[PATCH] D72271: [Clang] Handle target-specific builtins returning aggregates.

[Simon Tatham via Phabricator via cfe-commits]

simon_tatham updated this revision to Diff 236778.
simon_tatham marked an inline comment as done.
simon_tatham edited the summary of this revision.
simon_tatham added a comment.

Restructured as suggested.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D72271/new/

https://reviews.llvm.org/D72271

Files:
  clang/lib/CodeGen/CGBuiltin.cpp
  clang/test/CodeGen/arm-mve-intrinsics/vld24.c


Index: clang/test/CodeGen/arm-mve-intrinsics/vld24.c
===================================================================
--- clang/test/CodeGen/arm-mve-intrinsics/vld24.c
+++ clang/test/CodeGen/arm-mve-intrinsics/vld24.c
@@ -98,3 +98,45 @@
     vst2q_f16(addr, value);
 #endif /* POLYMORPHIC */
 }
+
+// CHECK-LABEL: @load_into_variable(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call { <8 x i16>, <8 x i16> } @llvm.arm.mve.vld2q.v8i16.p0i16(i16* [[ADDR:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[TMP0]], 0
+// CHECK-NEXT:    [[TMP2:%.*]] = insertvalue [[STRUCT_UINT16X8X2_T:%.*]] undef, <8 x i16> [[TMP1]], 0, 0
+// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[TMP0]], 1
+// CHECK-NEXT:    [[TMP4:%.*]] = insertvalue [[STRUCT_UINT16X8X2_T]] [[TMP2]], <8 x i16> [[TMP3]], 0, 1
+// CHECK-NEXT:    store <8 x i16> [[TMP1]], <8 x i16>* [[VALUES:%.*]], align 8
+// CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[VALUES]], i32 1
+// CHECK-NEXT:    store <8 x i16> [[TMP3]], <8 x i16>* [[ARRAYIDX4]], align 8
+// CHECK-NEXT:    ret void
+//
+void load_into_variable(const uint16_t *addr, uint16x8_t *values)
+{
+    uint16x8x2_t v;
+#ifdef POLYMORPHIC
+    v = vld2q(addr);
+#else /* POLYMORPHIC */
+    v = vld2q_u16(addr);
+#endif /* POLYMORPHIC */
+    values[0] = v.val[0];
+    values[1] = v.val[1];
+}
+
+// CHECK-LABEL: @extract_one_vector(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.arm.mve.vld2q.v4i32.p0i32(i32* [[ADDR:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP0]], 0
+// CHECK-NEXT:    [[TMP2:%.*]] = insertvalue [[STRUCT_INT32X4X2_T:%.*]] undef, <4 x i32> [[TMP1]], 0, 0
+// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP0]], 1
+// CHECK-NEXT:    [[TMP4:%.*]] = insertvalue [[STRUCT_INT32X4X2_T]] [[TMP2]], <4 x i32> [[TMP3]], 0, 1
+// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
+//
+int32x4_t extract_one_vector(const int32_t *addr)
+{
+#ifdef POLYMORPHIC
+    return vld2q(addr).val[0];
+#else /* POLYMORPHIC */
+    return vld2q_s32(addr).val[0];
+#endif /* POLYMORPHIC */
+}
Index: clang/lib/CodeGen/CGBuiltin.cpp
===================================================================
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -4327,9 +4327,30 @@
     return RValue::get(V);
   }
 
-  // See if we have a target specific builtin that needs to be lowered.
-  if (Value *V = EmitTargetBuiltinExpr(BuiltinID, E, ReturnValue))
-    return RValue::get(V);
+  // Some target-specific builtins can have aggregate return values, e.g.
+  // __builtin_arm_mve_vld2q_u32. So if the result is an aggregate, force
+  // ReturnValue to be non-null, so that the target-specific emission code can
+  // always just emit into it.
+  TypeEvaluationKind EvalKind = getEvaluationKind(E->getType());
+  if (EvalKind == TEK_Aggregate && ReturnValue.isNull()) {
+    Address DestPtr = CreateMemTemp(E->getType(), "agg.tmp");
+    ReturnValue = ReturnValueSlot(DestPtr, false);
+  }
+
+  // Now see if we can emit a target-specific builtin.
+  if (Value *V = EmitTargetBuiltinExpr(BuiltinID, E, ReturnValue)) {
+    switch (EvalKind) {
+    case TEK_Scalar:
+      return RValue::get(V);
+    case TEK_Aggregate:
+      return RValue::getAggregate(ReturnValue.getValue(),
+                                  ReturnValue.isVolatile());
+    case TEK_Complex:
+      llvm_unreachable("No current target builtin returns complex");
+    default:
+      llvm_unreachable("Bad evaluation kind in EmitBuiltinExpr");
+    }
+  }
 
   ErrorUnsupported(E, "builtin function");
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D72271.236778.patch
Type: text/x-patch
Size: 3713 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20200108/fb65c0c7/attachment.bin>