commit 9b470cc24704260fc6502cde6f6ca96811326264
Author: Jennifer Schmitz <jschmitz@nvidia.com>
Date:   Wed May 22 19:55:35 2024 +0530

    [PATCH] match.pd: Fold x/sqrt(x) to sqrt(x)
    
    This patch adds a pattern in match.pd folding x/sqrt(x) to sqrt(x) for -funsafe-math-optimizations. Test cases were added for double, float, and long double.
    
    The patch was bootstrapped and regtested on aarch64-linux-gnu, no regression.
    Ok for mainline?
    
    Signed-off-by: Jennifer Schmitz <jschmitz@nvidia.com>
    
    gcc/
    
            * match.pd: Fold x/sqrt(x) to sqrt(x).
    
    gcc/testsuite/
    
            * gcc.dg/tree-ssa/sqrt_div.c: New test.

diff --git a/gcc/match.pd b/gcc/match.pd
index 35e3d82b131..e1f68b4e31f 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -6457,6 +6457,8 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
  /* Fold comparisons against built-in math functions.  */
  (if (flag_unsafe_math_optimizations && ! flag_errno_math)
   (for sq (SQRT)
+   (simplify
+    (rdiv @0 (sq @0)) (sq @0))
    (simplify
     (cmp (sq @0) REAL_CST@1)
     (switch
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/sqrt_div.c b/gcc/testsuite/gcc.dg/tree-ssa/sqrt_div.c
new file mode 100644
index 00000000000..33dc4d9bddb
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/sqrt_div.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ffast-math -fdump-tree-forwprop-details" } */
+/* { dg-require-effective-target c99_runtime } */
+
+#define T(n, type, fname)          \
+type f##n (type x)                 \
+{                                  \
+  type t1 = __builtin_##fname (x); \
+  type t2 = x / t1;                \
+  return t2;                       \
+}                               
+
+T(1, double, sqrt)
+
+/* { dg-final { scan-tree-dump "gimple_simplified to t2_\[0-9\]+ = __builtin_sqrt .x_\[0-9\]*.D.." "forwprop1" } }     */
+
+T(2, float, sqrtf )
+
+/* { dg-final { scan-tree-dump "gimple_simplified to t2_\[0-9\]+ = __builtin_sqrtf .x_\[0-9\]*.D.." "forwprop1" } }     */
+
+T(3, long double, sqrtl)
+
+/* { dg-final { scan-tree-dump "gimple_simplified to t2_\[0-9\]+ = __builtin_sqrtl .x_\[0-9\]*.D.." "forwprop1" } } */