[AMDGPU] Run `unreachable-mbb-elimination` after isel to clean up PHIs.

Summary:
- As LCSSA is turned on just before isel, it may create PHI of the flow,
  which is consumed by pseudo structurized CFG instructions. When that
  PHIs are eliminated in O0, COPY may be placed wrongly as the these
  pseudo structurized CFG instructions are considering prologue of MBB.
- Run extra `unreachable-mbb-elimination` at the end of isel to clean up
  PHIs.

Reviewers: arsenm, rampitec

Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D64353

llvm-svn: 367023

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

@@ -882,6 +882,9 @@ bool GCNPassConfig::addInstSelector() {
   addPass(createSILowerI1CopiesPass());
   addPass(createSIFixupVectorISelPass());
   addPass(createSIAddIMGInitPass());
+  // FIXME: Remove this once the phi on CF_END is cleaned up by either removing
+  // LCSSA or other ways.
+  addPass(&UnreachableMachineBlockElimID);
   return false;
 }
 

llvm/test/CodeGen/AMDGPU/lcssa-optnone.ll

@@ -0,0 +1,26 @@
+; RUN: llc -march=amdgcn -O0 -o - %s | FileCheck %s
+
+; CHECK-LABEL: non_uniform_loop
+; CHECK: s_endpgm
+define amdgpu_kernel void @non_uniform_loop(float addrspace(1)* %array) {
+entry:
+  %w = tail call i32 @llvm.amdgcn.workitem.id.x()
+  br label %for.cond
+
+for.cond:
+  %i = phi i32 [0, %entry], [%i.next, %for.inc]
+  %cmp = icmp ult i32 %i, %w
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:
+  br label %for.inc
+
+for.inc:
+  %i.next = add i32 %i, 1
+  br label %for.cond
+
+for.end:
+  ret void
+}
+
+declare i32 @llvm.amdgcn.workitem.id.x()