[AMDGPU][True16][MC][CodeGen] true16 for v_cndmask_b16 (#119736)

Support true16 format for v_cndmask_b16 in MC and CodeGen in true16 and
fake16 flow.

Since we are replacing `v_cndmask_b16` to `v_cndmask_b16_t16/fake16`, we
have to at least update the fake16 codeGen to get codeGen test passing.
For this case, we have to update the true16 and with fake16 together,
otherwise some of the true16 tests will fail

Author: broxigarchen

llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp

@@ -3007,8 +3007,8 @@ 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_e32:
-    case AMDGPU::V_CNDMASK_B16_dpp:
+    case AMDGPU::V_CNDMASK_B16_fake16_e32:
+    case AMDGPU::V_CNDMASK_B16_fake16_dpp:
     case AMDGPU::V_CNDMASK_B32_e32:
     case AMDGPU::V_CNDMASK_B32_dpp:
     case AMDGPU::V_DIV_FMAS_F32_e64:
@@ -3023,8 +3023,8 @@ 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_e64:
-    case AMDGPU::V_CNDMASK_B16_e64_dpp:
+    case AMDGPU::V_CNDMASK_B16_fake16_e64:
+    case AMDGPU::V_CNDMASK_B16_fake16_e64_dpp:
     case AMDGPU::V_CNDMASK_B32_e64:
     case AMDGPU::V_CNDMASK_B32_e64_dpp:
     case AMDGPU::V_SUBB_U32_e64:

llvm/lib/Target/AMDGPU/SIInstructions.td

@@ -1245,11 +1245,22 @@ class VOPSelectPat <ValueType vt> : GCNPat <
   (vt (select i1:$src0, vt:$src1, vt:$src2)),
   (V_CNDMASK_B32_e64 0, VSrc_b32:$src2, 0, VSrc_b32:$src1, SSrc_i1:$src0)
 >;
+class VOPSelectPat_t16 <ValueType vt> : GCNPat <
+  (vt (select i1:$src0, vt:$src1, vt:$src2)),
+  (V_CNDMASK_B16_t16_e64 0, VSrcT_b16:$src2, 0, VSrcT_b16:$src1, SSrc_i1:$src0)
+>;
 
 def : VOPSelectModsPat <i32>;
 def : VOPSelectModsPat <f32>;
-def : VOPSelectPat <f16>;
-def : VOPSelectPat <i16>;
+foreach p = [NotHasTrue16BitInsts, UseFakeTrue16Insts] in
+let True16Predicate = p in {
+  def : VOPSelectPat <f16>;
+  def : VOPSelectPat <i16>;
+} // End True16Predicate = p
+let True16Predicate = UseRealTrue16Insts in {
+  def : VOPSelectPat_t16 <f16>;
+  def : VOPSelectPat_t16 <i16>;
+} // End True16Predicate = UseRealTrue16Insts
 
 let AddedComplexity = 1 in {
 def : GCNPat <

llvm/lib/Target/AMDGPU/VOP2Instructions.td

@@ -714,6 +714,26 @@ class VOP2e_SGPR<list<ValueType> ArgVT> : VOPProfile<ArgVT> {
 def VOP2e_I32_I32_I32_I1 : VOP2e_SGPR<[i32, i32, i32, i1]>;
 def VOP2e_I16_I16_I16_I1 : VOP2e_SGPR<[i16, i16, i16, i1]>;
 // V_CNDMASK_B16 is VOP3 only
+def VOP2e_I16_I16_I16_I1_true16 : VOP2e_SGPR<[i16, i16, i16, i1]> {
+  let IsTrue16 = 1;
+  let IsRealTrue16 = 1;
+  let HasOpSel = 1;
+  let DstRC64 = getVALUDstForVT<DstVT, 1, 1>.ret;
+  let Src0RC64 = getVOP3SrcForVT<Src0VT, 1/*IsTrue16*/>.ret;
+  let Src1RC64 = getVOP3SrcForVT<Src1VT, 1/*IsTrue16*/>.ret;
+  let Src2RC64 = getVOP3SrcForVT<Src2VT, 1/*IsTrue16*/>.ret;
+  let Src0Mod = getSrc0Mod<f16, DstVT, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+  let Src1Mod = getSrcMod<f16, 1/*IsTrue16*/, 0/*IsFake16*/>.ret;
+  let HasSrc2Mods = 0;
+  let InsVOP3OpSel = getInsVOP3Base<Src0RC64, Src1RC64,
+                    Src2RC64, NumSrcArgs,
+                    HasClamp, 1/*HasModifiers*/, 0/*HasSrc2Mods*/, HasOMod,
+                    Src0Mod, Src1Mod, Src2Mod, 1/*HasOpSel*/>.ret;
+  let Src0VOP3DPP = VGPRSrc_16;
+  let Src1VOP3DPP = getVOP3DPPSrcForVT<Src1VT, 0/*IsFake16*/>.ret;
+  let Src0ModVOP3DPP = getSrc0ModVOP3DPP<f16, DstVT, 0/*IsFake16*/>.ret;
+  let Src1ModVOP3DPP = getSrcModVOP3DPP<f16, 0/*IsFake16*/>.ret;
+}
 def VOP2e_I16_I16_I16_I1_fake16 : VOP2e_SGPR<[i16, i16, i16, i1]> {
   let IsTrue16 = 1;
   let DstRC64 = getVALUDstForVT<DstVT>.ret;
@@ -765,8 +785,10 @@ def VOP_WRITELANE : VOPProfile<[i32, i32, i32, i32]> {
 // VOP2 Instructions
 //===----------------------------------------------------------------------===//
 
-let SubtargetPredicate = isGFX11Plus in
-defm V_CNDMASK_B16 : VOP2eInst <"v_cndmask_b16", VOP2e_I16_I16_I16_I1_fake16>;
+let SubtargetPredicate = isGFX11Plus, True16Predicate = UseRealTrue16Insts in
+defm V_CNDMASK_B16_t16 : VOP2eInst <"v_cndmask_b16_t16", VOP2e_I16_I16_I16_I1_true16>;
+let SubtargetPredicate = isGFX11Plus, True16Predicate = UseFakeTrue16Insts in
+defm V_CNDMASK_B16_fake16 : VOP2eInst <"v_cndmask_b16_fake16", VOP2e_I16_I16_I16_I1_fake16>;
 defm V_CNDMASK_B32 : VOP2eInst_VOPD <"v_cndmask_b32", VOP2e_I32_I32_I32_I1, 0x9, "v_cndmask_b32">;
 let SubtargetPredicate = HasMadMacF32Insts, isReMaterializable = 1 in
 def V_MADMK_F32 : VOP2_Pseudo <"v_madmk_f32", VOP_MADMK_F32, []>;
@@ -1846,7 +1868,7 @@ defm V_FMAMK_F16           : VOP2Only_Real_MADK_t16_and_fake16_gfx11_gfx12<0x037
 defm V_FMAAK_F16           : VOP2Only_Real_MADK_t16_and_fake16_gfx11_gfx12<0x038, "v_fmaak_f16">;
 
 // VOP3 only.
-defm V_CNDMASK_B16         : VOP3Only_Realtriple_gfx11_gfx12<0x25d>;
+defm V_CNDMASK_B16         : VOP3Only_Realtriple_t16_and_fake16_gfx11_gfx12<0x25d, "v_cndmask_b16">;
 defm V_LDEXP_F32           : VOP3Only_Realtriple_gfx11_gfx12<0x31c>;
 defm V_BFM_B32             : VOP3Only_Realtriple_gfx11_gfx12<0x31d>;
 defm V_BCNT_U32_B32        : VOP3Only_Realtriple_gfx11_gfx12<0x31e>;