processor type for celeron d 220

W

wonslung

What processor type do you use for CPUTYPE in /etc/make.conf for a celeron d 220 (1.2 ghz)

it's based on a conroe core i think.

the handbook says to check /var/run/dmesg.boot but it doesn't give me a definitive answer...heres what i see there:
Code: 
CPU: Intel(R) Celeron(R) CPU          220  @ 1.20GHz (1200.05-MHz K8-class CPU)
  Origin = "GenuineIntel"  Id = 0x10661  Stepping = 1
  Features=0xafebfbff<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,TM,PBE>
  Features2=0xe31d<SSE3,RSVD2,MON,DS_CPL,TM2,SSSE3,CX16,xTPR,PDCM>
  AMD Features=0x20100800<SYSCALL,NX,LM>
  AMD Features2=0x1<LAHF>

Thanks for the help guys
 
Some types I gathered from searching the web:
Code: 
Pentium 4: pentium4
Pentium 4 (Prescott), Celeron D: nocona
Pentium D: nocona
Core Duo, Pentium Dual-Core T20XX/T21XX: prescott
Core 2 Duo/Quad, Pentium Dual-Core T23XX+/EXXXX: nocona
i7: nocona
Xeon w/o EM64T: pentium4
Xeon w/EM64T: nocona
Note: To determine EM64T (if it pops up yes, if not then no), $ dmesg | grep LM

Hope it helps. Another option is to use "native" (requires GCC 4.2 or above).

This selects the CPU to tune for at compilation time by determining the processor type of the compiling machine. Using -mtune=native will produce code optimized for the local machine under the constraints of the selected instruction set. Using -march=native will enable all instruction subsets supported by the local machine (hence the result might not run on different machines).
Click to expand...
 
DutchDaemon said:
Are you sure about D 220? I'd say 'Prescott', but the Celeron D series appears to have only 3.x designations, whereas there are Celeron 220's, but without the D. That one is a Conroe-L, but I don't know the associated cputype setting for that one. maybe 'core' or 'k8'.

http://en.wikipedia.org/wiki/List_of_Intel_Celeron_microprocessors#Celeron_D

http://en.wikipedia.org/wiki/List_of_Intel_Celeron_microprocessors#Celeron_.28Core.29
Click to expand...

the hosting company says it's a celeron d

i posted the info that i know how to find...is there anywhere else i can check?
 
dennylin93 said:
Some types I gathered from searching the web:
Code: 
Pentium 4: pentium4
Pentium 4 (Prescott), Celeron D: nocona
Pentium D: nocona
Core Duo, Pentium Dual-Core T20XX/T21XX: prescott
Core 2 Duo/Quad, Pentium Dual-Core T23XX+/EXXXX: nocona
i7: nocona
Xeon w/o EM64T: pentium4
Xeon w/EM64T: nocona
Note: To determine EM64T, $ dmesg | grep LM

Hope it helps. Another option is to use "native" (requires GCC 4.2 or above).
Click to expand...

when i do dmesg | grep LM i get this:

Code: 
dmesg | grep LM
  AMD Features=0x20100800<SYSCALL,NX,LM>
  AMD Features=0x20100800<SYSCALL,NX,LM>
 
Your dmesg's
Code: 
CPU          220  @ 1.20GHz
coincides with the 'regular' Celeron 220.

Code: 
Model Number 	sSpec Number 	Frequency
Celeron 220 	SLAF2 (A1) 	1200 MHz

The D-type Celerons run at higher speeds (2.1 - 3.3 GHz).
 
DutchDaemon said:
Your dmesg's
Code: 
CPU          220  @ 1.20GHz
coincides with the 'regular' Celeron 220.

Code: 
Model Number 	sSpec Number 	Frequency
Celeron 220 	SLAF2 (A1) 	1200 MHz

The D-type Celerons run at higher speeds (2.1 - 3.3 GHz).
Click to expand...

that's cool, i'm just going by what the hosting company lists it as, they probably made the mistake.

they say : "Celeron D 220 1.2 ghz"

either way, which cpu type should i put? nocona?
 
There is Celeron 220 at Wikipedia listed:
http://en.wikipedia.org/wiki/List_of_Intel_Celeron_microprocessors

Code: 
[B]Conroe-L | 65 nm | Intel Core 2 microarchitecture[/B]
All models support: [B]MMX, SSE, SSE2, SSE3, SSSE3, Intel 64, XD bit (an NX bit implementation)[/B]

[B]Celeron 220[/B]
SLAF2 (A1)
1200 MHz
512 KiB
533 MT/s
1.05 V - 1.3 V
19 W
Micro-FCBGA

So if you would want to use i386 version, then use prescott flag, and amd64 would use nacona flag.

Generaly speaking, treat is as regular Core 2 Duo CPU, but with single core only.
 
vermaden said:
Generaly speaking, treat is as regular Core 2 Duo CPU, but with single core only.
Click to expand...

thanks so much
i DID search the forums and google first before posting, saw a few questions similar but none for this exact processor, now it's a matter of record for anyone else who needs to know.

Thanks again guys.
 
vermaden said:
So if you would want to use i386 version, then use prescott flag, and amd64 would use nacona flag.
Click to expand...

It's safe to use nocona on both i386 and amd64 since FreeBSD aliases nocona to prescott on i386 (the same goes for other types as well). See /usr/src/share/mk/bsd.cpu.mk for the complete list.
 
to clarify...

I have a core 2 duo e7500, if I [cmd=]dmesg |grep LM[/cmd] and receive:
Code: 
AMD Features=0x20100800<SYSCALL,NX,LM>
AMD Features=0x20100800<SYSCALL,NX,LM>
AMD Features=0x20100800<SYSCALL,NX,LM>
as results, does this indicate that this in fact is an em64t enabled processor, and IS compatible with the amd64 distribution?

I have glacially slow compiling at the moment. I quit after about 2 days of it slowly recompiling the GENERIC kernel to reconfirm hardware compatibility. I want to use amd64 due to nessesary hptrr compatibilty, it will not work with i386+PAE.
 
You must log in or register to reply here.
Back
Top