[clang] d56d537 - [Clang] Allow vector and matrix type attributes for sub-byte _BitInt (#140253)
via cfe-commits
cfe-commits at lists.llvm.org
Tue May 20 06:06:42 PDT 2025
Author: Dmitry Sidorov
Date: 2025-05-20T15:06:36+02:00
New Revision: d56d537f9b003869e9376fd9e15bff99423ca4af
URL: https://github.com/llvm/llvm-project/commit/d56d537f9b003869e9376fd9e15bff99423ca4af
DIFF: https://github.com/llvm/llvm-project/commit/d56d537f9b003869e9376fd9e15bff99423ca4af.diff
LOG: [Clang] Allow vector and matrix type attributes for sub-byte _BitInt (#140253)
It is useful for several cases, particularly for 4-bit integers.
Added:
llvm/test/CodeGen/X86/vec-2bit-int.ll
Modified:
clang/include/clang/Basic/DiagnosticSemaKinds.td
clang/lib/AST/ASTContext.cpp
clang/lib/Sema/SemaType.cpp
clang/test/CodeGenCXX/ext-int.cpp
clang/test/CodeGenCXX/matrix-vector-bit-int.cpp
clang/test/SemaCXX/ext-int.cpp
clang/test/SemaCXX/matrix-type.cpp
Removed:
################################################################################
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
index d78a757c72e4a..66f9480d99380 100644
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -3257,8 +3257,7 @@ def err_attribute_too_few_arguments : Error<
"%0 attribute takes at least %1 argument%s1">;
def err_attribute_invalid_vector_type : Error<"invalid vector element type %0">;
def err_attribute_invalid_bitint_vector_type : Error<
- "'_BitInt' %select{vector|matrix}0 element width must be %select{a power of 2|"
- "at least as wide as 'CHAR_BIT'}1">;
+ "'_BitInt' %select{vector|matrix}0 element width must be a power of 2">;
def err_attribute_invalid_matrix_type : Error<"invalid matrix element type %0">;
def err_attribute_bad_neon_vector_size : Error<
"Neon vector size must be 64 or 128 bits">;
diff --git a/clang/lib/AST/ASTContext.cpp b/clang/lib/AST/ASTContext.cpp
index c58cd2c93fb60..b5417fcf20ddd 100644
--- a/clang/lib/AST/ASTContext.cpp
+++ b/clang/lib/AST/ASTContext.cpp
@@ -4577,8 +4577,7 @@ QualType ASTContext::getVectorType(QualType vecType, unsigned NumElts,
assert(vecType->isBuiltinType() ||
(vecType->isBitIntType() &&
// Only support _BitInt elements with byte-sized power of 2 NumBits.
- llvm::isPowerOf2_32(vecType->castAs<BitIntType>()->getNumBits()) &&
- vecType->castAs<BitIntType>()->getNumBits() >= 8));
+ llvm::isPowerOf2_32(vecType->castAs<BitIntType>()->getNumBits())));
// Check if we've already instantiated a vector of this type.
llvm::FoldingSetNodeID ID;
@@ -4650,8 +4649,7 @@ QualType ASTContext::getExtVectorType(QualType vecType,
assert(vecType->isBuiltinType() || vecType->isDependentType() ||
(vecType->isBitIntType() &&
// Only support _BitInt elements with byte-sized power of 2 NumBits.
- llvm::isPowerOf2_32(vecType->castAs<BitIntType>()->getNumBits()) &&
- vecType->castAs<BitIntType>()->getNumBits() >= 8));
+ llvm::isPowerOf2_32(vecType->castAs<BitIntType>()->getNumBits())));
// Check if we've already instantiated a vector of this type.
llvm::FoldingSetNodeID ID;
diff --git a/clang/lib/Sema/SemaType.cpp b/clang/lib/Sema/SemaType.cpp
index 9ed2326f151a3..28d441234262b 100644
--- a/clang/lib/Sema/SemaType.cpp
+++ b/clang/lib/Sema/SemaType.cpp
@@ -2321,9 +2321,9 @@ static bool CheckBitIntElementType(Sema &S, SourceLocation AttrLoc,
bool ForMatrixType = false) {
// Only support _BitInt elements with byte-sized power of 2 NumBits.
unsigned NumBits = BIT->getNumBits();
- if (!llvm::isPowerOf2_32(NumBits) || NumBits < 8)
+ if (!llvm::isPowerOf2_32(NumBits))
return S.Diag(AttrLoc, diag::err_attribute_invalid_bitint_vector_type)
- << ForMatrixType << (NumBits < 8);
+ << ForMatrixType;
return false;
}
diff --git a/clang/test/CodeGenCXX/ext-int.cpp b/clang/test/CodeGenCXX/ext-int.cpp
index f470398ec2095..a75b3701e36ef 100644
--- a/clang/test/CodeGenCXX/ext-int.cpp
+++ b/clang/test/CodeGenCXX/ext-int.cpp
@@ -571,6 +571,41 @@ void VectorTest(uint16_t4 first, uint16_t4 second) {
// CHECK: %[[ADD:.+]] = add <3 x i16> %[[Shuffle]], %[[Shuffle1]]
}
+typedef unsigned _BitInt(4) uint4_t4 __attribute__((ext_vector_type(4)));
+void VectorTest(uint4_t4 first, uint4_t4 second) {
+ // LIN64: define{{.*}} void @_Z10VectorTestDv4_DU4_S0_(i32 %{{.+}}, i32 %{{.+}})
+ // LIN32: define{{.*}} void @_Z10VectorTestDv4_DU4_S0_(<4 x i4> %{{.+}}, <4 x i4> %{{.+}})
+ // WIN64: define dso_local void @"?VectorTest@@YAXT?$__vector at U?$_UBitInt@$03 at __clang@@$03 at __clang@@0 at Z"(<4 x i4> %{{.+}}, <4 x i4> %{{.+}})
+ // WIN32: define dso_local void @"?VectorTest@@YAXT?$__vector at U?$_UBitInt@$03 at __clang@@$03 at __clang@@0 at Z"(<4 x i4> inreg %{{.+}}, <4 x i4> inreg %{{.+}})
+ first.xzw + second.zwx;
+ // CHECK: %[[Shuffle:.+]] = shufflevector <4 x i4> %{{.+}}, <4 x i4> poison, <3 x i32> <i32 0, i32 2, i32 3>
+ // CHECK: %[[Shuffle1:.+]] = shufflevector <4 x i4> %{{.+}}, <4 x i4> poison, <3 x i32> <i32 2, i32 3, i32 0>
+ // CHECK: %[[ADD:.+]] = add <3 x i4> %[[Shuffle]], %[[Shuffle1]]
+}
+
+typedef unsigned _BitInt(2) uint2_t2 __attribute__((ext_vector_type(2)));
+uint2_t2 TestBitIntVector2x2Alloca(uint2_t2 v1, uint2_t2 v2) {
+ // LIN64: define dso_local i16 @_Z25TestBitIntVector2x2AllocaDv2_DU2_S0_(i16 %[[V1Coerce:.+]], i16 %[[V2Coerce:.+]])
+ // LIN64: %[[RetVal:.+]] = alloca <2 x i2>, align 2
+ // LIN64: %[[V1Addr:.+]] = alloca <2 x i2>, align 2
+ // LIN64: %[[V2Addr:.+]] = alloca <2 x i2>, align 2
+ // LIN64: %[[RetValCoerce:.+]] = alloca i16, align 2
+ // LIN64: call void @llvm.memcpy.p0.p0.i64(ptr align 2 %[[RetValCoerce]], ptr align 2 %[[RetVal]], i64 1, i1 false)
+ // LIN64: %[[Ret:.+]] = load i16, ptr %[[RetValCoerce]], align 2
+ // LIN64: ret i16 %[[Ret]]
+
+ // LIN32: define dso_local <2 x i2> @_Z25TestBitIntVector2x2AllocaDv2_DU2_S0_(<2 x i2> %{{.+}}, <2 x i2> %{{.+}})
+ // LIN32: %[[V1Addr:.+]] = alloca <2 x i2>, align 2
+ // LIN32: %[[V2Addr:.+]] = alloca <2 x i2>, align 2
+ // LIN32: ret <2 x i2> %[[Ret:.+]]
+
+ // WIN: define dso_local <2 x i2> @"?TestBitIntVector2x2Alloca@@YAT?$__vector at U?$_UBitInt@$01 at __clang@@$01 at __clang@@T12 at 0@Z"(<2 x i2>{{.*}}, <2 x i2>{{.*}})
+ // WIN: %[[V1:.+]] = alloca <2 x i2>, align 2
+ // WIN: %[[V2:.+]] = alloca <2 x i2>, align 2
+ // WIN: ret <2 x i2> %[[Ret:.+]]
+ return v1 + v2;
+}
+
// Ensure that these types don't alias the normal int types.
void TBAATest(_BitInt(sizeof(int) * 8) ExtInt,
unsigned _BitInt(sizeof(int) * 8) ExtUInt,
diff --git a/clang/test/CodeGenCXX/matrix-vector-bit-int.cpp b/clang/test/CodeGenCXX/matrix-vector-bit-int.cpp
index 7dc3b6bd59822..2e7531b334ecb 100644
--- a/clang/test/CodeGenCXX/matrix-vector-bit-int.cpp
+++ b/clang/test/CodeGenCXX/matrix-vector-bit-int.cpp
@@ -7,6 +7,8 @@ using i32x3 = _BitInt(32) __attribute__((ext_vector_type(3)));
using i32x3x3 = _BitInt(32) __attribute__((matrix_type(3, 3)));
using i512x3 = _BitInt(512) __attribute__((ext_vector_type(3)));
using i512x3x3 = _BitInt(512) __attribute__((matrix_type(3, 3)));
+using i4x3 = _BitInt(4) __attribute__((ext_vector_type(3)));
+using i4x3x3 = _BitInt(4) __attribute__((matrix_type(3, 3)));
// CHECK-LABEL: define dso_local i32 @_Z2v1Dv3_DB8_(
// CHECK-SAME: i32 [[A_COERCE:%.*]]) #[[ATTR0:[0-9]+]] {
@@ -68,8 +70,34 @@ i512x3 v3(i512x3 a) {
return a + a;
}
+// CHECK-LABEL: define dso_local i32 @_Z2v4Dv3_DB4_(
+// CHECK-SAME: i32 [[A_COERCE:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[RETVAL:%.*]] = alloca <3 x i4>, align 4
+// CHECK-NEXT: [[A:%.*]] = alloca <3 x i4>, align 4
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <3 x i4>, align 4
+// CHECK-NEXT: [[RETVAL_COERCE:%.*]] = alloca i32, align 4
+// CHECK-NEXT: store i32 [[A_COERCE]], ptr [[A]], align 4
+// CHECK-NEXT: [[LOADVECN:%.*]] = load <4 x i4>, ptr [[A]], align 4
+// CHECK-NEXT: [[A1:%.*]] = shufflevector <4 x i4> [[LOADVECN]], <4 x i4> poison, <3 x i32> <i32 0, i32 1, i32 2>
+// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i4> [[A1]], <3 x i4> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison>
+// CHECK-NEXT: store <4 x i4> [[EXTRACTVEC]], ptr [[A_ADDR]], align 4
+// CHECK-NEXT: [[LOADVECN2:%.*]] = load <4 x i4>, ptr [[A_ADDR]], align 4
+// CHECK-NEXT: [[EXTRACTVEC3:%.*]] = shufflevector <4 x i4> [[LOADVECN2]], <4 x i4> poison, <3 x i32> <i32 0, i32 1, i32 2>
+// CHECK-NEXT: [[LOADVECN4:%.*]] = load <4 x i4>, ptr [[A_ADDR]], align 4
+// CHECK-NEXT: [[EXTRACTVEC5:%.*]] = shufflevector <4 x i4> [[LOADVECN4]], <4 x i4> poison, <3 x i32> <i32 0, i32 1, i32 2>
+// CHECK-NEXT: [[ADD:%.*]] = add <3 x i4> [[EXTRACTVEC3]], [[EXTRACTVEC5]]
+// CHECK-NEXT: store <3 x i4> [[ADD]], ptr [[RETVAL]], align 4
+// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[RETVAL_COERCE]], ptr align 4 [[RETVAL]], i64 2, i1 false)
+// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[RETVAL_COERCE]], align 4
+// CHECK-NEXT: ret i32 [[TMP0]]
+//
+i4x3 v4(i4x3 a) {
+ return a + a;
+}
+
// CHECK-LABEL: define dso_local noundef <9 x i8> @_Z2m1u11matrix_typeILm3ELm3EDB8_E(
-// CHECK-SAME: <9 x i8> noundef [[A:%.*]]) #[[ATTR3:[0-9]+]] {
+// CHECK-SAME: <9 x i8> noundef [[A:%.*]]) #[[ATTR4:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca [9 x i8], align 1
// CHECK-NEXT: store <9 x i8> [[A]], ptr [[A_ADDR]], align 1
@@ -83,7 +111,7 @@ i8x3x3 m1(i8x3x3 a) {
}
// CHECK-LABEL: define dso_local noundef <9 x i32> @_Z2m2u11matrix_typeILm3ELm3EDB32_E(
-// CHECK-SAME: <9 x i32> noundef [[A:%.*]]) #[[ATTR4:[0-9]+]] {
+// CHECK-SAME: <9 x i32> noundef [[A:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca [9 x i32], align 4
// CHECK-NEXT: store <9 x i32> [[A]], ptr [[A_ADDR]], align 4
@@ -97,7 +125,7 @@ i32x3x3 m2(i32x3x3 a) {
}
// CHECK-LABEL: define dso_local noundef <9 x i512> @_Z2m3u11matrix_typeILm3ELm3EDB512_E(
-// CHECK-SAME: <9 x i512> noundef [[A:%.*]]) #[[ATTR5:[0-9]+]] {
+// CHECK-SAME: <9 x i512> noundef [[A:%.*]]) #[[ATTR6:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca [9 x i512], align 8
// CHECK-NEXT: store <9 x i512> [[A]], ptr [[A_ADDR]], align 8
@@ -109,3 +137,17 @@ i32x3x3 m2(i32x3x3 a) {
i512x3x3 m3(i512x3x3 a) {
return a + a;
}
+
+// CHECK-LABEL: define dso_local noundef <9 x i4> @_Z2m4u11matrix_typeILm3ELm3EDB4_E(
+// CHECK-SAME: <9 x i4> noundef [[A:%.*]]) #[[ATTR7:[0-9]+]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca [9 x i4], align 1
+// CHECK-NEXT: store <9 x i4> [[A]], ptr [[A_ADDR]], align 1
+// CHECK-NEXT: [[TMP0:%.*]] = load <9 x i4>, ptr [[A_ADDR]], align 1
+// CHECK-NEXT: [[TMP1:%.*]] = load <9 x i4>, ptr [[A_ADDR]], align 1
+// CHECK-NEXT: [[TMP2:%.*]] = add <9 x i4> [[TMP0]], [[TMP1]]
+// CHECK-NEXT: ret <9 x i4> [[TMP2]]
+//
+i4x3x3 m4(i4x3x3 a) {
+ return a + a;
+}
diff --git a/clang/test/SemaCXX/ext-int.cpp b/clang/test/SemaCXX/ext-int.cpp
index d974221e774a7..5c566dafed931 100644
--- a/clang/test/SemaCXX/ext-int.cpp
+++ b/clang/test/SemaCXX/ext-int.cpp
@@ -84,17 +84,9 @@ struct is_same<T,T> {
};
// Reject vector types:
-// expected-error at +1{{'_BitInt' vector element width must be at least as wide as 'CHAR_BIT'}}
-typedef _BitInt(2) __attribute__((vector_size(16))) VecTy;
-// expected-error at +1{{'_BitInt' vector element width must be at least as wide as 'CHAR_BIT'}}
-typedef _BitInt(2) __attribute__((ext_vector_type(32))) OtherVecTy;
-// expected-error at +1{{'_BitInt' vector element width must be at least as wide as 'CHAR_BIT'}}
-typedef _BitInt(4) __attribute__((vector_size(16))) VecTy2;
-// expected-error at +1{{'_BitInt' vector element width must be at least as wide as 'CHAR_BIT'}}
-typedef _BitInt(4) __attribute__((ext_vector_type(32))) OtherVecTy2;
-// expected-error at +1{{'_BitInt' vector element width must be at least as wide as 'CHAR_BIT'}}
+// expected-error at +1{{'_BitInt' vector element width must be a power of 2}}
typedef _BitInt(5) __attribute__((vector_size(16))) VecTy3;
-// expected-error at +1{{'_BitInt' vector element width must be at least as wide as 'CHAR_BIT'}}
+// expected-error at +1{{'_BitInt' vector element width must be a power of 2}}
typedef _BitInt(5) __attribute__((ext_vector_type(32))) OtherVecTy3;
// expected-error at +1{{'_BitInt' vector element width must be a power of 2}}
typedef _BitInt(37) __attribute__((vector_size(16))) VecTy4;
diff --git a/clang/test/SemaCXX/matrix-type.cpp b/clang/test/SemaCXX/matrix-type.cpp
index bb7a8421ca9e3..186d3b6b35208 100644
--- a/clang/test/SemaCXX/matrix-type.cpp
+++ b/clang/test/SemaCXX/matrix-type.cpp
@@ -31,8 +31,7 @@ void matrix_unsupported_element_type() {
}
void matrix_unsupported_bit_int() {
- using m1 = _BitInt(2) __attribute__((matrix_type(4, 4))); // expected-error{{'_BitInt' matrix element width must be at least as wide as 'CHAR_BIT'}}
- using m2 = _BitInt(7) __attribute__((matrix_type(4, 4))); // expected-error{{'_BitInt' matrix element width must be at least as wide as 'CHAR_BIT'}}
+ using m2 = _BitInt(7) __attribute__((matrix_type(4, 4))); // expected-error{{'_BitInt' matrix element width must be a power of 2}}
using m3 = _BitInt(9) __attribute__((matrix_type(4, 4))); // expected-error{{'_BitInt' matrix element width must be a power of 2}}
using m4 = _BitInt(12) __attribute__((matrix_type(4, 4))); // expected-error{{'_BitInt' matrix element width must be a power of 2}}
using m5 = _BitInt(8) __attribute__((matrix_type(4, 4)));
diff --git a/llvm/test/CodeGen/X86/vec-2bit-int.ll b/llvm/test/CodeGen/X86/vec-2bit-int.ll
new file mode 100644
index 0000000000000..2e172fd45d33b
--- /dev/null
+++ b/llvm/test/CodeGen/X86/vec-2bit-int.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=x86_64-- | FileCheck %s
+
+define dso_local <2 x i2> @foo(<2 x i2> %v1, <2 x i2> %v2) {
+; CHECK-LABEL: foo:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: movq %xmm1, %rax
+; CHECK-NEXT: andb $3, %al
+; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,2,3]
+; CHECK-NEXT: movq %xmm2, %rcx
+; CHECK-NEXT: shlb $2, %cl
+; CHECK-NEXT: orb %al, %cl
+; CHECK-NEXT: andb $15, %cl
+; CHECK-NEXT: movb %cl, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT: movq %xmm0, %rax
+; CHECK-NEXT: andb $3, %al
+; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,2,3]
+; CHECK-NEXT: movq %xmm2, %rcx
+; CHECK-NEXT: shlb $2, %cl
+; CHECK-NEXT: orb %al, %cl
+; CHECK-NEXT: andb $15, %cl
+; CHECK-NEXT: movb %cl, -{{[0-9]+}}(%rsp)
+; CHECK-NEXT: paddq %xmm1, %xmm0
+; CHECK-NEXT: retq
+ entry:
+ %v2.addr = alloca <2 x i2>, align 2
+ %v1.addr = alloca <2 x i2>, align 2
+ store <2 x i2> %v2, ptr %v2.addr, align 2
+ store <2 x i2> %v1, ptr %v1.addr, align 2
+ %0 = load <2 x i2>, ptr %v1.addr, align 2
+ %1 = load <2 x i2>, ptr %v2.addr, align 2
+ %add = add <2 x i2> %0, %1
+ ret <2 x i2> %add
+}
More information about the cfe-commits
mailing list