RKSimon created this revision.
RKSimon added reviewers: fhahn, scanon, aaron.ballman, craig.topper.
RKSimon requested review of this revision.
Herald added a project: clang.
Similar to the existing bitwise reduction builtins, these are lowered to the
llvm.vector.reduce.add/mul intrinsic calls.
For other reductions, we've tried to share builtins for float/integer vectors,
but the fadd/fmul reduction builtins also take a starting value argument.
Technically I could support float by using default values, but we're probably
better off with specific fadd/fmul reduction builtins for both arguments.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D117829
Files:
clang/include/clang/Basic/Builtins.def
clang/lib/CodeGen/CGBuiltin.cpp
clang/lib/Sema/SemaChecking.cpp
clang/test/CodeGen/builtins-reduction-math.c
clang/test/Sema/builtins-reduction-math.c
Index: clang/test/Sema/builtins-reduction-math.c
===================================================================
--- clang/test/Sema/builtins-reduction-math.c
+++ clang/test/Sema/builtins-reduction-math.c
@@ -36,6 +36,40 @@
// expected-error@-1 {{1st argument must be a vector type (was 'int')}}
}
+void test_builtin_reduce_add(int i, float4 v, int3 iv) {
+ struct Foo s = __builtin_reduce_add(iv);
+ // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'int'}}
+
+ i = __builtin_reduce_add();
+ // expected-error@-1 {{too few arguments to function call, expected 1, have 0}}
+
+ i = __builtin_reduce_add(iv, iv);
+ // expected-error@-1 {{too many arguments to function call, expected 1, have 2}}
+
+ i = __builtin_reduce_add(i);
+ // expected-error@-1 {{1st argument must be a vector of integers (was 'int')}}
+
+ i = __builtin_reduce_add(v);
+ // expected-error@-1 {{1st argument must be a vector of integers (was 'float4' (vector of 4 'float' values))}}
+}
+
+void test_builtin_reduce_mul(int i, float4 v, int3 iv) {
+ struct Foo s = __builtin_reduce_mul(iv);
+ // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'int'}}
+
+ i = __builtin_reduce_mul();
+ // expected-error@-1 {{too few arguments to function call, expected 1, have 0}}
+
+ i = __builtin_reduce_mul(iv, iv);
+ // expected-error@-1 {{too many arguments to function call, expected 1, have 2}}
+
+ i = __builtin_reduce_mul(i);
+ // expected-error@-1 {{1st argument must be a vector of integers (was 'int')}}
+
+ i = __builtin_reduce_mul(v);
+ // expected-error@-1 {{1st argument must be a vector of integers (was 'float4' (vector of 4 'float' values))}}
+}
+
void test_builtin_reduce_xor(int i, float4 v, int3 iv) {
struct Foo s = __builtin_reduce_xor(iv);
// expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'int'}}
Index: clang/test/CodeGen/builtins-reduction-math.c
===================================================================
--- clang/test/CodeGen/builtins-reduction-math.c
+++ clang/test/CodeGen/builtins-reduction-math.c
@@ -58,6 +58,50 @@
unsigned long long r5 = __builtin_reduce_min(cvi1);
}
+void test_builtin_reduce_add(si8 vi1, u4 vu1) {
+ // CHECK: [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
+ // CHECK-NEXT: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> [[VI1]])
+ short r2 = __builtin_reduce_add(vi1);
+
+ // CHECK: [[VU1:%.+]] = load <4 x i32>, <4 x i32>* %vu1.addr, align 16
+ // CHECK-NEXT: call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[VU1]])
+ unsigned r3 = __builtin_reduce_add(vu1);
+
+ // CHECK: [[CVI1:%.+]] = load <8 x i16>, <8 x i16>* %cvi1, align 16
+ // CHECK-NEXT: [[RDX1:%.+]] = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> [[CVI1]])
+ // CHECK-NEXT: sext i16 [[RDX1]] to i32
+ const si8 cvi1 = vi1;
+ int r4 = __builtin_reduce_add(cvi1);
+
+ // CHECK: [[CVU1:%.+]] = load <4 x i32>, <4 x i32>* %cvu1, align 16
+ // CHECK-NEXT: [[RDX2:%.+]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[CVU1]])
+ // CHECK-NEXT: zext i32 [[RDX2]] to i64
+ const u4 cvu1 = vu1;
+ unsigned long long r5 = __builtin_reduce_add(cvu1);
+}
+
+void test_builtin_reduce_mul(si8 vi1, u4 vu1) {
+ // CHECK: [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
+ // CHECK-NEXT: call i16 @llvm.vector.reduce.mul.v8i16(<8 x i16> [[VI1]])
+ short r2 = __builtin_reduce_mul(vi1);
+
+ // CHECK: [[VU1:%.+]] = load <4 x i32>, <4 x i32>* %vu1.addr, align 16
+ // CHECK-NEXT: call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[VU1]])
+ unsigned r3 = __builtin_reduce_mul(vu1);
+
+ // CHECK: [[CVI1:%.+]] = load <8 x i16>, <8 x i16>* %cvi1, align 16
+ // CHECK-NEXT: [[RDX1:%.+]] = call i16 @llvm.vector.reduce.mul.v8i16(<8 x i16> [[CVI1]])
+ // CHECK-NEXT: sext i16 [[RDX1]] to i32
+ const si8 cvi1 = vi1;
+ int r4 = __builtin_reduce_mul(cvi1);
+
+ // CHECK: [[CVU1:%.+]] = load <4 x i32>, <4 x i32>* %cvu1, align 16
+ // CHECK-NEXT: [[RDX2:%.+]] = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[CVU1]])
+ // CHECK-NEXT: zext i32 [[RDX2]] to i64
+ const u4 cvu1 = vu1;
+ unsigned long long r5 = __builtin_reduce_mul(cvu1);
+}
+
void test_builtin_reduce_xor(si8 vi1, u4 vu1) {
// CHECK: [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
Index: clang/lib/Sema/SemaChecking.cpp
===================================================================
--- clang/lib/Sema/SemaChecking.cpp
+++ clang/lib/Sema/SemaChecking.cpp
@@ -2260,6 +2260,8 @@
}
// These builtins support vectors of integers only.
+ case Builtin::BI__builtin_reduce_add:
+ case Builtin::BI__builtin_reduce_mul:
case Builtin::BI__builtin_reduce_xor:
case Builtin::BI__builtin_reduce_or:
case Builtin::BI__builtin_reduce_and: {
Index: clang/lib/CodeGen/CGBuiltin.cpp
===================================================================
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -3218,6 +3218,12 @@
*this, E, GetIntrinsicID(E->getArg(0)->getType()), "rdx.min"));
}
+ case Builtin::BI__builtin_reduce_add:
+ return RValue::get(emitUnaryBuiltin(
+ *this, E, llvm::Intrinsic::vector_reduce_add, "rdx.add"));
+ case Builtin::BI__builtin_reduce_mul:
+ return RValue::get(emitUnaryBuiltin(
+ *this, E, llvm::Intrinsic::vector_reduce_mul, "rdx.mul"));
case Builtin::BI__builtin_reduce_xor:
return RValue::get(emitUnaryBuiltin(
*this, E, llvm::Intrinsic::vector_reduce_xor, "rdx.xor"));
Index: clang/include/clang/Basic/Builtins.def
===================================================================
--- clang/include/clang/Basic/Builtins.def
+++ clang/include/clang/Basic/Builtins.def
@@ -658,6 +658,8 @@
BUILTIN(__builtin_reduce_xor, "v.", "nct")
BUILTIN(__builtin_reduce_or, "v.", "nct")
BUILTIN(__builtin_reduce_and, "v.", "nct")
+BUILTIN(__builtin_reduce_add, "v.", "nct")
+BUILTIN(__builtin_reduce_mul, "v.", "nct")
BUILTIN(__builtin_matrix_transpose, "v.", "nFt")
BUILTIN(__builtin_matrix_column_major_load, "v.", "nFt")
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
