[v1] tree-ssa-math-opts: separate FMA-deferring trigger from reassoc reorder

Message ID 20260707213441.1553738-1-philipp.tomsich@vrull.eu
State New
Headers
Series [v1] tree-ssa-math-opts: separate FMA-deferring trigger from reassoc reorder |

Checks

Context Check Description
linaro-tcwg-bot/tcwg_gcc_build--master-arm success Build passed
linaro-tcwg-bot/tcwg_simplebootstrap_build--master-arm-bootstrap pending Build did not complete; will be retriggered
linaro-tcwg-bot/tcwg_gcc_build--master-aarch64 success Build passed
linaro-tcwg-bot/tcwg_simplebootstrap_build--master-aarch64-bootstrap fail Build failed

Commit Message

Philipp Tomsich July 7, 2026, 9:34 p.m. UTC
  param_avoid_fma_max_bits gates two independent transforms: the
widening_mul FMA-deferring in tree-ssa-math-opts.cc, which leaves a
loop-carried multiply-add as fmul + fadd, and the reassoc
loop-carried-FMA reorder added in r14-5779-g746344dd538
(PR tree-optimization/110279), which parallelises 3+ operand chains.
Both fire when TYPE_SIZE (elt) <= avoid-fma-max-bits, so for a given
type they switch on at the same threshold and a target cannot keep one
while dropping the other.

This hurts the AArch64 AVOID_CROSS_LOOP_FMA cores (the Ampere-1
family): a 2-operand reduction such as an sgemm inner K-loop is left as
fmul + fadd, slower than fmadd on their dispatch-bound pipeline, yet
setting avoid-fma-max-bits to 0 to avoid it also disables the reorder.

Add a generic -fwidening-mul-defer-fma (default on) that gates only the
widening_mul deferring; avoid-fma-max-bits keeps gating the reorder
alone.  The AVOID_CROSS_LOOP_FMA callback clears the flag.  No other
target and no default behaviour changes.

gcc/ChangeLog:

	* common.opt (fwidening-mul-defer-fma): New option.
	* tree-ssa-math-opts.cc (math_opts_dom_walker::after_dom_children):
	Gate fma_deferring_state's enable predicate on
	flag_widening_mul_defer_fma in addition to param_avoid_fma_max_bits.
	* config/aarch64/aarch64-tuning-flags.def (AVOID_CROSS_LOOP_FMA):
	Update the comment for the -fwidening-mul-defer-fma effect.
	* config/aarch64/aarch64.cc (aarch64_override_options_internal):
	Inside the AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA block, clear
	flag_widening_mul_defer_fma.
	* doc/invoke.texi (-fwidening-mul-defer-fma): Document.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/widening-mul-defer-fma-1.c: New test.
	* gcc.target/aarch64/widening-mul-defer-fma-2.c: New test.
	* gcc.target/aarch64/widening-mul-defer-fma-3.c: New test.

Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
---

 gcc/common.opt                                |  4 ++++
 gcc/config/aarch64/aarch64-tuning-flags.def   |  4 ++++
 gcc/config/aarch64/aarch64.cc                 | 12 ++++++++---
 gcc/doc/invoke.texi                           | 17 ++++++++++++++-
 .../aarch64/widening-mul-defer-fma-1.c        | 19 +++++++++++++++++
 .../aarch64/widening-mul-defer-fma-2.c        | 21 +++++++++++++++++++
 .../aarch64/widening-mul-defer-fma-3.c        | 20 ++++++++++++++++++
 gcc/tree-ssa-math-opts.cc                     |  3 ++-
 8 files changed, 95 insertions(+), 5 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
  

Comments

Andrea Pinski July 7, 2026, 9:40 p.m. UTC | #1
On Tue, Jul 7, 2026 at 2:35 PM Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
>
> param_avoid_fma_max_bits gates two independent transforms: the
> widening_mul FMA-deferring in tree-ssa-math-opts.cc, which leaves a
> loop-carried multiply-add as fmul + fadd, and the reassoc
> loop-carried-FMA reorder added in r14-5779-g746344dd538
> (PR tree-optimization/110279), which parallelises 3+ operand chains.
> Both fire when TYPE_SIZE (elt) <= avoid-fma-max-bits, so for a given
> type they switch on at the same threshold and a target cannot keep one
> while dropping the other.
>
> This hurts the AArch64 AVOID_CROSS_LOOP_FMA cores (the Ampere-1
> family): a 2-operand reduction such as an sgemm inner K-loop is left as
> fmul + fadd, slower than fmadd on their dispatch-bound pipeline, yet
> setting avoid-fma-max-bits to 0 to avoid it also disables the reorder.
>
> Add a generic -fwidening-mul-defer-fma (default on) that gates only the
> widening_mul deferring; avoid-fma-max-bits keeps gating the reorder
> alone.  The AVOID_CROSS_LOOP_FMA callback clears the flag.  No other
> target and no default behaviour changes.

Note this is just a review on the documentation and nothing else.

>
> gcc/ChangeLog:
>
>         * common.opt (fwidening-mul-defer-fma): New option.
>         * tree-ssa-math-opts.cc (math_opts_dom_walker::after_dom_children):
>         Gate fma_deferring_state's enable predicate on
>         flag_widening_mul_defer_fma in addition to param_avoid_fma_max_bits.
>         * config/aarch64/aarch64-tuning-flags.def (AVOID_CROSS_LOOP_FMA):
>         Update the comment for the -fwidening-mul-defer-fma effect.
>         * config/aarch64/aarch64.cc (aarch64_override_options_internal):
>         Inside the AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA block, clear
>         flag_widening_mul_defer_fma.
>         * doc/invoke.texi (-fwidening-mul-defer-fma): Document.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.target/aarch64/widening-mul-defer-fma-1.c: New test.
>         * gcc.target/aarch64/widening-mul-defer-fma-2.c: New test.
>         * gcc.target/aarch64/widening-mul-defer-fma-3.c: New test.
>
> Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
> ---
>
>  gcc/common.opt                                |  4 ++++
>  gcc/config/aarch64/aarch64-tuning-flags.def   |  4 ++++
>  gcc/config/aarch64/aarch64.cc                 | 12 ++++++++---
>  gcc/doc/invoke.texi                           | 17 ++++++++++++++-
>  .../aarch64/widening-mul-defer-fma-1.c        | 19 +++++++++++++++++
>  .../aarch64/widening-mul-defer-fma-2.c        | 21 +++++++++++++++++++
>  .../aarch64/widening-mul-defer-fma-3.c        | 20 ++++++++++++++++++
>  gcc/tree-ssa-math-opts.cc                     |  3 ++-
>  8 files changed, 95 insertions(+), 5 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
>  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
>  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
>
> diff --git a/gcc/common.opt b/gcc/common.opt
> index 218dddf5dfe9..9be7dd6b2315 100644
> --- a/gcc/common.opt
> +++ b/gcc/common.opt
> @@ -3639,6 +3639,10 @@ fweb
>  Common Var(flag_web) Optimization EnabledBy(funroll-loops)
>  Construct webs and split unrelated uses of single variable.
>
> +fwidening-mul-defer-fma
> +Common Var(flag_widening_mul_defer_fma) Init(1) Optimization
> +Defer forming an FMA whose result feeds a loop-header PHI, leaving a separate multiply and add, when FMA avoidance is requested via --param=avoid-fma-max-bits.

Don't mention --param in user documentation directly.

> +
>  ftree-builtin-call-dce
>  Common Var(flag_tree_builtin_call_dce) Init(0) Optimization
>  Enable conditional dead code elimination for builtin calls.
> diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def
> index 058dadecccaa..5b087bfc9f03 100644
> --- a/gcc/config/aarch64/aarch64-tuning-flags.def
> +++ b/gcc/config/aarch64/aarch64-tuning-flags.def
> @@ -40,6 +40,10 @@ AARCH64_EXTRA_TUNING_OPTION ("cse_sve_vl_constants", CSE_SVE_VL_CONSTANTS)
>
>  AARCH64_EXTRA_TUNING_OPTION ("matched_vector_throughput", MATCHED_VECTOR_THROUGHPUT)
>
> +/* For cores whose pipeline disfavours loop-carried serial FMAs: set
> +   avoid-fma-max-bits to 512 to enable the reassoc reorder for 3+ operand
> +   chains, and clear -fwidening-mul-defer-fma to suppress the widening-mul
> +   pass's FMA deferring.  */
>  AARCH64_EXTRA_TUNING_OPTION ("avoid_cross_loop_fma", AVOID_CROSS_LOOP_FMA)
>
>  AARCH64_EXTRA_TUNING_OPTION ("fully_pipelined_fma", FULLY_PIPELINED_FMA)
> diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
> index 78f1eae8336c..fdb5bbbdfbce 100644
> --- a/gcc/config/aarch64/aarch64.cc
> +++ b/gcc/config/aarch64/aarch64.cc
> @@ -20087,11 +20087,17 @@ aarch64_override_options_internal (struct gcc_options *opts,
>        && opts->x_optimize >= aarch64_tune_params.prefetch->default_opt_level)
>      opts->x_flag_prefetch_loop_arrays = 1;
>
> -  /* Avoid loop-dependant FMA chains.  */
> +  /* Avoid loop-dependant FMA chains.  The reassoc-side reorder helper
> +     keeps using --param=avoid-fma-max-bits; the widening-mul-side
> +     deferring is gated separately by -fwidening-mul-defer-fma, so we
> +     suppress only the deferring on these cores while leaving the reassoc
> +     reorder active.  */
>    if (aarch64_tune_params.extra_tuning_flags
>        & AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA)
> -    SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits,
> -                        512);
> +    {
> +      SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 512);
> +      SET_OPTION_IF_UNSET (opts, opts_set, flag_widening_mul_defer_fma, 0);
> +    }
>
>    /* Consider fully pipelined FMA in reassociation.  */
>    if (aarch64_tune_params.extra_tuning_flags
> diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> index 208625cafc55..f39902f77e9b 100644
> --- a/gcc/doc/invoke.texi
> +++ b/gcc/doc/invoke.texi
> @@ -694,7 +694,8 @@ Objective-C and Objective-C++ Dialects}.
>  -funconstrained-commons  -funit-at-a-time  -funroll-all-loops
>  -funroll-loops  -funsafe-math-optimizations  -funswitch-loops
>  -fipa-ra  -fvariable-expansion-in-unroller  -fvect-cost-model  -fvpt
> --fweb  -fwhole-program  -fwpa  -fuse-linker-plugin  -fzero-call-used-regs
> +-fweb  -fwhole-program  -fwidening-mul-defer-fma  -fwpa
> +-fuse-linker-plugin  -fzero-call-used-regs
>  -O  -O0  -O1  -O2  -O3  -Os  -Ofast  -Og  -Oz  --optimize}
>
>  @item Program Instrumentation Options
> @@ -15917,6 +15918,20 @@ however, make debugging impossible, since variables no longer stay in a
>
>  Enabled by default with @option{-funroll-loops}.
>
> +@opindex fwidening-mul-defer-fma
> +@opindex fno-widening-mul-defer-fma
> +@item -fwidening-mul-defer-fma
> +When FMA avoidance is requested for loop-carried reductions (that is, when
> +@option{--param=avoid-fma-max-bits} is non-zero), the widening-multiply pass
> +refuses to contract a multiply-add whose result feeds a loop-header PHI,
> +leaving a separate multiply and add.  Use @option{-fno-widening-mul-defer-fma}
> +to suppress this deferring and contract such reductions into an FMA, while
> +still leaving @option{--param=avoid-fma-max-bits} in effect for the
> +@file{tree-ssa-reassoc.cc} loop-carried-FMA reordering of longer chains.
> +This is useful on targets whose pipeline disfavours the extra floating-point
> +operation more than the loop-carried FMA latency.  The option is enabled by
> +default.
Here either.


> +
>  @opindex fwhole-program
>  @opindex fno-whole-program
>  @item -fwhole-program
> diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> new file mode 100644
> index 000000000000..b542274eb763
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> @@ -0,0 +1,19 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize -mcpu=ampere1" } */
> +
> +/* The ampere1 family sets AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA, which
> +   clears -fwidening-mul-defer-fma so that a 2-operand loop-carried
> +   reduction is contracted to fmadd rather than deferred to fmul + fadd.
> +   (avoid-fma-max-bits stays 512 to keep the reassoc reorder enabled.)  */
> +
> +double
> +dot (const double *a, const double *b, int n)
> +{
> +  double s = 0.0;
> +  for (int i = 0; i < n; i++)
> +    s += a[i] * b[i];
> +  return s;
> +}
> +
> +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> new file mode 100644
> index 000000000000..764dd2457435
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> @@ -0,0 +1,21 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512" } */
> +
> +/* With FMA deferring active (avoid-fma-max-bits > 0) and the default
> +   -fwidening-mul-defer-fma, the widening_mul pass refuses to form an FMA
> +   whose result feeds the loop-header phi: the reduction stays as a
> +   separate fmul + fadd.  This is the behaviour the new flag decouples
> +   from the reassoc reorder (also gated by avoid-fma-max-bits).  */
> +
> +double
> +dot (const double *a, const double *b, int n)
> +{
> +  double s = 0.0;
> +  for (int i = 0; i < n; i++)
> +    s += a[i] * b[i];
> +  return s;
> +}
> +
> +/* { dg-final { scan-assembler {\tfmul\t} } } */
> +/* { dg-final { scan-assembler {\tfadd\t} } } */
> +/* { dg-final { scan-assembler-not {\tfmadd\t} } } */
> diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> new file mode 100644
> index 000000000000..5e041afc18fc
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> @@ -0,0 +1,20 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512 -fno-widening-mul-defer-fma" } */
> +
> +/* Companion to widening-mul-defer-fma-2.c: the same reduction with FMA
> +   avoidance still requested for the reassoc reorder (avoid-fma-max-bits=512)
> +   but -fno-widening-mul-defer-fma now suppresses the widening_mul deferring,
> +   so the loop-carried multiply-add is contracted to a single fmadd.  This
> +   proves the new flag decouples the deferring from avoid-fma-max-bits.  */
> +
> +double
> +dot (const double *a, const double *b, int n)
> +{
> +  double s = 0.0;
> +  for (int i = 0; i < n; i++)
> +    s += a[i] * b[i];
> +  return s;
> +}
> +
> +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
> index f0ede668d95e..a00146922713 100644
> --- a/gcc/tree-ssa-math-opts.cc
> +++ b/gcc/tree-ssa-math-opts.cc
> @@ -6607,7 +6607,8 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
>  {
>    gimple_stmt_iterator gsi;
>
> -  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0);
> +  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0
> +                                && flag_widening_mul_defer_fma);
>
>    for (gphi_iterator psi_next, psi = gsi_start_phis (bb); !gsi_end_p (psi);
>         psi = psi_next)
> --
> 2.34.1
>
> base-commit: 3b443e764144526748d2b51d017d745f1956377e
> branch: ptomsich/475-widening-mul-defer-fma
  
Philipp Tomsich July 7, 2026, 9:46 p.m. UTC | #2
On Tue, 7 Jul 2026 at 23:40, Andrea Pinski
<andrew.pinski@oss.qualcomm.com> wrote:
>
> On Tue, Jul 7, 2026 at 2:35 PM Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
> >
> > param_avoid_fma_max_bits gates two independent transforms: the
> > widening_mul FMA-deferring in tree-ssa-math-opts.cc, which leaves a
> > loop-carried multiply-add as fmul + fadd, and the reassoc
> > loop-carried-FMA reorder added in r14-5779-g746344dd538
> > (PR tree-optimization/110279), which parallelises 3+ operand chains.
> > Both fire when TYPE_SIZE (elt) <= avoid-fma-max-bits, so for a given
> > type they switch on at the same threshold and a target cannot keep one
> > while dropping the other.
> >
> > This hurts the AArch64 AVOID_CROSS_LOOP_FMA cores (the Ampere-1
> > family): a 2-operand reduction such as an sgemm inner K-loop is left as
> > fmul + fadd, slower than fmadd on their dispatch-bound pipeline, yet
> > setting avoid-fma-max-bits to 0 to avoid it also disables the reorder.
> >
> > Add a generic -fwidening-mul-defer-fma (default on) that gates only the
> > widening_mul deferring; avoid-fma-max-bits keeps gating the reorder
> > alone.  The AVOID_CROSS_LOOP_FMA callback clears the flag.  No other
> > target and no default behaviour changes.
>
> Note this is just a review on the documentation and nothing else.
>
> >
> > gcc/ChangeLog:
> >
> >         * common.opt (fwidening-mul-defer-fma): New option.
> >         * tree-ssa-math-opts.cc (math_opts_dom_walker::after_dom_children):
> >         Gate fma_deferring_state's enable predicate on
> >         flag_widening_mul_defer_fma in addition to param_avoid_fma_max_bits.
> >         * config/aarch64/aarch64-tuning-flags.def (AVOID_CROSS_LOOP_FMA):
> >         Update the comment for the -fwidening-mul-defer-fma effect.
> >         * config/aarch64/aarch64.cc (aarch64_override_options_internal):
> >         Inside the AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA block, clear
> >         flag_widening_mul_defer_fma.
> >         * doc/invoke.texi (-fwidening-mul-defer-fma): Document.
> >
> > gcc/testsuite/ChangeLog:
> >
> >         * gcc.target/aarch64/widening-mul-defer-fma-1.c: New test.
> >         * gcc.target/aarch64/widening-mul-defer-fma-2.c: New test.
> >         * gcc.target/aarch64/widening-mul-defer-fma-3.c: New test.
> >
> > Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
> > ---
> >
> >  gcc/common.opt                                |  4 ++++
> >  gcc/config/aarch64/aarch64-tuning-flags.def   |  4 ++++
> >  gcc/config/aarch64/aarch64.cc                 | 12 ++++++++---
> >  gcc/doc/invoke.texi                           | 17 ++++++++++++++-
> >  .../aarch64/widening-mul-defer-fma-1.c        | 19 +++++++++++++++++
> >  .../aarch64/widening-mul-defer-fma-2.c        | 21 +++++++++++++++++++
> >  .../aarch64/widening-mul-defer-fma-3.c        | 20 ++++++++++++++++++
> >  gcc/tree-ssa-math-opts.cc                     |  3 ++-
> >  8 files changed, 95 insertions(+), 5 deletions(-)
> >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> >
> > diff --git a/gcc/common.opt b/gcc/common.opt
> > index 218dddf5dfe9..9be7dd6b2315 100644
> > --- a/gcc/common.opt
> > +++ b/gcc/common.opt
> > @@ -3639,6 +3639,10 @@ fweb
> >  Common Var(flag_web) Optimization EnabledBy(funroll-loops)
> >  Construct webs and split unrelated uses of single variable.
> >
> > +fwidening-mul-defer-fma
> > +Common Var(flag_widening_mul_defer_fma) Init(1) Optimization
> > +Defer forming an FMA whose result feeds a loop-header PHI, leaving a separate multiply and add, when FMA avoidance is requested via --param=avoid-fma-max-bits.
>
> Don't mention --param in user documentation directly.

That brings up a question we discussed in internal reviews: should
this even be a -fwidening-mul-defer-fma flag then — or just another
--param?
After all, this is the companion for a --param, so the alternate
opinion was to have a second --param that would be set to either 0 or
1.  However, such a param (that will always be set either to 0 or 1)
seems odd.

The third option discussed was a target-hook, but that doesn't allow a
commandline-override.

Any thoughts?

>
> > +
> >  ftree-builtin-call-dce
> >  Common Var(flag_tree_builtin_call_dce) Init(0) Optimization
> >  Enable conditional dead code elimination for builtin calls.
> > diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def
> > index 058dadecccaa..5b087bfc9f03 100644
> > --- a/gcc/config/aarch64/aarch64-tuning-flags.def
> > +++ b/gcc/config/aarch64/aarch64-tuning-flags.def
> > @@ -40,6 +40,10 @@ AARCH64_EXTRA_TUNING_OPTION ("cse_sve_vl_constants", CSE_SVE_VL_CONSTANTS)
> >
> >  AARCH64_EXTRA_TUNING_OPTION ("matched_vector_throughput", MATCHED_VECTOR_THROUGHPUT)
> >
> > +/* For cores whose pipeline disfavours loop-carried serial FMAs: set
> > +   avoid-fma-max-bits to 512 to enable the reassoc reorder for 3+ operand
> > +   chains, and clear -fwidening-mul-defer-fma to suppress the widening-mul
> > +   pass's FMA deferring.  */
> >  AARCH64_EXTRA_TUNING_OPTION ("avoid_cross_loop_fma", AVOID_CROSS_LOOP_FMA)
> >
> >  AARCH64_EXTRA_TUNING_OPTION ("fully_pipelined_fma", FULLY_PIPELINED_FMA)
> > diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
> > index 78f1eae8336c..fdb5bbbdfbce 100644
> > --- a/gcc/config/aarch64/aarch64.cc
> > +++ b/gcc/config/aarch64/aarch64.cc
> > @@ -20087,11 +20087,17 @@ aarch64_override_options_internal (struct gcc_options *opts,
> >        && opts->x_optimize >= aarch64_tune_params.prefetch->default_opt_level)
> >      opts->x_flag_prefetch_loop_arrays = 1;
> >
> > -  /* Avoid loop-dependant FMA chains.  */
> > +  /* Avoid loop-dependant FMA chains.  The reassoc-side reorder helper
> > +     keeps using --param=avoid-fma-max-bits; the widening-mul-side
> > +     deferring is gated separately by -fwidening-mul-defer-fma, so we
> > +     suppress only the deferring on these cores while leaving the reassoc
> > +     reorder active.  */
> >    if (aarch64_tune_params.extra_tuning_flags
> >        & AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA)
> > -    SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits,
> > -                        512);
> > +    {
> > +      SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 512);
> > +      SET_OPTION_IF_UNSET (opts, opts_set, flag_widening_mul_defer_fma, 0);
> > +    }
> >
> >    /* Consider fully pipelined FMA in reassociation.  */
> >    if (aarch64_tune_params.extra_tuning_flags
> > diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> > index 208625cafc55..f39902f77e9b 100644
> > --- a/gcc/doc/invoke.texi
> > +++ b/gcc/doc/invoke.texi
> > @@ -694,7 +694,8 @@ Objective-C and Objective-C++ Dialects}.
> >  -funconstrained-commons  -funit-at-a-time  -funroll-all-loops
> >  -funroll-loops  -funsafe-math-optimizations  -funswitch-loops
> >  -fipa-ra  -fvariable-expansion-in-unroller  -fvect-cost-model  -fvpt
> > --fweb  -fwhole-program  -fwpa  -fuse-linker-plugin  -fzero-call-used-regs
> > +-fweb  -fwhole-program  -fwidening-mul-defer-fma  -fwpa
> > +-fuse-linker-plugin  -fzero-call-used-regs
> >  -O  -O0  -O1  -O2  -O3  -Os  -Ofast  -Og  -Oz  --optimize}
> >
> >  @item Program Instrumentation Options
> > @@ -15917,6 +15918,20 @@ however, make debugging impossible, since variables no longer stay in a
> >
> >  Enabled by default with @option{-funroll-loops}.
> >
> > +@opindex fwidening-mul-defer-fma
> > +@opindex fno-widening-mul-defer-fma
> > +@item -fwidening-mul-defer-fma
> > +When FMA avoidance is requested for loop-carried reductions (that is, when
> > +@option{--param=avoid-fma-max-bits} is non-zero), the widening-multiply pass
> > +refuses to contract a multiply-add whose result feeds a loop-header PHI,
> > +leaving a separate multiply and add.  Use @option{-fno-widening-mul-defer-fma}
> > +to suppress this deferring and contract such reductions into an FMA, while
> > +still leaving @option{--param=avoid-fma-max-bits} in effect for the
> > +@file{tree-ssa-reassoc.cc} loop-carried-FMA reordering of longer chains.
> > +This is useful on targets whose pipeline disfavours the extra floating-point
> > +operation more than the loop-carried FMA latency.  The option is enabled by
> > +default.
> Here either.
>
>
> > +
> >  @opindex fwhole-program
> >  @opindex fno-whole-program
> >  @item -fwhole-program
> > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > new file mode 100644
> > index 000000000000..b542274eb763
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > @@ -0,0 +1,19 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize -mcpu=ampere1" } */
> > +
> > +/* The ampere1 family sets AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA, which
> > +   clears -fwidening-mul-defer-fma so that a 2-operand loop-carried
> > +   reduction is contracted to fmadd rather than deferred to fmul + fadd.
> > +   (avoid-fma-max-bits stays 512 to keep the reassoc reorder enabled.)  */
> > +
> > +double
> > +dot (const double *a, const double *b, int n)
> > +{
> > +  double s = 0.0;
> > +  for (int i = 0; i < n; i++)
> > +    s += a[i] * b[i];
> > +  return s;
> > +}
> > +
> > +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> > +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > new file mode 100644
> > index 000000000000..764dd2457435
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > @@ -0,0 +1,21 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512" } */
> > +
> > +/* With FMA deferring active (avoid-fma-max-bits > 0) and the default
> > +   -fwidening-mul-defer-fma, the widening_mul pass refuses to form an FMA
> > +   whose result feeds the loop-header phi: the reduction stays as a
> > +   separate fmul + fadd.  This is the behaviour the new flag decouples
> > +   from the reassoc reorder (also gated by avoid-fma-max-bits).  */
> > +
> > +double
> > +dot (const double *a, const double *b, int n)
> > +{
> > +  double s = 0.0;
> > +  for (int i = 0; i < n; i++)
> > +    s += a[i] * b[i];
> > +  return s;
> > +}
> > +
> > +/* { dg-final { scan-assembler {\tfmul\t} } } */
> > +/* { dg-final { scan-assembler {\tfadd\t} } } */
> > +/* { dg-final { scan-assembler-not {\tfmadd\t} } } */
> > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > new file mode 100644
> > index 000000000000..5e041afc18fc
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > @@ -0,0 +1,20 @@
> > +/* { dg-do compile } */
> > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512 -fno-widening-mul-defer-fma" } */
> > +
> > +/* Companion to widening-mul-defer-fma-2.c: the same reduction with FMA
> > +   avoidance still requested for the reassoc reorder (avoid-fma-max-bits=512)
> > +   but -fno-widening-mul-defer-fma now suppresses the widening_mul deferring,
> > +   so the loop-carried multiply-add is contracted to a single fmadd.  This
> > +   proves the new flag decouples the deferring from avoid-fma-max-bits.  */
> > +
> > +double
> > +dot (const double *a, const double *b, int n)
> > +{
> > +  double s = 0.0;
> > +  for (int i = 0; i < n; i++)
> > +    s += a[i] * b[i];
> > +  return s;
> > +}
> > +
> > +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> > +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> > diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
> > index f0ede668d95e..a00146922713 100644
> > --- a/gcc/tree-ssa-math-opts.cc
> > +++ b/gcc/tree-ssa-math-opts.cc
> > @@ -6607,7 +6607,8 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
> >  {
> >    gimple_stmt_iterator gsi;
> >
> > -  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0);
> > +  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0
> > +                                && flag_widening_mul_defer_fma);
> >
> >    for (gphi_iterator psi_next, psi = gsi_start_phis (bb); !gsi_end_p (psi);
> >         psi = psi_next)
> > --
> > 2.34.1
> >
> > base-commit: 3b443e764144526748d2b51d017d745f1956377e
> > branch: ptomsich/475-widening-mul-defer-fma
  
Andrea Pinski July 7, 2026, 9:51 p.m. UTC | #3
On Tue, Jul 7, 2026 at 2:46 PM Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
>
> On Tue, 7 Jul 2026 at 23:40, Andrea Pinski
> <andrew.pinski@oss.qualcomm.com> wrote:
> >
> > On Tue, Jul 7, 2026 at 2:35 PM Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
> > >
> > > param_avoid_fma_max_bits gates two independent transforms: the
> > > widening_mul FMA-deferring in tree-ssa-math-opts.cc, which leaves a
> > > loop-carried multiply-add as fmul + fadd, and the reassoc
> > > loop-carried-FMA reorder added in r14-5779-g746344dd538
> > > (PR tree-optimization/110279), which parallelises 3+ operand chains.
> > > Both fire when TYPE_SIZE (elt) <= avoid-fma-max-bits, so for a given
> > > type they switch on at the same threshold and a target cannot keep one
> > > while dropping the other.
> > >
> > > This hurts the AArch64 AVOID_CROSS_LOOP_FMA cores (the Ampere-1
> > > family): a 2-operand reduction such as an sgemm inner K-loop is left as
> > > fmul + fadd, slower than fmadd on their dispatch-bound pipeline, yet
> > > setting avoid-fma-max-bits to 0 to avoid it also disables the reorder.
> > >
> > > Add a generic -fwidening-mul-defer-fma (default on) that gates only the
> > > widening_mul deferring; avoid-fma-max-bits keeps gating the reorder
> > > alone.  The AVOID_CROSS_LOOP_FMA callback clears the flag.  No other
> > > target and no default behaviour changes.
> >
> > Note this is just a review on the documentation and nothing else.
> >
> > >
> > > gcc/ChangeLog:
> > >
> > >         * common.opt (fwidening-mul-defer-fma): New option.
> > >         * tree-ssa-math-opts.cc (math_opts_dom_walker::after_dom_children):
> > >         Gate fma_deferring_state's enable predicate on
> > >         flag_widening_mul_defer_fma in addition to param_avoid_fma_max_bits.
> > >         * config/aarch64/aarch64-tuning-flags.def (AVOID_CROSS_LOOP_FMA):
> > >         Update the comment for the -fwidening-mul-defer-fma effect.
> > >         * config/aarch64/aarch64.cc (aarch64_override_options_internal):
> > >         Inside the AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA block, clear
> > >         flag_widening_mul_defer_fma.
> > >         * doc/invoke.texi (-fwidening-mul-defer-fma): Document.
> > >
> > > gcc/testsuite/ChangeLog:
> > >
> > >         * gcc.target/aarch64/widening-mul-defer-fma-1.c: New test.
> > >         * gcc.target/aarch64/widening-mul-defer-fma-2.c: New test.
> > >         * gcc.target/aarch64/widening-mul-defer-fma-3.c: New test.
> > >
> > > Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
> > > ---
> > >
> > >  gcc/common.opt                                |  4 ++++
> > >  gcc/config/aarch64/aarch64-tuning-flags.def   |  4 ++++
> > >  gcc/config/aarch64/aarch64.cc                 | 12 ++++++++---
> > >  gcc/doc/invoke.texi                           | 17 ++++++++++++++-
> > >  .../aarch64/widening-mul-defer-fma-1.c        | 19 +++++++++++++++++
> > >  .../aarch64/widening-mul-defer-fma-2.c        | 21 +++++++++++++++++++
> > >  .../aarch64/widening-mul-defer-fma-3.c        | 20 ++++++++++++++++++
> > >  gcc/tree-ssa-math-opts.cc                     |  3 ++-
> > >  8 files changed, 95 insertions(+), 5 deletions(-)
> > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > >
> > > diff --git a/gcc/common.opt b/gcc/common.opt
> > > index 218dddf5dfe9..9be7dd6b2315 100644
> > > --- a/gcc/common.opt
> > > +++ b/gcc/common.opt
> > > @@ -3639,6 +3639,10 @@ fweb
> > >  Common Var(flag_web) Optimization EnabledBy(funroll-loops)
> > >  Construct webs and split unrelated uses of single variable.
> > >
> > > +fwidening-mul-defer-fma
> > > +Common Var(flag_widening_mul_defer_fma) Init(1) Optimization
> > > +Defer forming an FMA whose result feeds a loop-header PHI, leaving a separate multiply and add, when FMA avoidance is requested via --param=avoid-fma-max-bits.
> >
> > Don't mention --param in user documentation directly.
>
> That brings up a question we discussed in internal reviews: should
> this even be a -fwidening-mul-defer-fma flag then — or just another
> --param?
> After all, this is the companion for a --param, so the alternate
> opinion was to have a second --param that would be set to either 0 or
> 1.  However, such a param (that will always be set either to 0 or 1)
> seems odd.


There are plenty of params that are already only support 0 or 1.
Just after the line 34 of params.opt 4 in a row:
-param=asan-globals=
Common Joined UInteger Var(param_asan_globals) Init(1) IntegerRange(0, 1) Param
Enable asan globals protection.

And fully-pipelined-fma is one too:
-param=fully-pipelined-fma=
Common Joined UInteger Var(param_fully_pipelined_fma) Init(0)
IntegerRange(0, 1) Param Optimization
Whether the target fully pipelines FMA instructions.  If non-zero,
reassociation considers the benefit of parallelizing FMA's multiplication
part and addition part, assuming FMUL and FMA use the same units that can
also do FADD.



>
> The third option discussed was a target-hook, but that doesn't allow a
> commandline-override.
>
> Any thoughts?
>
> >
> > > +
> > >  ftree-builtin-call-dce
> > >  Common Var(flag_tree_builtin_call_dce) Init(0) Optimization
> > >  Enable conditional dead code elimination for builtin calls.
> > > diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def
> > > index 058dadecccaa..5b087bfc9f03 100644
> > > --- a/gcc/config/aarch64/aarch64-tuning-flags.def
> > > +++ b/gcc/config/aarch64/aarch64-tuning-flags.def
> > > @@ -40,6 +40,10 @@ AARCH64_EXTRA_TUNING_OPTION ("cse_sve_vl_constants", CSE_SVE_VL_CONSTANTS)
> > >
> > >  AARCH64_EXTRA_TUNING_OPTION ("matched_vector_throughput", MATCHED_VECTOR_THROUGHPUT)
> > >
> > > +/* For cores whose pipeline disfavours loop-carried serial FMAs: set
> > > +   avoid-fma-max-bits to 512 to enable the reassoc reorder for 3+ operand
> > > +   chains, and clear -fwidening-mul-defer-fma to suppress the widening-mul
> > > +   pass's FMA deferring.  */
> > >  AARCH64_EXTRA_TUNING_OPTION ("avoid_cross_loop_fma", AVOID_CROSS_LOOP_FMA)
> > >
> > >  AARCH64_EXTRA_TUNING_OPTION ("fully_pipelined_fma", FULLY_PIPELINED_FMA)
> > > diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
> > > index 78f1eae8336c..fdb5bbbdfbce 100644
> > > --- a/gcc/config/aarch64/aarch64.cc
> > > +++ b/gcc/config/aarch64/aarch64.cc
> > > @@ -20087,11 +20087,17 @@ aarch64_override_options_internal (struct gcc_options *opts,
> > >        && opts->x_optimize >= aarch64_tune_params.prefetch->default_opt_level)
> > >      opts->x_flag_prefetch_loop_arrays = 1;
> > >
> > > -  /* Avoid loop-dependant FMA chains.  */
> > > +  /* Avoid loop-dependant FMA chains.  The reassoc-side reorder helper
> > > +     keeps using --param=avoid-fma-max-bits; the widening-mul-side
> > > +     deferring is gated separately by -fwidening-mul-defer-fma, so we
> > > +     suppress only the deferring on these cores while leaving the reassoc
> > > +     reorder active.  */
> > >    if (aarch64_tune_params.extra_tuning_flags
> > >        & AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA)
> > > -    SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits,
> > > -                        512);
> > > +    {
> > > +      SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 512);
> > > +      SET_OPTION_IF_UNSET (opts, opts_set, flag_widening_mul_defer_fma, 0);
> > > +    }
> > >
> > >    /* Consider fully pipelined FMA in reassociation.  */
> > >    if (aarch64_tune_params.extra_tuning_flags
> > > diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> > > index 208625cafc55..f39902f77e9b 100644
> > > --- a/gcc/doc/invoke.texi
> > > +++ b/gcc/doc/invoke.texi
> > > @@ -694,7 +694,8 @@ Objective-C and Objective-C++ Dialects}.
> > >  -funconstrained-commons  -funit-at-a-time  -funroll-all-loops
> > >  -funroll-loops  -funsafe-math-optimizations  -funswitch-loops
> > >  -fipa-ra  -fvariable-expansion-in-unroller  -fvect-cost-model  -fvpt
> > > --fweb  -fwhole-program  -fwpa  -fuse-linker-plugin  -fzero-call-used-regs
> > > +-fweb  -fwhole-program  -fwidening-mul-defer-fma  -fwpa
> > > +-fuse-linker-plugin  -fzero-call-used-regs
> > >  -O  -O0  -O1  -O2  -O3  -Os  -Ofast  -Og  -Oz  --optimize}
> > >
> > >  @item Program Instrumentation Options
> > > @@ -15917,6 +15918,20 @@ however, make debugging impossible, since variables no longer stay in a
> > >
> > >  Enabled by default with @option{-funroll-loops}.
> > >
> > > +@opindex fwidening-mul-defer-fma
> > > +@opindex fno-widening-mul-defer-fma
> > > +@item -fwidening-mul-defer-fma
> > > +When FMA avoidance is requested for loop-carried reductions (that is, when
> > > +@option{--param=avoid-fma-max-bits} is non-zero), the widening-multiply pass
> > > +refuses to contract a multiply-add whose result feeds a loop-header PHI,
> > > +leaving a separate multiply and add.  Use @option{-fno-widening-mul-defer-fma}
> > > +to suppress this deferring and contract such reductions into an FMA, while
> > > +still leaving @option{--param=avoid-fma-max-bits} in effect for the
> > > +@file{tree-ssa-reassoc.cc} loop-carried-FMA reordering of longer chains.
> > > +This is useful on targets whose pipeline disfavours the extra floating-point
> > > +operation more than the loop-carried FMA latency.  The option is enabled by
> > > +default.
> > Here either.
> >
> >
> > > +
> > >  @opindex fwhole-program
> > >  @opindex fno-whole-program
> > >  @item -fwhole-program
> > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > > new file mode 100644
> > > index 000000000000..b542274eb763
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > > @@ -0,0 +1,19 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize -mcpu=ampere1" } */
> > > +
> > > +/* The ampere1 family sets AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA, which
> > > +   clears -fwidening-mul-defer-fma so that a 2-operand loop-carried
> > > +   reduction is contracted to fmadd rather than deferred to fmul + fadd.
> > > +   (avoid-fma-max-bits stays 512 to keep the reassoc reorder enabled.)  */
> > > +
> > > +double
> > > +dot (const double *a, const double *b, int n)
> > > +{
> > > +  double s = 0.0;
> > > +  for (int i = 0; i < n; i++)
> > > +    s += a[i] * b[i];
> > > +  return s;
> > > +}
> > > +
> > > +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> > > +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > > new file mode 100644
> > > index 000000000000..764dd2457435
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > > @@ -0,0 +1,21 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512" } */
> > > +
> > > +/* With FMA deferring active (avoid-fma-max-bits > 0) and the default
> > > +   -fwidening-mul-defer-fma, the widening_mul pass refuses to form an FMA
> > > +   whose result feeds the loop-header phi: the reduction stays as a
> > > +   separate fmul + fadd.  This is the behaviour the new flag decouples
> > > +   from the reassoc reorder (also gated by avoid-fma-max-bits).  */
> > > +
> > > +double
> > > +dot (const double *a, const double *b, int n)
> > > +{
> > > +  double s = 0.0;
> > > +  for (int i = 0; i < n; i++)
> > > +    s += a[i] * b[i];
> > > +  return s;
> > > +}
> > > +
> > > +/* { dg-final { scan-assembler {\tfmul\t} } } */
> > > +/* { dg-final { scan-assembler {\tfadd\t} } } */
> > > +/* { dg-final { scan-assembler-not {\tfmadd\t} } } */
> > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > > new file mode 100644
> > > index 000000000000..5e041afc18fc
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > > @@ -0,0 +1,20 @@
> > > +/* { dg-do compile } */
> > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512 -fno-widening-mul-defer-fma" } */
> > > +
> > > +/* Companion to widening-mul-defer-fma-2.c: the same reduction with FMA
> > > +   avoidance still requested for the reassoc reorder (avoid-fma-max-bits=512)
> > > +   but -fno-widening-mul-defer-fma now suppresses the widening_mul deferring,
> > > +   so the loop-carried multiply-add is contracted to a single fmadd.  This
> > > +   proves the new flag decouples the deferring from avoid-fma-max-bits.  */
> > > +
> > > +double
> > > +dot (const double *a, const double *b, int n)
> > > +{
> > > +  double s = 0.0;
> > > +  for (int i = 0; i < n; i++)
> > > +    s += a[i] * b[i];
> > > +  return s;
> > > +}
> > > +
> > > +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> > > +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> > > diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
> > > index f0ede668d95e..a00146922713 100644
> > > --- a/gcc/tree-ssa-math-opts.cc
> > > +++ b/gcc/tree-ssa-math-opts.cc
> > > @@ -6607,7 +6607,8 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
> > >  {
> > >    gimple_stmt_iterator gsi;
> > >
> > > -  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0);
> > > +  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0
> > > +                                && flag_widening_mul_defer_fma);
> > >
> > >    for (gphi_iterator psi_next, psi = gsi_start_phis (bb); !gsi_end_p (psi);
> > >         psi = psi_next)
> > > --
> > > 2.34.1
> > >
> > > base-commit: 3b443e764144526748d2b51d017d745f1956377e
> > > branch: ptomsich/475-widening-mul-defer-fma
  
Philipp Tomsich July 7, 2026, 9:53 p.m. UTC | #4
On Tue, 7 Jul 2026 at 23:51, Andrea Pinski
<andrew.pinski@oss.qualcomm.com> wrote:
>
> On Tue, Jul 7, 2026 at 2:46 PM Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
> >
> > On Tue, 7 Jul 2026 at 23:40, Andrea Pinski
> > <andrew.pinski@oss.qualcomm.com> wrote:
> > >
> > > On Tue, Jul 7, 2026 at 2:35 PM Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
> > > >
> > > > param_avoid_fma_max_bits gates two independent transforms: the
> > > > widening_mul FMA-deferring in tree-ssa-math-opts.cc, which leaves a
> > > > loop-carried multiply-add as fmul + fadd, and the reassoc
> > > > loop-carried-FMA reorder added in r14-5779-g746344dd538
> > > > (PR tree-optimization/110279), which parallelises 3+ operand chains.
> > > > Both fire when TYPE_SIZE (elt) <= avoid-fma-max-bits, so for a given
> > > > type they switch on at the same threshold and a target cannot keep one
> > > > while dropping the other.
> > > >
> > > > This hurts the AArch64 AVOID_CROSS_LOOP_FMA cores (the Ampere-1
> > > > family): a 2-operand reduction such as an sgemm inner K-loop is left as
> > > > fmul + fadd, slower than fmadd on their dispatch-bound pipeline, yet
> > > > setting avoid-fma-max-bits to 0 to avoid it also disables the reorder.
> > > >
> > > > Add a generic -fwidening-mul-defer-fma (default on) that gates only the
> > > > widening_mul deferring; avoid-fma-max-bits keeps gating the reorder
> > > > alone.  The AVOID_CROSS_LOOP_FMA callback clears the flag.  No other
> > > > target and no default behaviour changes.
> > >
> > > Note this is just a review on the documentation and nothing else.
> > >
> > > >
> > > > gcc/ChangeLog:
> > > >
> > > >         * common.opt (fwidening-mul-defer-fma): New option.
> > > >         * tree-ssa-math-opts.cc (math_opts_dom_walker::after_dom_children):
> > > >         Gate fma_deferring_state's enable predicate on
> > > >         flag_widening_mul_defer_fma in addition to param_avoid_fma_max_bits.
> > > >         * config/aarch64/aarch64-tuning-flags.def (AVOID_CROSS_LOOP_FMA):
> > > >         Update the comment for the -fwidening-mul-defer-fma effect.
> > > >         * config/aarch64/aarch64.cc (aarch64_override_options_internal):
> > > >         Inside the AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA block, clear
> > > >         flag_widening_mul_defer_fma.
> > > >         * doc/invoke.texi (-fwidening-mul-defer-fma): Document.
> > > >
> > > > gcc/testsuite/ChangeLog:
> > > >
> > > >         * gcc.target/aarch64/widening-mul-defer-fma-1.c: New test.
> > > >         * gcc.target/aarch64/widening-mul-defer-fma-2.c: New test.
> > > >         * gcc.target/aarch64/widening-mul-defer-fma-3.c: New test.
> > > >
> > > > Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
> > > > ---
> > > >
> > > >  gcc/common.opt                                |  4 ++++
> > > >  gcc/config/aarch64/aarch64-tuning-flags.def   |  4 ++++
> > > >  gcc/config/aarch64/aarch64.cc                 | 12 ++++++++---
> > > >  gcc/doc/invoke.texi                           | 17 ++++++++++++++-
> > > >  .../aarch64/widening-mul-defer-fma-1.c        | 19 +++++++++++++++++
> > > >  .../aarch64/widening-mul-defer-fma-2.c        | 21 +++++++++++++++++++
> > > >  .../aarch64/widening-mul-defer-fma-3.c        | 20 ++++++++++++++++++
> > > >  gcc/tree-ssa-math-opts.cc                     |  3 ++-
> > > >  8 files changed, 95 insertions(+), 5 deletions(-)
> > > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > > >
> > > > diff --git a/gcc/common.opt b/gcc/common.opt
> > > > index 218dddf5dfe9..9be7dd6b2315 100644
> > > > --- a/gcc/common.opt
> > > > +++ b/gcc/common.opt
> > > > @@ -3639,6 +3639,10 @@ fweb
> > > >  Common Var(flag_web) Optimization EnabledBy(funroll-loops)
> > > >  Construct webs and split unrelated uses of single variable.
> > > >
> > > > +fwidening-mul-defer-fma
> > > > +Common Var(flag_widening_mul_defer_fma) Init(1) Optimization
> > > > +Defer forming an FMA whose result feeds a loop-header PHI, leaving a separate multiply and add, when FMA avoidance is requested via --param=avoid-fma-max-bits.
> > >
> > > Don't mention --param in user documentation directly.
> >
> > That brings up a question we discussed in internal reviews: should
> > this even be a -fwidening-mul-defer-fma flag then — or just another
> > --param?
> > After all, this is the companion for a --param, so the alternate
> > opinion was to have a second --param that would be set to either 0 or
> > 1.  However, such a param (that will always be set either to 0 or 1)
> > seems odd.
>
>
> There are plenty of params that are already only support 0 or 1.
> Just after the line 34 of params.opt 4 in a row:
> -param=asan-globals=
> Common Joined UInteger Var(param_asan_globals) Init(1) IntegerRange(0, 1) Param
> Enable asan globals protection.
>
> And fully-pipelined-fma is one too:
> -param=fully-pipelined-fma=
> Common Joined UInteger Var(param_fully_pipelined_fma) Init(0)
> IntegerRange(0, 1) Param Optimization
> Whether the target fully pipelines FMA instructions.  If non-zero,
> reassociation considers the benefit of parallelizing FMA's multiplication
> part and addition part, assuming FMUL and FMA use the same units that can
> also do FADD.

I'll take this as "follow the established precedent, even if you don't
find it pretty".
ACK.

>
> >
> > The third option discussed was a target-hook, but that doesn't allow a
> > commandline-override.
> >
> > Any thoughts?
> >
> > >
> > > > +
> > > >  ftree-builtin-call-dce
> > > >  Common Var(flag_tree_builtin_call_dce) Init(0) Optimization
> > > >  Enable conditional dead code elimination for builtin calls.
> > > > diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def
> > > > index 058dadecccaa..5b087bfc9f03 100644
> > > > --- a/gcc/config/aarch64/aarch64-tuning-flags.def
> > > > +++ b/gcc/config/aarch64/aarch64-tuning-flags.def
> > > > @@ -40,6 +40,10 @@ AARCH64_EXTRA_TUNING_OPTION ("cse_sve_vl_constants", CSE_SVE_VL_CONSTANTS)
> > > >
> > > >  AARCH64_EXTRA_TUNING_OPTION ("matched_vector_throughput", MATCHED_VECTOR_THROUGHPUT)
> > > >
> > > > +/* For cores whose pipeline disfavours loop-carried serial FMAs: set
> > > > +   avoid-fma-max-bits to 512 to enable the reassoc reorder for 3+ operand
> > > > +   chains, and clear -fwidening-mul-defer-fma to suppress the widening-mul
> > > > +   pass's FMA deferring.  */
> > > >  AARCH64_EXTRA_TUNING_OPTION ("avoid_cross_loop_fma", AVOID_CROSS_LOOP_FMA)
> > > >
> > > >  AARCH64_EXTRA_TUNING_OPTION ("fully_pipelined_fma", FULLY_PIPELINED_FMA)
> > > > diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
> > > > index 78f1eae8336c..fdb5bbbdfbce 100644
> > > > --- a/gcc/config/aarch64/aarch64.cc
> > > > +++ b/gcc/config/aarch64/aarch64.cc
> > > > @@ -20087,11 +20087,17 @@ aarch64_override_options_internal (struct gcc_options *opts,
> > > >        && opts->x_optimize >= aarch64_tune_params.prefetch->default_opt_level)
> > > >      opts->x_flag_prefetch_loop_arrays = 1;
> > > >
> > > > -  /* Avoid loop-dependant FMA chains.  */
> > > > +  /* Avoid loop-dependant FMA chains.  The reassoc-side reorder helper
> > > > +     keeps using --param=avoid-fma-max-bits; the widening-mul-side
> > > > +     deferring is gated separately by -fwidening-mul-defer-fma, so we
> > > > +     suppress only the deferring on these cores while leaving the reassoc
> > > > +     reorder active.  */
> > > >    if (aarch64_tune_params.extra_tuning_flags
> > > >        & AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA)
> > > > -    SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits,
> > > > -                        512);
> > > > +    {
> > > > +      SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 512);
> > > > +      SET_OPTION_IF_UNSET (opts, opts_set, flag_widening_mul_defer_fma, 0);
> > > > +    }
> > > >
> > > >    /* Consider fully pipelined FMA in reassociation.  */
> > > >    if (aarch64_tune_params.extra_tuning_flags
> > > > diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> > > > index 208625cafc55..f39902f77e9b 100644
> > > > --- a/gcc/doc/invoke.texi
> > > > +++ b/gcc/doc/invoke.texi
> > > > @@ -694,7 +694,8 @@ Objective-C and Objective-C++ Dialects}.
> > > >  -funconstrained-commons  -funit-at-a-time  -funroll-all-loops
> > > >  -funroll-loops  -funsafe-math-optimizations  -funswitch-loops
> > > >  -fipa-ra  -fvariable-expansion-in-unroller  -fvect-cost-model  -fvpt
> > > > --fweb  -fwhole-program  -fwpa  -fuse-linker-plugin  -fzero-call-used-regs
> > > > +-fweb  -fwhole-program  -fwidening-mul-defer-fma  -fwpa
> > > > +-fuse-linker-plugin  -fzero-call-used-regs
> > > >  -O  -O0  -O1  -O2  -O3  -Os  -Ofast  -Og  -Oz  --optimize}
> > > >
> > > >  @item Program Instrumentation Options
> > > > @@ -15917,6 +15918,20 @@ however, make debugging impossible, since variables no longer stay in a
> > > >
> > > >  Enabled by default with @option{-funroll-loops}.
> > > >
> > > > +@opindex fwidening-mul-defer-fma
> > > > +@opindex fno-widening-mul-defer-fma
> > > > +@item -fwidening-mul-defer-fma
> > > > +When FMA avoidance is requested for loop-carried reductions (that is, when
> > > > +@option{--param=avoid-fma-max-bits} is non-zero), the widening-multiply pass
> > > > +refuses to contract a multiply-add whose result feeds a loop-header PHI,
> > > > +leaving a separate multiply and add.  Use @option{-fno-widening-mul-defer-fma}
> > > > +to suppress this deferring and contract such reductions into an FMA, while
> > > > +still leaving @option{--param=avoid-fma-max-bits} in effect for the
> > > > +@file{tree-ssa-reassoc.cc} loop-carried-FMA reordering of longer chains.
> > > > +This is useful on targets whose pipeline disfavours the extra floating-point
> > > > +operation more than the loop-carried FMA latency.  The option is enabled by
> > > > +default.
> > > Here either.
> > >
> > >
> > > > +
> > > >  @opindex fwhole-program
> > > >  @opindex fno-whole-program
> > > >  @item -fwhole-program
> > > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > > > new file mode 100644
> > > > index 000000000000..b542274eb763
> > > > --- /dev/null
> > > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > > > @@ -0,0 +1,19 @@
> > > > +/* { dg-do compile } */
> > > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize -mcpu=ampere1" } */
> > > > +
> > > > +/* The ampere1 family sets AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA, which
> > > > +   clears -fwidening-mul-defer-fma so that a 2-operand loop-carried
> > > > +   reduction is contracted to fmadd rather than deferred to fmul + fadd.
> > > > +   (avoid-fma-max-bits stays 512 to keep the reassoc reorder enabled.)  */
> > > > +
> > > > +double
> > > > +dot (const double *a, const double *b, int n)
> > > > +{
> > > > +  double s = 0.0;
> > > > +  for (int i = 0; i < n; i++)
> > > > +    s += a[i] * b[i];
> > > > +  return s;
> > > > +}
> > > > +
> > > > +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> > > > +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> > > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > > > new file mode 100644
> > > > index 000000000000..764dd2457435
> > > > --- /dev/null
> > > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > > > @@ -0,0 +1,21 @@
> > > > +/* { dg-do compile } */
> > > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512" } */
> > > > +
> > > > +/* With FMA deferring active (avoid-fma-max-bits > 0) and the default
> > > > +   -fwidening-mul-defer-fma, the widening_mul pass refuses to form an FMA
> > > > +   whose result feeds the loop-header phi: the reduction stays as a
> > > > +   separate fmul + fadd.  This is the behaviour the new flag decouples
> > > > +   from the reassoc reorder (also gated by avoid-fma-max-bits).  */
> > > > +
> > > > +double
> > > > +dot (const double *a, const double *b, int n)
> > > > +{
> > > > +  double s = 0.0;
> > > > +  for (int i = 0; i < n; i++)
> > > > +    s += a[i] * b[i];
> > > > +  return s;
> > > > +}
> > > > +
> > > > +/* { dg-final { scan-assembler {\tfmul\t} } } */
> > > > +/* { dg-final { scan-assembler {\tfadd\t} } } */
> > > > +/* { dg-final { scan-assembler-not {\tfmadd\t} } } */
> > > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > > > new file mode 100644
> > > > index 000000000000..5e041afc18fc
> > > > --- /dev/null
> > > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > > > @@ -0,0 +1,20 @@
> > > > +/* { dg-do compile } */
> > > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512 -fno-widening-mul-defer-fma" } */
> > > > +
> > > > +/* Companion to widening-mul-defer-fma-2.c: the same reduction with FMA
> > > > +   avoidance still requested for the reassoc reorder (avoid-fma-max-bits=512)
> > > > +   but -fno-widening-mul-defer-fma now suppresses the widening_mul deferring,
> > > > +   so the loop-carried multiply-add is contracted to a single fmadd.  This
> > > > +   proves the new flag decouples the deferring from avoid-fma-max-bits.  */
> > > > +
> > > > +double
> > > > +dot (const double *a, const double *b, int n)
> > > > +{
> > > > +  double s = 0.0;
> > > > +  for (int i = 0; i < n; i++)
> > > > +    s += a[i] * b[i];
> > > > +  return s;
> > > > +}
> > > > +
> > > > +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> > > > +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> > > > diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
> > > > index f0ede668d95e..a00146922713 100644
> > > > --- a/gcc/tree-ssa-math-opts.cc
> > > > +++ b/gcc/tree-ssa-math-opts.cc
> > > > @@ -6607,7 +6607,8 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
> > > >  {
> > > >    gimple_stmt_iterator gsi;
> > > >
> > > > -  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0);
> > > > +  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0
> > > > +                                && flag_widening_mul_defer_fma);
> > > >
> > > >    for (gphi_iterator psi_next, psi = gsi_start_phis (bb); !gsi_end_p (psi);
> > > >         psi = psi_next)
> > > > --
> > > > 2.34.1
> > > >
> > > > base-commit: 3b443e764144526748d2b51d017d745f1956377e
> > > > branch: ptomsich/475-widening-mul-defer-fma
  
Philipp Tomsich July 8, 2026, 9:58 a.m. UTC | #5
Superseded by v2 at
https://gcc.gnu.org/pipermail/gcc-patches/2026-July/723165.html

On Tue, 7 Jul 2026 at 23:53, Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
>
> On Tue, 7 Jul 2026 at 23:51, Andrea Pinski
> <andrew.pinski@oss.qualcomm.com> wrote:
> >
> > On Tue, Jul 7, 2026 at 2:46 PM Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
> > >
> > > On Tue, 7 Jul 2026 at 23:40, Andrea Pinski
> > > <andrew.pinski@oss.qualcomm.com> wrote:
> > > >
> > > > On Tue, Jul 7, 2026 at 2:35 PM Philipp Tomsich <philipp.tomsich@vrull.eu> wrote:
> > > > >
> > > > > param_avoid_fma_max_bits gates two independent transforms: the
> > > > > widening_mul FMA-deferring in tree-ssa-math-opts.cc, which leaves a
> > > > > loop-carried multiply-add as fmul + fadd, and the reassoc
> > > > > loop-carried-FMA reorder added in r14-5779-g746344dd538
> > > > > (PR tree-optimization/110279), which parallelises 3+ operand chains.
> > > > > Both fire when TYPE_SIZE (elt) <= avoid-fma-max-bits, so for a given
> > > > > type they switch on at the same threshold and a target cannot keep one
> > > > > while dropping the other.
> > > > >
> > > > > This hurts the AArch64 AVOID_CROSS_LOOP_FMA cores (the Ampere-1
> > > > > family): a 2-operand reduction such as an sgemm inner K-loop is left as
> > > > > fmul + fadd, slower than fmadd on their dispatch-bound pipeline, yet
> > > > > setting avoid-fma-max-bits to 0 to avoid it also disables the reorder.
> > > > >
> > > > > Add a generic -fwidening-mul-defer-fma (default on) that gates only the
> > > > > widening_mul deferring; avoid-fma-max-bits keeps gating the reorder
> > > > > alone.  The AVOID_CROSS_LOOP_FMA callback clears the flag.  No other
> > > > > target and no default behaviour changes.
> > > >
> > > > Note this is just a review on the documentation and nothing else.
> > > >
> > > > >
> > > > > gcc/ChangeLog:
> > > > >
> > > > >         * common.opt (fwidening-mul-defer-fma): New option.
> > > > >         * tree-ssa-math-opts.cc (math_opts_dom_walker::after_dom_children):
> > > > >         Gate fma_deferring_state's enable predicate on
> > > > >         flag_widening_mul_defer_fma in addition to param_avoid_fma_max_bits.
> > > > >         * config/aarch64/aarch64-tuning-flags.def (AVOID_CROSS_LOOP_FMA):
> > > > >         Update the comment for the -fwidening-mul-defer-fma effect.
> > > > >         * config/aarch64/aarch64.cc (aarch64_override_options_internal):
> > > > >         Inside the AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA block, clear
> > > > >         flag_widening_mul_defer_fma.
> > > > >         * doc/invoke.texi (-fwidening-mul-defer-fma): Document.
> > > > >
> > > > > gcc/testsuite/ChangeLog:
> > > > >
> > > > >         * gcc.target/aarch64/widening-mul-defer-fma-1.c: New test.
> > > > >         * gcc.target/aarch64/widening-mul-defer-fma-2.c: New test.
> > > > >         * gcc.target/aarch64/widening-mul-defer-fma-3.c: New test.
> > > > >
> > > > > Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
> > > > > ---
> > > > >
> > > > >  gcc/common.opt                                |  4 ++++
> > > > >  gcc/config/aarch64/aarch64-tuning-flags.def   |  4 ++++
> > > > >  gcc/config/aarch64/aarch64.cc                 | 12 ++++++++---
> > > > >  gcc/doc/invoke.texi                           | 17 ++++++++++++++-
> > > > >  .../aarch64/widening-mul-defer-fma-1.c        | 19 +++++++++++++++++
> > > > >  .../aarch64/widening-mul-defer-fma-2.c        | 21 +++++++++++++++++++
> > > > >  .../aarch64/widening-mul-defer-fma-3.c        | 20 ++++++++++++++++++
> > > > >  gcc/tree-ssa-math-opts.cc                     |  3 ++-
> > > > >  8 files changed, 95 insertions(+), 5 deletions(-)
> > > > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > > > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > > > >  create mode 100644 gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > > > >
> > > > > diff --git a/gcc/common.opt b/gcc/common.opt
> > > > > index 218dddf5dfe9..9be7dd6b2315 100644
> > > > > --- a/gcc/common.opt
> > > > > +++ b/gcc/common.opt
> > > > > @@ -3639,6 +3639,10 @@ fweb
> > > > >  Common Var(flag_web) Optimization EnabledBy(funroll-loops)
> > > > >  Construct webs and split unrelated uses of single variable.
> > > > >
> > > > > +fwidening-mul-defer-fma
> > > > > +Common Var(flag_widening_mul_defer_fma) Init(1) Optimization
> > > > > +Defer forming an FMA whose result feeds a loop-header PHI, leaving a separate multiply and add, when FMA avoidance is requested via --param=avoid-fma-max-bits.
> > > >
> > > > Don't mention --param in user documentation directly.
> > >
> > > That brings up a question we discussed in internal reviews: should
> > > this even be a -fwidening-mul-defer-fma flag then — or just another
> > > --param?
> > > After all, this is the companion for a --param, so the alternate
> > > opinion was to have a second --param that would be set to either 0 or
> > > 1.  However, such a param (that will always be set either to 0 or 1)
> > > seems odd.
> >
> >
> > There are plenty of params that are already only support 0 or 1.
> > Just after the line 34 of params.opt 4 in a row:
> > -param=asan-globals=
> > Common Joined UInteger Var(param_asan_globals) Init(1) IntegerRange(0, 1) Param
> > Enable asan globals protection.
> >
> > And fully-pipelined-fma is one too:
> > -param=fully-pipelined-fma=
> > Common Joined UInteger Var(param_fully_pipelined_fma) Init(0)
> > IntegerRange(0, 1) Param Optimization
> > Whether the target fully pipelines FMA instructions.  If non-zero,
> > reassociation considers the benefit of parallelizing FMA's multiplication
> > part and addition part, assuming FMUL and FMA use the same units that can
> > also do FADD.
>
> I'll take this as "follow the established precedent, even if you don't
> find it pretty".
> ACK.
>
> >
> > >
> > > The third option discussed was a target-hook, but that doesn't allow a
> > > commandline-override.
> > >
> > > Any thoughts?
> > >
> > > >
> > > > > +
> > > > >  ftree-builtin-call-dce
> > > > >  Common Var(flag_tree_builtin_call_dce) Init(0) Optimization
> > > > >  Enable conditional dead code elimination for builtin calls.
> > > > > diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def
> > > > > index 058dadecccaa..5b087bfc9f03 100644
> > > > > --- a/gcc/config/aarch64/aarch64-tuning-flags.def
> > > > > +++ b/gcc/config/aarch64/aarch64-tuning-flags.def
> > > > > @@ -40,6 +40,10 @@ AARCH64_EXTRA_TUNING_OPTION ("cse_sve_vl_constants", CSE_SVE_VL_CONSTANTS)
> > > > >
> > > > >  AARCH64_EXTRA_TUNING_OPTION ("matched_vector_throughput", MATCHED_VECTOR_THROUGHPUT)
> > > > >
> > > > > +/* For cores whose pipeline disfavours loop-carried serial FMAs: set
> > > > > +   avoid-fma-max-bits to 512 to enable the reassoc reorder for 3+ operand
> > > > > +   chains, and clear -fwidening-mul-defer-fma to suppress the widening-mul
> > > > > +   pass's FMA deferring.  */
> > > > >  AARCH64_EXTRA_TUNING_OPTION ("avoid_cross_loop_fma", AVOID_CROSS_LOOP_FMA)
> > > > >
> > > > >  AARCH64_EXTRA_TUNING_OPTION ("fully_pipelined_fma", FULLY_PIPELINED_FMA)
> > > > > diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
> > > > > index 78f1eae8336c..fdb5bbbdfbce 100644
> > > > > --- a/gcc/config/aarch64/aarch64.cc
> > > > > +++ b/gcc/config/aarch64/aarch64.cc
> > > > > @@ -20087,11 +20087,17 @@ aarch64_override_options_internal (struct gcc_options *opts,
> > > > >        && opts->x_optimize >= aarch64_tune_params.prefetch->default_opt_level)
> > > > >      opts->x_flag_prefetch_loop_arrays = 1;
> > > > >
> > > > > -  /* Avoid loop-dependant FMA chains.  */
> > > > > +  /* Avoid loop-dependant FMA chains.  The reassoc-side reorder helper
> > > > > +     keeps using --param=avoid-fma-max-bits; the widening-mul-side
> > > > > +     deferring is gated separately by -fwidening-mul-defer-fma, so we
> > > > > +     suppress only the deferring on these cores while leaving the reassoc
> > > > > +     reorder active.  */
> > > > >    if (aarch64_tune_params.extra_tuning_flags
> > > > >        & AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA)
> > > > > -    SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits,
> > > > > -                        512);
> > > > > +    {
> > > > > +      SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 512);
> > > > > +      SET_OPTION_IF_UNSET (opts, opts_set, flag_widening_mul_defer_fma, 0);
> > > > > +    }
> > > > >
> > > > >    /* Consider fully pipelined FMA in reassociation.  */
> > > > >    if (aarch64_tune_params.extra_tuning_flags
> > > > > diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> > > > > index 208625cafc55..f39902f77e9b 100644
> > > > > --- a/gcc/doc/invoke.texi
> > > > > +++ b/gcc/doc/invoke.texi
> > > > > @@ -694,7 +694,8 @@ Objective-C and Objective-C++ Dialects}.
> > > > >  -funconstrained-commons  -funit-at-a-time  -funroll-all-loops
> > > > >  -funroll-loops  -funsafe-math-optimizations  -funswitch-loops
> > > > >  -fipa-ra  -fvariable-expansion-in-unroller  -fvect-cost-model  -fvpt
> > > > > --fweb  -fwhole-program  -fwpa  -fuse-linker-plugin  -fzero-call-used-regs
> > > > > +-fweb  -fwhole-program  -fwidening-mul-defer-fma  -fwpa
> > > > > +-fuse-linker-plugin  -fzero-call-used-regs
> > > > >  -O  -O0  -O1  -O2  -O3  -Os  -Ofast  -Og  -Oz  --optimize}
> > > > >
> > > > >  @item Program Instrumentation Options
> > > > > @@ -15917,6 +15918,20 @@ however, make debugging impossible, since variables no longer stay in a
> > > > >
> > > > >  Enabled by default with @option{-funroll-loops}.
> > > > >
> > > > > +@opindex fwidening-mul-defer-fma
> > > > > +@opindex fno-widening-mul-defer-fma
> > > > > +@item -fwidening-mul-defer-fma
> > > > > +When FMA avoidance is requested for loop-carried reductions (that is, when
> > > > > +@option{--param=avoid-fma-max-bits} is non-zero), the widening-multiply pass
> > > > > +refuses to contract a multiply-add whose result feeds a loop-header PHI,
> > > > > +leaving a separate multiply and add.  Use @option{-fno-widening-mul-defer-fma}
> > > > > +to suppress this deferring and contract such reductions into an FMA, while
> > > > > +still leaving @option{--param=avoid-fma-max-bits} in effect for the
> > > > > +@file{tree-ssa-reassoc.cc} loop-carried-FMA reordering of longer chains.
> > > > > +This is useful on targets whose pipeline disfavours the extra floating-point
> > > > > +operation more than the loop-carried FMA latency.  The option is enabled by
> > > > > +default.
> > > > Here either.
> > > >
> > > >
> > > > > +
> > > > >  @opindex fwhole-program
> > > > >  @opindex fno-whole-program
> > > > >  @item -fwhole-program
> > > > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > > > > new file mode 100644
> > > > > index 000000000000..b542274eb763
> > > > > --- /dev/null
> > > > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
> > > > > @@ -0,0 +1,19 @@
> > > > > +/* { dg-do compile } */
> > > > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize -mcpu=ampere1" } */
> > > > > +
> > > > > +/* The ampere1 family sets AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA, which
> > > > > +   clears -fwidening-mul-defer-fma so that a 2-operand loop-carried
> > > > > +   reduction is contracted to fmadd rather than deferred to fmul + fadd.
> > > > > +   (avoid-fma-max-bits stays 512 to keep the reassoc reorder enabled.)  */
> > > > > +
> > > > > +double
> > > > > +dot (const double *a, const double *b, int n)
> > > > > +{
> > > > > +  double s = 0.0;
> > > > > +  for (int i = 0; i < n; i++)
> > > > > +    s += a[i] * b[i];
> > > > > +  return s;
> > > > > +}
> > > > > +
> > > > > +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> > > > > +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> > > > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > > > > new file mode 100644
> > > > > index 000000000000..764dd2457435
> > > > > --- /dev/null
> > > > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
> > > > > @@ -0,0 +1,21 @@
> > > > > +/* { dg-do compile } */
> > > > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512" } */
> > > > > +
> > > > > +/* With FMA deferring active (avoid-fma-max-bits > 0) and the default
> > > > > +   -fwidening-mul-defer-fma, the widening_mul pass refuses to form an FMA
> > > > > +   whose result feeds the loop-header phi: the reduction stays as a
> > > > > +   separate fmul + fadd.  This is the behaviour the new flag decouples
> > > > > +   from the reassoc reorder (also gated by avoid-fma-max-bits).  */
> > > > > +
> > > > > +double
> > > > > +dot (const double *a, const double *b, int n)
> > > > > +{
> > > > > +  double s = 0.0;
> > > > > +  for (int i = 0; i < n; i++)
> > > > > +    s += a[i] * b[i];
> > > > > +  return s;
> > > > > +}
> > > > > +
> > > > > +/* { dg-final { scan-assembler {\tfmul\t} } } */
> > > > > +/* { dg-final { scan-assembler {\tfadd\t} } } */
> > > > > +/* { dg-final { scan-assembler-not {\tfmadd\t} } } */
> > > > > diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > > > > new file mode 100644
> > > > > index 000000000000..5e041afc18fc
> > > > > --- /dev/null
> > > > > +++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
> > > > > @@ -0,0 +1,20 @@
> > > > > +/* { dg-do compile } */
> > > > > +/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512 -fno-widening-mul-defer-fma" } */
> > > > > +
> > > > > +/* Companion to widening-mul-defer-fma-2.c: the same reduction with FMA
> > > > > +   avoidance still requested for the reassoc reorder (avoid-fma-max-bits=512)
> > > > > +   but -fno-widening-mul-defer-fma now suppresses the widening_mul deferring,
> > > > > +   so the loop-carried multiply-add is contracted to a single fmadd.  This
> > > > > +   proves the new flag decouples the deferring from avoid-fma-max-bits.  */
> > > > > +
> > > > > +double
> > > > > +dot (const double *a, const double *b, int n)
> > > > > +{
> > > > > +  double s = 0.0;
> > > > > +  for (int i = 0; i < n; i++)
> > > > > +    s += a[i] * b[i];
> > > > > +  return s;
> > > > > +}
> > > > > +
> > > > > +/* { dg-final { scan-assembler {\tfmadd\t} } } */
> > > > > +/* { dg-final { scan-assembler-not {\tfmul\t} } } */
> > > > > diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
> > > > > index f0ede668d95e..a00146922713 100644
> > > > > --- a/gcc/tree-ssa-math-opts.cc
> > > > > +++ b/gcc/tree-ssa-math-opts.cc
> > > > > @@ -6607,7 +6607,8 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
> > > > >  {
> > > > >    gimple_stmt_iterator gsi;
> > > > >
> > > > > -  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0);
> > > > > +  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0
> > > > > +                                && flag_widening_mul_defer_fma);
> > > > >
> > > > >    for (gphi_iterator psi_next, psi = gsi_start_phis (bb); !gsi_end_p (psi);
> > > > >         psi = psi_next)
> > > > > --
> > > > > 2.34.1
> > > > >
> > > > > base-commit: 3b443e764144526748d2b51d017d745f1956377e
> > > > > branch: ptomsich/475-widening-mul-defer-fma
  

Patch

diff --git a/gcc/common.opt b/gcc/common.opt
index 218dddf5dfe9..9be7dd6b2315 100644
--- a/gcc/common.opt
+++ b/gcc/common.opt
@@ -3639,6 +3639,10 @@  fweb
 Common Var(flag_web) Optimization EnabledBy(funroll-loops)
 Construct webs and split unrelated uses of single variable.
 
+fwidening-mul-defer-fma
+Common Var(flag_widening_mul_defer_fma) Init(1) Optimization
+Defer forming an FMA whose result feeds a loop-header PHI, leaving a separate multiply and add, when FMA avoidance is requested via --param=avoid-fma-max-bits.
+
 ftree-builtin-call-dce
 Common Var(flag_tree_builtin_call_dce) Init(0) Optimization
 Enable conditional dead code elimination for builtin calls.
diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def
index 058dadecccaa..5b087bfc9f03 100644
--- a/gcc/config/aarch64/aarch64-tuning-flags.def
+++ b/gcc/config/aarch64/aarch64-tuning-flags.def
@@ -40,6 +40,10 @@  AARCH64_EXTRA_TUNING_OPTION ("cse_sve_vl_constants", CSE_SVE_VL_CONSTANTS)
 
 AARCH64_EXTRA_TUNING_OPTION ("matched_vector_throughput", MATCHED_VECTOR_THROUGHPUT)
 
+/* For cores whose pipeline disfavours loop-carried serial FMAs: set
+   avoid-fma-max-bits to 512 to enable the reassoc reorder for 3+ operand
+   chains, and clear -fwidening-mul-defer-fma to suppress the widening-mul
+   pass's FMA deferring.  */
 AARCH64_EXTRA_TUNING_OPTION ("avoid_cross_loop_fma", AVOID_CROSS_LOOP_FMA)
 
 AARCH64_EXTRA_TUNING_OPTION ("fully_pipelined_fma", FULLY_PIPELINED_FMA)
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 78f1eae8336c..fdb5bbbdfbce 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -20087,11 +20087,17 @@  aarch64_override_options_internal (struct gcc_options *opts,
       && opts->x_optimize >= aarch64_tune_params.prefetch->default_opt_level)
     opts->x_flag_prefetch_loop_arrays = 1;
 
-  /* Avoid loop-dependant FMA chains.  */
+  /* Avoid loop-dependant FMA chains.  The reassoc-side reorder helper
+     keeps using --param=avoid-fma-max-bits; the widening-mul-side
+     deferring is gated separately by -fwidening-mul-defer-fma, so we
+     suppress only the deferring on these cores while leaving the reassoc
+     reorder active.  */
   if (aarch64_tune_params.extra_tuning_flags
       & AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA)
-    SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits,
-			 512);
+    {
+      SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 512);
+      SET_OPTION_IF_UNSET (opts, opts_set, flag_widening_mul_defer_fma, 0);
+    }
 
   /* Consider fully pipelined FMA in reassociation.  */
   if (aarch64_tune_params.extra_tuning_flags
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 208625cafc55..f39902f77e9b 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -694,7 +694,8 @@  Objective-C and Objective-C++ Dialects}.
 -funconstrained-commons  -funit-at-a-time  -funroll-all-loops
 -funroll-loops  -funsafe-math-optimizations  -funswitch-loops
 -fipa-ra  -fvariable-expansion-in-unroller  -fvect-cost-model  -fvpt
--fweb  -fwhole-program  -fwpa  -fuse-linker-plugin  -fzero-call-used-regs
+-fweb  -fwhole-program  -fwidening-mul-defer-fma  -fwpa
+-fuse-linker-plugin  -fzero-call-used-regs
 -O  -O0  -O1  -O2  -O3  -Os  -Ofast  -Og  -Oz  --optimize}
 
 @item Program Instrumentation Options
@@ -15917,6 +15918,20 @@  however, make debugging impossible, since variables no longer stay in a
 
 Enabled by default with @option{-funroll-loops}.
 
+@opindex fwidening-mul-defer-fma
+@opindex fno-widening-mul-defer-fma
+@item -fwidening-mul-defer-fma
+When FMA avoidance is requested for loop-carried reductions (that is, when
+@option{--param=avoid-fma-max-bits} is non-zero), the widening-multiply pass
+refuses to contract a multiply-add whose result feeds a loop-header PHI,
+leaving a separate multiply and add.  Use @option{-fno-widening-mul-defer-fma}
+to suppress this deferring and contract such reductions into an FMA, while
+still leaving @option{--param=avoid-fma-max-bits} in effect for the
+@file{tree-ssa-reassoc.cc} loop-carried-FMA reordering of longer chains.
+This is useful on targets whose pipeline disfavours the extra floating-point
+operation more than the loop-carried FMA latency.  The option is enabled by
+default.
+
 @opindex fwhole-program
 @opindex fno-whole-program
 @item -fwhole-program
diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
new file mode 100644
index 000000000000..b542274eb763
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-1.c
@@ -0,0 +1,19 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -ffast-math -fno-tree-vectorize -mcpu=ampere1" } */
+
+/* The ampere1 family sets AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA, which
+   clears -fwidening-mul-defer-fma so that a 2-operand loop-carried
+   reduction is contracted to fmadd rather than deferred to fmul + fadd.
+   (avoid-fma-max-bits stays 512 to keep the reassoc reorder enabled.)  */
+
+double
+dot (const double *a, const double *b, int n)
+{
+  double s = 0.0;
+  for (int i = 0; i < n; i++)
+    s += a[i] * b[i];
+  return s;
+}
+
+/* { dg-final { scan-assembler {\tfmadd\t} } } */
+/* { dg-final { scan-assembler-not {\tfmul\t} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
new file mode 100644
index 000000000000..764dd2457435
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-2.c
@@ -0,0 +1,21 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512" } */
+
+/* With FMA deferring active (avoid-fma-max-bits > 0) and the default
+   -fwidening-mul-defer-fma, the widening_mul pass refuses to form an FMA
+   whose result feeds the loop-header phi: the reduction stays as a
+   separate fmul + fadd.  This is the behaviour the new flag decouples
+   from the reassoc reorder (also gated by avoid-fma-max-bits).  */
+
+double
+dot (const double *a, const double *b, int n)
+{
+  double s = 0.0;
+  for (int i = 0; i < n; i++)
+    s += a[i] * b[i];
+  return s;
+}
+
+/* { dg-final { scan-assembler {\tfmul\t} } } */
+/* { dg-final { scan-assembler {\tfadd\t} } } */
+/* { dg-final { scan-assembler-not {\tfmadd\t} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
new file mode 100644
index 000000000000..5e041afc18fc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/widening-mul-defer-fma-3.c
@@ -0,0 +1,20 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -ffast-math -fno-tree-vectorize --param=avoid-fma-max-bits=512 -fno-widening-mul-defer-fma" } */
+
+/* Companion to widening-mul-defer-fma-2.c: the same reduction with FMA
+   avoidance still requested for the reassoc reorder (avoid-fma-max-bits=512)
+   but -fno-widening-mul-defer-fma now suppresses the widening_mul deferring,
+   so the loop-carried multiply-add is contracted to a single fmadd.  This
+   proves the new flag decouples the deferring from avoid-fma-max-bits.  */
+
+double
+dot (const double *a, const double *b, int n)
+{
+  double s = 0.0;
+  for (int i = 0; i < n; i++)
+    s += a[i] * b[i];
+  return s;
+}
+
+/* { dg-final { scan-assembler {\tfmadd\t} } } */
+/* { dg-final { scan-assembler-not {\tfmul\t} } } */
diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
index f0ede668d95e..a00146922713 100644
--- a/gcc/tree-ssa-math-opts.cc
+++ b/gcc/tree-ssa-math-opts.cc
@@ -6607,7 +6607,8 @@  math_opts_dom_walker::after_dom_children (basic_block bb)
 {
   gimple_stmt_iterator gsi;
 
-  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0);
+  fma_deferring_state fma_state (param_avoid_fma_max_bits > 0
+				 && flag_widening_mul_defer_fma);
 
   for (gphi_iterator psi_next, psi = gsi_start_phis (bb); !gsi_end_p (psi);
        psi = psi_next)