diff mbox series

[8/9] Try to simplify (X >> C1) * (C2 << C1) -> X * C2

Message ID 20241018111806.4026759-9-richard.sandiford@arm.com
State New
Headers show
Series Add more folds related to exact division | expand

Commit Message

Richard Sandiford Oct. 18, 2024, 11:18 a.m. UTC
This patch adds a rule to simplify (X >> C1) * (C2 << C1) -> X * C2
when the low C1 bits of X are known to be zero.  As with the earlier
X >> C1 << (C2 + C1) patch, any single conversion is allowed between
the shift and the multiplication.

gcc/
	* match.pd: Simplify (X >> C1) * (C2 << C1) -> X * C2 if the
	low C1 bits of X are zero.

gcc/testsuite/
	* gcc.dg/tree-ssa/shifts-3.c: New test.
	* gcc.dg/tree-ssa/shifts-4.c: Likewise.
	* gcc.target/aarch64/sve/cnt_fold_5.c: Likewise.
---
 gcc/match.pd                                  | 13 ++++
 gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c      | 65 +++++++++++++++++++
 gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c      | 23 +++++++
 .../gcc.target/aarch64/sve/cnt_fold_5.c       | 38 +++++++++++
 4 files changed, 139 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c
 create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_5.c

Comments

Richard Biener Oct. 18, 2024, 12:10 p.m. UTC | #1
On Fri, 18 Oct 2024, Richard Sandiford wrote:

> This patch adds a rule to simplify (X >> C1) * (C2 << C1) -> X * C2
> when the low C1 bits of X are known to be zero.  As with the earlier
> X >> C1 << (C2 + C1) patch, any single conversion is allowed between
> the shift and the multiplication.

OK.

Thanks,
Richard.

> gcc/
> 	* match.pd: Simplify (X >> C1) * (C2 << C1) -> X * C2 if the
> 	low C1 bits of X are zero.
> 
> gcc/testsuite/
> 	* gcc.dg/tree-ssa/shifts-3.c: New test.
> 	* gcc.dg/tree-ssa/shifts-4.c: Likewise.
> 	* gcc.target/aarch64/sve/cnt_fold_5.c: Likewise.
> ---
>  gcc/match.pd                                  | 13 ++++
>  gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c      | 65 +++++++++++++++++++
>  gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c      | 23 +++++++
>  .../gcc.target/aarch64/sve/cnt_fold_5.c       | 38 +++++++++++
>  4 files changed, 139 insertions(+)
>  create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c
>  create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c
>  create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_5.c
> 
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 41903554478..85f5eeefa08 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -4915,6 +4915,19 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
>        && wi::to_widest (@2) >= wi::to_widest (@1)
>        && wi::to_widest (@1) <= wi::ctz (get_nonzero_bits (@0)))
>    (lshift (convert @0) (minus @2 @1))))
> +
> +/* (X >> C1) * (C2 << C1) -> X * C2 if the low C1 bits of X are zero.  */
> +(simplify
> + (mult (convert? (rshift (with_possible_nonzero_bits2 @0) INTEGER_CST@1))
> +       poly_int_tree_p@2)
> + (with { poly_widest_int factor; }
> +  (if (INTEGRAL_TYPE_P (type)
> +       && wi::ltu_p (wi::to_wide (@1), element_precision (type))
> +       && wi::to_widest (@1) <= wi::ctz (get_nonzero_bits (@0))
> +       && multiple_p (wi::to_poly_widest (@2),
> +		      widest_int (1) << tree_to_uhwi (@1),
> +		      &factor))
> +   (mult (convert @0) { wide_int_to_tree (type, factor); }))))
>  #endif
>  
>  /* For (x << c) >> c, optimize into x & ((unsigned)-1 >> c) for
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c b/gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c
> new file mode 100644
> index 00000000000..dcff518e630
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c
> @@ -0,0 +1,65 @@
> +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
> +
> +unsigned int
> +f1 (unsigned int x)
> +{
> +  if (x & 3)
> +    __builtin_unreachable ();
> +  x >>= 2;
> +  return x * 20;
> +}
> +
> +unsigned int
> +f2 (unsigned int x)
> +{
> +  if (x & 3)
> +    __builtin_unreachable ();
> +  unsigned char y = x;
> +  y >>= 2;
> +  return y * 36;
> +}
> +
> +unsigned long
> +f3 (unsigned int x)
> +{
> +  if (x & 3)
> +    __builtin_unreachable ();
> +  x >>= 2;
> +  return (unsigned long) x * 88;
> +}
> +
> +int
> +f4 (int x)
> +{
> +  if (x & 15)
> +    __builtin_unreachable ();
> +  x >>= 4;
> +  return x * 48;
> +}
> +
> +unsigned int
> +f5 (int x)
> +{
> +  if (x & 31)
> +    __builtin_unreachable ();
> +  x >>= 5;
> +  return x * 3200;
> +}
> +
> +unsigned int
> +f6 (unsigned int x)
> +{
> +  if (x & 1)
> +    __builtin_unreachable ();
> +  x >>= 1;
> +  return x * (~0U / 3 & -2);
> +}
> +
> +/* { dg-final { scan-tree-dump-not {<[a-z]*_div_expr,} "optimized" } } */
> +/* { dg-final { scan-tree-dump-not {<rshift_expr,} "optimized" } } */
> +/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 5,} "optimized" } } */
> +/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 9,} "optimized" } } */
> +/* { dg-final { scan-tree-dump {<(?:widen_)?mult_expr, [^,]*, [^,]*, 22,} "optimized" } } */
> +/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 3,} "optimized" } } */
> +/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 100,} "optimized" } } */
> +/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 715827882,} "optimized" { target int32 } } } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c b/gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c
> new file mode 100644
> index 00000000000..5638653d0c2
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c
> @@ -0,0 +1,23 @@
> +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
> +
> +unsigned int
> +f1 (unsigned int x)
> +{
> +  if (x & 3)
> +    __builtin_unreachable ();
> +  x >>= 2;
> +  return x * 10;
> +}
> +
> +unsigned int
> +f2 (unsigned int x)
> +{
> +  if (x & 3)
> +    __builtin_unreachable ();
> +  x >>= 3;
> +  return x * 24;
> +}
> +
> +/* { dg-final { scan-tree-dump-times {<rshift_expr,} 2 "optimized" } } */
> +/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 10,} "optimized" } } */
> +/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 24,} "optimized" } } */
> diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_5.c b/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_5.c
> new file mode 100644
> index 00000000000..3f60e9b4941
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_5.c
> @@ -0,0 +1,38 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> +
> +#include <arm_sve.h>
> +
> +/*
> +** f1:
> +**	...
> +**	cntd	[^\n]+
> +**	...
> +**	mul	[^\n]+
> +**	ret
> +*/
> +uint64_t
> +f1 (int x)
> +{
> +  if (x & 3)
> +    __builtin_unreachable ();
> +  x >>= 2;
> +  return (uint64_t) x * svcnth ();
> +}
> +
> +/*
> +** f2:
> +**	...
> +**	asr	[^\n]+
> +**	...
> +**	ret
> +*/
> +uint64_t
> +f2 (int x)
> +{
> +  if (x & 3)
> +    __builtin_unreachable ();
> +  x >>= 2;
> +  return (uint64_t) x * svcntw ();
> +}
>
diff mbox series

Patch

diff --git a/gcc/match.pd b/gcc/match.pd
index 41903554478..85f5eeefa08 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4915,6 +4915,19 @@  DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
       && wi::to_widest (@2) >= wi::to_widest (@1)
       && wi::to_widest (@1) <= wi::ctz (get_nonzero_bits (@0)))
   (lshift (convert @0) (minus @2 @1))))
+
+/* (X >> C1) * (C2 << C1) -> X * C2 if the low C1 bits of X are zero.  */
+(simplify
+ (mult (convert? (rshift (with_possible_nonzero_bits2 @0) INTEGER_CST@1))
+       poly_int_tree_p@2)
+ (with { poly_widest_int factor; }
+  (if (INTEGRAL_TYPE_P (type)
+       && wi::ltu_p (wi::to_wide (@1), element_precision (type))
+       && wi::to_widest (@1) <= wi::ctz (get_nonzero_bits (@0))
+       && multiple_p (wi::to_poly_widest (@2),
+		      widest_int (1) << tree_to_uhwi (@1),
+		      &factor))
+   (mult (convert @0) { wide_int_to_tree (type, factor); }))))
 #endif
 
 /* For (x << c) >> c, optimize into x & ((unsigned)-1 >> c) for
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c b/gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c
new file mode 100644
index 00000000000..dcff518e630
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/shifts-3.c
@@ -0,0 +1,65 @@ 
+/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
+
+unsigned int
+f1 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 2;
+  return x * 20;
+}
+
+unsigned int
+f2 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  unsigned char y = x;
+  y >>= 2;
+  return y * 36;
+}
+
+unsigned long
+f3 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 2;
+  return (unsigned long) x * 88;
+}
+
+int
+f4 (int x)
+{
+  if (x & 15)
+    __builtin_unreachable ();
+  x >>= 4;
+  return x * 48;
+}
+
+unsigned int
+f5 (int x)
+{
+  if (x & 31)
+    __builtin_unreachable ();
+  x >>= 5;
+  return x * 3200;
+}
+
+unsigned int
+f6 (unsigned int x)
+{
+  if (x & 1)
+    __builtin_unreachable ();
+  x >>= 1;
+  return x * (~0U / 3 & -2);
+}
+
+/* { dg-final { scan-tree-dump-not {<[a-z]*_div_expr,} "optimized" } } */
+/* { dg-final { scan-tree-dump-not {<rshift_expr,} "optimized" } } */
+/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 5,} "optimized" } } */
+/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 9,} "optimized" } } */
+/* { dg-final { scan-tree-dump {<(?:widen_)?mult_expr, [^,]*, [^,]*, 22,} "optimized" } } */
+/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 3,} "optimized" } } */
+/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 100,} "optimized" } } */
+/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 715827882,} "optimized" { target int32 } } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c b/gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c
new file mode 100644
index 00000000000..5638653d0c2
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/shifts-4.c
@@ -0,0 +1,23 @@ 
+/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
+
+unsigned int
+f1 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 2;
+  return x * 10;
+}
+
+unsigned int
+f2 (unsigned int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 3;
+  return x * 24;
+}
+
+/* { dg-final { scan-tree-dump-times {<rshift_expr,} 2 "optimized" } } */
+/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 10,} "optimized" } } */
+/* { dg-final { scan-tree-dump {<mult_expr, [^,]*, [^,]*, 24,} "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_5.c b/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_5.c
new file mode 100644
index 00000000000..3f60e9b4941
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_5.c
@@ -0,0 +1,38 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include <arm_sve.h>
+
+/*
+** f1:
+**	...
+**	cntd	[^\n]+
+**	...
+**	mul	[^\n]+
+**	ret
+*/
+uint64_t
+f1 (int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 2;
+  return (uint64_t) x * svcnth ();
+}
+
+/*
+** f2:
+**	...
+**	asr	[^\n]+
+**	...
+**	ret
+*/
+uint64_t
+f2 (int x)
+{
+  if (x & 3)
+    __builtin_unreachable ();
+  x >>= 2;
+  return (uint64_t) x * svcntw ();
+}