Path: ...!weretis.net!feeder9.news.weretis.net!i2pn.org!i2pn2.org!.POSTED!not-for-mail
From: mitchalsup@aol.com (MitchAlsup1)
Newsgroups: comp.arch
Subject: Re: Is Intel exceptionally unsuccessful as an architecture
 =?UTF-8?B?ZGVzaWduZXI/?=
Date: Sun, 22 Sep 2024 02:21:54 +0000
Organization: Rocksolid Light
Message-ID: <cf3e8a094ff8186b1bba2b3369da1e93@www.novabbs.org>
References: <memo.20240913205156.19028s@jgd.cix.co.uk> <vcd3ds$3o6ae$2@dont-email.me> <2935676af968e40e7cad204d40cafdcf@www.novabbs.org> <vcd7pr$3op6a$3@dont-email.me> <7wCGO.45461$xO0f.1783@fx48.iad> <20240918190414.00005806@yahoo.com> <8e1aed9ce25c70cc555731140ae14eb1@www.novabbs.org> <vcfln9$836k$1@dont-email.me> <vcgi7p$fmaa$2@dont-email.me> <f6093802cde5821a88ff715b8139fc04@www.novabbs.org> <vcicir$ov66$1@dont-email.me> <ad85483a2a41b704c1cbb6e796aaf9f4@www.novabbs.org> <vcisaf$ulcv$1@dont-email.me> <vcjk4q$132af$1@dont-email.me> <vcnugl$1vkui$7@dont-email.me>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 8bit
Injection-Info: i2pn2.org;
	logging-data="2950424"; mail-complaints-to="usenet@i2pn2.org";
	posting-account="65wTazMNTleAJDh/pRqmKE7ADni/0wesT78+pyiDW8A";
User-Agent: Rocksolid Light
X-Spam-Checker-Version: SpamAssassin 4.0.0
X-Rslight-Site: $2y$10$lkWgCixXw1B2CusIasrGKu6ZRqDva8Scc0yM2VnrX6oOGNUWKAYtC
X-Rslight-Posting-User: ac58ceb75ea22753186dae54d967fed894c3dce8
Bytes: 2285
Lines: 20

On Sun, 22 Sep 2024 2:13:42 +0000, Lawrence D'Oliveiro wrote:

> On Fri, 20 Sep 2024 06:52:07 -0400, Paul A. Clayton wrote:
>
>> From what I understand, GPUs also typically have
>> memory controllers optimized for throughput rather than latency, with
>> larger queue depth.
>
> Fine. If they aren’t designed for low latency, then you can’t call them
> “interactive”, can you? Since that requires quick response. They seem
> more oriented towards batch operation in the background.

Think about it like this::

A GPU can perform 1T-10T calculations per second running at 1GHz.

Try doing that with a CPU.

They are entirely different on the spectrum of design and architecture.
Things that work to make CPUs faster do not make GPUs faster--and for
the most part--vice versa.