[AMDGPU] Fix the mis-handling of `vreg_1` copied from scalar register.

Summary:
- Don't treat the use of a scalar register as `vreg_1` an VGPR usage.
  Otherwise, that promotes that scalar register into vector one, which
  breaks the assumption that scalar register holds the lane mask.
- The issue is triggered in a complicated case, where if the uses of
  that (lane mask) scalar register is legalized firstly before its
  definition, e.g., due to the mismatch block placement and its
  topological order or loop. In that cases, the legalization of PHI
  introduces the use of that scalar register as `vreg_1`.

Reviewers: rampitec, nhaehnle, arsenm, alex-t

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

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D62492

llvm-svn: 361847

2 files changed, 49 insertions, 1 deletions

diff --git a/llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp b/llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
index d20910baed3..fb151b4ffdc 100644
--- a/llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
@@ -588,7 +588,9 @@ bool SIFixSGPRCopies::runOnMachineFunction(MachineFunction &MF) {
             }
 
             if (UseMI->isPHI()) {
-              if (!TRI->isSGPRReg(MRI, Use.getReg()))
+              const TargetRegisterClass *UseRC = MRI.getRegClass(Use.getReg());
+              if (!TRI->isSGPRReg(MRI, Use.getReg()) &&
+                  UseRC != &AMDGPU::VReg_1RegClass)
                 hasVGPRUses++;
               continue;
             }
@@ -633,8 +635,10 @@ bool SIFixSGPRCopies::runOnMachineFunction(MachineFunction &MF) {
 
         if ((!TRI->isVGPR(MRI, PHIRes) && RC0 != &AMDGPU::VReg_1RegClass) &&
             (hasVGPRInput || hasVGPRUses > 1)) {
+          LLVM_DEBUG(dbgs() << "Fixing PHI: " << MI);
           TII->moveToVALU(MI);
         } else {
+          LLVM_DEBUG(dbgs() << "Legalizing PHI: " << MI);
           TII->legalizeOperands(MI, MDT);
         }
 
diff --git a/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies.mir b/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies.mir
index 3d6e05cb2c9..306e62a4309 100644
--- a/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies.mir
+++ b/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies.mir
@@ -16,3 +16,47 @@ body:               |
     %6:sreg_32 = S_ADD_I32 %2:sreg_32, %5:sreg_32, implicit-def $scc
     %7:sreg_32 = S_ADDC_U32 %3:sreg_32, %1:sreg_32, implicit-def $scc, implicit $scc
 ...
+
+# Test to ensure i1 phi copies from scalar registers through another phi won't
+# be promoted into vector ones.
+# GCN-LABEL: name: fix-sgpr-i1-phi-copies
+# GCN: .8:
+# GCN-NOT: vreg_64 = PHI
+---
+name: fix-sgpr-i1-phi-copies
+tracksRegLiveness: true
+body:               |
+  bb.9:
+    S_BRANCH %bb.0
+
+  bb.4:
+    S_CBRANCH_SCC1 %bb.6, implicit undef $scc
+
+  bb.5:
+    %3:vreg_1 = IMPLICIT_DEF
+
+  bb.6:
+    %4:vreg_1 = PHI %2:sreg_64, %bb.4, %3:vreg_1, %bb.5
+
+  bb.7:
+    %5:vreg_1 = PHI %2:sreg_64, %bb.3, %4:vreg_1, %bb.6
+    S_BRANCH %bb.8
+
+  bb.0:
+    S_CBRANCH_SCC1 %bb.2, implicit undef $scc
+
+  bb.1:
+    %0:sreg_64 = S_MOV_B64 0
+    S_BRANCH %bb.3
+
+  bb.2:
+    %1:sreg_64 = S_MOV_B64 -1
+    S_BRANCH %bb.3
+
+  bb.3:
+    %2:sreg_64 = PHI %0:sreg_64, %bb.1, %1:sreg_64, %bb.2
+    S_CBRANCH_SCC1 %bb.7, implicit undef $scc
+    S_BRANCH %bb.4
+
+  bb.8:
+...