Index: llvm/lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
===================================================================
--- llvm/lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
+++ llvm/lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
@@ -406,7 +406,9 @@
   // If the load and store are consecutive, use the loadInst location to
   // reduce register pressure.
   MachineInstr *StInst = StoreInst;
-  if (StoreInst->getPrevNode() == LoadInst)
+  auto PrevInstrIt = skipDebugInstructionsBackward(
+      --MachineBasicBlock::instr_iterator(StoreInst), MBB->instr_begin());
+  if (PrevInstrIt.getNodePtr() == LoadInst)
     StInst = LoadInst;
   MachineInstr *NewStore =
       BuildMI(*MBB, StInst, StInst->getDebugLoc(), TII->get(NStoreOpcode))
@@ -530,7 +532,7 @@
       if (!isPotentialBlockedMemCpyLd(MI.getOpcode()))
         continue;
       int DefVR = MI.getOperand(0).getReg();
-      if (!MRI->hasOneUse(DefVR))
+      if (!MRI->hasOneNonDBGUse(DefVR))
         continue;
       for (auto UI = MRI->use_nodbg_begin(DefVR), UE = MRI->use_nodbg_end();
            UI != UE;) {
Index: llvm/test/CodeGen/X86/avoid-sfb-g-no-change.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/X86/avoid-sfb-g-no-change.ll
@@ -0,0 +1,98 @@
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu | FileCheck %s
+
+; This was generated from:
+;
+; using alpha = float __attribute__((ext_vector_type(4)));
+;
+; void bravo(alpha charlie) {
+;   unsigned char *delta = (unsigned char *)&charlie;
+;   delta[0] = 0;
+;   volatile alpha echo = charlie;
+; }
+;
+; Using the command line:
+; clang -g -c 1.cpp -O2 -S -emit-llvm -fno-strict-aliasing --target=x86_64-unknown-unknown -o test.ll
+
+; CHECK: 	movaps	%xmm0, -16(%rbp)
+; CHECK: 	movb	$0, -16(%rbp)
+; CHECK: 	movb	-16(%rbp), %al
+; CHECK: 	movb	%al, -32(%rbp)
+; CHECK: 	movq	-15(%rbp), %rax
+; CHECK: 	movq	%rax, -31(%rbp)
+; CHECK: 	movl	-7(%rbp), %eax
+; CHECK: 	movl	%eax, -23(%rbp)
+; CHECK: 	movzwl	-3(%rbp), %eax
+; CHECK: 	movw	%ax, -19(%rbp)
+; CHECK: 	movb	-1(%rbp), %al
+; CHECK: 	movb	%al, -17(%rbp)
+
+; Function Attrs: nounwind uwtable
+define dso_local void @_Z5bravoDv4_f(<4 x float> %charlie) local_unnamed_addr #0 !dbg !10 {
+entry:
+  %charlie.addr = alloca <4 x float>, align 16
+  %echo = alloca <4 x float>, align 16
+  call void @llvm.dbg.value(metadata <4 x float> %charlie, metadata !19, metadata !DIExpression()), !dbg !23
+  store <4 x float> %charlie, <4 x float>* %charlie.addr, align 16
+  call void @llvm.dbg.value(metadata i8* undef, metadata !20, metadata !DIExpression()), !dbg !24
+  %charlie.addr.0.charlie.addr.0.arrayidx.sroa_cast = bitcast <4 x float>* %charlie.addr to i8*, !dbg !25
+  store i8 0, i8* %charlie.addr.0.charlie.addr.0.arrayidx.sroa_cast, align 16, !dbg !25
+  %echo.0.echo.0..sroa_cast = bitcast <4 x float>* %echo to i8*, !dbg !26
+  call void @llvm.lifetime.start.p0i8(i64 16, i8* nonnull %echo.0.echo.0..sroa_cast), !dbg !26
+  call void @llvm.dbg.declare(metadata <4 x float>* %echo, metadata !21, metadata !DIExpression()), !dbg !27
+  %charlie.addr.0.charlie.addr.0. = load <4 x float>, <4 x float>* %charlie.addr, align 16, !dbg !28
+  call void @llvm.dbg.value(metadata <4 x float> %charlie.addr.0.charlie.addr.0., metadata !19, metadata !DIExpression()), !dbg !23
+  store volatile <4 x float> %charlie.addr.0.charlie.addr.0., <4 x float>* %echo, align 16, !dbg !27
+  call void @llvm.lifetime.end.p0i8(i64 16, i8* nonnull %echo.0.echo.0..sroa_cast), !dbg !29
+  ret void, !dbg !29
+}
+
+; Function Attrs: nounwind readnone speculatable
+declare void @llvm.dbg.declare(metadata, metadata, metadata) #1
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture) #2
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture) #2
+
+; Function Attrs: nounwind readnone speculatable
+declare void @llvm.dbg.value(metadata, metadata, metadata) #1
+
+attributes #0 = { nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="128" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { nounwind readnone speculatable }
+attributes #2 = { argmemonly nounwind }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!6, !7, !8}
+!llvm.ident = !{!9}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 9.0.0 (https://github.com/llvm/llvm-project.git c4018508182effbdf77905533365ee9ee5ae9a12)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, retainedTypes: !3, nameTableKind: None)
+!1 = !DIFile(filename: "1.cpp", directory: "C:\5CUsers\5Cgbdawsoc\5CDocuments\5Cllvm\5Cbg40969")
+!2 = !{}
+!3 = !{!4}
+!4 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !5, size: 64)
+!5 = !DIBasicType(name: "unsigned char", size: 8, encoding: DW_ATE_unsigned_char)
+!6 = !{i32 2, !"Dwarf Version", i32 4}
+!7 = !{i32 2, !"Debug Info Version", i32 3}
+!8 = !{i32 1, !"wchar_size", i32 4}
+!9 = !{!"clang version 9.0.0 (https://github.com/llvm/llvm-project.git c4018508182effbdf77905533365ee9ee5ae9a12)"}
+!10 = distinct !DISubprogram(name: "bravo", linkageName: "_Z5bravoDv4_f", scope: !1, file: !1, line: 3, type: !11, scopeLine: 3, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !18)
+!11 = !DISubroutineType(types: !12)
+!12 = !{null, !13}
+!13 = !DIDerivedType(tag: DW_TAG_typedef, name: "alpha", file: !1, line: 1, baseType: !14)
+!14 = !DICompositeType(tag: DW_TAG_array_type, baseType: !15, size: 128, flags: DIFlagVector, elements: !16)
+!15 = !DIBasicType(name: "float", size: 32, encoding: DW_ATE_float)
+!16 = !{!17}
+!17 = !DISubrange(count: 4)
+!18 = !{!19, !20, !21}
+!19 = !DILocalVariable(name: "charlie", arg: 1, scope: !10, file: !1, line: 3, type: !13)
+!20 = !DILocalVariable(name: "delta", scope: !10, file: !1, line: 4, type: !4)
+!21 = !DILocalVariable(name: "echo", scope: !10, file: !1, line: 6, type: !22)
+!22 = !DIDerivedType(tag: DW_TAG_volatile_type, baseType: !13)
+!23 = !DILocation(line: 3, column: 18, scope: !10)
+!24 = !DILocation(line: 4, column: 18, scope: !10)
+!25 = !DILocation(line: 5, column: 12, scope: !10)
+!26 = !DILocation(line: 6, column: 3, scope: !10)
+!27 = !DILocation(line: 6, column: 18, scope: !10)
+!28 = !DILocation(line: 6, column: 25, scope: !10)
+!29 = !DILocation(line: 7, column: 1, scope: !10)