[PowerPC] allow D-form VSX load/store when accessing FrameIndex without offset

VSX D-form load/store instructions of POWER9 require the offset be a multiple of 16 and a helper`isOffsetMultipleOf` is used to check this.
So far, the helper handles FrameIndex + offset case, but not handling FrameIndex without offset case. Due to this, we are missing opportunities to exploit D-form instructions when accessing an object or array allocated on stack.
For example, x-form store (stxvx) is used for int a[4] = {0}; instead of d-form store (stxv). For larger arrays, D-form instruction is not used when accessing the first 16-byte. Using D-form instructions reduces register pressure as well as instructions.

Differential Revision: https://reviews.llvm.org/D45079

llvm-svn: 329377

2 files changed, 54 insertions, 8 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp b/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
index ec822aa53ca..bb9d5244f0e 100644
--- a/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
@@ -3937,20 +3937,28 @@ bool PPCDAGToDAGISel::isOffsetMultipleOf(SDNode *N, unsigned Val) const {
   else if (STN)
     AddrOp = STN->getOperand(2);
 
+  // If the address points a frame object or a frame object with an offset,
+  // we need to check the object alignment.
   short Imm = 0;
-  if (AddrOp.getOpcode() == ISD::ADD) {
+  if (FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(
+          AddrOp.getOpcode() == ISD::ADD ? AddrOp.getOperand(0) :
+                                           AddrOp)) {
     // If op0 is a frame index that is under aligned, we can't do it either,
     // because it is translated to r31 or r1 + slot + offset. We won't know the
     // slot number until the stack frame is finalized.
-    if (FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(AddrOp.getOperand(0))) {
-      const MachineFrameInfo &MFI = CurDAG->getMachineFunction().getFrameInfo();
-      unsigned SlotAlign = MFI.getObjectAlignment(FI->getIndex());
-      if ((SlotAlign % Val) != 0)
-        return false;
-    }
-    return isIntS16Immediate(AddrOp.getOperand(1), Imm) && !(Imm % Val);
+    const MachineFrameInfo &MFI = CurDAG->getMachineFunction().getFrameInfo();
+    unsigned SlotAlign = MFI.getObjectAlignment(FI->getIndex());
+    if ((SlotAlign % Val) != 0)
+      return false;
+
+    // If we have an offset, we need further check on the offset.
+    if (AddrOp.getOpcode() != ISD::ADD)
+      return true;
   }
 
+  if (AddrOp.getOpcode() == ISD::ADD)
+    return isIntS16Immediate(AddrOp.getOperand(1), Imm) && !(Imm % Val);
+
   // If the address comes from the outside, the offset will be zero.
   return AddrOp.getOpcode() == ISD::CopyFromReg;
 }
diff --git a/llvm/test/CodeGen/PowerPC/vsx-p9.ll b/llvm/test/CodeGen/PowerPC/vsx-p9.ll
index 1ca679f474c..d7bea34f754 100644
--- a/llvm/test/CodeGen/PowerPC/vsx-p9.ll
+++ b/llvm/test/CodeGen/PowerPC/vsx-p9.ll
@@ -411,3 +411,41 @@ entry:
 }
 
 declare void @sink(...)
+
+; stack object should be accessed using D-form load/store instead of X-form
+define signext i32 @func1() {
+; CHECK-LABEL: @func1
+; CHECK-NOT: stxvx
+; CHECK: stxv {{[0-9]+}}, {{[0-9]+}}(1)
+; CHECK-NOT: stxvx
+; CHECK: blr
+entry:
+  %a = alloca [4 x i32], align 4
+  %0 = bitcast [4 x i32]* %a to i8*
+  call void @llvm.memset.p0i8.i64(i8* nonnull align 4 %0, i8 0, i64 16, i1 false)
+  %arraydecay = getelementptr inbounds [4 x i32], [4 x i32]* %a, i64 0, i64 0
+  %call = call signext i32 @callee(i32* nonnull %arraydecay) #3
+  ret i32 %call
+}
+
+; stack object should be accessed using D-form load/store instead of X-form
+define signext i32 @func2() {
+; CHECK-LABEL: @func2
+; CHECK-NOT: stxvx
+; CHECK: stxv [[ZEROREG:[0-9]+]], {{[0-9]+}}(1)
+; CHECK: stxv [[ZEROREG]], {{[0-9]+}}(1)
+; CHECK: stxv [[ZEROREG]], {{[0-9]+}}(1)
+; CHECK: stxv [[ZEROREG]], {{[0-9]+}}(1)
+; CHECK-NOT: stxvx
+; CHECK: blr
+entry:
+  %a = alloca [16 x i32], align 4
+  %0 = bitcast [16 x i32]* %a to i8*
+  call void @llvm.memset.p0i8.i64(i8* nonnull align 4 %0, i8 0, i64 64, i1 false)
+  %arraydecay = getelementptr inbounds [16 x i32], [16 x i32]* %a, i64 0, i64 0
+  %call = call signext i32 @callee(i32* nonnull %arraydecay) #3
+  ret i32 %call
+}
+
+declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) #1
+declare signext i32 @callee(i32*) local_unnamed_addr #2