GlobalISel: Fix narrowScalar for load/store with different mem size

This was ignoring the memory size, and producing multiple loads/stores
if the operand size was different from the memory size.

I assume this is the intent of not having an explicit G_ANYEXTLOAD
(although I think that would probably be better).

llvm-svn: 352523

2 files changed, 49 insertions, 4 deletions

diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index fef1605fecf..7e3c0ed809c 100644
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -537,6 +537,18 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI,
       return UnableToLegalize;
 
     const auto &MMO = **MI.memoperands_begin();
+    unsigned DstReg = MI.getOperand(0).getReg();
+    LLT DstTy = MRI.getType(DstReg);
+
+    if (8 * MMO.getSize() != DstTy.getSizeInBits()) {
+      unsigned TmpReg = MRI.createGenericVirtualRegister(NarrowTy);
+      auto &MMO = **MI.memoperands_begin();
+      MIRBuilder.buildLoad(TmpReg, MI.getOperand(1).getReg(), MMO);
+      MIRBuilder.buildAnyExt(DstReg, TmpReg);
+      MI.eraseFromParent();
+      return Legalized;
+    }
+
     // This implementation doesn't work for atomics. Give up instead of doing
     // something invalid.
     if (MMO.getOrdering() != AtomicOrdering::NotAtomic ||
@@ -566,8 +578,8 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI,
 
       DstRegs.push_back(DstReg);
     }
-    unsigned DstReg = MI.getOperand(0).getReg();
-    if(MRI.getType(DstReg).isVector())
+
+    if (DstTy.isVector())
       MIRBuilder.buildBuildVector(DstReg, DstRegs);
     else
       MIRBuilder.buildMerge(DstReg, DstRegs);
@@ -608,6 +620,19 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI,
       return UnableToLegalize;
 
     const auto &MMO = **MI.memoperands_begin();
+
+    unsigned SrcReg = MI.getOperand(0).getReg();
+    LLT SrcTy = MRI.getType(SrcReg);
+
+    if (8 * MMO.getSize() != SrcTy.getSizeInBits()) {
+      unsigned TmpReg = MRI.createGenericVirtualRegister(NarrowTy);
+      auto &MMO = **MI.memoperands_begin();
+      MIRBuilder.buildTrunc(TmpReg, SrcReg);
+      MIRBuilder.buildStore(TmpReg, MI.getOperand(1).getReg(), MMO);
+      MI.eraseFromParent();
+      return Legalized;
+    }
+
     // This implementation doesn't work for atomics. Give up instead of doing
     // something invalid.
     if (MMO.getOrdering() != AtomicOrdering::NotAtomic ||
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
index 9e6fa061c10..1338ffed6e0 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
@@ -229,12 +229,31 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST,
     });
 
   getActionDefinitionsBuilder({G_LOAD, G_STORE})
+    .narrowScalarIf([](const LegalityQuery &Query) {
+        unsigned Size = Query.Types[0].getSizeInBits();
+        unsigned MemSize = Query.MMODescrs[0].SizeInBits;
+        return (Size > 32 && MemSize < Size);
+      },
+      [](const LegalityQuery &Query) {
+        return std::make_pair(0, LLT::scalar(32));
+      })
     .legalIf([=, &ST](const LegalityQuery &Query) {
         const LLT &Ty0 = Query.Types[0];
 
+        unsigned Size = Ty0.getSizeInBits();
+        unsigned MemSize = Query.MMODescrs[0].SizeInBits;
+        if (Size > 32 && MemSize < Size)
+          return false;
+
+        if (Ty0.isVector() && Size != MemSize)
+          return false;
+
         // TODO: Decompose private loads into 4-byte components.
         // TODO: Illegal flat loads on SI
-        switch (Ty0.getSizeInBits()) {
+        switch (MemSize) {
+        case 8:
+        case 16:
+          return Size == 32;
         case 32:
         case 64:
         case 128:
@@ -250,7 +269,8 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST,
         default:
           return false;
         }
-      });
+      })
+    .clampScalar(0, S32, S64);
 
 
   auto &ExtLoads = getActionDefinitionsBuilder({G_SEXTLOAD, G_ZEXTLOAD})