Talk:Parallel computing

{{Talk header|noarchive=yes}}

{{Article history|action1=FAC

|action1date=16:28, 18 November 2007

|action1link=Wikipedia:Featured article candidates/Parallel computing/archive1

|action1result=failed

|action1oldid=172277547

|action2=GAN

|action2date=09:42, 16 January 2008

|action2result=listed

|action2oldid=183547682

|action3=FAC

|action3date=18:17, 6 May 2008

|action3link=Wikipedia:Featured article candidates/Parallel computing

|action3result=promoted

|action3oldid=210137652

|topic=engtech

|currentstatus=FA

|maindate=March 18, 2009

}}

{{WikiProject banner shell|class=FA|vital=yes|1=

{{WikiProject Computing|importance=Top|science=yes|science-importance=Top}}

{{WikiProject Computer science|importance=Top}}

{{WikiProject Spoken Wikipedia}}

}}

{{archives

|auto= short

|index= /Archive index

|search= yes

|bot= MiszaBot I

|age= 60

}}

{{User:MiszaBot/config

|archiveheader = {{talkarchivenav|noredlinks=y}}

|maxarchivesize = 125K

|counter = 1

|minthreadsleft = 4

|algo = old(60d)

|archive = Talk:Parallel computing/Archive %(counter)d

}}

{{User:HBC Archive Indexerbot/OptIn

|target=Talk:Parallel computing/Archive index

|mask=Talk:Parallel computing/Archive <#>

|leading_zeros=0

|indexhere=yes

}}

GPU (SLI, Crossfire)

Similar principle was applied to GPUs: Scalable Link Interface, AMD CrossFireX, NVLink Bridge. It would be good to expand upon, how it is similar and how it differs from CPU parallel computing. [https://graphicscardhub.com/nvidia-sli/ ... It is based on the principle of parallel processing where two or more GPUs share the load...] 89.201.184.8 (talk) 09:03, 26 April 2020 (UTC)

A more fundamental classification

I'm missing a more fundamental classification of parallelism that is not rooted in implementation details of contemporary computers, or computing at all, just the possible ways to split work.

I think there are fundamentally two ways to split work so it can be worked on simultaneously:

  1. Parallel: Distribute the work so that work units take different paths.
  2. Series: Split the work in stages that can be pipelined.

Someone must have thought about this before.—Anordal (talk) 21:40, 14 January 2021 (UTC)

Parallel vs. Concurrent

Based on the descriptions in these two articles, how can you be parallel without being concurrent? Digital27 (talk) 01:49, 15 November 2023 (UTC)

:On further thought, should we really be making the distinction between parallel and concurrent? Digital27 (talk) 16:54, 15 November 2023 (UTC)

::They are different.

::When two jobs run parallel they run at the same time.

::When two jobs run concurrent, they share a core but appear to run at the same time. This is multitasking. FrankYang43338 (talk) 18:44, 23 March 2024 (UTC)