This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Question about vectorization limit
- From: Richard Biener <richard dot guenther at gmail dot com>
- To: Toon Moene <toon at moene dot org>
- Cc: Jakub Jelinek <jakub at redhat dot com>, Dehao Chen <dehao at google dot com>, GCC Development <gcc at gcc dot gnu dot org>
- Date: Fri, 31 May 2013 15:53:28 +0200
- Subject: Re: Question about vectorization limit
- References: <CAO2gOZX7_-08m_+AEybF0RwG=8Y_qPG_+wjmgsq6ymVWTr3=Vw at mail dot gmail dot com> <CAFiYyc3ehiZeyrXUb+wgj_tBi7WqmeHNQdFK9vDinnMWYHYswA at mail dot gmail dot com> <51A8A3EF dot 3010508 at moene dot org> <20130531134131 dot GT1493 at tucnak dot redhat dot com> <51A8AA4B dot 6080001 at moene dot org>
On Fri, May 31, 2013 at 3:48 PM, Toon Moene <toon@moene.org> wrote:
> On 05/31/2013 03:41 PM, Jakub Jelinek wrote:
>
>> On Fri, May 31, 2013 at 03:21:51PM +0200, Toon Moene wrote:
>
>
>>> SUBROUTINE XYZ(A, B, N)
>>> DIMENSION A(N), B(N)
>>> DO I = 1, N
>>> IF (A(I)> 0.0) THEN
>>> A(I) = B(I) / A(I)
>>> ELSE
>>> A(I) = B(I)
>>> ENDIF
>>> ENDDO
>>> END
>>
>>
>> Well, in this case (with -Ofast) it is just the case that ifcvt
>> or earlier passes did a poor job at moving the load from B(I)
>> before the conditional, which, if we ignore exceptions, should be
>> possible,
>> as both branches read from the same memory.
>> The store to A(I) is already hoisted by cselim out of the conditional.
>>
>> If you rewrite the above into:
>> SUBROUTINE XYZ(A, B, N)
>> DIMENSION A(N), B(N)
>> DO I = 1, N
>> C = B(I)
>> IF (A(I)> 0.0) THEN
>> A(I) = C / A(I)
>> ELSE
>> A(I) = C
>> ENDIF
>> ENDDO
>> END
>>
>> then it is vectorized just fine.
>
>
> But this "inner loop" has at least 3 basic blocks - so what does the
> "loop->num_nodes != 2" test exactly codify ?
>
> Is Dehao just looking at the wrong test ? And why is this test there ?
As I said, the test is there to early out for loops we can't vectorize anyway
(currently, that is, as Jakub says in future we may have infrastructure to
deal with some cases).
Richard.