Re: is it em64t ?
On Thu, Jan 12, 2006 at 11:38:08PM -0400, Peter Cordes wrote: I think that's all wrong. The flags are more or less a decoding of the CPUID result codes. As for HT, my dad's old laptop 1.7GHz P4-mobile (Northwood) has the ht flag, but it sure as hell doesn't have two logical CPUs. I looked at (but didn't really come close to understanding ;P) the relevant kernel code, and I Nak. Are you sure you are running an SMP kernel on it? The ht flag means that the processor is hyperthreading capable. If your dad's lappy doesn't show 2 cpus, it may be because HT is disabled in the BIOS. If the BIOS doesn't have an option for enabling HT, then check for a BIOS update! Some manufacturers actually shipped machines with HT capable processors in the early days that couldn't do HT. Doesn't mean the processor wasn't capable of it. Cheers, a -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
If I have a HT cpu, should I use smp kernel image? processor : 0 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Pentium(R) 4 CPU 2.66GHz stepping: 1 cpu MHz : 2661.169 cache size : 1024 KB fdiv_bug: no hlt_bug : no f00f_bug: no coma_bug: no fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm pni monitor ds_cpl tm2 cid cx16 xtpr bogomips: 5325.45 Thanks
Re: is it em64t ?
zzz haha kiedys napisal: If I have a HT cpu, should I use smp kernel image? Yes, you should if you want two logical cpus -- Registered Linux User 369908 [EMAIL PROTECTED] -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
On Sat, Jan 07, 2006 at 12:45:04PM +0100, Ernest jw ter Kuile wrote: On Saturday 07 January 2006 11:46, Hamish Moffatt wrote: It does, but what if HyperThreading was present but disabled in the BIOS? I don't know how you would tell in that case. Most of these flags are not set simply because the kernel found a certain type of processor. They are the result of elaborate startup tests which detect these capabilities. If a capability is disabled in the bios, two things can happen 1) the kernel does not detect it at all; in which case the relevant flag is not set; 2) the kernel detects the capability but switched off; in which case the kernel will attempt to switch it on (if it can of course). If this succeeds the flag is set, if not you will often see an error and the flag is not switched on. I have been told, however, that a few processor capabilities are so bound to the a certain type of cpu that their flag is simply set if that cpu is found. I don't know under which category the hyperthreading flag falls, but knowing that hyperthreading can be disabled in the bios, I would not expect the kernel to simply set that flag blindly. I think that's all wrong. The flags are more or less a decoding of the CPUID result codes. As for HT, my dad's old laptop 1.7GHz P4-mobile (Northwood) has the ht flag, but it sure as hell doesn't have two logical CPUs. I looked at (but didn't really come close to understanding ;P) the relevant kernel code, and I think the ht flag indicates support for an API for asking how many logical CPUs there are, and so on, not that there actually are multiple logical CPUs on that physical CPU. The kernel log messages (look in /var/log/dmesg if other messages have bumped them from the ring buffer) are more useful than the ht flag. I don't remember if x86info is useful for this or not, but it's generally good at finding out about CPUs. -- #define X(x,y) x##y Peter Cordes ; e-mail: X([EMAIL PROTECTED] , des.ca) The gods confound the man who first found out how to distinguish the hours! Confound him, too, who in this place set up a sundial, to cut and hack my day so wretchedly into small pieces! -- Plautus, 200 BC -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
On Sun, Jan 08, 2006 at 03:08:21AM +0100, Markus Boas wrote: Just an example powerrechner:/# cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3000.261 cache size : 1024 KB physical id : 0 siblings: 2 core id : 0 cpu cores : 1 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl cid cx16 xtpr bogomips: 6007.19 clflush size: 64 cache_alignment : 128 address sizes : 36 bits physical, 48 bits virtual power management: processor : 1 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3000.261 cache size : 1024 KB physical id : 3 siblings: 2 core id : 0 cpu cores : 1 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl cid cx16 xtpr bogomips: 6000.44 clflush size: 64 cache_alignment : 128 address sizes : 36 bits physical, 48 bits virtual power management: processor : 2 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3000.261 cache size : 1024 KB physical id : 0 siblings: 2 core id : 0 cpu cores : 1 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl cid cx16 xtpr bogomips: 6000.42 clflush size: 64 cache_alignment : 128 address sizes : 36 bits physical, 48 bits virtual power management: processor : 3 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3000.261 cache size : 1024 KB physical id : 3 siblings: 2 core id : 0 cpu cores : 1 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl cid cx16 xtpr bogomips: 6000.44 clflush size: 64 cache_alignment : 128 address sizes : 36 bits physical, 48 bits virtual power management: This is a dual Xeon with ht. Also an em64t. Dual single core hyperthreading xeons if I read the above correctly. Certainly given the physical id is 0 on two of them, and 3 on two of them, and there is 4 cpus listing 2 siblings, and all of them show core id 0, that is how I would understand it. If any showed core id other than 0, I would assume dual core. Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
Le jeudi 05 janvier 2006 à 11:09 +0100, Erik Mouw a écrit : On Thu, Jan 05, 2006 at 10:22:51AM +0100, Koen Vermeer wrote: On Thu, 2006-01-05 at 17:04 +0800, zzz haha wrote: i have a p4 machine. how can i know if it has em64t? A somewhat stupid but nevertheless possibly useful suggestion: Try to boot the Debian x86-64 installation CD. If it works, you either have an em64t or an amd64 processor. Since you state your machine is a p4, you may safely rule out the latter possibility. Alternatively, try to find out what processor is in there, and check the Intel website. Maybe there's also a flag in /proc/cpuinfo that indicates em64t capabilities. The lm flag in /proc/cpuinfo tells the CPU can do long mode, which means it has the 64 bit extensions. By the way: I need to work on a Xeon machine remotely, and I wondered if it had multiple processors (it is not a dual-core) or simply HyperThreading. How can I distinguish? Here is /proc/cpuinfo: processor : 0 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3001.253 cache size : 1024 KB physical id : 0 siblings: 2 fdiv_bug: no hlt_bug : no f00f_bug: no coma_bug: no fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm pni monitor ds_cpl cid bogomips: 5947.39 processor : 1 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3001.253 cache size : 1024 KB physical id : 0 siblings: 2 fdiv_bug: no hlt_bug : no f00f_bug: no coma_bug: no fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm pni monitor ds_cpl cid bogomips: 5996.54 Thanks Erik -- Jérôme Warnier FLOSS Consultant http://beeznest.neteb
Re: is it em64t ?
Jerome Warnier wrote: By the way: I need to work on a Xeon machine remotely, and I wondered if it had multiple processors (it is not a dual-core) or simply HyperThreading. How can I distinguish? Here is /proc/cpuinfo: flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm pni monitor ds_cpl cid I'm no expert in processors, but I'd guess that ht there in the flags means it has HyperThreading support. -- Please recycle. Eduardo M KALINOWSKI [EMAIL PROTECTED] http://move.to/hpkb -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
Jerome Warnier wrote: By the way: I need to work on a Xeon machine remotely, and I wondered if it had multiple processors (it is not a dual-core) or simply HyperThreading. How can I distinguish? Here is /proc/cpuinfo: processor : 0 ... physical id : 0 siblings: 2 ... processor : 1 ... physical id : 0 siblings: 2 You can see two logical processors (numbered 0 and 1), which are both parts of a single physical processor (with physical id 0). Each processor is one of 2 siblings. = this is a single hyperthreaded processor Michal -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
Le samedi 07 janvier 2006 à 21:46 +1100, Hamish Moffatt a écrit : On Sat, Jan 07, 2006 at 08:34:31AM -0200, Eduardo M KALINOWSKI wrote: Jerome Warnier wrote: By the way: I need to work on a Xeon machine remotely, and I wondered if it had multiple processors (it is not a dual-core) or simply HyperThreading. How can I distinguish? Here is /proc/cpuinfo: flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm pni monitor ds_cpl cid I'm no expert in processors, but I'd guess that ht there in the flags means it has HyperThreading support. It does, but what if HyperThreading was present but disabled in the BIOS? I don't know how you would tell in that case. Or SMP support disabled in the kernel. Hamish -- Hamish Moffatt VK3SB [EMAIL PROTECTED] [EMAIL PROTECTED] -- Jérôme Warnier FLOSS Consultant http://beeznest.net
Re: is it em64t ?
Le samedi 07 janvier 2006 à 11:56 +0100, Michal Schmidt a écrit : Jerome Warnier wrote: By the way: I need to work on a Xeon machine remotely, and I wondered if it had multiple processors (it is not a dual-core) or simply HyperThreading. How can I distinguish? Here is /proc/cpuinfo: processor : 0 ... physical id : 0 siblings: 2 ... processor : 1 ... physical id : 0 siblings: 2 You can see two logical processors (numbered 0 and 1), which are both parts of a single physical processor (with physical id 0). Each processor is one of 2 siblings. = this is a single hyperthreaded processor Thanks, this is all I wanted to know, exactly the way I wanted it. Michal -- Jérôme Warnier FLOSS Consultant http://beeznest.net
Re: is it em64t ?
On Saturday 07 January 2006 11:46, Hamish Moffatt wrote: It does, but what if HyperThreading was present but disabled in the BIOS? I don't know how you would tell in that case. Most of these flags are not set simply because the kernel found a certain type of processor. They are the result of elaborate startup tests which detect these capabilities. If a capability is disabled in the bios, two things can happen 1) the kernel does not detect it at all; in which case the relevant flag is not set; 2) the kernel detects the capability but switched off; in which case the kernel will attempt to switch it on (if it can of course). If this succeeds the flag is set, if not you will often see an error and the flag is not switched on. I have been told, however, that a few processor capabilities are so bound to the a certain type of cpu that their flag is simply set if that cpu is found. I don't know under which category the hyperthreading flag falls, but knowing that hyperthreading can be disabled in the bios, I would not expect the kernel to simply set that flag blindly. Ernest. -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
On Sat, Jan 07, 2006 at 11:00:44AM +0100, Jerome Warnier wrote: processor : 0 [snip] physical id : 0 siblings: 2 [snip] processor : 1 physical id : 0 siblings: 2 [snip] Both CPUs are physical ID 0 and both say they are part of a set of 2 siblings. I am quite sure that means it is using hyperthreading, and is not dual core or dual cpu. Just hyperthreading. Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
Just an example powerrechner:/# cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3000.261 cache size : 1024 KB physical id : 0 siblings: 2 core id : 0 cpu cores : 1 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl cid cx16 xtpr bogomips: 6007.19 clflush size: 64 cache_alignment : 128 address sizes : 36 bits physical, 48 bits virtual power management: processor : 1 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3000.261 cache size : 1024 KB physical id : 3 siblings: 2 core id : 0 cpu cores : 1 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl cid cx16 xtpr bogomips: 6000.44 clflush size: 64 cache_alignment : 128 address sizes : 36 bits physical, 48 bits virtual power management: processor : 2 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3000.261 cache size : 1024 KB physical id : 0 siblings: 2 core id : 0 cpu cores : 1 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl cid cx16 xtpr bogomips: 6000.42 clflush size: 64 cache_alignment : 128 address sizes : 36 bits physical, 48 bits virtual power management: processor : 3 vendor_id : GenuineIntel cpu family : 15 model : 4 model name : Intel(R) Xeon(TM) CPU 3.00GHz stepping: 1 cpu MHz : 3000.261 cache size : 1024 KB physical id : 3 siblings: 2 core id : 0 cpu cores : 1 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl cid cx16 xtpr bogomips: 6000.44 clflush size: 64 cache_alignment : 128 address sizes : 36 bits physical, 48 bits virtual power management: This is a dual Xeon with ht. Also an em64t. Am Samstag 07 Januar 2006 20:43 schrieb Lennart Sorensen: On Sat, Jan 07, 2006 at 11:00:44AM +0100, Jerome Warnier wrote: processor : 0 [snip] physical id : 0 siblings: 2 [snip] processor : 1 physical id : 0 siblings: 2 [snip] Both CPUs are physical ID 0 and both say they are part of a set of 2 siblings. I am quite sure that means it is using hyperthreading, and is not dual core or dual cpu. Just hyperthreading. Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
On Thu, 2006-01-05 at 17:04 +0800, zzz haha wrote: i have a p4 machine. how can i know if it has em64t? A somewhat stupid but nevertheless possibly useful suggestion: Try to boot the Debian x86-64 installation CD. If it works, you either have an em64t or an amd64 processor. Since you state your machine is a p4, you may safely rule out the latter possibility. Alternatively, try to find out what processor is in there, and check the Intel website. Maybe there's also a flag in /proc/cpuinfo that indicates em64t capabilities. Koen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
On Thu, Jan 05, 2006 at 10:22:51AM +0100, Koen Vermeer wrote: On Thu, 2006-01-05 at 17:04 +0800, zzz haha wrote: i have a p4 machine. how can i know if it has em64t? A somewhat stupid but nevertheless possibly useful suggestion: Try to boot the Debian x86-64 installation CD. If it works, you either have an em64t or an amd64 processor. Since you state your machine is a p4, you may safely rule out the latter possibility. Alternatively, try to find out what processor is in there, and check the Intel website. Maybe there's also a flag in /proc/cpuinfo that indicates em64t capabilities. The lm flag in /proc/cpuinfo tells the CPU can do long mode, which means it has the 64 bit extensions. Erik -- +-- Erik Mouw -- www.harddisk-recovery.com -- +31 70 370 12 90 -- | Lab address: Delftechpark 26, 2628 XH, Delft, The Netherlands -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: is it em64t ?
The lm flag in /proc/cpuinfo tells the CPU can do long mode, which means it has the 64 bit extensions. thank you!
Re: AMD64 VS EM64T
On Sat, Dec 04, 2004 at 05:50:05AM -0600, [EMAIL PROTECTED] wrote: did you read http://www.tecchannel.de/hardware/1441/index.html ? A bunch of 32bit windows benchmarks run on 32bit windows XP. Is that NOT providing what you meant ? Certainly not what I meant. Non of that article has any 64bit mode benchmarks at all. And I am quite sure of that even though my knowledge of German is pretty low. Lennart Sorensen
Re: AMD64 VS EM64T
Lennart, (B (Bdid you read (B (Bhttp://www.tecchannel.de/hardware/1441/index.html ? (B (BIs that NOT providing what you meant ? (B (BBest regards (B (BNils Valentin (B (B (B On Fri, Dec 03, 2004 at 11:49:15PM +0900, Nils Valentin wrote: (B there is a 67 page Benchmark comparison betweeen the Athlon type CPUs (B and the (B Pentium 4 types (including Prescott). The review does NOT include the (B Opterons ;-(, but is has a lot of very detailed benchmark charts. 29 (B charts (B for data transfers of each CPU alone + 35 benchmark charts (comparison). (B (B (B The only problem is as far as I know this article is only available in (B German. (B (B http://www.tecchannel.de/hardware/1244/index.html (B (B "Test: Athlon 64 FX-55 4000+" (B (B They have a english website here : (B (B http://www.tecchannel.com/ (B (B ,but unfortunately it does not contain even as near info as the german (B pages. (B The article above does not seem to be available in english. (B (B The article is free to read online or you can buy the PDF version for (B 0.80 (B Euro (1$). (B (B I have it but the copyright does not allow me to forward it to anybody
Re: AMD64 VS EM64T
Hi lennart, (B (Bsorry I meant this link http://www.tecchannel.de/hardware/1456/index.html (B (BIts a Linux comparison (but only 32 bit - waiting for the 64 bit update) (B (BBest regards (B (BNils Valentin (B (B (B On Fri, Dec 03, 2004 at 11:49:15PM +0900, Nils Valentin wrote: (B there is a 67 page Benchmark comparison betweeen the Athlon type CPUs (B and the (B Pentium 4 types (including Prescott). The review does NOT include the (B Opterons ;-(, but is has a lot of very detailed benchmark charts. 29 (B charts (B for data transfers of each CPU alone + 35 benchmark charts (comparison). (B (B (B The only problem is as far as I know this article is only available in (B German. (B (B http://www.tecchannel.de/hardware/1244/index.html (B (B "Test: Athlon 64 FX-55 4000+" (B (B They have a english website here : (B (B http://www.tecchannel.com/ (B (B ,but unfortunately it does not contain even as near info as the german (B pages. (B The article above does not seem to be available in english. (B (B The article is free to read online or you can buy the PDF version for (B 0.80 (B Euro (1$). (B (B I have it but the copyright does not allow me to forward it to anybody
Re: AMD64 VS EM64T
Jin Zhao wrote: I am currently faced with choosing one of them as our forthcoming 64 bit platform. So far I read a couple of reviews, most of which seems favor AMD64 a little bit. I also did some initial testings on an opteron box with Debian pure64 unstale. So far it looks good. Here's a review comparing amd64 to emt64 under SuSE 9.1 Pro with Linux 2.6.4. Slightly dated and limited review, but should give you a good feel. http://anandtech.com/linux/showdoc.aspx?i=2163 -Peter
Re: AMD64 VS EM64T
Hi Everybody, there is a 67 page Benchmark comparison betweeen the Athlon type CPUs and the Pentium 4 types (including Prescott). The review does NOT include the Opterons ;-(, but is has a lot of very detailed benchmark charts. 29 charts for data transfers of each CPU alone + 35 benchmark charts (comparison). The only problem is as far as I know this article is only available in German. http://www.tecchannel.de/hardware/1244/index.html Test: Athlon 64 FX-55 4000+ They have a english website here : http://www.tecchannel.com/ ,but unfortunately it does not contain even as near info as the german pages. The article above does not seem to be available in english. The article is free to read online or you can buy the PDF version for 0.80 Euro (1$). I have it but the copyright does not allow me to forward it to anybody. (Thank you for understanding) Best regards Nils Valentin On Friday 03 December 2004 09:04, Jin Zhao wrote: Just found out this excellent article about server performance: http://www.samag.com/documents/s=9408/sam0411b/0411b.htm This is the best I read so far and I highly recommend it to everybody considering 64 bit. However, it is still purely from a hardware view. Does anybody knows any reviews from OS softwares, esp Linux? Which platform linux works better with, AMD64 or EM64T? Thanks, Jin Paolo Alexis Falcone wrote: On Thu, 02 Dec 2004 15:41:10 -0600, Jin Zhao [EMAIL PROTECTED] wrote: I am currently faced with choosing one of them as our forthcoming 64 bit platform. So far I read a couple of reviews, most of which seems favor AMD64 a little bit. I also did some initial testings on an opteron box with Debian pure64 unstale. So far it looks good. The price differrence is not a big issue. The most important are performance, reliability and compatibility, esp on Linux, most likely Debian. We will use them to run server side java applicaitons. Redhat mentioned this in their realease statement: Software IOTLB Intel EM64T does not support an IOMMU in hardware while AMD64 processors do. This means that physical addresses above 4GB (32 bits) cannot reliably be the source or destination of DMA operations. Therefore, the Red Hat Enterprise Linux 3 Update 2 kernel bounces all DMA operations to or from physical addresses above 4GB to buffers that the kernel pre-allocated below 4GB at boot time. This is likely to result in lower performance for IO-intensive workloads for Intel EM64T as compared to AMD64 processors. This issue may affect database usage, but probably not a java applicaiton server. There might be other unkown issues as well. I am eager to know what are the Debian team and users' point on these two platforms, esp those who already used them. AMD's original implementation of their AMD64 architecture is gauged as superior engineering-wise by many hardware reviewers. The Intel implementation still suffers from bandwidth starvation as the same bus architecture as of old is still being used. This causes problems when you get more processors and memory, which the AMD implementation solves by making each processor have its own set of memory and resources. -- kind regards Nils Valentin Tokyo/Japan http://www.be-known-online.com/mysql/
Re: AMD64 VS EM64T
Hi veverybody, also this two articles are only in german http://www.tecchannel.de/hardware/1441/index.html http://www.tecchannel.de/hardware/1456/index.html I still hope that somevody finds them useful. Best regards Nils Valentin Tokyo / Japan http://www.be-known-online.com On Friday 03 December 2004 09:04, Jin Zhao wrote: Just found out this excellent article about server performance: http://www.samag.com/documents/s=9408/sam0411b/0411b.htm This is the best I read so far and I highly recommend it to everybody considering 64 bit. However, it is still purely from a hardware view. Does anybody knows any reviews from OS softwares, esp Linux? Which platform linux works better with, AMD64 or EM64T? Thanks, Jin Paolo Alexis Falcone wrote: On Thu, 02 Dec 2004 15:41:10 -0600, Jin Zhao [EMAIL PROTECTED] wrote: I am currently faced with choosing one of them as our forthcoming 64 bit platform. So far I read a couple of reviews, most of which seems favor AMD64 a little bit. I also did some initial testings on an opteron box with Debian pure64 unstale. So far it looks good. The price differrence is not a big issue. The most important are performance, reliability and compatibility, esp on Linux, most likely Debian. We will use them to run server side java applicaitons. Redhat mentioned this in their realease statement: Software IOTLB Intel EM64T does not support an IOMMU in hardware while AMD64 processors do. This means that physical addresses above 4GB (32 bits) cannot reliably be the source or destination of DMA operations. Therefore, the Red Hat Enterprise Linux 3 Update 2 kernel bounces all DMA operations to or from physical addresses above 4GB to buffers that the kernel pre-allocated below 4GB at boot time. This is likely to result in lower performance for IO-intensive workloads for Intel EM64T as compared to AMD64 processors. This issue may affect database usage, but probably not a java applicaiton server. There might be other unkown issues as well. I am eager to know what are the Debian team and users' point on these two platforms, esp those who already used them. AMD's original implementation of their AMD64 architecture is gauged as superior engineering-wise by many hardware reviewers. The Intel implementation still suffers from bandwidth starvation as the same bus architecture as of old is still being used. This causes problems when you get more processors and memory, which the AMD implementation solves by making each processor have its own set of memory and resources. -- kind regards Nils Valentin Tokyo/Japan http://www.be-known-online.com/mysql/
Re: AMD64 VS EM64T
O.K I found one more article. Here are all 4 articles neatly listed up http://www.tecchannel.de/hardware/1441/index.html http://www.tecchannel.de/hardware/1456/index.html http://www.tecchannel.de/hardware/1244/index.html http://www.tecchannel.de/hardware/1235/index.html Best regards Nils Valentin Tokyo / Japan http://www.be-known-online.com On Saturday 04 December 2004 00:35, Nils Valentin wrote: Hi veverybody, also this two articles are only in german http://www.tecchannel.de/hardware/1441/index.html http://www.tecchannel.de/hardware/1456/index.html I still hope that somevody finds them useful. Best regards Nils Valentin Tokyo / Japan http://www.be-known-online.com On Friday 03 December 2004 09:04, Jin Zhao wrote: Just found out this excellent article about server performance: http://www.samag.com/documents/s=9408/sam0411b/0411b.htm This is the best I read so far and I highly recommend it to everybody considering 64 bit. However, it is still purely from a hardware view. Does anybody knows any reviews from OS softwares, esp Linux? Which platform linux works better with, AMD64 or EM64T? Thanks, Jin Paolo Alexis Falcone wrote: On Thu, 02 Dec 2004 15:41:10 -0600, Jin Zhao [EMAIL PROTECTED] wrote: I am currently faced with choosing one of them as our forthcoming 64 bit platform. So far I read a couple of reviews, most of which seems favor AMD64 a little bit. I also did some initial testings on an opteron box with Debian pure64 unstale. So far it looks good. The price differrence is not a big issue. The most important are performance, reliability and compatibility, esp on Linux, most likely Debian. We will use them to run server side java applicaitons. Redhat mentioned this in their realease statement: Software IOTLB Intel EM64T does not support an IOMMU in hardware while AMD64 processors do. This means that physical addresses above 4GB (32 bits) cannot reliably be the source or destination of DMA operations. Therefore, the Red Hat Enterprise Linux 3 Update 2 kernel bounces all DMA operations to or from physical addresses above 4GB to buffers that the kernel pre-allocated below 4GB at boot time. This is likely to result in lower performance for IO-intensive workloads for Intel EM64T as compared to AMD64 processors. This issue may affect database usage, but probably not a java applicaiton server. There might be other unkown issues as well. I am eager to know what are the Debian team and users' point on these two platforms, esp those who already used them. AMD's original implementation of their AMD64 architecture is gauged as superior engineering-wise by many hardware reviewers. The Intel implementation still suffers from bandwidth starvation as the same bus architecture as of old is still being used. This causes problems when you get more processors and memory, which the AMD implementation solves by making each processor have its own set of memory and resources. -- kind regards Nils Valentin Tokyo/Japan http://www.be-known-online.com/mysql/
Re: AMD64 VS EM64T
On Fri, Dec 03, 2004 at 11:49:15PM +0900, Nils Valentin wrote: there is a 67 page Benchmark comparison betweeen the Athlon type CPUs and the Pentium 4 types (including Prescott). The review does NOT include the Opterons ;-(, but is has a lot of very detailed benchmark charts. 29 charts for data transfers of each CPU alone + 35 benchmark charts (comparison). The only problem is as far as I know this article is only available in German. http://www.tecchannel.de/hardware/1244/index.html Test: Athlon 64 FX-55 4000+ They have a english website here : http://www.tecchannel.com/ ,but unfortunately it does not contain even as near info as the german pages. The article above does not seem to be available in english. The article is free to read online or you can buy the PDF version for 0.80 Euro (1$). I have it but the copyright does not allow me to forward it to anybody. (Thank you for understanding) I think what the original question wanted to know, is the performance of opteron/athlon 64 in 64bit mode vs. xeon em64t in 64bit mode. Most published benchmarks are for windows and in 32bit mode which doesn't tell anything useful unfortunately. Certainly comments I have seen on this list so far is that the athlon 64 is almost always faster in 64bit mode than 32bit mode, and the xeon varies, sometimes gaining a small amount, sometimes loosing a small amount, but no major improvement or loss in performance of 64bit vs. 32bit. of course programs that have optimized 32bit assembler but no optimized 64bit assembler are usually much faster in 32bit mode, although that is entirely due to optimized vs unoptimized. Len Sorensen
Re: AMD64 VS EM64T
On Thu, 02 Dec 2004 15:41:10 -0600, Jin Zhao [EMAIL PROTECTED] wrote: I am currently faced with choosing one of them as our forthcoming 64 bit platform. So far I read a couple of reviews, most of which seems favor AMD64 a little bit. I also did some initial testings on an opteron box with Debian pure64 unstale. So far it looks good. The price differrence is not a big issue. The most important are performance, reliability and compatibility, esp on Linux, most likely Debian. We will use them to run server side java applicaitons. Redhat mentioned this in their realease statement: Software IOTLB Intel EM64T does not support an IOMMU in hardware while AMD64 processors do. This means that physical addresses above 4GB (32 bits) cannot reliably be the source or destination of DMA operations. Therefore, the Red Hat Enterprise Linux 3 Update 2 kernel bounces all DMA operations to or from physical addresses above 4GB to buffers that the kernel pre-allocated below 4GB at boot time. This is likely to result in lower performance for IO-intensive workloads for Intel EM64T as compared to AMD64 processors. This issue may affect database usage, but probably not a java applicaiton server. There might be other unkown issues as well. I am eager to know what are the Debian team and users' point on these two platforms, esp those who already used them. AMD's original implementation of their AMD64 architecture is gauged as superior engineering-wise by many hardware reviewers. The Intel implementation still suffers from bandwidth starvation as the same bus architecture as of old is still being used. This causes problems when you get more processors and memory, which the AMD implementation solves by making each processor have its own set of memory and resources. -- Paolo Alexis Falcone [EMAIL PROTECTED]
Re: AMD64 VS EM64T
Just found out this excellent article about server performance: http://www.samag.com/documents/s=9408/sam0411b/0411b.htm This is the best I read so far and I highly recommend it to everybody considering 64 bit. However, it is still purely from a hardware view. Does anybody knows any reviews from OS softwares, esp Linux? Which platform linux works better with, AMD64 or EM64T? Thanks, Jin Paolo Alexis Falcone wrote: On Thu, 02 Dec 2004 15:41:10 -0600, Jin Zhao [EMAIL PROTECTED] wrote: I am currently faced with choosing one of them as our forthcoming 64 bit platform. So far I read a couple of reviews, most of which seems favor AMD64 a little bit. I also did some initial testings on an opteron box with Debian pure64 unstale. So far it looks good. The price differrence is not a big issue. The most important are performance, reliability and compatibility, esp on Linux, most likely Debian. We will use them to run server side java applicaitons. Redhat mentioned this in their realease statement: Software IOTLB Intel EM64T does not support an IOMMU in hardware while AMD64 processors do. This means that physical addresses above 4GB (32 bits) cannot reliably be the source or destination of DMA operations. Therefore, the Red Hat Enterprise Linux 3 Update 2 kernel bounces all DMA operations to or from physical addresses above 4GB to buffers that the kernel pre-allocated below 4GB at boot time. This is likely to result in lower performance for IO-intensive workloads for Intel EM64T as compared to AMD64 processors. This issue may affect database usage, but probably not a java applicaiton server. There might be other unkown issues as well. I am eager to know what are the Debian team and users' point on these two platforms, esp those who already used them. AMD's original implementation of their AMD64 architecture is gauged as superior engineering-wise by many hardware reviewers. The Intel implementation still suffers from bandwidth starvation as the same bus architecture as of old is still being used. This causes problems when you get more processors and memory, which the AMD implementation solves by making each processor have its own set of memory and resources.