AWS Graviton1 To Graviton4 Benchmarks

Benchmarks by Michael Larabel for a future article looking at AWS Graviton1, Graviton2, Graviton3, Graviton4 metal performance.

HTML result view exported from: https://openbenchmarking.org/result/2407243-NE-GRAVITON434&rdt&grr.

Timed Node.js Compilation

Time To Compile

Stockfish

Chess Benchmark

Timed Godot Game Engine Compilation

Time To Compile

Blender

Blend File: Classroom - Compute: CPU-Only

Numpy Benchmark

Blender

Blend File: Fishy Cat - Compute: CPU-Only

C-Ray

Resolution: 5K - Rays Per Pixel: 16

libavif avifenc

Encoder Speed: 0

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Only

High Performance Conjugate Gradient

X Y Z: 104 104 104 - RT: 60

Timed PHP Compilation

Time To Compile

Speedb

Test: Read While Writing

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenSSL

Algorithm: ChaCha20

OpenSSL

Algorithm: AES-128-GCM

OpenSSL

Algorithm: SHA256

OpenSSL

Algorithm: ChaCha20-Poly1305

OpenSSL

Algorithm: AES-256-GCM

OpenSSL

Algorithm: SHA512

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

libavif avifenc

Encoder Speed: 2

PyPerformance

Benchmark: xml_etree

C-Ray

Resolution: 4K - Rays Per Pixel: 16

RocksDB

Test: Update Random

Speedb

Test: Random Read

RocksDB

Test: Read While Writing

RocksDB

Test: Random Read

Stress-NG

Test: CPU Cache

PyPerformance

Benchmark: python_startup

srsRAN Project

Test: PUSCH Processor Benchmark, Throughput Thread

ACES DGEMM

Sustained Floating-Point Rate

GraphicsMagick

Operation: Enhanced

John The Ripper

Test: bcrypt

Speedb

Test: Update Random

John The Ripper

Test: Blowfish

GraphicsMagick

Operation: Noise-Gaussian

John The Ripper

Test: HMAC-SHA512

Speedb

Test: Read Random Write Random

GraphicsMagick

Operation: Sharpen

John The Ripper

Test: MD5

RocksDB

Test: Read Random Write Random

GraphicsMagick

Operation: HWB Color Space

srsRAN Project

Test: PUSCH Processor Benchmark, Throughput Total

LZ4 Compression

Compression Level: 12 - Decompression Speed

LZ4 Compression

Compression Level: 12 - Compression Speed

LZ4 Compression

Compression Level: 9 - Decompression Speed

LZ4 Compression

Compression Level: 9 - Compression Speed

PHPBench

PHP Benchmark Suite

PyPerformance

Benchmark: regex_compile

C-Ray

Resolution: 1080p - Rays Per Pixel: 16

PyPerformance

Benchmark: pathlib

Coremark

CoreMark Size 666 - Iterations Per Second

WebP Image Encode

Encode Settings: Quality 100, Lossless

PyPerformance

Benchmark: crypto_pyaes

7-Zip Compression

Test: Decompression Rating

7-Zip Compression

Test: Compression Rating

John The Ripper

Test: WPA PSK

PyPerformance

Benchmark: json_loads

Stress-NG

Test: Power Math

Stress-NG

Test: Matrix 3D Math

Stress-NG

Test: Vector Floating Point

Stress-NG

Test: Logarithmic Math

Stress-NG

Test: Trigonometric Math

Stress-NG

Test: Floating Point

Stress-NG

Test: Memory Copying

Stress-NG

Test: Matrix Math

Stress-NG

Test: Vector Math

Stress-NG

Test: Fused Multiply-Add

miniFE

Problem Size: Small

srsRAN Project

Test: PDSCH Processor Benchmark, Throughput Total

srsRAN Project

Test: PDSCH Processor Benchmark, Throughput Thread

libavif avifenc

Encoder Speed: 6, Lossless

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

WebP Image Encode

Encode Settings: Quality 100

WebP Image Encode

Encode Settings: Default

Phoronix Test Suite v10.8.5