[AMDGPU] Fix a weird WWM intrinsic issue.

I found a really strange WWM issue through a very convoluted shader that
essentially boils down to a bug in SIInstrInfo where canReadVGPR did not
correctly identify that WWM is like a copy and can have a VGPR as its
source.

Differential Revision: https://reviews.llvm.org/D56002

llvm-svn: 352500

3 files changed, 64 insertions, 17 deletions

diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 45687d4486e..b857d9df823 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -3277,18 +3277,6 @@ const TargetRegisterClass *SIInstrInfo::getOpRegClass(const MachineInstr &MI,
   return RI.getRegClass(RCID);
 }
 
-bool SIInstrInfo::canReadVGPR(const MachineInstr &MI, unsigned OpNo) const {
-  switch (MI.getOpcode()) {
-  case AMDGPU::COPY:
-  case AMDGPU::REG_SEQUENCE:
-  case AMDGPU::PHI:
-  case AMDGPU::INSERT_SUBREG:
-    return RI.hasVGPRs(getOpRegClass(MI, 0));
-  default:
-    return RI.hasVGPRs(getOpRegClass(MI, OpNo));
-  }
-}
-
 void SIInstrInfo::legalizeOpWithMove(MachineInstr &MI, unsigned OpIdx) const {
   MachineBasicBlock::iterator I = MI;
   MachineBasicBlock *MBB = MI.getParent();
@@ -4957,7 +4945,23 @@ void SIInstrInfo::addUsersToMoveToVALUWorklist(
   for (MachineRegisterInfo::use_iterator I = MRI.use_begin(DstReg),
          E = MRI.use_end(); I != E;) {
     MachineInstr &UseMI = *I->getParent();
-    if (!canReadVGPR(UseMI, I.getOperandNo())) {
+
+    unsigned OpNo = 0;
+
+    switch (UseMI.getOpcode()) {
+    case AMDGPU::COPY:
+    case AMDGPU::WQM:
+    case AMDGPU::WWM:
+    case AMDGPU::REG_SEQUENCE:
+    case AMDGPU::PHI:
+    case AMDGPU::INSERT_SUBREG:
+      break;
+    default:
+      OpNo = I.getOperandNo();
+      break;
+    }
+
+    if (!RI.hasVGPRs(getOpRegClass(UseMI, OpNo))) {
       Worklist.insert(&UseMI);
 
       do {
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.h b/llvm/lib/Target/AMDGPU/SIInstrInfo.h
index bdc53f6257e..2aa9a33c5aa 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.h
@@ -762,10 +762,6 @@ public:
     return RI.getRegSizeInBits(*getOpRegClass(MI, OpNo)) / 8;
   }
 
-  /// \returns true if it is legal for the operand at index \p OpNo
-  /// to read a VGPR.
-  bool canReadVGPR(const MachineInstr &MI, unsigned OpNo) const;
-
   /// Legalize the \p OpIndex operand of this instruction by inserting
   /// a MOV.  For example:
   /// ADD_I32_e32 VGPR0, 15
diff --git a/llvm/test/CodeGen/AMDGPU/fix-wwm-vgpr-copy.ll b/llvm/test/CodeGen/AMDGPU/fix-wwm-vgpr-copy.ll
new file mode 100644
index 00000000000..3375efa14dd
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/fix-wwm-vgpr-copy.ll
@@ -0,0 +1,47 @@
+; RUN: llc -mtriple=amdgcn--amdpal -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+declare i64 @llvm.amdgcn.icmp.i32(i32, i32, i32) #0
+declare i32 @llvm.amdgcn.set.inactive.i32(i32, i32) #0
+declare i32 @llvm.amdgcn.wwm.i32(i32) #1
+declare void @llvm.amdgcn.tbuffer.store.f32(float, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #2
+declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #2
+
+define amdgpu_hs void @foo(i32 inreg %arg, <4 x i32> inreg %buffer) {
+entry:
+  br label %work
+
+bb42:
+  br label %bb602
+
+bb602:
+  %tmp603 = phi i32 [ 0, %bb42 ], [ 1, %work ]
+  %tmp607 = icmp eq i32 %tmp603, %tmp1196
+  br i1 %tmp607, label %bb49, label %bb54
+
+bb49:
+  tail call void @llvm.amdgcn.tbuffer.store.f32(float 1.000000e+00, <4 x i32> %buffer, i32 0, i32 1, i32 1, i32 4, i32 4, i32 7, i1 true, i1 false) #7
+  ret void
+
+bb54:
+  ret void
+
+work:
+; GCN: s_not_b64 exec, exec
+; GCN: v_mov_b32_e32 v[[tmp1189:[0-9]+]], 1
+; GCN: s_not_b64 exec, exec
+  %tmp1189 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 4, i32 1)
+
+; GCN: s_or_saveexec_b64 s{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]{{\]}}, -1
+; GCN: v_lshlrev_b32_e32 v[[tmp1191:[0-9]+]], 2, v[[tmp1189]]
+  %tmp1191 = mul i32 %tmp1189, 4
+
+; GCN: s_mov_b64 exec, s{{\[}}[[LO]]:[[HI]]{{\]}}
+  %tmp1196 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp1191)
+
+  %tmp34 = icmp eq i32 %arg, 0
+  br i1 %tmp34, label %bb602, label %bb42
+}
+
+attributes #0 = { convergent nounwind readnone }
+attributes #1 = { nounwind readnone speculatable }
+attributes #2 = { nounwind writeonly }