[AMDGPU] Improve zeroesHigh16BitsOfDest for GFX9 legacy opcodes

[foad]

Summary

Pseudos like V_MAD_U16 and V_FMA_F16 map down to what GFX9 calls
v_mad_legacy_u16 and v_fma_legacy_f16, which are documented to have the
same zeroing behaviour as on GFX8.

[arsenm]

It would be nice to have end to end tests for these cases to make sure the encoding ends up OK

llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp

bool GCNSubtarget::zeroesHigh16BitsOfDest(unsigned Opcode) const {
   case AMDGPU::V_MAX_U16_e64:
   case AMDGPU::V_MAX_U16_e32:
   case AMDGPU::V_MIN_U16_e64:
   case AMDGPU::V_MIN_U16_e32:
   case AMDGPU::V_MAX_I16_e64:
   case AMDGPU::V_MAX_I16_e32:
   case AMDGPU::V_MIN_I16_e64:
   case AMDGPU::V_MIN_I16_e32:
+  case AMDGPU::V_MAD_F16_e64:
+  case AMDGPU::V_MAD_U16_e64:
+  case AMDGPU::V_MAD_I16_e64:
+  case AMDGPU::V_FMA_F16_e64:
+  case AMDGPU::V_DIV_FIXUP_F16_e64:
     // On gfx10, all 16-bit instructions preserve the high bits.
     return getGeneration() <= AMDGPUSubtarget::GFX9;
-  case AMDGPU::V_MAD_F16_e64:
   case AMDGPU::V_MADAK_F16:
   case AMDGPU::V_MADMK_F16:
   case AMDGPU::V_MAC_F16_e64:
   case AMDGPU::V_MAC_F16_e32:
   case AMDGPU::V_FMAMK_F16:
   case AMDGPU::V_FMAAK_F16:
-  case AMDGPU::V_MAD_U16_e64:
-  case AMDGPU::V_MAD_I16_e64:
-  case AMDGPU::V_FMA_F16_e64:
   case AMDGPU::V_FMAC_F16_e64:
   case AMDGPU::V_FMAC_F16_e32:
-  case AMDGPU::V_DIV_FIXUP_F16_e64:
     // In gfx9, the preferred handling of the unused high 16-bits changed. Most
     // instructions maintain the legacy behavior of 0ing. Some instructions
     // changed to preserving the high bits.
     return getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS;
   case AMDGPU::V_MAD_MIXLO_F16:
   case AMDGPU::V_MAD_MIXHI_F16:
   default:
     return false;

llvm/test/CodeGen/AMDGPU/high-bits-zeroed-16-bit-ops.mir

bb.0:
     ; GFX8-NEXT: $vgpr0 = COPY %op
     ; GFX9-LABEL: name: v_mad_f16
     ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
     ; GFX9-NEXT: {{  $}}
     ; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
     ; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
     ; GFX9-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
     ; GFX9-NEXT: %op:vgpr_32 = nofpexcept V_MAD_F16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
-    ; GFX9-NEXT: %and:vgpr_32 = V_AND_B32_e32 65535, %op, implicit $exec
-    ; GFX9-NEXT: $vgpr0 = COPY %and
+    ; GFX9-NEXT: $vgpr0 = COPY %op
     ; GFX10-LABEL: name: v_mad_f16
     ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
     ; GFX10-NEXT: {{  $}}
     ; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
     ; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
     ; GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
     ; GFX10-NEXT: %op:vgpr_32 = nofpexcept V_MAD_F16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
     ; GFX10-NEXT: %and:vgpr_32 = V_AND_B32_e32 65535, %op, implicit $exec
bb.0:
     ; GFX8-NEXT: $vgpr0 = COPY %op
     ; GFX9-LABEL: name: v_fma_f16
     ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
     ; GFX9-NEXT: {{  $}}
     ; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
     ; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
     ; GFX9-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
     ; GFX9-NEXT: %op:vgpr_32 = nofpexcept V_FMA_F16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
-    ; GFX9-NEXT: %and:vgpr_32 = V_AND_B32_e32 65535, %op, implicit $exec
-    ; GFX9-NEXT: $vgpr0 = COPY %and
+    ; GFX9-NEXT: $vgpr0 = COPY %op
     ; GFX10-LABEL: name: v_fma_f16
     ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
     ; GFX10-NEXT: {{  $}}
     ; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
     ; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
     ; GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
     ; GFX10-NEXT: %op:vgpr_32 = nofpexcept V_FMA_F16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
     ; GFX10-NEXT: %and:vgpr_32 = V_AND_B32_e32 65535, %op, implicit $exec
bb.0:
     ; GFX8-NEXT: $vgpr0 = COPY %op
     ; GFX9-LABEL: name: v_div_fixup_f16
     ; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
     ; GFX9-NEXT: {{  $}}
     ; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
     ; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
     ; GFX9-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
     ; GFX9-NEXT: %op:vgpr_32 = nofpexcept V_DIV_FIXUP_F16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
-    ; GFX9-NEXT: %and:vgpr_32 = V_AND_B32_e32 65535, %op, implicit $exec
-    ; GFX9-NEXT: $vgpr0 = COPY %and
+    ; GFX9-NEXT: $vgpr0 = COPY %op
     ; GFX10-LABEL: name: v_div_fixup_f16
     ; GFX10: liveins: $vgpr0, $vgpr1, $vgpr2
     ; GFX10-NEXT: {{  $}}
     ; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
     ; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
     ; GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
     ; GFX10-NEXT: %op:vgpr_32 = nofpexcept V_DIV_FIXUP_F16_e64 0, [[COPY]], 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
     ; GFX10-NEXT: %and:vgpr_32 = V_AND_B32_e32 65535, %op, implicit $exec