| 1 |
On Mon, Mar 23, 2015 at 6:41 PM, Fernando Rodriguez |
| 2 |
<frodriguez.developer@×××××××.com> wrote: |
| 3 |
> On Monday, March 23, 2015 6:18:46 PM Mike Gilbert wrote: |
| 4 |
>> On Mon, Mar 23, 2015 at 9:51 PM, Walter Dnes <waltdnes@××××××××.org> wrote: |
| 5 |
>> > On Sun, Mar 22, 2015 at 09:25:53PM -0400, Fernando Rodriguez wrote |
| 6 |
>> > |
| 7 |
>> >> I guess gcc devs are careful when using the model numbers (Intel |
| 8 |
>> >> lists 3 for Atoms, gcc uses only two so that may account for the |
| 9 |
>> >> models I mentioned) but the chance of error is there. The -mno-xxx |
| 10 |
>> >> flags would safeguard against it. |
| 11 |
>> > |
| 12 |
>> > I have one of the earliest Atom chips. Some people have a hard time |
| 13 |
>> > believing this, but it's a 32-bit-only chip; a couple of lines from |
| 14 |
>> > /proc/cpuinfo |
| 15 |
>> > |
| 16 |
>> > model name : Intel(R) Atom(TM) CPU Z520 @ 1.33GHz |
| 17 |
>> > address sizes : 32 bits physical, 32 bits virtual |
| 18 |
>> > |
| 19 |
>> > Intel gives the CPU's specs at... |
| 20 |
>> > |
| 21 |
>> > http://ark.intel.com/products/35466/Intel-Atom-Processor-Z520-512K-Cache-1_33-GHz-533-MHz-FSB |
| 22 |
>> > |
| 23 |
>> > ...where it specifically says... |
| 24 |
>> > |
| 25 |
>> > Intel 64 # No |
| 26 |
>> > |
| 27 |
>> > I want to make absolutely certain that "illegal instructions" are not |
| 28 |
>> > compiled for it. |
| 29 |
>> |
| 30 |
>> You will probably need to add -m32 to CFLAGS to avoid building 64-bit |
| 31 |
>> objects on the 64-bit machine. |
| 32 |
>> |
| 33 |
> |
| 34 |
> Your CPU is an example of what I'm saying, not just because it doesn't have 64 |
| 35 |
> bit extensions but because it doesn't have MMX (at least according to the |
| 36 |
> specs) and according to the GCC manual -march=atom means: "Intel Atom CPU with |
| 37 |
> 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3 and SSSE3 instruction set |
| 38 |
> support." So I guess it's more common than I thought. |
| 39 |
> |
| 40 |
> So you may also want to add -mno-mmx to be sure. GCC does check for mmx but it |
| 41 |
> doesn't not use it on the output (probably a bug?). |
| 42 |
> |
| 43 |
|
| 44 |
It's much more likely that Intel's website doesn't bother including |
| 45 |
MMX because it is so damn old that nobody cares. |
| 46 |
|
| 47 |
/proc/cpuinfo would be a more reliable source of data. |
Archives