[llvm] [AArch64] Don't try to sink and(load) (PR #122274)

[David Sherwood via llvm-commits]

================
@@ -40,3 +40,49 @@ vector.body:                                      ; preds = %vector.body, %vecto
   store <2 x i32> %3, ptr %4, align 4
   br label %vector.body
 }
+
+; This test got stuck in a loop hoisting the and to the load, and sinking it back to the mull
+define i32 @dup_and_load(ptr %p, i1 %c) {
+; CHECK-LABEL: dup_and_load:
+; CHECK:       // %bb.0: // %for.body.lr.ph
+; CHECK-NEXT:    mov x8, x0
+; CHECK-NEXT:    ldrb w0, [x0]
+; CHECK-NEXT:    tbz w1, #0, .LBB1_3
+; CHECK-NEXT:  // %bb.1: // %ph
+; CHECK-NEXT:    dup v0.8h, w0
+; CHECK-NEXT:    mov w9, wzr
+; CHECK-NEXT:  .LBB1_2: // %vector.body
+; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    ldr d1, [x8]
+; CHECK-NEXT:    add w9, w9, #1
+; CHECK-NEXT:    cmp w9, #100
+; CHECK-NEXT:    ushll v1.8h, v1.8b, #0
+; CHECK-NEXT:    umull2 v2.4s, v0.8h, v1.8h
+; CHECK-NEXT:    umull v1.4s, v0.4h, v1.4h
+; CHECK-NEXT:    stp q1, q2, [x8]
+; CHECK-NEXT:    b.lt .LBB1_2
+; CHECK-NEXT:  .LBB1_3: // %end
+; CHECK-NEXT:    ret
+for.body.lr.ph:
+  %l = load i32, ptr %p
+  %conv314 = and i32 %l, 255
+  br i1 %c, label %ph, label %end
+
+ph:
+  %broadcast.splatinsert = insertelement <8 x i32> poison, i32 %conv314, i32 0
+  %broadcast.splat = shufflevector <8 x i32> %broadcast.splatinsert, <8 x i32> poison, <8 x i32> zeroinitializer
+  br label %vector.body
+
+vector.body:                                      ; preds = %vector.body, %vector.ph
----------------
david-arm wrote:

Does this need to be a loop in order to trigger the crash? Just wondering if it could be a normal block to reduce the lines of IR.

https://github.com/llvm/llvm-project/pull/122274