[AArch64][GISel] Add fp128 and i128 sitofp/uitofp handling (#97691)

Legalize sitofp/uitofp involving fp128/i128 types into a libcall. 
Vector with i128/fp128 types are scalarized.

Author: Him188

llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp

@@ -1154,16 +1154,13 @@ LegalizerHelper::libcall(MachineInstr &MI, LostDebugLocObserver &LocObserver) {
   }
   case TargetOpcode::G_SITOFP:
   case TargetOpcode::G_UITOFP: {
-    // FIXME: Support other types
     unsigned FromSize = MRI.getType(MI.getOperand(1).getReg()).getSizeInBits();
-    unsigned ToSize = MRI.getType(MI.getOperand(0).getReg()).getSizeInBits();
-    if ((FromSize != 32 && FromSize != 64) || (ToSize != 32 && ToSize != 64))
+    Type *ToTy =
+        getFloatTypeForLLT(Ctx, MRI.getType(MI.getOperand(0).getReg()));
+    if ((FromSize != 32 && FromSize != 64 && FromSize != 128) || !ToTy)
       return UnableToLegalize;
     LegalizeResult Status = conversionLibcall(
-        MI, MIRBuilder,
-        ToSize == 64 ? Type::getDoubleTy(Ctx) : Type::getFloatTy(Ctx),
-        FromSize == 32 ? Type::getInt32Ty(Ctx) : Type::getInt64Ty(Ctx),
-        LocObserver);
+        MI, MIRBuilder, ToTy, Type::getIntNTy(Ctx, FromSize), LocObserver);
     if (Status != Legalized)
       return Status;
     break;

llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp

@@ -711,34 +711,49 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
           {{s32, s128}, {s64, s128}, {s128, s128}, {s128, s32}, {s128, s64}});
 
   getActionDefinitionsBuilder({G_SITOFP, G_UITOFP})
-      .legalForCartesianProduct({s32, s64, v2s64, v4s32, v2s32})
+      .legalFor({{s32, s32},
+                 {s64, s32},
+                 {s32, s64},
+                 {s64, s64},
+                 {v2s64, v2s64},
+                 {v4s32, v4s32},
+                 {v2s32, v2s32}})
       .legalIf([=](const LegalityQuery &Query) {
         return HasFP16 &&
                (Query.Types[0] == s16 || Query.Types[0] == v4s16 ||
                 Query.Types[0] == v8s16) &&
                (Query.Types[1] == s32 || Query.Types[1] == s64 ||
                 Query.Types[1] == v4s16 || Query.Types[1] == v8s16);
       })
-      .widenScalarToNextPow2(1)
-      .clampScalar(1, s32, s64)
-      .widenScalarToNextPow2(0)
-      .clampScalarOrElt(0, MinFPScalar, s64)
-      .moreElementsToNextPow2(0)
+      .scalarizeIf(scalarOrEltWiderThan(1, 64), 1)
+      .scalarizeIf(scalarOrEltWiderThan(0, 64), 0)
+      .moreElementsToNextPow2(1)
+      .widenScalarOrEltToNextPow2OrMinSize(1)
+      .minScalar(1, s32)
+      .widenScalarOrEltToNextPow2OrMinSize(0, /*MinSize=*/HasFP16 ? 16 : 32)
       .widenScalarIf(
           [=](const LegalityQuery &Query) {
-            return Query.Types[0].getScalarSizeInBits() <
-                   Query.Types[1].getScalarSizeInBits();
+            return Query.Types[1].getScalarSizeInBits() <= 64 &&
+                   Query.Types[0].getScalarSizeInBits() <
+                       Query.Types[1].getScalarSizeInBits();
           },
           LegalizeMutations::changeElementSizeTo(0, 1))
       .widenScalarIf(
           [=](const LegalityQuery &Query) {
-            return Query.Types[0].getScalarSizeInBits() >
-                   Query.Types[1].getScalarSizeInBits();
+            return Query.Types[0].getScalarSizeInBits() <= 64 &&
+                   Query.Types[0].getScalarSizeInBits() >
+                       Query.Types[1].getScalarSizeInBits();
           },
           LegalizeMutations::changeElementSizeTo(1, 0))
       .clampNumElements(0, v4s16, v8s16)
       .clampNumElements(0, v2s32, v4s32)
-      .clampMaxNumElements(0, s64, 2);
+      .clampMaxNumElements(0, s64, 2)
+      .libcallFor({{s16, s128},
+                   {s32, s128},
+                   {s64, s128},
+                   {s128, s128},
+                   {s128, s32},
+                   {s128, s64}});
 
   // Control-flow
   getActionDefinitionsBuilder(G_BRCOND)

llvm/test/CodeGen/AArch64/GlobalISel/select-fp-casts.mir

@@ -635,79 +635,3 @@ body:             |
     %1(s64) = G_FPTOUI %0
     $x0 = COPY %1(s64)
 ...
-
----
-name:            sitofp_v2s64_v2s32
-legalized:       true
-regBankSelected: true
-
-body:             |
-  bb.0:
-    liveins: $d0
-
-    ; CHECK-LABEL: name: sitofp_v2s64_v2s32
-    ; CHECK: [[COPY:%[0-9]+]]:fpr64 = COPY $d0
-    ; CHECK: [[SSHLLv2i32_shift:%[0-9]+]]:fpr128 = SSHLLv2i32_shift [[COPY]], 0
-    ; CHECK: [[SCVTFv2f64_:%[0-9]+]]:fpr128 = nofpexcept SCVTFv2f64 [[SSHLLv2i32_shift]]
-    ; CHECK: $q0 = COPY [[SCVTFv2f64_]]
-    %0:fpr(<2 x s32>) = COPY $d0
-    %1:fpr(<2 x s64>) = G_SITOFP %0
-    $q0 = COPY %1(<2 x s64>)
-...
-
----
-name:            uitofp_v2s64_v2s32
-legalized:       true
-regBankSelected: true
-
-body:             |
-  bb.0:
-    liveins: $d0
-
-    ; CHECK-LABEL: name: uitofp_v2s64_v2s32
-    ; CHECK: [[COPY:%[0-9]+]]:fpr64 = COPY $d0
-    ; CHECK: [[USHLLv2i32_shift:%[0-9]+]]:fpr128 = USHLLv2i32_shift [[COPY]], 0
-    ; CHECK: [[UCVTFv2f64_:%[0-9]+]]:fpr128 = nofpexcept UCVTFv2f64 [[USHLLv2i32_shift]]
-    ; CHECK: $q0 = COPY [[UCVTFv2f64_]]
-    %0:fpr(<2 x s32>) = COPY $d0
-    %1:fpr(<2 x s64>) = G_UITOFP %0
-    $q0 = COPY %1(<2 x s64>)
-...
-
----
-name:            sitofp_v2s32_v2s64
-legalized:       true
-regBankSelected: true
-
-body:             |
-  bb.0:
-    liveins: $q0
-
-    ; CHECK-LABEL: name: sitofp_v2s32_v2s64
-    ; CHECK: [[COPY:%[0-9]+]]:fpr128 = COPY $q0
-    ; CHECK: [[SCVTFv2f64_:%[0-9]+]]:fpr128 = nofpexcept SCVTFv2f64 [[COPY]]
-    ; CHECK: [[FCVTNv2i32_:%[0-9]+]]:fpr64 = nofpexcept FCVTNv2i32 [[SCVTFv2f64_]]
-    ; CHECK: $d0 = COPY [[FCVTNv2i32_]]
-    %0:fpr(<2 x s64>) = COPY $q0
-    %1:fpr(<2 x s32>) = G_SITOFP %0
-    $d0 = COPY %1(<2 x s32>)
-...
-
----
-name:            uitofp_v2s32_v2s64
-legalized:       true
-regBankSelected: true
-
-body:             |
-  bb.0:
-    liveins: $q0
-
-    ; CHECK-LABEL: name: uitofp_v2s32_v2s64
-    ; CHECK: [[COPY:%[0-9]+]]:fpr128 = COPY $q0
-    ; CHECK: [[UCVTFv2f64_:%[0-9]+]]:fpr128 = nofpexcept UCVTFv2f64 [[COPY]]
-    ; CHECK: [[FCVTNv2i32_:%[0-9]+]]:fpr64 = nofpexcept FCVTNv2i32 [[UCVTFv2f64_]]
-    ; CHECK: $d0 = COPY [[FCVTNv2i32_]]
-    %0:fpr(<2 x s64>) = COPY $q0
-    %1:fpr(<2 x s32>) = G_UITOFP %0
-    $d0 = COPY %1(<2 x s32>)
-...