On Tue, Aug 10, 2021 at 2:13 PM liuhongt <[email protected]> wrote:
>
> Hi:
> AVX512F supported vscalefs{s,d} which is the same as ldexp except the
> second operand should be floating point.
> Bootstrapped and regtested on x86_64-linux-gnu{-m32,}.
>
> gcc/ChangeLog:
>
> PR target/98309
> * config/i386/i386.md (ldexp<mode>3): Extend to vscalefs[sd]
> when TARGET_AVX512F and TARGET_SSE_MATH.
>
> gcc/testsuite/ChangeLog:
>
> PR target/98309
> * gcc.target/i386/pr98309-1.c: New test.
> * gcc.target/i386/pr98309-2.c: New test.
OK.
Thanks,
Uros.
> ---
> gcc/config/i386/i386.md | 34 +++++++++++++++-----
> gcc/testsuite/gcc.target/i386/pr98309-1.c | 18 +++++++++++
> gcc/testsuite/gcc.target/i386/pr98309-2.c | 39 +++++++++++++++++++++++
> 3 files changed, 83 insertions(+), 8 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/i386/pr98309-1.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr98309-2.c
>
> diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
> index bc1c30b77f4..56b09c566ed 100644
> --- a/gcc/config/i386/i386.md
> +++ b/gcc/config/i386/i386.md
> @@ -17914,17 +17914,35 @@ (define_expand "ldexp<mode>3"
> [(use (match_operand:MODEF 0 "register_operand"))
> (use (match_operand:MODEF 1 "general_operand"))
> (use (match_operand:SI 2 "register_operand"))]
> - "TARGET_USE_FANCY_MATH_387
> - && (!(SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH)
> - || TARGET_MIX_SSE_I387)
> + "((TARGET_USE_FANCY_MATH_387
> + && (!(SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH)
> + || TARGET_MIX_SSE_I387))
> + || (TARGET_AVX512F && TARGET_SSE_MATH))
> && flag_unsafe_math_optimizations"
> {
> - rtx op0 = gen_reg_rtx (XFmode);
> - rtx op1 = gen_reg_rtx (XFmode);
> + /* Prefer avx512f version. */
> + if (TARGET_AVX512F && TARGET_SSE_MATH)
> + {
> + rtx op2 = gen_reg_rtx (<MODE>mode);
> + emit_insn (gen_floatsi<mode>2 (op2, operands[2]));
> + operands[0] = lowpart_subreg (<ssevecmodef>mode, operands[0],
> <MODE>mode);
> + if (MEM_P (operands[1]))
> + operands[1] = force_reg (<MODE>mode, operands[1]);
> + operands[1] = lowpart_subreg (<ssevecmodef>mode, operands[1],
> <MODE>mode);
> + op2 = lowpart_subreg (<ssevecmodef>mode, op2, <MODE>mode);
> + emit_insn (gen_avx512f_vmscalef<ssevecmodelower> (operands[0],
> + operands[1],
> + op2));
> + }
> + else
> + {
> + rtx op0 = gen_reg_rtx (XFmode);
> + rtx op1 = gen_reg_rtx (XFmode);
>
> - emit_insn (gen_extend<mode>xf2 (op1, operands[1]));
> - emit_insn (gen_ldexpxf3 (op0, op1, operands[2]));
> - emit_insn (gen_truncxf<mode>2 (operands[0], op0));
> + emit_insn (gen_extend<mode>xf2 (op1, operands[1]));
> + emit_insn (gen_ldexpxf3 (op0, op1, operands[2]));
> + emit_insn (gen_truncxf<mode>2 (operands[0], op0));
> + }
> DONE;
> })
>
> diff --git a/gcc/testsuite/gcc.target/i386/pr98309-1.c
> b/gcc/testsuite/gcc.target/i386/pr98309-1.c
> new file mode 100644
> index 00000000000..3a7afb58971
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr98309-1.c
> @@ -0,0 +1,18 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512f -O2 -mfpmath=sse -ffast-math" } */
> +/* { dg-final { scan-assembler-times "vcvtsi2s\[sd\]" "2" } } */
> +/* { dg-final { scan-assembler-times "vscalefs\[sd\]" "2" } } */
> +
> +double
> +__attribute__((noipa))
> +foo (double a, int b)
> +{
> + return __builtin_ldexp (a, b);
> +}
> +
> +float
> +__attribute__((noipa))
> +foo2 (float a, int b)
> +{
> + return __builtin_ldexpf (a, b);
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr98309-2.c
> b/gcc/testsuite/gcc.target/i386/pr98309-2.c
> new file mode 100644
> index 00000000000..ecfb9168b7d
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr98309-2.c
> @@ -0,0 +1,39 @@
> +/* { dg-do run } */
> +/* { dg-options "-mavx512f -O2 -mfpmath=sse -ffast-math" } */
> +/* { dg-require-effective-target avx512f } */
> +
> +#define AVX512F
> +#ifndef CHECK
> +#define CHECK "avx512f-helper.h"
> +#endif
> +
> +#include CHECK
> +
> +#include "pr98309-1.c"
> +
> +double
> +__attribute__((noipa, target("fpmath=387")))
> +foo_i387 (double a, int b)
> +{
> + return __builtin_ldexp (a, b);
> +}
> +
> +float
> +__attribute__((noipa, target("fpmath=387")))
> +foo2_i387 (float a, int b)
> +{
> + return __builtin_ldexpf (a, b);
> +}
> +
> +static void
> +test_512 (void)
> +{
> + float fa = 14.5;
> + double da = 44.5;
> + int fb = 12;
> + int db = 8;
> + if (foo_i387 (da, db) != foo (da, db))
> + abort ();
> + if (foo2_i387 (fa, fb) != foo2 (fa, fb))
> + abort ();
> +}
> --
> 2.27.0
>
