Question

Pentium III or higher: 64-bit / 128-bit integer operations

Asked by: dude_1967

Hello,

I would like to implement various mathematical operations using relatively large integers for several highly optimized mathematical analyses in C++.

Are there simple assembly sequences, for Pentium III or higher, to program the following:

1) unsigned 64-bit * unsigned 64-bit multiply with unsigned 128-bit unsigned result.
2) unsigned 128-bit / unsigned 64-bit division with unsigned 64-bit result.
3) 64-bit unsigned + 64-bit unsigned addition with indication of carry.
4) 64-bit unsigned - 64-bit unsigned subtraction with indication of borrow.

I would really like to use SSE2 or something like that, as opposed to complicated sequences with eax:edx, etc. Most of my assembly experience is with 386 and some ID and timing stuff with CPUID and RDTSC stuff. Thus I could really use some help with the newer SSE stuff.

Are there any true 128-bit registers (or some combination registers such as the old eax:edx for old 386) for the new Pentium III and higher processors?

Thank you  very much for any assistance.

Sincerely, Chris.

This Question has been solved and asker verified All Experts Exchange premium technology solutions are available to subscription members.

Subscribe now for full access to Experts Exchange and get

Instant Access to this Solution

  • Plus...
  • 30 Day FREE access, no risk, no obligation
  • Collaborate with the world's top tech experts
  • Unlimited access to our exclusive solution database
  • Never be left without tech help again

Subscribe Now

Asked On
2003-12-11 at 05:20:40ID20822875
Tags

integer

Topic

Assembly Programming Language

Participating Experts
2
Points
500
Comments
5

Trusted by hundreds of thousands everyday for fast, accurate and reliable tech support.

  • "The time we save is the biggest benefit of Experts Exchange to Warner Bros. What could take multiple guys 2 hours or more each to find is accessed in around 15 minutes on Experts Exchange." Mike Kapnisakis, Warner Bros.
  • "Our team likes having a resource that is more secure than just using Google and most experts using this service really know their stuff. It's nice to look here first versus using Google." Dayna Sellner, Lockheed Martin
  • "Anytime that I've been stumped with a problem, 9 out of 10 times Experts Exchange has either the accepted solution or an open discussion of the potential solution to the problem." Kenny Red, eBay Inc.

See what Experts Exchange can do for you.

Got a question?

We've got the answer.

Experts Exchange has been collecting answers to technology questions since 1996…3 million and counting! If you have a question, chances are we already have your answer.

Screenshot of Experts Exchange Knowledgebase

Need individual assistance?

Our experts are ready to help.

If you can't find the exact answer you're looking for, ask our exclusive community of 50,000 experts. You’ll get a personalized answer from a trusted professional.

Screenshot of Experts Exchange Knowledgebase

Want to learn from the best?

Read articles from industry experts.

Thousands of free tech tips, tricks, how-to’s and tutorials are available in our peer reviewed articles section. See for yourself how smart our experts are, no login required.

Screenshot of an Article

Working on a long term project?

Store your work and research.

Save solutions to your questions, answers you’ve discovered through searching plus helpful articles in your personal knowledgebase for easy future access.

Screenshot of Experts Exchange Knowledgebase

Access the answers to your technology questions today.

Subscribe Now

30-day free trial. Register in 60 seconds.

What Makes Experts Exchange Unique?

Members of the expert community talk about why the experience at Experts Exchange is different than what you will find anywhere else.

Trusted by the world's most respected brands.

image of each brand's logo

Faithfully serving IT professionals since 1996.

Experts Exchange Logo

Try it out and discover for yourself.

Subscribe Now

30-day free trial. Register in 60 seconds.

Related Solutions

  1. Floating Point Optimization for Pentium III
    I have a floating-point intensive Delphi 4 code. Can the enhanced capabilities of the Pentium III be utilized with Inprise's compiler? (I have read somewhere that the PIII is capable of dual-pipelining certain floating point calcuations.)
  2. Pentium II vs Pentium III
    What is the new technology that have plug into Pentium III and not yet in Pentium II?
  3. Getting eax,edx into char[4]
    I am using Micro-C (http://www.dunfield.com) and need to access the pentium's cpu timestampusing opcode 0x0f31. I can't use the datatype "long" as that is not supported by Micro-C. I need to get the 32bit contents of the two registers eax and edx into two char[4] ar...

Free Tech Articles

  1. WARNING: 5 Reasons why you should NEVER fix a computer for free.
    It is in our nature to love the puzzle. We are obsessed. The lot of us. We love puzzles. We love the challenge. We thrive on finding the answer. We hate disarray. It bothers us deep in our soul. W...
  2. SCCM OSD Basic troubleshooting
    SCCM 2007 OSD is a fantastic way to deploy operating systems, however, like most things SCCM issues can sometimes be difficult to resolve due to the sheer volume of logs to sift through and the dispe...
  3. Migrate Small Business Server 2003 to Exchange 2010 and Windows 2008 R2
    This guide is intended to provide step by step instructions on how to migrate from Small Business Server 2003 to Windows 2008 R2 with Exchange 2010. For this migration to work you will need the fo...
  4. Create a Win7 Gadget
    This article shows you how to create a simple "Gadget" -- a sort of mini-application supported by Windows 7 and Vista. Gadgets can be dropped anywhere on the desktop to provide instant information, ...
  5. Outlook continually prompting for username and password
    There have been a lot of questions recently regarding Outlook prompting for a username and password whilst using Exchange 2007. There are a few reasons why this would happen and I will try to cover t...
  6. Backup Exchange 2010 Information Store using Windows Backup
    There seems to be quite a lot of confusion around the ability to backup Exchange 2010 using the built in Windows Backup feature. This stems from the omission of this feature prior to Exchange 2007 s...

Cloud Class Webinars

  1. Avoiding Bugs in Microsoft Access
    Alison Balter takes and in-depth look at avoiding bugs in Access. In this webinar you will learn about using the immediate window to debug your applications, invoking the debugger, using breakpoints to troubleshoot, stepping through code, setting the next statement to execute, ...
  2. Top 10 Best New Features in Visio 2010
    Scott Helmers gives live demonstrations of the top 10 new features in Visio 2010. This webinar will teach you how to create compelling diagrams by adding shapes to the page with a single click, linking the shapes in a diagram to data in Excel (or SQL Server, or SharePoint), ...
  3. IT Consultant Business Secrets Revealed
    Michael Munger, Experts Exchange tech pro and IT consultant, pulls back the curtain on his very successful businesses and answers question on every IT consultant and business owner should know about. He shares secrets on what he did to solve the 5 most common problems in IT, ...
  4. Disaster Recovery and Business Continuity
    Quest CTO, Mike Billon, gives an overview of the steps involved in building a dunamic disaster recovery plan. Through case studies and an examination of software/hardware tooles for monitoring and testing, you'll gain a better understandin of where you are, where you want ...
  5. Organize Your Visio Diagrams with Containers and Lists
    Scott Helmers uses cross functional flowcharts, wireframe diagrams, data graphic legends and seating charts to teach you: how to ustilize all three new structured diagram components in Visio 2010, the best practices for organizeing shapes in previous version of Visio, how to organize ...
  6. How to Us Objects, Properties, Events and Methods in Microsoft Access
    Alison Dalter gives an in-depbth look at objects, properties, events and methods in Microsoft Access. In this webinar you will learn about using the object browser, referring to objects, working with properties and methods, working with object variables, understanding the ...

Join the Community

Give a Little. Get a Lot.

Join the community of experts here and help other tech pros by answering question in your area of expertise. You can earn FREE access to all Experts Exchange's premium features and resources.

Join the Community

Answers

 

by: terageekPosted on 2003-12-11 at 18:14:59ID: 9925362

The PIII only supports SSE, not SSE2.
If you want to work with integers, then you want MMX (SSE works on floats, and each 128 bit register is treated as 4 parallel 32 bit floats).

You can use MMX instructions to manipulate some 64 bit values for addition and subtraction.  I believe that you can multiply 2 64-bit numbers, but you will need to specifiy if you want the low 64-bits of the result or the high 64-bits of the result.  I don't believe you can divide 128 bits by 64 bits however.

http://www.tommesani.com/MMXPrimer.html

 

by: dude_1967Posted on 2003-12-15 at 08:25:33ID: 9942661

Dear terageek,

I have been working a while with your suggestions. I think that my question was not clear. In addition, I would like to start with something a bit easier for me. Let's just examine the simple unsigned multiplication of unsigned 32-bit a * unsigned 32-bit b = unsigned 64-bit c.

I have coded this in a mixed C++ / ASM project using VC6, SP5 in the dialect of 386 assembler below.

Can this be done faster using something from the Pentium IV or higher? I was mistaken since I thought the newer stuff with SSE2 was in PIII as well. Let's look at the PIV architecture.

Let's start with this simple example. After mastering the 32 * 32 = 64 stuff, I would like to study the next level (64 bit * 64 bit = 128 bit).

Can you or anyone else please look at the sample and try to get this more modern that the 386 stuff?

Thanks once again for any help.

Sincerely, Chris.

int main(int argc, char* argv[])
{
  unsigned __int32 a = 0x33333333;
  unsigned __int32 b = 0x66666666;

  unsigned __int32 aa = 0xBBBBBBBB;
  unsigned __int32 bb = 0xEEEEEEEE;

  unsigned __int64 c, cc;

  // Multiply c  =  a *  b
  // Multiply cc = aa * bb
  __asm
  {
    mov eax, dword ptr [a]
    imul dword ptr [b]
    mov dword ptr [c], eax
    mov dword ptr [c + 4], edx

    mov eax, dword ptr [aa]
    mul dword ptr [bb]
    mov dword ptr [cc], eax
    mov dword ptr [cc + 4], edx
  }

  // Test c  =  a *  b
  unsigned __int64 t  = static_cast<unsigned __int64>( a) *  b;

  // Test cc = aa * bb
  unsigned __int64 tt = static_cast<unsigned __int64>(aa) * bb;

  // Final check.
  const bool ok = t == c && tt == cc;

  return ok ? 0 : 1;
}

 

by: terageekPosted on 2003-12-17 at 09:54:05ID: 9958278

I am not sure I can give you all of the detailed info you would need here.  Here are a couple of links to get you started...

Intel's page for the P4 has a lot of usefull articles...

http://www.intel.com/cd/ids/developer/asmo-na/eng/microprocessors/ia32/pentium4/optimization/index.htm

You will probably want to start with the P4 instruction set reference to read up on the MMX, SSE and SSE2 instructions...

http://developer.intel.com/design/pentium4/manuals/245471.htm

And if you want to get ahead of the curve, you can start reading up on the 13 new instructions in Prescott (the Pentium V?)

http://www.intel.com/cd/ids/developer/asmo-na/eng/microprocessors/ia32/pentium4/optimization/43988.htm

 

by: mtmikePosted on 2003-12-17 at 13:40:38ID: 9959981

I think the MMX/SSE/SSE2 extensions will not be very useful for what you want to accomplish. Since you are new to them, a short overview...

MMX:

This adds eight 64-bit registers (labelled mm0-mm7) and 54 instructions. The mmx instructions operate on packed dwords, words or bytes. Depending on the instruction, a 64-bit mmx operand is either treated as two dwords, four words or eight bytes. For example:

paddb mm0,mm1 ; add eight packed bytes
paddw mm0,mm1 ; add four packed words
paddd mm0,mm1 ; add two packed dwords

The instruction set contains logical, (saturating) arithmetic, multiplication, data movement, packing/unpacking and comparison operations.

Multiplication is limited to signed words. You can only compute one half of the result at a time:

pmullw mm0,mm1 ; multiply four signed words and store the low word of the result
pmulhw mm0,mm1 ; multiply four signed words and store the high word of the result

Or you can do a widening multiply-add:

pmaddwd mm0,mm1; multiply four signed words and add each pair of results.

The mmx instruction set was later extended with an unsigned multiply (P3):

pmulhuw mm0,mm1 ; multiply four unsigned words and store the high word of the result

So, doing 32 x 32 -> 64 multiply word-wise is certainly going to take a lot more instructions than the plain x86 version. Since mmx has no indication of carry, adding partial results is going to be tricky.

SSE (P3):

This adds eight 128-bit registers (xmm0-xmm7). All new sse instructions operate on packed floats. There is no support for integer arithmetic (only logical and packing instructions).

SSE2 (P4):

This adds support for doubles and some integer instructions. Of interest are:

pmuludq mm0,mm1 ; multiply two unsigned dwords to a qword
pmuludq xmm0,xmm1 ; multiply four unsigned dwords to two qwords

paddq mm0,mm1 ; qword add
paddq xmm0,xmm1 ; add two packed qwords

psubq mm0,mm1 ; qword sub
psubq xmm0,xmm1 ; substract two packed qwords

These might accelerate 32 x 32 -> 64 multiplies since you can do two of them at a time.

A 64 x 64 -> 128 multiply could be implemented by doing four 32 x 32 -> 64 multiplies (two instructions). The partial results will have to be added using plain old "adc" since sse has no carry support. The multiplies will be a little bit more efficient, but you will end up having to do a lot of register transfers.

The paddq/psubq instructions are also unsuitable for your purposes since they give no indication of carry/borrow.

There are no mmx/sse integer division instructions.

 

by: dude_1967Posted on 2003-12-17 at 23:41:58ID: 9962644

mtmike, terageek,

Thanks for the clearly thought out and relevant suggestions as well as the advise on further reading. It seems like it could take some careful design and a bit of time to work out the optimal solution. I have split the question points and now consider this topic closed for the purpooses of the forum. I'll continue working on a decent solution.

Thanks again.

Also my complements to the forum---always a source of competent information.

Sincerely, Chris.

20120131-EE-VQP-002

3 Ways to Join

30-Day Free Trial

The Experts

98% positive feedback on 31,087 answers since March 2000. angeliii is a Microsoft Most Valuable Professional for his work with MS SQL Server & Develoment.

He has also proven his knowledge of Visual Basic Programming, PHP Scripting and Oracle Databases.

The Experts

97% positive feedback on 10,752 answers since July 2000. lrmoore has more than 18 years experience in the networking industry.

The six-time Mircosoft MVPs specialties include firewalls, virtual private networking, and network management.

Testimonials

"...and excellent source for support... Kind of like having your very own IT dept." Electriciansnet

Testimonials

"I was apprehensive at signing up at first. However... it has already made my life as an IT administrator much easier." JaCrews

Testimonials

"WOW! You guys have great, active, and knowledgeable people on here." moore50

Business Clients

Business Clients

In the Press

"If you’ve got a question... Experts Exchange can supply an answer.”

In the Press

"...an invaluable aid for both IT professionals and those who require tech support."

In the Press

"where IT professionals provide quick answers on just about any topic"

Business Account Plans

Loading Advertisement...