AMDGPU: Handle gfx950 change in mfma_f64_16x16x4 + valu hazard (#117262)

Increase from 11 wait states to 19

Author: arsenm

llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp

@@ -2603,6 +2603,7 @@ int GCNHazardRecognizer::checkMAIVALUHazards(MachineInstr *MI) {
     const int DMFMA16x16WriteVgprMemExpReadWaitStates = 18;
     const int DMFMA4x4WriteVgprVALUReadWaitStates = 6;
     const int DMFMA16x16WriteVgprVALUReadWaitStates = 11;
+    const int GFX950_DMFMA16x16WriteVgprVALUReadWaitStates = 19;
     const int DotWriteSameDotReadSrcAB = 3;
     const int DotWriteDifferentVALURead = 3;
     const int DMFMABetweenVALUWriteVMEMRead = 2;
@@ -2663,9 +2664,12 @@ int GCNHazardRecognizer::checkMAIVALUHazards(MachineInstr *MI) {
           break;
         case 8:
         case 16:
-          NeedWaitStates = IsMemOrExport
-                               ? DMFMA16x16WriteVgprMemExpReadWaitStates
-                               : DMFMA16x16WriteVgprVALUReadWaitStates;
+          NeedWaitStates =
+              IsMemOrExport
+                  ? DMFMA16x16WriteVgprMemExpReadWaitStates
+                  : (ST.hasGFX950Insts()
+                         ? GFX950_DMFMA16x16WriteVgprVALUReadWaitStates
+                         : DMFMA16x16WriteVgprVALUReadWaitStates);
           break;
         default:
           llvm_unreachable("unexpected dgemm");

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

@@ -1,4 +1,5 @@
-# RUN: llc -mtriple=amdgcn -mcpu=gfx940 -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefix=GCN %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx940 -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefixes=GCN,GFX940 %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx950 -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefixes=GCN,GFX950 %s
 
 # GCN-LABEL: name: valu_write_vgpr_sgemm_mfma_read
 # GCN:      V_MOV_B32
@@ -803,8 +804,12 @@ body:             |
 ...
 # GCN-LABEL: name: dmfma16x16_write_vgpr_valu_read
 # GCN:      V_MFMA
-# GCN-NEXT: S_NOP 7
-# GCN-NEXT: S_NOP 2
+# GFX940-NEXT: S_NOP 7
+# GFX940-NEXT: S_NOP 2
+
+# GFX950-NEXT: S_NOP 7
+# GFX950-NEXT: S_NOP 7
+# GFX950-NEXT: S_NOP 2
 # GCN-NEXT: V_MOV_B32
 name:            dmfma16x16_write_vgpr_valu_read
 body:             |
@@ -867,8 +872,13 @@ body:             |
 ...
 # GCN-LABEL: name: dmfma16x16_write_vgpr_dot_read
 # GCN:      V_MFMA
-# GCN-NEXT: S_NOP 7
-# GCN-NEXT: S_NOP 2
+# GFX940-NEXT: S_NOP 7
+# GFX940-NEXT: S_NOP 2
+
+# GFX950-NEXT: S_NOP 7
+# GFX950-NEXT: S_NOP 7
+# GFX950-NEXT: S_NOP 2
+
 # GCN-NEXT: V_DOT
 name:            dmfma16x16_write_vgpr_dot_read
 body:             |
@@ -1505,8 +1515,12 @@ body:             |
 ...
 # GCN-LABEL: name: dmfma16x16_write_agpr_valu_read
 # GCN:      V_MFMA
-# GCN-NEXT: S_NOP 7
-# GCN-NEXT: S_NOP 2
+# GFX940-NEXT: S_NOP 7
+# GFX940-NEXT: S_NOP 2
+
+# GFX950-NEXT: S_NOP 7
+# GFX950-NEXT: S_NOP 7
+# GFX950-NEXT: S_NOP 2
 # GCN-NEXT: V_ACCVGPR_READ_B32_e64
 name:            dmfma16x16_write_agpr_valu_read
 body:             |