home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.sgi
- Path: sparky!uunet!cs.utexas.edu!sun-barr!ames!sgi!fido!fangio.asd.sgi.com!rck
- From: rck@fangio.asd.sgi.com (Robert Keller)
- Subject: Re: RV1 graphics boards on GTX machines
- Message-ID: <padg3dg@fido.asd.sgi.com>
- Keywords: RV1
- Sender: news@fido.asd.sgi.com (Usenet News Admin)
- Organization: Silicon Graphics, Inc., Mountain View, CA
- References: <95054@bu.edu>
- Date: Tue, 1 Sep 1992 17:16:54 GMT
- Lines: 29
-
- In article <95054@bu.edu> jdh@bu-pub.bu.edu (Jason Heirtzler) writes:
- >What does the "1" in RV1 refer to?
-
- It means that it is the "1" design of the RV board subsystem for
- GTX graphics. The RV2 is the second iteration.
-
- As a design matures, often a "cost reduced" version comes out to
- replace some of the more expensive portions of a board design.
- The RV1 to RV2 transition condensed three 9U vme size boards down
- to one, as well as adding h/w alu operations.
-
- >More importantly, is the performance problem anything to
- >worry about?
-
- Unless you use framebuffer alu operations a lot I wouldn't worry
- about it. In X parlance this would mean a GC's alu function being
- something other that GXcopy.
-
- >Maybe there's a snippet of code that someone
- >has that would demonstrate the problem?
-
- try "x11perf -rop GXxor -rect100"
-
- To determine extactly what kind of graphics subsystem you have:
- try running /usr/gfx/gfxinfo.
-
- relax, don't worry, have a homebrew.
-
- ...robert
-