add v_cndmask_t16 to hazardmask

Author: broxigarchen

llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp

@@ -2994,7 +2994,9 @@ bool GCNHazardRecognizer::fixVALUMaskWriteHazard(MachineInstr *MI) {
     switch (I.getOpcode()) {
     case AMDGPU::V_ADDC_U32_e32:
     case AMDGPU::V_ADDC_U32_dpp:
+    case AMDGPU::V_CNDMASK_B16_t16_e32:
     case AMDGPU::V_CNDMASK_B16_fake16_e32:
+    case AMDGPU::V_CNDMASK_B16_t16_dpp:
     case AMDGPU::V_CNDMASK_B16_fake16_dpp:
     case AMDGPU::V_CNDMASK_B32_e32:
     case AMDGPU::V_CNDMASK_B32_dpp:
@@ -3010,7 +3012,9 @@ bool GCNHazardRecognizer::fixVALUMaskWriteHazard(MachineInstr *MI) {
              HazardReg == AMDGPU::VCC_HI;
     case AMDGPU::V_ADDC_U32_e64:
     case AMDGPU::V_ADDC_U32_e64_dpp:
+    case AMDGPU::V_CNDMASK_B16_t16_e64:
     case AMDGPU::V_CNDMASK_B16_fake16_e64:
+    case AMDGPU::V_CNDMASK_B16_t16_e64_dpp:
     case AMDGPU::V_CNDMASK_B16_fake16_e64_dpp:
     case AMDGPU::V_CNDMASK_B32_e64:
     case AMDGPU::V_CNDMASK_B32_e64_dpp:

llvm/test/CodeGen/AMDGPU/valu-mask-write-hazard-true16.mir

@@ -0,0 +1,20 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -mattr=+real-true16 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN %s
+
+--- |
+  @mem = internal unnamed_addr addrspace(4) constant [4 x <4 x i32>] [<4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>]
+
+  define amdgpu_gs void @mask_hazard_cndmask_t16_dpp4() { ret void }
+---
+name:            mask_hazard_cndmask_t16_dpp4
+body:            |
+  bb.0:
+    ; GCN-LABEL: name: mask_hazard_cndmask_t16_dpp4
+    ; GCN: $vgpr0_lo16 = V_CNDMASK_B16_t16_e64_dpp $vgpr0_lo16, 0, $vgpr1_lo16, 0, $vgpr2_lo16, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
+    ; GCN-NEXT: $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
+    ; GCN-NEXT: S_WAITCNT_DEPCTR 65534
+    ; GCN-NEXT: S_ENDPGM 0
+    $vgpr0_lo16 = V_CNDMASK_B16_t16_e64_dpp $vgpr0_lo16, 0, $vgpr1_lo16, 0, $vgpr2_lo16, $sgpr2_sgpr3, 0, 1, 15, 15, 1, implicit $exec
+    $sgpr2_sgpr3 = S_CSELECT_B64 -1, 0, implicit $scc
+    S_ENDPGM 0
+...