AMD Zen 4 CPU Security Mitigation Benchmarks

AMD Zen 4 CPU mitigation security tests by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2209265-NE-ZEN4MITIG74
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
Web Browsers 1 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 6 Tests
CPU Massive 11 Tests
Creator Workloads 10 Tests
Database Test Suite 10 Tests
Disk Test Suite 2 Tests
Encoding 4 Tests
Game Development 3 Tests
Go Language Tests 3 Tests
Imaging 4 Tests
Java 2 Tests
Common Kernel Benchmarks 6 Tests
Multi-Core 7 Tests
Node.js + NPM Tests 2 Tests
Productivity 3 Tests
Programmer / Developer System Benchmarks 5 Tests
Python Tests 6 Tests
Server 14 Tests
Server CPU Tests 5 Tests
Single-Threaded 4 Tests
Texture Compression 2 Tests
Video Encoding 3 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
Performance Per
Dollar
Date
Run
  Test
  Duration
Default
September 24 2022
  14 Hours, 40 Minutes
mitigations=off
September 24 2022
  23 Hours, 26 Minutes
Invert Hiding All Results Option
  19 Hours, 3 Minutes
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):

AMD Zen 4 CPU Security Mitigation Benchmarks Suite 1.0.0 System Test suite extracted from AMD Zen 4 CPU Security Mitigation Benchmarks. pts/stress-ng-1.5.1 --sendfile 0 Test: SENDFILE pts/stargate-1.0.1 192000 512 Sample Rate: 192000 - Buffer Size: 512 pts/stargate-1.0.1 96000 512 Sample Rate: 96000 - Buffer Size: 512 pts/renaissance-1.3.0 reactors Test: Savina Reactors.IO pts/spark-1.0.0 -r 40000000 -p 2000 Row Count: 40000000 - Partitions: 2000 - Calculate Pi Benchmark pts/renaissance-1.3.0 dotty Test: Scala Dotty pts/stargate-1.0.1 192000 1024 Sample Rate: 192000 - Buffer Size: 1024 pts/spark-1.0.0 -r 40000000 -p 100 Row Count: 40000000 - Partitions: 100 - Calculate Pi Benchmark pts/spark-1.0.0 -r 10000000 -p 2000 Row Count: 10000000 - Partitions: 2000 - Calculate Pi Benchmark pts/spark-1.0.0 -r 10000000 -p 100 Row Count: 10000000 - Partitions: 100 - Calculate Pi Benchmark pts/luaradio-1.0.0 Test: Five Back to Back FIR Filters pts/stargate-1.0.1 96000 1024 Sample Rate: 96000 - Buffer Size: 1024 pts/redis-1.4.0 -t set -c 50 Test: SET - Parallel Connections: 50 system/selenium-1.0.30 ares6 Chrome Benchmark: ARES-6 - Browser: Google Chrome pts/osbench-1.0.2 create_files.exe target Test: Create Files pts/sockperf-1.1.0 ping-pong Test: Latency Ping Pong pts/compilebench-1.0.3 READ_COMPILED_TREE Test: Read Compiled Tree pts/stargate-1.0.1 48000 512 Sample Rate: 480000 - Buffer Size: 512 pts/apache-2.0.1 -c 200 Concurrent Requests: 200 pts/renaissance-1.3.0 dec-tree Test: Random Forest pts/renaissance-1.3.0 future-genetic Test: Genetic Algorithm Using Jenetics + Futures pts/sockperf-1.1.0 throughput Test: Throughput system/selenium-1.0.30 jetstream2 Firefox Benchmark: Jetstream 2 - Browser: Firefox pts/stargate-1.0.1 48000 1024 Sample Rate: 480000 - Buffer Size: 1024 pts/build-python-1.0.0 Build Configuration: Default pts/renaissance-1.3.0 als Test: Apache Spark ALS pts/dacapobench-1.0.1 jython Java Test: Jython pts/nginx-2.0.1 -c 500 Concurrent Requests: 500 pts/spark-1.0.0 -r 10000000 -p 2000 Row Count: 10000000 - Partitions: 2000 - Calculate Pi Benchmark Using Dataframe system/inkscape-1.0.1 Operation: SVG Files To PNG pts/renaissance-1.3.0 page-rank Test: Apache Spark PageRank system/octave-benchmark-1.0.1 pts/nginx-2.0.1 -c 1000 Concurrent Requests: 1000 pts/spark-1.0.0 -r 10000000 -p 100 Row Count: 10000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe pts/spark-1.0.0 -r 40000000 -p 100 Row Count: 40000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe pts/node-web-tooling-1.0.1 pts/aom-av1-3.5.0 --cpu-used=8 --rt Bosphorus_1920x1080_120fps_420_8bit_YUV.y4m Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p pts/spark-1.0.0 -r 10000000 -p 2000 Row Count: 10000000 - Partitions: 2000 - Inner Join Test Time system/selenium-1.0.30 speedometer Chrome Benchmark: Speedometer - Browser: Google Chrome pts/nginx-2.0.1 -c 200 Concurrent Requests: 200 system/selenium-1.0.30 jetstream2 Chrome Benchmark: Jetstream 2 - Browser: Google Chrome pts/nginx-2.0.1 -c 100 Concurrent Requests: 100 pts/avifenc-1.2.0 -s 6 Encoder Speed: 6 pts/stress-ng-1.5.1 --futex 0 Test: Futex pts/dacapobench-1.0.1 h2 Java Test: H2 pts/dacapobench-1.0.1 tradebeans Java Test: Tradebeans pts/spark-1.0.0 -r 40000000 -p 100 Row Count: 40000000 - Partitions: 100 - SHA-512 Benchmark Time pts/osbench-1.0.2 launch_programs.exe Test: Launch Programs pts/build-python-1.0.0 --enable-optimizations --with-lto Build Configuration: Released Build, PGO + LTO Optimized pts/clickhouse-1.1.0 100M Rows Web Analytics Dataset, Third Run system/rawtherapee-1.0.1 Total Benchmark Time pts/spark-1.0.0 -r 40000000 -p 100 Row Count: 40000000 - Partitions: 100 - Group By Test Time pts/aom-av1-3.5.0 --cpu-used=9 --rt Bosphorus_3840x2160.y4m Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K pts/aom-av1-3.5.0 --cpu-used=6 --rt Bosphorus_3840x2160.y4m Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K pts/renaissance-1.3.0 db-shootout Test: In-Memory Database Shootout system/libreoffice-1.0.0 --convert-to pdf documents/* Test: 20 Documents To PDF pts/aom-av1-3.5.0 --cpu-used=8 --rt Bosphorus_3840x2160.y4m Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K system/selenium-1.0.30 speedometer Firefox Benchmark: Speedometer - Browser: Firefox pts/build-mesa-1.0.0 Time To Compile pts/clickhouse-1.1.0 100M Rows Web Analytics Dataset, Second Run pts/apache-2.0.1 -c 20 Concurrent Requests: 20 pts/stress-ng-1.5.1 --cache 0 Test: CPU Cache pts/spark-1.0.0 -r 40000000 -p 2000 Row Count: 40000000 - Partitions: 2000 - Calculate Pi Benchmark Using Dataframe pts/spark-1.0.0 -r 10000000 -p 2000 Row Count: 10000000 - Partitions: 2000 - SHA-512 Benchmark Time pts/webp-1.2.0 -q 100 Encode Settings: Quality 100 pts/clickhouse-1.1.0 100M Rows Web Analytics Dataset, First Run / Cold Cache pts/aom-av1-3.5.0 --cpu-used=10 --rt Bosphorus_1920x1080_120fps_420_8bit_YUV.y4m Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p pts/dragonflydb-1.0.0 -c 50 --ratio=1:5 Clients: 50 - Set To Get Ratio: 1:5 pts/apache-2.0.1 -c 1000 Concurrent Requests: 1000 pts/dragonflydb-1.0.0 -c 50 --ratio=5:1 Clients: 50 - Set To Get Ratio: 5:1 pts/nginx-2.0.1 -c 1 Concurrent Requests: 1 system/selenium-1.0.30 kraken Chrome Benchmark: Kraken - Browser: Google Chrome pts/apache-2.0.1 -c 100 Concurrent Requests: 100 system/wireguard-1.0.1 system/selenium-1.0.30 pspdfkit Firefox Benchmark: PSPDFKit WASM - Browser: Firefox pts/node-express-loadtest-1.0.1 pts/aom-av1-3.5.0 --cpu-used=10 --rt Bosphorus_3840x2160.y4m Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K pts/compilebench-1.0.3 INITIAL_CREATE Test: Initial Create pts/svt-av1-2.6.0 --preset 10 -i Bosphorus_3840x2160.y4m -w 3840 -h 2160 Encoder Mode: Preset 10 - Input: Bosphorus 4K pts/nginx-2.0.1 -c 20 Concurrent Requests: 20 pts/spark-1.0.0 -r 10000000 -p 100 Row Count: 10000000 - Partitions: 100 - Group By Test Time pts/spark-1.0.0 -r 10000000 -p 2000 Row Count: 10000000 - Partitions: 2000 - Repartition Test Time pts/avifenc-1.2.0 -s 6 -l Encoder Speed: 6, Lossless pts/spark-1.0.0 -r 40000000 -p 100 Row Count: 40000000 - Partitions: 100 - Broadcast Inner Join Test Time pts/osbench-1.0.2 create_threads.exe Test: Create Threads pts/dacapobench-1.0.1 tradesoap Java Test: Tradesoap pts/memtier-benchmark-1.4.0 -P redis -c 50 --ratio=5:1 Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1 pts/svt-av1-2.6.0 --preset 10 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Preset 10 - Input: Bosphorus 1080p pts/renaissance-1.3.0 movie-lens Test: ALS Movie Lens pts/stress-ng-1.5.1 --malloc 0 Test: Malloc pts/dragonflydb-1.0.0 -c 200 --ratio=5:1 Clients: 200 - Set To Get Ratio: 5:1 pts/memtier-benchmark-1.4.0 -P redis -c 500 --ratio=1:10 Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:10 pts/spark-1.0.0 -r 40000000 -p 2000 Row Count: 40000000 - Partitions: 2000 - Broadcast Inner Join Test Time pts/cassandra-1.1.1 WRITE Test: Writes pts/memtier-benchmark-1.4.0 -P redis -c 500 --ratio=5:1 Protocol: Redis - Clients: 500 - Set To Get Ratio: 5:1 pts/spark-1.0.0 -r 10000000 -p 100 Row Count: 10000000 - Partitions: 100 - SHA-512 Benchmark Time pts/spark-1.0.0 -r 40000000 -p 2000 Row Count: 40000000 - Partitions: 2000 - Group By Test Time pts/dragonflydb-1.0.0 -c 200 --ratio=1:5 Clients: 200 - Set To Get Ratio: 1:5 pts/spark-1.0.0 -r 10000000 -p 100 Row Count: 10000000 - Partitions: 100 - Repartition Test Time pts/spark-1.0.0 -r 40000000 -p 2000 Row Count: 40000000 - Partitions: 2000 - Inner Join Test Time pts/spark-1.0.0 -r 10000000 -p 100 Row Count: 10000000 - Partitions: 100 - Broadcast Inner Join Test Time pts/aom-av1-3.5.0 --cpu-used=9 --rt Bosphorus_1920x1080_120fps_420_8bit_YUV.y4m Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p pts/build-godot-1.0.0 Time To Compile pts/svt-av1-2.6.0 --preset 8 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Preset 8 - Input: Bosphorus 1080p pts/etcd-1.0.0 range KEY --total=4000000 --conns 500 --clients 1000 Test: RANGE - Connections: 500 - Clients: 1000 pts/stress-ng-1.5.1 --memfd 0 Test: MEMFD pts/spark-1.0.0 -r 40000000 -p 100 Row Count: 40000000 - Partitions: 100 - Inner Join Test Time pts/etcd-1.0.0 range KEY --total=4000000 --conns 100 --clients 1000 Test: RANGE - Connections: 100 - Clients: 1000 pts/apache-2.0.1 -c 1 Concurrent Requests: 1 pts/svt-av1-2.6.0 --preset 12 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Preset 12 - Input: Bosphorus 1080p pts/stress-ng-1.5.1 --fork 0 Test: Forking pts/spark-1.0.0 -r 40000000 -p 100 Row Count: 40000000 - Partitions: 100 - Repartition Test Time pts/spark-1.0.0 -r 10000000 -p 2000 Row Count: 10000000 - Partitions: 2000 - Group By Test Time pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 500 --clients 1000 Test: PUT - Connections: 500 - Clients: 1000 pts/osbench-1.0.2 mem_alloc.exe Test: Memory Allocations pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 100 --clients 1000 Test: PUT - Connections: 100 - Clients: 1000 - Average Latency pts/etcd-1.0.0 range KEY --total=4000000 --conns 50 --clients 1000 Test: RANGE - Connections: 50 - Clients: 1000 - Average Latency pts/astcenc-1.4.0 -medium -repeats 20 Preset: Medium pts/etcd-1.0.0 range KEY --total=4000000 --conns 100 --clients 1000 Test: RANGE - Connections: 100 - Clients: 1000 - Average Latency pts/etcd-1.0.0 range KEY --total=4000000 --conns 500 --clients 1000 Test: RANGE - Connections: 500 - Clients: 1000 - Average Latency pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 500 --clients 1000 Test: PUT - Connections: 500 - Clients: 1000 - Average Latency pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 100 --clients 1000 Test: PUT - Connections: 100 - Clients: 1000 pts/stress-ng-1.5.1 --numa 0 Test: NUMA pts/memtier-benchmark-1.4.0 -P redis -c 50 --ratio=1:10 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10 pts/stress-ng-1.5.1 --cpu 0 --cpu-method all Test: CPU Stress pts/etcd-1.0.0 range KEY --total=4000000 --conns 100 --clients 100 Test: RANGE - Connections: 100 - Clients: 100 - Average Latency pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 100 --clients 100 Test: PUT - Connections: 100 - Clients: 100 - Average Latency pts/etcd-1.0.0 range KEY --total=4000000 --conns 500 --clients 100 Test: RANGE - Connections: 500 - Clients: 100 - Average Latency pts/etcd-1.0.0 range KEY --total=4000000 --conns 50 --clients 100 Test: RANGE - Connections: 50 - Clients: 100 - Average Latency pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 500 --clients 100 Test: PUT - Connections: 500 - Clients: 100 - Average Latency pts/spark-1.0.0 -r 10000000 -p 2000 Row Count: 10000000 - Partitions: 2000 - Broadcast Inner Join Test Time system/selenium-1.0.30 pspdfkit Chrome Benchmark: PSPDFKit WASM - Browser: Google Chrome pts/spark-1.0.0 -r 40000000 -p 2000 Row Count: 40000000 - Partitions: 2000 - Repartition Test Time pts/svt-av1-2.6.0 --preset 8 -i Bosphorus_3840x2160.y4m -w 3840 -h 2160 Encoder Mode: Preset 8 - Input: Bosphorus 4K pts/etcd-1.0.0 range KEY --total=4000000 --conns 50 --clients 1000 Test: RANGE - Connections: 50 - Clients: 1000 pts/stress-ng-1.5.1 --msg 0 Test: System V Message Passing pts/avifenc-1.2.0 -s 2 Encoder Speed: 2 pts/postmark-1.1.2 Disk Transaction Performance pts/etcpak-1.1.0 -b -M --rgba Benchmark: Multi-Threaded - Configuration: ETC2 pts/svt-av1-2.6.0 --preset 12 -i Bosphorus_3840x2160.y4m -w 3840 -h 2160 Encoder Mode: Preset 12 - Input: Bosphorus 4K pts/apache-2.0.1 -c 500 Concurrent Requests: 500 pts/osbench-1.0.2 create_processes.exe Test: Create Processes pts/renaissance-1.3.0 naive-bayes Test: Apache Spark Bayes pts/etcpak-1.1.0 -b --rgba Benchmark: Single-Threaded - Configuration: ETC2 pts/etcd-1.0.0 range KEY --total=4000000 --conns 50 --clients 100 Test: RANGE - Connections: 50 - Clients: 100 system/selenium-1.0.30 wasmcollision Firefox Benchmark: WASM collisionDetection - Browser: Firefox pts/keydb-1.3.1 pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 50 --clients 1000 Test: PUT - Connections: 50 - Clients: 1000 - Average Latency pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 50 --clients 100 Test: PUT - Connections: 50 - Clients: 100 pts/luaradio-1.0.0 Test: Complex Phase pts/renaissance-1.3.0 akka-uct Test: Akka Unbalanced Cobwebbed Tree pts/etcd-1.0.0 range KEY --total=4000000 --conns 100 --clients 100 Test: RANGE - Connections: 100 - Clients: 100 pts/stress-ng-1.5.1 --memcpy 0 Test: Memory Copying pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 500 --clients 100 Test: PUT - Connections: 500 - Clients: 100 pts/stress-ng-1.5.1 --io-uring 0 Test: IO_uring pts/astcenc-1.4.0 -thorough -repeats 10 Preset: Thorough pts/spark-1.0.0 -r 40000000 -p 2000 Row Count: 40000000 - Partitions: 2000 - SHA-512 Benchmark Time pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 50 --clients 1000 Test: PUT - Connections: 50 - Clients: 1000 pts/etcd-1.0.0 range KEY --total=4000000 --conns 500 --clients 100 Test: RANGE - Connections: 500 - Clients: 100 pts/stress-ng-1.5.1 --mmap 0 Test: MMAP pts/astcenc-1.4.0 -exhaustive -repeats 2 Preset: Exhaustive pts/stress-ng-1.5.1 --atomic 0 Test: Atomic pts/luaradio-1.0.0 Test: Hilbert Transform pts/stress-ng-1.5.1 --sem 0 Test: Semaphores pts/stress-ng-1.5.1 --vecmath 0 Test: Vector Math pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 100 --clients 100 Test: PUT - Connections: 100 - Clients: 100 pts/renaissance-1.3.0 finagle-http Test: Finagle HTTP Requests pts/compilebench-1.0.3 COMPILE Test: Compile system/selenium-1.0.30 wasmcollision Chrome Benchmark: WASM collisionDetection - Browser: Google Chrome pts/webp-1.2.0 -q 100 -m 6 Encode Settings: Quality 100, Highest Compression pts/luaradio-1.0.0 Test: FM Deemphasis Filter pts/stress-ng-1.5.1 --matrix 0 Test: Matrix Math pts/stress-ng-1.5.1 --qsort 0 Test: Glibc Qsort Data Sorting pts/stress-ng-1.5.1 --sock 0 Test: Socket Activity pts/stress-ng-1.5.1 --crypt 0 Test: Crypto pts/couchdb-1.2.0 300 1000 30 Bulk Size: 300 - Inserts: 1000 - Rounds: 30 pts/couchdb-1.2.0 100 3000 30 Bulk Size: 100 - Inserts: 3000 - Rounds: 30 pts/couchdb-1.2.0 100 1000 30 Bulk Size: 100 - Inserts: 1000 - Rounds: 30 pts/etcd-1.0.0 put --total=4000000 --val-size=256 --key-size=8 --conns 50 --clients 100 Test: PUT - Connections: 50 - Clients: 100 - Average Latency pts/webp-1.2.0 Encode Settings: Default system/selenium-1.0.30 wasmconvolute Chrome Benchmark: WASM imageConvolute - Browser: Google Chrome system/selenium-1.0.30 wasmconvolute Firefox Benchmark: WASM imageConvolute - Browser: Firefox system/selenium-1.0.30 stylebench Chrome Benchmark: StyleBench - Browser: Google Chrome system/selenium-1.0.30 stylebench Firefox Benchmark: StyleBench - Browser: Firefox system/selenium-1.0.30 kraken Firefox Benchmark: Kraken - Browser: Firefox system/selenium-1.0.30 ares6 Firefox Benchmark: ARES-6 - Browser: Firefox pts/stress-ng-1.5.1 --str 0 Test: Glibc C String Functions pts/stress-ng-1.5.1 --switch 0 Test: Context Switching pts/stress-ng-1.5.1 --rdrand 0 Test: x86_64 RdRand pts/sqlite-speedtest-1.0.1 Timed Time - Size 1,000 pts/redis-1.4.0 -t set -c 1000 Test: SET - Parallel Connections: 1000 pts/redis-1.4.0 -t get -c 1000 Test: GET - Parallel Connections: 1000 pts/redis-1.4.0 -t get -c 50 Test: GET - Parallel Connections: 50 pts/spark-1.0.0 -r 10000000 -p 100 Row Count: 10000000 - Partitions: 100 - Inner Join Test Time pts/aom-av1-3.5.0 --cpu-used=6 --rt Bosphorus_1920x1080_120fps_420_8bit_YUV.y4m Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p pts/webp-1.2.0 -q 100 -lossless Encode Settings: Quality 100, Lossless pts/dacapobench-1.0.1 eclipse Java Test: Eclipse pts/sockperf-1.1.0 under-load Test: Latency Under Load