What the PS2 can do
- Thread starter tsumake
- Start date
- Status
sorry antime, should have been more specific.
The EE VU0 and VU1 both are designed to deal with floating point operations; hence being based on a 128kbit instruction length. The SH-4 (SH7750) has fixed length 16kbit instruction, but can also use 64bit for floating point.
The SH7750 has also got variable external data paths that can be configured to 8,16,32 or 64bits. The MMU in the SH7750 can also be scaled to match cache size. Also, variable bit depths (16,32,64,128)available to the SH7750 make it more capable of being optimized to deal with tasks that involve the use of smaller intergers.
What i'm trying to get is the SH-4 is more suited to 2D than the EE and its fixed instruction lengths in VU0 and VU1 which are used as the backbone of the chips number crunching power.
The EE VU0 and VU1 both are designed to deal with floating point operations; hence being based on a 128kbit instruction length. The SH-4 (SH7750) has fixed length 16kbit instruction, but can also use 64bit for floating point.
The SH7750 has also got variable external data paths that can be configured to 8,16,32 or 64bits. The MMU in the SH7750 can also be scaled to match cache size. Also, variable bit depths (16,32,64,128)available to the SH7750 make it more capable of being optimized to deal with tasks that involve the use of smaller intergers.
What i'm trying to get is the SH-4 is more suited to 2D than the EE and its fixed instruction lengths in VU0 and VU1 which are used as the backbone of the chips number crunching power.
<!--QuoteBegin-antime@Wed, 2004-11-03 @ 06:08 AM
You are seriously confused, and that makes no sense at all.
[post=122619]Quoted post[/post]
[/quote]
sorry, ill explain better.
ee is designed to deal specifically with 128bit intergers (VU0, VU1)
sh7750 is designed to deal with 16bit intergers via hardware not software implementation.
3d requires floating point ops, but 2d calculations don't require the same accuracy so 16bit is more efficient,... yes?
unless you are doing some crazy look ups or fractals
Do any PS2 games use native progressive output? I can't play 2D PS2 games on my friend's HDTV without gagging. He needs to get like an upscan converter. The interlacing artifacts are ugly and annoying. He had similar problems with his Xbox until I smacked him on the head and told him to go get a friggin YPbPr hookup, so he could enjoy progressive display.
Edit: Yes, I know its his TV's fault. But it's got a DVI port, so a decent upscan converter should do the job better, I would think.
Edit: Yes, I know its his TV's fault. But it's got a DVI port, so a decent upscan converter should do the job better, I would think.
antime
Extra Hard Mid Boss
Using wide registers for calculating small values only means you have a larger number of empty bits in the result. I really do recommend you actually read up on how the two processors work, your earlier statements make it painfully obvious you are seriously misinformed.
Instruction length has essentially nothing to do with what type of math is being used, and VU0/1 have a 32-bit (not kbit) instruction length. I think you mean register width, but even in that case they do have 16 32-bit integer registers, just like SH-4 (and this is ignoring the fact that EE also has a fast MIPS core with its own integer registers and ALU).
The SuperH instruction set does consist of 16-bit instructions, but the instruction width has nothing to do with the register or ALU width (the EE MIPS core for example has 32-bit instruction length but 128-bit registers)
This is a bus interface feature and is transparent to an application programmer. It's for connecting peripherals and memories of different widths and having them all work correctly without having to demangle the words in software. EE doesn't have this problem since it is a custom chip that was designed for PS2.
I have no idea what you mean by this, and I've read Chapter 3 of the SH7750 manual several times.
If you only want a smaller result, you simply ignore the high bits.
SH-4, VU, and MIPS processors all have fixed-length instructions. And the MIPS core in the EE can take the SH7750 to school in integer ops with both VU procs tied behind its back.
Luckily someone came to your rescue.
Take a look at this though,
http://www.digitpress.com/forum/viewtopic....=asc&highlight=
i decided to hold the poll in neutral territory for your sake. I am will to furhter test any of your hypothosees there. But i have my imperical data.
- Status
Similar threads
