[X86] Add a combine to turn (insert_subvector zero, (insert_subvector zero, X, Idx), Idx) into an insert of X into the larger zero vector.

llvm-svn: 312460

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -35656,11 +35656,22 @@ static SDValue combineInsertSubvector(SDNode *N, SelectionDAG &DAG,
   unsigned IdxVal = cast<ConstantSDNode>(Idx)->getZExtValue();
   MVT SubVecVT = SubVec.getSimpleValueType();
 
+  if (ISD::isBuildVectorAllZeros(Vec.getNode())) {
     // Inserting zeros into zeros is a nop.
-  if (ISD::isBuildVectorAllZeros(Vec.getNode()) &&
+    if (ISD::isBuildVectorAllZeros(SubVec.getNode()))
-      ISD::isBuildVectorAllZeros(SubVec.getNode()))
       return Vec;
 
+    // If we're inserting into a zero vector and then into a larger zero vector,
+    // just insert into the larger zero vector directly.
+    if (SubVec.getOpcode() == ISD::INSERT_SUBVECTOR &&
+        ISD::isBuildVectorAllZeros(SubVec.getOperand(0).getNode())) {
+      unsigned Idx2Val = cast<ConstantSDNode>(Idx)->getZExtValue();
+      return DAG.getNode(ISD::INSERT_SUBVECTOR, dl, OpVT, Vec,
+                         SubVec.getOperand(1),
+                         DAG.getIntPtrConstant(IdxVal + Idx2Val, dl));
+    }
+  }
+
   // If this is an insert of an extract, combine to a shuffle. Don't do this
   // if the insert or extract can be represented with a subregister operation.
   if (SubVec.getOpcode() == ISD::EXTRACT_SUBVECTOR &&

llvm/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll

@@ -1134,13 +1134,11 @@ define <8 x double> @test_mm512_zextpd128_pd512(<2 x double> %a0) nounwind {
 ; X32-LABEL: test_mm512_zextpd128_pd512:
 ; X32:       # BB#0:
 ; X32-NEXT:    vmovaps %xmm0, %xmm0
-; X32-NEXT:    vmovaps %ymm0, %ymm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm512_zextpd128_pd512:
 ; X64:       # BB#0:
 ; X64-NEXT:    vmovaps %xmm0, %xmm0
-; X64-NEXT:    vmovaps %ymm0, %ymm0
 ; X64-NEXT:    retq
   %res = shufflevector <2 x double> %a0, <2 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3>
   ret <8 x double> %res
@@ -1196,13 +1194,11 @@ define <8 x i64> @test_mm512_zextsi128_si512(<2 x i64> %a0) nounwind {
 ; X32-LABEL: test_mm512_zextsi128_si512:
 ; X32:       # BB#0:
 ; X32-NEXT:    vmovaps %xmm0, %xmm0
-; X32-NEXT:    vmovaps %ymm0, %ymm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm512_zextsi128_si512:
 ; X64:       # BB#0:
 ; X64-NEXT:    vmovaps %xmm0, %xmm0
-; X64-NEXT:    vmovaps %ymm0, %ymm0
 ; X64-NEXT:    retq
   %res = shufflevector <2 x i64> %a0, <2 x i64> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3>
   ret <8 x i64> %res

llvm/test/CodeGen/X86/merge-consecutive-loads-512.ll

@@ -107,14 +107,12 @@ define <8 x double> @merge_8f64_f64_12zzuuzz(double* %ptr) nounwind uwtable noin
 ; ALL-LABEL: merge_8f64_f64_12zzuuzz:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vmovaps 8(%rdi), %xmm0
-; ALL-NEXT:    vmovaps %ymm0, %ymm0
 ; ALL-NEXT:    retq
 ;
 ; X32-AVX512F-LABEL: merge_8f64_f64_12zzuuzz:
 ; X32-AVX512F:       # BB#0:
 ; X32-AVX512F-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-AVX512F-NEXT:    vmovaps 8(%eax), %xmm0
-; X32-AVX512F-NEXT:    vmovaps %ymm0, %ymm0
 ; X32-AVX512F-NEXT:    retl
   %ptr0 = getelementptr inbounds double, double* %ptr, i64 1
   %ptr1 = getelementptr inbounds double, double* %ptr, i64 2