EPYC 7F72 Kernel Testing

AMD EPYC 7F72 24-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2009146-FI-EPYC7F72K42
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

AV1 3 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 16 Tests
Compression Tests 2 Tests
CPU Massive 35 Tests
Creator Workloads 18 Tests
Database Test Suite 7 Tests
Disk Test Suite 3 Tests
Encoding 6 Tests
Fortran Tests 2 Tests
Game Development 4 Tests
HPC - High Performance Computing 13 Tests
Imaging 5 Tests
Java 3 Tests
Common Kernel Benchmarks 12 Tests
Machine Learning 7 Tests
Molecular Dynamics 2 Tests
Multi-Core 22 Tests
Networking Test Suite 2 Tests
Node.js + NPM Tests 2 Tests
NVIDIA GPU Compute 4 Tests
OCR 2 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 10 Tests
Python 4 Tests
Renderers 2 Tests
Scientific Computing 4 Tests
Server 14 Tests
Server CPU Tests 25 Tests
Single-Threaded 8 Tests
Video Encoding 6 Tests
Common Workstation Benchmarks 6 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 5.9-rc4
September 10 2020
  23 Hours, 36 Minutes
Linux 5.9-rc4 + patch
September 11 2020
  1 Day, 14 Minutes
Linux 5.8
September 13 2020
  23 Hours, 9 Minutes
Invert Hiding All Results Option
  23 Hours, 39 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

EPYC 7F72 Kernel Testing AMD EPYC 7F72 24-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite. Linux 5.9-rc4: Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350 OS: Ubuntu 20.04, Kernel: 5.9.0-rc4-pts (x86_64) 20200910, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 Linux 5.9-rc4 + patch: Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Network: 2 x Intel I350 OS: Ubuntu 20.04, Kernel: 5.9.0-rc4-pts-patch (x86_64) 20200911, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768 Linux 5.8: Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Network: 2 x Intel I350 OS: Ubuntu 20.04, Kernel: 5.8.0-pts (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768 Apache Siege 2.4.29 Concurrent Users: 200 Transactions Per Second > Higher Is Better Linux 5.9-rc4 ......... 19552.82 |=============== Linux 5.9-rc4 + patch . 19590.51 |=============== Linux 5.8 ............. 57546.34 |============================================= Apache Siege 2.4.29 Concurrent Users: 100 Transactions Per Second > Higher Is Better Linux 5.9-rc4 ......... 20975.03 |============================ Linux 5.9-rc4 + patch . 20384.64 |=========================== Linux 5.8 ............. 33610.11 |============================================= Hackbench Count: 4 - Type: Process Seconds < Lower Is Better Linux 5.9-rc4 ......... 9.252 |================================================ Linux 5.9-rc4 + patch . 9.122 |=============================================== Linux 5.8 ............. 6.434 |================================= Apache Siege 2.4.29 Concurrent Users: 50 Transactions Per Second > Higher Is Better Linux 5.9-rc4 ......... 26919.66 |================================= Linux 5.9-rc4 + patch . 27677.37 |================================== Linux 5.8 ............. 36228.06 |============================================= Hackbench Count: 2 - Type: Process Seconds < Lower Is Better Linux 5.9-rc4 ......... 5.558 |================================================ Linux 5.9-rc4 + patch . 5.600 |================================================ Linux 5.8 ............. 4.321 |===================================== Hackbench Count: 2 - Type: Thread Seconds < Lower Is Better Linux 5.9-rc4 ......... 5.951 |================================================ Linux 5.9-rc4 + patch . 5.910 |================================================ Linux 5.8 ............. 4.670 |====================================== OSBench Test: Create Processes us Per Event < Lower Is Better Linux 5.9-rc4 ......... 49.75 |============================================= Linux 5.9-rc4 + patch . 53.49 |================================================ Linux 5.8 ............. 43.67 |======================================= Hackbench Count: 4 - Type: Thread Seconds < Lower Is Better Linux 5.9-rc4 ......... 9.550 |================================================ Linux 5.9-rc4 + patch . 9.523 |================================================ Linux 5.8 ............. 7.925 |======================================== Stress-NG 0.11.07 Test: MMAP Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 410.72 |=============================================== Linux 5.9-rc4 + patch . 403.89 |============================================== Linux 5.8 ............. 350.33 |======================================== Hackbench Count: 8 - Type: Process Seconds < Lower Is Better Linux 5.9-rc4 ......... 15.02 |================================================ Linux 5.9-rc4 + patch . 14.62 |=============================================== Linux 5.8 ............. 13.08 |========================================== Stress-NG 0.11.07 Test: Context Switching Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 10013372.56 |===================================== Linux 5.9-rc4 + patch . 11280975.34 |========================================== Linux 5.8 ............. 10450619.33 |======================================= Stress-NG 0.11.07 Test: Forking Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 57705.57 |======================================== Linux 5.9-rc4 + patch . 58452.66 |========================================= Linux 5.8 ............. 64896.91 |============================================= PyPerformance 1.0.0 Benchmark: python_startup Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 8.79 |================================================= Linux 5.9-rc4 + patch . 8.62 |================================================ Linux 5.8 ............. 7.82 |============================================ Hackbench Count: 8 - Type: Thread Seconds < Lower Is Better Linux 5.9-rc4 ......... 16.52 |================================================ Linux 5.9-rc4 + patch . 16.15 |=============================================== Linux 5.8 ............. 14.76 |=========================================== Stress-NG 0.11.07 Test: System V Message Passing Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 12519608.14 |====================================== Linux 5.9-rc4 + patch . 12462106.06 |====================================== Linux 5.8 ............. 13824575.94 |========================================== OSBench Test: Launch Programs us Per Event < Lower Is Better Linux 5.9-rc4 ......... 68.90 |================================================ Linux 5.9-rc4 + patch . 67.12 |=============================================== Linux 5.8 ............. 62.32 |=========================================== Stress-NG 0.11.07 Test: MEMFD Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 825.00 |=============================================== Linux 5.9-rc4 + patch . 824.32 |=============================================== Linux 5.8 ............. 748.43 |=========================================== Hackbench Count: 32 - Type: Process Seconds < Lower Is Better Linux 5.9-rc4 ......... 56.69 |================================================ Linux 5.9-rc4 + patch . 54.91 |============================================== Linux 5.8 ............. 51.59 |============================================ pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 50% us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.1200 |=============================================== Linux 5.9-rc4 + patch . 0.1103 |=========================================== Linux 5.8 ............. 0.1101 |=========================================== Memcached mcperf 1.6.0 Method: Append - Connections: 1 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 41729.0 |============================================ Linux 5.9-rc4 + patch . 43306.4 |============================================== Linux 5.8 ............. 39856.0 |========================================== pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 50% us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.1137 |============================================= Linux 5.9-rc4 + patch . 0.1089 |=========================================== Linux 5.8 ............. 0.1183 |=============================================== OSBench Test: Create Threads us Per Event < Lower Is Better Linux 5.9-rc4 ......... 22.45 |=============================================== Linux 5.9-rc4 + patch . 22.78 |================================================ Linux 5.8 ............. 21.00 |============================================ Memcached mcperf 1.6.0 Method: Add - Connections: 16 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 39677.1 |============================================= Linux 5.9-rc4 + patch . 40435.2 |============================================== Linux 5.8 ............. 37421.6 |=========================================== Memcached mcperf 1.6.0 Method: Append - Connections: 16 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 41622.6 |============================================= Linux 5.9-rc4 + patch . 42918.6 |============================================== Linux 5.8 ............. 40015.3 |=========================================== Memcached mcperf 1.6.0 Method: Set - Connections: 16 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 39836.5 |============================================= Linux 5.9-rc4 + patch . 40598.2 |============================================== Linux 5.8 ............. 37981.5 |=========================================== Memcached mcperf 1.6.0 Method: Prepend - Connections: 16 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 41932.0 |============================================= Linux 5.9-rc4 + patch . 42834.2 |============================================== Linux 5.8 ............. 40102.3 |=========================================== perf-bench Benchmark: Epoll Wait ops/sec > Higher Is Better Linux 5.9-rc4 ......... 10720 |============================================= Linux 5.9-rc4 + patch . 11440 |================================================ Linux 5.8 ............. 11138 |=============================================== Hackbench Count: 16 - Type: Process Seconds < Lower Is Better Linux 5.9-rc4 ......... 27.21 |================================================ Linux 5.9-rc4 + patch . 25.58 |============================================= Linux 5.8 ............. 27.27 |================================================ Memcached mcperf 1.6.0 Method: Prepend - Connections: 1 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 42450.5 |============================================== Linux 5.9-rc4 + patch . 42294.7 |============================================== Linux 5.8 ............. 39907.8 |=========================================== Memcached mcperf 1.6.0 Method: Replace - Connections: 16 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 41885.2 |============================================= Linux 5.9-rc4 + patch . 42390.3 |============================================== Linux 5.8 ............. 39855.4 |=========================================== Memcached mcperf 1.6.0 Method: Get - Connections: 16 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 60759.6 |============================================= Linux 5.9-rc4 + patch . 62084.5 |============================================== Linux 5.8 ............. 58492.5 |=========================================== Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1 Microseconds < Lower Is Better Linux 5.9-rc4 ......... 21.04 |================================================ Linux 5.9-rc4 + patch . 19.85 |============================================= Linux 5.8 ............. 20.93 |================================================ Java Gradle Build Gradle Build: Reactor Seconds < Lower Is Better Linux 5.9-rc4 ......... 333.13 |============================================== Linux 5.9-rc4 + patch . 337.87 |=============================================== Linux 5.8 ............. 318.95 |============================================ Memcached mcperf 1.6.0 Method: Replace - Connections: 1 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 40974.7 |============================================= Linux 5.9-rc4 + patch . 41621.8 |============================================== Linux 5.8 ............. 39296.6 |=========================================== Geekbench 5 Test: CPU Single Core - Gaussian Blur Mpixels/sec > Higher Is Better Linux 5.9-rc4 ......... 72.6 |================================================= Linux 5.9-rc4 + patch . 68.6 |============================================== Linux 5.8 ............. 72.0 |================================================= G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times Seconds < Lower Is Better Linux 5.9-rc4 ......... 22.98 |================================================ Linux 5.9-rc4 + patch . 21.72 |============================================= Linux 5.8 ............. 21.91 |============================================== Memcached mcperf 1.6.0 Method: Add - Connections: 1 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 39749.9 |============================================== Linux 5.9-rc4 + patch . 39085.7 |============================================= Linux 5.8 ............. 37569.4 |=========================================== Apache Cassandra 3.11.4 Test: Writes Op/s > Higher Is Better Linux 5.9-rc4 ......... 184151 |=============================================== Linux 5.9-rc4 + patch . 174367 |============================================= Linux 5.8 ............. 176581 |============================================= Memcached mcperf 1.6.0 Method: Set - Connections: 1 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 39138.5 |============================================= Linux 5.9-rc4 + patch . 40095.9 |============================================== Linux 5.8 ............. 38084.2 |============================================ ECP-CANDLE 0.3 Benchmark: P1B2 Seconds < Lower Is Better Linux 5.9-rc4 ......... 40.36 |=============================================== Linux 5.9-rc4 + patch . 39.09 |============================================== Linux 5.8 ............. 40.99 |================================================ PyPerformance 1.0.0 Benchmark: raytrace Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 517 |================================================== Linux 5.9-rc4 + patch . 495 |================================================ Linux 5.8 ............. 495 |================================================ Apache Benchmark 2.4.29 Static Web Page Serving Requests Per Second > Higher Is Better Linux 5.9-rc4 ......... 28386.73 |=========================================== Linux 5.9-rc4 + patch . 28553.85 |============================================ Linux 5.8 ............. 29495.14 |============================================= Memcached mcperf 1.6.0 Method: Delete - Connections: 1 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 60717.2 |============================================== Linux 5.9-rc4 + patch . 60980.7 |============================================== Linux 5.8 ............. 58784.8 |============================================ NGINX Benchmark 1.9.9 Static Web Page Serving Requests Per Second > Higher Is Better Linux 5.9-rc4 ......... 32458.44 |=========================================== Linux 5.9-rc4 + patch . 32866.12 |============================================ Linux 5.8 ............. 33656.47 |============================================= High Performance Conjugate Gradient 3.1 GFLOP/s > Higher Is Better Linux 5.9-rc4 ......... 17.05 |================================================ Linux 5.9-rc4 + patch . 16.58 |=============================================== Linux 5.8 ............. 16.45 |============================================== Geekbench 5 Test: CPU Multi Core Score > Higher Is Better Linux 5.9-rc4 ......... 25743 |================================================ Linux 5.9-rc4 + patch . 25586 |================================================ Linux 5.8 ............. 24851 |============================================== AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 0.30 |================================================= Linux 5.9-rc4 + patch . 0.29 |=============================================== Linux 5.8 ............. 0.29 |=============================================== AOM AV1 2.0 Encoder Mode: Speed 8 Realtime Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 32.26 |================================================ Linux 5.9-rc4 + patch . 31.60 |=============================================== Linux 5.8 ............. 31.23 |============================================== FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size Files/s > Higher Is Better Linux 5.9-rc4 ......... 886.9 |============================================== Linux 5.9-rc4 + patch . 895.4 |=============================================== Linux 5.8 ............. 916.0 |================================================ PyPerformance 1.0.0 Benchmark: float Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 128 |================================================== Linux 5.9-rc4 + patch . 124 |================================================ Linux 5.8 ............. 125 |================================================= Timed LLVM Compilation 10.0 Time To Compile Seconds < Lower Is Better Linux 5.9-rc4 ......... 283.24 |============================================== Linux 5.9-rc4 + patch . 291.53 |=============================================== Linux 5.8 ............. 282.64 |============================================== Compile Bench 0.6 Test: Initial Create MB/s > Higher Is Better Linux 5.9-rc4 ......... 585.65 |============================================== Linux 5.9-rc4 + patch . 587.33 |============================================== Linux 5.8 ............. 603.17 |=============================================== C-Blosc 2.0 Beta 5 Compressor: blosclz MB/s > Higher Is Better Linux 5.9-rc4 ......... 9682.3 |============================================== Linux 5.9-rc4 + patch . 9810.9 |=============================================== Linux 5.8 ............. 9529.0 |============================================== Schbench Message Threads: 2 - Workers Per Message Thread: 6 usec, 99.9th Latency Percentile < Lower Is Better Linux 5.9-rc4 ......... 34 |================================================== Linux 5.9-rc4 + patch . 34 |================================================== Linux 5.8 ............. 35 |=================================================== AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 3.52 |================================================= Linux 5.9-rc4 + patch . 3.42 |================================================ Linux 5.8 ............. 3.50 |================================================= iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 20 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 34617 |=============================================== Linux 5.9-rc4 + patch . 35326 |================================================ Linux 5.8 ............. 35608 |================================================ iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 32 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 31821 |================================================ Linux 5.9-rc4 + patch . 30970 |=============================================== Linux 5.8 ............. 30959 |=============================================== Rodinia 3.1 Test: OpenMP Leukocyte Seconds < Lower Is Better Linux 5.9-rc4 ......... 53.47 |=============================================== Linux 5.9-rc4 + patch . 54.95 |================================================ Linux 5.8 ............. 54.57 |================================================ FS-Mark 3.3 Test: 1000 Files, 1MB Size, No Sync/FSync Files/s > Higher Is Better Linux 5.9-rc4 ......... 2442.3 |============================================== Linux 5.9-rc4 + patch . 2424.6 |============================================== Linux 5.8 ............. 2490.7 |=============================================== Schbench Message Threads: 4 - Workers Per Message Thread: 8 usec, 99.9th Latency Percentile < Lower Is Better Linux 5.9-rc4 ......... 37 |================================================== Linux 5.9-rc4 + patch . 37 |================================================== Linux 5.8 ............. 38 |=================================================== Node.js Octane Benchmark Score > Higher Is Better Linux 5.9-rc4 ......... 41798 |================================================ Linux 5.9-rc4 + patch . 40728 |=============================================== Linux 5.8 ............. 41816 |================================================ AOM AV1 2.0 Encoder Mode: Speed 6 Realtime Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 18.69 |================================================ Linux 5.9-rc4 + patch . 18.21 |=============================================== Linux 5.8 ............. 18.32 |=============================================== PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Single Thread - Mode: Read Only TPS > Higher Is Better Linux 5.9-rc4 ......... 20409.59 |============================================ Linux 5.9-rc4 + patch . 20600.04 |============================================ Linux 5.8 ............. 20934.70 |============================================= DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap msec < Lower Is Better Linux 5.9-rc4 ......... 3677 |================================================= Linux 5.9-rc4 + patch . 3585 |================================================ Linux 5.8 ............. 3617 |================================================ Schbench Message Threads: 2 - Workers Per Message Thread: 8 usec, 99.9th Latency Percentile < Lower Is Better Linux 5.9-rc4 ......... 39 |================================================== Linux 5.9-rc4 + patch . 39 |================================================== Linux 5.8 ............. 40 |=================================================== Renaissance 0.10.0 Test: In-Memory Database Shootout ms < Lower Is Better Linux 5.9-rc4 ......... 5229.25 |============================================== Linux 5.9-rc4 + patch . 5214.59 |============================================== Linux 5.8 ............. 5098.66 |============================================= Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 16 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 157893.78 |============================================ Linux 5.9-rc4 + patch . 154016.44 |=========================================== Linux 5.8 ............. 157569.11 |============================================ Stress-NG 0.11.07 Test: Socket Activity Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 13647.40 |============================================ Linux 5.9-rc4 + patch . 13905.76 |============================================= Linux 5.8 ............. 13570.30 |============================================ perf-bench Benchmark: Sched Pipe ops/sec > Higher Is Better Linux 5.9-rc4 ......... 281265 |=============================================== Linux 5.9-rc4 + patch . 282779 |=============================================== Linux 5.8 ............. 276116 |============================================== pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 50% us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.1156 |=============================================== Linux 5.9-rc4 + patch . 0.1146 |=============================================== Linux 5.8 ............. 0.1129 |============================================== Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Seconds < Lower Is Better Linux 5.9-rc4 ......... 889.88 |=============================================== Linux 5.9-rc4 + patch . 876.25 |============================================== Linux 5.8 ............. 869.96 |============================================== Hackbench Count: 16 - Type: Thread Seconds < Lower Is Better Linux 5.9-rc4 ......... 30.85 |================================================ Linux 5.9-rc4 + patch . 30.53 |================================================ Linux 5.8 ............. 30.17 |=============================================== iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 32 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 34398 |=============================================== Linux 5.9-rc4 + patch . 34280 |=============================================== Linux 5.8 ............. 35056 |================================================ AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 2.26 |================================================= Linux 5.9-rc4 + patch . 2.21 |================================================ Linux 5.8 ............. 2.26 |================================================= perf-bench Benchmark: Memset 1MB GB/sec > Higher Is Better Linux 5.9-rc4 ......... 58.64 |=============================================== Linux 5.9-rc4 + patch . 59.92 |================================================ Linux 5.8 ............. 59.13 |=============================================== Schbench Message Threads: 4 - Workers Per Message Thread: 4 usec, 99.9th Latency Percentile < Lower Is Better Linux 5.9-rc4 ......... 46 |================================================== Linux 5.9-rc4 + patch . 47 |=================================================== Linux 5.8 ............. 46 |================================================== Stress-NG 0.11.07 Test: Memory Copying Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 12488.10 |============================================ Linux 5.9-rc4 + patch . 12753.86 |============================================= Linux 5.8 ............. 12739.56 |============================================= x264 2019-12-17 H.264 Video Encoding Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 174.85 |=============================================== Linux 5.9-rc4 + patch . 171.77 |============================================== Linux 5.8 ............. 171.25 |============================================== DaCapo Benchmark 9.12-MR1 Java Test: H2 msec < Lower Is Better Linux 5.9-rc4 ......... 4098 |================================================ Linux 5.9-rc4 + patch . 4184 |================================================= Linux 5.8 ............. 4138 |================================================ Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1 Connections/sec > Higher Is Better Linux 5.9-rc4 ......... 12697 |=============================================== Linux 5.9-rc4 + patch . 12800 |=============================================== Linux 5.8 ............. 12963 |================================================ FS-Mark 3.3 Test: 1000 Files, 1MB Size Files/s > Higher Is Better Linux 5.9-rc4 ......... 898.4 |=============================================== Linux 5.9-rc4 + patch . 917.2 |================================================ Linux 5.8 ............. 900.7 |=============================================== Stress-NG 0.11.07 Test: Malloc Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 507114594.73 |========================================= Linux 5.9-rc4 + patch . 501004926.05 |========================================= Linux 5.8 ............. 496833797.02 |======================================== Renaissance 0.10.0 Test: Akka Unbalanced Cobwebbed Tree ms < Lower Is Better Linux 5.9-rc4 ......... 14532.64 |============================================ Linux 5.9-rc4 + patch . 14690.06 |============================================= Linux 5.8 ............. 14829.73 |============================================= Compile Bench 0.6 Test: Compile MB/s > Higher Is Better Linux 5.9-rc4 ......... 1949.98 |============================================= Linux 5.9-rc4 + patch . 1950.71 |============================================= Linux 5.8 ............. 1988.91 |============================================== Memcached mcperf 1.6.0 Method: Delete - Connections: 16 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 59868.9 |============================================== Linux 5.9-rc4 + patch . 60526.0 |============================================== Linux 5.8 ............. 59368.2 |============================================= Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 16 Microseconds < Lower Is Better Linux 5.9-rc4 ......... 20.94 |================================================ Linux 5.9-rc4 + patch . 20.56 |=============================================== Linux 5.8 ............. 20.96 |================================================ MariaDB 10.5.2 Clients: 16 Queries Per Second > Higher Is Better Linux 5.9-rc4 ......... 6316 |================================================ Linux 5.9-rc4 + patch . 6343 |================================================ Linux 5.8 ............. 6438 |================================================= ECP-CANDLE 0.3 Benchmark: P3B1 Seconds < Lower Is Better Linux 5.9-rc4 ......... 614.69 |============================================== Linux 5.9-rc4 + patch . 622.25 |=============================================== Linux 5.8 ............. 626.31 |=============================================== Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better Linux 5.9-rc4 ......... 61.05 |=============================================== Linux 5.9-rc4 + patch . 61.97 |================================================ Linux 5.8 ............. 62.19 |================================================ AI Benchmark Alpha 0.1.2 Device Training Score Score > Higher Is Better Linux 5.9-rc4 ......... 1451 |================================================ Linux 5.9-rc4 + patch . 1478 |================================================= Linux 5.8 ............. 1456 |================================================ Renaissance 0.10.0 Test: Twitter HTTP Requests ms < Lower Is Better Linux 5.9-rc4 ......... 3405.96 |============================================= Linux 5.9-rc4 + patch . 3444.91 |============================================== Linux 5.8 ............. 3384.02 |============================================= DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans msec < Lower Is Better Linux 5.9-rc4 ......... 5302 |================================================= Linux 5.9-rc4 + patch . 5254 |================================================= Linux 5.8 ............. 5210 |================================================ Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better Linux 5.9-rc4 ......... 81.03 |================================================ Linux 5.9-rc4 + patch . 79.64 |=============================================== Linux 5.8 ............. 80.73 |================================================ PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Single Thread - Mode: Read Write TPS > Higher Is Better Linux 5.9-rc4 ......... 3064.15 |============================================= Linux 5.9-rc4 + patch . 3103.42 |============================================== Linux 5.8 ............. 3117.38 |============================================== Memcached mcperf 1.6.0 Method: Get - Connections: 1 Operations Per Second > Higher Is Better Linux 5.9-rc4 ......... 58072.3 |============================================= Linux 5.9-rc4 + patch . 58812.6 |============================================== Linux 5.8 ............. 59073.3 |============================================== Geekbench 5 Test: CPU Single Core Score > Higher Is Better Linux 5.9-rc4 ......... 1149 |================================================= Linux 5.9-rc4 + patch . 1130 |================================================ Linux 5.8 ............. 1148 |================================================= Himeno Benchmark 3.0 Poisson Pressure Solver MFLOPS > Higher Is Better Linux 5.9-rc4 ......... 4084.74 |============================================= Linux 5.9-rc4 + patch . 4150.82 |============================================== Linux 5.8 ............. 4126.67 |============================================== DaCapo Benchmark 9.12-MR1 Java Test: Jython msec < Lower Is Better Linux 5.9-rc4 ......... 4624 |================================================ Linux 5.9-rc4 + patch . 4624 |================================================ Linux 5.8 ............. 4698 |================================================= iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 1 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 37701 |================================================ Linux 5.9-rc4 + patch . 37672 |================================================ Linux 5.8 ............. 37121 |=============================================== pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Writes us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.0590 |============================================== Linux 5.9-rc4 + patch . 0.0594 |=============================================== Linux 5.8 ............. 0.0599 |=============================================== Stress-NG 0.11.07 Test: SENDFILE Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 387421.39 |============================================ Linux 5.9-rc4 + patch . 391202.84 |============================================ Linux 5.8 ............. 385334.22 |=========================================== Rodinia 3.1 Test: OpenMP Streamcluster Seconds < Lower Is Better Linux 5.9-rc4 ......... 14.36 |=============================================== Linux 5.9-rc4 + patch . 14.36 |=============================================== Linux 5.8 ............. 14.58 |================================================ Zstd Compression 1.4.5 Compression Level: 19 MB/s > Higher Is Better Linux 5.9-rc4 ......... 102.4 |================================================ Linux 5.9-rc4 + patch . 100.9 |=============================================== Linux 5.8 ............. 100.9 |=============================================== OSBench Test: Memory Allocations Ns Per Event < Lower Is Better Linux 5.9-rc4 ......... 104.05 |=============================================== Linux 5.9-rc4 + patch . 102.55 |============================================== Linux 5.8 ............. 102.89 |============================================== Timed Apache Compilation 2.4.41 Time To Compile Seconds < Lower Is Better Linux 5.9-rc4 ......... 23.30 |================================================ Linux 5.9-rc4 + patch . 23.37 |================================================ Linux 5.8 ............. 23.05 |=============================================== Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better Linux 5.9-rc4 ......... 28.90 |================================================ Linux 5.9-rc4 + patch . 28.64 |=============================================== Linux 5.8 ............. 29.03 |================================================ AI Benchmark Alpha 0.1.2 Device AI Score Score > Higher Is Better Linux 5.9-rc4 ......... 3325 |================================================ Linux 5.9-rc4 + patch . 3362 |================================================= Linux 5.8 ............. 3316 |================================================ OSBench Test: Create Files us Per Event < Lower Is Better Linux 5.9-rc4 ......... 14.88 |================================================ Linux 5.9-rc4 + patch . 14.94 |================================================ Linux 5.8 ............. 14.73 |=============================================== PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only TPS > Higher Is Better Linux 5.9-rc4 ......... 403854.03 |============================================ Linux 5.9-rc4 + patch . 402885.86 |=========================================== Linux 5.8 ............. 408399.06 |============================================ Stress-NG 0.11.07 Test: Semaphores Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 3456386.40 |=========================================== Linux 5.9-rc4 + patch . 3441381.21 |========================================== Linux 5.8 ............. 3487114.64 |=========================================== perf-bench Benchmark: Futex Lock-Pi ops/sec > Higher Is Better Linux 5.9-rc4 ......... 230 |================================================== Linux 5.9-rc4 + patch . 228 |================================================== Linux 5.8 ............. 227 |================================================= LeelaChessZero 0.26 Backend: Eigen Nodes Per Second > Higher Is Better Linux 5.9-rc4 ......... 2114 |================================================= Linux 5.9-rc4 + patch . 2114 |================================================= Linux 5.8 ............. 2087 |================================================ AI Benchmark Alpha 0.1.2 Device Inference Score Score > Higher Is Better Linux 5.9-rc4 ......... 1874 |================================================= Linux 5.9-rc4 + patch . 1884 |================================================= Linux 5.8 ............. 1860 |================================================ Renaissance 0.10.0 Test: Genetic Algorithm Using Jenetics + Futures ms < Lower Is Better Linux 5.9-rc4 ......... 1800.31 |============================================= Linux 5.9-rc4 + patch . 1815.12 |============================================== Linux 5.8 ............. 1823.49 |============================================== Stress-NG 0.11.07 Test: NUMA Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 578.19 |============================================== Linux 5.9-rc4 + patch . 585.61 |=============================================== Linux 5.8 ............. 579.32 |============================================== YafaRay 3.4.1 Total Time For Sample Scene Seconds < Lower Is Better Linux 5.9-rc4 ......... 90.18 |================================================ Linux 5.9-rc4 + patch . 89.91 |================================================ Linux 5.8 ............. 89.04 |=============================================== BRL-CAD 7.30.8 VGR Performance Metric VGR Performance Metric > Higher Is Better Linux 5.9-rc4 ......... 305706 |=============================================== Linux 5.9-rc4 + patch . 304906 |=============================================== Linux 5.8 ............. 301850 |============================================== Apache Siege 2.4.29 Concurrent Users: 10 Transactions Per Second > Higher Is Better Linux 5.9-rc4 ......... 20243.63 |============================================= Linux 5.9-rc4 + patch . 20149.13 |============================================ Linux 5.8 ............. 20398.99 |============================================= pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Writes us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.0586 |=============================================== Linux 5.9-rc4 + patch . 0.0579 |============================================== Linux 5.8 ............. 0.0586 |=============================================== PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU FPS > Higher Is Better Linux 5.9-rc4 ......... 24.00 |=============================================== Linux 5.9-rc4 + patch . 24.29 |================================================ Linux 5.8 ............. 24.21 |================================================ SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 369.70 |=============================================== Linux 5.9-rc4 + patch . 367.35 |=============================================== Linux 5.8 ............. 365.29 |============================================== Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better Linux 5.9-rc4 ......... 1.66 |================================================ Linux 5.9-rc4 + patch . 1.67 |================================================= Linux 5.8 ............. 1.68 |================================================= x265 3.1.2 H.265 1080p Video Encoding Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 60.67 |================================================ Linux 5.9-rc4 + patch . 60.70 |================================================ Linux 5.8 ............. 59.99 |=============================================== Geekbench 5 Test: CPU Single Core - Horizon Detection Gpixels/sec > Higher Is Better Linux 5.9-rc4 ......... 26.6 |================================================= Linux 5.9-rc4 + patch . 26.3 |================================================ Linux 5.8 ............. 26.5 |================================================= FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads Files/s > Higher Is Better Linux 5.9-rc4 ......... 1869.8 |=============================================== Linux 5.9-rc4 + patch . 1854.5 |============================================== Linux 5.8 ............. 1875.5 |=============================================== Renaissance 0.10.0 Test: Apache Spark ALS ms < Lower Is Better Linux 5.9-rc4 ......... 2108.75 |============================================= Linux 5.9-rc4 + patch . 2132.30 |============================================== Linux 5.8 ............. 2117.26 |============================================== SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 56.68 |================================================ Linux 5.9-rc4 + patch . 56.12 |================================================ Linux 5.8 ............. 56.06 |=============================================== TensorFlow Lite 2020-08-23 Model: NASNet Mobile Microseconds < Lower Is Better Linux 5.9-rc4 ......... 98874.3 |============================================== Linux 5.9-rc4 + patch . 98318.6 |============================================== Linux 5.8 ............. 97790.3 |============================================= PyPerformance 1.0.0 Benchmark: regex_compile Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 183 |================================================== Linux 5.9-rc4 + patch . 182 |================================================== Linux 5.8 ............. 181 |================================================= RawTherapee Total Benchmark Time Seconds < Lower Is Better Linux 5.9-rc4 ......... 50.54 |================================================ Linux 5.9-rc4 + patch . 50.42 |=============================================== Linux 5.8 ............. 50.97 |================================================ Build2 0.12 Time To Compile Seconds < Lower Is Better Linux 5.9-rc4 ......... 67.81 |=============================================== Linux 5.9-rc4 + patch . 68.55 |================================================ Linux 5.8 ............. 68.01 |================================================ PyPerformance 1.0.0 Benchmark: pathlib Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 18.6 |================================================= Linux 5.9-rc4 + patch . 18.4 |================================================ Linux 5.8 ............. 18.4 |================================================ Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 369.27 |=============================================== Linux 5.9-rc4 + patch . 369.43 |=============================================== Linux 5.8 ............. 365.52 |=============================================== MariaDB 10.5.2 Clients: 128 Queries Per Second > Higher Is Better Linux 5.9-rc4 ......... 565 |================================================== Linux 5.9-rc4 + patch . 561 |================================================= Linux 5.8 ............. 567 |================================================== Stress-NG 0.11.07 Test: Vector Math Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 199819.54 |============================================ Linux 5.9-rc4 + patch . 198393.34 |============================================ Linux 5.8 ............. 200464.43 |============================================ MariaDB 10.5.2 Clients: 64 Queries Per Second > Higher Is Better Linux 5.9-rc4 ......... 1256 |================================================= Linux 5.9-rc4 + patch . 1250 |================================================ Linux 5.8 ............. 1263 |================================================= Renaissance 0.10.0 Test: Random Forest ms < Lower Is Better Linux 5.9-rc4 ......... 1980.28 |============================================== Linux 5.9-rc4 + patch . 1966.52 |============================================== Linux 5.8 ............. 1959.97 |============================================== Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better Linux 5.9-rc4 ......... 39.42 |================================================ Linux 5.9-rc4 + patch . 39.02 |================================================ Linux 5.8 ............. 39.40 |================================================ Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better Linux 5.9-rc4 ......... 7.349 |================================================ Linux 5.9-rc4 + patch . 7.277 |================================================ Linux 5.8 ............. 7.308 |================================================ Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better Linux 5.9-rc4 ......... 14.99 |================================================ Linux 5.9-rc4 + patch . 14.84 |================================================ Linux 5.8 ............. 14.96 |================================================ librsvg Operation: SVG Files To PNG Seconds < Lower Is Better Linux 5.9-rc4 ......... 29.48 |================================================ Linux 5.9-rc4 + patch . 29.54 |================================================ Linux 5.8 ............. 29.26 |================================================ ECP-CANDLE 0.3 Benchmark: P3B2 Seconds < Lower Is Better Linux 5.9-rc4 ......... 863.38 |=============================================== Linux 5.9-rc4 + patch . 871.63 |=============================================== Linux 5.8 ............. 867.95 |=============================================== perf-bench Benchmark: Futex Hash ops/sec > Higher Is Better Linux 5.9-rc4 ......... 4481219 |============================================== Linux 5.9-rc4 + patch . 4524020 |============================================== Linux 5.8 ............. 4489484 |============================================== Geekbench 5 Test: CPU Single Core - Face Detection images/sec > Higher Is Better Linux 5.9-rc4 ......... 9.60 |================================================= Linux 5.9-rc4 + patch . 9.54 |================================================= Linux 5.8 ............. 9.51 |================================================= Rodinia 3.1 Test: OpenMP HotSpot3D Seconds < Lower Is Better Linux 5.9-rc4 ......... 97.48 |================================================ Linux 5.9-rc4 + patch . 96.59 |================================================ Linux 5.8 ............. 97.24 |================================================ Timed Linux Kernel Compilation 5.4 Time To Compile Seconds < Lower Is Better Linux 5.9-rc4 ......... 38.71 |================================================ Linux 5.9-rc4 + patch . 38.99 |================================================ Linux 5.8 ............. 38.63 |================================================ SQLite Speedtest 3.30 Timed Time - Size 1,000 Seconds < Lower Is Better Linux 5.9-rc4 ......... 72.17 |================================================ Linux 5.9-rc4 + patch . 71.94 |================================================ Linux 5.8 ............. 72.59 |================================================ PyPerformance 1.0.0 Benchmark: 2to3 Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 348 |================================================== Linux 5.9-rc4 + patch . 346 |================================================== Linux 5.8 ............. 345 |================================================== pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Writes us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.0577 |=============================================== Linux 5.9-rc4 + patch . 0.0582 |=============================================== Linux 5.8 ............. 0.0582 |=============================================== libavif avifenc 0.7.3 Encoder Speed: 8 Seconds < Lower Is Better Linux 5.9-rc4 ......... 5.548 |================================================ Linux 5.9-rc4 + patch . 5.554 |================================================ Linux 5.8 ............. 5.596 |================================================ Ethr 2019-01-02 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 100940.67 |============================================ Linux 5.9-rc4 + patch . 101621.00 |============================================ Linux 5.8 ............. 100755.11 |============================================ PyPerformance 1.0.0 Benchmark: crypto_pyaes Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 118 |================================================== Linux 5.9-rc4 + patch . 118 |================================================== Linux 5.8 ............. 117 |================================================== PyPerformance 1.0.0 Benchmark: nbody Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 118 |================================================== Linux 5.9-rc4 + patch . 119 |================================================== Linux 5.8 ............. 118 |================================================== PyPerformance 1.0.0 Benchmark: chaos Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 120 |================================================== Linux 5.9-rc4 + patch . 119 |================================================== Linux 5.8 ............. 119 |================================================== Intel Open Image Denoise 1.2.0 Scene: Memorial Images / Sec > Higher Is Better Linux 5.9-rc4 ......... 18.28 |================================================ Linux 5.9-rc4 + patch . 18.35 |================================================ Linux 5.8 ............. 18.43 |================================================ PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU FPS > Higher Is Better Linux 5.9-rc4 ......... 654.03 |=============================================== Linux 5.9-rc4 + patch . 650.52 |=============================================== Linux 5.8 ............. 648.79 |=============================================== Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 16 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 2758.07 |============================================== Linux 5.9-rc4 + patch . 2737.02 |============================================== Linux 5.8 ............. 2736.14 |============================================== libavif avifenc 0.7.3 Encoder Speed: 10 Seconds < Lower Is Better Linux 5.9-rc4 ......... 5.413 |================================================ Linux 5.9-rc4 + patch . 5.427 |================================================ Linux 5.8 ............. 5.456 |================================================ Rodinia 3.1 Test: OpenMP LavaMD Seconds < Lower Is Better Linux 5.9-rc4 ......... 99.15 |================================================ Linux 5.9-rc4 + patch . 99.01 |================================================ Linux 5.8 ............. 98.37 |================================================ libavif avifenc 0.7.3 Encoder Speed: 0 Seconds < Lower Is Better Linux 5.9-rc4 ......... 62.08 |================================================ Linux 5.9-rc4 + patch . 62.51 |================================================ Linux 5.8 ............. 62.57 |================================================ PyPerformance 1.0.0 Benchmark: django_template Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 51.3 |================================================= Linux 5.9-rc4 + patch . 51.7 |================================================= Linux 5.8 ............. 51.7 |================================================= PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write TPS > Higher Is Better Linux 5.9-rc4 ......... 31955.15 |============================================= Linux 5.9-rc4 + patch . 31943.59 |============================================= Linux 5.8 ............. 32192.64 |============================================= Geekbench 5 Test: CPU Multi Core - Gaussian Blur Mpixels/sec > Higher Is Better Linux 5.9-rc4 ......... 1.30 |================================================= Linux 5.9-rc4 + patch . 1.29 |================================================= Linux 5.8 ............. 1.29 |================================================= SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 6.731 |================================================ Linux 5.9-rc4 + patch . 6.718 |================================================ Linux 5.8 ............. 6.680 |================================================ libavif avifenc 0.7.3 Encoder Speed: 2 Seconds < Lower Is Better Linux 5.9-rc4 ......... 37.90 |================================================ Linux 5.9-rc4 + patch . 37.62 |================================================ Linux 5.8 ............. 37.76 |================================================ PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU FPS > Higher Is Better Linux 5.9-rc4 ......... 29.67 |================================================ Linux 5.9-rc4 + patch . 29.45 |================================================ Linux 5.8 ............. 29.57 |================================================ Renaissance 0.10.0 Test: Apache Spark PageRank ms < Lower Is Better Linux 5.9-rc4 ......... 3683.32 |============================================== Linux 5.9-rc4 + patch . 3666.59 |============================================== Linux 5.8 ............. 3656.01 |============================================== Compile Bench 0.6 Test: Read Compiled Tree MB/s > Higher Is Better Linux 5.9-rc4 ......... 3023.05 |============================================== Linux 5.9-rc4 + patch . 3000.73 |============================================== Linux 5.8 ............. 3023.05 |============================================== Geekbench 5 Test: CPU Multi Core - Face Detection images/sec > Higher Is Better Linux 5.9-rc4 ......... 231.5 |================================================ Linux 5.9-rc4 + patch . 232.5 |================================================ Linux 5.8 ............. 233.2 |================================================ OCRMyPDF 9.6.0+dfsg Processing 60 Page PDF Document Seconds < Lower Is Better Linux 5.9-rc4 ......... 18.88 |================================================ Linux 5.9-rc4 + patch . 19.02 |================================================ Linux 5.8 ............. 18.95 |================================================ Blender 2.90 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better Linux 5.9-rc4 ......... 86.98 |================================================ Linux 5.9-rc4 + patch . 86.49 |================================================ Linux 5.8 ............. 86.35 |================================================ G'MIC Test: 2D Function Plotting, 1000 Times Seconds < Lower Is Better Linux 5.9-rc4 ......... 187.64 |=============================================== Linux 5.9-rc4 + patch . 187.46 |=============================================== Linux 5.8 ............. 186.29 |=============================================== Blender 2.90 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better Linux 5.9-rc4 ......... 214.42 |=============================================== Linux 5.9-rc4 + patch . 214.17 |=============================================== Linux 5.8 ............. 215.71 |=============================================== OpenVKL 0.9 Benchmark: vklBenchmark Items / Sec > Higher Is Better Linux 5.9-rc4 ......... 290.20 |=============================================== Linux 5.9-rc4 + patch . 290.65 |=============================================== Linux 5.8 ............. 292.28 |=============================================== Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better Linux 5.9-rc4 ......... 24.70 |================================================ Linux 5.9-rc4 + patch . 24.73 |================================================ Linux 5.8 ............. 24.56 |================================================ PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU FPS > Higher Is Better Linux 5.9-rc4 ......... 13.57 |================================================ Linux 5.9-rc4 + patch . 13.53 |================================================ Linux 5.8 ............. 13.48 |================================================ Hugin Panorama Photo Assistant + Stitching Time Seconds < Lower Is Better Linux 5.9-rc4 ......... 50.69 |================================================ Linux 5.9-rc4 + patch . 50.95 |================================================ Linux 5.8 ............. 50.62 |================================================ G'MIC Test: 3D Elevated Function In Random Colors, 100 Times Seconds < Lower Is Better Linux 5.9-rc4 ......... 96.43 |================================================ Linux 5.9-rc4 + patch . 95.83 |================================================ Linux 5.8 ............. 95.81 |================================================ PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU FPS > Higher Is Better Linux 5.9-rc4 ......... 3.13 |================================================= Linux 5.9-rc4 + patch . 3.15 |================================================= Linux 5.8 ............. 3.13 |================================================= Blender 2.90 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better Linux 5.9-rc4 ......... 67.28 |================================================ Linux 5.9-rc4 + patch . 66.87 |================================================ Linux 5.8 ............. 67.01 |================================================ CP2K Molecular Dynamics 6.1 Fayalite-FIST Data Seconds < Lower Is Better Linux 5.9-rc4 ......... 533.88 |=============================================== Linux 5.9-rc4 + patch . 536.98 |=============================================== Linux 5.8 ............. 537.09 |=============================================== Coremark 1.0 CoreMark Size 666 - Iterations Per Second Iterations/Sec > Higher Is Better Linux 5.9-rc4 ......... 993262.70 |============================================ Linux 5.9-rc4 + patch . 993613.53 |============================================ Linux 5.8 ............. 999077.15 |============================================ PyBench 2018-02-16 Total For Average Test Times Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 1068 |================================================= Linux 5.9-rc4 + patch . 1064 |================================================= Linux 5.8 ............. 1062 |================================================= Renaissance 0.10.0 Test: Scala Dotty ms < Lower Is Better Linux 5.9-rc4 ......... 1655.73 |============================================== Linux 5.9-rc4 + patch . 1658.82 |============================================== Linux 5.8 ............. 1649.87 |============================================== SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 285.77 |=============================================== Linux 5.9-rc4 + patch . 284.30 |=============================================== Linux 5.8 ............. 285.09 |=============================================== Stress-NG 0.11.07 Test: CPU Stress Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 8853.55 |============================================== Linux 5.9-rc4 + patch . 8880.22 |============================================== Linux 5.8 ............. 8898.87 |============================================== Git Time To Complete Common Git Commands Seconds < Lower Is Better Linux 5.9-rc4 ......... 54.99 |================================================ Linux 5.9-rc4 + patch . 55.27 |================================================ Linux 5.8 ............. 55.08 |================================================ SQLite 3.30.1 Threads / Copies: 8 Seconds < Lower Is Better Linux 5.9-rc4 ......... 4.619 |================================================ Linux 5.9-rc4 + patch . 4.639 |================================================ Linux 5.8 ............. 4.616 |================================================ MariaDB 10.5.2 Clients: 32 Queries Per Second > Higher Is Better Linux 5.9-rc4 ......... 2849 |================================================= Linux 5.9-rc4 + patch . 2846 |================================================= Linux 5.8 ............. 2860 |================================================= Rodinia 3.1 Test: OpenMP CFD Solver Seconds < Lower Is Better Linux 5.9-rc4 ......... 10.60 |================================================ Linux 5.9-rc4 + patch . 10.63 |================================================ Linux 5.8 ............. 10.64 |================================================ pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Reads us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.0446 |=============================================== Linux 5.9-rc4 + patch . 0.0447 |=============================================== Linux 5.8 ............. 0.0445 |=============================================== Blender 2.90 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better Linux 5.9-rc4 ......... 196.64 |=============================================== Linux 5.9-rc4 + patch . 196.27 |=============================================== Linux 5.8 ............. 197.15 |=============================================== MariaDB 10.5.2 Clients: 512 Queries Per Second > Higher Is Better Linux 5.9-rc4 ......... 467 |================================================== Linux 5.9-rc4 + patch . 467 |================================================== Linux 5.8 ............. 469 |================================================== TensorFlow Lite 2020-08-23 Model: Inception V4 Microseconds < Lower Is Better Linux 5.9-rc4 ......... 1315513 |============================================== Linux 5.9-rc4 + patch . 1310450 |============================================== Linux 5.8 ............. 1310057 |============================================== PHPBench 0.8.1 PHP Benchmark Suite Score > Higher Is Better Linux 5.9-rc4 ......... 573649 |=============================================== Linux 5.9-rc4 + patch . 575978 |=============================================== Linux 5.8 ............. 575324 |=============================================== Tesseract OCR 4.1.1 Time To OCR 7 Images Seconds < Lower Is Better Linux 5.9-rc4 ......... 28.74 |================================================ Linux 5.9-rc4 + patch . 28.86 |================================================ Linux 5.8 ............. 28.86 |================================================ perf-bench Benchmark: Syscall Basic ops/sec > Higher Is Better Linux 5.9-rc4 ......... 17262967 |============================================= Linux 5.9-rc4 + patch . 17307552 |============================================= Linux 5.8 ............. 17238058 |============================================= PyPerformance 1.0.0 Benchmark: pickle_pure_python Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 499 |================================================== Linux 5.9-rc4 + patch . 499 |================================================== Linux 5.8 ............. 501 |================================================== LeelaChessZero 0.26 Backend: BLAS Nodes Per Second > Higher Is Better Linux 5.9-rc4 ......... 2255 |================================================= Linux 5.9-rc4 + patch . 2246 |================================================= Linux 5.8 ............. 2248 |================================================= PyPerformance 1.0.0 Benchmark: json_loads Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 26.2 |================================================= Linux 5.9-rc4 + patch . 26.3 |================================================= Linux 5.8 ............. 26.3 |================================================= PyPerformance 1.0.0 Benchmark: go Milliseconds < Lower Is Better Linux 5.9-rc4 ......... 263 |================================================== Linux 5.9-rc4 + patch . 263 |================================================== Linux 5.8 ............. 262 |================================================== TensorFlow Lite 2020-08-23 Model: SqueezeNet Microseconds < Lower Is Better Linux 5.9-rc4 ......... 87232.2 |============================================== Linux 5.9-rc4 + patch . 87168.0 |============================================== Linux 5.8 ............. 86930.6 |============================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Microseconds < Lower Is Better Linux 5.9-rc4 ......... 58870.8 |============================================== Linux 5.9-rc4 + patch . 58877.5 |============================================== Linux 5.8 ............. 58686.1 |============================================== ASTC Encoder 2.0 Preset: Medium Seconds < Lower Is Better Linux 5.9-rc4 ......... 6.71 |================================================= Linux 5.9-rc4 + patch . 6.69 |================================================= Linux 5.8 ............. 6.71 |================================================= pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 50% us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.1007 |=============================================== Linux 5.9-rc4 + patch . 0.1009 |=============================================== Linux 5.8 ............. 0.1010 |=============================================== ASTC Encoder 2.0 Preset: Thorough Seconds < Lower Is Better Linux 5.9-rc4 ......... 10.48 |================================================ Linux 5.9-rc4 + patch . 10.46 |================================================ Linux 5.8 ............. 10.45 |================================================ Blender 2.90 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better Linux 5.9-rc4 ......... 284.71 |=============================================== Linux 5.9-rc4 + patch . 285.02 |=============================================== Linux 5.8 ............. 284.21 |=============================================== Zstd Compression 1.4.5 Compression Level: 3 MB/s > Higher Is Better Linux 5.9-rc4 ......... 8384.5 |=============================================== Linux 5.9-rc4 + patch . 8383.1 |=============================================== Linux 5.8 ............. 8361.7 |=============================================== TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Microseconds < Lower Is Better Linux 5.9-rc4 ......... 1146990 |============================================== Linux 5.9-rc4 + patch . 1149627 |============================================== Linux 5.8 ............. 1146897 |============================================== pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Reads us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.0446 |=============================================== Linux 5.9-rc4 + patch . 0.0446 |=============================================== Linux 5.8 ............. 0.0445 |=============================================== pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Reads us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.0446 |=============================================== Linux 5.9-rc4 + patch . 0.0445 |=============================================== Linux 5.8 ............. 0.0446 |=============================================== pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Reads us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.0447 |=============================================== Linux 5.9-rc4 + patch . 0.0448 |=============================================== Linux 5.8 ............. 0.0447 |=============================================== MariaDB 10.5.2 Clients: 256 Queries Per Second > Higher Is Better Linux 5.9-rc4 ......... 470 |================================================== Linux 5.9-rc4 + patch . 471 |================================================== Linux 5.8 ............. 471 |================================================== perf-bench Benchmark: Memcpy 1MB GB/sec > Higher Is Better Linux 5.9-rc4 ......... 9.232573 |============================================= Linux 5.9-rc4 + patch . 9.214093 |============================================= Linux 5.8 ............. 9.226524 |============================================= PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU FPS > Higher Is Better Linux 5.9-rc4 ......... 10.41 |================================================ Linux 5.9-rc4 + patch . 10.42 |================================================ Linux 5.8 ............. 10.43 |================================================ Stress-NG 0.11.07 Test: Crypto Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 6306.14 |============================================== Linux 5.9-rc4 + patch . 6305.67 |============================================== Linux 5.8 ............. 6317.76 |============================================== ASTC Encoder 2.0 Preset: Fast Seconds < Lower Is Better Linux 5.9-rc4 ......... 5.42 |================================================= Linux 5.9-rc4 + patch . 5.43 |================================================= Linux 5.8 ............. 5.42 |================================================= pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Writes us - Average Page Latency < Lower Is Better Linux 5.9-rc4 ......... 0.0543 |=============================================== Linux 5.9-rc4 + patch . 0.0544 |=============================================== Linux 5.8 ............. 0.0544 |=============================================== Stress-NG 0.11.07 Test: Matrix Math Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 101892.21 |============================================ Linux 5.9-rc4 + patch . 102008.94 |============================================ Linux 5.8 ............. 101825.56 |============================================ PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU FPS > Higher Is Better Linux 5.9-rc4 ......... 5.75 |================================================= Linux 5.9-rc4 + patch . 5.76 |================================================= Linux 5.8 ............. 5.76 |================================================= ASTC Encoder 2.0 Preset: Exhaustive Seconds < Lower Is Better Linux 5.9-rc4 ......... 81.12 |================================================ Linux 5.9-rc4 + patch . 81.05 |================================================ Linux 5.8 ............. 80.99 |================================================ OpenSSL 1.1.1 RSA 4096-bit Performance Signs Per Second > Higher Is Better Linux 5.9-rc4 ......... 6339.1 |=============================================== Linux 5.9-rc4 + patch . 6349.1 |=============================================== Linux 5.8 ............. 6339.1 |=============================================== TensorFlow Lite 2020-08-23 Model: Mobilenet Float Microseconds < Lower Is Better Linux 5.9-rc4 ......... 58012.2 |============================================== Linux 5.9-rc4 + patch . 57955.4 |============================================== Linux 5.8 ............. 57927.7 |============================================== KeyDB 5.3.1 Ops/sec > Higher Is Better Linux 5.9-rc4 ......... 407410.68 |============================================ Linux 5.9-rc4 + patch . 407892.70 |============================================ Linux 5.8 ............. 407304.60 |============================================ Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 1 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 900.40 |=============================================== Linux 5.9-rc4 + patch . 901.47 |=============================================== Linux 5.8 ............. 900.88 |=============================================== Stress-NG 0.11.07 Test: Atomic Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 365322.27 |============================================ Linux 5.9-rc4 + patch . 364924.54 |============================================ Linux 5.8 ............. 365355.88 |============================================ Geekbench 5 Test: CPU Multi Core - Horizon Detection Gpixels/sec > Higher Is Better Linux 5.9-rc4 ......... 689.0 |================================================ Linux 5.9-rc4 + patch . 689.3 |================================================ Linux 5.8 ............. 688.9 |================================================ Nebular Empirical Analysis Tool 2020-02-29 Seconds < Lower Is Better Linux 5.9-rc4 ......... 16.28 |================================================ Linux 5.9-rc4 + patch . 16.28 |================================================ Linux 5.8 ............. 16.28 |================================================ NAMD 2.14 ATPase Simulation - 327,506 Atoms days/ns < Lower Is Better Linux 5.9-rc4 ......... 0.85790 |============================================== Linux 5.9-rc4 + patch . 0.85795 |============================================== Linux 5.8 ............. 0.85800 |============================================== PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: CPU FPS > Higher Is Better Linux 5.9-rc4 ......... 1.1 |================================================== Linux 5.9-rc4 + patch . 1.1 |================================================== Linux 5.8 ............. 1.1 |================================================== iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 32 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 33.6 |================================================= Linux 5.9-rc4 + patch . 33.6 |================================================= Linux 5.8 ............. 33.6 |================================================= iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 20 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 21 |=================================================== Linux 5.9-rc4 + patch . 21 |=================================================== Linux 5.8 ............. 21 |=================================================== iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 1 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 1.05 |================================================= Linux 5.9-rc4 + patch . 1.05 |================================================= Linux 5.8 ............. 1.05 |================================================= iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 20 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 19999 |================================================ Linux 5.9-rc4 + patch . 19999 |================================================ Linux 5.8 ............. 19999 |================================================ iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 32 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 3200 |================================================= Linux 5.9-rc4 + patch . 3200 |================================================= Linux 5.8 ............. 3200 |================================================= iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 20 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 2000 |================================================= Linux 5.9-rc4 + patch . 2000 |================================================= Linux 5.8 ............. 2000 |================================================= iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 1 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 1000 |================================================= Linux 5.9-rc4 + patch . 1000 |================================================= Linux 5.8 ............. 1000 |================================================= iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 1 Mbits/sec > Higher Is Better Linux 5.9-rc4 ......... 100 |================================================== Linux 5.9-rc4 + patch . 100 |================================================== Linux 5.8 ............. 100 |================================================== Schbench Message Threads: 4 - Workers Per Message Thread: 6 usec, 99.9th Latency Percentile < Lower Is Better Linux 5.9-rc4 ......... 41 |================================================= Linux 5.9-rc4 + patch . 41 |================================================= Linux 5.8 ............. 43 |=================================================== Schbench Message Threads: 4 - Workers Per Message Thread: 2 usec, 99.9th Latency Percentile < Lower Is Better Linux 5.9-rc4 ......... 25 |=================================================== Linux 5.9-rc4 + patch . 23 |=============================================== Linux 5.8 ............. 25 |=================================================== Schbench Message Threads: 2 - Workers Per Message Thread: 4 usec, 99.9th Latency Percentile < Lower Is Better Linux 5.9-rc4 ......... 29 |============================================ Linux 5.9-rc4 + patch . 34 |=================================================== Linux 5.8 ............. 30 |============================================= Schbench Message Threads: 2 - Workers Per Message Thread: 2 usec, 99.9th Latency Percentile < Lower Is Better Linux 5.9-rc4 ......... 27 |=================================================== Linux 5.9-rc4 + patch . 26 |================================================= Linux 5.8 ............. 25 |=============================================== Apache Siege 2.4.29 Concurrent Users: 250 Transactions Per Second > Higher Is Better Linux 5.9-rc4 ......... 19657.26 |=============== Linux 5.9-rc4 + patch . 19731.42 |=============== Linux 5.8 ............. 59490.65 |============================================= Apache Siege 2.4.29 Concurrent Users: 1 Transactions Per Second > Higher Is Better Linux 5.9-rc4 ......... 6789.89 |======================================= Linux 5.9-rc4 + patch . 6918.14 |======================================== Linux 5.8 ............. 7912.29 |============================================== Apache Cassandra 3.11.4 Test: Reads Op/s > Higher Is Better Linux 5.9-rc4 ......... 1008 |================================================= Linux 5.9-rc4 + patch . 730 |=================================== Linux 5.8 ............. 572 |============================ Stress-NG 0.11.07 Test: Glibc C String Functions Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 3436106.84 |=========================================== Linux 5.9-rc4 + patch . 3322250.21 |========================================== Linux 5.8 ............. 3354956.81 |========================================== Stress-NG 0.11.07 Test: CPU Cache Bogo Ops/s > Higher Is Better Linux 5.9-rc4 ......... 53.87 |================================================ Linux 5.9-rc4 + patch . 52.17 |============================================== Linux 5.8 ............. 51.95 |============================================== Redis 5.0.5 Test: SET Requests Per Second > Higher Is Better Linux 5.9-rc4 ......... 1444961.84 |======================================= Linux 5.9-rc4 + patch . 1505075.70 |======================================== Linux 5.8 ............. 1600412.63 |=========================================== Redis 5.0.5 Test: GET Requests Per Second > Higher Is Better Linux 5.9-rc4 ......... 1768092.33 |====================================== Linux 5.9-rc4 + patch . 1750558.62 |====================================== Linux 5.8 ............. 1996950.61 |=========================================== Redis 5.0.5 Test: LPUSH Requests Per Second > Higher Is Better Linux 5.9-rc4 ......... 1218625.21 |======================================= Linux 5.9-rc4 + patch . 1231050.56 |======================================= Linux 5.8 ............. 1353713.40 |=========================================== Redis 5.0.5 Test: SADD Requests Per Second > Higher Is Better Linux 5.9-rc4 ......... 1620429.83 |====================================== Linux 5.9-rc4 + patch . 1612914.46 |====================================== Linux 5.8 ............. 1817867.40 |=========================================== Redis 5.0.5 Test: LPOP Requests Per Second > Higher Is Better Linux 5.9-rc4 ......... 1332716.88 |======================================== Linux 5.9-rc4 + patch . 1278815.50 |======================================= Linux 5.8 ............. 1420279.27 |=========================================== Hackbench Count: 1 - Type: Process Seconds < Lower Is Better Linux 5.9-rc4 ......... 3.093 |======================================== Linux 5.9-rc4 + patch . 3.756 |================================================ Linux 5.8 ............. 3.062 |======================================= Hackbench Count: 1 - Type: Thread Seconds < Lower Is Better Linux 5.9-rc4 ......... 3.894 |============================================== Linux 5.9-rc4 + patch . 4.104 |================================================ Linux 5.8 ............. 3.239 |====================================== SVT-VP9 0.1 Tuning: VMAF Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better Linux 5.9-rc4 ......... 353.44 |=============================================== Linux 5.9-rc4 + patch . 351.74 |=============================================== Linux 5.8 ............. 350.31 |=============================================== Node.js Express HTTP Load Test Requests Per Second > Higher Is Better Linux 5.9-rc4 ......... 8380 |================================================ Linux 5.9-rc4 + patch . 7652 |============================================ Linux 5.8 ............. 8608 |================================================= Renaissance 0.10.0 Test: Savina Reactors.IO ms < Lower Is Better Linux 5.9-rc4 ......... 15131.10 |============================================= Linux 5.9-rc4 + patch . 14681.45 |============================================ Linux 5.8 ............. 14187.88 |========================================== Renaissance 0.10.0 Test: Apache Spark Bayes ms < Lower Is Better Linux 5.9-rc4 ......... 224.90 |============================================== Linux 5.9-rc4 + patch . 224.17 |============================================== Linux 5.8 ............. 228.29 |=============================================== Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 16 Connections/sec > Higher Is Better Linux 5.9-rc4 ......... 47475 |===================================== Linux 5.9-rc4 + patch . 59438 |=============================================== Linux 5.8 ............. 61266 |================================================