On closer inspection, the sse2 test code in:
http://www.loria.fr/~thome/vrac/gf2x-201309240733-4b5636d.tar.gz
the previously linked
http://www.loria.fr/~thome/vracgf2x-201309232352-49027b2.tar.gz
and the code above all compile (gcc -msse2 test.c), however when they are
run the output of:
./a.out || echo $?
is
Illegal instruction (core dumped)
132
However... If I add in the flags that I think you are using -std=gnu99 -g
-O4 -Wall -W, it now compiles and runs.
I am attaching the file that compiles and its object dump.
You may be able to come up with something better that breaks optimization.
For reference the following does, it may be simpler to just drop the
optimization flags for the purpose of the system testing (since there could
in principle be other tests going on that also silently pass when they
should fail).
#include <stdlib.h>
#include <emmintrin.h>
#include <stdio.h>
__v2di x; /* Our code currently uses these, but it should not */
int main() {
__m128i foo = _mm_setr_epi32(rand(), rand(), rand(), rand());
__m128i bar = _mm_setr_epi32(rand(), 0x26622626, 0xabbabbab,
0xfeed1664);
foo = _mm_mullo_epi16(foo, bar);
if( _mm_extract_epi16(foo, 0) )
{
printf("XX");
return 0;
}
else
{
printf("YY");
return _mm_extract_epi16(foo, 0);
}
}
- Andrew
On Tue, Sep 24, 2013 at 1:44 AM, Emmanuel Thomé <emmanuel.th...@gmail.com>wrote:
>
> On Tuesday, September 24, 2013 2:41:58 AM UTC+2, Andrew Fiori wrote:
>
>> The linked tar.gz file doesn't appear to fix the problem (I am assuming
>> this is what you wanted me to test).
>> It still tries to compile with sse2 on the non-sse 2 machine
>>
>> I am attaching the config.log as well as the output from both make and
>> make tune-lowlevel.
>>
>
> ok ; It seems that optimization got me.
> Please try again with the repository tip, or
> http://www.loria.fr/~thome/vrac/gf2x-201309240733-4b5636d.tar.gz
>
> E.
>
>>
>> --
> You received this message because you are subscribed to a topic in the
> Google Groups "sage-devel" group.
> To unsubscribe from this topic, visit
> https://groups.google.com/d/topic/sage-devel/Cp1lDMzyCrU/unsubscribe.
> To unsubscribe from this group and all its topics, send an email to
> sage-devel+unsubscr...@googlegroups.com.
> To post to this group, send email to sage-devel@googlegroups.com.
> Visit this group at http://groups.google.com/group/sage-devel.
> For more options, visit https://groups.google.com/groups/opt_out.
>
--
You received this message because you are subscribed to the Google Groups
"sage-devel" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to sage-devel+unsubscr...@googlegroups.com.
To post to this group, send email to sage-devel@googlegroups.com.
Visit this group at http://groups.google.com/group/sage-devel.
For more options, visit https://groups.google.com/groups/opt_out.
./a.out: file format elf32-i386
Disassembly of section .init:
08048294 <_init>:
8048294: 53 push %ebx
8048295: 83 ec 08 sub $0x8,%esp
8048298: e8 00 00 00 00 call 804829d <_init+0x9>
804829d: 5b pop %ebx
804829e: 81 c3 57 1d 00 00 add $0x1d57,%ebx
80482a4: 8b 83 fc ff ff ff mov -0x4(%ebx),%eax
80482aa: 85 c0 test %eax,%eax
80482ac: 74 05 je 80482b3 <_init+0x1f>
80482ae: e8 2d 00 00 00 call 80482e0 <__gmon_start__@plt>
80482b3: e8 e8 00 00 00 call 80483a0 <frame_dummy>
80482b8: e8 93 01 00 00 call 8048450 <__do_global_ctors_aux>
80482bd: 83 c4 08 add $0x8,%esp
80482c0: 5b pop %ebx
80482c1: c3 ret
Disassembly of section .plt:
080482d0 <__gmon_start__@plt-0x10>:
80482d0: ff 35 f8 9f 04 08 pushl 0x8049ff8
80482d6: ff 25 fc 9f 04 08 jmp *0x8049ffc
80482dc: 00 00 add %al,(%eax)
...
080482e0 <__gmon_start__@plt>:
80482e0: ff 25 00 a0 04 08 jmp *0x804a000
80482e6: 68 00 00 00 00 push $0x0
80482eb: e9 e0 ff ff ff jmp 80482d0 <_init+0x3c>
080482f0 <__libc_start_main@plt>:
80482f0: ff 25 04 a0 04 08 jmp *0x804a004
80482f6: 68 08 00 00 00 push $0x8
80482fb: e9 d0 ff ff ff jmp 80482d0 <_init+0x3c>
Disassembly of section .text:
08048300 <main>:
8048300: 55 push %ebp
8048301: b8 00 b2 00 00 mov $0xb200,%eax
8048306: 89 e5 mov %esp,%ebp
8048308: 83 e4 f0 and $0xfffffff0,%esp
804830b: c9 leave
804830c: c3 ret
804830d: 90 nop
804830e: 90 nop
804830f: 90 nop
08048310 <_start>:
8048310: 31 ed xor %ebp,%ebp
8048312: 5e pop %esi
8048313: 89 e1 mov %esp,%ecx
8048315: 83 e4 f0 and $0xfffffff0,%esp
8048318: 50 push %eax
8048319: 54 push %esp
804831a: 52 push %edx
804831b: 68 40 84 04 08 push $0x8048440
8048320: 68 d0 83 04 08 push $0x80483d0
8048325: 51 push %ecx
8048326: 56 push %esi
8048327: 68 00 83 04 08 push $0x8048300
804832c: e8 bf ff ff ff call 80482f0 <__libc_start_main@plt>
8048331: f4 hlt
8048332: 90 nop
8048333: 90 nop
8048334: 90 nop
8048335: 90 nop
8048336: 90 nop
8048337: 90 nop
8048338: 90 nop
8048339: 90 nop
804833a: 90 nop
804833b: 90 nop
804833c: 90 nop
804833d: 90 nop
804833e: 90 nop
804833f: 90 nop
08048340 <__do_global_dtors_aux>:
8048340: 55 push %ebp
8048341: 89 e5 mov %esp,%ebp
8048343: 53 push %ebx
8048344: 83 ec 04 sub $0x4,%esp
8048347: 80 3d 10 a0 04 08 00 cmpb $0x0,0x804a010
804834e: 75 3f jne 804838f
<__do_global_dtors_aux+0x4f>
8048350: a1 14 a0 04 08 mov 0x804a014,%eax
8048355: bb 20 9f 04 08 mov $0x8049f20,%ebx
804835a: 81 eb 1c 9f 04 08 sub $0x8049f1c,%ebx
8048360: c1 fb 02 sar $0x2,%ebx
8048363: 83 eb 01 sub $0x1,%ebx
8048366: 39 d8 cmp %ebx,%eax
8048368: 73 1e jae 8048388
<__do_global_dtors_aux+0x48>
804836a: 8d b6 00 00 00 00 lea 0x0(%esi),%esi
8048370: 83 c0 01 add $0x1,%eax
8048373: a3 14 a0 04 08 mov %eax,0x804a014
8048378: ff 14 85 1c 9f 04 08 call *0x8049f1c(,%eax,4)
804837f: a1 14 a0 04 08 mov 0x804a014,%eax
8048384: 39 d8 cmp %ebx,%eax
8048386: 72 e8 jb 8048370
<__do_global_dtors_aux+0x30>
8048388: c6 05 10 a0 04 08 01 movb $0x1,0x804a010
804838f: 83 c4 04 add $0x4,%esp
8048392: 5b pop %ebx
8048393: 5d pop %ebp
8048394: c3 ret
8048395: 8d 74 26 00 lea 0x0(%esi,%eiz,1),%esi
8048399: 8d bc 27 00 00 00 00 lea 0x0(%edi,%eiz,1),%edi
080483a0 <frame_dummy>:
80483a0: 55 push %ebp
80483a1: 89 e5 mov %esp,%ebp
80483a3: 83 ec 18 sub $0x18,%esp
80483a6: a1 24 9f 04 08 mov 0x8049f24,%eax
80483ab: 85 c0 test %eax,%eax
80483ad: 74 12 je 80483c1 <frame_dummy+0x21>
80483af: b8 00 00 00 00 mov $0x0,%eax
80483b4: 85 c0 test %eax,%eax
80483b6: 74 09 je 80483c1 <frame_dummy+0x21>
80483b8: c7 04 24 24 9f 04 08 movl $0x8049f24,(%esp)
80483bf: ff d0 call *%eax
80483c1: c9 leave
80483c2: c3 ret
80483c3: 90 nop
80483c4: 90 nop
80483c5: 90 nop
80483c6: 90 nop
80483c7: 90 nop
80483c8: 90 nop
80483c9: 90 nop
80483ca: 90 nop
80483cb: 90 nop
80483cc: 90 nop
80483cd: 90 nop
80483ce: 90 nop
80483cf: 90 nop
080483d0 <__libc_csu_init>:
80483d0: 55 push %ebp
80483d1: 57 push %edi
80483d2: 56 push %esi
80483d3: 53 push %ebx
80483d4: e8 69 00 00 00 call 8048442 <__i686.get_pc_thunk.bx>
80483d9: 81 c3 1b 1c 00 00 add $0x1c1b,%ebx
80483df: 83 ec 1c sub $0x1c,%esp
80483e2: 8b 6c 24 30 mov 0x30(%esp),%ebp
80483e6: 8d bb 20 ff ff ff lea -0xe0(%ebx),%edi
80483ec: e8 a3 fe ff ff call 8048294 <_init>
80483f1: 8d 83 20 ff ff ff lea -0xe0(%ebx),%eax
80483f7: 29 c7 sub %eax,%edi
80483f9: c1 ff 02 sar $0x2,%edi
80483fc: 85 ff test %edi,%edi
80483fe: 74 29 je 8048429 <__libc_csu_init+0x59>
8048400: 31 f6 xor %esi,%esi
8048402: 8d b6 00 00 00 00 lea 0x0(%esi),%esi
8048408: 8b 44 24 38 mov 0x38(%esp),%eax
804840c: 89 2c 24 mov %ebp,(%esp)
804840f: 89 44 24 08 mov %eax,0x8(%esp)
8048413: 8b 44 24 34 mov 0x34(%esp),%eax
8048417: 89 44 24 04 mov %eax,0x4(%esp)
804841b: ff 94 b3 20 ff ff ff call *-0xe0(%ebx,%esi,4)
8048422: 83 c6 01 add $0x1,%esi
8048425: 39 fe cmp %edi,%esi
8048427: 75 df jne 8048408 <__libc_csu_init+0x38>
8048429: 83 c4 1c add $0x1c,%esp
804842c: 5b pop %ebx
804842d: 5e pop %esi
804842e: 5f pop %edi
804842f: 5d pop %ebp
8048430: c3 ret
8048431: eb 0d jmp 8048440 <__libc_csu_fini>
8048433: 90 nop
8048434: 90 nop
8048435: 90 nop
8048436: 90 nop
8048437: 90 nop
8048438: 90 nop
8048439: 90 nop
804843a: 90 nop
804843b: 90 nop
804843c: 90 nop
804843d: 90 nop
804843e: 90 nop
804843f: 90 nop
08048440 <__libc_csu_fini>:
8048440: f3 c3 repz ret
08048442 <__i686.get_pc_thunk.bx>:
8048442: 8b 1c 24 mov (%esp),%ebx
8048445: c3 ret
8048446: 90 nop
8048447: 90 nop
8048448: 90 nop
8048449: 90 nop
804844a: 90 nop
804844b: 90 nop
804844c: 90 nop
804844d: 90 nop
804844e: 90 nop
804844f: 90 nop
08048450 <__do_global_ctors_aux>:
8048450: 55 push %ebp
8048451: 89 e5 mov %esp,%ebp
8048453: 53 push %ebx
8048454: 83 ec 04 sub $0x4,%esp
8048457: a1 14 9f 04 08 mov 0x8049f14,%eax
804845c: 83 f8 ff cmp $0xffffffff,%eax
804845f: 74 13 je 8048474
<__do_global_ctors_aux+0x24>
8048461: bb 14 9f 04 08 mov $0x8049f14,%ebx
8048466: 66 90 xchg %ax,%ax
8048468: 83 eb 04 sub $0x4,%ebx
804846b: ff d0 call *%eax
804846d: 8b 03 mov (%ebx),%eax
804846f: 83 f8 ff cmp $0xffffffff,%eax
8048472: 75 f4 jne 8048468
<__do_global_ctors_aux+0x18>
8048474: 83 c4 04 add $0x4,%esp
8048477: 5b pop %ebx
8048478: 5d pop %ebp
8048479: c3 ret
804847a: 90 nop
804847b: 90 nop
Disassembly of section .fini:
0804847c <_fini>:
804847c: 53 push %ebx
804847d: 83 ec 08 sub $0x8,%esp
8048480: e8 00 00 00 00 call 8048485 <_fini+0x9>
8048485: 5b pop %ebx
8048486: 81 c3 6f 1b 00 00 add $0x1b6f,%ebx
804848c: e8 af fe ff ff call 8048340 <__do_global_dtors_aux>
8048491: 83 c4 08 add $0x8,%esp
8048494: 5b pop %ebx
8048495: c3 ret
#include <emmintrin.h>
__v2di x; /* Our code currently uses these, but it should not */
int main() {
__m128i foo = _mm_setr_epi32(0x8cab1e00, 0x12345678, 0xdeadbeef, 0xbebecafe);
__m128i bar = _mm_setr_epi32(0x12323717, 0x26622626, 0xabbabbab, 0xfeed1664);
foo = _mm_mullo_epi16(foo, bar);
return _mm_extract_epi16(foo, 0);
}
