diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -12296,13 +12296,17 @@
   MachineBasicBlock *Exit = ML->getExitBlock();
 
   if (Pre && Exit) {
-    BuildMI(*Pre, Pre->getFirstTerminator(), DebugLoc(),
-            TII->get(AMDGPU::S_INST_PREFETCH))
-      .addImm(1); // prefetch 2 lines behind PC
-
-    BuildMI(*Exit, Exit->getFirstNonDebugInstr(), DebugLoc(),
-            TII->get(AMDGPU::S_INST_PREFETCH))
-      .addImm(2); // prefetch 1 line behind PC
+    auto PreTerm = Pre->getFirstTerminator();
+    if (PreTerm == Pre->begin() ||
+        std::prev(PreTerm)->getOpcode() != AMDGPU::S_INST_PREFETCH)
+      BuildMI(*Pre, PreTerm, DebugLoc(), TII->get(AMDGPU::S_INST_PREFETCH))
+          .addImm(1); // prefetch 2 lines behind PC
+
+    auto ExitHead = Exit->getFirstNonDebugInstr();
+    if (ExitHead == Exit->end() ||
+        ExitHead->getOpcode() != AMDGPU::S_INST_PREFETCH)
+      BuildMI(*Exit, ExitHead, DebugLoc(), TII->get(AMDGPU::S_INST_PREFETCH))
+          .addImm(2); // prefetch 1 line behind PC
   }
 
   return CacheLineAlign;
diff --git a/llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll b/llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll
--- a/llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll
+++ b/llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll
@@ -11,8 +11,6 @@
 ; GFX10-NEXT:    s_mov_b32 s1, 0
 ; GFX10-NEXT:    ; implicit-def: $sgpr2
 ; GFX10-NEXT:    s_inst_prefetch 0x1
-; GFX10-NEXT:    s_inst_prefetch 0x1
-; GFX10-NEXT:    s_inst_prefetch 0x1
 ; GFX10-NEXT:    s_branch .LBB0_2
 ; GFX10-NEXT:    .p2align 6
 ; GFX10-NEXT:  .LBB0_1: ; %Flow
@@ -50,8 +48,6 @@
 ; GFX10-NEXT:    s_branch .LBB0_1
 ; GFX10-NEXT:  .LBB0_4: ; %loop0_merge
 ; GFX10-NEXT:    s_inst_prefetch 0x2
-; GFX10-NEXT:    s_inst_prefetch 0x2
-; GFX10-NEXT:    s_inst_prefetch 0x2
 ; GFX10-NEXT:    s_endpgm
 branch1_true:
   br label %2