[AMDGPU] Increate hazard for store dwordx3/4 to 2 waitstates on gfx940

[rampitec]

Summary

Fixes: SWDEV-327053

[kzhuravl]

LGTM, thanks!

llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp

 
 int
 GCNHazardRecognizer::checkVALUHazardsHelper(const MachineOperand &Def,
                                             const MachineRegisterInfo &MRI) {
   // Helper to check for the hazard where VMEM instructions that store more than
   // 8 bytes can have there store data over written by the next instruction.
   const SIRegisterInfo *TRI = ST.getRegisterInfo();
 
-  const int VALUWaitStates = 1;
+  const int VALUWaitStates = ST.hasGFX940Insts() ? 2 : 1;
   int WaitStatesNeeded = 0;
 
   if (!TRI->isVectorRegister(MRI, Def.getReg()))
     return WaitStatesNeeded;
   Register Reg = Def.getReg();
   auto IsHazardFn = [this, Reg, TRI](const MachineInstr &MI) {
     int DataIdx = createsVALUHazard(MI);
     return DataIdx >= 0 &&

llvm/test/CodeGen/AMDGPU/gfx940-hazards.mir

 # GCN-NEXT: S_NOP 0
 # GCN-NEXT: V_READFIRSTLANE_B32
 name:            valu_write_vgpr_readfirstlane_read
 body:             |
   bb.0:
     $vgpr1 = V_ADD_CO_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $exec
     $sgpr1 = V_READFIRSTLANE_B32 $vgpr1, implicit $exec
 ...
+
+# GCN-LABEL: name: global_store_dwordx4_data_hazard
+# GCN:      GLOBAL_STORE_DWORDX4
+# GCN-NEXT: S_NOP 1
+# GCN-NEXT: V_MOV_B32_e32
+name: global_store_dwordx4_data_hazard
+
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
+    GLOBAL_STORE_DWORDX4 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5, 0, 0, implicit $exec
+    $vgpr2 = V_MOV_B32_e32 0, implicit $exec
+...
+
+# GCN-LABEL: name: global_store_dwordx3_data_hazard
+# GCN:      GLOBAL_STORE_DWORDX3
+# GCN-NEXT: S_NOP 1
+# GCN-NEXT: V_MOV_B32_e32
+name: global_store_dwordx3_data_hazard
+
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4
+    GLOBAL_STORE_DWORDX3 $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4, 0, 0, implicit $exec
+    $vgpr2 = V_MOV_B32_e32 0, implicit $exec
+...

llvm/test/CodeGen/AMDGPU/mai-hazards-gfx940.mir

 name:            dgemm_to_fmac64
 body:             |
   bb.0:
     $vgpr0_vgpr1 = V_MFMA_F64_4X4X4F64_vgprcd_e64 $vgpr0_vgpr1, $vgpr0_vgpr1, $vgpr0_vgpr1, 0, 0, 0, implicit $mode, implicit $exec
     $vgpr4_vgpr5 = V_FMAC_F64_e32 $vgpr4_vgpr5, $vgpr4_vgpr5, $vgpr4_vgpr5, implicit $mode, implicit $exec
 ...
 # GCN-LABEL: name: flat_store_data_agpr_overwritten
 # GCN:      FLAT_STORE_DWORDX4
-# GCN-NEXT: S_NOP 0
+# GCN-NEXT: S_NOP 1
 # GCN-NEXT: V_ACCVGPR_WRITE_B32_e64
 name: flat_store_data_agpr_overwritten
 body: |
   bb.0:
     FLAT_STORE_DWORDX4 $vgpr4_vgpr5, $agpr0_agpr1_agpr2_agpr3, 0, 0, implicit $mode, implicit $exec, implicit $flat_scr
     $agpr0 = V_ACCVGPR_WRITE_B32_e64 0, implicit $mode, implicit $exec
 ...
 # GCN-LABEL: name: dot_write_vgpr_accv_read