This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH v2, rs6000] Fold vector absolutes in GIMPLE
- From: Richard Biener <richard dot guenther at gmail dot com>
- To: will_schmidt at vnet dot ibm dot com
- Cc: GCC Patches <gcc-patches at gcc dot gnu dot org>, Segher Boessenkool <segher at kernel dot crashing dot org>, David Edelsohn <dje dot gcc at gmail dot com>, Bill Schmidt <wschmidt at linux dot vnet dot ibm dot com>
- Date: Thu, 1 Jun 2017 09:42:00 +0200
- Subject: Re: [PATCH v2, rs6000] Fold vector absolutes in GIMPLE
- Authentication-results: sourceware.org; auth=none
- References: <1496259495.15163.199.camel@brimstone.rchland.ibm.com>
On Wed, May 31, 2017 at 9:38 PM, Will Schmidt <will_schmidt@vnet.ibm.com> wrote:
> Hi,
>
> Add support for early expansion of vector absolute built-ins.
>
> [V2] Per reviews and feedback, skip the early folding for
> integral types based on a check against TYPE_OVERFLOW_WRAPS(arg0).
>
> Added test variants to exercise the -fwrapv option during
> this folding.
>
> OK for trunk? (bootstraps running, pending review).
Looks good to me now.
> [gcc]
>
> 2017-05-31 Will Schmidt <will_schmidt@vnet.ibm.com>
>
> * config/rs6000/rs6000.c (rs6000_gimple_fold_builtin): Add handling
> for early expansion of vector absolute builtins.
>
> [gcc/testsuite]
>
> 2017-05-31 Will Schmidt <will_schmidt@vnet.ibm.com>
>
> * gcc.target/powerpc/fold-vec-abs-char.c: New.
> * gcc.target/powerpc/fold-vec-abs-floatdouble.c: New.
> * gcc.target/powerpc/fold-vec-abs-int.c: New.
> * gcc.target/powerpc/fold-vec-abs-longlong.c: New.
> * gcc.target/powerpc/fold-vec-abs-short.c: New.
> * gcc.target/powerpc/fold-vec-abs-char-fwrapv.c: New.
> * gcc.target/powerpc/fold-vec-abs-int-fwrapv.c: New.
> * gcc.target/powerpc/fold-vec-abs-longlong-fwrapv.c: New.
> * gcc.target/powerpc/fold-vec-abs-short-fwrapv.c: New.
>
> diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
> index dac673c..46d281a 100644
> --- a/gcc/config/rs6000/rs6000.c
> +++ b/gcc/config/rs6000/rs6000.c
> @@ -17333,6 +17333,24 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
> gsi_replace (gsi, g, true);
> return true;
> }
> + /* flavors of vec_abs. */
> + case ALTIVEC_BUILTIN_ABS_V16QI:
> + case ALTIVEC_BUILTIN_ABS_V8HI:
> + case ALTIVEC_BUILTIN_ABS_V4SI:
> + case ALTIVEC_BUILTIN_ABS_V4SF:
> + case P8V_BUILTIN_ABS_V2DI:
> + case VSX_BUILTIN_XVABSDP:
> + {
> + arg0 = gimple_call_arg (stmt, 0);
> + if ( INTEGRAL_TYPE_P (TREE_TYPE (TREE_TYPE(arg0)))
> + && ! TYPE_OVERFLOW_WRAPS (TREE_TYPE (TREE_TYPE(arg0))))
> + return false;
> + lhs = gimple_call_lhs (stmt);
> + gimple *g = gimple_build_assign (lhs, ABS_EXPR, arg0);
> + gimple_set_location (g, gimple_location (stmt));
> + gsi_replace (gsi, g, true);
> + return true;
> + }
> default:
> break;
> }
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-char-fwrapv.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-char-fwrapv.c
> new file mode 100644
> index 0000000..739f06e
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-char-fwrapv.c
> @@ -0,0 +1,18 @@
> +/* Verify that overloaded built-ins for vec_abs with char
> + inputs produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_altivec_ok } */
> +/* { dg-options "-maltivec -O2 -fwrapv" } */
> +
> +#include <altivec.h>
> +
> +vector signed char
> +test2 (vector signed char x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "vspltisw|vxor" 1 } } */
> +/* { dg-final { scan-assembler-times "vsububm" 1 } } */
> +/* { dg-final { scan-assembler-times "vmaxsb" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-char.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-char.c
> new file mode 100644
> index 0000000..239c919
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-char.c
> @@ -0,0 +1,18 @@
> +/* Verify that overloaded built-ins for vec_abs with char
> + inputs produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_altivec_ok } */
> +/* { dg-options "-maltivec -O2" } */
> +
> +#include <altivec.h>
> +
> +vector signed char
> +test2 (vector signed char x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "vspltisw|vxor" 1 } } */
> +/* { dg-final { scan-assembler-times "vsububm" 1 } } */
> +/* { dg-final { scan-assembler-times "vmaxsb" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-floatdouble.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-floatdouble.c
> new file mode 100644
> index 0000000..1a08618
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-floatdouble.c
> @@ -0,0 +1,23 @@
> +/* Verify that overloaded built-ins for vec_abs with float and
> + double inputs for VSX produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_vsx_ok } */
> +/* { dg-options "-mvsx -O2" } */
> +
> +#include <altivec.h>
> +
> +vector float
> +test1 (vector float x)
> +{
> + return vec_abs (x);
> +}
> +
> +vector double
> +test2 (vector double x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "xvabssp" 1 } } */
> +/* { dg-final { scan-assembler-times "xvabsdp" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-int-fwrapv.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-int-fwrapv.c
> new file mode 100644
> index 0000000..34dead4
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-int-fwrapv.c
> @@ -0,0 +1,18 @@
> +/* Verify that overloaded built-ins for vec_abs with int
> + inputs produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_altivec_ok } */
> +/* { dg-options "-maltivec -O2 -fwrapv" } */
> +
> +#include <altivec.h>
> +
> +vector signed int
> +test1 (vector signed int x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "vspltisw|vxor" 1 } } */
> +/* { dg-final { scan-assembler-times "vsubuwm" 1 } } */
> +/* { dg-final { scan-assembler-times "vmaxsw" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-int.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-int.c
> new file mode 100644
> index 0000000..77d9ca5
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-int.c
> @@ -0,0 +1,18 @@
> +/* Verify that overloaded built-ins for vec_abs with int
> + inputs produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_altivec_ok } */
> +/* { dg-options "-maltivec -O2" } */
> +
> +#include <altivec.h>
> +
> +vector signed int
> +test1 (vector signed int x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "vspltisw|vxor" 1 } } */
> +/* { dg-final { scan-assembler-times "vsubuwm" 1 } } */
> +/* { dg-final { scan-assembler-times "vmaxsw" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-longlong-fwrapv.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-longlong-fwrapv.c
> new file mode 100644
> index 0000000..934618b
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-longlong-fwrapv.c
> @@ -0,0 +1,18 @@
> +/* Verify that overloaded built-ins for vec_abs with long long
> + inputs produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_p8vector_ok } */
> +/* { dg-options "-mpower8-vector -O2 -fwrapv" } */
> +
> +#include <altivec.h>
> +
> +vector signed long long
> +test3 (vector signed long long x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "vspltisw|vxor" 1 } } */
> +/* { dg-final { scan-assembler-times "vsubudm" 1 } } */
> +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-longlong.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-longlong.c
> new file mode 100644
> index 0000000..5b59d19
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-longlong.c
> @@ -0,0 +1,18 @@
> +/* Verify that overloaded built-ins for vec_abs with long long
> + inputs produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_p8vector_ok } */
> +/* { dg-options "-mpower8-vector -O2" } */
> +
> +#include <altivec.h>
> +
> +vector signed long long
> +test3 (vector signed long long x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "vspltisw|vxor" 1 } } */
> +/* { dg-final { scan-assembler-times "vsubudm" 1 } } */
> +/* { dg-final { scan-assembler-times "vmaxsd" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-short-fwrapv.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-short-fwrapv.c
> new file mode 100644
> index 0000000..2562179
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-short-fwrapv.c
> @@ -0,0 +1,18 @@
> +/* Verify that overloaded built-ins for vec_abs with short
> + inputs produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_altivec_ok } */
> +/* { dg-options "-maltivec -O2 -fwrapv" } */
> +
> +#include <altivec.h>
> +
> +vector signed short
> +test3 (vector signed short x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "vspltisw|vxor" 1 } } */
> +/* { dg-final { scan-assembler-times "vsubuhm" 1 } } */
> +/* { dg-final { scan-assembler-times "vmaxsh" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-short.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-short.c
> new file mode 100644
> index 0000000..d312000
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-abs-short.c
> @@ -0,0 +1,18 @@
> +/* Verify that overloaded built-ins for vec_abs with short
> + inputs produce the right results. */
> +
> +/* { dg-do compile } */
> +/* { dg-require-effective-target powerpc_altivec_ok } */
> +/* { dg-options "-maltivec -O2" } */
> +
> +#include <altivec.h>
> +
> +vector signed short
> +test3 (vector signed short x)
> +{
> + return vec_abs (x);
> +}
> +
> +/* { dg-final { scan-assembler-times "vspltisw|vxor" 1 } } */
> +/* { dg-final { scan-assembler-times "vsubuhm" 1 } } */
> +/* { dg-final { scan-assembler-times "vmaxsh" 1 } } */
>
>