EPYC 7763 Linux 5.16 2 x AMD EPYC 7763 64-Core testing with a AMD DAYTONA_X (RYM1001D BIOS) and ASPEED on Ubuntu 21.04 via the Phoronix Test Suite. v5.15: Processor: 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 21.04, Kernel: 5.15.0-051500-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080 v5.16-rc1: Processor: 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710 OS: Ubuntu 21.04, Kernel: 5.16.0-051600rc1-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080 OpenVKL 1.0 Benchmark: vklBenchmark ISPC Items / Sec > Higher Is Better v5.15 . 270 |================================================================== PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average Latency ms < Lower Is Better v5.15 ..... 21.90 |============================================================ v5.16-rc1 . 20.84 |========================================================= PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Write TPS > Higher Is Better v5.15 ..... 11770 |========================================================== v5.16-rc1 . 12213 |============================================================ PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average Latency ms < Lower Is Better v5.15 ..... 0.294 |============================================================ v5.16-rc1 . 0.291 |=========================================================== PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Only TPS > Higher Is Better v5.15 ..... 854179 |========================================================== v5.16-rc1 . 868463 |=========================================================== PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 500 - Mode: Read Only - Average Latency ms < Lower Is Better v5.15 ..... 0.750 |======================================================== v5.16-rc1 . 0.802 |============================================================ PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 500 - Mode: Read Only TPS > Higher Is Better v5.15 ..... 688739 |=========================================================== v5.16-rc1 . 634584 |====================================================== MariaDB 10.6.4 Clients: 512 Queries Per Second > Higher Is Better v5.15 ..... 384 |============================================================== v5.16-rc1 . 318 |=================================================== Redis Memtier / Redis Benchmark Test: LPUSH and LPOP: lpush Requests Per Second > Higher Is Better v5.15 ..... 256494.10 |======================================================= v5.16-rc1 . 259481.89 |======================================================== PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average Latency ms < Lower Is Better v5.15 ..... 49.13 |=========================================================== v5.16-rc1 . 49.90 |============================================================ PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 500 - Mode: Read Write TPS > Higher Is Better v5.15 ..... 10180 |============================================================ v5.16-rc1 . 10035 |=========================================================== ONNX Runtime 1.9.1 Model: fcn-resnet101-11 - Device: CPU Inferences Per Minute > Higher Is Better v5.15 ..... 221 |============================================================ v5.16-rc1 . 229 |============================================================== Redis Memtier / Redis Benchmark Test: LPUSH and LPOP: lpop Requests Per Second > Higher Is Better v5.15 ..... 245897.07 |======================================================== v5.16-rc1 . 246433.02 |======================================================== Apache HTTP Server 2.4.48 Concurrent Requests: 1000 Requests Per Second > Higher Is Better v5.15 ..... 103534.31 |======================================================== v5.16-rc1 . 86758.02 |=============================================== ONNX Runtime 1.9.1 Model: shufflenet-v2-10 - Device: CPU Inferences Per Minute > Higher Is Better v5.15 ..... 6010 |========================================================= v5.16-rc1 . 6414 |============================================================= Redis Memtier / Redis Benchmark Test: MIX Operations Per Second > Higher Is Better v5.15 ..... 170021.85 |======================================================== v5.16-rc1 . 132876.26 |============================================ Blender 2.92 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better v5.15 ..... 65.62 |============================================================ v5.16-rc1 . 64.94 |=========================================================== Redis Memtier / Redis Benchmark Test: SET Operations Per Second > Higher Is Better v5.15 ..... 129963.26 |================================================ v5.16-rc1 . 151238.19 |======================================================== Redis Memtier / Redis Benchmark Test: GET Operations Per Second > Higher Is Better v5.15 ..... 181292.77 |======================================================== v5.16-rc1 . 129984.45 |======================================== ONNX Runtime 1.9.1 Model: yolov4 - Device: CPU Inferences Per Minute > Higher Is Better v5.15 ..... 323 |============================================================== v5.16-rc1 . 311 |============================================================ ONNX Runtime 1.9.1 Model: super-resolution-10 - Device: CPU Inferences Per Minute > Higher Is Better v5.15 ..... 6455 |============================================================= v5.16-rc1 . 6435 |============================================================= Stress-NG 0.13.02 Test: IO_uring Bogo Ops/s > Higher Is Better v5.15 ..... 817842.40 |==================================================== v5.16-rc1 . 883063.47 |======================================================== Apache HTTP Server 2.4.48 Concurrent Requests: 500 Requests Per Second > Higher Is Better v5.15 ..... 88954.90 |======================================================= v5.16-rc1 . 91666.52 |========================================================= nginx 1.21.1 Concurrent Requests: 500 Requests Per Second > Higher Is Better v5.15 ..... 86598.63 |========================================================= v5.16-rc1 . 85215.55 |======================================================== nginx 1.21.1 Concurrent Requests: 1000 Requests Per Second > Higher Is Better v5.15 ..... 88466.50 |========================================================= v5.16-rc1 . 86415.68 |======================================================== Apache HTTP Server 2.4.48 Concurrent Requests: 200 Requests Per Second > Higher Is Better v5.15 ..... 98923.95 |================================================== v5.16-rc1 . 110374.97 |======================================================== nginx 1.21.1 Concurrent Requests: 200 Requests Per Second > Higher Is Better v5.15 ..... 81636.48 |========================================================= v5.16-rc1 . 78569.59 |======================================================= nginx 1.21.1 Concurrent Requests: 100 Requests Per Second > Higher Is Better v5.15 ..... 88818.81 |========================================================= v5.16-rc1 . 85642.56 |======================================================= Apache HTTP Server 2.4.48 Concurrent Requests: 100 Requests Per Second > Higher Is Better v5.15 ..... 72966.00 |================================================== v5.16-rc1 . 82904.30 |========================================================= NAS Parallel Benchmarks 3.4 Test / Class: EP.D Total Mop/s > Higher Is Better v5.15 ..... 10057.08 |======================================================== v5.16-rc1 . 10224.44 |========================================================= Timed Node.js Compilation 15.11 Time To Compile Seconds < Lower Is Better v5.15 ..... 71.78 |============================================================ v5.16-rc1 . 72.05 |============================================================ Timed Linux Kernel Compilation 5.14 Time To Compile Seconds < Lower Is Better v5.15 ..... 17.71 |============================================================ v5.16-rc1 . 17.62 |============================================================ Nginx Test: Short Connection - Connections: 1000 Requests Per Second > Higher Is Better v5.15 ..... 17134.48 |========================================================= v5.16-rc1 . 14199.34 |=============================================== Nginx Test: Long Connection - Connections: 500 Requests Per Second > Higher Is Better v5.15 ..... 186112.56 |======================================================== v5.16-rc1 . 181103.98 |====================================================== Nginx Test: Long Connection - Connections: 1000 Requests Per Second > Higher Is Better v5.15 ..... 170772.67 |======================================================== v5.16-rc1 . 170460.41 |======================================================== Nginx Test: Short Connection - Connections: 500 Requests Per Second > Higher Is Better v5.15 ..... 40631.10 |========================================================= v5.16-rc1 . 37294.57 |==================================================== Blender 2.92 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better v5.15 ..... 57.71 |============================================================ v5.16-rc1 . 57.70 |============================================================ Timed Godot Game Engine Compilation 3.2.3 Time To Compile Seconds < Lower Is Better v5.15 ..... 51.11 |========================================================== v5.16-rc1 . 52.72 |============================================================ rav1e 0.5 Speed: 1 Frames Per Second > Higher Is Better v5.15 ..... 0.424 |=========================================================== v5.16-rc1 . 0.432 |============================================================ rav1e 0.5 Speed: 5 Frames Per Second > Higher Is Better v5.15 ..... 1.727 |========================================================== v5.16-rc1 . 1.792 |============================================================ OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer FPS > Higher Is Better v5.15 ..... 12.05 |============================================================ v5.16-rc1 . 12.00 |============================================================ Stress-NG 0.13.02 Test: Socket Activity Bogo Ops/s > Higher Is Better v5.15 ..... 18156.28 |========================================================= v5.16-rc1 . 17168.85 |====================================================== NAS Parallel Benchmarks 3.4 Test / Class: IS.D Total Mop/s > Higher Is Better v5.15 ..... 4467.33 |========================================================== v5.16-rc1 . 4489.33 |========================================================== NAS Parallel Benchmarks 3.4 Test / Class: CG.C Total Mop/s > Higher Is Better v5.15 ..... 46917.02 |======================================================== v5.16-rc1 . 47403.85 |========================================================= Stress-NG 0.13.02 Test: NUMA Bogo Ops/s > Higher Is Better v5.15 ..... 110.30 |=========================================================== v5.16-rc1 . 99.98 |===================================================== Stress-NG 0.13.02 Test: Memory Copying Bogo Ops/s > Higher Is Better v5.15 ..... 10620.84 |======================================================== v5.16-rc1 . 10842.63 |========================================================= Stress-NG 0.13.02 Test: Context Switching Bogo Ops/s > Higher Is Better v5.15 ..... 4209840.78 |======================================================= v5.16-rc1 . 4230412.60 |======================================================= Stress-NG 0.13.02 Test: Malloc Bogo Ops/s > Higher Is Better v5.15 ..... 2910792259.49 |==================================================== v5.16-rc1 . 2898520832.35 |==================================================== Stress-NG 0.13.02 Test: Semaphores Bogo Ops/s > Higher Is Better v5.15 ..... 12428899.87 |====================================================== v5.16-rc1 . 12435829.84 |====================================================== Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better v5.15 ..... 69.81 |========================================================= v5.16-rc1 . 73.79 |============================================================ OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis FPS > Higher Is Better v5.15 ..... 125 |============================================================== v5.16-rc1 . 125 |============================================================== rav1e 0.5 Speed: 6 Frames Per Second > Higher Is Better v5.15 ..... 2.282 |=========================================================== v5.16-rc1 . 2.327 |============================================================ Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 Images / Sec > Higher Is Better v5.15 ..... 1.25 |============================================================= v5.16-rc1 . 1.24 |============================================================= rav1e 0.5 Speed: 10 Frames Per Second > Higher Is Better v5.15 ..... 5.277 |========================================================== v5.16-rc1 . 5.493 |============================================================ Timed Mesa Compilation 21.0 Time To Compile Seconds < Lower Is Better v5.15 ..... 16.84 |=========================================================== v5.16-rc1 . 17.02 |============================================================ NAS Parallel Benchmarks 3.4 Test / Class: SP.C Total Mop/s > Higher Is Better v5.15 ..... 116224.14 |======================================================== v5.16-rc1 . 114213.96 |======================================================= NAS Parallel Benchmarks 3.4 Test / Class: BT.C Total Mop/s > Higher Is Better v5.15 ..... 257895.76 |======================================================== v5.16-rc1 . 257584.03 |======================================================== Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 Images / Sec > Higher Is Better v5.15 ..... 2.53 |============================================================= v5.16-rc1 . 2.46 |=========================================================== NAS Parallel Benchmarks 3.4 Test / Class: LU.C Total Mop/s > Higher Is Better v5.15 ..... 286850.45 |======================================================= v5.16-rc1 . 292955.62 |======================================================== Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better v5.15 ..... 70.61 |============================================================ v5.16-rc1 . 68.34 |========================================================== OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer FPS > Higher Is Better v5.15 ..... 38.46 |============================================================ v5.16-rc1 . 38.46 |============================================================ NAS Parallel Benchmarks 3.4 Test / Class: FT.C Total Mop/s > Higher Is Better v5.15 ..... 117978.35 |======================================================= v5.16-rc1 . 119295.40 |======================================================== Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better v5.15 ..... 101.29 |=========================================================== v5.16-rc1 . 99.06 |========================================================== Embree 3.13 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better v5.15 ..... 110.86 |=========================================================== v5.16-rc1 . 108.55 |========================================================== NAS Parallel Benchmarks 3.4 Test / Class: SP.B Total Mop/s > Higher Is Better v5.15 ..... 149781.22 |======================================================== v5.16-rc1 . 149108.85 |======================================================== OSBench Test: Create Files us Per Event < Lower Is Better v5.15 ..... 16.30 |============================================================ v5.16-rc1 . 16.25 |============================================================ NAS Parallel Benchmarks 3.4 Test / Class: MG.C Total Mop/s > Higher Is Better v5.15 ..... 101908.99 |======================================================== v5.16-rc1 . 102006.15 |======================================================== OSBench Test: Memory Allocations Ns Per Event < Lower Is Better v5.15 ..... 72.83 |============================================================ v5.16-rc1 . 69.95 |========================================================== OSBench Test: Create Processes us Per Event < Lower Is Better v5.15 ..... 46.53 |==================================================== v5.16-rc1 . 53.59 |============================================================ OSBench Test: Create Threads us Per Event < Lower Is Better v5.15 ..... 27.28 |========================================================= v5.16-rc1 . 28.47 |============================================================ OSBench Test: Launch Programs us Per Event < Lower Is Better v5.15 ..... 61.08 |========================================================= v5.16-rc1 . 64.63 |============================================================ OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis FPS > Higher Is Better v5.15 ..... 166.67 |=========================================================== v5.16-rc1 . 166.67 |=========================================================== ctx_clock Context Switch Time Clocks < Lower Is Better v5.15 ..... 147 |============================================================== v5.16-rc1 . 147 |============================================================== Nginx Test: Short Connection - Connections: 100 Requests Per Second > Higher Is Better Nginx Test: Long Connection - Connections: 100 Requests Per Second > Higher Is Better OpenVKL 1.0 Benchmark: vklBenchmark Scalar Items / Sec > Higher Is Better