What in the world does MMX+ do?

[PCfreak15]

What programs would possibly benefit from MMX+? Also the K7 was already faster than any intel P6 cpu so why extend MMX?

Pentium 4 2.4(B)GHz
i845PE, NO INTEGRATED 3D DECCELERATOR HERE!
512MB PC2700 DDR-SDRAM CL2.5
Dual 80GB Hard Drives 7200RPM 2M/8M ATA100
ATi Radeon 9600 Pro 128MB 4xAGP

 

[Spitfire_x86]

MMX+ is actually partial SSE (Integer SSE). Early Athlons/Durons & "T-bird" Athons didn't have complete SSE suppot. MMX+ is another name of the partial SSE support of these CPUs

------------
<A HREF="http://geocities.com/spitfire_x86" target="_new">My Website</A>

<A HREF="http://geocities.com/spitfire_x86/myrig.html" target="_new">My Rig</A> & <A HREF="http://geocities.com/spitfire_x86/benchmark.html" target="_new">3DMark score</A>

 

[Crashman]

LOL, you really are a freak! The Coppermine core was faster than the original K7! I know you'll go nuts and say something crazy, but facts are facts: The PIII with off-die cache was kinda slow, the K7 with off-die cache was a little faster, the Coppermine (onboard cache) was faster than the K7 with off-die cache, the Thuderbird was faster than the Coppermine, the PIII Tualatin was faster than the Thunderbird. So in all cases PIII had the last laugh, or did they? The XP processors came next, and were faster than the Tualatin. Also, I think they were introduced before the Tualatin. But wait, there's more! If you're going to call the XP processors a K7, then you'll also want to call the Pentium M a P6, which means that it's faster (clock for clock)! LOL. But of course the K7 by that definition goes all the way up to 2.33GHz, so it still wins by being clocked higher.

There goes your proof for the K7 always being faster than the P6. It was always a horse race, AMD won by producing faster clocked CPU's.

<font color=blue>Only a place as big as the internet could be home to a hero as big as Crashman!</font color=blue>
<font color=red>Only a place as big as the internet could be home to an ego as large as Crashman's!</font color=red>

 

[Spitfire_x86]

If you're going to call the XP processors a K7, then you'll also want to call the Pentium M a P6, which means that it's faster (clock for clock)

AXP is of course K7. Difference between T-bird and Palomino is much less than difference between Tualatin and Pentium-M.

IMO, Barton vs. K8(minus x86-64) = Tualatin vs. Pentium-M

------------
<A HREF="http://geocities.com/spitfire_x86" target="_new">My Website</A>

<A HREF="http://geocities.com/spitfire_x86/myrig.html" target="_new">My Rig</A> & <A HREF="http://geocities.com/spitfire_x86/benchmark.html" target="_new">3DMark score</A>

 

[endyen]

The t-bred is closer to the A64 than the P111 is to the P-M.
Those extra 5 pipes are really deep.

 

[Crashman]

Can't forget the barton! PIII-Tualatin was easily perceivable as faster than the XP1600+ (same clock speed), but darned if it could compete against a 1400MHz (underclocked by multiplier) Barton.

<font color=blue>Only a place as big as the internet could be home to a hero as big as Crashman!</font color=blue>
<font color=red>Only a place as big as the internet could be home to an ego as large as Crashman's!</font color=red>

 

[PCfreak15]

Well in most benchmarks the K7 beat the copprmine until the external cache on athlon was dropped to 1/3 speed. Around 900 to 1000MHz the coppermine could compete but not win. Atleast in FPU apps like games and video/audio. I'm an intel fan but I have to admit athlon had PIII beat. Check www.anandtech.com for older articles on the two CPUs, tomshardware is very intel biased.

Pentium 4 2.4(B)GHz
i845PE, NO INTEGRATED 3D DECCELERATOR HERE!
512MB PC2700 DDR-SDRAM CL2.5
Dual 80GB Hard Drives 7200RPM 2M/8M ATA100
ATi Radeon 9600 Pro 128MB 4xAGP