Adrian Cockcroft

JANUARY 20, 2023

Here’s some predictions I’m making: Jack Dongarra’s efforts to highlight the low efficiency of the HPCG benchmark as an issue will influence the next generation of supercomputer architectures to optimize for sparse matrix computations. Next generation architectures will use CXL3.0 petaflops, which is 0.8% of peak capacity.

Architecture 52

Architecture Latency Benchmarking AWS 52

John McCalpin

APRIL 25, 2023

This metric is interesting because we don’t always have the luxury of parallelizing every application we run, and our operating systems almost always process each call (e.g., GHz, 1530 GB/s peak BW from 6 HBM stacks), I see single-thread sustained memory bandwidth of 304 GB/s on the ReadOnly benchmark used here.

Benchmarking 97

Benchmarking Cache Latency Tuning 97

The Morning Paper

MAY 12, 2019

An open-source benchmark suite for microservices and their hardware-software implications for cloud & edge systems Gan et al., A typical architecture diagram for one of these services looks like this: Suitably armed with a set of benchmark microservices applications, the investigation can begin! ASPLOS’19.

Open Source 61

Open Source Hardware Benchmarking Systems 61

John McCalpin

APRIL 2, 2020

All of the SPECfp_rate2000 results were downloaded from www.spec.org, the results were sorted by processor type, and “peak floating-point operations per cycle” was manually added for each processor type. This includes all architectures, all compilers, all operating systems, and all system configurations.

Benchmarking 59

Benchmarking Performance Latency Architecture 59

Percona

JULY 1, 2023

It efficiently manages read and write operations, optimizes data access, and minimizes contention, resulting in high throughput and low latency to ensure that applications perform at their best. Doing extensive benchmarks will be the subject of a future blog post. Migration to RDS can be performed using Percona XtraBackup.

AWS 52

AWS Database Serverless Storage 52

SQL Server According to Bob

JANUARY 11, 2020

Many high-end disk subsystems provide high-speed cache facilities to reduce the latency of read and write operations. SQL Server always checks I/O completion status for any operating system error conditions and proper data transfer size and then handles errors appropriately. The data transfer size is not valid.

Servers 40

Servers Cache Media Hardware 40

ScaleOut Software

MAY 15, 2014

Likewise, object access paths must be heavily multi-threaded and avoid lock contention to minimize access latency and maximize throughput. We believe that installing our software should be as straightforward as we can make it, requiring minimal knowledge of the host operating system and the fewest possible explicit configuration settings.

Cache 40

Cache Servers Network Design 40