On Wed, 2020-08-26 at 22:45 -0400, Michael Meissner via Gcc-patches wrote:
> PowerPC: Add power10 xsmaxcqp/xsmincqp support.
>
> This patch adds support for the ISA 3.1 (power10) IEEE 128-bit "C" minimum and
> maximum functions. Because of the NaN differences, the built-in functions
> will
> only generate these instructions if -ffast-math is used until the conditional
> move support is added in the next patch.
>
> I have built compilers on a little endian power9 Linux system with all 4
> patches applied. I did bootstrap builds and ran the testsuite, with no
> regressions. Previous versions of the patch was also tested on a little
> endian
> power8 Linux system. I would like to check this patch into the master branch
> for GCC 11. At this time, I do not anticipate needing to backport these
> changes to GCC 10.3.
>
>
> gcc/
> 2020-08-26 Michael Meissner <[email protected]>
>
* config/rs6000/rs6000.c (rs6000_emit_minmax): Add 128-bit
clause to if-check.
> * config/rs6000/rs6000.h (FLOAT128_IEEE_MINMAX_P): New helper
> macro.
ok
> * config/rs6000/rs6000.md (FSCALAR): New mode iterator for floating
> point scalars.
> (Fm): New mode attribute for floating point scalars.
Mixed feels on mixed case, but I defer. :-)
> (s<minmax><mode>): Add support for the ISA 3.1 IEEE 128-bit
> minimum and maximum instructions.
> (s<minmax><mode>3_vsx): Add support for the ISA 3.1 IEEE 128-bit
> minimum and maximum instructions.
>
> gcc/testsuite/
> 2020-08-26 Michael Meissner <[email protected]>
>
> * gcc.target/powerpc/float128-minmax-2.c: New test.
>
the rest lgtm,
thanks
-Will
> ---
> gcc/config/rs6000/rs6000.c | 3 +-
> gcc/config/rs6000/rs6000.h | 4 +++
> gcc/config/rs6000/rs6000.md | 28 +++++++++++++++----
> .../gcc.target/powerpc/float128-minmax-2.c | 15 ++++++++++
> 4 files changed, 43 insertions(+), 7 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/powerpc/float128-minmax-2.c
>
> diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
> index 6324f930628..05eb141a2cd 100644
> --- a/gcc/config/rs6000/rs6000.c
> +++ b/gcc/config/rs6000/rs6000.c
> @@ -15445,7 +15445,8 @@ rs6000_emit_minmax (rtx dest, enum rtx_code code, rtx
> op0, rtx op1)
> /* VSX/altivec have direct min/max insns. */
> if ((code == SMAX || code == SMIN)
> && (VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)
> - || (mode == SFmode && VECTOR_UNIT_VSX_P (DFmode))))
> + || (mode == SFmode && VECTOR_UNIT_VSX_P (DFmode))
> + || FLOAT128_IEEE_MINMAX_P (mode)))
> {
> emit_insn (gen_rtx_SET (dest, gen_rtx_fmt_ee (code, mode, op0, op1)));
> return;
> diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
> index bbd8060e143..b504aaa0199 100644
> --- a/gcc/config/rs6000/rs6000.h
> +++ b/gcc/config/rs6000/rs6000.h
> @@ -345,6 +345,10 @@ extern const char *host_detect_local_cpu (int argc,
> const char **argv);
> || ((MODE) == TDmode) \
> || (!TARGET_FLOAT128_TYPE && FLOAT128_IEEE_P (MODE)))
>
> +/* Macro whether the float128 min/max instructions are enabled. */
> +#define FLOAT128_IEEE_MINMAX_P(MODE) \
> + (TARGET_POWER10 && TARGET_FLOAT128_HW && FLOAT128_IEEE_P (MODE))
> +
> /* Return true for floating point that does not use a vector register. */
> #define SCALAR_FLOAT_MODE_NOT_VECTOR_P(MODE) \
> (SCALAR_FLOAT_MODE_P (MODE) && !FLOAT128_VECTOR_P (MODE))
> diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
> index 43b620ae1c0..006e60f09bc 100644
> --- a/gcc/config/rs6000/rs6000.md
> +++ b/gcc/config/rs6000/rs6000.md
> @@ -789,6 +789,18 @@ (define_code_attr minmax [(smin "min")
> (define_code_attr SMINMAX [(smin "SMIN")
> (smax "SMAX")])
>
> +;; Mode iterator for scalar binary floating point operations
> +(define_mode_iterator FSCALAR [SF
> + DF
> + (KF "FLOAT128_IEEE_MINMAX_P (KFmode)")
> + (TF "FLOAT128_IEEE_MINMAX_P (TFmode)")])
> +
> +;; Constraints to use for scalar FP operations
> +(define_mode_attr Fm [(SF "wa")
> + (DF "wa")
> + (TF "v")
> + (KF "v")])
> +
> ;; Iterator to optimize the following cases:
> ;; D-form load to FPR register & move to Altivec register
> ;; Move Altivec register to FPR register and store
> @@ -5142,9 +5154,9 @@ (define_insn "copysign<mode>3_fcpsgn"
> ;; to allow either DF/SF to use only traditional registers.
>
> (define_expand "s<minmax><mode>3"
> - [(set (match_operand:SFDF 0 "gpc_reg_operand")
> - (fp_minmax:SFDF (match_operand:SFDF 1 "gpc_reg_operand")
> - (match_operand:SFDF 2 "gpc_reg_operand")))]
> + [(set (match_operand:FSCALAR 0 "gpc_reg_operand")
> + (fp_minmax:FSCALAR (match_operand:FSCALAR 1 "gpc_reg_operand")
> + (match_operand:FSCALAR 2 "gpc_reg_operand")))]
> "TARGET_MINMAX"
> {
> rs6000_emit_minmax (operands[0], <SMINMAX>, operands[1], operands[2]);
> @@ -5152,11 +5164,15 @@ (define_expand "s<minmax><mode>3"
> })
>
> (define_insn "*s<minmax><mode>3_vsx"
> - [(set (match_operand:SFDF 0 "vsx_register_operand" "=<Fv>")
> - (fp_minmax:SFDF (match_operand:SFDF 1 "vsx_register_operand" "<Fv>")
> - (match_operand:SFDF 2 "vsx_register_operand" "<Fv>")))]
> + [(set (match_operand:FSCALAR 0 "vsx_register_operand" "=<Fm>")
> + (fp_minmax:FSCALAR
> + (match_operand:FSCALAR 1 "vsx_register_operand" "<Fm>")
> + (match_operand:FSCALAR 2 "vsx_register_operand" "<Fm>")))]
> "TARGET_VSX && TARGET_HARD_FLOAT"
> {
> + if (FLOAT128_IEEE_P (<MODE>mode))
> + return "xs<minmax>cqp %0,%1,%2";
> +
> return (TARGET_P9_MINMAX
> ? "xs<minmax>cdp %x0,%x1,%x2"
> : "xs<minmax>dp %x0,%x1,%x2");
> diff --git a/gcc/testsuite/gcc.target/powerpc/float128-minmax-2.c
> b/gcc/testsuite/gcc.target/powerpc/float128-minmax-2.c
> new file mode 100644
> index 00000000000..c71ba08c9f8
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/float128-minmax-2.c
> @@ -0,0 +1,15 @@
> +/* { dg-require-effective-target ppc_float128_hw } */
> +/* { dg-require-effective-target power10_ok } */
> +/* { dg-options "-mdejagnu-cpu=power10 -O2 -ffast-math" } */
> +
> +#ifndef TYPE
> +#define TYPE _Float128
> +#endif
> +
> +/* Test that the fminf128/fmaxf128 functions generate if/then/else and not a
> + call. */
> +TYPE f128_min (TYPE a, TYPE b) { return __builtin_fminf128 (a, b); }
> +TYPE f128_max (TYPE a, TYPE b) { return __builtin_fmaxf128 (a, b); }
> +
> +/* { dg-final { scan-assembler {\mxsmaxcqp\M} } } */
> +/* { dg-final { scan-assembler {\mxsmincqp\M} } } */
> --
> 2.22.0
>
>
