[X86][Combine] Ensure single use chain in extract-load combine

The problem is that `SrcBC = peekThroughBitcasts(Src)` doesn't ensure
single use chain. It results in the situation when a cast may have
multiple users and instead of replacing a load we introduce a new one.
The situation is worsened by the fact that we've replaced the token from
the original load and its correct memory order now is not guaranteed.

Author: e-kud

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -46258,7 +46258,8 @@ static SDValue combineExtractWithShuffle(SDNode *N, SelectionDAG &DAG,
 
   // If we're extracting a single element from a broadcast load and there are
   // no other users, just create a single load.
-  if (SrcBC.getOpcode() == X86ISD::VBROADCAST_LOAD && SrcBC.hasOneUse()) {
+  if (peekThroughOneUseBitcasts(Src).getOpcode() == X86ISD::VBROADCAST_LOAD &&
+      SrcBC.hasOneUse()) {
     auto *MemIntr = cast<MemIntrinsicSDNode>(SrcBC);
     unsigned SrcBCWidth = SrcBC.getScalarValueSizeInBits();
     if (MemIntr->getMemoryVT().getSizeInBits() == SrcBCWidth &&

llvm/test/CodeGen/X86/extractelement-load.ll

@@ -573,14 +573,17 @@ define dso_local <2 x float> @multiuse_of_single_value_from_vbroadcast_load(ptr
 ; X64-AVX-LABEL: multiuse_of_single_value_from_vbroadcast_load:
 ; X64-AVX:       # %bb.0:
 ; X64-AVX-NEXT:    pushq %rbx
+; X64-AVX-NEXT:    subq $16, %rsp
 ; X64-AVX-NEXT:    movq %rsi, %rbx
-; X64-AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
-; X64-AVX-NEXT:    vmovsd %xmm0, (%rdi)
+; X64-AVX-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
+; X64-AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; X64-AVX-NEXT:    vmovlps %xmm0, (%rdi)
 ; X64-AVX-NEXT:    vmovaps 32(%rsi), %xmm0
 ; X64-AVX-NEXT:    callq ccosf@PLT
 ; X64-AVX-NEXT:    vmovlps %xmm0, 32(%rbx)
-; X64-AVX-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
+; X64-AVX-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
 ; X64-AVX-NEXT:    callq ccosf@PLT
+; X64-AVX-NEXT:    addq $16, %rsp
 ; X64-AVX-NEXT:    popq %rbx
 ; X64-AVX-NEXT:    retq
   %p1 = getelementptr [5 x <2 x float>], ptr %arr, i64 0, i64 3