maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Add kadd intrinsics to match gcc and icc. 

This adds the following intrinsics:
_kadd_mask64
_kadd_mask32
_kadd_mask16
_kadd_mask8

These are missing from the Intel Intrinsics Guide, but are implemented by both gcc and icc.

llvm-svn: 340879
This commit is contained in:
Craig Topper 2018-08-28 22:32:14 +00:00
parent c8074aa654
commit a65bf65e0b
6 changed files with 101 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
clang/include/clang/Basic/BuiltinsX86.def
View File

@ -1737,6 +1737,10 @@ TARGET_BUILTIN(__builtin_ia32_fpclassps512_mask, "UsV16fIiUs", "ncV:512:", "avx5
TARGET_BUILTIN(__builtin_ia32_fpclasspd512_mask, "UcV8dIiUc", "ncV:512:", "avx512dq")
TARGET_BUILTIN(__builtin_ia32_fpclasssd_mask, "UcV2dIiUc", "ncV:128:", "avx512dq")
TARGET_BUILTIN(__builtin_ia32_fpclassss_mask, "UcV4fIiUc", "ncV:128:", "avx512dq")
TARGET_BUILTIN(__builtin_ia32_kaddqi, "UcUcUc", "nc", "avx512dq")
TARGET_BUILTIN(__builtin_ia32_kaddhi, "UsUsUs", "nc", "avx512dq")
TARGET_BUILTIN(__builtin_ia32_kaddsi, "UiUiUi", "nc", "avx512bw")
TARGET_BUILTIN(__builtin_ia32_kadddi, "ULLiULLiULLi", "nc", "avx512bw")
TARGET_BUILTIN(__builtin_ia32_kandqi, "UcUcUc", "nc", "avx512dq")
TARGET_BUILTIN(__builtin_ia32_kandhi, "UsUsUs", "nc", "avx512f")
TARGET_BUILTIN(__builtin_ia32_kandsi, "UiUiUi", "nc", "avx512bw")

30
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -8613,7 +8613,7 @@ static Value *EmitX86MaskLogic(CodeGenFunction &CGF, Instruction::BinaryOps Opc,
LHS = CGF.Builder.CreateNot(LHS);
return CGF.Builder.CreateBitCast(CGF.Builder.CreateBinOp(Opc, LHS, RHS),
CGF.Builder.getIntNTy(std::max(NumElts, 8U)));
Ops[0]->getType());
}
static Value *EmitX86Select(CodeGenFunction &CGF,
@ -10031,6 +10031,34 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
return Builder.CreateZExt(Cmp, ConvertType(E->getType()));
}
case X86::BI__builtin_ia32_kaddqi:
case X86::BI__builtin_ia32_kaddhi:
case X86::BI__builtin_ia32_kaddsi:
case X86::BI__builtin_ia32_kadddi: {
Intrinsic::ID IID;
switch (BuiltinID) {
default: llvm_unreachable("Unsupported intrinsic!");
case X86::BI__builtin_ia32_kaddqi:
IID = Intrinsic::x86_avx512_kadd_b;
break;
case X86::BI__builtin_ia32_kaddhi:
IID = Intrinsic::x86_avx512_kadd_w;
break;
case X86::BI__builtin_ia32_kaddsi:
IID = Intrinsic::x86_avx512_kadd_d;
break;
case X86::BI__builtin_ia32_kadddi:
IID = Intrinsic::x86_avx512_kadd_q;
break;
}
unsigned NumElts = Ops[0]->getType()->getIntegerBitWidth();
Value *LHS = getMaskVecValue(*this, Ops[0], NumElts);
Value *RHS = getMaskVecValue(*this, Ops[1], NumElts);
Function *Intr = CGM.getIntrinsic(IID);
Value *Res = Builder.CreateCall(Intr, {LHS, RHS});
return Builder.CreateBitCast(Res, Ops[0]->getType());
}
case X86::BI__builtin_ia32_kandqi:
case X86::BI__builtin_ia32_kandhi:
case X86::BI__builtin_ia32_kandsi:

12
clang/lib/Headers/avx512bwintrin.h
View File

@ -143,6 +143,18 @@ _kortest_mask64_u8(__mmask64 __A, __mmask64 __B, unsigned char *__C) {
return (unsigned char)__builtin_ia32_kortestzdi(__A, __B);
}
static __inline__ __mmask32 __DEFAULT_FN_ATTRS
_kadd_mask32(__mmask32 __A, __mmask32 __B)
{
return (__mmask32)__builtin_ia32_kaddsi((__mmask32)__A, (__mmask32)__B);
}
static __inline__ __mmask64 __DEFAULT_FN_ATTRS
_kadd_mask64(__mmask64 __A, __mmask64 __B)
{
return (__mmask64)__builtin_ia32_kadddi((__mmask64)__A, (__mmask64)__B);
}
/* Integer compare */
#define _mm512_cmp_epi8_mask(a, b, p) \

12
clang/lib/Headers/avx512dqintrin.h
View File

@ -86,6 +86,18 @@ _kortest_mask8_u8(__mmask8 __A, __mmask8 __B, unsigned char *__C) {
return (unsigned char)__builtin_ia32_kortestzqi(__A, __B);
}
static __inline__ __mmask8 __DEFAULT_FN_ATTRS
_kadd_mask8(__mmask8 __A, __mmask8 __B)
{
return (__mmask8)__builtin_ia32_kaddqi((__mmask8)__A, (__mmask8)__B);
}
static __inline__ __mmask16 __DEFAULT_FN_ATTRS
_kadd_mask16(__mmask16 __A, __mmask16 __B)
{
return (__mmask16)__builtin_ia32_kaddhi((__mmask16)__A, (__mmask16)__B);
}
static __inline__ __m512i __DEFAULT_FN_ATTRS512
_mm512_mullo_epi64 (__m512i __A, __m512i __B) {
return (__m512i) ((__v8du) __A * (__v8du) __B);

22
clang/test/CodeGen/avx512bw-builtins.c
View File

@ -226,6 +226,28 @@ unsigned char test_kortest_mask64_u8(__m512i __A, __m512i __B, __m512i __C, __m5
_mm512_cmpneq_epu8_mask(__C, __D), CF);
}
__mmask32 test_kadd_mask32(__m512i __A, __m512i __B, __m512i __C, __m512i __D, __m512i __E, __m512i __F) {
// CHECK-LABEL: @test_kadd_mask32
// CHECK: [[LHS:%.*]] = bitcast i32 %{{.*}} to <32 x i1>
// CHECK: [[RHS:%.*]] = bitcast i32 %{{.*}} to <32 x i1>
// CHECK: [[RES:%.*]] = call <32 x i1> @llvm.x86.avx512.kadd.d(<32 x i1> [[LHS]], <32 x i1> [[RHS]])
// CHECK: bitcast <32 x i1> [[RES]] to i32
return _mm512_mask_cmpneq_epu16_mask(_kadd_mask32(_mm512_cmpneq_epu16_mask(__A, __B),
_mm512_cmpneq_epu16_mask(__C, __D)),
__E, __F);
}
__mmask64 test_kadd_mask64(__m512i __A, __m512i __B, __m512i __C, __m512i __D, __m512i __E, __m512i __F) {
// CHECK-LABEL: @test_kadd_mask64
// CHECK: [[LHS:%.*]] = bitcast i64 %{{.*}} to <64 x i1>
// CHECK: [[RHS:%.*]] = bitcast i64 %{{.*}} to <64 x i1>
// CHECK: [[RES:%.*]] = call <64 x i1> @llvm.x86.avx512.kadd.q(<64 x i1> [[LHS]], <64 x i1> [[RHS]])
// CHECK: bitcast <64 x i1> [[RES]] to i64
return _mm512_mask_cmpneq_epu8_mask(_kadd_mask64(_mm512_cmpneq_epu8_mask(__A, __B),
_mm512_cmpneq_epu8_mask(__C, __D)),
__E, __F);
}
__mmask64 test_mm512_cmpeq_epi8_mask(__m512i __a, __m512i __b) {
// CHECK-LABEL: @test_mm512_cmpeq_epi8_mask
// CHECK: icmp eq <64 x i8> %{{.*}}, %{{.*}}

22
clang/test/CodeGen/avx512dq-builtins.c
View File

@ -114,6 +114,28 @@ unsigned char test_kortest_mask8_u8(__m512i __A, __m512i __B, __m512i __C, __m51
_mm512_cmpneq_epu64_mask(__C, __D), CF);
}
__mmask8 test_kadd_mask8(__m512i __A, __m512i __B, __m512i __C, __m512i __D, __m512i __E, __m512i __F) {
// CHECK-LABEL: @test_kadd_mask8
// CHECK: [[LHS:%.*]] = bitcast i8 %{{.*}} to <8 x i1>
// CHECK: [[RHS:%.*]] = bitcast i8 %{{.*}} to <8 x i1>
// CHECK: [[RES:%.*]] = call <8 x i1> @llvm.x86.avx512.kadd.b(<8 x i1> [[LHS]], <8 x i1> [[RHS]])
// CHECK: bitcast <8 x i1> [[RES]] to i8
return _mm512_mask_cmpneq_epu64_mask(_kadd_mask8(_mm512_cmpneq_epu64_mask(__A, __B),
_mm512_cmpneq_epu64_mask(__C, __D)),
__E, __F);
}
__mmask16 test_kadd_mask16(__m512i __A, __m512i __B, __m512i __C, __m512i __D, __m512i __E, __m512i __F) {
// CHECK-LABEL: @test_kadd_mask16
// CHECK: [[LHS:%.*]] = bitcast i16 %{{.*}} to <16 x i1>
// CHECK: [[RHS:%.*]] = bitcast i16 %{{.*}} to <16 x i1>
// CHECK: [[RES:%.*]] = call <16 x i1> @llvm.x86.avx512.kadd.w(<16 x i1> [[LHS]], <16 x i1> [[RHS]])
// CHECK: bitcast <16 x i1> [[RES]] to i16
return _mm512_mask_cmpneq_epu32_mask(_kadd_mask16(_mm512_cmpneq_epu32_mask(__A, __B),
_mm512_cmpneq_epu32_mask(__C, __D)),
__E, __F);
}
__m512i test_mm512_mullo_epi64 (__m512i __A, __m512i __B) {
// CHECK-LABEL: @test_mm512_mullo_epi64
// CHECK: mul <8 x i64>