Index: llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
+++ llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
@@ -2209,8 +2209,13 @@
   bool Changed = false;
 
   if (MOI.isAtomic()) {
-    if (MOI.getOrdering() == AtomicOrdering::Acquire ||
-        MOI.getOrdering() == AtomicOrdering::Release ||
+    if (MOI.getOrdering() == AtomicOrdering::Acquire)
+      Changed |= CC->insertWait(MI, MOI.getScope(), MOI.getOrderingAddrSpace(),
+                                SIMemOp::LOAD | SIMemOp::STORE,
+                                MOI.getIsCrossAddressSpaceOrdering(),
+                                Position::BEFORE);
+
+    if (MOI.getOrdering() == AtomicOrdering::Release ||
         MOI.getOrdering() == AtomicOrdering::AcquireRelease ||
         MOI.getOrdering() == AtomicOrdering::SequentiallyConsistent)
       /// TODO: This relies on a barrier always generating a waitcnt
Index: llvm/test/CodeGen/AMDGPU/memory-legalizer-fence.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/memory-legalizer-fence.ll
+++ llvm/test/CodeGen/AMDGPU/memory-legalizer-fence.ll
@@ -1335,14 +1335,12 @@
 ;
 ; GFX940-NOTTGSPLIT-LABEL: agent_acquire_fence:
 ; GFX940-NOTTGSPLIT:       ; %bb.0: ; %entry
-; GFX940-NOTTGSPLIT-NEXT:    buffer_wbl2 sc1
 ; GFX940-NOTTGSPLIT-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GFX940-NOTTGSPLIT-NEXT:    buffer_inv sc1
 ; GFX940-NOTTGSPLIT-NEXT:    s_endpgm
 ;
 ; GFX940-TGSPLIT-LABEL: agent_acquire_fence:
 ; GFX940-TGSPLIT:       ; %bb.0: ; %entry
-; GFX940-TGSPLIT-NEXT:    buffer_wbl2 sc1
 ; GFX940-TGSPLIT-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GFX940-TGSPLIT-NEXT:    buffer_inv sc1
 ; GFX940-TGSPLIT-NEXT:    s_endpgm
@@ -1641,14 +1639,12 @@
 ;
 ; GFX940-NOTTGSPLIT-LABEL: agent_one_as_acquire_fence:
 ; GFX940-NOTTGSPLIT:       ; %bb.0: ; %entry
-; GFX940-NOTTGSPLIT-NEXT:    buffer_wbl2 sc1
 ; GFX940-NOTTGSPLIT-NEXT:    s_waitcnt vmcnt(0)
 ; GFX940-NOTTGSPLIT-NEXT:    buffer_inv sc1
 ; GFX940-NOTTGSPLIT-NEXT:    s_endpgm
 ;
 ; GFX940-TGSPLIT-LABEL: agent_one_as_acquire_fence:
 ; GFX940-TGSPLIT:       ; %bb.0: ; %entry
-; GFX940-TGSPLIT-NEXT:    buffer_wbl2 sc1
 ; GFX940-TGSPLIT-NEXT:    s_waitcnt vmcnt(0)
 ; GFX940-TGSPLIT-NEXT:    buffer_inv sc1
 ; GFX940-TGSPLIT-NEXT:    s_endpgm
@@ -1935,7 +1931,6 @@
 ;
 ; GFX90A-NOTTGSPLIT-LABEL: system_acquire_fence:
 ; GFX90A-NOTTGSPLIT:       ; %bb.0: ; %entry
-; GFX90A-NOTTGSPLIT-NEXT:    buffer_wbl2
 ; GFX90A-NOTTGSPLIT-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GFX90A-NOTTGSPLIT-NEXT:    buffer_invl2
 ; GFX90A-NOTTGSPLIT-NEXT:    buffer_wbinvl1_vol
@@ -1943,7 +1938,6 @@
 ;
 ; GFX90A-TGSPLIT-LABEL: system_acquire_fence:
 ; GFX90A-TGSPLIT:       ; %bb.0: ; %entry
-; GFX90A-TGSPLIT-NEXT:    buffer_wbl2
 ; GFX90A-TGSPLIT-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GFX90A-TGSPLIT-NEXT:    buffer_invl2
 ; GFX90A-TGSPLIT-NEXT:    buffer_wbinvl1_vol
@@ -1951,14 +1945,12 @@
 ;
 ; GFX940-NOTTGSPLIT-LABEL: system_acquire_fence:
 ; GFX940-NOTTGSPLIT:       ; %bb.0: ; %entry
-; GFX940-NOTTGSPLIT-NEXT:    buffer_wbl2 sc0 sc1
 ; GFX940-NOTTGSPLIT-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GFX940-NOTTGSPLIT-NEXT:    buffer_inv sc0 sc1
 ; GFX940-NOTTGSPLIT-NEXT:    s_endpgm
 ;
 ; GFX940-TGSPLIT-LABEL: system_acquire_fence:
 ; GFX940-TGSPLIT:       ; %bb.0: ; %entry
-; GFX940-TGSPLIT-NEXT:    buffer_wbl2 sc0 sc1
 ; GFX940-TGSPLIT-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GFX940-TGSPLIT-NEXT:    buffer_inv sc0 sc1
 ; GFX940-TGSPLIT-NEXT:    s_endpgm
@@ -2255,7 +2247,6 @@
 ;
 ; GFX90A-NOTTGSPLIT-LABEL: system_one_as_acquire_fence:
 ; GFX90A-NOTTGSPLIT:       ; %bb.0: ; %entry
-; GFX90A-NOTTGSPLIT-NEXT:    buffer_wbl2
 ; GFX90A-NOTTGSPLIT-NEXT:    s_waitcnt vmcnt(0)
 ; GFX90A-NOTTGSPLIT-NEXT:    buffer_invl2
 ; GFX90A-NOTTGSPLIT-NEXT:    buffer_wbinvl1_vol
@@ -2263,7 +2254,6 @@
 ;
 ; GFX90A-TGSPLIT-LABEL: system_one_as_acquire_fence:
 ; GFX90A-TGSPLIT:       ; %bb.0: ; %entry
-; GFX90A-TGSPLIT-NEXT:    buffer_wbl2
 ; GFX90A-TGSPLIT-NEXT:    s_waitcnt vmcnt(0)
 ; GFX90A-TGSPLIT-NEXT:    buffer_invl2
 ; GFX90A-TGSPLIT-NEXT:    buffer_wbinvl1_vol
@@ -2271,14 +2261,12 @@
 ;
 ; GFX940-NOTTGSPLIT-LABEL: system_one_as_acquire_fence:
 ; GFX940-NOTTGSPLIT:       ; %bb.0: ; %entry
-; GFX940-NOTTGSPLIT-NEXT:    buffer_wbl2 sc0 sc1
 ; GFX940-NOTTGSPLIT-NEXT:    s_waitcnt vmcnt(0)
 ; GFX940-NOTTGSPLIT-NEXT:    buffer_inv sc0 sc1
 ; GFX940-NOTTGSPLIT-NEXT:    s_endpgm
 ;
 ; GFX940-TGSPLIT-LABEL: system_one_as_acquire_fence:
 ; GFX940-TGSPLIT:       ; %bb.0: ; %entry
-; GFX940-TGSPLIT-NEXT:    buffer_wbl2 sc0 sc1
 ; GFX940-TGSPLIT-NEXT:    s_waitcnt vmcnt(0)
 ; GFX940-TGSPLIT-NEXT:    buffer_inv sc0 sc1
 ; GFX940-TGSPLIT-NEXT:    s_endpgm