601 |=============================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.270 |================================================================ b . 0.285 |==================================================================== c . 0.286 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only TPS > Higher Is Better a . 163009 |================================================================ b . 170386 |=================================================================== c . 162692 |================================================================ PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency ms < Lower Is Better a . 0.613 |==================================================================== b . 0.587 |================================================================= c . 0.615 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only TPS > Higher Is Better a . 154762 |============================================================ b . 173250 |=================================================================== c . 167141 |================================================================= PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better a . 1.615 |==================================================================== b . 1.443 |============================================================= c . 1.496 |=============================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Write TPS > Higher Is Better a . 4491 |================================================================= b . 4770 |===================================================================== c . 3807 |======================================================= PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency ms < Lower Is Better a . 11.13 |========================================================== b . 10.48 |====================================================== c . 13.13 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only TPS > Higher Is Better a . 168618 |=================================================================== b . 133815 |===================================================== c . 98790 |======================================= PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency ms < Lower Is Better a . 2.965 |======================================== b . 3.736 |================================================== c . 5.061 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only TPS > Higher Is Better a . 106427 |======================================================== b . 127387 |=================================================================== c . 121459 |================================================================ PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency ms < Lower Is Better a . 7.517 |==================================================================== b . 6.280 |========================================================= c . 6.587 |============================================================ PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write TPS > Higher Is Better a . 5148 |===================================================================== b . 5036 |=================================================================== c . 4346 |========================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency ms < Lower Is Better a . 19.42 |========================================================= b . 19.86 |=========================================================== c . 23.01 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Write TPS > Higher Is Better a . 5258 |===================================================================== b . 5060 |================================================================== c . 4505 |=========================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency ms < Lower Is Better a . 47.55 |========================================================== b . 49.41 |============================================================= c . 55.49 |==================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write TPS > Higher Is Better a . 5162 |===================================================================== b . 4721 |=============================================================== c . 4217 |======================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency ms < Lower Is Better a . 96.86 |======================================================= b . 105.91 |============================================================ c . 118.56 |=================================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Write TPS > Higher Is Better a . 4518 |===================================================================== b . 4514 |===================================================================== c . 4104 |=============================================================== PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency ms < Lower Is Better a . 177.09 |============================================================= b . 177.23 |============================================================= c . 194.94 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 3.4136 |=================================================================== b . 3.3567 |================================================================== c . 3.4003 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 875.43 |================================================================== b . 887.62 |=================================================================== c . 876.73 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 3.2897 |=================================================================== b . 3.2950 |=================================================================== c . 3.2326 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 303.97 |================================================================== b . 303.48 |================================================================== c . 309.33 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 29.47 |==================================================================== b . 29.62 |==================================================================== c . 28.38 |================================================================= Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 101.73 |================================================================= b . 101.21 |================================================================ c . 105.59 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 18.10 |==================================================================== b . 16.98 |================================================================ c . 16.59 |============================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 55.24 |============================================================== b . 58.86 |================================================================== c . 60.26 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 10.67 |==================================================================== b . 10.69 |==================================================================== c . 10.57 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 280.50 |================================================================== b . 280.50 |================================================================== c . 282.94 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 6.4244 |================================================================== b . 6.4058 |================================================================== c . 6.4858 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 155.63 |=================================================================== b . 156.09 |=================================================================== c . 154.16 |================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 20.10 |==================================================================== b . 20.16 |==================================================================== c . 20.04 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 149.04 |=================================================================== b . 148.43 |=================================================================== c . 149.48 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 17.72 |=================================================================== b . 17.95 |==================================================================== c . 17.72 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 56.41 |==================================================================== b . 55.69 |=================================================================== c . 56.42 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 43.15 |==================================================================== b . 43.05 |==================================================================== c . 42.88 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 69.44 |==================================================================== b . 69.64 |==================================================================== c . 69.90 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 37.99 |=================================================================== b . 38.79 |==================================================================== c . 38.62 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 26.31 |==================================================================== b . 25.76 |=================================================================== c . 25.88 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 30.14 |==================================================================== b . 30.15 |==================================================================== c . 30.22 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 99.49 |==================================================================== b . 99.45 |==================================================================== c . 99.22 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 24.70 |================================================================== b . 25.24 |==================================================================== c . 25.27 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 40.48 |==================================================================== b . 39.60 |=================================================================== c . 39.56 |================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 4.0502 |=================================================================== b . 4.0529 |=================================================================== c . 4.0287 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 734.59 |=================================================================== b . 735.40 |=================================================================== c . 738.29 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 4.2014 |=================================================================== b . 4.1893 |=================================================================== c . 4.1841 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 238.00 |=================================================================== b . 238.68 |=================================================================== c . 238.98 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 15.06 |==================================================================== b . 15.05 |==================================================================== c . 14.94 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 199.13 |=================================================================== b . 199.07 |=================================================================== c . 200.01 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 10.05 |============================================================== b . 10.52 |================================================================= c . 11.06 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 99.50 |==================================================================== b . 95.09 |================================================================= c . 90.43 |============================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 3.4341 |================================================================== b . 3.4302 |================================================================== c . 3.4656 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 866.76 |=================================================================== b . 864.38 |=================================================================== c . 860.17 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 3.2499 |================================================================= b . 3.2812 |================================================================== c . 3.3428 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 307.70 |=================================================================== b . 304.76 |================================================================== c . 299.14 |================================================================= OpenEMS 0.0.35-86 Test: pyEMS Coupler MCells/s > Higher Is Better a . 15.88 |=================================================================== b . 16.07 |==================================================================== c . 15.43 |================================================================= OpenEMS 0.0.35-86 Test: openEMS MSL_NotchFilter MCells/s > Higher Is Better a . 60.99 |============================================================ b . 60.86 |============================================================ c . 69.33 |====================================================================