home *** CD-ROM | disk | FTP | other *** search
- Path: nntp.teleport.com!sschaem
- From: sschaem@teleport.com (Stephan Schaem)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: Amiga doesn`t need Pl
- Date: 24 Feb 1996 15:34:02 GMT
- Organization: Teleport - Portland's Public Access (503) 220-1016
- Distribution: world
- Message-ID: <4gnb5a$3n2@maureen.teleport.com>
- References: <john.hendrikx.4gpu@grafix.xs4all.nl>
- NNTP-Posting-Host: kelly.teleport.com
- X-Newsreader: TIN [version 1.2 PL2]
-
- John Hendrikx (john.hendrikx@grafix.xs4all.nl) wrote:
- : The 'copying' loop simply doesn't exist on the clones, just paste it wherever
- : you want it in the gfx-buffer and be done with it. This is likely to be as
- : fast as a DOOM clone of the A1200 but with the C2P pass disabled (ie, no
- : display).
-
- By past you mean copy from local mem to gfx card mem.... like fastmem to
- chipmem. C2P is a small factor added to the copy, mainly because the
- problem is really slow 'gfx card'/chip mem on the amiga.
-
- : There is no Amiga with the same power as the P133. And my 'average' (and 2
- : year old $100) VLB Gfx card handles 15 MB/sec easily, more than enough to do
- : 640x480 in 2 frames.
-
- I would like to compare the latest gouraud/tmap loop on 68060 VS P5
- runing all in the L1 cache. My guess is that is take more then 2x
- the mhz for the pentium to get the same number of pixel rendered.
- But out of the chip, expensive l2 cache and boosted mhz make a diference
- in the overall performance.
- The cpu is not the problem, the amiga HW (From CBM) sux big time.
-
- : There is no (good) clone because it requires a 040 + fast Chunky gfx-card,
- : period. Caused of course by the fact that 040 + fast Chunky gfx-card is a rare
- : combination found in the Amiga world.
-
- The CPU is not the problem... and 030 can render doom in 'fastmem' 'easy'.
- The killing factor is the slow video memory. an 030 compete easy with
- a 486 in integer operation (mhz for mhz, not on an inst basis but on an
- overall small cached loop... like tmap)
-
- : >> >makes it worse though, on Amiga you'd require a 68060 to do fast DOOM (
-
- : JrF> the C2P problem on 040 is a PCer myth! C2P doesn't make it worse.
-
- : Yes it does, see TextDemo. The percentage of CPU time used for the C2P is
- : NON-EXISTANT on the clones, because the 'fast-ram buffer' we use on Amiga is
- : called 'the screen' on the clones. No extra copying (or converting for that
- : matter) needed.
-
- Again the problem is not c2p but slow video memory...Does PC alway cache
- video memory on the L1 cache? I hear many people rendering in local mem
- then doing a copy.
-
- : That's TextDemo 5.7x (unreleased version) someone tested for me. 15-20 FPS for
- : a 68060/50 which is supposed to be 2-3 times as powerfull as a 486DX2/50 is
- : quite depressing, considering that that 486 will do it at 30 FPS. Now just
- : translate that to the slower Amiga's (ie, the ones only equipped with 030's and
- : 040's).
-
- 1.2 meg , around 15frames second used to copy the fastmem buffer to chip. So
- 100mips*75% / 320*200*20 = 58.5 cycle per pixel rendered in 060 local mem!
- that is HUGE! when you know that a 040 need ~10 cycle per pixel to do
- floor/ceiling gouraud shaded texture mapping. why would a 50mhz 060 be 6
- time slower then a 40mhz 040 when working only in local fastmem?!?!!!?!??!!?
- (I assume here that you do gouraud shade your quads)
-
- If you imagine you set the fps at 35fps (max doom ever gonna go on any
- PC), this shouldnt take more then 50% of the 040/060 to update from
- fast to chip.... now dont tell me you cant render 35fps on a 25mhz 060?!
-
- Now if you tell me that textdemo do bump mapping and 3 axis free rotation
- I would say that 15-20 fps is pretty good :)
-
- Stephan
-