GMP 4.3.1 misdetects intel X7460

[Torbjorn Granlund]

David Harvey <dmharvey at cims.nyu.edu> writes:

  GMP 4.3.1 is misdetecting the following chip (intel xeon X7460
  dunnington):
  
  processor       : 0
  vendor_id       : GenuineIntel
  cpu family      : 6
  model           : 29
  model name      : Intel(R) Xeon(R) CPU           X7460  @ 2.66GHz
  stepping        : 1
  cpu MHz         : 2666.761
  cache size      : 16384 KB
  physical id     : 0
  siblings        : 6
  core id         : 0
  cpu cores       : 6
  fpu             : yes
  fpu_exception   : yes
  cpuid level     : 11
  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 syscall nx lm constant_tsc arch_perfmon pebs bts rep_good pni
  monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr dca sse4_1 lahf_lm
  bogomips        : 5336.60
  clflush size    : 64
  cache_alignment : 64
  address sizes   : 40 bits physical, 48 bits virtual
  power management:
  
OK, so model==29 isn't an atom.  Well, Intel seems to mix processor
model numbers randomly.

Any idea of what type of processor that is?  There are, to my knowledge,
three different "core" microarchitecture variants.

Gen 1, 65nm "Core 2" with Conroe, Merom, etc, with slow integer division
Gen 2, 45nm, "Core 2" with Penryn, with faster integer division
Gen 3, 45 nm, "Core iN", Nehalem with Bloomfield,Lynnfield with many
pipeline differences (better pipelining, sometimes longer latencies)

Do you know to which of these "model 29" belongs?

If not, please run and time this program, it will tell the latter two
apart:

        .globl  main
main:
        mov     $2666666667, %ecx
1:      mul
        dec     %ecx
        jnz     1b
        ret


-- 
Torbjörn