On Tue, 19 Nov 2013, Sergey Ostanevich wrote:
> :) agree to you, but as soon as you're a user who tries to introduce
> vector code and face a bug in cost model you'd like to have a
> workaround until the bug will be fixed and compiler will come to you
> with new OS distribution, don't you?
>
> I propose the following, yet SLP have to use a NULL as a loop info
> which looks somewhat hacky.
I think this is overengineering. -fvect-cost-model will do as
workaround. And -fsimd-vect-cost-model has what I consider
duplicate - "simd" and "vect".
Richard.
> Sergos
>
>
> * common.opt: Added new option -fsimd-vect-cost-model
> * tree-vectorizer.h (unlimited_cost_model): Interface update
> to rely on particular loop info
> * tree-vect-data-refs.c (vect_peeling_hash_insert): Update to
> unlimited_cost_model call according to new interface
> (vect_peeling_hash_choose_best_peeling): Ditto
> (vect_enhance_data_refs_alignment): Ditto
> * tree-vect-slp.c: Ditto
> * tree-vect-loop.c (vect_estimate_min_profitable_iters): Ditto
> plus issue a warning in case cost model overrides users' directive
>
>
>
> diff --git a/gcc/common.opt b/gcc/common.opt
> index d5971df..87b3b37 100644
> --- a/gcc/common.opt
> +++ b/gcc/common.opt
> @@ -2296,6 +2296,10 @@ fvect-cost-model=
> Common Joined RejectNegative Enum(vect_cost_model)
> Var(flag_vect_cost_model) Init(VECT_COST_MODEL_DEFAULT)
> Specifies the cost model for vectorization
>
> +fsimd-vect-cost-model=
> +Common Joined RejectNegative Enum(vect_cost_model)
> Var(flag_simd_vect_cost_model) Init(VECT_COST_MODEL_UNLIMITED)
> +Specifies the cost model for vectorization in loops marked with
> #pragma omp simd
> +
> Enum
> Name(vect_cost_model) Type(enum vect_cost_model) UnknownError(unknown
> vectorizer cost model %qs)
>
> diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
> index 83d1f45..e26f704 100644
> --- a/gcc/tree-vect-data-refs.c
> +++ b/gcc/tree-vect-data-refs.c
> @@ -1090,7 +1090,8 @@ vect_peeling_hash_insert (loop_vec_info
> loop_vinfo, struct data_reference *dr,
> *new_slot = slot;
> }
>
> - if (!supportable_dr_alignment && unlimited_cost_model ())
> + if (!supportable_dr_alignment
> + && unlimited_cost_model (LOOP_VINFO_LOOP (loop_vinfo)))
> slot->count += VECT_MAX_COST;
> }
>
> @@ -1200,7 +1201,7 @@ vect_peeling_hash_choose_best_peeling
> (loop_vec_info loop_vinfo,
> res.peel_info.dr = NULL;
> res.body_cost_vec = stmt_vector_for_cost ();
>
> - if (!unlimited_cost_model ())
> + if (!unlimited_cost_model (LOOP_VINFO_LOOP (loop_vinfo)))
> {
> res.inside_cost = INT_MAX;
> res.outside_cost = INT_MAX;
> @@ -1429,7 +1430,7 @@ vect_enhance_data_refs_alignment (loop_vec_info
> loop_vinfo)
> vectorization factor.
> We do this automtically for cost model, since we
> calculate cost
> for every peeling option. */
> - if (unlimited_cost_model ())
> + if (unlimited_cost_model (LOOP_VINFO_LOOP (loop_vinfo)))
> possible_npeel_number = vf /nelements;
>
> /* Handle the aligned case. We may decide to align some other
> @@ -1437,7 +1438,7 @@ vect_enhance_data_refs_alignment (loop_vec_info
> loop_vinfo)
> if (DR_MISALIGNMENT (dr) == 0)
> {
> npeel_tmp = 0;
> - if (unlimited_cost_model ())
> + if (unlimited_cost_model (LOOP_VINFO_LOOP (loop_vinfo)))
> possible_npeel_number++;
> }
>
> diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
> index 86ebbd2..be66172 100644
> --- a/gcc/tree-vect-loop.c
> +++ b/gcc/tree-vect-loop.c
> @@ -2696,7 +2696,7 @@ vect_estimate_min_profitable_iters
> (loop_vec_info loop_vinfo,
> void *target_cost_data = LOOP_VINFO_TARGET_COST_DATA (loop_vinfo);
>
> /* Cost model disabled. */
> - if (unlimited_cost_model ())
> + if (unlimited_cost_model (LOOP_VINFO_LOOP (loop_vinfo)))
> {
> dump_printf_loc (MSG_NOTE, vect_location, "cost model disabled.\n");
> *ret_min_profitable_niters = 0;
> @@ -2929,6 +2929,11 @@ vect_estimate_min_profitable_iters
> (loop_vec_info loop_vinfo,
> /* vector version will never be profitable. */
> else
> {
> + if (LOOP_VINFO_LOOP (loop_vinfo)->force_vect)
> + {
> + pedwarn (vect_location, 0, "Vectorization did not happen
> for the loop");
> + }
> +
> if (dump_enabled_p ())
> dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
> "cost model: the vector iteration cost = %d "
> diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
> index 247bdfd..4b25964 100644
> --- a/gcc/tree-vect-slp.c
> +++ b/gcc/tree-vect-slp.c
> @@ -2171,7 +2171,7 @@ vect_slp_analyze_bb_1 (basic_block bb)
> }
>
> /* Cost model: check if the vectorization is worthwhile. */
> - if (!unlimited_cost_model ()
> + if (!unlimited_cost_model (NULL)
> && !vect_bb_vectorization_profitable_p (bb_vinfo))
> {
> if (dump_enabled_p ())
> diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
> index a6c5b59..2916906 100644
> --- a/gcc/tree-vectorizer.h
> +++ b/gcc/tree-vectorizer.h
> @@ -919,9 +919,12 @@ known_alignment_for_access_p (struct
> data_reference *data_ref_info)
>
> /* Return true if the vect cost model is unlimited. */
> static inline bool
> -unlimited_cost_model ()
> +unlimited_cost_model (loop_p loop)
> {
> - return flag_vect_cost_model == VECT_COST_MODEL_UNLIMITED;
> + return (flag_vect_cost_model == VECT_COST_MODEL_UNLIMITED
> + || (loop != NULL
> + && loop->force_vect
> + && flag_simd_vect_cost_model == VECT_COST_MODEL_UNLIMITED));
> }
>
> /* Source location */
>
> On Mon, Nov 18, 2013 at 7:13 PM, Richard Biener <rguent...@suse.de> wrote:
> > On Mon, 18 Nov 2013, Sergey Ostanevich wrote:
> >
> >> I would agree that the example is just for the case cost model makes
> >> correct estimation But how can we assure ourself that it won't have any
> >> mistakes in the future?
> >
> > We call it bugs and not mistakes and we have bugzilla for it.
> >
> > Richard.
> >
> >> I believe it'll be Ok to introduce an extra flag as Jakub proposed for the
> >> dedicated simd-forced vectorization to use unlimited cost model. This
> >> can be default for -fopenmp or there should be a warning issued that
> >> compiler overrides user's request of vectorization. In such a case user
> >> can enforce vectorization (even with mentioned results :) with this
> >> unlimited cost model for simd.
> >>
> >>
> >>
> >> On Fri, Nov 15, 2013 at 6:24 PM, Richard Biener <rguent...@suse.de> wrote:
> >> > On Fri, 15 Nov 2013, Sergey Ostanevich wrote:
> >> >
> >> >> Richard,
> >> >>
> >> >> here's an example that causes trigger for the cost model.
> >> >
> >> > I hardly believe that (AVX2)
> >> >
> >> > .L9:
> >> > vmovups (%rsi), %xmm3
> >> > addl $1, %r8d
> >> > addq $256, %rsi
> >> > vinsertf128 $0x1, -240(%rsi), %ymm3, %ymm1
> >> > vmovups -224(%rsi), %xmm3
> >> > vinsertf128 $0x1, -208(%rsi), %ymm3, %ymm3
> >> > vshufps $136, %ymm3, %ymm1, %ymm3
> >> > vperm2f128 $3, %ymm3, %ymm3, %ymm2
> >> > vshufps $68, %ymm2, %ymm3, %ymm1
> >> > vshufps $238, %ymm2, %ymm3, %ymm2
> >> > vmovups -192(%rsi), %xmm3
> >> > vinsertf128 $1, %xmm2, %ymm1, %ymm2
> >> > vinsertf128 $0x1, -176(%rsi), %ymm3, %ymm1
> >> > vmovups -160(%rsi), %xmm3
> >> > vinsertf128 $0x1, -144(%rsi), %ymm3, %ymm3
> >> > vshufps $136, %ymm3, %ymm1, %ymm3
> >> > vperm2f128 $3, %ymm3, %ymm3, %ymm1
> >> > vshufps $68, %ymm1, %ymm3, %ymm4
> >> > vshufps $238, %ymm1, %ymm3, %ymm1
> >> > vmovups -128(%rsi), %xmm3
> >> > vinsertf128 $1, %xmm1, %ymm4, %ymm1
> >> > vshufps $136, %ymm1, %ymm2, %ymm1
> >> > vperm2f128 $3, %ymm1, %ymm1, %ymm2
> >> > vshufps $68, %ymm2, %ymm1, %ymm4
> >> > vshufps $238, %ymm2, %ymm1, %ymm2
> >> > vinsertf128 $0x1, -112(%rsi), %ymm3, %ymm1
> >> > vmovups -96(%rsi), %xmm3
> >> > vinsertf128 $1, %xmm2, %ymm4, %ymm4
> >> > vinsertf128 $0x1, -80(%rsi), %ymm3, %ymm3
> >> > vshufps $136, %ymm3, %ymm1, %ymm3
> >> > vperm2f128 $3, %ymm3, %ymm3, %ymm2
> >> > vshufps $68, %ymm2, %ymm3, %ymm1
> >> > vshufps $238, %ymm2, %ymm3, %ymm2
> >> > vmovups -64(%rsi), %xmm3
> >> > vinsertf128 $1, %xmm2, %ymm1, %ymm2
> >> > vinsertf128 $0x1, -48(%rsi), %ymm3, %ymm1
> >> > vmovups -32(%rsi), %xmm3
> >> > vinsertf128 $0x1, -16(%rsi), %ymm3, %ymm3
> >> > cmpl %r8d, %edi
> >> > vshufps $136, %ymm3, %ymm1, %ymm3
> >> > vperm2f128 $3, %ymm3, %ymm3, %ymm1
> >> > vshufps $68, %ymm1, %ymm3, %ymm5
> >> > vshufps $238, %ymm1, %ymm3, %ymm1
> >> > vinsertf128 $1, %xmm1, %ymm5, %ymm1
> >> > vshufps $136, %ymm1, %ymm2, %ymm1
> >> > vperm2f128 $3, %ymm1, %ymm1, %ymm2
> >> > vshufps $68, %ymm2, %ymm1, %ymm3
> >> > vshufps $238, %ymm2, %ymm1, %ymm2
> >> > vinsertf128 $1, %xmm2, %ymm3, %ymm1
> >> > vshufps $136, %ymm1, %ymm4, %ymm1
> >> > vperm2f128 $3, %ymm1, %ymm1, %ymm2
> >> > vshufps $68, %ymm2, %ymm1, %ymm3
> >> > vshufps $238, %ymm2, %ymm1, %ymm2
> >> > vinsertf128 $1, %xmm2, %ymm3, %ymm2
> >> > vaddps %ymm2, %ymm0, %ymm0
> >> > ja .L9
> >> >
> >> > is more efficient than
> >> >
> >> > .L3:
> >> > vaddss (%rcx,%rax), %xmm0, %xmm0
> >> > addq $32, %rax
> >> > cmpq %rdx, %rax
> >> > jne .L3
> >> >
> >> > ;)
> >> >
> >> >> As soon as
> >> >> elemental functions will appear and we update the vectorizer so it can
> >> >> accept
> >> >> an elemental function inside the loop - we will have the same
> >> >> situation as we have
> >> >> it now: cost model will bail out with profitability estimation.
> >> >
> >> > Yes.
> >> >
> >> >> Still we have no chance to get info on how efficient the bar() function
> >> >> when it
> >> >> is in vector form.
> >> >
> >> > Well I assume you mean that the speedup when vectorizing the elemental
> >> > will offset whatever wreckage we cause with vectorizing the rest of the
> >> > statements. I'd say you can at least compare to unrolling by
> >> > the vectorization factor, building the vector inputs to the elemental
> >> > from scalars, distributing the vector result from the elemental to
> >> > scalars.
> >> >
> >> >> I believe I should repeat: #pragma omp simd is intended for
> >> >> introduction of an
> >> >> instruction-level parallel region on developer's request, hence should
> >> >> be treated
> >> >> in same manner as #pragma omp parallel. Vectorizer cost model is an
> >> >> obstacle
> >> >> here, not a help.
> >> >
> >> > Surely not if there isn't an elemental call in it. With it the
> >> > cost model of course will have not enough information to decide.
> >> >
> >> > But still, what's the difference to the case where we cannot vectorize
> >> > the function? What happens if we cannot vectorize the elemental?
> >> > Do we have to build scalar versions for all possible vector sizes?
> >> >
> >> > Richard.
> >> >
> >> >> Regards,
> >> >> Sergos
> >> >>
> >> >>
> >> >> On Fri, Nov 15, 2013 at 1:08 AM, Richard Biener <rguent...@suse.de>
> >> >> wrote:
> >> >> > Sergey Ostanevich <sergos....@gmail.com> wrote:
> >> >> >>this is only for the whole file? I mean to have a particular loop
> >> >> >>vectorized in a
> >> >> >>file while all others - up to compiler's cost model. is there such a
> >> >> >>machinery?
> >> >> >
> >> >> > No, there is not.
> >> >> >
> >> >> > Richard.
> >> >> >
> >> >> >>Sergos
> >> >> >>
> >> >> >>On Thu, Nov 14, 2013 at 12:39 PM, Richard Biener <rguent...@suse.de>
> >> >> >>wrote:
> >> >> >>> On Wed, 13 Nov 2013, Sergey Ostanevich wrote:
> >> >> >>>
> >> >> >>>> I will get some tests.
> >> >> >>>> As for cost analysis - simply consider the pragma as a request to
> >> >> >>>> vectorize. How can I - as a developer - enforce it beyond the
> >> >> >>pragma?
> >> >> >>>
> >> >> >>> You can disable the cost model via -fvect-cost-model=unlimited
> >> >> >>>
> >> >> >>> Richard.
> >> >> >>>
> >> >> >>>> On Wed, Nov 13, 2013 at 12:55 PM, Richard Biener
> >> >> >>>> <rguent...@suse.de>
> >> >> >>wrote:
> >> >> >>>> > On Tue, 12 Nov 2013, Sergey Ostanevich wrote:
> >> >> >>>> >
> >> >> >>>> >> The reason patch was in its original state is because we want
> >> >> >>>> >> to notify user that his assumption of profitability may be
> >> >> >>>> >> wrong.
> >> >> >>>> >> This is not a part of any spec and as far as I know ICC does not
> >> >> >>>> >> notify user about the case. Still it can be a good hint for
> >> >> >>>> >> those
> >> >> >>>> >> users who tries to get as much as possible performance.
> >> >> >>>> >>
> >> >> >>>> >> Richard's comment on the vectorization problems is about the
> >> >> >>>> >> same
> >> >> >>-
> >> >> >>>> >> to inform user that his attempt to force vectorization is
> >> >> >>>> >> failed.
> >> >> >>>> >>
> >> >> >>>> >> As for profitable or not - sometimes I believe it's impossible
> >> >> >>>> >> to
> >> >> >>be
> >> >> >>>> >> precise. For OMP we have case of a vector version of a function
> >> >> >>>> >> and we have no chance to figure out whether it is profitable to
> >> >> >>use
> >> >> >>>> >> it or to loose it. If we can't map the loop for any vector
> >> >> >>>> >> length
> >> >> >>>> >> other than 1 - I believe in this case we have to bail out and
> >> >> >>report.
> >> >> >>>> >> Is it about 'never profitable'?
> >> >> >>>> >
> >> >> >>>> > For example. I think we should report non-vectorized loops
> >> >> >>>> > that are marked with force_vect anyway, with
> >> >> >>-Wdisabled-optimization.
> >> >> >>>> > Another case is that a loop may be profitable to vectorize if
> >> >> >>>> > the ISA supports a gather instruction but otherwise not. Or if
> >> >> >>the
> >> >> >>>> > ISA supports efficient vector construction from N not loop
> >> >> >>>> > invariant scalars (for vectorization of strided loads).
> >> >> >>>> >
> >> >> >>>> > Simply disregarding all of the cost analysis sounds completely
> >> >> >>>> > bogus to me.
> >> >> >>>> >
> >> >> >>>> > I'd simply go for the diagnostic for now, not changing anything
> >> >> >>else.
> >> >> >>>> > We want to have a good understanding about why the cost model is
> >> >> >>>> > so bad that we have to force to ignore it for #pragma simd - thus
> >> >> >>we
> >> >> >>>> > want testcases.
> >> >> >>>> >
> >> >> >>>> > Richard.
> >> >> >>>> >
> >> >> >>>> >>
> >> >> >>>> >> On Tue, Nov 12, 2013 at 6:35 PM, Richard Biener
> >> >> >><rguent...@suse.de> wrote:
> >> >> >>>> >> > On 11/12/13 3:16 PM, Jakub Jelinek wrote:
> >> >> >>>> >> >> On Tue, Nov 12, 2013 at 05:46:14PM +0400, Sergey Ostanevich
> >> >> >>wrote:
> >> >> >>>> >> >>> ivdep just substitutes all cross-iteration data analysis,
> >> >> >>>> >> >>> nothing related to cost model. ICC does not cancel its
> >> >> >>>> >> >>> cost model in case of #pragma ivdep
> >> >> >>>> >> >>>
> >> >> >>>> >> >>> as for the safelen - OMP standart treats it as a limitation
> >> >> >>>> >> >>> for the vector length. this means if no safelen is present
> >> >> >>>> >> >>> an arbitrary vector length can be used.
> >> >> >>>> >> >>
> >> >> >>>> >> >> I was talking about GCC loop->safelen, which is INT_MAX for
> >> >> >>#pragma omp simd
> >> >> >>>> >> >> without safelen clause or #pragma simd without vectorlength
> >> >> >>clause.
> >> >> >>>> >> >>
> >> >> >>>> >> >>> so I believe loop->force_vect is the only trigger to
> >> >> >>disregard
> >> >> >>>> >> >>> the cost model
> >> >> >>>> >> >>
> >> >> >>>> >> >> Anyway, in that case I think the originally posted patch is
> >> >> >>wrong,
> >> >> >>>> >> >> if we want to treat force_vect as disregard all the cost
> >> >> >>>> >> >> model
> >> >> >>and
> >> >> >>>> >> >> force vectorization (well, the name of the field already kind
> >> >> >>of suggest
> >> >> >>>> >> >> that), then IMHO we should treat it the same as
> >> >> >>-fvect-cost-model=unlimited
> >> >> >>>> >> >> for those loops.
> >> >> >>>> >> >
> >> >> >>>> >> > Err - the user may have a specific sub-architecture in mind
> >> >> >>when using
> >> >> >>>> >> > #pragma simd, if you say we should completely ignore the cost
> >> >> >>model
> >> >> >>>> >> > then should we also sorry () if we cannot vectorize the loop
> >> >> >>(either
> >> >> >>>> >> > because of GCC deficiencies or lack of sub-target support)?
> >> >> >>>> >> >
> >> >> >>>> >> > That said, at least in the cases that the cost model says the
> >> >> >>loop
> >> >> >>>> >> > is never profitable to vectorize we should follow its advice.
> >> >> >>>> >> >
> >> >> >>>> >> > Richard.
> >> >> >>>> >> >
> >> >> >>>> >> >> Thus (untested):
> >> >> >>>> >> >>
> >> >> >>>> >> >> 2013-11-12 Jakub Jelinek <ja...@redhat.com>
> >> >> >>>> >> >>
> >> >> >>>> >> >> * tree-vect-loop.c
> >> >> >>>> >> >> (vect_estimate_min_profitable_iters):
> >> >> >>Use
> >> >> >>>> >> >> unlimited cost model also for force_vect loops.
> >> >> >>>> >> >>
> >> >> >>>> >> >> --- gcc/tree-vect-loop.c.jj 2013-11-12 12:09:40.000000000
> >> >> >>+0100
> >> >> >>>> >> >> +++ gcc/tree-vect-loop.c 2013-11-12 15:11:43.821404330
> >> >> >>+0100
> >> >> >>>> >> >> @@ -2702,7 +2702,7 @@ vect_estimate_min_profitable_iters
> >> >> >>>> >> >> (loop
> >> >> >>>> >> >> void *target_cost_data = LOOP_VINFO_TARGET_COST_DATA
> >> >> >>(loop_vinfo);
> >> >> >>>> >> >>
> >> >> >>>> >> >> /* Cost model disabled. */
> >> >> >>>> >> >> - if (unlimited_cost_model ())
> >> >> >>>> >> >> + if (unlimited_cost_model () || LOOP_VINFO_LOOP
> >> >> >>(loop_vinfo)->force_vect)
> >> >> >>>> >> >> {
> >> >> >>>> >> >> dump_printf_loc (MSG_NOTE, vect_location, "cost model
> >> >> >>disabled.\n");
> >> >> >>>> >> >> *ret_min_profitable_niters = 0;
> >> >> >>>> >> >>
> >> >> >>>> >> >> Jakub
> >> >> >>>> >> >>
> >> >> >>>> >> >
> >> >> >>>> >>
> >> >> >>>> >>
> >> >> >>>> >
> >> >> >>>> > --
> >> >> >>>> > Richard Biener <rguent...@suse.de>
> >> >> >>>> > SUSE / SUSE Labs
> >> >> >>>> > SUSE LINUX Products GmbH - Nuernberg - AG Nuernberg - HRB 16746
> >> >> >>>> > GF: Jeff Hawn, Jennifer Guild, Felix Imend
> >> >> >>>>
> >> >> >>>>
> >> >> >>>
> >> >> >>> --
> >> >> >>> Richard Biener <rguent...@suse.de>
> >> >> >>> SUSE / SUSE Labs
> >> >> >>> SUSE LINUX Products GmbH - Nuernberg - AG Nuernberg - HRB 16746
> >> >> >>> GF: Jeff Hawn, Jennifer Guild, Felix Imend"orffer
> >> >> >
> >> >> >
> >> >>
> >> >
> >> > --
> >> > Richard Biener <rguent...@suse.de>
> >> > SUSE / SUSE Labs
> >> > SUSE LINUX Products GmbH - Nuernberg - AG Nuernberg - HRB 16746
> >> > GF: Jeff Hawn, Jennifer Guild, Felix Imend"orffer
> >>
> >>
> >
> > --
> > Richard Biener <rguent...@suse.de>
> > SUSE / SUSE Labs
> > SUSE LINUX Products GmbH - Nuernberg - AG Nuernberg - HRB 16746
> > GF: Jeff Hawn, Jennifer Guild, Felix Imend"orffer
>
>
--
Richard Biener <rguent...@suse.de>
SUSE / SUSE Labs
SUSE LINUX Products GmbH - Nuernberg - AG Nuernberg - HRB 16746
GF: Jeff Hawn, Jennifer Guild, Felix Imend"orffer
