simon_tatham updated this revision to Diff 236564.
simon_tatham added a comment.
Thanks for the helpful advice!
Here's a revised version that checks `getEvaluationKind`. I've also added a
test for the `vld2q(...).val[0]` construction you mentioned: you're right, of
course, that that also crashed existing clang, and it still crashed with my
previous patch applied. This version seems to work in both cases.
> and then we can just require EmitTargetBuiltinExpr to return null or
> something else that makes it clear that they've done the right thing with the
> slot that was passed in
The current return value of `EmitTargetBuiltinExpr` will be the `llvm::Value *`
corresponding to the last of a sequence of store instructions that writes the
constructed aggregate into the return value slot. There's no need to actually
use that `Value` for anything in this case, but we can still test that it's
non-null, to find out whether `EmitTargetBuiltinExpr` has successfully
recognized a builtin and generated some code, or whether we have to fall
through to the `ErrorUnsupported`.
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
@@ -4328,8 +4328,26 @@
}
// See if we have a target specific builtin that needs to be lowered.
- if (Value *V = EmitTargetBuiltinExpr(BuiltinID, E, ReturnValue))
- return RValue::get(V);
+ switch (getEvaluationKind(E->getType())) {
+ case TEK_Scalar:
+ if (Value *V = EmitTargetBuiltinExpr(BuiltinID, E, ReturnValue))
+ return RValue::get(V);
+ break;
+ case TEK_Aggregate: {
+ if (ReturnValue.isNull()) {
+ Address DestPtr = CreateMemTemp(E->getType(), "agg.tmp");
+ ReturnValue = ReturnValueSlot(DestPtr, false);
+ }
+ if (EmitTargetBuiltinExpr(BuiltinID, E, ReturnValue))
+ return RValue::getAggregate(ReturnValue.getValue(),
+ ReturnValue.isVolatile());
+ break;
+ }
+ case TEK_Complex:
+ llvm_unreachable("No currently supported builtin returns complex");
+ default:
+ llvm_unreachable("Bad evaluation kind in EmitBuiltinExpr");
+ }
ErrorUnsupported(E, "builtin function");
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
@@ -4328,8 +4328,26 @@
}
// See if we have a target specific builtin that needs to be lowered.
- if (Value *V = EmitTargetBuiltinExpr(BuiltinID, E, ReturnValue))
- return RValue::get(V);
+ switch (getEvaluationKind(E->getType())) {
+ case TEK_Scalar:
+ if (Value *V = EmitTargetBuiltinExpr(BuiltinID, E, ReturnValue))
+ return RValue::get(V);
+ break;
+ case TEK_Aggregate: {
+ if (ReturnValue.isNull()) {
+ Address DestPtr = CreateMemTemp(E->getType(), "agg.tmp");
+ ReturnValue = ReturnValueSlot(DestPtr, false);
+ }
+ if (EmitTargetBuiltinExpr(BuiltinID, E, ReturnValue))
+ return RValue::getAggregate(ReturnValue.getValue(),
+ ReturnValue.isVolatile());
+ break;
+ }
+ case TEK_Complex:
+ llvm_unreachable("No currently supported builtin returns complex");
+ default:
+ llvm_unreachable("Bad evaluation kind in EmitBuiltinExpr");
+ }
ErrorUnsupported(E, "builtin function");
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
