On Mon, Apr 16, 2012 at 11:25 AM, Nick Foster wrote:
> On Mon, Apr 16, 2012 at 5:50 AM, Joanna Rutkowska
> wrote:
>>
>> On 04/16/12 14:20, Joanna Rutkowska wrote:
>> /.../
>> >
>> > So, it seems like it is not a Xen issue, but instead that the kernel
>> > I'm using in the VM (essentially a vanill
On Mon, Apr 16, 2012 at 5:50 AM, Joanna Rutkowska <
joa...@invisiblethingslab.com> wrote:
> On 04/16/12 14:20, Joanna Rutkowska wrote:
> /.../
> >
> > So, it seems like it is not a Xen issue, but instead that the kernel
> > I'm using in the VM (essentially a vanilla 3.0.4) is not enabling AVX
> >
On Mon, Apr 16, 2012 at 05:20, Joanna Rutkowska
wrote:
>> Joanna, let us know how this works for you. I'm going to be on the
>> road for the next few days, so I'll be sparsely available.
>
> Yes, it works! I can now use the gr_add block to add to sin signals, how
> cool! ;)
>
> BTW, as Nick's pat
On 04/16/12 14:20, Joanna Rutkowska wrote:
/.../
>
> So, it seems like it is not a Xen issue, but instead that the kernel
> I'm using in the VM (essentially a vanilla 3.0.4) is not enabling AVX
> in XCR0. It would be interesting if anybody could try this on a
> non-Xen system with a similarly old
On 04/16/12 13:47, Tom Rondeau wrote:
> On Sun, Apr 15, 2012 at 8:24 PM, Nick Foster wrote:
>> > Attached is a patch with one further check -- to make sure the check that
>> > AVX is enabled by the OS, is enabled by the OS.
>> >
>> > No kidding.
>> >
>> > --n
> Wonderful, Nick, thanks.
>
> Joanna
On Sun, Apr 15, 2012 at 8:24 PM, Nick Foster wrote:
> Attached is a patch with one further check -- to make sure the check that
> AVX is enabled by the OS, is enabled by the OS.
>
> No kidding.
>
> --n
Wonderful, Nick, thanks.
Joanna, let us know how this works for you. I'm going to be on the
ro
Attached is a patch with one further check -- to make sure the check that
AVX is enabled by the OS, is enabled by the OS.
No kidding.
--n
On Sun, Apr 15, 2012 at 4:09 PM, Nick Foster wrote:
> On Sun, Apr 15, 2012 at 2:26 PM, Joanna Rutkowska <
> joa...@invisiblethingslab.com> wrote:
>
>
> Ano
On Sun, Apr 15, 2012 at 2:26 PM, Joanna Rutkowska <
joa...@invisiblethingslab.com> wrote:
> Another potential explanations of why this doesn't work I could come up
> with:
>
> 1) Perhaps volk somehow erroneously interprets cpuid info and assumes
> that AVX is present, while it is no...? Tom, can
On 04/15/12 17:45, Tom Rondeau wrote:
> Yes, so the vmovss is an AVX instruction (the AVX version of movss),
> but your processor doesn't have AVX according to your flags above.
> Except that it does. According to Intel, the i5-2540M processor
> supports AVX, but your OS isn't recognizing the avx f
On Sun, Apr 15, 2012 at 11:51 AM, Marcus D. Leech wrote:
> On 04/15/2012 11:45 AM, Tom Rondeau wrote:
>>
>>
>> Yes, so the vmovss is an AVX instruction (the AVX version of movss),
>> but your processor doesn't have AVX according to your flags above.
>> Except that it does. According to Intel, the
On 04/15/2012 11:45 AM, Tom Rondeau wrote:
Yes, so the vmovss is an AVX instruction (the AVX version of movss),
but your processor doesn't have AVX according to your flags above.
Except that it does. According to Intel, the i5-2540M processor
supports AVX, but your OS isn't recognizing the avx f
On Sun, Apr 15, 2012 at 11:04 AM, Joanna Rutkowska
wrote:
> On 04/15/12 16:59, Joanna Rutkowska wrote:
>> With dbg symbols:
>>
>> Starting program:
>> /rw/home/user/gnuradio/gnuradio/volk/build/apps/volk_profile
>> [Thread debugging using libthread_db enabled]
>> Using Volk machine: avx_64
>> RUN_
On 04/15/12 16:59, Joanna Rutkowska wrote:
> With dbg symbols:
>
> Starting program:
> /rw/home/user/gnuradio/gnuradio/volk/build/apps/volk_profile
> [Thread debugging using libthread_db enabled]
> Using Volk machine: avx_64
> RUN_VOLK_TESTS: volk_16ic_s32f_deinterleave_real_32f_a
>
> Program rec
On 04/15/12 16:52, Tom Rondeau wrote:
> On Sun, Apr 15, 2012 at 10:50 AM, Joanna Rutkowska
> wrote:
>> > On 04/15/12 16:46, Tom Rondeau wrote:
>>> >> Unfortunately, that doesn't narrow things down. How about running
>>> >> volk_profile under gdb? Let's see if we can find the instruction it's
>>> >
On Sun, Apr 15, 2012 at 10:50 AM, Joanna Rutkowska
wrote:
> On 04/15/12 16:46, Tom Rondeau wrote:
>> Unfortunately, that doesn't narrow things down. How about running
>> volk_profile under gdb? Let's see if we can find the instruction it's
>> puking on.
>>
>> I find it odd that in your original po
On 04/15/12 16:46, Tom Rondeau wrote:
> Unfortunately, that doesn't narrow things down. How about running
> volk_profile under gdb? Let's see if we can find the instruction it's
> puking on.
>
> I find it odd that in your original post, it looks like volk_profile
> is running avx_64, but your proc
On Sun, Apr 15, 2012 at 10:32 AM, Joanna Rutkowska
wrote:
> On 04/15/12 16:29, Tom Rondeau wrote:
>> On Sun, Apr 15, 2012 at 10:11 AM, Joanna Rutkowska
>> wrote:
>> Does 'make test' pass? If not, can you run:
>>
>> ctest -V -R volk
>>
>> And provide the output.
>
> It fails:
>
> [user@rflab vo
On 04/15/12 16:32, Joanna Rutkowska wrote:
> On 04/15/12 16:29, Tom Rondeau wrote:
>> > On Sun, Apr 15, 2012 at 10:11 AM, Joanna Rutkowska
>> > wrote:
>> > On 04/15/12 15:28, Tom Rondeau wrote:
>> >>> >> On Sun, Apr 15, 2012 at 7:07 AM, Joanna Rutkowska
>> >>> >> wrote:
On 04/15/12 16:29, Tom Rondeau wrote:
> On Sun, Apr 15, 2012 at 10:11 AM, Joanna Rutkowska
> wrote:
>> > On 04/15/12 15:28, Tom Rondeau wrote:
>>> >> On Sun, Apr 15, 2012 at 7:07 AM, Joanna Rutkowska
>>> >> wrote:
>>> Hello, I'm getting the invalid opcode exception whenever the volk
>>>
On Sun, Apr 15, 2012 at 10:11 AM, Joanna Rutkowska
wrote:
> On 04/15/12 15:28, Tom Rondeau wrote:
>> On Sun, Apr 15, 2012 at 7:07 AM, Joanna Rutkowska
>> wrote:
>>> Hello, I'm getting the invalid opcode exception whenever the volk
>>> library is used from gr/grc. It is also easy to reproduce by e
On 04/15/12 15:28, Tom Rondeau wrote:
> On Sun, Apr 15, 2012 at 7:07 AM, Joanna Rutkowska
> wrote:
>> Hello, I'm getting the invalid opcode exception whenever the volk
>> library is used from gr/grc. It is also easy to reproduce by executing
>> volk_profile:
>>
>> [user@rflab gnuradio]$ volk_profi
On Sun, Apr 15, 2012 at 7:07 AM, Joanna Rutkowska
wrote:
> Hello, I'm getting the invalid opcode exception whenever the volk
> library is used from gr/grc. It is also easy to reproduce by executing
> volk_profile:
>
> [user@rflab gnuradio]$ volk_profile
> Using Volk machine: avx_64
> RUN_VOLK_TEST
On 04/15/12 13:07, Joanna Rutkowska wrote:
> Hello, I'm getting the invalid opcode exception whenever the volk
> library is used from gr/grc. It is also easy to reproduce by executing
> volk_profile:
>
> [user@rflab gnuradio]$ volk_profile
> Using Volk machine: avx_64
> RUN_VOLK_TESTS: volk_16ic_s
Hello, I'm getting the invalid opcode exception whenever the volk
library is used from gr/grc. It is also easy to reproduce by executing
volk_profile:
[user@rflab gnuradio]$ volk_profile
Using Volk machine: avx_64
RUN_VOLK_TESTS: volk_16ic_s32f_deinterleave_real_32f_a
Illegal instruction
[user@rfl
24 matches
Mail list logo
