diff mbox series

[v4] MATCH: Simplify `a rrotate (32-b) -> a lrotate b` [PR109906]

Message ID 20241111113604.16704-1-quic_eikagupt@quicinc.com
State New
Headers show
Series [v4] MATCH: Simplify `a rrotate (32-b) -> a lrotate b` [PR109906] | expand

Commit Message

Eikansh Gupta Nov. 11, 2024, 11:36 a.m. UTC
The pattern `a rrotate (32-b)` should be optimized to `a lrotate b`.
The same is also true for `a lrotate (32-b)`. It can be optimized to
`a rrotate b`.

This patch adds following patterns:
a rrotate (32-b) -> a lrotate b
a lrotate (32-b) -> a rrotate b

Bootstrapped and tested on x86_64-linux-gnu with no regressions.

	PR tree-optimization/109906

gcc/ChangeLog:

	* match.pd (a rrotate (32-b) -> a lrotate b): New pattern
	(a lrotate (32-b) -> a rrotate b): New pattern

gcc/testsuite/ChangeLog:

	* gcc.dg/tree-ssa/pr109906.c: New test.

Signed-off-by: Eikansh Gupta <quic_eikagupt@quicinc.com>
---
 gcc/match.pd                             |  9 ++++++
 gcc/testsuite/gcc.dg/tree-ssa/pr109906.c | 41 ++++++++++++++++++++++++
 2 files changed, 50 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr109906.c

Comments

Jeff Law Nov. 11, 2024, 7:38 p.m. UTC | #1
On 11/11/24 4:36 AM, Eikansh Gupta wrote:
> The pattern `a rrotate (32-b)` should be optimized to `a lrotate b`.
> The same is also true for `a lrotate (32-b)`. It can be optimized to
> `a rrotate b`.
> 
> This patch adds following patterns:
> a rrotate (32-b) -> a lrotate b
> a lrotate (32-b) -> a rrotate b
> 
> Bootstrapped and tested on x86_64-linux-gnu with no regressions.
> 
> 	PR tree-optimization/109906
> 
> gcc/ChangeLog:
> 
> 	* match.pd (a rrotate (32-b) -> a lrotate b): New pattern
> 	(a lrotate (32-b) -> a rrotate b): New pattern
> 
> gcc/testsuite/ChangeLog:
> 
> 	* gcc.dg/tree-ssa/pr109906.c: New test.
> 
> Signed-off-by: Eikansh Gupta <quic_eikagupt@quicinc.com>
OK.
jeff
Andrew Pinski Nov. 14, 2024, 8:38 a.m. UTC | #2
On Mon, Nov 11, 2024 at 11:39 AM Jeff Law <jeffreyalaw@gmail.com> wrote:
>
>
>
> On 11/11/24 4:36 AM, Eikansh Gupta wrote:
> > The pattern `a rrotate (32-b)` should be optimized to `a lrotate b`.
> > The same is also true for `a lrotate (32-b)`. It can be optimized to
> > `a rrotate b`.
> >
> > This patch adds following patterns:
> > a rrotate (32-b) -> a lrotate b
> > a lrotate (32-b) -> a rrotate b
> >
> > Bootstrapped and tested on x86_64-linux-gnu with no regressions.
> >
> >       PR tree-optimization/109906
> >
> > gcc/ChangeLog:
> >
> >       * match.pd (a rrotate (32-b) -> a lrotate b): New pattern
> >       (a lrotate (32-b) -> a rrotate b): New pattern
> >
> > gcc/testsuite/ChangeLog:
> >
> >       * gcc.dg/tree-ssa/pr109906.c: New test.
> >
> > Signed-off-by: Eikansh Gupta <quic_eikagupt@quicinc.com>
> OK.

Pushed as r15-5231-g879c1619ab5a708514cbb1f3754e59f30ba29e6c .

Thanks,
Andrew

> jeff
>
diff mbox series

Patch

diff --git a/gcc/match.pd b/gcc/match.pd
index 5ec31ef6269..0e8e95a9277 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4861,6 +4861,15 @@  DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
 			    build_int_cst (TREE_TYPE (@1),
 					   element_precision (type)), @1); }))
 
+/* a rrotate (32-b) -> a lrotate b */
+/* a lrotate (32-b) -> a rrotate b */
+(for rotate (lrotate rrotate)
+     orotate (rrotate lrotate)
+ (simplify
+  (rotate @0 (minus INTEGER_CST@1 @2))
+   (if (element_precision (TREE_TYPE (@0)) == wi::to_wide (@1))
+     (orotate @0 @2))))
+
 /* Turn (a OP c1) OP c2 into a OP (c1+c2).  */
 (for op (lrotate rrotate rshift lshift)
  (simplify
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr109906.c b/gcc/testsuite/gcc.dg/tree-ssa/pr109906.c
new file mode 100644
index 00000000000..9aa015d8c65
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr109906.c
@@ -0,0 +1,41 @@ 
+/* PR tree-optimization/109906 */
+/* { dg-do compile } */
+/* { dg-options "-O1 -fdump-tree-optimized-raw" } */
+/* { dg-require-effective-target int32 } */
+
+/* Implementation of rotate right operation */
+static inline
+unsigned rrotate(unsigned x, int t)
+{
+  if (t >= 32) __builtin_unreachable();
+  unsigned tl = x >> (t);
+  unsigned th = x << (32 - t);
+  return tl | th;
+}
+
+/* Here rotate left is achieved by doing rotate right by (32 - x) */
+unsigned rotateleft(unsigned t, int x)
+{
+  return rrotate (t, 32 - x);
+}
+
+/* Implementation of rotate left operation */
+static inline
+unsigned lrotate(unsigned x, int t)
+{
+  if (t >= 32) __builtin_unreachable();
+  unsigned tl = x << (t);
+  unsigned th = x >> (32 - t);
+  return tl | th;
+}
+
+/* Here rotate right is achieved by doing rotate left by (32 - x) */
+unsigned rotateright(unsigned t, int x)
+{
+  return lrotate (t, 32 - x);
+}
+
+/* Shouldn't have instruction for (32 - x). */
+/* { dg-final { scan-tree-dump-not "minus_expr" "optimized" } } */
+/* { dg-final { scan-tree-dump "rrotate_expr" "optimized" } } */
+/* { dg-final { scan-tree-dump "lrotate_expr" "optimized" } } */