SSE3 Royalties

ahock

Member
Nov 29, 2004
165
0
0
Hi Guys;

Just wanna ask about this. Correct me if I'm wrong but SSE1 SSE2 SSE3 are technology made by Intel. I heard AMD will incorporate SSE3 to its latest processor aside from MMX and SSE2 that they had already. Question is doeas AMD paying any royalties to Intel in borrowing this technology?
 

Nyati13

Senior member
Jan 2, 2003
785
1
76

The two companies have a lot of cross-licensing with each other, so AMD gets to use SSE3 for free, and Intel gets to use AMD64 for free.
(Of course, AMD calls their SSE3 addition "SSE3", and Intel calls their AMD64 "EMT64", because they suck)
 

Midnight Rambler

Diamond Member
Oct 9, 1999
4,200
0
0
(Of course, AMD calls their SSE3 addition "SSE3", and Intel calls their AMD64 "EMT64", because they suck)
Yeah, like AMD would have stuck with the same name if it had been INTELSSE3 instead of just SSE3. You expect Intel to associate AMD's name with it's product ? NEITHER company would so something like that ...
 

Thermalrock

Senior member
Oct 30, 2004
553
0
0
well maybe if intel would had called sse3 intelsse3, amd would have dropped the intel in it too. emt is prolly just an encrypted version of the abbreviation 'amd'. kinda rhymes too.
 

berkut7

Member
Oct 29, 2004
57
0
0
Originally posted by: Nyati13

The two companies have a lot of cross-licensing with each other, so AMD gets to use SSE3 for free, and Intel gets to use AMD64 for free.
(Of course, AMD calls their SSE3 addition "SSE3", and Intel calls their AMD64 "EMT64", because they suck)
Didn't AMD call their SSE implementation 3DNow! Proffesional or something like that?
 

jiffylube1024

Diamond Member
Feb 17, 2002
7,430
0
71
Originally posted by: berkut7
Originally posted by: Nyati13

The two companies have a lot of cross-licensing with each other, so AMD gets to use SSE3 for free, and Intel gets to use AMD64 for free.
(Of course, AMD calls their SSE3 addition "SSE3", and Intel calls their AMD64 "EMT64", because they suck)
Didn't AMD call their SSE implementation 3DNow! Proffesional or something like that?

They may have, or included SSE (1) under one of the 3DNow! revisions, but they for sure gave this up with SSE2, which they call just that. Same with the (soon to be supported) SSE3.
 

BEL6772

Senior member
Oct 26, 2004
225
0
0
Well, he did say "anything". I think hyperthreading is kind of a non-issue at this point, though. Both companies are working on multi-core products, so 'virtual' multicore is being replaced by the real deal.
 

klah

Diamond Member
Aug 13, 2002
7,070
1
0
http://www.geek.com/news/geekn.../bch20040609025489.htm

I had a chance to discuss Intel's microprocessor plans with an Intel marketing manager from Oregon. This Intel employee was able to clarify Intel's plans for both the Prescott and the Pentium M processors. Intel is planning on developing a derivative of the Pentium M for the desktop, but this new processor will not replace Prescott. The main reason for this, according to Intel, is that the Pentium M short-pipeline core is poorly suited to Hyper-Threading.

Probably the same reason it was never implemented in the A64, with higher IPC and a shorter pipeline than the p4 it doesn't help too much.

 

Duvie

Elite Member
Feb 5, 2001
16,215
0
71
Originally posted by: Midnight Rambler
(Of course, AMD calls their SSE3 addition "SSE3", and Intel calls their AMD64 "EMT64", because they suck)
Yeah, like AMD would have stuck with the same name if it had been INTELSSE3 instead of just SSE3. You expect Intel to associate AMD's name with it's product ? NEITHER company would so something like that ...


Nice answer...funny how logic passes ppl so often when it appears they really just want to take a shot at INtel or opposing cpu company...
 

ahock

Member
Nov 29, 2004
165
0
0
the story did not confirm anything but does this mean to say that we will not be seeing any Centrino laptop which supports hyper threading??????
 

Zebo

Elite Member
Jul 29, 2001
39,398
19
81
All the deals are secret and speculation from anyone in this thread... who knows?

They simply agreed to stop sueing each other back in 1995 and share some stuff. What stuff, how much, how much money involved is never talked about.

Found a link to deal:

AMD, Intel finally settle dispute
By Brian Fuller

SAN JOSE, Calif. -- It's finally over. The corporate war between Intel Corp. and Advanced Micro Devices Inc. over intellectual-property rights ended last week, when they settled all outstanding lawsuits and agreed to negotiate future cross-licensing.

The settlement covered a half-dozen cases. It came after U.S. Magistrate Patricia Trumbull, presiding over a lawsuit involving the 486, told both sides to try to work out their differences.

They then brought to a close a bitter seven-year legal battle over patent, copyright and contract-law issues that raised and answered many intellectual property questions hanging over the electronics industry. Under the settlement, all litigation involving each company will be dropped. AMD will have a perpetual license to the microcode in the Intel 386 and 486 microprocessors but agreed that it has no right to copy any other Intel microcode, including that of the Pentium, the forthcoming P6 and 486 ICE (in-circuit emulation).

Intel and AMD will negotiate a new patent cross-license agreement that will take effect Jan. 1, 1996.

AMD will pay Intel $58 million in damages related to the in-circuit emulation case. There, Judge Trumbull found that AMD illegally copied the code from Intel's microprocessor, even though AMD never enabled the code. Intel will pay AMD the $18 million awarded by an arbitrator in a dispute involving the two companies' 1976 patent cross-licensing agreement.

AMD, which will drop its antitrust case against Intel, agreed to make no more than 20 percent of its 486 processors using Intel microcode at foundries. The agreement also gives AMD and its customers a license to Intel's Crawford '338 patent, covering memory management. Intel lost its claim on that patent in a similar case involving Cyrix Corp.


http://www.eet.com/news/95/hr832.html#Monday4
--------------------------------------------------------------------------------
 

ahock

Member
Nov 29, 2004
165
0
0
wow so in the future we may see AMD64 with hyper threading support????? Do you think AMD copied presidio and pacifica that to Intel's Vanderpool and LaGrande???
 

BEL6772

Senior member
Oct 26, 2004
225
0
0
Presidio and Pacifica sound very similar to LaGrande and Vanderpool. I imagine that the two companies are sharing information and trying to standardize the interface to the technologies. It would be in the industry's best interest if the technology worked no matter whose chip was plugged in. Also, they both have to work with Microsoft, which has no desire to make two versions of software to do the same thing. They have probably agreed that if their independantly developed solutions turn out to be substantially the same that they won't sue one another. I really doubt that either company is engaged in wholesale copying, though.

BTW, EM64T stands for Extended Memory 64 Technology.
 

prd00

Junior Member
Aug 10, 2004
8
0
0
Nope.. AMD own hyperThreading patent as in here..
http://patft.uspto.gov/netacgi...16&RS=PN/5,944,816

Abstract

A microprocessor including a context file configured to store multiple contexts is provided. The microprocessor may execute multiple threads, each thread having its own context within the microprocessor. In one embodiment, the present microprocessor is capable of executing at least two threads concurrently: a task and an interrupt service routine. Interrupt service routines may be executed without disturbing a task's context and without performing a context save operation. Instead, the interrupt service routine accesses a context which is independent of the context of the task. In another embodiment, the context file includes multiple interrupt service routine contexts. Multiple ISR context storages allow for nested interrupts to be performed concurrently. In yet another embodiment, the microprocessor is configured to execute multiple tasks and multiple interrupt service routines concurrently. Multiple tasks may be executed concurrently by the microprocessor in addition to executing multiple interrupt service routines concurrently. In still another embodiment, the microprocessor includes a primary context and multiple local context storages coupled to each of its execution units. A given execution unit may execute instructions referencing the primary context or the local context connected thereto.

Inventors: Dutton; Drew J. (Austin, TX); Christie; David S. (Austin, TX); Barnes; Brian C. (Round Rock, TX)
Assignee: Advanced Micro Devices, Inc. (Sunnyvale, CA)
Appl. No.: 649809
Filed: May 17, 1996

This is just a proof that HyperThreading was AMD's invention, which Intel claimed as theirs. While AMD64 which Intel will use with EM64T is claimed as also Intel's Invention.. Wow... will they claim that telephone as theirs too? And that Bell stole their invention like they told the IDF about AMD?
Oh.. sorry.. they invented my wife.. alright.. Now tell me, who copies who??
 

prd00

Junior Member
Aug 10, 2004
8
0
0
Oh, and it is filed at 1996.. AMD already got HyperThreading technology since 1996. They just didn't use it, or perhaps use them in a way we don't recognize.
 

LTC8K6

Lifer
Mar 10, 2004
28,520
1,576
126
Yeah, AMD invented everything! :D

Too bad about that cross licensing agreement they have with Intel...... :beer:
 

prd00

Junior Member
Aug 10, 2004
8
0
0
Not exactly.. some of AMD's CPU are Intel's too, like those i386 instruction, and those K5/K6 sockets. :D
 

foxkm

Senior member
Dec 11, 2002
229
0
0
Originally posted by: berkut7
Originally posted by: Nyati13

The two companies have a lot of cross-licensing with each other, so AMD gets to use SSE3 for free, and Intel gets to use AMD64 for free.
(Of course, AMD calls their SSE3 addition "SSE3", and Intel calls their AMD64 "EMT64", because they suck)
Didn't AMD call their SSE implementation 3DNow! Proffesional or something like that?

3dNOW is a different technology than SSE. 3dNOW was introducted in mid 1998 with the K6-2 series. SSE didn't come along until 1999 when the P3 was release as a drop in replacement to the P2
 

Wingznut

Elite Member
Dec 28, 1999
16,968
2
0
Originally posted by: Gamingphreek
IIRC Intel had to pay a large sum of money for -64 bit extension. THey didn't do an even trade as SSE3 is not worth nearly as much as -64 extensions.
Where did you get that from?

 

DAPUNISHER

Super Moderator CPU Forum Mod and Elite Member
Super Moderator
Aug 22, 2001
32,039
32,524
146
Originally posted by: Wingznut
Originally posted by: Gamingphreek
IIRC Intel had to pay a large sum of money for -64 bit extension. THey didn't do an even trade as SSE3 is not worth nearly as much as -64 extensions.
Where did you get that from?
Coming here is getting to be like reading quotes from Baghdad Bob for you now isn't it?

 

Gamingphreek

Lifer
Mar 31, 2003
11,679
0
81
Originally posted by: DAPUNISHER
Originally posted by: Wingznut
Originally posted by: Gamingphreek
IIRC Intel had to pay a large sum of money for -64 bit extension. THey didn't do an even trade as SSE3 is not worth nearly as much as -64 extensions.
Where did you get that from?
Coming here is getting to be like reading quotes from Baghdad Bob for you now isn't it?

?

At any rate i posted that a while back in the Highly Technical thread. I got a very nice definition of what went on i processor extensions.

-Kevin