match.pd: Simplify 1 / X for integer X [PR95424]

This patch implements an optimization for the following C++ code:

int f(int x) {
    return 1 / x;
}

int f(unsigned int x) {
    return 1 / x;
}

Before this patch, x86-64 gcc -std=c++20 -O3 produces the following assembly:

f(int):
    xor edx, edx
    mov eax, 1
    idiv edi
    ret
f(unsigned int):
    xor edx, edx
    mov eax, 1
    div edi
    ret

In comparison, clang++ -std=c++20 -O3 produces the following assembly:

f(int):
    lea ecx, [rdi + 1]
    xor eax, eax
    cmp ecx, 3
    cmovb eax, edi
    ret
f(unsigned int):
    xor eax, eax
    cmp edi, 1
    sete al
    ret

Clang's output is more efficient as it avoids expensive div operations.

With this patch, GCC now produces the following assembly:

f(int):
    lea eax, [rdi + 1]
    cmp eax, 2
    mov eax, 0
    cmovbe eax, edi
    ret
f(unsigned int):
    xor eax, eax
    cmp edi, 1
    sete al
    ret

which is virtually identical to Clang's assembly output. Any slight differences
in the output for f(int) is possibly related to a different missed optimization.

v2: https://gcc.gnu.org/pipermail/gcc-patches/2022-January/587751.html
Changes from v2:
1. Refactor from using a switch statement to using the built-in
if-else statement.

v1: https://gcc.gnu.org/pipermail/gcc-patches/2022-January/587634.html
Changes from v1:
1. Refactor common if conditions.
2. Use build_[minus_]one_cst (type) to get -1/1 of the correct type.
3. Match only for TRUNC_DIV_EXPR and TYPE_PRECISION (type) > 1.

gcc/ChangeLog:

	PR tree-optimization/95424
	* match.pd: Simplify 1 / X where X is an integer.

gcc/match.pd

@@ -435,6 +435,19 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
        && TYPE_UNSIGNED (type))
    (trunc_divmod @0 @1))))
 
+ /* 1 / X -> X == 1 for unsigned integer X.
+    1 / X -> X >= -1 && X <= 1 ? X : 0 for signed integer X.
+    But not for 1 / 0 so that we can get proper warnings and errors,
+    and not for 1-bit integers as they are edge cases better handled elsewhere. */
+(simplify
+  (trunc_div integer_onep@0 @1)
+  (if (INTEGRAL_TYPE_P (type) && !integer_zerop (@1) && TYPE_PRECISION (type) > 1)
+    (if (TYPE_UNSIGNED (type))
+      (eq @1 { build_one_cst (type); })
+      (with { tree utype = unsigned_type_for (type); }
+        (cond (le (plus (convert:utype @1) { build_one_cst (utype); }) { build_int_cst (utype, 2); })
+          @1 { build_zero_cst (type); })))))
+
 /* Combine two successive divisions.  Note that combining ceil_div
    and floor_div is trickier and combining round_div even more so.  */
 (for div (trunc_div exact_div)

gcc/testsuite/gcc.dg/tree-ssa/divide-6.c

@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O -fdump-tree-optimized" } */
+
+unsigned int f(unsigned int x) {
+  return 1 / x;
+}
+
+/* { dg-final { scan-tree-dump-not "1 / x_..D.;" "optimized" } } */
+/* { dg-final { scan-tree-dump "x_..D. == 1;" "optimized" } } */

gcc/testsuite/gcc.dg/tree-ssa/divide-7.c

@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O -fdump-tree-optimized" } */
+
+int f(int x) {
+  return 1 / x;
+}
+
+/* { dg-final { scan-tree-dump-not "1 / x_..D.;" "optimized" } } */
+/* { dg-final { scan-tree-dump ".. <= 2 ? x_..D. : 0;" "optimized" } } */