On Mon, Jun 20, 2016 at 9:35 PM, Ilya Verbin <iver...@gmail.com> wrote:
> Hi!
>
> This patch emits vrsqrt28ps instruction in ix86_emit_swsqrtsf for recip case
> and
> vrcp28ps(vrsqrt28ps(a)) for !recip.
> Regtested using various benchmarks on a AVX-512ER machine. OK for trunk?
>
>
> gcc/
> * config/i386/i386.c (ix86_emit_swsqrtsf): Emit vrsqrt28ps.
> * config/i386/sse.md (define_expand "rsqrtv16sf2"): New.
> gcc/testsuite/
> * gcc.target/i386/avx512er-vrsqrt28ps-3.c: New test.
> * gcc.target/i386/avx512er-vrsqrt28ps-4.c: New test.
> * gcc.target/i386/avx512er-vrsqrt28ps-5.c: New test.
> * gcc.target/i386/avx512er-vrsqrt28ps-6.c: New test.
OK.
Thanks,
Uros.
>
> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
> index 8e0bf26..edd3d23 100644
> --- a/gcc/config/i386/i386.c
> +++ b/gcc/config/i386/i386.c
> @@ -48722,6 +48722,24 @@ void ix86_emit_swsqrtsf (rtx res, rtx a,
> machine_mode mode, bool recip)
> e2 = gen_reg_rtx (mode);
> e3 = gen_reg_rtx (mode);
>
> + if (TARGET_AVX512ER && mode == V16SFmode)
> + {
> + if (recip)
> + /* res = rsqrt28(a) estimate */
> + emit_insn (gen_rtx_SET (res, gen_rtx_UNSPEC (mode, gen_rtvec (1, a),
> + UNSPEC_RSQRT28)));
> + else
> + {
> + /* x0 = rsqrt28(a) estimate */
> + emit_insn (gen_rtx_SET (x0, gen_rtx_UNSPEC (mode, gen_rtvec (1, a),
> + UNSPEC_RSQRT28)));
> + /* res = rcp28(x0) estimate */
> + emit_insn (gen_rtx_SET (res, gen_rtx_UNSPEC (mode, gen_rtvec (1,
> x0),
> + UNSPEC_RCP28)));
> + }
> + return;
> + }
> +
> real_from_integer (&r, VOIDmode, -3, SIGNED);
> mthree = const_double_from_real_value (r, SFmode);
>
> diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
> index 6056ddc..c1ea04f 100644
> --- a/gcc/config/i386/sse.md
> +++ b/gcc/config/i386/sse.md
> @@ -1559,6 +1559,17 @@
> DONE;
> })
>
> +(define_expand "rsqrtv16sf2"
> + [(set (match_operand:V16SF 0 "register_operand")
> + (unspec:V16SF
> + [(match_operand:V16SF 1 "vector_operand")]
> + UNSPEC_RSQRT28))]
> + "TARGET_SSE_MATH && TARGET_AVX512ER"
> +{
> + ix86_emit_swsqrtsf (operands[0], operands[1], V16SFmode, true);
> + DONE;
> +})
> +
> (define_insn "<sse>_rsqrt<mode>2"
> [(set (match_operand:VF1_128_256 0 "register_operand" "=x")
> (unspec:VF1_128_256
> diff --git a/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-3.c
> b/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-3.c
> new file mode 100644
> index 0000000..1ba8172
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-3.c
> @@ -0,0 +1,47 @@
> +/* { dg-do run } */
> +/* { dg-require-effective-target avx512er } */
> +/* { dg-options "-O2 -ffast-math -ftree-vectorize -mavx512er" } */
> +
> +#include <math.h>
> +#include "avx512er-check.h"
> +
> +#define MAX 1000
> +#define EPS 0.00001
> +
> +__attribute__ ((noinline, optimize (1)))
> +void static
> +compute_rsqrt_ref (float *a, float *r)
> +{
> + for (int i = 0; i < MAX; i++)
> + r[i] = 1.0 / sqrtf (a[i]);
> +}
> +
> +__attribute__ ((noinline))
> +void static
> +compute_rsqrt_exp (float *a, float *r)
> +{
> + for (int i = 0; i < MAX; i++)
> + r[i] = 1.0 / sqrtf (a[i]);
> +}
> +
> +void static
> +avx512er_test (void)
> +{
> + float in[MAX];
> + float ref[MAX];
> + float exp[MAX];
> +
> + for (int i = 0; i < MAX; i++)
> + in[i] = 8765.987 - 8.6756 * i;
> +
> + compute_rsqrt_ref (in, ref);
> + compute_rsqrt_exp (in, exp);
> +
> + for (int i = 0; i < MAX; i++)
> + {
> + float rel_err = (ref[i] - exp[i]) / ref[i];
> + rel_err = rel_err > 0.0 ? rel_err : -rel_err;
> + if (rel_err > EPS)
> + abort ();
> + }
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-4.c
> b/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-4.c
> new file mode 100644
> index 0000000..2f5f73f
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-4.c
> @@ -0,0 +1,7 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -ffast-math -ftree-vectorize -mavx512er" } */
> +
> +#include "avx512er-vrsqrt28ps-3.c"
> +
> +/* { dg-final { scan-assembler-times
> "vrsqrt28ps\[^\n\r\]*zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
> +/* { dg-final { scan-assembler-not "vrcp28ps\[^\n\r\]*zmm\[0-9\]+(?:\n|\[
> \\t\]+#)" } } */
> diff --git a/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-5.c
> b/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-5.c
> new file mode 100644
> index 0000000..e067a81
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-5.c
> @@ -0,0 +1,47 @@
> +/* { dg-do run } */
> +/* { dg-require-effective-target avx512er } */
> +/* { dg-options "-O2 -ffast-math -ftree-vectorize -mavx512er" } */
> +
> +#include <math.h>
> +#include "avx512er-check.h"
> +
> +#define MAX 1000
> +#define EPS 0.00001
> +
> +__attribute__ ((noinline, optimize (1)))
> +void static
> +compute_sqrt_ref (float *a, float *r)
> +{
> + for (int i = 0; i < MAX; i++)
> + r[i] = sqrtf (a[i]);
> +}
> +
> +__attribute__ ((noinline))
> +void static
> +compute_sqrt_exp (float *a, float *r)
> +{
> + for (int i = 0; i < MAX; i++)
> + r[i] = sqrtf (a[i]);
> +}
> +
> +void static
> +avx512er_test (void)
> +{
> + float in[MAX];
> + float ref[MAX];
> + float exp[MAX];
> +
> + for (int i = 0; i < MAX; i++)
> + in[i] = 8765.987 - 8.6756 * i;
> +
> + compute_sqrt_ref (in, ref);
> + compute_sqrt_exp (in, exp);
> +
> + for (int i = 0; i < MAX; i++)
> + {
> + float rel_err = (ref[i] - exp[i]) / ref[i];
> + rel_err = rel_err > 0.0 ? rel_err : -rel_err;
> + if (rel_err > EPS)
> + abort ();
> + }
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-6.c
> b/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-6.c
> new file mode 100644
> index 0000000..77c5cba
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ps-6.c
> @@ -0,0 +1,7 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -ffast-math -ftree-vectorize -mavx512er" } */
> +
> +#include "avx512er-vrsqrt28ps-5.c"
> +
> +/* { dg-final { scan-assembler-times
> "vrsqrt28ps\[^\n\r\]*zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
> +/* { dg-final { scan-assembler-times "vrcp28ps\[^\n\r\]*zmm\[0-9\]+(?:\n|\[
> \\t\]+#)" 1 } } */
>
>
> -- Ilya
