| Message ID | 20211105053851.24542-1-hongtao.liu@intel.com |
|---|---|
| State | New |
| Headers | show |
| Series | [1/2,Gimple] Simplify (trunc)fmax/fmin((extend)a, (extend)b) to MAX/MIN(a, b) | expand |
On Fri, Nov 5, 2021 at 6:38 AM liuhongt <hongtao.liu@intel.com> wrote: > > a and b are same type as trunc type and has less precision than > extend type, the transformation is guarded by flag_finite_math_only. > > Bootstrapped and regtested under x86_64-pc-linux-gnu{-m32,} > Ok for trunk? > > gcc/ChangeLog: > > PR target/102464 > * match.pd: Simplify (trunc)fmax/fmin((extend)a, (extend)b) to > MAX/MIN(a,b) > > gcc/testsuite/ChangeLog: > > * gcc.target/i386/pr102464-maxmin.c: New test. > --- > gcc/match.pd | 14 ++++++ > .../gcc.target/i386/pr102464-maxmin.c | 44 +++++++++++++++++++ > 2 files changed, 58 insertions(+) > create mode 100644 gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > diff --git a/gcc/match.pd b/gcc/match.pd > index f63079023d0..857ce7f712a 100644 > --- a/gcc/match.pd > +++ b/gcc/match.pd > @@ -6182,6 +6182,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > && direct_internal_fn_supported_p (IFN_COPYSIGN, > type, OPTIMIZE_FOR_BOTH)) > (IFN_COPYSIGN @0 @1)))) > + > +(for maxmin (max min) > + (simplify > + (convert (maxmin (convert@2 @0) (convert @1))) > + (if (flag_finite_math_only I suppose you are concerned about infinities, not about NaNs. Please use !HONOR_INFINITIES (@2) then (in general testing flag_* is frowned upon). You may want to do the FLOAT_TYPE_P tests first. > + && optimize > + && FLOAT_TYPE_P (type) > + && FLOAT_TYPE_P (TREE_TYPE (@2)) > + && types_match (type, TREE_TYPE (@0)) > + && types_match (type, TREE_TYPE (@1)) > + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2)) > + && optab_handler (maxmin == MAX_EXPR ? smax_optab : smin_optab, > + TYPE_MODE (type)) != CODE_FOR_nothing) > + (maxmin @0 @1)))) > #endif > > (for froms (XFLOORL XCEILL XROUNDL XRINTL) > diff --git a/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > new file mode 100644 > index 00000000000..37867235a6c > --- /dev/null > +++ b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > @@ -0,0 +1,44 @@ > +/* PR target/102464. */ > +/* { dg-do compile } */ > +/* { dg-options "-O2 -mavx512fp16 -mavx512vl -ffast-math -ftree-vectorize -mtune=generic -mfpmath=sse" } */ > +/* { dg-final { scan-assembler-times "vmaxph" 3 } } */ > +/* { dg-final { scan-assembler-times "vminph" 3 } } */ > +/* { dg-final { scan-assembler-times "vmaxsh" 3 } } */ > +/* { dg-final { scan-assembler-times "vminsh" 3 } } */ > +/* { dg-final { scan-assembler-times "vmaxps" 2 } } */ > +/* { dg-final { scan-assembler-times "vminps" 2 } } */ > +/* { dg-final { scan-assembler-times "vmaxss" 2 } } */ > +/* { dg-final { scan-assembler-times "vminss" 2 } } */ > +/* { dg-final { scan-assembler-times "vmaxpd" 1 } } */ > +/* { dg-final { scan-assembler-times "vminpd" 1 } } */ > +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */ > +/* { dg-final { scan-assembler-times "vminsd" 1 } } */ > + > +#include<math.h> > +#define FOO(CODE,TYPE,SUFFIX) \ > + void \ > + foo_vect_##CODE##TYPE##SUFFIX (TYPE* __restrict a, TYPE* b, TYPE* c) \ > + { \ > + for (int i = 0; i != 8; i++) \ > + a[i] = CODE##SUFFIX (b[i], c[i]); \ > + } \ > + TYPE \ > + foo_##CODE##TYPE##SUFFIX (TYPE b, TYPE c) \ > + { \ > + return CODE##l (b, c); \ > + } > + > +FOO (fmax, _Float16, f); > +FOO (fmax, _Float16,); > +FOO (fmax, _Float16, l); > +FOO (fmin, _Float16, f); > +FOO (fmin, _Float16,); > +FOO (fmin, _Float16, l); > + > +FOO (fmax, float,); > +FOO (fmax, float, l); > +FOO (fmin, float,); > +FOO (fmin, float, l); > + > +FOO (fmax, double, l); > +FOO (fmin, double, l); > -- > 2.18.1 >
On Fri, Nov 5, 2021 at 5:52 PM Richard Biener <richard.guenther@gmail.com> wrote: > > On Fri, Nov 5, 2021 at 6:38 AM liuhongt <hongtao.liu@intel.com> wrote: > > > > a and b are same type as trunc type and has less precision than > > extend type, the transformation is guarded by flag_finite_math_only. > > > > Bootstrapped and regtested under x86_64-pc-linux-gnu{-m32,} > > Ok for trunk? > > > > gcc/ChangeLog: > > > > PR target/102464 > > * match.pd: Simplify (trunc)fmax/fmin((extend)a, (extend)b) to > > MAX/MIN(a,b) > > > > gcc/testsuite/ChangeLog: > > > > * gcc.target/i386/pr102464-maxmin.c: New test. > > --- > > gcc/match.pd | 14 ++++++ > > .../gcc.target/i386/pr102464-maxmin.c | 44 +++++++++++++++++++ > > 2 files changed, 58 insertions(+) > > create mode 100644 gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > diff --git a/gcc/match.pd b/gcc/match.pd > > index f63079023d0..857ce7f712a 100644 > > --- a/gcc/match.pd > > +++ b/gcc/match.pd > > @@ -6182,6 +6182,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > > && direct_internal_fn_supported_p (IFN_COPYSIGN, > > type, OPTIMIZE_FOR_BOTH)) > > (IFN_COPYSIGN @0 @1)))) > > + > > +(for maxmin (max min) > > + (simplify > > + (convert (maxmin (convert@2 @0) (convert @1))) > > + (if (flag_finite_math_only > > I suppose you are concerned about infinities, not about NaNs. > Please use !HONOR_INFINITIES (@2) then (in general testing > flag_* is frowned upon). You may want to do the FLOAT_TYPE_P > tests first. I'm concerned about NANs since MAX/MIN_EXPR are different from IEEE minimum and maximum operations at NAN operations. So i think i'd use MODE_HAS_NANS(@2)? > > > + && optimize > > + && FLOAT_TYPE_P (type) > > + && FLOAT_TYPE_P (TREE_TYPE (@2)) > > + && types_match (type, TREE_TYPE (@0)) > > + && types_match (type, TREE_TYPE (@1)) > > + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2)) > > + && optab_handler (maxmin == MAX_EXPR ? smax_optab : smin_optab, > > + TYPE_MODE (type)) != CODE_FOR_nothing) > > + (maxmin @0 @1)))) > > #endif > > > > (for froms (XFLOORL XCEILL XROUNDL XRINTL) > > diff --git a/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > new file mode 100644 > > index 00000000000..37867235a6c > > --- /dev/null > > +++ b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > @@ -0,0 +1,44 @@ > > +/* PR target/102464. */ > > +/* { dg-do compile } */ > > +/* { dg-options "-O2 -mavx512fp16 -mavx512vl -ffast-math -ftree-vectorize -mtune=generic -mfpmath=sse" } */ > > +/* { dg-final { scan-assembler-times "vmaxph" 3 } } */ > > +/* { dg-final { scan-assembler-times "vminph" 3 } } */ > > +/* { dg-final { scan-assembler-times "vmaxsh" 3 } } */ > > +/* { dg-final { scan-assembler-times "vminsh" 3 } } */ > > +/* { dg-final { scan-assembler-times "vmaxps" 2 } } */ > > +/* { dg-final { scan-assembler-times "vminps" 2 } } */ > > +/* { dg-final { scan-assembler-times "vmaxss" 2 } } */ > > +/* { dg-final { scan-assembler-times "vminss" 2 } } */ > > +/* { dg-final { scan-assembler-times "vmaxpd" 1 } } */ > > +/* { dg-final { scan-assembler-times "vminpd" 1 } } */ > > +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */ > > +/* { dg-final { scan-assembler-times "vminsd" 1 } } */ > > + > > +#include<math.h> > > +#define FOO(CODE,TYPE,SUFFIX) \ > > + void \ > > + foo_vect_##CODE##TYPE##SUFFIX (TYPE* __restrict a, TYPE* b, TYPE* c) \ > > + { \ > > + for (int i = 0; i != 8; i++) \ > > + a[i] = CODE##SUFFIX (b[i], c[i]); \ > > + } \ > > + TYPE \ > > + foo_##CODE##TYPE##SUFFIX (TYPE b, TYPE c) \ > > + { \ > > + return CODE##l (b, c); \ > > + } > > + > > +FOO (fmax, _Float16, f); > > +FOO (fmax, _Float16,); > > +FOO (fmax, _Float16, l); > > +FOO (fmin, _Float16, f); > > +FOO (fmin, _Float16,); > > +FOO (fmin, _Float16, l); > > + > > +FOO (fmax, float,); > > +FOO (fmax, float, l); > > +FOO (fmin, float,); > > +FOO (fmin, float, l); > > + > > +FOO (fmax, double, l); > > +FOO (fmin, double, l); > > -- > > 2.18.1 > > -- BR, Hongtao
On Mon, Nov 8, 2021 at 2:30 AM Hongtao Liu <crazylht@gmail.com> wrote: > > On Fri, Nov 5, 2021 at 5:52 PM Richard Biener > <richard.guenther@gmail.com> wrote: > > > > On Fri, Nov 5, 2021 at 6:38 AM liuhongt <hongtao.liu@intel.com> wrote: > > > > > > a and b are same type as trunc type and has less precision than > > > extend type, the transformation is guarded by flag_finite_math_only. > > > > > > Bootstrapped and regtested under x86_64-pc-linux-gnu{-m32,} > > > Ok for trunk? > > > > > > gcc/ChangeLog: > > > > > > PR target/102464 > > > * match.pd: Simplify (trunc)fmax/fmin((extend)a, (extend)b) to > > > MAX/MIN(a,b) > > > > > > gcc/testsuite/ChangeLog: > > > > > > * gcc.target/i386/pr102464-maxmin.c: New test. > > > --- > > > gcc/match.pd | 14 ++++++ > > > .../gcc.target/i386/pr102464-maxmin.c | 44 +++++++++++++++++++ > > > 2 files changed, 58 insertions(+) > > > create mode 100644 gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > > > diff --git a/gcc/match.pd b/gcc/match.pd > > > index f63079023d0..857ce7f712a 100644 > > > --- a/gcc/match.pd > > > +++ b/gcc/match.pd > > > @@ -6182,6 +6182,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > > > && direct_internal_fn_supported_p (IFN_COPYSIGN, > > > type, OPTIMIZE_FOR_BOTH)) > > > (IFN_COPYSIGN @0 @1)))) > > > + > > > +(for maxmin (max min) > > > + (simplify > > > + (convert (maxmin (convert@2 @0) (convert @1))) > > > + (if (flag_finite_math_only > > > > I suppose you are concerned about infinities, not about NaNs. > > Please use !HONOR_INFINITIES (@2) then (in general testing > > flag_* is frowned upon). You may want to do the FLOAT_TYPE_P > > tests first. > I'm concerned about NANs since MAX/MIN_EXPR are different from IEEE > minimum and maximum operations at NAN operations. But you are already only handling non-IEEE MAX/MIN_EXPR where the behavior with a NaN argument is unspecified? > So i think i'd use MODE_HAS_NANS(@2)? > > > > > + && optimize > > > + && FLOAT_TYPE_P (type) > > > + && FLOAT_TYPE_P (TREE_TYPE (@2)) > > > + && types_match (type, TREE_TYPE (@0)) > > > + && types_match (type, TREE_TYPE (@1)) > > > + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2)) > > > + && optab_handler (maxmin == MAX_EXPR ? smax_optab : smin_optab, > > > + TYPE_MODE (type)) != CODE_FOR_nothing) And just noticing this now - since we're only changing the type a MAX/MIN_EXPR operate on, we don't really need to do the optab check. At RTL expansion we'd eventually try a wider mode. > > > + (maxmin @0 @1)))) > > > #endif > > > > > > (for froms (XFLOORL XCEILL XROUNDL XRINTL) > > > diff --git a/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > new file mode 100644 > > > index 00000000000..37867235a6c > > > --- /dev/null > > > +++ b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > @@ -0,0 +1,44 @@ > > > +/* PR target/102464. */ > > > +/* { dg-do compile } */ > > > +/* { dg-options "-O2 -mavx512fp16 -mavx512vl -ffast-math -ftree-vectorize -mtune=generic -mfpmath=sse" } */ > > > +/* { dg-final { scan-assembler-times "vmaxph" 3 } } */ > > > +/* { dg-final { scan-assembler-times "vminph" 3 } } */ > > > +/* { dg-final { scan-assembler-times "vmaxsh" 3 } } */ > > > +/* { dg-final { scan-assembler-times "vminsh" 3 } } */ > > > +/* { dg-final { scan-assembler-times "vmaxps" 2 } } */ > > > +/* { dg-final { scan-assembler-times "vminps" 2 } } */ > > > +/* { dg-final { scan-assembler-times "vmaxss" 2 } } */ > > > +/* { dg-final { scan-assembler-times "vminss" 2 } } */ > > > +/* { dg-final { scan-assembler-times "vmaxpd" 1 } } */ > > > +/* { dg-final { scan-assembler-times "vminpd" 1 } } */ > > > +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */ > > > +/* { dg-final { scan-assembler-times "vminsd" 1 } } */ > > > + > > > +#include<math.h> > > > +#define FOO(CODE,TYPE,SUFFIX) \ > > > + void \ > > > + foo_vect_##CODE##TYPE##SUFFIX (TYPE* __restrict a, TYPE* b, TYPE* c) \ > > > + { \ > > > + for (int i = 0; i != 8; i++) \ > > > + a[i] = CODE##SUFFIX (b[i], c[i]); \ > > > + } \ > > > + TYPE \ > > > + foo_##CODE##TYPE##SUFFIX (TYPE b, TYPE c) \ > > > + { \ > > > + return CODE##l (b, c); \ > > > + } > > > + > > > +FOO (fmax, _Float16, f); > > > +FOO (fmax, _Float16,); > > > +FOO (fmax, _Float16, l); > > > +FOO (fmin, _Float16, f); > > > +FOO (fmin, _Float16,); > > > +FOO (fmin, _Float16, l); > > > + > > > +FOO (fmax, float,); > > > +FOO (fmax, float, l); > > > +FOO (fmin, float,); > > > +FOO (fmin, float, l); > > > + > > > +FOO (fmax, double, l); > > > +FOO (fmin, double, l); > > > -- > > > 2.18.1 > > > > > > > -- > BR, > Hongtao
On Mon, Nov 8, 2021 at 4:59 PM Richard Biener <richard.guenther@gmail.com> wrote: > > On Mon, Nov 8, 2021 at 2:30 AM Hongtao Liu <crazylht@gmail.com> wrote: > > > > On Fri, Nov 5, 2021 at 5:52 PM Richard Biener > > <richard.guenther@gmail.com> wrote: > > > > > > On Fri, Nov 5, 2021 at 6:38 AM liuhongt <hongtao.liu@intel.com> wrote: > > > > > > > > a and b are same type as trunc type and has less precision than > > > > extend type, the transformation is guarded by flag_finite_math_only. > > > > > > > > Bootstrapped and regtested under x86_64-pc-linux-gnu{-m32,} > > > > Ok for trunk? > > > > > > > > gcc/ChangeLog: > > > > > > > > PR target/102464 > > > > * match.pd: Simplify (trunc)fmax/fmin((extend)a, (extend)b) to > > > > MAX/MIN(a,b) > > > > > > > > gcc/testsuite/ChangeLog: > > > > > > > > * gcc.target/i386/pr102464-maxmin.c: New test. > > > > --- > > > > gcc/match.pd | 14 ++++++ > > > > .../gcc.target/i386/pr102464-maxmin.c | 44 +++++++++++++++++++ > > > > 2 files changed, 58 insertions(+) > > > > create mode 100644 gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > > > > > diff --git a/gcc/match.pd b/gcc/match.pd > > > > index f63079023d0..857ce7f712a 100644 > > > > --- a/gcc/match.pd > > > > +++ b/gcc/match.pd > > > > @@ -6182,6 +6182,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > > > > && direct_internal_fn_supported_p (IFN_COPYSIGN, > > > > type, OPTIMIZE_FOR_BOTH)) > > > > (IFN_COPYSIGN @0 @1)))) > > > > + > > > > +(for maxmin (max min) > > > > + (simplify > > > > + (convert (maxmin (convert@2 @0) (convert @1))) > > > > + (if (flag_finite_math_only > > > > > > I suppose you are concerned about infinities, not about NaNs. > > > Please use !HONOR_INFINITIES (@2) then (in general testing > > > flag_* is frowned upon). You may want to do the FLOAT_TYPE_P > > > tests first. > > I'm concerned about NANs since MAX/MIN_EXPR are different from IEEE > > minimum and maximum operations at NAN operations. > > But you are already only handling non-IEEE MAX/MIN_EXPR where the > behavior with a NaN argument is unspecified? Oh yes, it's already guarded by /* Convert fmin/fmax to MIN_EXPR/MAX_EXPR. C99 requires these functions to return the numeric arg if the other one is NaN. MIN and MAX don't honor that, so only transform if -ffinite-math-only is set. C99 doesn't require -0.0 to be handled, so we don't have to worry about it either. */ (if (flag_finite_math_only) (simplify > > > So i think i'd use MODE_HAS_NANS(@2)? > > > > > > > + && optimize > > > > + && FLOAT_TYPE_P (type) > > > > + && FLOAT_TYPE_P (TREE_TYPE (@2)) > > > > + && types_match (type, TREE_TYPE (@0)) > > > > + && types_match (type, TREE_TYPE (@1)) > > > > + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2)) > > > > + && optab_handler (maxmin == MAX_EXPR ? smax_optab : smin_optab, > > > > + TYPE_MODE (type)) != CODE_FOR_nothing) > > And just noticing this now - since we're only changing the type a MAX/MIN_EXPR > operate on, we don't really need to do the optab check. At RTL expansion > we'd eventually try a wider mode. Changed. Updated: + +(for maxmin (max min) + (simplify + (convert (maxmin (convert@2 @0) (convert @1))) + (if (optimize + && FLOAT_TYPE_P (type) + && FLOAT_TYPE_P (TREE_TYPE (@2)) + && types_match (type, TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@1)) + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2))) + (maxmin @0 @1)))) > > > > > + (maxmin @0 @1)))) > > > > #endif > > > > > > > > (for froms (XFLOORL XCEILL XROUNDL XRINTL) > > > > diff --git a/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > new file mode 100644 > > > > index 00000000000..37867235a6c > > > > --- /dev/null > > > > +++ b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > @@ -0,0 +1,44 @@ > > > > +/* PR target/102464. */ > > > > +/* { dg-do compile } */ > > > > +/* { dg-options "-O2 -mavx512fp16 -mavx512vl -ffast-math -ftree-vectorize -mtune=generic -mfpmath=sse" } */ > > > > +/* { dg-final { scan-assembler-times "vmaxph" 3 } } */ > > > > +/* { dg-final { scan-assembler-times "vminph" 3 } } */ > > > > +/* { dg-final { scan-assembler-times "vmaxsh" 3 } } */ > > > > +/* { dg-final { scan-assembler-times "vminsh" 3 } } */ > > > > +/* { dg-final { scan-assembler-times "vmaxps" 2 } } */ > > > > +/* { dg-final { scan-assembler-times "vminps" 2 } } */ > > > > +/* { dg-final { scan-assembler-times "vmaxss" 2 } } */ > > > > +/* { dg-final { scan-assembler-times "vminss" 2 } } */ > > > > +/* { dg-final { scan-assembler-times "vmaxpd" 1 } } */ > > > > +/* { dg-final { scan-assembler-times "vminpd" 1 } } */ > > > > +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */ > > > > +/* { dg-final { scan-assembler-times "vminsd" 1 } } */ > > > > + > > > > +#include<math.h> > > > > +#define FOO(CODE,TYPE,SUFFIX) \ > > > > + void \ > > > > + foo_vect_##CODE##TYPE##SUFFIX (TYPE* __restrict a, TYPE* b, TYPE* c) \ > > > > + { \ > > > > + for (int i = 0; i != 8; i++) \ > > > > + a[i] = CODE##SUFFIX (b[i], c[i]); \ > > > > + } \ > > > > + TYPE \ > > > > + foo_##CODE##TYPE##SUFFIX (TYPE b, TYPE c) \ > > > > + { \ > > > > + return CODE##l (b, c); \ > > > > + } > > > > + > > > > +FOO (fmax, _Float16, f); > > > > +FOO (fmax, _Float16,); > > > > +FOO (fmax, _Float16, l); > > > > +FOO (fmin, _Float16, f); > > > > +FOO (fmin, _Float16,); > > > > +FOO (fmin, _Float16, l); > > > > + > > > > +FOO (fmax, float,); > > > > +FOO (fmax, float, l); > > > > +FOO (fmin, float,); > > > > +FOO (fmin, float, l); > > > > + > > > > +FOO (fmax, double, l); > > > > +FOO (fmin, double, l); > > > > -- > > > > 2.18.1 > > > > > > > > > > > > -- > > BR, > > Hongtao
On Tue, Nov 9, 2021 at 3:37 AM Hongtao Liu <crazylht@gmail.com> wrote: > > On Mon, Nov 8, 2021 at 4:59 PM Richard Biener > <richard.guenther@gmail.com> wrote: > > > > On Mon, Nov 8, 2021 at 2:30 AM Hongtao Liu <crazylht@gmail.com> wrote: > > > > > > On Fri, Nov 5, 2021 at 5:52 PM Richard Biener > > > <richard.guenther@gmail.com> wrote: > > > > > > > > On Fri, Nov 5, 2021 at 6:38 AM liuhongt <hongtao.liu@intel.com> wrote: > > > > > > > > > > a and b are same type as trunc type and has less precision than > > > > > extend type, the transformation is guarded by flag_finite_math_only. > > > > > > > > > > Bootstrapped and regtested under x86_64-pc-linux-gnu{-m32,} > > > > > Ok for trunk? > > > > > > > > > > gcc/ChangeLog: > > > > > > > > > > PR target/102464 > > > > > * match.pd: Simplify (trunc)fmax/fmin((extend)a, (extend)b) to > > > > > MAX/MIN(a,b) > > > > > > > > > > gcc/testsuite/ChangeLog: > > > > > > > > > > * gcc.target/i386/pr102464-maxmin.c: New test. > > > > > --- > > > > > gcc/match.pd | 14 ++++++ > > > > > .../gcc.target/i386/pr102464-maxmin.c | 44 +++++++++++++++++++ > > > > > 2 files changed, 58 insertions(+) > > > > > create mode 100644 gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > > > > > > > diff --git a/gcc/match.pd b/gcc/match.pd > > > > > index f63079023d0..857ce7f712a 100644 > > > > > --- a/gcc/match.pd > > > > > +++ b/gcc/match.pd > > > > > @@ -6182,6 +6182,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > > > > > && direct_internal_fn_supported_p (IFN_COPYSIGN, > > > > > type, OPTIMIZE_FOR_BOTH)) > > > > > (IFN_COPYSIGN @0 @1)))) > > > > > + > > > > > +(for maxmin (max min) > > > > > + (simplify > > > > > + (convert (maxmin (convert@2 @0) (convert @1))) > > > > > + (if (flag_finite_math_only > > > > > > > > I suppose you are concerned about infinities, not about NaNs. > > > > Please use !HONOR_INFINITIES (@2) then (in general testing > > > > flag_* is frowned upon). You may want to do the FLOAT_TYPE_P > > > > tests first. > > > I'm concerned about NANs since MAX/MIN_EXPR are different from IEEE > > > minimum and maximum operations at NAN operations. > > > > But you are already only handling non-IEEE MAX/MIN_EXPR where the > > behavior with a NaN argument is unspecified? > Oh yes, it's already guarded by > /* Convert fmin/fmax to MIN_EXPR/MAX_EXPR. C99 requires these > functions to return the numeric arg if the other one is NaN. > MIN and MAX don't honor that, so only transform if -ffinite-math-only > is set. C99 doesn't require -0.0 to be handled, so we don't have to > worry about it either. */ > (if (flag_finite_math_only) > (simplify > > > > > > So i think i'd use MODE_HAS_NANS(@2)? > > > > > > > > > + && optimize > > > > > + && FLOAT_TYPE_P (type) > > > > > + && FLOAT_TYPE_P (TREE_TYPE (@2)) > > > > > + && types_match (type, TREE_TYPE (@0)) > > > > > + && types_match (type, TREE_TYPE (@1)) > > > > > + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2)) > > > > > + && optab_handler (maxmin == MAX_EXPR ? smax_optab : smin_optab, > > > > > + TYPE_MODE (type)) != CODE_FOR_nothing) > > > > And just noticing this now - since we're only changing the type a MAX/MIN_EXPR > > operate on, we don't really need to do the optab check. At RTL expansion > > we'd eventually try a wider mode. > Changed. > Updated: > + > +(for maxmin (max min) > + (simplify > + (convert (maxmin (convert@2 @0) (convert @1))) > + (if (optimize > + && FLOAT_TYPE_P (type) > + && FLOAT_TYPE_P (TREE_TYPE (@2)) > + && types_match (type, TREE_TYPE (@0)) > + && types_match (type, TREE_TYPE (@1)) > + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2))) since FLOAT_TYPE_P also matches vector types please use && element_precision (type) < element_precision (TREE_TYPE (@2)) > + (maxmin @0 @1)))) OK with that change. Thanks, Richard. > > > > > > > + (maxmin @0 @1)))) > > > > > #endif > > > > > > > > > > (for froms (XFLOORL XCEILL XROUNDL XRINTL) > > > > > diff --git a/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > > new file mode 100644 > > > > > index 00000000000..37867235a6c > > > > > --- /dev/null > > > > > +++ b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > > @@ -0,0 +1,44 @@ > > > > > +/* PR target/102464. */ > > > > > +/* { dg-do compile } */ > > > > > +/* { dg-options "-O2 -mavx512fp16 -mavx512vl -ffast-math -ftree-vectorize -mtune=generic -mfpmath=sse" } */ > > > > > +/* { dg-final { scan-assembler-times "vmaxph" 3 } } */ > > > > > +/* { dg-final { scan-assembler-times "vminph" 3 } } */ > > > > > +/* { dg-final { scan-assembler-times "vmaxsh" 3 } } */ > > > > > +/* { dg-final { scan-assembler-times "vminsh" 3 } } */ > > > > > +/* { dg-final { scan-assembler-times "vmaxps" 2 } } */ > > > > > +/* { dg-final { scan-assembler-times "vminps" 2 } } */ > > > > > +/* { dg-final { scan-assembler-times "vmaxss" 2 } } */ > > > > > +/* { dg-final { scan-assembler-times "vminss" 2 } } */ > > > > > +/* { dg-final { scan-assembler-times "vmaxpd" 1 } } */ > > > > > +/* { dg-final { scan-assembler-times "vminpd" 1 } } */ > > > > > +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */ > > > > > +/* { dg-final { scan-assembler-times "vminsd" 1 } } */ > > > > > + > > > > > +#include<math.h> > > > > > +#define FOO(CODE,TYPE,SUFFIX) \ > > > > > + void \ > > > > > + foo_vect_##CODE##TYPE##SUFFIX (TYPE* __restrict a, TYPE* b, TYPE* c) \ > > > > > + { \ > > > > > + for (int i = 0; i != 8; i++) \ > > > > > + a[i] = CODE##SUFFIX (b[i], c[i]); \ > > > > > + } \ > > > > > + TYPE \ > > > > > + foo_##CODE##TYPE##SUFFIX (TYPE b, TYPE c) \ > > > > > + { \ > > > > > + return CODE##l (b, c); \ > > > > > + } > > > > > + > > > > > +FOO (fmax, _Float16, f); > > > > > +FOO (fmax, _Float16,); > > > > > +FOO (fmax, _Float16, l); > > > > > +FOO (fmin, _Float16, f); > > > > > +FOO (fmin, _Float16,); > > > > > +FOO (fmin, _Float16, l); > > > > > + > > > > > +FOO (fmax, float,); > > > > > +FOO (fmax, float, l); > > > > > +FOO (fmin, float,); > > > > > +FOO (fmin, float, l); > > > > > + > > > > > +FOO (fmax, double, l); > > > > > +FOO (fmin, double, l); > > > > > -- > > > > > 2.18.1 > > > > > > > > > > > > > > > > > -- > > > BR, > > > Hongtao > > > > -- > BR, > Hongtao
On Tue, Nov 9, 2021 at 6:21 PM Richard Biener <richard.guenther@gmail.com> wrote: > > On Tue, Nov 9, 2021 at 3:37 AM Hongtao Liu <crazylht@gmail.com> wrote: > > > > On Mon, Nov 8, 2021 at 4:59 PM Richard Biener > > <richard.guenther@gmail.com> wrote: > > > > > > On Mon, Nov 8, 2021 at 2:30 AM Hongtao Liu <crazylht@gmail.com> wrote: > > > > > > > > On Fri, Nov 5, 2021 at 5:52 PM Richard Biener > > > > <richard.guenther@gmail.com> wrote: > > > > > > > > > > On Fri, Nov 5, 2021 at 6:38 AM liuhongt <hongtao.liu@intel.com> wrote: > > > > > > > > > > > > a and b are same type as trunc type and has less precision than > > > > > > extend type, the transformation is guarded by flag_finite_math_only. > > > > > > > > > > > > Bootstrapped and regtested under x86_64-pc-linux-gnu{-m32,} > > > > > > Ok for trunk? > > > > > > > > > > > > gcc/ChangeLog: > > > > > > > > > > > > PR target/102464 > > > > > > * match.pd: Simplify (trunc)fmax/fmin((extend)a, (extend)b) to > > > > > > MAX/MIN(a,b) > > > > > > > > > > > > gcc/testsuite/ChangeLog: > > > > > > > > > > > > * gcc.target/i386/pr102464-maxmin.c: New test. > > > > > > --- > > > > > > gcc/match.pd | 14 ++++++ > > > > > > .../gcc.target/i386/pr102464-maxmin.c | 44 +++++++++++++++++++ > > > > > > 2 files changed, 58 insertions(+) > > > > > > create mode 100644 gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > > > > > > > > > diff --git a/gcc/match.pd b/gcc/match.pd > > > > > > index f63079023d0..857ce7f712a 100644 > > > > > > --- a/gcc/match.pd > > > > > > +++ b/gcc/match.pd > > > > > > @@ -6182,6 +6182,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > > > > > > && direct_internal_fn_supported_p (IFN_COPYSIGN, > > > > > > type, OPTIMIZE_FOR_BOTH)) > > > > > > (IFN_COPYSIGN @0 @1)))) > > > > > > + > > > > > > +(for maxmin (max min) > > > > > > + (simplify > > > > > > + (convert (maxmin (convert@2 @0) (convert @1))) > > > > > > + (if (flag_finite_math_only > > > > > > > > > > I suppose you are concerned about infinities, not about NaNs. > > > > > Please use !HONOR_INFINITIES (@2) then (in general testing > > > > > flag_* is frowned upon). You may want to do the FLOAT_TYPE_P > > > > > tests first. > > > > I'm concerned about NANs since MAX/MIN_EXPR are different from IEEE > > > > minimum and maximum operations at NAN operations. > > > > > > But you are already only handling non-IEEE MAX/MIN_EXPR where the > > > behavior with a NaN argument is unspecified? > > Oh yes, it's already guarded by > > /* Convert fmin/fmax to MIN_EXPR/MAX_EXPR. C99 requires these > > functions to return the numeric arg if the other one is NaN. > > MIN and MAX don't honor that, so only transform if -ffinite-math-only > > is set. C99 doesn't require -0.0 to be handled, so we don't have to > > worry about it either. */ > > (if (flag_finite_math_only) > > (simplify > > > > > > > > > So i think i'd use MODE_HAS_NANS(@2)? > > > > > > > > > > > + && optimize > > > > > > + && FLOAT_TYPE_P (type) > > > > > > + && FLOAT_TYPE_P (TREE_TYPE (@2)) > > > > > > + && types_match (type, TREE_TYPE (@0)) > > > > > > + && types_match (type, TREE_TYPE (@1)) > > > > > > + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2)) > > > > > > + && optab_handler (maxmin == MAX_EXPR ? smax_optab : smin_optab, > > > > > > + TYPE_MODE (type)) != CODE_FOR_nothing) > > > > > > And just noticing this now - since we're only changing the type a MAX/MIN_EXPR > > > operate on, we don't really need to do the optab check. At RTL expansion > > > we'd eventually try a wider mode. > > Changed. > > Updated: > > + > > +(for maxmin (max min) > > + (simplify > > + (convert (maxmin (convert@2 @0) (convert @1))) > > + (if (optimize > > + && FLOAT_TYPE_P (type) > > + && FLOAT_TYPE_P (TREE_TYPE (@2)) > > + && types_match (type, TREE_TYPE (@0)) > > + && types_match (type, TREE_TYPE (@1)) > > + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2))) > > since FLOAT_TYPE_P also matches vector types please use > > && element_precision (type) < element_precision (TREE_TYPE (@2)) > > > + (maxmin @0 @1)))) > > OK with that change. > Yes, thanks for the review. > Thanks, > Richard. > > > > > > > > > > + (maxmin @0 @1)))) > > > > > > #endif > > > > > > > > > > > > (for froms (XFLOORL XCEILL XROUNDL XRINTL) > > > > > > diff --git a/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > > > new file mode 100644 > > > > > > index 00000000000..37867235a6c > > > > > > --- /dev/null > > > > > > +++ b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c > > > > > > @@ -0,0 +1,44 @@ > > > > > > +/* PR target/102464. */ > > > > > > +/* { dg-do compile } */ > > > > > > +/* { dg-options "-O2 -mavx512fp16 -mavx512vl -ffast-math -ftree-vectorize -mtune=generic -mfpmath=sse" } */ > > > > > > +/* { dg-final { scan-assembler-times "vmaxph" 3 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vminph" 3 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vmaxsh" 3 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vminsh" 3 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vmaxps" 2 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vminps" 2 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vmaxss" 2 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vminss" 2 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vmaxpd" 1 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vminpd" 1 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */ > > > > > > +/* { dg-final { scan-assembler-times "vminsd" 1 } } */ > > > > > > + > > > > > > +#include<math.h> > > > > > > +#define FOO(CODE,TYPE,SUFFIX) \ > > > > > > + void \ > > > > > > + foo_vect_##CODE##TYPE##SUFFIX (TYPE* __restrict a, TYPE* b, TYPE* c) \ > > > > > > + { \ > > > > > > + for (int i = 0; i != 8; i++) \ > > > > > > + a[i] = CODE##SUFFIX (b[i], c[i]); \ > > > > > > + } \ > > > > > > + TYPE \ > > > > > > + foo_##CODE##TYPE##SUFFIX (TYPE b, TYPE c) \ > > > > > > + { \ > > > > > > + return CODE##l (b, c); \ > > > > > > + } > > > > > > + > > > > > > +FOO (fmax, _Float16, f); > > > > > > +FOO (fmax, _Float16,); > > > > > > +FOO (fmax, _Float16, l); > > > > > > +FOO (fmin, _Float16, f); > > > > > > +FOO (fmin, _Float16,); > > > > > > +FOO (fmin, _Float16, l); > > > > > > + > > > > > > +FOO (fmax, float,); > > > > > > +FOO (fmax, float, l); > > > > > > +FOO (fmin, float,); > > > > > > +FOO (fmin, float, l); > > > > > > + > > > > > > +FOO (fmax, double, l); > > > > > > +FOO (fmin, double, l); > > > > > > -- > > > > > > 2.18.1 > > > > > > > > > > > > > > > > > > > > > > -- > > > > BR, > > > > Hongtao > > > > > > > > -- > > BR, > > Hongtao
diff --git a/gcc/match.pd b/gcc/match.pd index f63079023d0..857ce7f712a 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -6182,6 +6182,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) && direct_internal_fn_supported_p (IFN_COPYSIGN, type, OPTIMIZE_FOR_BOTH)) (IFN_COPYSIGN @0 @1)))) + +(for maxmin (max min) + (simplify + (convert (maxmin (convert@2 @0) (convert @1))) + (if (flag_finite_math_only + && optimize + && FLOAT_TYPE_P (type) + && FLOAT_TYPE_P (TREE_TYPE (@2)) + && types_match (type, TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@1)) + && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@2)) + && optab_handler (maxmin == MAX_EXPR ? smax_optab : smin_optab, + TYPE_MODE (type)) != CODE_FOR_nothing) + (maxmin @0 @1)))) #endif (for froms (XFLOORL XCEILL XROUNDL XRINTL) diff --git a/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c new file mode 100644 index 00000000000..37867235a6c --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr102464-maxmin.c @@ -0,0 +1,44 @@ +/* PR target/102464. */ +/* { dg-do compile } */ +/* { dg-options "-O2 -mavx512fp16 -mavx512vl -ffast-math -ftree-vectorize -mtune=generic -mfpmath=sse" } */ +/* { dg-final { scan-assembler-times "vmaxph" 3 } } */ +/* { dg-final { scan-assembler-times "vminph" 3 } } */ +/* { dg-final { scan-assembler-times "vmaxsh" 3 } } */ +/* { dg-final { scan-assembler-times "vminsh" 3 } } */ +/* { dg-final { scan-assembler-times "vmaxps" 2 } } */ +/* { dg-final { scan-assembler-times "vminps" 2 } } */ +/* { dg-final { scan-assembler-times "vmaxss" 2 } } */ +/* { dg-final { scan-assembler-times "vminss" 2 } } */ +/* { dg-final { scan-assembler-times "vmaxpd" 1 } } */ +/* { dg-final { scan-assembler-times "vminpd" 1 } } */ +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */ +/* { dg-final { scan-assembler-times "vminsd" 1 } } */ + +#include<math.h> +#define FOO(CODE,TYPE,SUFFIX) \ + void \ + foo_vect_##CODE##TYPE##SUFFIX (TYPE* __restrict a, TYPE* b, TYPE* c) \ + { \ + for (int i = 0; i != 8; i++) \ + a[i] = CODE##SUFFIX (b[i], c[i]); \ + } \ + TYPE \ + foo_##CODE##TYPE##SUFFIX (TYPE b, TYPE c) \ + { \ + return CODE##l (b, c); \ + } + +FOO (fmax, _Float16, f); +FOO (fmax, _Float16,); +FOO (fmax, _Float16, l); +FOO (fmin, _Float16, f); +FOO (fmin, _Float16,); +FOO (fmin, _Float16, l); + +FOO (fmax, float,); +FOO (fmax, float, l); +FOO (fmin, float,); +FOO (fmin, float, l); + +FOO (fmax, double, l); +FOO (fmin, double, l);
a and b are same type as trunc type and has less precision than extend type, the transformation is guarded by flag_finite_math_only. Bootstrapped and regtested under x86_64-pc-linux-gnu{-m32,} Ok for trunk? gcc/ChangeLog: PR target/102464 * match.pd: Simplify (trunc)fmax/fmin((extend)a, (extend)b) to MAX/MIN(a,b) gcc/testsuite/ChangeLog: * gcc.target/i386/pr102464-maxmin.c: New test. --- gcc/match.pd | 14 ++++++ .../gcc.target/i386/pr102464-maxmin.c | 44 +++++++++++++++++++ 2 files changed, 58 insertions(+) create mode 100644 gcc/testsuite/gcc.target/i386/pr102464-maxmin.c