[R] Xeon CPU and ATLAS
Peter Dalgaard
p.dalgaard at biostat.ku.dk
Sat Mar 13 02:16:35 CET 2004
rossini at blindglobe.net (A.J. Rossini) writes:
> > I think the difference between P4 and Xeon is the SSE1 vs SSE2 thing,
> > so you'd want the P4SSE2 DLL, but others may be able to speak more
> > authoritatively.
>
> SSE1 vs SSE2 is PIII vs PIV (so depends if your xeons are p3 or p4 (?
> not sure if there is such a thing) based.
Sure? I have
turmalin:/usr/local/src/ATLAS/>ls CONFIG/ARCHS/
21164.tgz ConfDump.log Makefile PIIISSE1.tgz PPCG4AltiVec.tgz
21164GOTO.tgz CreateDef.sh P4SSE1.tgz POWER.tgz PPRO.tgz
21264.tgz CreateDirs.sh P4SSE2 POWER2Thin.tgz SGIIP28.tgz
21264GOTO.tgz CreateTar.sh P4SSE2.tgz POWER3.tgz SGIIP30.tgz
ATHLON.tgz HP9735.tgz P5MMX.tgz PPC604.tgz SunUS2.tgz
ATHLON3DNow2.tgz IA64Itan.tgz PII.tgz PPC604e.tgz SunUS5.tgz
ATHLONSSE1.tgz KillDirs.sh PIII.tgz PPCG4.tgz negflt.c
so it would seem that there's both P4SSE1 and PIIISSE1. However,
"lannerfalk" (which you shared an office with for a while) is a P4,
with SSE2, and actually quite difficult to tell apart from the Xeon
chips in "turmalin":
CPU: L1 I cache: 12K, L1 D cache: 8K
CPU: L2 cache: 512K
CPU: Hyper-Threading is disabled
CPU: Common caps: 3febfbff 00000000 00000000 00000000
CPU0: Intel(R) Pentium(R) 4 CPU 2.20GHz stepping 04
vs.
CPU: Trace cache: 12K uops, L1 D cache: 8K
CPU: L2 cache: 512K
CPU: Physical Processor ID: 0
Intel machine check reporting enabled on CPU#1.
CPU: After generic, caps: bfebfbff 00000000 00000000 00000000
CPU: Common caps: bfebfbff 00000000 00000000 00000000
CPU1: Intel(R) Xeon(TM) CPU 2.80GHz stepping 07
And their /proc/cpuinfo entries are also similar except for the clock
speed and number of siblings. So SSE2 is certainly not the difference
between P4 and Xeon - stepping number issue, perhaps?
--
O__ ---- Peter Dalgaard Blegdamsvej 3
c/ /'_ --- Dept. of Biostatistics 2200 Cph. N
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907
More information about the R-help
mailing list