From: oluade01
This patch adds new RTL for ABDL (sabdl, sabdl2, uabdl, uabdl2).
gcc/ChangeLog:
* config/aarch64/aarch64-simd.md
(vec_widen_abdl_lo_, vec_widen_abdl_hi_):
Expansions for abd vec widen optabs.
(aarch64_abdl_insn): VQW based abdl RTL.
* confi
From: oluade01
This updates vect_recog_abd_pattern to recognize the widening
variant of absolute difference (ABDL, ABDL2).
gcc/ChangeLog:
* internal-fn.cc (widening_fn_p, decomposes_to_hilo_fn_p):
Add IFN_VEC_WIDEN_ABD to the switch statement.
* internal-fn.def (VEC_WIDE
> Sorry, my fault, but I meant the comment about avoiding
> (minus (max…) (min…)) for both patterns, not just the first.
Change made.
> I think the review suggestions for 1/2 will change the tests.
> For example:
>
> TEST2(signed, short, char)
This is the case and the tests have been updated to
> Sorry, my fault. I was using the original type names in this
> suggestion, rather than the TYPE1…TYPE5 ones. Should be:
>
>WIDEN_ABD exists to optimize the case where TYPE4 is at least
>twice as wide as TYPE3.
Change made.
> Lingering use of “L” suffixes here. Maybe:
>
> stmts
From: oluade01
This patch adds new RTL for ABDL (sabdl, sabdl2, uabdl, uabdl2).
gcc/ChangeLog:
* config/aarch64/aarch64-simd.md
(vec_widen_abdl_lo_, vec_widen_abdl_hi_):
Expansions for abd vec widen optabs.
(aarch64_abdl_insn): VQW based abdl RTL.
* confi
> > +(define_insn "aarch64_abdl_hi_internal"
> > + [(set (match_operand: 0 "register_operand" "=w")
> > + (minus:
> > + (USMAX:
> > + (:
> > + (vec_select:
> > + (match_operand:VQW 1 "register_operand" "w")
> > + (match_operand:VQW 3 "vect_par_cnst_hi_half"
From: oluade01
This updates vect_recog_abd_pattern to recognize the widening
variant of absolute difference (ABDL, ABDL2).
gcc/ChangeLog:
* internal-fn.cc (widening_fn_p, decomposes_to_hilo_fn_p):
Add IFN_VEC_WIDEN_ABD to the switch statement.
* internal-fn.def (VEC_WIDE
> The new optabs need to be documented in doc/md.texi.
Done.
> “Long” is a bit of an architecture-specific term. Maybe just:
>
>Try to find the following ABsolute Difference (ABD) or
>widening ABD (WIDEN_ABD) pattern:
Change made.
> >> - VTYPE x, y, out;
> >> + VTYPE x, y;
> >
From: oluade01
This patch adds new RTL for ABDL (sabdl, sabdl2, uabdl, uabdl2).
gcc/ChangeLog:
* config/aarch64/aarch64-simd.md
(vec_widen_abdl_lo_, vec_widen_abdl_hi_):
Expansions for abd vec widen optabs.
(aarch64_abdl_insn): VQW based abdl RTL.
* confi
From: oluade01
This updates vect_recog_abd_pattern to recognize the widening
variant of absolute difference (ABDL, ABDL2).
gcc/ChangeLog:
* internal-fn.cc (widening_fn_p, decomposes_to_hilo_fn_p):
Add IFN_VEC_WIDEN_ABD to the switch statement.
* internal-fn.def (VEC_WIDE
From: oluade01
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.texi (sabd, uabd): Document them.
* internal-fn.def (ABD): Use new optab.
* optabs.def (sabd_optab, uabd_optab): New optabs,
* tree-vect-pattern
From: oluade01
This patch adds new RTL and tests for sabd and uabd
PR tree-optimization/109156
gcc/ChangeLog:
* config/aarch64/aarch64-simd-builtins.def (sabd, uabd):
Change the mode to 3.
* config/aarch64/aarch64-simd.md (aarch64_abd):
Rename to abd3.
*
From: oluade01
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.texi (sabd, uabd): Document them.
* internal-fn.def (ABD): Use new optab.
* optabs.def (sabd_optab, uabd_optab): New optabs,
* tree-vect-pattern
From: oluade01
This patch adds new RTL and tests for sabd and uabd
PR tree-optimization/109156
gcc/ChangeLog:
* config/aarch64/aarch64-simd-builtins.def (sabd, uabd):
Change the mode to 3.
* config/aarch64/aarch64-simd.md (aarch64_abd):
Rename to abd3.
*
> It would be good to add a:
>
> /* { dg-final { scan-assembler-not {\tabs\t} } } */
>
> to be the positive tests, to make it more obvious that all separate
> ABS instructions are elided.
Done.
Patch is in the next response.
From: oluade01
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.texi (sabd, uabd): Document them.
* internal-fn.def (ABD): Use new optab.
* optabs.def (sabd_optab, uabd_optab): New optabs,
* tree-vect-pattern
New patch to address issue brought up in a different
thread: mptjzwgplp2@arm.com
> > + /* Failed to find a widen operation so we check for a regular
> > MINUS_EXPR. */
> > + if (diff
> > + && gimple_assign_rhs_code (diff) == MINUS_EXPR
> > + && (TYPE_UNSIGNED (abs_type) || TYPE_O
From: oluade01
This patch adds new RTL and tests for sabd and uabd
PR tree-optimization/109156
gcc/ChangeLog:
* config/aarch64/aarch64-simd-builtins.def (sabd, uabd):
Change the mode to 3.
* config/aarch64/aarch64-simd.md (aarch64_abd):
Rename to abd3.
*
> It would be good to mark all of these functions with __attribute__((noipa)),
> since I think interprocedural optimisations might otherwise defeat the
> runtime test in abd_run_1.c (in the sense that we might end up folding
> things at compile time and not testing the vector versions of the functi
From: oluade01
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.texi (sabd, uabd): Document them.
* internal-fn.def (ABD): Use new optab.
* optabs.def (sabd_optab, uabd_optab): New optabs,
* tree-vect-pattern
From: oluade01
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.texi (sabd, uabd): Document them.
* internal-fn.def (ABD): Use new optab.
* optabs.def (sabd_optab, uabd_optab): New optabs,
* tree-vect-pattern
> > + if (TYPE_PRECISION (unprom_diff.type) != TYPE_PRECISION (abs_type)
> > + && TYPE_UNSIGNED (unprom_diff.type)
> > + && TYPE_UNSIGNED (abs_type))
>
> The last line is now redundant, since TYPE_UNSIGNED was checked above.
Done.
> > + // Failed to find a widen operation so we check
From: oluade01
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.texi (sabd, uabd): Document them.
* internal-fn.def (ABD): Use new optab.
* optabs.def (sabd_optab, uabd_optab): New optabs,
* tree-vect-pattern
> > + if (reject_unsigned && TYPE_UNSIGNED (abs_type))
> > +return false;
> > + if (!ANY_INTEGRAL_TYPE_P (abs_type) || TYPE_OVERFLOW_WRAPS (abs_type))
> > +return false;
>
> Could you explain the reject_unsigned behaviour? I'd have expected
> TYPE_OVERFLOW_WRAPS (abs_type) to reject the
From: oluade01
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.texi (sabd, uabd): Document them.
* internal-fn.def (ABD): Use new optab.
* optabs.def (sabd_optab, uabd_optab): New optabs,
* tree-vect-pattern
> Yeah. Like Tami says, this is what the instruction does.
>
> I think all three definitions are equivalent: the extend/operate/truncate
> one, the ?: one above, and the "max - min" one. Probably just personal
> preference as to which seems more natural.
Decided to switch to using the ?: one as
From: Oluwatamilore Adebayo
Sent: Wednesday, May 10, 2023 14:29
To: Richard Biener ; gcc-patches@gcc.gnu.org;
Richard Sandiford
Subject: Re: [PATCH] vect: Missed opportunity to use [SU]ABD
When using inputs of 0x7fff and 0x8000 the result yielded is -1.
When using inputs of -1 and 0x7fff the
When using inputs of 0x7fff and 0x8000 the result yielded is -1.
When using inputs of -1 and 0x7fff the results yielded is 0x8000.
Tami
From: Richard Biener
Sent: Wednesday, May 10, 2023 10:49 AM
To: Oluwatamilore Adebayo ;
gcc-patches@gcc.gnu.org ; richard.guent
>From afa416dab831795f7e1114da2fb9e94ea3b8c519 Mon Sep 17 00:00:00 2001
From: oluade01
Date: Fri, 14 Apr 2023 15:10:07 +0100
Subject: [PATCH 2/4] AArch64: New RTL for ABD
This patch adds new RTL and tests for sabd and uabd
PR tree-optimization/109156
gcc/ChangeLog:
* config/aarch64/aar
>From 0b5f469171c340ef61a48a31877d495bb77bd35f Mon Sep 17 00:00:00 2001
From: oluade01
Date: Fri, 14 Apr 2023 10:24:43 +0100
Subject: [PATCH 1/4] Missed opportunity to use [SU]ABD
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.tex
>From 0b5f469171c340ef61a48a31877d495bb77bd35f Mon Sep 17 00:00:00 2001
From: oluade01
Date: Fri, 14 Apr 2023 10:24:43 +0100
Subject: [PATCH 1/4] Missed opportunity to use [SU]ABD
This adds a recognition pattern for the non-widening
absolute difference (ABD).
gcc/ChangeLog:
* doc/md.tex
31 matches
Mail list logo
