Revert "[AMDGPU] Split entry basic block after alloca instructions."

This reverts commit 98f4713.

Without any (theoretical/practical) guarantee that all the allocas within
*entry* basic block are clustered together at the beginning of the block,
this patch is doomed to fail. Hence reverting it.

llvm/lib/Target/AMDGPU/AMDGPUReplaceLDSUseWithPointer.cpp

@@ -191,19 +191,10 @@ class ReplaceLDSUseImpl {
     if (!BasicBlockEntry.second)
       return BasicBlockEntry.first->second;
 
-    // Split entry basic block of kernel K just after alloca.
-    //
-    // Find the split point just after alloca.
-    auto &EBB = K->getEntryBlock();
-    auto *EI = &(*(EBB.getFirstInsertionPt()));
-    BasicBlock::reverse_iterator RIT(EBB.getTerminator());
-    while (!isa<AllocaInst>(*RIT) && (&*RIT != EI))
-      ++RIT;
-    if (isa<AllocaInst>(*RIT))
-      --RIT;
-
-    // Split entry basic block.
-    IRBuilder<> Builder(&*RIT);
+    // Split entry basic block of kernel K.
+    auto *EI = &(*(K->getEntryBlock().getFirstInsertionPt()));
+    IRBuilder<> Builder(EI);
+
     Value *Mbcnt =
         Builder.CreateIntrinsic(Intrinsic::amdgcn_mbcnt_lo, {},
                                 {Builder.getInt32(-1), Builder.getInt32(0)});