[3/3,APX,CCMP] Support ccmp for float compare

The ccmp insn itself doesn't support fp compare, but x86 has fp comi
insn that changes EFLAG which can be the scc input to ccmp. Allow
scalar fp compare in ix86_gen_ccmp_first except ORDERED/UNORDERD
compare which can not be identified in ccmp.

gcc/ChangeLog:

	* config/i386/i386-expand.cc (ix86_gen_ccmp_first): Add fp
	compare and check the allowed fp compare type.
	(ix86_gen_ccmp_next): Adjust compare_code input to ccmp for
	fp compare.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/apx-ccmp-1.c: Add test for fp compare.
	* gcc.target/i386/apx-ccmp-2.c: Likewise.
---
 gcc/config/i386/i386-expand.cc             | 53 ++++++++++++++++++++--
 gcc/testsuite/gcc.target/i386/apx-ccmp-1.c | 45 +++++++++++++++++-
 gcc/testsuite/gcc.target/i386/apx-ccmp-2.c | 47 +++++++++++++++++++
 3 files changed, 138 insertions(+), 7 deletions(-)

On Wed, May 15, 2024 at 4:21 PM Hongyu Wang <hongyu.wang@intel.com> wrote:
>
> The ccmp insn itself doesn't support fp compare, but x86 has fp comi
> insn that changes EFLAG which can be the scc input to ccmp. Allow
> scalar fp compare in ix86_gen_ccmp_first except ORDERED/UNORDERD
> compare which can not be identified in ccmp.
Ok if the second patch(middle-end part) is approved.
>
> gcc/ChangeLog:
>
>         * config/i386/i386-expand.cc (ix86_gen_ccmp_first): Add fp
>         compare and check the allowed fp compare type.
>         (ix86_gen_ccmp_next): Adjust compare_code input to ccmp for
>         fp compare.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.target/i386/apx-ccmp-1.c: Add test for fp compare.
>         * gcc.target/i386/apx-ccmp-2.c: Likewise.
> ---
>  gcc/config/i386/i386-expand.cc             | 53 ++++++++++++++++++++--
>  gcc/testsuite/gcc.target/i386/apx-ccmp-1.c | 45 +++++++++++++++++-
>  gcc/testsuite/gcc.target/i386/apx-ccmp-2.c | 47 +++++++++++++++++++
>  3 files changed, 138 insertions(+), 7 deletions(-)
>
> diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
> index f00525e449f..7507034dc91 100644
> --- a/gcc/config/i386/i386-expand.cc
> +++ b/gcc/config/i386/i386-expand.cc
> @@ -25571,18 +25571,58 @@ ix86_gen_ccmp_first (rtx_insn **prep_seq, rtx_insn **gen_seq,
>    if (op_mode == VOIDmode)
>      op_mode = GET_MODE (op1);
>
> +  /* We only supports following scalar comparisons that use just 1
> +     instruction: DI/SI/QI/HI/DF/SF/HF.
> +     Unordered/Ordered compare cannot be corretly indentified by
> +     ccmp so they are not supported.  */
>    if (!(op_mode == DImode || op_mode == SImode || op_mode == HImode
> -       || op_mode == QImode))
> +       || op_mode == QImode || op_mode == DFmode || op_mode == SFmode
> +       || op_mode == HFmode)
> +      || code == ORDERED
> +      || code == UNORDERED)
>      {
>        end_sequence ();
>        return NULL_RTX;
>      }
>
>    /* Canonicalize the operands according to mode.  */
> -  if (!nonimmediate_operand (op0, op_mode))
> -    op0 = force_reg (op_mode, op0);
> -  if (!x86_64_general_operand (op1, op_mode))
> -    op1 = force_reg (op_mode, op1);
> +  if (SCALAR_INT_MODE_P (op_mode))
> +    {
> +      if (!nonimmediate_operand (op0, op_mode))
> +       op0 = force_reg (op_mode, op0);
> +      if (!x86_64_general_operand (op1, op_mode))
> +       op1 = force_reg (op_mode, op1);
> +    }
> +  else
> +    {
> +      /* op0/op1 can be canonicallized from expand_fp_compare, so
> +        just adjust the code to make it generate supported fp
> +        condition.  */
> +      if (ix86_fp_compare_code_to_integer (code) == UNKNOWN)
> +       {
> +         /* First try to split condition if we don't need to honor
> +            NaNs, as the ORDERED/UNORDERED check always fall
> +            through.  */
> +         if (!HONOR_NANS (op_mode))
> +           {
> +             rtx_code first_code;
> +             split_comparison (code, op_mode, &first_code, &code);
> +           }
> +         /* Otherwise try to swap the operand order and check if
> +            the comparison is supported.  */
> +         else
> +           {
> +             code = swap_condition (code);
> +             std::swap (op0, op1);
> +           }
> +
> +         if (ix86_fp_compare_code_to_integer (code) == UNKNOWN)
> +           {
> +             end_sequence ();
> +             return NULL_RTX;
> +           }
> +       }
> +    }
>
>    *prep_seq = get_insns ();
>    end_sequence ();
> @@ -25647,6 +25687,9 @@ ix86_gen_ccmp_next (rtx_insn **prep_seq, rtx_insn **gen_seq, rtx prev,
>    dfv = ix86_get_flags_cc ((rtx_code) cmp_code);
>
>    prev_code = GET_CODE (prev);
> +  /* Fixup FP compare code here.  */
> +  if (GET_MODE (XEXP (prev, 0)) == CCFPmode)
> +    prev_code = ix86_fp_compare_code_to_integer (prev_code);
>
>    if (bit_code != AND)
>      prev_code = reverse_condition (prev_code);
> diff --git a/gcc/testsuite/gcc.target/i386/apx-ccmp-1.c b/gcc/testsuite/gcc.target/i386/apx-ccmp-1.c
> index 5a2dad89f1f..e4e112f07e0 100644
> --- a/gcc/testsuite/gcc.target/i386/apx-ccmp-1.c
> +++ b/gcc/testsuite/gcc.target/i386/apx-ccmp-1.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile { target { ! ia32 } } } */
> -/* { dg-options "-O2 -mapx-features=ccmp" } */
> +/* { dg-options "-O2 -ffast-math -mapx-features=ccmp" } */
>
>  int
>  f1 (int a)
> @@ -56,8 +56,49 @@ f9 (int a, int b)
>    return a == 3 || a == 0;
>  }
>
> +int
> +f10 (float a, int b, float c)
> +{
> +  return a > c || b < 19;
> +}
> +
> +int
> +f11 (float a, int b)
> +{
> +  return a == 0.0 && b > 21;
> +}
> +
> +int
> +f12 (double a, int b)
> +{
> +  return a < 3.0 && b != 23;
> +}
> +
> +int
> +f13 (double a, double b, int c, int d)
> +{
> +  a += b;
> +  c += d;
> +  return a != b || c == d;
> +}
> +
> +int
> +f14 (double a, int b)
> +{
> +  return b != 0 && a < 1.5;
> +}
> +
> +int
> +f15 (double a, double b, int c, int d)
> +{
> +  return c != d || a <= b;
> +}
> +
>  /* { dg-final { scan-assembler-times "ccmpg" 2 } } */
>  /* { dg-final { scan-assembler-times "ccmple" 2 } } */
>  /* { dg-final { scan-assembler-times "ccmpne" 4 } } */
> -/* { dg-final { scan-assembler-times "ccmpe" 1 } } */
> +/* { dg-final { scan-assembler-times "ccmpe" 3 } } */
> +/* { dg-final { scan-assembler-times "ccmpbe" 1 } } */
> +/* { dg-final { scan-assembler-times "ccmpa" 1 } } */
> +/* { dg-final { scan-assembler-times "ccmpbl" 2 } } */
>
> diff --git a/gcc/testsuite/gcc.target/i386/apx-ccmp-2.c b/gcc/testsuite/gcc.target/i386/apx-ccmp-2.c
> index 30a1c216c1b..0123a686d2c 100644
> --- a/gcc/testsuite/gcc.target/i386/apx-ccmp-2.c
> +++ b/gcc/testsuite/gcc.target/i386/apx-ccmp-2.c
> @@ -42,6 +42,47 @@ int foo_noapx(int a, int b, int c, int d)
>    return sum;
>  }
>
> +__attribute__((noinline, noclone,
> +              optimize(("finite-math-only")), target("apxf")))
> +double foo_fp_apx(int a, double b, int c, double d)
> +{
> +  int sum = a;
> +  double sumd = b;
> +
> +  if (a != c)
> +    {
> +      sum += a;
> +      if (a < c || sumd != d || sum > c)
> +       {
> +         c += a;
> +         sum += a + c;
> +       }
> +    }
> +
> +  return sum + sumd;
> +}
> +
> +__attribute__((noinline, noclone,
> +              optimize(("finite-math-only")), target("no-apxf")))
> +double foo_fp_noapx(int a, double b, int c, double d)
> +{
> +  int sum = a;
> +  double sumd = b;
> +
> +  if (a != c)
> +    {
> +      sum += a;
> +      if (a < c || sumd != d || sum > c)
> +       {
> +         c += a;
> +         sum += a + c;
> +       }
> +    }
> +
> +  return sum + sumd;
> +}
> +
> +
>  int main (void)
>  {
>    if (!__builtin_cpu_supports ("apxf"))
> @@ -53,5 +94,11 @@ int main (void)
>    if (val1 != val2)
>      __builtin_abort ();
>
> +  double val3 = foo_fp_noapx (24, 7.5, 32, 2.0);
> +  double val4 = foo_fp_apx (24, 7.5, 32, 2.0);
> +
> +  if (val3 != val4)
> +    __builtin_abort ();
> +
>    return 0;
>  }
> --
> 2.31.1
>