Summary of PCI-Survey - version 0.2 - 28.03.94 ----------------------------------------------------- (c) by Michael Will - for personal use only. michaelw@desaster.sunflower.sub.org Professional printing (as in magazines) requires special permission by the author, Michael Will. ----------------------------------------------------- * Preface Hello, Because I plan to get me a PCI-Board and because the situation is not very clear at all whether it works or not, and which configuration, I made a survery and took some hours to compile the information gathered therein. If you have information to add, please mail me, if you have questions, feel free to ask :-) Help on my style/language is welcome as well - I am no native-speaker so I expect to do occasional mistakes :-) (Speaking of "onboard-chip" in the following I mean a on-motherboard-chip instead of expansion-card. Someone pointed out to me that this might not be that obvious) * What is PCI / Why PCI The PC-architecture has several BUS-Systems to choose from: ISA cheap, slow, standard, many cards available EISA expensive, fast, some cards available MCA ex-ibm-proprietary, fast but not very wide-spread ISA/Vesa-Local-Bus cheap, fast, some cards available, not very standard PCI-Local-Bus expensive, fast, some cards available, the up-coming standard ISA/Local-Bus had some problems with high-frequenzy, and was not very relyable, but due to its low price and higher performance sold very well. EISA was reliable, but rather expensive, more for power-users, and servers, not for the average user. PCI now has the advantage, that it is like EISA not proprietary, fast as EISA (or even faster), 64bit-wide. This will be important with the i586 (they would rather like to read as Pentium). PCI is not like ISA/Local-Bus prozessor-dependend. This means you can use the winner-1000-PCI in an Alpha-driven-PCI-board as well as in a i486/i586-driven PCI-Board). * The onboard-SCSI-II-chip NCR53c810 One very nice feature of the PCI-Boards is the onboard-SCSI-II-chip, which is said to be as fast as the EISA-Adaptec-1742, but much cheaper. Drivers for DOS/OS2 are available. Linux does not have the driver yet, but Drew Eckard is working on it, the iX Multiuser Multitasking Magazine is supporting the driver development. It seems to be not yet stable-enough for release but people are already testing it... It is not easy to write the driver, because it is radicaly different from the normal NCR-Chip. Until it is finished Linux-users have to disable the chip and use a cheap ISA-Card... Drew said about the SCSI on PCI: Currently, your only PCI SCSI option that stands a chance of working is the Buslogic 946. It purports to be Adaptec 1540 compatable, like the EISA/VESA/ISA boards in the series. I'm working on getting the Linux NCR53c810 driver stable, some one else is doing the same thing for one of the BSD flavors. Fast busmaster, often included on motherboard implementations, supposedly available for $100 in card for sans BIOS (many of the PCI boards that don't include the NCR onboard still have the NCR BIOS). This covers the majority of PCI SCSI adapters on the market (Nexstor, Chaintech, Gigabyte, FIC, etc). Adaptec is shipping a FAST WIDE version of the AIC-7770 with a PCI interface, AIR is using it on their Pentium boards, but I haven't seen any board level product with it. Scott Ferris is working on the AIC-7770 driver under Linux, but I don't know of anyone doing the same thing under one of the BSDs. Emulux has a propriety FAST+WIDE PCI controller, it's unlikely that it will show up as supported under one of the BSDs or Linux anytime soon since the NCR based controllers are cheaper and more prevalant (even included on many mainboards which don't have a real price difference versus non SCSI equipped boards) and the Buslogic controllers are compatable with the 1540 so I doubt anyone will buy them. Forex is shipping a PCI SCSI adapter, I don't have details. Not every PCI-Board has got the chip. ASUS does, and one of the J-Bond-boards does, too. The NCR-Chip is clever enough to work with drives formatted by other controllers, and should be no problem. * ASUS-Board - detailed information from heinrich@zsv.gmd.de: -- 3 PCI, 4 ISA Slots (3x16, 1x8 Bit) -- ZIF Sockel for the CPU -- room for 4 72pin-Simms (max. 128M) -- Award BIOS in Flash-Eprom -- Onboard: NCR-SCSI, 1par, 2ser (with FIFO), AT-Bus, Floppy The board does like most in that price-class only write-through cache, no write-back. (which should not be grave, maybe 3% of performance?). The BIOS supports scsi-drives under DOS/Windows without additional drivers, but with the board come addtitional drivers which are said to give better performance, for DOS/Windows(ASPI), OS2, Windows-NT, SCO_Unix, Netware (3.11 and 4, if interpreted correctly) Gert Doering was saying the SCO-Unix-driver for the onboard-SCSI-Chip was not working properly. After two or three times doing: $ time dd if=/dev/rhd20 of=/dev/null bs=100k count=500 it kernel-panicked... * Video-Cards People have successfully used #9 XGE Level 12, ELSA Winner 1000 boards, and others with the S3928P under Linux. tldraben@eos.ncsu.edu said about the following cards: Diamond Stealth W32 Text mode works, X11 sufferered from "pixel dust" ET4000/W32 unbearable #9GXEL13 Works, virtual consoles corrupted when switched. Had to buy card from Dell. The people which answered where using the following boards: ASUS strauss@dagoba.escape.de - half-successful, works, but... ut@informatik.uni-kiel.d400.de - half-sucessful, works almost heinrich@zsv.gmd.de - successful CARSTEN@AWORLD.aworld.de - successful egooch@mc.com - successfull - but trouble with the serialport SPACE? ub9x@rz.uni-karlsruhe.de - successful Gateway-2000 kenf@clark.net - going to. dmarples@comms.eee.strathclyde.ac.uk - successful, but... Intel-Premier grif@cs.ucr.edu - successful Comtrade Best Buy PCI / PCI48X MB Rev 1.0 tldraben@eos.ncsu.edu - "Works, I believe it has buggy Saturn chipset" IDeal PCI / PCI48X MB Rev 1.0 tldraben@eos.ncsu.edu - "Did not work with PCI48X motherboard" CMD Tech. PCI IDE / CSA-6400C tldraben@eos.ncsu.edu - "Works" GA-486iS (Gigabyte) Stefan.Dalibor@informatik.uni-erlangen.de - success with problems. * Success: ub9x@rz.uni-karlsruhe.de with SPACE-board, 8MB RAM, S3 805 1MB DRAM PCI 260MB Seagate IDE-Harddiskdrive because of lack of NCR53c810-Driver, 0.99pl15d, does seem to work well. grif@cs.ucr.edu with 17 machines running a 60Mhz-i586 on Intel-Premier-PCI-Board heinrich@zsv.gmd.de with ASUS-PCI-Board (SP3) having: -- Asus PCI-Board with AMD 486/dx2-66 and 16M RAM -- Fujitsu 2196ESA 1G SCSI-II -- Future Domain 850MEX Controller (cheap-SCSI-Controller, almost a clone to Seagates ST01... soon there should be a driver for the onboard-NCR53c810 -Controller. -- ATI Graphics Ultra (the older one with Mach-8 Chip, ISA-Bus) -- Slackware 1.1.1 He just exchanged the boards, plugged his cards in, connected the cables, and it worked perfect. He does not use any PCI-Cards yet, though. CARSTEN@AWORLD.aworld.de with: ASUS-PCI-Board with 486DX66/2, miro-crystal 8s PCI driven by the S3-drivers of XFree86-2.0, not using the oboard SCSI-Chip yet because of lack of driver, but tried it on DOS, it was very fast. No problems with compatibility at all. * Problems: dmarples@comms.eee.strathclyde.ac.uk runns: G/W 2000 4DX2/66 PCI ATI-Graphics-Ultra-Pro IDE of indetermiate make It works nice - only the IDE-Card runs in ISA-compatibility-mode, and works a lot faster when switched into PCI-Mode by a DOS-program... thus not that fast in Linux, patch would be nice. ut@informatik.uni-kiel.d400.de has got a: ASUS-PCI board with AMD486dx40 (but actualy running at 33Mhz?!) His ISA-ET3000 Optima 1024A ISA Karte seems to block the IRQs, so he has got problems with his two serial ports. The dealer said it could even be the SIMMS, and the board would in general sometimes have problems with ATI-PCI-cards, but no problems with PCI-S3. (I wonder what this dealer is, selling a broken machine like that...) Apart from that, Linux and X-Window does seem to work nice. Frank Strauss (strauss@dagoba.escape.de) has got a: ASUS SP3 Board i486DX2/66 with NCR53c810 disabled Adaptec 1542B in ISA Slot with 2 Harddiskdrives (200MB Maxtor, 420MB Fijutsu), SyQuest 88MB and Tandberg Streamer ELSA Winner 1000 PCI, 1MB-VRAM Soundblaster Pro in ISA Slot at IRQ 5 Onboard IDE disabled Onboard serial, parallel, FD enabled - after a reset, the machine sometimes 'hangs' (soft and hard-reset the same) - this is probably not related to the Adaptec and the Soundcard, because even without these the system sometimes fails to come up. But if it runs, (and the ELSA-WINNER-1000-PCI-message appears) it runs ok. - the two serial ports are detected as 16550 as they should, but at some mailbox-sessions there was heavy data-loss at V42bis... The problem seems to be in the hardware... - CPU->PCI-Burst seems to work well with DOS/MS-Windows - CPU->PCI-Burst does not work properly with linux0.99p15, Messing up when switching the virtual-consoles, crashing completely when calling big apps like ghostview, or xdvi, leaving the SCSI-LED on (!). (I suspect these apps would be using a lot of CPU->PCI-burst because of the big heap of data to transmit to the PCI-Winner-1000) - After disabling CPU->PCI-Burst, it works well, the Winner-1000 at 1152x846 (not much fontcache with 1MB) does 93k xstones. OpaqueMove with twm is more than just endureable :-) With CPU->PCI-Burst it yielded 95k xstones, so he considers it as not too grave to do without. His only problem is that he would like to run his Winner-1000 at 1152x900 which fails because it seems to take any x-resolution higher than 1024pixels as a 1280pixel-resolution, thus wasting a lot end resulting in a y-resolution of 816pixels... but this is probably no PCI-related problem. egooch@mc.com about his board: BOARD: ASUS PCI/I-486 SP3 RAM: 16MB (4x4M-SIMM) CPU: 486DX33 CPU BIOS: Ver. 4.50 (12/30/93) Floppy: Two floppy drives (1.2 and 1.44), using ASUS on-board floppy controller SCSI: tried both WD7000 SCSI controller and Adaptec 1542CF and worked. Two SCSI 320M hard drives SCSI NEC84 CDROM drive SCSI QIC150 Archive tape drive Video: Tseng ET4000 ISA graphics card Sound: PAS16 sound card Printer attached to on-board ASUS parallel port He has nothing in the PCI-Slots yet, but wants to buy a PCI-Video-Card, currently uses WD7000 SCSI controller but will switch to the NCR-Chip onboard as soon as the driver is out. Everything works perfect - only the first serial port which has a 14.4K-Modem attached does hang occasianly after reconnecting with the modem after having used it previously. He says that would not be unique to ASUS but rather a bug in the SMC-chipset with its 16550UART. The logitech-serial-mouse on the second port works fine. Stefan.Dalibor@informatik.uni-erlangen.de runs: Board: GA-486iS from Gigabyte w/ 256Kb 2L-Cache, i486-DX2 Bios: AMI, 93/8 SCSI: no scsi-NCR-chip on-board, using Adaptec 1542C, Video: ELSA Winner 1000 Linux: 0.99pl14 + SCSI-Clustering-Patches / Slackware 1.1.1 All seems to go well, but he has not tried neither networking, printing or a streamer yet. Before applying the Clustering- patches he had some problems with hangs triggered by "find", but this no longer is the case - perhaps it was an older kernel-bug. The ELSA-Winner-1000 sometimes hangs. very strange patterns on the screen resolved only by booting... The dealer has told him it was a bug in the ELSA-Card, but the manufacturer claims it had solved the problem. The bug is not reproducable so he does not take any action at the moment. All in all the machine seems to work very well using it a lot for textprocessing (emacs, LaTeX, xfig, ghostview). Interaction is surprisingly responsive, few difference from the 3 to 4-times as expensive sun he works on... CPU->PCI-Burst is still disabled because the bios does not support the PCI-things well? * Conclusion: Not a clear one, yet... *sigh*... Most people seem to have set their heart on the ASUS-Board, two sucessful, two with Problems. I will try to get them together to check their configuration, maybe it is only a configuration-problem. * Thanks I gathered my Information mostly by mail and by three news-postings by the following people: CARSTEN@AWORLD.aworld.de dmarples@comms.eee.strathclyde.ac.uk drew@kinglear.cs.Colorado.EDU Working at the PCI-NCR53c810-Driver duncan@spd.eee.strathclyde.ac.uk fm3@irz.inf.tu-dresden.de grif@ucrengr.ucr.edu heinrich@zsv.gmd.de hm@ix.de iX-Magazine hm@seneca.ix.de kebsch.pad@sni.de kenf@clark.net matthias@penthouse.boerde.de ortloff@omega.informatik.uni-dortmund.de preberle@cip.informatik.uni-erlangen.de rob@me62.lbl.gov rsi@netcom.com sk001sp@unidui.uni-duisburg.de strauss@dagoba.escape.de strauss@dagoba.priconet.de ub9x@rz.uni-karlsruhe.de ut@informatik.uni-kiel.d400.de Stefan.Dalibor@informatik.uni-erlangen.de tldraben@eos.ncsu.edu mundkur@eagle.ece.uci.edu ooch@jericho.mc.com Gert Doering