Rebase

Author: Pierre-vh

llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp

@@ -1092,12 +1092,13 @@ void WaitcntBrackets::updateByEvent(WaitEventType E, MachineInstr &Inst) {
             }
           }
         }
-        if (Slot || LDSDMAStores.size() == NUM_LDSDMA - 1)
+        if (Slot)
           break;
         // The slot may not be valid because it can be >= NUM_LDSDMA which
         // means the scoreboard cannot track it. We still want to preserve the
         // MI in order to check alias information, though.
         LDSDMAStores.push_back(&Inst);
+        Slot = LDSDMAStores.size();
         break;
       }
       setVMemScore(LDSDMA_BEGIN, T, CurrScore);

llvm/test/CodeGen/AMDGPU/lds-dma-waits.ll

@@ -221,7 +221,7 @@ define amdgpu_kernel void @buffer_load_lds_dword_10_arrays(<4 x i32> %rsrc, i32
 ; GFX9-NEXT:    s_waitcnt vmcnt(2)
 ; GFX9-NEXT:    ds_read_b32 v7, v9 offset:1792
 ; GFX9-NEXT:    ; wave barrier
-; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_waitcnt vmcnt(1)
 ; GFX9-NEXT:    ds_read_b32 v8, v9 offset:2048
 ; GFX9-NEXT:    ; wave barrier
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
@@ -288,7 +288,7 @@ define amdgpu_kernel void @buffer_load_lds_dword_10_arrays(<4 x i32> %rsrc, i32
 ; GFX10-NEXT:    s_waitcnt vmcnt(2)
 ; GFX10-NEXT:    ds_read_b32 v7, v9 offset:1792
 ; GFX10-NEXT:    ; wave barrier
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    s_waitcnt vmcnt(1)
 ; GFX10-NEXT:    ds_read_b32 v8, v9 offset:2048
 ; GFX10-NEXT:    ; wave barrier
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)