John McCalpin

FEBRUARY 17, 2025

“Latency” is the duration from the execution of a load instruction (to an address that misses in all the caches), and the completion of that load instruction when the data is returned from memory. . The example below is for a 2005-era processor with 60 ns memory latency and 6.4

Latency 71

Latency Hardware Cache Systems 71

John McCalpin

FEBRUARY 17, 2025

“Latency” is the duration from the execution of a load instruction (to an address that misses in all the caches), and the completion of that load instruction when the data is returned from memory. . The example below is for a 2005-era processor with 60 ns memory latency and 6.4

Latency 40

Latency Hardware Cache Systems 40

John McCalpin

APRIL 2, 2020

The presentation discusses a family of simple performance models that I developed over the last 20 years — originally in support of processor and system design at SGI (1996-1999), IBM (1999-2005), and AMD (2006-2008), but more recently in support of system procurements at The Texas Advanced Computing Center (TACC) (2009-present).

Benchmarking 59

Benchmarking Performance Latency Architecture 59

Dean Hume

APRIL 24, 2018

Electricity used by servers doubled between 2000 and 2005 (and has continued growing ever since) from 12 billion to 23 billion kilowatt hours. Without effective caching on the client, the server will see an increase in workload, more CPU usage and ultimately increased latency for the end user. Show me the money!

Energy 40

Energy Cache Traffic Website 40

Dean Hume

APRIL 24, 2018

Electricity used by servers doubled between 2000 and 2005 (and has continued growing ever since) from 12 billion to 23 billion kilowatt hours. Without effective caching on the client, the server will see an increase in workload, more CPU usage and ultimately increased latency for the end user. Show me the money!

Energy 40

Energy Cache Traffic Website 40

Dean Hume

APRIL 24, 2018

Electricity used by servers doubled between 2000 and 2005 (and has continued growing ever since) from 12 billion to 23 billion kilowatt hours. Without effective caching on the client, the server will see an increase in workload, more CPU usage and ultimately increased latency for the end user. Show me the money!

Energy 40

Energy Cache Traffic Website 40

John McCalpin

APRIL 2, 2020

The presentation discusses a family of simple performance models that I developed over the last 20 years — originally in support of processor and system design at SGI (1996-1999), IBM (1999-2005), and AMD (2006-2008), but more recently in support of system procurements at The Texas Advanced Computing Center (TACC) (2009-present).

Benchmarking 40

Benchmarking Performance Latency Architecture 40