[PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Alan Lawrence]

This lets the vectorizer handle some simple strides expressed using left-shift
rather than mul, e.g. a[i << 1] (whereas previously only a[i * 2] would have
been handled).

This patch does *not* handle the general case of shifts - neither a[i << j]
nor a[1 << i] will be handled; that would be a significantly bigger patch
(probably duplicating or generalizing much of chrec_fold_multiply and
chrec_fold_multiply_poly_poly in tree-chrec.c), and would probably also only
be applicable to machines with gather-load support.

Bootstrapped+check-gcc,g++,gfortran on x86_64, AArch64 and ARM, also Ada on x86_64.

Is this OK for trunk?

gcc/ChangeLog:

	PR tree-optimization/65963
	* tree-scalar-evolution.c (interpret_rhs_expr): Handle some LSHIFT_EXPRs
	as equivalent MULT_EXPRs.

gcc/testsuite/ChangeLog:

	* gcc.dg/vect/vect-strided-shift-1.c: New.
---
 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
 gcc/tree-scalar-evolution.c                      | 18 +++++++++++++
 2 files changed, 51 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c

diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
new file mode 100644
index 0000000..b1ce2ec
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
@@ -0,0 +1,33 @@
+/* PR tree-optimization/65963.  */
+#include "tree-vect.h"
+
+#define N 512
+
+int in[2*N], out[N];
+
+__attribute__ ((noinline)) void
+loop (void)
+{
+  for (int i = 0; i < N; i++)
+    out[i] = in[i << 1] + 7;
+}
+
+int
+main (int argc, char **argv)
+{
+  check_vect ();
+  for (int i = 0; i < 2*N; i++)
+    {
+      in[i] = i;
+      __asm__ volatile ("" : : : "memory");
+    }
+  loop ();
+  __asm__ volatile ("" : : : "memory");
+  for (int i = 0; i < N; i++)
+    {
+      if (out[i] != i*2 + 7)
+	abort ();
+    }
+  return 0;
+}
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
index 0753bf3..e478b0e 100644
--- a/gcc/tree-scalar-evolution.c
+++ b/gcc/tree-scalar-evolution.c
@@ -1831,12 +1831,30 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
       break;
 
     case MULT_EXPR:
+    case LSHIFT_EXPR:
+      /* Handle A<<B as A * (1<<B).  */
       chrec1 = analyze_scalar_evolution (loop, rhs1);
       chrec2 = analyze_scalar_evolution (loop, rhs2);
       chrec1 = chrec_convert (type, chrec1, at_stmt);
       chrec2 = chrec_convert (type, chrec2, at_stmt);
       chrec1 = instantiate_parameters (loop, chrec1);
       chrec2 = instantiate_parameters (loop, chrec2);
+      if (code == LSHIFT_EXPR)
+	{
+	  /* Do the shift in the larger size, as in e.g. (long) << (int)32,
+	     we must do 1<<32 as a long or we'd overflow.  */
+	  tree type = TREE_TYPE (chrec2);
+	  if (TYPE_PRECISION (TREE_TYPE (chrec1)) > TYPE_PRECISION (type))
+	    type = TREE_TYPE (chrec1);
+	  if (TYPE_PRECISION (type) == 0)
+	    {
+	      res = chrec_dont_know;
+	      break;
+	    }
+	  chrec2 = fold_build2 (LSHIFT_EXPR, type,
+				build_int_cst (type, 1),
+				chrec2);
+	}
       res = chrec_fold_multiply (type, chrec1, chrec2);
       break;
 
-- 
1.9.1

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Richard Biener]

On Fri, Oct 16, 2015 at 5:25 PM, Alan Lawrence <alan.lawrence@arm.com> wrote:
> This lets the vectorizer handle some simple strides expressed using left-shift
> rather than mul, e.g. a[i << 1] (whereas previously only a[i * 2] would have
> been handled).
>
> This patch does *not* handle the general case of shifts - neither a[i << j]
> nor a[1 << i] will be handled; that would be a significantly bigger patch
> (probably duplicating or generalizing much of chrec_fold_multiply and
> chrec_fold_multiply_poly_poly in tree-chrec.c), and would probably also only
> be applicable to machines with gather-load support.
>
> Bootstrapped+check-gcc,g++,gfortran on x86_64, AArch64 and ARM, also Ada on x86_64.
>
> Is this OK for trunk?
>
> gcc/ChangeLog:
>
>         PR tree-optimization/65963
>         * tree-scalar-evolution.c (interpret_rhs_expr): Handle some LSHIFT_EXPRs
>         as equivalent MULT_EXPRs.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.dg/vect/vect-strided-shift-1.c: New.
> ---
>  gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
>  gcc/tree-scalar-evolution.c                      | 18 +++++++++++++
>  2 files changed, 51 insertions(+)
>  create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
>
> diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
> new file mode 100644
> index 0000000..b1ce2ec
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
> @@ -0,0 +1,33 @@
> +/* PR tree-optimization/65963.  */
> +#include "tree-vect.h"
> +
> +#define N 512
> +
> +int in[2*N], out[N];
> +
> +__attribute__ ((noinline)) void
> +loop (void)
> +{
> +  for (int i = 0; i < N; i++)
> +    out[i] = in[i << 1] + 7;
> +}
> +
> +int
> +main (int argc, char **argv)
> +{
> +  check_vect ();
> +  for (int i = 0; i < 2*N; i++)
> +    {
> +      in[i] = i;
> +      __asm__ volatile ("" : : : "memory");
> +    }
> +  loop ();
> +  __asm__ volatile ("" : : : "memory");
> +  for (int i = 0; i < N; i++)
> +    {
> +      if (out[i] != i*2 + 7)
> +       abort ();
> +    }
> +  return 0;
> +}
> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
> diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
> index 0753bf3..e478b0e 100644
> --- a/gcc/tree-scalar-evolution.c
> +++ b/gcc/tree-scalar-evolution.c
> @@ -1831,12 +1831,30 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
>        break;
>
>      case MULT_EXPR:
> +    case LSHIFT_EXPR:
> +      /* Handle A<<B as A * (1<<B).  */
>        chrec1 = analyze_scalar_evolution (loop, rhs1);
>        chrec2 = analyze_scalar_evolution (loop, rhs2);
>        chrec1 = chrec_convert (type, chrec1, at_stmt);
>        chrec2 = chrec_convert (type, chrec2, at_stmt);
>        chrec1 = instantiate_parameters (loop, chrec1);
>        chrec2 = instantiate_parameters (loop, chrec2);
> +      if (code == LSHIFT_EXPR)
> +       {
> +         /* Do the shift in the larger size, as in e.g. (long) << (int)32,
> +            we must do 1<<32 as a long or we'd overflow.  */

Err, you should always do the shift in the type of rhs1.  You should also
avoid the chrec_convert of rhs2 above for shifts.  I think globbing
shifts and multiplies together doesn't make the code any clearer.

Richard.

> +         tree type = TREE_TYPE (chrec2);
> +         if (TYPE_PRECISION (TREE_TYPE (chrec1)) > TYPE_PRECISION (type))
> +           type = TREE_TYPE (chrec1);
> +         if (TYPE_PRECISION (type) == 0)
> +           {
> +             res = chrec_dont_know;
> +             break;
> +           }
> +         chrec2 = fold_build2 (LSHIFT_EXPR, type,
> +                               build_int_cst (type, 1),
> +                               chrec2);
> +       }
>        res = chrec_fold_multiply (type, chrec1, chrec2);
>        break;
>
> --
> 1.9.1
>

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Alan Lawrence]

On 19/10/15 12:49, Richard Biener wrote:

> Err, you should always do the shift in the type of rhs1.  You should also
> avoid the chrec_convert of rhs2 above for shifts.

Err, yes, indeed.  Needed to keep the chrec_convert before the
chrec_fold_multiply, and the rest followed.  How's this?

Bootstrapped+check-gcc,g++ on x86, ARM, AArch64.

gcc/ChangeLog (as before):

	PR tree-optimization/65963
	* tree-scalar-evolution.c (interpret_rhs_expr): Handle some LSHIFT_EXPRs
	as equivalent MULT_EXPRs.

gcc/testsuite/ChangeLog:

	* gcc.dg/vect/vect-strided-shift-1.c: New.
---
 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
 gcc/tree-scalar-evolution.c                      | 15 +++++++++++
 2 files changed, 48 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c

diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
new file mode 100644
index 0000000..b1ce2ec
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
@@ -0,0 +1,33 @@
+/* PR tree-optimization/65963.  */
+#include "tree-vect.h"
+
+#define N 512
+
+int in[2*N], out[N];
+
+__attribute__ ((noinline)) void
+loop (void)
+{
+  for (int i = 0; i < N; i++)
+    out[i] = in[i << 1] + 7;
+}
+
+int
+main (int argc, char **argv)
+{
+  check_vect ();
+  for (int i = 0; i < 2*N; i++)
+    {
+      in[i] = i;
+      __asm__ volatile ("" : : : "memory");
+    }
+  loop ();
+  __asm__ volatile ("" : : : "memory");
+  for (int i = 0; i < N; i++)
+    {
+      if (out[i] != i*2 + 7)
+	abort ();
+    }
+  return 0;
+}
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
index 0753bf3..129682f 100644
--- a/gcc/tree-scalar-evolution.c
+++ b/gcc/tree-scalar-evolution.c
@@ -1840,6 +1840,21 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
       res = chrec_fold_multiply (type, chrec1, chrec2);
       break;
 
+    case LSHIFT_EXPR:
+      /* Handle A<<B as A * (1<<B).  */
+      chrec1 = analyze_scalar_evolution (loop, rhs1);
+      chrec2 = analyze_scalar_evolution (loop, rhs2);
+      chrec1 = chrec_convert (type, chrec1, at_stmt);
+      chrec1 = instantiate_parameters (loop, chrec1);
+      chrec2 = instantiate_parameters (loop, chrec2);
+
+      chrec2 = fold_build2 (LSHIFT_EXPR, TREE_TYPE (rhs1),
+			    build_int_cst (TREE_TYPE (rhs1), 1),
+			    chrec2);
+      chrec2 = chrec_convert (type, chrec2, at_stmt);
+      res = chrec_fold_multiply (type, chrec1, chrec2);
+      break;
+
     CASE_CONVERT:
       /* In case we have a truncation of a widened operation that in
          the truncated type has undefined overflow behavior analyze
-- 
1.9.1

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Richard Biener]

On Fri, Oct 23, 2015 at 5:15 PM, Alan Lawrence <alan.lawrence@arm.com> wrote:
> On 19/10/15 12:49, Richard Biener wrote:
>
>> Err, you should always do the shift in the type of rhs1.  You should also
>> avoid the chrec_convert of rhs2 above for shifts.
>
> Err, yes, indeed.  Needed to keep the chrec_convert before the
> chrec_fold_multiply, and the rest followed.  How's this?
>
> Bootstrapped+check-gcc,g++ on x86, ARM, AArch64.
>
> gcc/ChangeLog (as before):
>
>         PR tree-optimization/65963
>         * tree-scalar-evolution.c (interpret_rhs_expr): Handle some LSHIFT_EXPRs
>         as equivalent MULT_EXPRs.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.dg/vect/vect-strided-shift-1.c: New.
> ---
>  gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
>  gcc/tree-scalar-evolution.c                      | 15 +++++++++++
>  2 files changed, 48 insertions(+)
>  create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
>
> diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
> new file mode 100644
> index 0000000..b1ce2ec
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
> @@ -0,0 +1,33 @@
> +/* PR tree-optimization/65963.  */
> +#include "tree-vect.h"
> +
> +#define N 512
> +
> +int in[2*N], out[N];
> +
> +__attribute__ ((noinline)) void
> +loop (void)
> +{
> +  for (int i = 0; i < N; i++)
> +    out[i] = in[i << 1] + 7;
> +}
> +
> +int
> +main (int argc, char **argv)
> +{
> +  check_vect ();
> +  for (int i = 0; i < 2*N; i++)
> +    {
> +      in[i] = i;
> +      __asm__ volatile ("" : : : "memory");
> +    }
> +  loop ();
> +  __asm__ volatile ("" : : : "memory");
> +  for (int i = 0; i < N; i++)
> +    {
> +      if (out[i] != i*2 + 7)
> +       abort ();
> +    }
> +  return 0;
> +}
> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
> diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
> index 0753bf3..129682f 100644
> --- a/gcc/tree-scalar-evolution.c
> +++ b/gcc/tree-scalar-evolution.c
> @@ -1840,6 +1840,21 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
>        res = chrec_fold_multiply (type, chrec1, chrec2);
>        break;
>
> +    case LSHIFT_EXPR:
> +      /* Handle A<<B as A * (1<<B).  */
> +      chrec1 = analyze_scalar_evolution (loop, rhs1);
> +      chrec2 = analyze_scalar_evolution (loop, rhs2);
> +      chrec1 = chrec_convert (type, chrec1, at_stmt);
> +      chrec1 = instantiate_parameters (loop, chrec1);
> +      chrec2 = instantiate_parameters (loop, chrec2);
> +      chrec2 = fold_build2 (LSHIFT_EXPR, TREE_TYPE (rhs1),
> +                           build_int_cst (TREE_TYPE (rhs1), 1),

'type' instead of TREE_TYPE (rhs1)

> +                           chrec2);
> +      chrec2 = chrec_convert (type, chrec2, at_stmt);

so you can remove this chrec_convert.

Ok with that change.

Richard.

> +      res = chrec_fold_multiply (type, chrec1, chrec2);
> +      break;
> +
>      CASE_CONVERT:
>        /* In case we have a truncation of a widened operation that in
>           the truncated type has undefined overflow behavior analyze
> --
> 1.9.1
>

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Alan Lawrence]

--in-reply-to <CAFiYyc3TePGbER2Jqc8-X_ij4GHtjjoxfzFFcNYzHxhGQbE0iQ@mail.gmail.com>

On 26/10/15 08:58, Richard Biener wrote:
>
> On Fri, Oct 23, 2015 at 5:15 PM, Alan Lawrence <alan.lawrence@arm.com> wrote:
>> +      chrec2 = fold_build2 (LSHIFT_EXPR, TREE_TYPE (rhs1),
>> +                           build_int_cst (TREE_TYPE (rhs1), 1),
>
> 'type' instead of TREE_TYPE (rhs1)

I presume you mean the first of the two (allowing removal of the chrec_convert),
and that I keep the second TREE_TYPE (rhs1), consistent with your previous
observation that I should do the multiply in the type of rhs1. (This appears
correct looking at e.g. gcc.target/i386/avx2-vpsllwi-2.c)

Hence, I've committed the attached as r229437.

Thanks, Alan
---
 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
 gcc/tree-scalar-evolution.c                      | 14 ++++++++++
 2 files changed, 47 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c

diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
new file mode 100644
index 0000000..b1ce2ec
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
@@ -0,0 +1,33 @@
+/* PR tree-optimization/65963.  */
+#include "tree-vect.h"
+
+#define N 512
+
+int in[2*N], out[N];
+
+__attribute__ ((noinline)) void
+loop (void)
+{
+  for (int i = 0; i < N; i++)
+    out[i] = in[i << 1] + 7;
+}
+
+int
+main (int argc, char **argv)
+{
+  check_vect ();
+  for (int i = 0; i < 2*N; i++)
+    {
+      in[i] = i;
+      __asm__ volatile ("" : : : "memory");
+    }
+  loop ();
+  __asm__ volatile ("" : : : "memory");
+  for (int i = 0; i < N; i++)
+    {
+      if (out[i] != i*2 + 7)
+	abort ();
+    }
+  return 0;
+}
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
index 0753bf3..8e95ddd 100644
--- a/gcc/tree-scalar-evolution.c
+++ b/gcc/tree-scalar-evolution.c
@@ -1840,6 +1840,20 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
       res = chrec_fold_multiply (type, chrec1, chrec2);
       break;
 
+    case LSHIFT_EXPR:
+      /* Handle A<<B as A * (1<<B).  */
+      chrec1 = analyze_scalar_evolution (loop, rhs1);
+      chrec2 = analyze_scalar_evolution (loop, rhs2);
+      chrec1 = chrec_convert (type, chrec1, at_stmt);
+      chrec1 = instantiate_parameters (loop, chrec1);
+      chrec2 = instantiate_parameters (loop, chrec2);
+
+      chrec2 = fold_build2 (LSHIFT_EXPR, type,
+			    build_int_cst (TREE_TYPE (rhs1), 1),
+			    chrec2);
+      res = chrec_fold_multiply (type, chrec1, chrec2);
+      break;
+
     CASE_CONVERT:
       /* In case we have a truncation of a widened operation that in
          the truncated type has undefined overflow behavior analyze
-- 
1.9.1

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[H.J. Lu]

On Tue, Oct 27, 2015 at 5:40 AM, Alan Lawrence <alan.lawrence@arm.com> wrote:
> --in-reply-to <CAFiYyc3TePGbER2Jqc8-X_ij4GHtjjoxfzFFcNYzHxhGQbE0iQ@mail.gmail.com>
>
> On 26/10/15 08:58, Richard Biener wrote:
>>
>> On Fri, Oct 23, 2015 at 5:15 PM, Alan Lawrence <alan.lawrence@arm.com> wrote:
>>> +      chrec2 = fold_build2 (LSHIFT_EXPR, TREE_TYPE (rhs1),
>>> +                           build_int_cst (TREE_TYPE (rhs1), 1),
>>
>> 'type' instead of TREE_TYPE (rhs1)
>
> I presume you mean the first of the two (allowing removal of the chrec_convert),
> and that I keep the second TREE_TYPE (rhs1), consistent with your previous
> observation that I should do the multiply in the type of rhs1. (This appears
> correct looking at e.g. gcc.target/i386/avx2-vpsllwi-2.c)
>
> Hence, I've committed the attached as r229437.
>

It caused:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68112


-- 
H.J.

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Alan Lawrence]

On 27/10/15 22:27, H.J. Lu wrote:
>
> It caused:
>
> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68112

Bah :(.

So yes, in general case, we can't rewrite (a << 1) to (a * 2) as for signed
types (0x7f...f) << 1 == -2 whereas (0x7f...f * 2) is undefined behaviour.
Oh well :(...

I don't have a really good fix for this. The best way I can see would be to try
to make definedness of overflow a property of either the type, or maybe of the
chrec, and settable on a finer granularity than at present, rather than
TYPE_OVERFLOW_UNDEFINED = (type is signed) && !(a bunch of global flags).
However, I don't think I'm going to have time for that patch before end of
stage 1.

So, I've reverted my r229437. There is a simpler fix: to only apply the rewrite
for unsigned types. I attach that patch, which I've bootstrapped on x86; but
although I think this way is correct, I'm not really sure whether this is
something that should go in. Thoughts?

--Alan
---
 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
 gcc/tree-scalar-evolution.c                      | 19 ++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c

diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
new file mode 100644
index 0000000..40e6561
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
@@ -0,0 +1,33 @@
+/* PR tree-optimization/65963.  */
+#include "tree-vect.h"
+
+#define N 512
+
+int in[2*N], out[N];
+
+__attribute__ ((noinline)) void
+loop (void)
+{
+  for (unsigned i = 0; i < N; i++)
+    out[i] = in[i << 1] + 7;
+}
+
+int
+main (int argc, char **argv)
+{
+  check_vect ();
+  for (int i = 0; i < 2*N; i++)
+    {
+      in[i] = i;
+      __asm__ volatile ("" : : : "memory");
+    }
+  loop ();
+  __asm__ volatile ("" : : : "memory");
+  for (int i = 0; i < N; i++)
+    {
+      if (out[i] != i*2 + 7)
+	abort ();
+    }
+  return 0;
+}
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
index 0753bf3..d8f3d46 100644
--- a/gcc/tree-scalar-evolution.c
+++ b/gcc/tree-scalar-evolution.c
@@ -1840,6 +1840,25 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
       res = chrec_fold_multiply (type, chrec1, chrec2);
       break;
 
+    case LSHIFT_EXPR:
+      if (!TYPE_OVERFLOW_UNDEFINED (type))
+	{
+	  /* Handle A<<B as A * (1<<B).  */
+	  chrec1 = analyze_scalar_evolution (loop, rhs1);
+	  chrec2 = analyze_scalar_evolution (loop, rhs2);
+	  chrec1 = chrec_convert (type, chrec1, at_stmt);
+	  chrec1 = instantiate_parameters (loop, chrec1);
+	  chrec2 = instantiate_parameters (loop, chrec2);
+
+	  chrec2 = fold_build2 (LSHIFT_EXPR, type,
+				build_int_cst (TREE_TYPE (rhs1), 1),
+				chrec2);
+	  res = chrec_fold_multiply (type, chrec1, chrec2);
+	}
+      else
+	res = chrec_dont_know;
+      break;
+
     CASE_CONVERT:
       /* In case we have a truncation of a widened operation that in
          the truncated type has undefined overflow behavior analyze
-- 
1.9.1

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Richard Biener]

On Tue, Nov 3, 2015 at 11:15 AM, Alan Lawrence <alan.lawrence@arm.com> wrote:
> On 27/10/15 22:27, H.J. Lu wrote:
>>
>> It caused:
>>
>> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68112
>
> Bah :(.
>
> So yes, in general case, we can't rewrite (a << 1) to (a * 2) as for signed
> types (0x7f...f) << 1 == -2 whereas (0x7f...f * 2) is undefined behaviour.
> Oh well :(...
>
> I don't have a really good fix for this. The best way I can see would be to try
> to make definedness of overflow a property of either the type, or maybe of the
> chrec, and settable on a finer granularity than at present, rather than
> TYPE_OVERFLOW_UNDEFINED = (type is signed) && !(a bunch of global flags).
> However, I don't think I'm going to have time for that patch before end of
> stage 1.
>
> So, I've reverted my r229437. There is a simpler fix: to only apply the rewrite
> for unsigned types. I attach that patch, which I've bootstrapped on x86; but
> although I think this way is correct, I'm not really sure whether this is
> something that should go in. Thoughts?
>
> --Alan
> ---
>  gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
>  gcc/tree-scalar-evolution.c                      | 19 ++++++++++++++
>  2 files changed, 52 insertions(+)
>  create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
>
> diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
> new file mode 100644
> index 0000000..40e6561
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
> @@ -0,0 +1,33 @@
> +/* PR tree-optimization/65963.  */
> +#include "tree-vect.h"
> +
> +#define N 512
> +
> +int in[2*N], out[N];
> +
> +__attribute__ ((noinline)) void
> +loop (void)
> +{
> +  for (unsigned i = 0; i < N; i++)
> +    out[i] = in[i << 1] + 7;
> +}
> +
> +int
> +main (int argc, char **argv)
> +{
> +  check_vect ();
> +  for (int i = 0; i < 2*N; i++)
> +    {
> +      in[i] = i;
> +      __asm__ volatile ("" : : : "memory");
> +    }
> +  loop ();
> +  __asm__ volatile ("" : : : "memory");
> +  for (int i = 0; i < N; i++)
> +    {
> +      if (out[i] != i*2 + 7)
> +       abort ();
> +    }
> +  return 0;
> +}
> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
> diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
> index 0753bf3..d8f3d46 100644
> --- a/gcc/tree-scalar-evolution.c
> +++ b/gcc/tree-scalar-evolution.c
> @@ -1840,6 +1840,25 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
>        res = chrec_fold_multiply (type, chrec1, chrec2);
>        break;
>
> +    case LSHIFT_EXPR:
> +      if (!TYPE_OVERFLOW_UNDEFINED (type))

I think this should simply re-write A << B to (type) (unsigned-type) A
* (1U << B).

Does that then still vectorize the signed case?

> +       {
> +         /* Handle A<<B as A * (1<<B).  */
> +         chrec1 = analyze_scalar_evolution (loop, rhs1);
> +         chrec2 = analyze_scalar_evolution (loop, rhs2);
> +         chrec1 = chrec_convert (type, chrec1, at_stmt);
> +         chrec1 = instantiate_parameters (loop, chrec1);
> +         chrec2 = instantiate_parameters (loop, chrec2);
> +
> +         chrec2 = fold_build2 (LSHIFT_EXPR, type,
> +                               build_int_cst (TREE_TYPE (rhs1), 1),
> +                               chrec2);
> +         res = chrec_fold_multiply (type, chrec1, chrec2);
> +       }
> +      else
> +       res = chrec_dont_know;
> +      break;
> +
>      CASE_CONVERT:
>        /* In case we have a truncation of a widened operation that in
>           the truncated type has undefined overflow behavior analyze
> --
> 1.9.1
>

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Alan Lawrence]

On 3 November 2015 at 11:35, Richard Biener <richard.guenther@gmail.com> wrote:
>
> I think this should simply re-write A << B to (type) (unsigned-type) A
> * (1U << B).
>
> Does that then still vectorize the signed case?

I didn't realize our representation of chrec's could express that.
Yes, it does - thanks! (And the avx512ifma- test is compiled without warnings.)

Patch attached. I've added a platform-independent version of the failing AVX512
test too.

--Alan

gcc/ChangeLog:

	PR tree-optimization/65963
	* tree-scalar-evolution.c (interpret_rhs_expr): Try to handle
	LSHIFT_EXPRs as equivalent unsigned MULT_EXPRs.

gcc/testsuite/ChangeLog:

	* gcc.dg/pr68112.c: New.
	* gcc.dg/vect/vect-strided-shift-1.c: New.
---
 gcc/testsuite/gcc.dg/pr68112.c                   | 11 ++++++++
 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
 gcc/tree-scalar-evolution.c                      | 17 ++++++++++++
 3 files changed, 61 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/pr68112.c
 create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c

diff --git a/gcc/testsuite/gcc.dg/pr68112.c b/gcc/testsuite/gcc.dg/pr68112.c
new file mode 100644
index 0000000..0a45b03
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr68112.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -Waggressive-loop-optimizations" } */
+
+int *a;
+
+void
+foo ()
+{
+  for (int i = 0; i < 65536; i++)
+    *a = i << 24;
+}
diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
new file mode 100644
index 0000000..b1ce2ec
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
@@ -0,0 +1,33 @@
+/* PR tree-optimization/65963.  */
+#include "tree-vect.h"
+
+#define N 512
+
+int in[2*N], out[N];
+
+__attribute__ ((noinline)) void
+loop (void)
+{
+  for (int i = 0; i < N; i++)
+    out[i] = in[i << 1] + 7;
+}
+
+int
+main (int argc, char **argv)
+{
+  check_vect ();
+  for (int i = 0; i < 2*N; i++)
+    {
+      in[i] = i;
+      __asm__ volatile ("" : : : "memory");
+    }
+  loop ();
+  __asm__ volatile ("" : : : "memory");
+  for (int i = 0; i < N; i++)
+    {
+      if (out[i] != i*2 + 7)
+	abort ();
+    }
+  return 0;
+}
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
index 0753bf3..60d515d 100644
--- a/gcc/tree-scalar-evolution.c
+++ b/gcc/tree-scalar-evolution.c
@@ -1840,6 +1840,23 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
       res = chrec_fold_multiply (type, chrec1, chrec2);
       break;
 
+    case LSHIFT_EXPR:
+      {
+	/* Handle A<<B as A * (1<<B).  */
+	tree uns = unsigned_type_for (type);
+	chrec1 = analyze_scalar_evolution (loop, rhs1);
+	chrec2 = analyze_scalar_evolution (loop, rhs2);
+	chrec1 = chrec_convert (uns, chrec1, at_stmt);
+	chrec1 = instantiate_parameters (loop, chrec1);
+	chrec2 = instantiate_parameters (loop, chrec2);
+
+	tree one = build_int_cst (unsigned_type_for (TREE_TYPE (rhs1)), 1);
+	chrec2 = fold_build2 (LSHIFT_EXPR, uns, one, chrec2);
+	res = chrec_fold_multiply (uns, chrec1, chrec2);
+	res = chrec_convert (type, res, at_stmt);
+      }
+      break;
+
     CASE_CONVERT:
       /* In case we have a truncation of a widened operation that in
          the truncated type has undefined overflow behavior analyze
-- 
1.9.1

Re: [PATCH] tree-scalar-evolution.c: Handle LSHIFT by constant

[Richard Biener]

On Thu, Nov 5, 2015 at 2:26 PM, Alan Lawrence <alan.lawrence@arm.com> wrote:
> On 3 November 2015 at 11:35, Richard Biener <richard.guenther@gmail.com> wrote:
>>
>> I think this should simply re-write A << B to (type) (unsigned-type) A
>> * (1U << B).
>>
>> Does that then still vectorize the signed case?
>
> I didn't realize our representation of chrec's could express that.
> Yes, it does - thanks! (And the avx512ifma- test is compiled without warnings.)
>
> Patch attached. I've added a platform-independent version of the failing AVX512
> test too.
>
> --Alan
>
> gcc/ChangeLog:
>
>         PR tree-optimization/65963
>         * tree-scalar-evolution.c (interpret_rhs_expr): Try to handle
>         LSHIFT_EXPRs as equivalent unsigned MULT_EXPRs.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.dg/pr68112.c: New.
>         * gcc.dg/vect/vect-strided-shift-1.c: New.
> ---
>  gcc/testsuite/gcc.dg/pr68112.c                   | 11 ++++++++
>  gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
>  gcc/tree-scalar-evolution.c                      | 17 ++++++++++++
>  3 files changed, 61 insertions(+)
>  create mode 100644 gcc/testsuite/gcc.dg/pr68112.c
>  create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
>
> diff --git a/gcc/testsuite/gcc.dg/pr68112.c b/gcc/testsuite/gcc.dg/pr68112.c
> new file mode 100644
> index 0000000..0a45b03
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/pr68112.c
> @@ -0,0 +1,11 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -Waggressive-loop-optimizations" } */
> +
> +int *a;
> +
> +void
> +foo ()
> +{
> +  for (int i = 0; i < 65536; i++)
> +    *a = i << 24;
> +}
> diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
> new file mode 100644
> index 0000000..b1ce2ec
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
> @@ -0,0 +1,33 @@
> +/* PR tree-optimization/65963.  */
> +#include "tree-vect.h"
> +
> +#define N 512
> +
> +int in[2*N], out[N];
> +
> +__attribute__ ((noinline)) void
> +loop (void)
> +{
> +  for (int i = 0; i < N; i++)
> +    out[i] = in[i << 1] + 7;
> +}
> +
> +int
> +main (int argc, char **argv)
> +{
> +  check_vect ();
> +  for (int i = 0; i < 2*N; i++)
> +    {
> +      in[i] = i;
> +      __asm__ volatile ("" : : : "memory");
> +    }
> +  loop ();
> +  __asm__ volatile ("" : : : "memory");
> +  for (int i = 0; i < N; i++)
> +    {
> +      if (out[i] != i*2 + 7)
> +       abort ();
> +    }
> +  return 0;
> +}
> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect" { target { vect_strided2 } } } } */
> diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
> index 0753bf3..60d515d 100644
> --- a/gcc/tree-scalar-evolution.c
> +++ b/gcc/tree-scalar-evolution.c
> @@ -1840,6 +1840,23 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
>        res = chrec_fold_multiply (type, chrec1, chrec2);
>        break;
>
> +    case LSHIFT_EXPR:
> +      {
> +       /* Handle A<<B as A * (1<<B).  */
> +       tree uns = unsigned_type_for (type);
> +       chrec1 = analyze_scalar_evolution (loop, rhs1);
> +       chrec2 = analyze_scalar_evolution (loop, rhs2);
> +       chrec1 = chrec_convert (uns, chrec1, at_stmt);
> +       chrec1 = instantiate_parameters (loop, chrec1);
> +       chrec2 = instantiate_parameters (loop, chrec2);
> +
> +       tree one = build_int_cst (unsigned_type_for (TREE_TYPE (rhs1)), 1);

use 'uns' for the type.

Ok with that change.

Richard.

> +       chrec2 = fold_build2 (LSHIFT_EXPR, uns, one, chrec2);
> +       res = chrec_fold_multiply (uns, chrec1, chrec2);
> +       res = chrec_convert (type, res, at_stmt);
> +      }
> +      break;
> +
>      CASE_CONVERT:
>        /* In case we have a truncation of a widened operation that in
>           the truncated type has undefined overflow behavior analyze
> --
> 1.9.1
>