Ampere Altra Max 128 Core vs. AMD EPYC vs. Intel Xeon Linux Performance - Ubuntu 23.10 Server Benchmarks

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2312011-NE-AMPERE21815&grr&sor.

High Performance Conjugate Gradient

X Y Z: 144 144 144 - RT: 60

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

CloverLeaf

Input: clover_bm16

NWChem

Input: C240 Buckyball

libxsmm

M N K: 128

ASKAP

Test: tConvolve MT - Gridding

Stockfish

Total Time

DuckDB

Benchmark: TPC-H Parquet

Timed Linux Kernel Compilation

Build: allmodconfig

Graph500

Scale: 26

Graph500

Scale: 26

Graph500

Scale: 26

Graph500

Scale: 26

Timed Gem5 Compilation

Time To Compile

PostgreSQL

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

PostgreSQL

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

ClickHouse

100M Rows Hits Dataset, Third Run

ClickHouse

100M Rows Hits Dataset, Second Run

ClickHouse

100M Rows Hits Dataset, First Run / Cold Cache

OpenSSL

Algorithm: SHA256

OpenSSL

Algorithm: AES-128-GCM

OpenSSL

Algorithm: AES-256-GCM

OpenSSL

Algorithm: SHA512

OpenSSL

Algorithm: ChaCha20-Poly1305

OpenSSL

Algorithm: ChaCha20

libxsmm

M N K: 256

DuckDB

Benchmark: IMDB

Timed LLVM Compilation

Build System: Ninja

Timed Node.js Compilation

Time To Compile

CloverLeaf

Input: clover_bm64_short

RocksDB

Test: Random Read

PostgreSQL

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

PostgreSQL

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

Timed Godot Game Engine Compilation

Time To Compile

Apache Cassandra

Test: Writes

ASKAP

Test: tConvolve MPI - Gridding

ASKAP

Test: tConvolve MPI - Degridding

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400

asmFish

1024 Hash Memory, 26 Depth

Memcached

Set To Get Ratio: 1:100

RocksDB

Test: Read While Writing

Xmrig

Variant: Wownero - Hash Count: 1M

John The Ripper

Test: MD5

Sysbench

Test: CPU

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

Xmrig

Variant: Monero - Hash Count: 1M

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200

Memcached

Set To Get Ratio: 1:10

Helsing

Digit Range: 14 digit

GraphicsMagick

Operation: Sharpen

GraphicsMagick

Operation: Enhanced

RawTherapee

Total Benchmark Time

Timed Linux Kernel Compilation

Build: defconfig

Stress-NG

Test: Matrix Math

miniBUDE

Implementation: OpenMP - Input Deck: BM2

miniBUDE

Implementation: OpenMP - Input Deck: BM2

Coremark

CoreMark Size 666 - Iterations Per Second

Algebraic Multi-Grid Benchmark

7-Zip Compression

Test: Decompression Rating

7-Zip Compression

Test: Compression Rating

Rodinia

Test: OpenMP LavaMD

Primesieve

Length: 1e13

Liquid-DSP

Threads: 240 - Buffer Length: 256 - Filter Length: 512

Liquid-DSP

Threads: 128 - Buffer Length: 256 - Filter Length: 512

Stress-NG

Test: NUMA

John The Ripper

Test: WPA PSK

Stress-NG

Test: Vector Math

Stress-NG

Test: Memory Copying

Stress-NG

Test: AVX-512 VNNI

Stress-NG

Test: Fused Multiply-Add

Stress-NG

Test: Wide Vector Math

Stress-NG

Test: Floating Point

Stress-NG

Test: Vector Floating Point

John The Ripper

Test: bcrypt

John The Ripper

Test: Blowfish

LULESH

NAS Parallel Benchmarks

Test / Class: LU.C

NAS Parallel Benchmarks

Test / Class: SP.C

NAS Parallel Benchmarks

Test / Class: BT.C

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

NAS Parallel Benchmarks

Test / Class: IS.D

NAS Parallel Benchmarks

Test / Class: CG.C

miniFE

Problem Size: Small

NAS Parallel Benchmarks

Test / Class: FT.C

ACES DGEMM

Sustained Floating-Point Rate

NAS Parallel Benchmarks

Test / Class: MG.C

Timed Gem5 Compilation

CPU Power Consumption Monitor

CPU Power Consumption Monitor

Phoronix Test Suite System Monitoring