Message-ID: <3E550374.9689AEF@yahoo.com> From: CBFalconer Reply-To: cbfalconer@worldnet.att.net Organization: Ched Research X-Mailer: Mozilla 4.75 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) References: <3e4e51f7.231256839@news.eircom.net> <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> <3e53eff2$1$wg$mr2ice@news.fltg.net> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Lines: 38 Date: Thu, 20 Feb 2003 16:42:03 GMT NNTP-Posting-Host: 12.90.174.115 X-Complaints-To: abuse@worldnet.att.net X-Trace: bgtnsc04-news.ops.worldnet.att.net 1045759323 12.90.174.115 (Thu, 20 Feb 2003 16:42:03 GMT) NNTP-Posting-Date: Thu, 20 Feb 2003 16:42:03 GMT Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.mailgate.org!newsfeed.icl.net!newsfeed.fjserv.net!news-FFM2.ecrc.net!feed2.news.rcn.net!rcn!wn14feed!worldnet.att.net!bgtnsc04-news.ops.worldnet.att.net.POSTED!not-for-mail Xref: chonsp.franklin.ch alt.folklore.computers:129489 "J. Clarke" wrote: > On Wed, 19 Feb 2003 15:57:32 -0500, Julian Thomas wrote: > > J. Clarke > > > may have used oatmeal boxes, old string, > > and new, used, and recycled electrons to say (at least in part): > > > >> Whether a PC has ECC or not is buyer's choice. Nearly all server > >> and workstation class machines can support it if the purchaser > >> chooses to put in the appropriate RAM modules. Some "desktop" > >> and consumer machines can support it as well. The machine I'm > >> using right now has ECC "from the CPU cache out to memory and > >> back again" > > > > These days there are very few motherboards for Thunderbird that > > offer ECC. Epox 8k7a seems to be almost the only one, and that's > > not widely available. > > Any of the 762 boards will support ECC. The 761 chipset has the > necessary support however vendors seem to not enable it. Trouble > with AMD is that most of the vendors are targetting the consumer > market, not the workstation/server market, and in the consumer > market for those who even know that ECC exists, it is considered > to be undesirable because there is an infinitesimal performance > penalty that might cost a tenth of an FPS in Quake. And also the 'saving' of approximately 10% of the memory cost, to be repaid many times over the first time something is destroyed by any memory failures. I would almost rather buy day old hamburger that has been kept in the sun. -- Chuck F (cbfalconer@yahoo.com) (cbfalconer@worldnet.att.net) Available for consulting/temporary embedded and systems. USE worldnet address! ###### From: "J. Clarke" Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) Date: Thu, 20 Feb 2003 12:02:42 -0500 Organization: http://extra.newsguy.com Lines: 43 Message-ID: References: <3e4e51f7.231256839@news.eircom.net> <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> <3e53eff2$1$wg$mr2ice@news.fltg.net> <3E550374.9689AEF@yahoo.com> NNTP-Posting-Host: p-936.newsdawg.com Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit User-Agent: Pan/0.13.3 (That cat's something I can't explain) Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.mailgate.org!newsfeed.stueberl.de!logbridge.uoregon.edu!pln-e!spln!dex!extra.newsguy.com!newsp.newsguy.com!enews1 Xref: chonsp.franklin.ch alt.folklore.computers:129461 On Thu, 20 Feb 2003 16:42:03 +0000, CBFalconer wrote: > "J. Clarke" wrote: >> On Wed, 19 Feb 2003 15:57:32 -0500, Julian Thomas wrote: >> > J. Clarke >> >> > may have used oatmeal boxes, old string, and new, used, and recycled >> > electrons to say (at least in part): >> > >> >> Whether a PC has ECC or not is buyer's choice. Nearly all server >> >> and workstation class machines can support it if the purchaser >> >> chooses to put in the appropriate RAM modules. Some "desktop" and >> >> consumer machines can support it as well. The machine I'm using >> >> right now has ECC "from the CPU cache out to memory and back again" >> > >> > These days there are very few motherboards for Thunderbird that offer >> > ECC. Epox 8k7a seems to be almost the only one, and that's not widely >> > available. >> >> Any of the 762 boards will support ECC. The 761 chipset has the >> necessary support however vendors seem to not enable it. Trouble with >> AMD is that most of the vendors are targetting the consumer market, not >> the workstation/server market, and in the consumer market for those who >> even know that ECC exists, it is considered to be undesirable because >> there is an infinitesimal performance penalty that might cost a tenth >> of an FPS in Quake. > > And also the 'saving' of approximately 10% of the memory cost, to be > repaid many times over the first time something is destroyed by any > memory failures. Sometimes. But remember, some of these are the folks who run RAID 1 and shell out 700 bucks for a Vapochill or Prometeia phase-change cooler in the hopes of running their P4 at 3.5 GHz. > I would almost rather buy day old hamburger that has been kept in the > sun. -- --John Reply to jclarke at ae tee tee global dot net (was jclarke at eye bee em dot net) ###### X-Trace-PostClient-IP: 68.147.131.211 From: Brian Inglis Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) Organization: Systematic Software Reply-To: Brian.Inglis@SystematicSw.ab.ca Message-ID: References: <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> <3e53eff2$1$wg$mr2ice@news.fltg.net> <3E550374.9689AEF@yahoo.com> X-Newsreader: Forte Agent 1.92/32.572 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Lines: 58 Date: Mon, 24 Feb 2003 06:53:01 GMT NNTP-Posting-Host: 24.71.223.147 X-Complaints-To: abuse@shaw.ca X-Trace: news3.calgary.shaw.ca 1046069581 24.71.223.147 (Sun, 23 Feb 2003 23:53:01 MST) NNTP-Posting-Date: Sun, 23 Feb 2003 23:53:01 MST Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.mailgate.org!cyclone.bc.net!sjc70.webusenet.com!news.webusenet.com!pd2nf1so.cg.shawcable.net!residential.shaw.ca!news3.calgary.shaw.ca.POSTED!not-for-mail Xref: chonsp.franklin.ch alt.folklore.computers:130120 On Thu, 20 Feb 2003 12:02:42 -0500 in alt.folklore.computers, "J. Clarke" wrote: >On Thu, 20 Feb 2003 16:42:03 +0000, CBFalconer wrote: > >> "J. Clarke" wrote: >>> On Wed, 19 Feb 2003 15:57:32 -0500, Julian Thomas wrote: >>> > J. Clarke >>> >>> > may have used oatmeal boxes, old string, and new, used, and recycled >>> > electrons to say (at least in part): >>> > >>> >> Whether a PC has ECC or not is buyer's choice. Nearly all server >>> >> and workstation class machines can support it if the purchaser >>> >> chooses to put in the appropriate RAM modules. Some "desktop" and >>> >> consumer machines can support it as well. The machine I'm using >>> >> right now has ECC "from the CPU cache out to memory and back again" >>> > >>> > These days there are very few motherboards for Thunderbird that offer >>> > ECC. Epox 8k7a seems to be almost the only one, and that's not widely >>> > available. >>> >>> Any of the 762 boards will support ECC. The 761 chipset has the >>> necessary support however vendors seem to not enable it. Trouble with >>> AMD is that most of the vendors are targetting the consumer market, not >>> the workstation/server market, and in the consumer market for those who >>> even know that ECC exists, it is considered to be undesirable because >>> there is an infinitesimal performance penalty that might cost a tenth >>> of an FPS in Quake. >> >> And also the 'saving' of approximately 10% of the memory cost, to be >> repaid many times over the first time something is destroyed by any >> memory failures. > >Sometimes. But remember, some of these are the folks who run RAID 1 and >shell out 700 bucks for a Vapochill or Prometeia phase-change cooler in >the hopes of running their P4 at 3.5 GHz. I'd think ECC would be an essential protective investment if you're paying serious money for speed, and not just trying to get a few extra percent of something for no cost. IMHO you can't detect any difference unless you can double the speed of a system, or push response below the annoyance threshold of whatever you're trying to do. >> I would almost rather buy day old hamburger that has been kept in the >> sun. I'm not sure Suns have enough cooling for that to be safe! Thanks. Take care, Brian Inglis Calgary, Alberta, Canada -- Brian.Inglis@CSi.com (Brian dot Inglis at SystematicSw dot ab dot ca) fake address use address above to reply abuse@aol.com tosspam@aol.com abuse@att.com abuse@earthlink.com abuse@hotmail.com abuse@mci.com abuse@msn.com abuse@sprint.com abuse@yahoo.com abuse@cadvision.com abuse@shaw.ca abuse@telus.com abuse@ibsystems.com uce@ftc.gov spam traps ###### From: "J. Clarke" Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) Date: Mon, 24 Feb 2003 09:53:02 -0500 Organization: http://extra.newsguy.com Lines: 64 Message-ID: References: <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> <3e53eff2$1$wg$mr2ice@news.fltg.net> <3E550374.9689AEF@yahoo.com> NNTP-Posting-Host: p-379.newsdawg.com Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit User-Agent: Pan/0.13.3 (That cat's something I can't explain) Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.imp.ch!news.imp.ch!snoopy.risq.qc.ca!newsfeed.telusplanet.net!pln-e!spln!dex!extra.newsguy.com!newsp.newsguy.com!enews3 Xref: chonsp.franklin.ch alt.folklore.computers:130087 On Mon, 24 Feb 2003 06:53:01 +0000, Brian Inglis wrote: > On Thu, 20 Feb 2003 12:02:42 -0500 in alt.folklore.computers, "J. > Clarke" wrote: > >>On Thu, 20 Feb 2003 16:42:03 +0000, CBFalconer wrote: >> >>> "J. Clarke" wrote: >>>> On Wed, 19 Feb 2003 15:57:32 -0500, Julian Thomas wrote: >>>> > J. Clarke >>>> >>>> > may have used oatmeal boxes, old string, and new, used, and >>>> > recycled electrons to say (at least in part): >>>> > >>>> >> Whether a PC has ECC or not is buyer's choice. Nearly all server >>>> >> and workstation class machines can support it if the purchaser >>>> >> chooses to put in the appropriate RAM modules. Some "desktop" and >>>> >> consumer machines can support it as well. The machine I'm using >>>> >> right now has ECC "from the CPU cache out to memory and back >>>> >> again" >>>> > >>>> > These days there are very few motherboards for Thunderbird that >>>> > offer ECC. Epox 8k7a seems to be almost the only one, and that's >>>> > not widely available. >>>> >>>> Any of the 762 boards will support ECC. The 761 chipset has the >>>> necessary support however vendors seem to not enable it. Trouble >>>> with AMD is that most of the vendors are targetting the consumer >>>> market, not the workstation/server market, and in the consumer market >>>> for those who even know that ECC exists, it is considered to be >>>> undesirable because there is an infinitesimal performance penalty >>>> that might cost a tenth of an FPS in Quake. >>> >>> And also the 'saving' of approximately 10% of the memory cost, to be >>> repaid many times over the first time something is destroyed by any >>> memory failures. >> >>Sometimes. But remember, some of these are the folks who run RAID 1 and >>shell out 700 bucks for a Vapochill or Prometeia phase-change cooler in >>the hopes of running their P4 at 3.5 GHz. > > I'd think ECC would be an essential protective investment if you're > paying serious money for speed, and not just trying to get a few extra > percent of something for no cost. IMHO you can't detect any difference > unless you can double the speed of a system, or push response below the > annoyance threshold of whatever you're trying to do. Overclocking is the computer equivalent of hotrodding. Not much practical utility but can be fun if your mind goes in that direction. Always cracks me up the way these kids talk about one machine which has 2% better performance than another "kicking it's ass" or "wiping the floor with it". >>> I would almost rather buy day old hamburger that has been kept in the >>> sun. > > I'm not sure Suns have enough cooling for that to be safe! > > Thanks. Take care, Brian Inglis Calgary, Alberta, Canada -- --John Reply to jclarke at ae tee tee global dot net (was jclarke at eye bee em dot net) ###### From: "Helmut P. Einfalt" Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) Date: Mon, 24 Feb 2003 16:06:47 -0000 Organization: T-Online Lines: 12 Message-ID: References: <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> <3e53eff2$1$wg$mr2ice@news.fltg.net> <3E550374.9689AEF@yahoo.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit X-Trace: news.t-online.com 1046102833 07 21488 kglkEwlVS5A-1H 030224 16:07:13 X-Complaints-To: abuse@t-online.com X-Sender: 340076712632-0001@t-dialin.net X-Newsreader: Microsoft Outlook Express 4.72.3110.5 X-MimeOLE: Produced By Microsoft MimeOLE V4.72.3110.3 Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.mailgate.org!newsfeed.icl.net!newsfeed.fjserv.net!kibo.news.demon.net!demon!newsfeed.vmunix.org!newsfeed01.sul.t-online.de!newsmm00.sul.t-online.com!t-online.de!news.t-online.com!not-for-mail Xref: chonsp.franklin.ch alt.folklore.computers:130067 >Always cracks me up the way these kids talk about >one machine which has 2% better performance than another... ...and bear in mind that it is *benchmark* perfomance more often than not...! Helmut -- Brought to you by IBM PS/2 power ###### From: "J. Clarke" Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) Date: Mon, 10 Mar 2003 12:15:53 -0500 Organization: http://extra.newsguy.com Lines: 44 Message-ID: References: <3e4e51f7.231256839@news.eircom.net> <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> <3e53eff2$1$wg$mr2ice@news.fltg.net> <3E550374.9689AEF@yahoo.com> NNTP-Posting-Host: p-439.newsdawg.com Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit User-Agent: Pan/0.13.3 (That cat's something I can't explain) Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.imp.ch!news.imp.ch!newsfeed.stueberl.de!cox.net!border3.nntp.aus1.giganews.com!nntp.giganews.com!newsfeed1.easynews.com!easynews.com!easynews!pln-e!spln!dex!extra.newsguy.com!newsp.newsguy.com!enews2 Xref: chonsp.franklin.ch alt.folklore.computers:131660 On Thu, 20 Feb 2003 16:42:03 +0000, CBFalconer wrote: > "J. Clarke" wrote: >> On Wed, 19 Feb 2003 15:57:32 -0500, Julian Thomas wrote: >> > J. Clarke >> >> > may have used oatmeal boxes, old string, >> > and new, used, and recycled electrons to say (at least in part): >> > >> >> Whether a PC has ECC or not is buyer's choice. Nearly all server >> >> and workstation class machines can support it if the purchaser >> >> chooses to put in the appropriate RAM modules. Some "desktop" >> >> and consumer machines can support it as well. The machine I'm >> >> using right now has ECC "from the CPU cache out to memory and >> >> back again" >> > >> > These days there are very few motherboards for Thunderbird that >> > offer ECC. Epox 8k7a seems to be almost the only one, and that's >> > not widely available. >> >> Any of the 762 boards will support ECC. The 761 chipset has the >> necessary support however vendors seem to not enable it. Trouble >> with AMD is that most of the vendors are targetting the consumer >> market, not the workstation/server market, and in the consumer >> market for those who even know that ECC exists, it is considered >> to be undesirable because there is an infinitesimal performance >> penalty that might cost a tenth of an FPS in Quake. > > And also the 'saving' of approximately 10% of the memory cost, to > be repaid many times over the first time something is destroyed by > any memory failures. Sometimes. But remember, some of these are the folks who run RAID 1 and shell out 700 bucks for a Vapochill or Prometeia phase-change cooler in the hopes of running their P4 at 3.5 GHz. > I would almost rather buy day old hamburger that has been kept in > the sun. -- --John Reply to jclarke at ae tee tee global dot net (was jclarke at eye bee em dot net) ###### From: jmfbahciv@aol.com Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) Date: Tue, 11 Mar 03 12:47:30 GMT Organization: UltraNet Communications, Inc. Lines: 45 Message-ID: References: <3e4e51f7.231256839@news.eircom.net> <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> X-Trace: UmFuZG9tSVZhMn5AUt2b7+qswrzB0NnznvRmtMEca6EbP1NXtvKgTcRHDQVmI4Lk X-Complaints-To: abuse@rcn.com NNTP-Posting-Date: 11 Mar 2003 13:33:07 GMT X-Newsreader: News Xpress Version 1.0 Beta #4 Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.imp.ch!news.imp.ch!snoopy.risq.qc.ca!headwall.stanford.edu!newsfeed.stanford.edu!logbridge.uoregon.edu!feed2.news.rcn.net!feed1.news.rcn.net!rcn!207-172-216-30 Xref: chonsp.franklin.ch alt.folklore.computers:131760 In article , "J. Clarke" wrote: >On Thu, 20 Feb 2003 16:42:03 +0000, CBFalconer wrote: > >> "J. Clarke" wrote: >>> On Wed, 19 Feb 2003 15:57:32 -0500, Julian Thomas wrote: >>> > J. Clarke >>> >>> > may have used oatmeal boxes, old string, >>> > and new, used, and recycled electrons to say (at least in part): >>> > >>> >> Whether a PC has ECC or not is buyer's choice. Nearly all server >>> >> and workstation class machines can support it if the purchaser >>> >> chooses to put in the appropriate RAM modules. Some "desktop" >>> >> and consumer machines can support it as well. The machine I'm >>> >> using right now has ECC "from the CPU cache out to memory and >>> >> back again" >>> > >>> > These days there are very few motherboards for Thunderbird that >>> > offer ECC. Epox 8k7a seems to be almost the only one, and that's >>> > not widely available. >>> >>> Any of the 762 boards will support ECC. The 761 chipset has the >>> necessary support however vendors seem to not enable it. Trouble >>> with AMD is that most of the vendors are targetting the consumer >>> market, not the workstation/server market, and in the consumer >>> market for those who even know that ECC exists, it is considered >>> to be undesirable because there is an infinitesimal performance >>> penalty that might cost a tenth of an FPS in Quake. >> >> And also the 'saving' of approximately 10% of the memory cost, to >> be repaid many times over the first time something is destroyed by >> any memory failures. > >Sometimes. But remember, some of these are the folks who run RAID 1 and shell out >700 bucks for a Vapochill or Prometeia phase-change cooler in the hopes of >running their P4 at 3.5 GHz. My brain has spazzed. I read this and immediately thought of very expensive moon cheese. Sorry, John. /BAH Subtract a hundred and four for e-mail. ###### X-Trace-PostClient-IP: 68.147.131.211 From: Brian Inglis Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) Organization: Systematic Software Reply-To: Brian.Inglis@SystematicSw.ab.ca Message-ID: References: <3e4e51f7.231256839@news.eircom.net> <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> <3e53eff2$1$wg$mr2ice@news.fltg.net> <3E550374.9689AEF@yahoo.com> X-Newsreader: Forte Agent 1.92/32.572 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Lines: 51 Date: Tue, 11 Mar 2003 06:13:22 GMT NNTP-Posting-Host: 24.71.223.147 X-Complaints-To: abuse@shaw.ca X-Trace: news1.calgary.shaw.ca 1047363202 24.71.223.147 (Mon, 10 Mar 2003 23:13:22 MST) NNTP-Posting-Date: Mon, 10 Mar 2003 23:13:22 MST Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.mailgate.org!newsfeed.stueberl.de!cox.net!pd2nf1so.cg.shawcable.net!residential.shaw.ca!news1.calgary.shaw.ca.POSTED!not-for-mail Xref: chonsp.franklin.ch alt.folklore.computers:131811 On Mon, 10 Mar 2003 12:15:53 -0500 in alt.folklore.computers, "J. Clarke" wrote: >On Thu, 20 Feb 2003 16:42:03 +0000, CBFalconer wrote: > >> "J. Clarke" wrote: >>> On Wed, 19 Feb 2003 15:57:32 -0500, Julian Thomas wrote: >>> > J. Clarke >>> >>> > may have used oatmeal boxes, old string, >>> > and new, used, and recycled electrons to say (at least in part): >>> > >>> >> Whether a PC has ECC or not is buyer's choice. Nearly all server >>> >> and workstation class machines can support it if the purchaser >>> >> chooses to put in the appropriate RAM modules. Some "desktop" >>> >> and consumer machines can support it as well. The machine I'm >>> >> using right now has ECC "from the CPU cache out to memory and >>> >> back again" >>> > >>> > These days there are very few motherboards for Thunderbird that >>> > offer ECC. Epox 8k7a seems to be almost the only one, and that's >>> > not widely available. >>> >>> Any of the 762 boards will support ECC. The 761 chipset has the >>> necessary support however vendors seem to not enable it. Trouble >>> with AMD is that most of the vendors are targetting the consumer >>> market, not the workstation/server market, and in the consumer >>> market for those who even know that ECC exists, it is considered >>> to be undesirable because there is an infinitesimal performance >>> penalty that might cost a tenth of an FPS in Quake. >> >> And also the 'saving' of approximately 10% of the memory cost, to >> be repaid many times over the first time something is destroyed by >> any memory failures. > >Sometimes. But remember, some of these are the folks who run RAID 1 and shell out >700 bucks for a Vapochill or Prometeia phase-change cooler in the hopes of >running their P4 at 3.5 GHz. And what effect does the extra speed have on the on-chip cache? Is the non-trivial benchmark performance increase anything like the cycle speed increase? Thanks. Take care, Brian Inglis Calgary, Alberta, Canada -- Brian.Inglis@CSi.com (Brian dot Inglis at SystematicSw dot ab dot ca) fake address use address above to reply abuse@aol.com tosspam@aol.com abuse@att.com abuse@earthlink.com abuse@hotmail.com abuse@mci.com abuse@msn.com abuse@sprint.com abuse@yahoo.com abuse@cadvision.com abuse@shaw.ca abuse@telus.com abuse@ibsystems.com uce@ftc.gov spam traps ###### From: "J. Clarke" Newsgroups: comp.os.vms,alt.folklore.computers Subject: Re: ECC (was IBM says AMD dead in 5yrs ... -- Microsoft Monopoly vs. IBM monopoly) Date: Tue, 11 Mar 2003 12:50:19 -0500 Organization: http://extra.newsguy.com Lines: 56 Message-ID: References: <3e4e51f7.231256839@news.eircom.net> <3e4ebc62.258504087@news.eircom.net> <3E4EC55B.4000204@fsi.net> <3e4f144f$0$192$75868355@news.frii.net> <3E50446A.5839564E@cits1.stanford.edu> <3E510611.C9CDB7F4@yahoo.com> <3e53eff2$1$wg$mr2ice@news.fltg.net> <3E550374.9689AEF@yahoo.com> NNTP-Posting-Host: p-304.newsdawg.com Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit User-Agent: Pan/0.13.4 (She had eyes like strange sins.) Path: chonsp.franklin.ch!pfaff.ethz.ch!news-zh.switch.ch!news.mailgate.org!cyclone.bc.net!logbridge.uoregon.edu!pln-e!spln!dex!extra.newsguy.com!newsp.newsguy.com!enews2 Xref: chonsp.franklin.ch alt.folklore.computers:131787 On Tue, 11 Mar 2003 06:13:22 +0000, Brian Inglis wrote: > On Mon, 10 Mar 2003 12:15:53 -0500 in alt.folklore.computers, "J. > Clarke" wrote: > >>On Thu, 20 Feb 2003 16:42:03 +0000, CBFalconer wrote: >> >>> "J. Clarke" wrote: >>>> On Wed, 19 Feb 2003 15:57:32 -0500, Julian Thomas wrote: >>>> > J. Clarke >>>> >>>> > may have used oatmeal boxes, old string, >>>> > and new, used, and recycled electrons to say (at least in part): >>>> > >>>> >> Whether a PC has ECC or not is buyer's choice. Nearly all server >>>> >> and workstation class machines can support it if the purchaser >>>> >> chooses to put in the appropriate RAM modules. Some "desktop" >>>> >> and consumer machines can support it as well. The machine I'm >>>> >> using right now has ECC "from the CPU cache out to memory and >>>> >> back again" >>>> > >>>> > These days there are very few motherboards for Thunderbird that >>>> > offer ECC. Epox 8k7a seems to be almost the only one, and that's >>>> > not widely available. >>>> >>>> Any of the 762 boards will support ECC. The 761 chipset has the >>>> necessary support however vendors seem to not enable it. Trouble >>>> with AMD is that most of the vendors are targetting the consumer >>>> market, not the workstation/server market, and in the consumer >>>> market for those who even know that ECC exists, it is considered >>>> to be undesirable because there is an infinitesimal performance >>>> penalty that might cost a tenth of an FPS in Quake. >>> >>> And also the 'saving' of approximately 10% of the memory cost, to >>> be repaid many times over the first time something is destroyed by >>> any memory failures. >> >>Sometimes. But remember, some of these are the folks who run RAID 1 and shell out >>700 bucks for a Vapochill or Prometeia phase-change cooler in the hopes of >>running their P4 at 3.5 GHz. > > And what effect does the extra speed have on the on-chip cache? > Is the non-trivial benchmark performance increase anything like > the cycle speed increase? It appears to be negligible in most cases. I've not tried this sort of experiment myself--for some reason I find the overclocking culture of more interest than I do the technology. > Thanks. Take care, Brian Inglis Calgary, Alberta, Canada -- --John Reply to jclarke at ae tee tee global dot net (was jclarke at eye bee em dot net)