>4GB ram in win x86 possible?


Recommended Posts

is unlikely considering that 64-bit processors have wider registers (64-bits) to push more data through the pipes. It should be the same or better.

The amount of data doesn't affect the speed at which a smaller amount of data goes through it. It's pretty close to the same. It does depend on the processor arch and there is a tiny translation penalty for 32 bit apps.

Of course, there's also the portion of memory the GPU takes, 32 bit apps with LAA and all that to consider so it's not a simple comparison.

you know its possible for Pentium Pro processor can have up to 64 GB memory,

but only 4 GB can be accessed at a time.

PAE is an ancient old technolgy (1995), its already there before x86-64 CPU exisited,

but Microsoft only actively used it in their 64-bit OS.

Its not a Software limitation

yes it is, unless you're talking about CPU before 1998 that is.

XP pre-dates multicore CPUs, it isn't optimised for them in the slightest (let alone low power/scaling stuff which CPUs do now). Newer versions of Windows make much better use of the underlying hardware (DWM offloads all desktop drawing to the GPU, Direct2D/DirectWrite offloads all application drawing to the GPU, etc.)

What a load of crap. Multiple CPU systems were in use for many many years, the difference to the OS between a different CPU and a different core is very small.

What a load of crap. Multiple CPU systems were in use for many many years, the difference to the OS between a different CPU and a different core is very small.

For server class systems, yes. But the desktop certainly didn't have multiple core/CPU systems as the norm.

When XP was released, a system with 4 CPU cores and 4GB+ of RAM was a high end server and well outside the design specifications.

  • Like 1

Slumdog - Normally people are willing to give some consideration to alternative views, but you have pretty much the entire of the posters against you on this.

32bit will run more slowly on x64 enabled chips. The x64 chips either have less registers for x86 instructions, or virtualise the calls and instructions. Since the Core range, this has been the case, but it's becoming more pronounced over time as Intel and AMD start to push for more x64 usage. I am aware there was a register issue with certain batches of Core processors, but the Core2 range had fixed that and begun this trend.

On top of this, XP doesn't have access to DirectDraw/Direct2D, thus it IS slower for more complex graphical browser based workloads. Chrome and Firefox both leverage varying levels of Direct2D or proprietary hardware acceleration. Thus, both will be faster on 7/8.

A lot of the people in this thread are extremely knowledgeable in a vast array of disciplines. Pretty much everyone is saying you're wrong on this. If you choose not to regard this point of view, fine, but you shouldn't expect us to blow smoke up your ass to validate your views.

PAE cannot (to the best of my knowledge) be enabled on XP. Consider 64 bit systems, and consider Windows 7. Even if you don't like the interface, there are significant improvements to thread handling, core allocation, memory management, graphical interfaces, Direct X draw and layers. Hell, consider 8 and user Start8 or whatever you want. I don't care about the interface disagreements, but the kernel is much improved.

Even if you insist on using FIrefox in CPU rendering modes, you will find noteworthy performance improvements from the better process scheduling on 7.

Lastly: Even if you enable PAE on XP, there are issues with process limitations (something people mistook for threads.. seriously) and most apps are compiled to only address 2GB of space at a max. Unless you enable particular compiler flags, most compilers will automatically compile for a maximum of 2gb of addressable space per process.

So.. Time to move on.

EDIT:: It's worth noting my CPU knowledge is a little out of date. The_decryptor pointed out some changes to the Core iX processors that invalidated much of what I said about performance overheads. Either way, x64 is still faster >.<

  • Like 2

For server class systems, yes. But the desktop certainly didn't have multiple core/CPU systems as the norm.

When XP was released, a system with 4 CPU cores and 4GB+ of RAM was a high end server and well outside the design specifications.

I remember when XP came out, I installed it on a 2 year old laptop. It had a 300mhz processor, and 64mb of RAM. At school, the best computer was a 900mhz PC with something insane like 128mb of RAM. A year later, I was talking to a friend who built a computer with 256mb of RAM in his computer. This was enough for him to disable his page file.

I mean, I guess it's like using puppy Linux as your main OS. I don't know why but to each their own.

I remember when XP came out, I installed it on a 2 year old laptop. It had a 300mhz processor, and 64mb of RAM. At school, the best computer was a 900mhz PC with something insane like 128mb of RAM. A year later, I was talking to a friend who built a computer with 256mb of RAM in his computer. This was enough for him to disable his page file.

I mean, I guess it's like using puppy Linux as your main OS. I don't know why but to each their own.

My first build had 1GB of RAM on a Prescott based Pentium 4. I was blown away by the speed, XP screamed along.

I disabled PageFile and was blown away with the speed :D Now days, You don't need to disable paging because your system will have so much memory it only pages when MS's algorithm is being ****..

I liked XP (hated it when I first started using it) but 7 was a mile forwards in all regards. Vista was an improvement, but Microsoft has their priorities wrong. Even if you don't like Vista, there's nothing not to like about 7 >.<

EDIT::

Might I just add Greenwizard, your app isn't really a productivity app, some might contend it does the exact opposite :p

The amount of data doesn't affect the speed at which a smaller amount of data goes through it. It's pretty close to the same. It does depend on the processor arch and there is a tiny translation penalty for 32 bit apps.

But, any 64-bit data can now fit in a register. Unmentioned, but 64-bit processors also tend to have more registers as well.

What?

Can't use more than 4GB RAM with a 32-bit OS. If you want to use more, you'll have to dump that dinosaur of an OS you seem hell bent on using.

You missed the part where he said x64.. You know.. Being capable of more than 4GB of addressable memory O.o

You missed the part where he said x64.. You know.. Being capable of more than 4GB of addressable memory O.o

No I didn't. I was surprised that anyone would say that XP x64 was a good OS. The comment below "What?" was to the OP. Will edit.

No I didn't. I was surprised that anyone would say that XP x64 was a good OS. The comment below "What?" was to the OP. Will edit.

Windows XP Professional x64 Edition (XP x64) isn't bad at all. Windows XP 64-bit Edition (XP 64-bit) on the other hand had isn't all that good because it wasn't supported well.

there are kernel hacks floating around, which enable PAE support in xp/vista/7 x86, but as others said, PAE has been disabled for a reason in the consumer editions of windows.

although the hacks do work, it's not advisable to use them, if you want to use the pc for multimedia/gaming stuff, because it's very likely you will run into incompatible drivers.

-andy-

It's almost like all his knowledge of computer and OS stopped at 2005. Welcome to 2013. Why are you hell bend on keeping Windows XP? What's SO good about XP that keeps you from upgrading to Win7 x64?

high standards and unwillingness to compromise... if i have to drop the standards might as well move to win8 x64. and yes im already triple booting these 3OSes so there is no question of being stuck in 2005.

btw where did you pull out the year 2005 from?

dated is still faster if you use a web browser other than ie.... which i suppose everyone does ALL the time.

im looking for hacks mainly.

Then read that article. It tells you how to enable it by editing your boot.ini file.

EDIT: Whoops, this one does: http://msdn.microsof...8(v=vs.85).aspx

2005 about is when the XP kernel and GDI was deprecated and Longhorn development was underway, I think.

Windows XP Professional x64 Edition (XP x64) isn't bad at all. Windows XP 64-bit Edition (XP 64-bit) on the other hand had isn't all that good because it wasn't supported well.

Well one of those is for Itanium processors, there's probably nobody who uses those aside in certain very, very specific server environments.

It's almost like all his knowledge of computer and OS stopped at 2005. Welcome to 2013. Why are you hell bend on keeping Windows XP? What's SO good about XP that keeps you from upgrading to Win7 x64?

He's one of the reasons why after 12 years, XP still has ~40% market share. The scary thing is that there are many, many systems admins that think like this, and mistake their own stubbornness, and unwillingness to adapt, as maintaining high standards.

He's one of the reasons why after 12 years, XP still has ~40% market share. The scary thing is that there are many, many systems admins that think like this, and mistake their own stubbornness, and unwillingness to adapt, as maintaining high standards.

scared for whom? srsly :shiftyninja:

More to the point, there are lots of people with not very much money >.<

Enabling PAE on XP will only enable access to 4GB of RAM >.>

pae is automatically enabled on xp sp3 + x86_64 processors... this thread is about going beyond 4gb... where is the vast array of expertise when after 5 pages the subject of the thread is not even grasped.? :/

This topic is now closed to further replies.
  • Recently Browsing   0 members

    • No registered users viewing this page.
  • Posts

    • No, size is not the only selling point. I did not even remotely say that. Your claim was that "building your own will be faster and cheaper". This is false. You cannot build something close to that form factor with off-the-shelf parts. You can build a Mini-ITX PC and pay more, or something larger and pay less. But these are different market segments. It's apples and oranges.
    • There is a default resolution setting in Settings > Display that can be changed with a click. You can also change the settings on a per-game basis. No CLI needed. Also, Steam has countless games that are not "[perpetual] alpha/beta games", so no need for the straw man. Plus you can use other stores as well. And console games (e.g. PS5) cost a fortune, which itself more than negates the price subsidy on the system, unless you plan on exclusively playing 1 or 2 games. It's true that you shouldn't buy a system that doesn't support the game(s) you want to play, but I think that's kinda obvious, and applies to every console as well as PC. I don't game in the living room and have no need of a Steam Machine, but there is a clear market segment that would find it useful.
    • RSS Guard 5.2.0 by Razvan Serea RSS Guard is a simple (yet powerful) feed reader. It is able to fetch the most known feed formats, including RSS/RDF and ATOM. It's free, it's open-source. RSS Guard currently supports Czech, Dutch, English, French, German, Italian. RSS Guard will never depend on other services - this includes online news aggregators like Feedly, The Old Reader and others. RSS Guard is developed on top of the Qt library and it supports these operating systems: Windows GNU/Linux OS/2 (eComStation) Mac OS X xBSD (possibly) Android (possibly) other platforms supported by Qt The core features of RSS Guard are: support for online feed synchronization via plugins, Tiny Tiny RSS (from RSS Guard 3.0.0). multiplatform, support for all feed formats, simplicity, import/export of feeds to/from OPML 2.0, downloader with own tab and support for up to 6 parallel downloads, message filter with regular expressions, feed metadata fetching including icons, simple Adblock functionality, customized popup notifications, Google-based auto-completion for internal web browser location bar, ability to cleanup internal message database with various options, enhanced feed auto-updating with separate time intervals, multiple data backend support, SQLite (in-memory DBs too), MySQL. is able to specify target database by its name (MySQL backend), “portable” mode support with clever auto-detection, feed categorization, drap-n-drop for feed list, automatic checking for updates, ability to discover existing feeds on websites, full support of podcasts (both RSS & ATOM), ability to backup/restore database or settings, fully-featured recycle bin, printing of messages and any web pages, can be fully controlled via keyboard, feed authentication (Digest-MD5, BASIC, NTLM-2), handles tons of messages & feeds, sweet look & feel, fully adjustable toolbars (changeable buttons and style), ability to check for updates on all platforms + self-updating on Windows, hideable main menu, toolbars and list headers, KFeanza-based default icon theme + ability to create your own icon themes, fully skinnable user interface + ability to create your own skins, “newspaper” view, plenty of skins, support for "feed://" URI scheme, ability to hide list of feeds/categories, open-source development model based on GNU GPL license, version 3, tabbed interface, integrated web browser with adjustable behavior + external browser support, internal web browser mouse gestures support, desktop integration via tray icon, localizations to some languages, Qt library is the only dependency, open-source development model and friendly author waiting for your feedback, no ads, no hidden costs. RSS Guard 5.2.0 changelog: Added: Feed auto-fetch can now also be delayed while Feral GameMode is active on Linux and startup auto-fetch is skipped when GameMode is already active. (#2265) WebEngine builds can now use RSS Guard generated proxy auto-config (PAC) rules so article/web browsing follows per-account and per-feed proxy settings more closely. (#2273) Generated PAC rules now also cover related subdomains and use Public Suffix List data, so feeds such as feeds.bbc.co.uk can also proxy resources from images.bbc.co.uk. (#2273) Standard feeds can now define extra proxy domains, useful when article images, stylesheets or other page resources are loaded from a CDN or another domain that should use the same feed proxy. (#2273) RSS Guard now asks for proxy credentials when a WebEngine page needs proxy authentication and can fill credentials from the current feed proxy when available. (#2273) Network settings again include an option to ignore all cookies, which clears stored cookies and prevents new cookies from being accepted. Standard RSS/ATOM feeds can now individually ignore cookies while downloading feed data. Stored cookies can now be deleted from the Tools menu. Custom skin colors can now override the feed list article count color separately from feed titles, including a separate highlighted color. (#2275) Settings dialog can now search across available settings and highlight matching controls. (#1754) Standard RSS/ATOM feeds can now optionally be reported as broken when they are valid but contain no articles. (#2039) Standard RSS/ATOM feeds can now override the application-wide feed connection timeout per feed. (#1023) Tray icon can now use a custom background color and unread-count text color, with an option to reuse the generated icon as the application icon. (#1973) Support for more benevolent parsing of Gemlog entries (#2295). Article list can now show when an article was received by RSS Guard. (#947) Feed deep discovery now actually scrapes all links found in the website and checks if they are feeds or not. This greatly enhances usability of the deep discovery mode and discovers many more feeds than before. (#2306) Search boxes now show a small dot when the feed or article list is hiding some items because of active filtering. (#873) Articles now have a shortcut-assignable action to open the homepage of the feed they belong to. (#2060) Fixed: Parallel feed updates no longer crash when multiple update results are processed at the same time. (64cf521) Links in WebEngine articles opened from feeds such as Kill the Newsletter now open correctly instead of being swallowed by the embedded page. (#2272) Relative article URLs resolution was kinda broken. (#2282) Clicking article URL did not work when the URL had "fragment" set. (#2293) The default proxy setting now uses Qt/system default proxy behavior instead of forcing no proxy. (e0263ad) WebEngine article loading now keeps the current feed context, so feed-specific proxy credentials remain available while the article page loads. (fdd0f00) Download: RSS Guard 5.2.0 (64-bit) | Portable | ~ 130.0 MB (Open Source) Link: RSS Guard Home Page | Other Operating Systems | Screenshot Get alerted to all of our Software updates on Twitter at @NeowinSoftware
    • This is gonna separate the creeps from the rest of the crowd.
  • Recent Achievements

    • Rookie
      DaviKar went up a rank
      Rookie
    • Dedicated
      HidekoYamamoto94 earned a badge
      Dedicated
    • One Month Later
      timbobit earned a badge
      One Month Later
    • One Month Later
      nates earned a badge
      One Month Later
    • Week One Done
      Almohandis earned a badge
      Week One Done
  • Popular Contributors

    1. 1
      +primortal
      462
    2. 2
      +Edouard
      161
    3. 3
      PsYcHoKiLLa
      110
    4. 4
      Michael Scrip
      83
    5. 5
      Steven P.
      69
  • Tell a friend

    Love Neowin? Tell a friend!