2023 new AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (1603 BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads), Motherboard: ASUS ROG ZENITH II EXTREME (1603 BIOS), Chipset: AMD Starship/Matisse, Memory: 4 x 16 GB DDR4-3600MT/s Corsair CMT64GX4M4Z3600C16, Disk: Samsung SSD 980 PRO 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc7-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.47), Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads), Motherboard: ASUS ROG ZENITH II EXTREME (1603 BIOS), Chipset: AMD Starship/Matisse, Memory: 4 x 16 GB DDR4-3600MT/s Corsair CMT64GX4M4Z3600C16, Disk: Samsung SSD 980 PRO 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc7-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.47), Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160 c: Processor: AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads), Motherboard: ASUS ROG ZENITH II EXTREME (1603 BIOS), Chipset: AMD Starship/Matisse, Memory: 4 x 16 GB DDR4-3600MT/s Corsair CMT64GX4M4Z3600C16, Disk: Samsung SSD 980 PRO 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc7-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.47), Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160 VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 3.809 |==================================================================== b . 3.803 |==================================================================== c . 3.758 |=================================================================== VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 8.933 |==================================================================== b . 8.883 |==================================================================== c . 8.856 |=================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 7.434 |==================================================================== b . 7.407 |==================================================================== c . 7.415 |==================================================================== VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 17.35 |==================================================================== b . 17.31 |==================================================================== c . 17.31 |==================================================================== ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Queries Per Minute, Geo Mean > Higher Is Better a . 216.80 |=================================================================== b . 217.01 |=================================================================== c . 206.93 |================================================================ ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Queries Per Minute, Geo Mean > Higher Is Better a . 240.84 |=================================================================== b . 227.29 |=============================================================== c . 229.25 |================================================================ ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Queries Per Minute, Geo Mean > Higher Is Better a . 231.92 |=================================================================== b . 233.48 |=================================================================== c . 226.34 |================================================================= Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 3.16 |==================================================================== b . 3.09 |================================================================== c . 3.21 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 56.16 |==================================================================== b . 55.60 |=================================================================== c . 56.04 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.43 |==================================================================== b . 3.49 |===================================================================== c . 3.46 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 4.55 |==================================================================== b . 4.27 |================================================================ c . 4.63 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 1.611880247 |======================================================== b . 1.790000000 |============================================================== c . 1.630000000 |======================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 1.46 |=================================================================== b . 1.38 |=============================================================== c . 1.51 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 1.01 |================================================================== b . 1.05 |==================================================================== c . 1.06 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 3.34 |===================================================================== b . 3.32 |===================================================================== c . 3.25 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Calculate Pi Benchmark Seconds < Lower Is Better a . 56.41 |==================================================================== b . 56.66 |==================================================================== c . 56.54 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.39 |===================================================================== b . 3.37 |===================================================================== c . 3.37 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Group By Test Time Seconds < Lower Is Better a . 4.55 |================================================================= b . 4.84 |===================================================================== c . 4.55 |================================================================= Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Repartition Test Time Seconds < Lower Is Better a . 1.75 |===================================================================== b . 1.67 |================================================================== c . 1.71 |=================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Inner Join Test Time Seconds < Lower Is Better a . 1.79 |===================================================================== b . 1.80 |===================================================================== c . 1.57 |============================================================ Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 1.31 |================================================================= b . 1.39 |===================================================================== c . 1.18 |=========================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 3.42 |=================================================================== b . 3.50 |===================================================================== c . 3.49 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 56.47 |==================================================================== b . 55.83 |=================================================================== c . 55.22 |================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.46 |===================================================================== b . 3.40 |==================================================================== c . 3.40 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Group By Test Time Seconds < Lower Is Better a . 4.91 |===================================================================== b . 4.77 |=================================================================== c . 4.45 |=============================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Repartition Test Time Seconds < Lower Is Better a . 1.914188324 |============================================================ b . 1.800000000 |======================================================== c . 1.980000000 |============================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Inner Join Test Time Seconds < Lower Is Better a . 1.89 |===================================================================== b . 1.74 |================================================================ c . 1.88 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 1000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 1.50 |================================================================ b . 1.62 |===================================================================== c . 1.43 |============================================================= Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 3.52 |===================================================================== b . 3.48 |==================================================================== c . 3.53 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 55.89 |=================================================================== b . 55.60 |=================================================================== c . 56.58 |==================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.383115781 |============================================================ b . 3.490000000 |============================================================== c . 3.460000000 |============================================================= Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Group By Test Time Seconds < Lower Is Better a . 4.93 |===================================================================== b . 4.76 |=================================================================== c . 4.71 |================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Repartition Test Time Seconds < Lower Is Better a . 2.19 |===================================================================== b . 2.20 |===================================================================== c . 2.03 |================================================================ Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Inner Join Test Time Seconds < Lower Is Better a . 1.94 |=============================================================== b . 2.08 |=================================================================== c . 2.13 |===================================================================== Apache Spark 3.3 Row Count: 1000000 - Partitions: 2000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 2.16 |===================================================================== b . 1.92 |============================================================= c . 1.86 |=========================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 8.644669927 |============================================================= b . 8.480000000 |=========================================================== c . 8.840000000 |============================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 55.27 |=================================================================== b . 56.08 |==================================================================== c . 55.32 |=================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.39 |===================================================================== b . 3.40 |===================================================================== c . 3.38 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 6.63 |===================================================================== b . 6.48 |=================================================================== c . 6.51 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 4.87 |================================================================= b . 5.19 |===================================================================== c . 5.17 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 5.62 |==================================================================== b . 5.63 |==================================================================== c . 5.70 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 4.95 |================================================================== b . 5.18 |===================================================================== c . 5.13 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 500 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 8.72 |===================================================================== b . 8.69 |===================================================================== c . 8.75 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 500 - Calculate Pi Benchmark Seconds < Lower Is Better a . 57.47 |==================================================================== b . 55.81 |================================================================== c . 55.95 |================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.38 |================================================================== b . 3.43 |=================================================================== c . 3.51 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 500 - Group By Test Time Seconds < Lower Is Better a . 6.28 |=================================================================== b . 6.48 |===================================================================== c . 6.36 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 500 - Repartition Test Time Seconds < Lower Is Better a . 4.73 |=================================================================== b . 4.86 |===================================================================== c . 4.76 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 500 - Inner Join Test Time Seconds < Lower Is Better a . 5.72 |==================================================================== b . 5.56 |================================================================== c . 5.81 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 500 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 4.82 |================================================================= b . 5.04 |==================================================================== c . 5.08 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 14.16 |================================================================ b . 14.56 |================================================================== c . 14.94 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 56.05 |==================================================================== b . 55.16 |================================================================== c . 56.41 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.39 |=============================================================== b . 3.70 |===================================================================== c . 3.44 |================================================================ Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 8.24 |==================================================================== b . 7.87 |================================================================= c . 8.31 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 8.92 |===================================================================== b . 8.82 |==================================================================== c . 8.85 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 9.860000000 |========================================================== b . 9.920000000 |========================================================== c . 10.441529534 |============================================================= Apache Spark 3.3 Row Count: 20000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 9.14 |==================================================================== b . 9.04 |==================================================================== c . 9.24 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 500 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 14.51 |==================================================================== b . 14.44 |==================================================================== c . 14.17 |================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 500 - Calculate Pi Benchmark Seconds < Lower Is Better a . 54.87 |=================================================================== b . 56.08 |==================================================================== c . 54.88 |=================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.44 |===================================================================== b . 3.38 |==================================================================== c . 3.38 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 500 - Group By Test Time Seconds < Lower Is Better a . 8.30 |==================================================================== b . 8.39 |===================================================================== c . 8.09 |=================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 500 - Repartition Test Time Seconds < Lower Is Better a . 8.85 |================================================================== b . 8.93 |=================================================================== c . 9.22 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 500 - Inner Join Test Time Seconds < Lower Is Better a . 9.86 |===================================================================== b . 9.62 |=================================================================== c . 9.73 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 500 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 9.35 |===================================================================== b . 9.14 |=================================================================== c . 9.24 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 25.49 |================================================================= b . 26.56 |==================================================================== c . 25.64 |================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Calculate Pi Benchmark Seconds < Lower Is Better a . 54.84 |================================================================== b . 55.43 |=================================================================== c . 56.38 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.38 |=================================================================== b . 3.46 |===================================================================== c . 3.47 |===================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Group By Test Time Seconds < Lower Is Better a . 16.85 |==================================================================== b . 16.53 |=================================================================== c . 16.74 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Repartition Test Time Seconds < Lower Is Better a . 16.23 |==================================================================== b . 16.24 |==================================================================== c . 16.05 |=================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Inner Join Test Time Seconds < Lower Is Better a . 18.15 |================================================================== b . 18.62 |==================================================================== c . 18.11 |================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 100 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 17.07 |=================================================================== b . 17.24 |==================================================================== c . 17.07 |=================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 24.98 |=============================================================== b . 25.35 |================================================================ c . 26.81 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Calculate Pi Benchmark Seconds < Lower Is Better a . 56.75 |==================================================================== b . 56.95 |==================================================================== c . 55.60 |================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.43 |===================================================================== b . 3.44 |===================================================================== c . 3.43 |===================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Group By Test Time Seconds < Lower Is Better a . 17.48 |==================================================================== b . 17.42 |==================================================================== c . 17.48 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Repartition Test Time Seconds < Lower Is Better a . 16.30 |==================================================================== b . 16.38 |==================================================================== c . 15.70 |================================================================= Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Inner Join Test Time Seconds < Lower Is Better a . 18.08 |=================================================================== b . 18.22 |==================================================================== c . 18.15 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 17.80 |==================================================================== b . 17.32 |================================================================== c . 17.20 |================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 1000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 8.70 |===================================================================== b . 8.64 |===================================================================== c . 8.65 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 1000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 55.96 |==================================================================== b . 54.80 |=================================================================== c . 55.10 |=================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 1000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.42 |=================================================================== b . 3.51 |===================================================================== c . 3.44 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 1000 - Group By Test Time Seconds < Lower Is Better a . 6.40 |===================================================================== b . 6.23 |=================================================================== c . 6.29 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 1000 - Repartition Test Time Seconds < Lower Is Better a . 4.87 |==================================================================== b . 4.97 |===================================================================== c . 4.88 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 1000 - Inner Join Test Time Seconds < Lower Is Better a . 5.58 |========================================================== b . 5.66 |=========================================================== c . 6.64 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 1000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 4.95 |=============================================================== b . 5.43 |===================================================================== c . 5.40 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 2000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 8.94 |=================================================================== b . 9.03 |==================================================================== c . 9.16 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 2000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 55.47 |=================================================================== b . 56.34 |==================================================================== c . 55.12 |=================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 2000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.37 |==================================================================== b . 3.40 |==================================================================== c . 3.43 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 2000 - Group By Test Time Seconds < Lower Is Better a . 6.72 |=================================================================== b . 6.81 |==================================================================== c . 6.90 |===================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 2000 - Repartition Test Time Seconds < Lower Is Better a . 5.61 |===================================================================== b . 5.28 |================================================================= c . 5.20 |================================================================ Apache Spark 3.3 Row Count: 10000000 - Partitions: 2000 - Inner Join Test Time Seconds < Lower Is Better a . 6.36 |=================================================================== b . 6.57 |===================================================================== c . 6.43 |==================================================================== Apache Spark 3.3 Row Count: 10000000 - Partitions: 2000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 6.09 |==================================================================== b . 6.10 |==================================================================== c . 6.16 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 1000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 14.52 |==================================================================== b . 14.51 |==================================================================== c . 14.16 |================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 1000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 57.36 |==================================================================== b . 54.98 |================================================================= c . 55.55 |================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 1000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.39 |===================================================================== b . 3.38 |===================================================================== c . 3.39 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 1000 - Group By Test Time Seconds < Lower Is Better a . 8.08 |==================================================================== b . 8.11 |==================================================================== c . 8.19 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 1000 - Repartition Test Time Seconds < Lower Is Better a . 8.33 |============================================================== b . 8.71 |================================================================= c . 9.27 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 1000 - Inner Join Test Time Seconds < Lower Is Better a . 9.93 |=============================================================== b . 10.70 |==================================================================== c . 9.79 |============================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 1000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 10.09 |==================================================================== b . 9.48 |================================================================ c . 9.32 |=============================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 2000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 15.97 |==================================================================== b . 14.29 |============================================================= c . 14.71 |=============================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 2000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 55.16 |=================================================================== b . 55.92 |=================================================================== c . 56.36 |==================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 2000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.41 |===================================================================== b . 3.36 |==================================================================== c . 3.41 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 2000 - Group By Test Time Seconds < Lower Is Better a . 9.01 |===================================================================== b . 8.84 |==================================================================== c . 8.76 |=================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 2000 - Repartition Test Time Seconds < Lower Is Better a . 9.28 |===================================================================== b . 8.97 |=================================================================== c . 9.26 |===================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 2000 - Inner Join Test Time Seconds < Lower Is Better a . 10.43 |=================================================================== b . 10.58 |==================================================================== c . 10.44 |=================================================================== Apache Spark 3.3 Row Count: 20000000 - Partitions: 2000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 10.28 |================================================================== b . 10.55 |==================================================================== c . 10.43 |=================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 1000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 26.04 |==================================================================== b . 25.88 |=================================================================== c . 26.23 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 1000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 55.60 |================================================================== b . 56.12 |=================================================================== c . 56.87 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 1000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.44 |===================================================================== b . 3.40 |==================================================================== c . 3.45 |===================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 1000 - Group By Test Time Seconds < Lower Is Better a . 17.85 |==================================================================== b . 17.73 |==================================================================== c . 17.65 |=================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 1000 - Repartition Test Time Seconds < Lower Is Better a . 15.62 |================================================================ b . 16.59 |==================================================================== c . 15.97 |================================================================= Apache Spark 3.3 Row Count: 40000000 - Partitions: 1000 - Inner Join Test Time Seconds < Lower Is Better a . 17.76 |================================================================= b . 17.79 |================================================================== c . 18.45 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 1000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 17.46 |=================================================================== b . 17.48 |=================================================================== c . 17.79 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 2000 - SHA-512 Benchmark Time Seconds < Lower Is Better a . 25.76 |================================================================== b . 26.38 |==================================================================== c . 25.98 |=================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 2000 - Calculate Pi Benchmark Seconds < Lower Is Better a . 56.78 |==================================================================== b . 55.25 |================================================================== c . 55.30 |================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 2000 - Calculate Pi Benchmark Using Dataframe Seconds < Lower Is Better a . 3.40 |===================================================================== b . 3.39 |===================================================================== c . 3.37 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 2000 - Group By Test Time Seconds < Lower Is Better a . 17.58 |==================================================================== b . 17.60 |==================================================================== c . 17.65 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 2000 - Repartition Test Time Seconds < Lower Is Better a . 16.17 |=================================================================== b . 16.06 |=================================================================== c . 16.38 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 2000 - Inner Join Test Time Seconds < Lower Is Better a . 19.04 |================================================================== b . 18.88 |================================================================== c . 19.51 |==================================================================== Apache Spark 3.3 Row Count: 40000000 - Partitions: 2000 - Broadcast Inner Join Test Time Seconds < Lower Is Better a . 18.23 |================================================================== b . 18.17 |================================================================== c . 18.81 |==================================================================== Memcached 1.6.18 Set To Get Ratio: 1:1 Ops/sec > Higher Is Better a . 1591288.82 |============================================================== b . 1602278.84 |=============================================================== c . 1614717.75 |=============================================================== Memcached 1.6.18 Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 3640442.11 |=============================================================== b . 3667823.02 |=============================================================== c . 3637603.67 |============================================================== Memcached 1.6.18 Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 3706097.76 |=============================================================== b . 3712642.45 |=============================================================== c . 3711642.32 |=============================================================== Memcached 1.6.18 Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 3226477.91 |=============================================================== b . 3238867.13 |=============================================================== c . 3212714.28 |============================================================== 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 . 25.28 |==================================================================== b . 24.90 |=================================================================== c . 25.26 |==================================================================== 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 . 632.27 |================================================================== b . 637.16 |=================================================================== c . 632.76 |=================================================================== 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 . 16.17 |==================================================================== b . 16.21 |==================================================================== c . 16.10 |==================================================================== 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 . 61.82 |==================================================================== b . 61.68 |==================================================================== c . 62.10 |==================================================================== 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 . 267.42 |=================================================================== b . 266.86 |=================================================================== c . 268.21 |=================================================================== 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 . 59.76 |==================================================================== b . 59.90 |==================================================================== c . 59.62 |==================================================================== 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 . 77.87 |==================================================================== b . 76.62 |=================================================================== c . 77.12 |=================================================================== 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 . 12.83 |=================================================================== b . 13.04 |==================================================================== c . 12.96 |==================================================================== 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 . 89.97 |==================================================================== b . 89.39 |==================================================================== c . 89.04 |=================================================================== 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 . 177.80 |================================================================== b . 178.96 |=================================================================== c . 179.64 |=================================================================== 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 . 29.71 |==================================================================== b . 28.69 |================================================================== c . 28.37 |================================================================= 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 . 33.65 |================================================================= b . 34.85 |=================================================================== c . 35.24 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 138.82 |=================================================================== b . 137.96 |=================================================================== c . 138.27 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 115.10 |=================================================================== b . 115.76 |=================================================================== c . 115.49 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 67.09 |==================================================================== b . 67.14 |==================================================================== c . 67.13 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 14.89 |==================================================================== b . 14.88 |==================================================================== c . 14.89 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 297.47 |================================================================== b . 299.12 |=================================================================== c . 299.93 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 53.76 |==================================================================== b . 53.47 |==================================================================== c . 53.30 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 134.77 |=================================================================== b . 133.89 |=================================================================== c . 132.28 |================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 7.4128 |================================================================== b . 7.4619 |================================================================== c . 7.5530 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 198.24 |=================================================================== b . 198.69 |=================================================================== c . 198.47 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 80.68 |==================================================================== b . 80.50 |==================================================================== c . 80.59 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 88.67 |==================================================================== b . 87.42 |=================================================================== c . 88.22 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 11.27 |=================================================================== b . 11.43 |==================================================================== c . 11.33 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 32.19 |=================================================================== b . 32.82 |==================================================================== c . 32.44 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 491.96 |=================================================================== b . 486.15 |================================================================== c . 492.94 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 21.31 |==================================================================== b . 21.45 |==================================================================== c . 21.40 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 46.92 |==================================================================== b . 46.61 |==================================================================== c . 46.73 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 100.48 |=================================================================== b . 100.69 |=================================================================== c . 100.60 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 159.21 |=================================================================== b . 158.87 |=================================================================== c . 159.01 |=================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 42.93 |================================================================ b . 45.29 |=================================================================== c . 45.64 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 23.29 |==================================================================== b . 22.07 |================================================================ c . 21.91 |================================================================ Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 25.32 |==================================================================== b . 24.87 |=================================================================== c . 25.31 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 630.03 |================================================================== b . 636.95 |=================================================================== c . 630.95 |================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 16.10 |=================================================================== b . 16.23 |==================================================================== c . 16.21 |==================================================================== Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 62.12 |==================================================================== b . 61.63 |=================================================================== c . 61.68 |==================================================================== CloudSuite Data Analytics 4.0 Hadoop Slaves: 1 ms < Lower Is Better a . 63396 |=================================================================== b . 62263 |================================================================== c . 64351 |==================================================================== CloudSuite Data Analytics 4.0 Hadoop Slaves: 4 ms < Lower Is Better a . 1282161 |================================================================== b . 1285523 |================================================================== c . 1290818 |================================================================== CloudSuite Data Analytics 4.0 Hadoop Slaves: 8 ms < Lower Is Better a . 1283837 |================================================================== b . 1276206 |================================================================== c . 1283805 |================================================================== CloudSuite Data Analytics 4.0 Hadoop Slaves: 32 ms < Lower Is Better a . 1286055 |================================================================== b . 1274682 |================================================================= c . 1277138 |================================================================== CloudSuite Data Analytics 4.0 Hadoop Slaves: 64 ms < Lower Is Better a . 1280792 |================================================================== b . 1283914 |================================================================== c . 1280550 |================================================================== CloudSuite Graph Analytics 4.0 GraphX Algorithm: Page Rank ms < Lower Is Better a . 11438 |=================================================================== b . 11307 |================================================================== c . 11584 |==================================================================== CloudSuite Graph Analytics 4.0 GraphX Algorithm: Triangle Count ms < Lower Is Better CloudSuite Graph Analytics 4.0 GraphX Algorithm: Connected Components ms < Lower Is Better a . 14338 |=============================================================== b . 15387 |==================================================================== c . 14198 |=============================================================== CloudSuite In-Memory Analytics 4.0 Training Set Size: Large ms < Lower Is Better a . 143356 |================================================================== b . 144863 |=================================================================== c . 143016 |================================================================== CloudSuite In-Memory Analytics 4.0 Training Set Size: Small ms < Lower Is Better a . 45941 |==================================================================== b . 45704 |==================================================================== c . 45505 |=================================================================== CloudSuite Web Serving Load Scale: 100 ops/sec > Higher Is Better a . 19.35 |=================================================================== b . 18.20 |=============================================================== c . 19.60 |==================================================================== CloudSuite Web Serving Load Scale: 400 ops/sec > Higher Is Better a . 37.15 |==================================================================== b . 37.02 |==================================================================== c . 37.05 |==================================================================== CloudSuite Web Serving Load Scale: 500 ops/sec > Higher Is Better a . 35.08 |=================================================================== b . 35.73 |==================================================================== c . 34.60 |================================================================== OpenEMS 0.0.35-86 Test: pyEMS Coupler MCells/s > Higher Is Better a . 19.86 |==================================================================== b . 19.60 |=================================================================== c . 19.88 |==================================================================== OpenEMS 0.0.35-86 Test: openEMS MSL_NotchFilter MCells/s > Higher Is Better a . 14.63 |==================================================================== b . 14.64 |==================================================================== c . 14.50 |=================================================================== RocksDB 7.9.2 Test: Random Fill Op/s > Higher Is Better a . 911640 |=================================================================== b . 896530 |================================================================== c . 911359 |=================================================================== RocksDB 7.9.2 Test: Random Read Op/s > Higher Is Better a . 131073357 |================================================================ b . 132034808 |================================================================ c . 131994679 |================================================================ RocksDB 7.9.2 Test: Update Random Op/s > Higher Is Better a . 788635 |=================================================================== b . 787714 |=================================================================== c . 786611 |=================================================================== RocksDB 7.9.2 Test: Sequential Fill Op/s > Higher Is Better a . 1030362 |================================================================== b . 1003634 |================================================================ c . 1035331 |================================================================== RocksDB 7.9.2 Test: Random Fill Sync Op/s > Higher Is Better a . 5559 |===================================================================== b . 3954 |================================================= c . 3996 |================================================== RocksDB 7.9.2 Test: Read While Writing Op/s > Higher Is Better a . 4696370 |================================================================== b . 4664918 |================================================================== c . 4696807 |================================================================== RocksDB 7.9.2 Test: Read Random Write Random Op/s > Higher Is Better a . 2763110 |================================================================== b . 2755551 |================================================================= c . 2776604 |==================================================================