[llvm] InstCombine: improve optimizations for ceiling division with no overflow (PR #142869)

[Nikita Popov via llvm-commits]

================
@@ -4273,4 +4273,245 @@ define i32 @fold_zext_nneg_add_const_fail2(i8 %x) {
 }
 
 declare void @llvm.assume(i1)
+declare i32 @llvm.ctlz.i32(i32, i1)
+
+; Ceiling division by power-of-2: (x >> log2(N)) + ((x & (N-1)) != 0) -> (x + (N-1)) >> log2(N)
+; This is only valid when x + (N-1) doesn't overflow
+
+; Test with known range that prevents overflow
+define noundef range(i32 0, 100) i32 @ceil_div_by_8_known_range(i32 noundef range(i32 0, 100) %x) {
+; CHECK-LABEL: @ceil_div_by_8_known_range(
+; CHECK-NEXT:    [[TMP1:%.*]] = add nuw nsw i32 [[X:%.*]], 7
+; CHECK-NEXT:    [[R:%.*]] = lshr i32 [[TMP1]], 3
+; CHECK-NEXT:    ret i32 [[R]]
+;
+  %shr = lshr i32 %x, 3
+  %and = and i32 %x, 7
+  %cmp = icmp ne i32 %and, 0
+  %ext = zext i1 %cmp to i32
+  %r = add i32 %shr, %ext
+  ret i32 %r
+}
+
+; Test with the exact IR from the original testcase
+define noundef range(i32 0, 6) i32 @ceil_div_from_clz(i32 noundef %v) {
----------------
nikic wrote:

```suggestion
define i32 @ceil_div_from_clz(i32 %v) {
```

https://github.com/llvm/llvm-project/pull/142869