Skip to content

[X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name #123335

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jan 24, 2025
Merged

[X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name #123335

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ef97938
[X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name
phoebewang Jan 17, 2025
6ff17f4
Merge remote-tracking branch 'origin/main' into BF16
phoebewang Jan 23, 2025
91a3429
Format X86InstrFMA3Info.cpp
phoebewang Jan 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
96 changes: 48 additions & 48 deletions clang/include/clang/Basic/BuiltinsX86.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5304,75 +5304,75 @@ let Features = "avx10.2-256", Attributes = [NoThrow, RequiredVectorWidth<128>] i
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vaddnepbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
def vaddbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vaddnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
def vaddbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vaddnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
def vaddbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vdivnepbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
def vdivbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vdivnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
def vdivbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vdivnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
def vdivbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vmaxpbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
def vmaxbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vmaxpbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
def vmaxbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vmaxpbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
def vmaxbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vminpbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
def vminbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vminpbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
def vminbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vminpbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
def vminbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vmulnepbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
def vmulbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vmulnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
def vmulbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vmulnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
def vmulbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vsubnepbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
def vsubbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vsubnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
def vsubbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vsubnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
def vsubbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
Expand All @@ -5385,120 +5385,120 @@ let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vcmppbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, _Vector<32, __bf16>, _Constant int, unsigned int)">;
def vcmpbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, _Vector<32, __bf16>, _Constant int, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vcmppbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, _Vector<16, __bf16>, _Constant int, unsigned short)">;
def vcmpbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, _Vector<16, __bf16>, _Constant int, unsigned short)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vcmppbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, _Vector<8, __bf16>, _Constant int, unsigned char)">;
def vfpclasspbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, _Constant int, unsigned char)">;
def vcmpbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, _Vector<8, __bf16>, _Constant int, unsigned char)">;
def vfpclassbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, _Constant int, unsigned char)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vfpclasspbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, _Constant int, unsigned short)">;
def vfpclassbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, _Constant int, unsigned short)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vfpclasspbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, _Constant int, unsigned int)">;
def vfpclassbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, _Constant int, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vscalefpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
def vscalefbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vscalefpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
def vscalefbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vscalefpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
def vscalefbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vrcppbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
def vrcpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vrcppbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
def vrcpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vrcppbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
def vrcpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vgetexppbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
def vgetexpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vgetexppbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
def vgetexpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vgetexppbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
def vgetexpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vrsqrtpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
def vrsqrtbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vrsqrtpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
def vrsqrtbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vrsqrtpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
def vrsqrtbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vreducenepbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Constant int, _Vector<8, __bf16>, unsigned char)">;
def vreducebf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Constant int, _Vector<8, __bf16>, unsigned char)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vreducenepbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Constant int, _Vector<16, __bf16>, unsigned short)">;
def vreducebf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Constant int, _Vector<16, __bf16>, unsigned short)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vreducenepbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Constant int, _Vector<32, __bf16>, unsigned int)">;
def vreducebf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Constant int, _Vector<32, __bf16>, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vrndscalenepbf16_128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Constant int, _Vector<8, __bf16>, unsigned char)">;
def vrndscalebf16_128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Constant int, _Vector<8, __bf16>, unsigned char)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vrndscalenepbf16_256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Constant int, _Vector<16, __bf16>, unsigned short)">;
def vrndscalebf16_256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Constant int, _Vector<16, __bf16>, unsigned short)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vrndscalenepbf16_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Constant int, _Vector<32, __bf16>, unsigned int)">;
def vrndscalebf16_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Constant int, _Vector<32, __bf16>, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vgetmantpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Constant int, _Vector<8, __bf16>, unsigned char)">;
def vgetmantbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Constant int, _Vector<8, __bf16>, unsigned char)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vgetmantpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Constant int, _Vector<16, __bf16>, unsigned short)">;
def vgetmantbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Constant int, _Vector<16, __bf16>, unsigned short)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vgetmantpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Constant int, _Vector<32, __bf16>, unsigned int)">;
def vgetmantbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Constant int, _Vector<32, __bf16>, unsigned int)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vsqrtnepbf16 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>)">;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why do we sometimes skip 128 suffix and sometimes 512 (see vrndscalenepbf16_mask)?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it followed __builtin_ia32_sqrtph. The reason maybe due to some instructions have SSE->AVX->AVX512 evolution, some only new introduced in AVX512.

Anyway, there's no naming convention for them AFAIK.

def vsqrtbf16 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vsqrtnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>)">;
def vsqrtbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>)">;
}

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vsqrtnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>)">;
def vsqrtbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>)">;
def vfmaddnepbh512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, _Vector<32, __bf16>)">;
}

Expand Down
30 changes: 15 additions & 15 deletions clang/lib/CodeGen/CGBuiltin.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16556,9 +16556,9 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
case X86::BI__builtin_ia32_sqrtph256:
case X86::BI__builtin_ia32_sqrtph:
case X86::BI__builtin_ia32_sqrtph512:
case X86::BI__builtin_ia32_vsqrtnepbf16256:
case X86::BI__builtin_ia32_vsqrtnepbf16:
case X86::BI__builtin_ia32_vsqrtnepbf16512:
case X86::BI__builtin_ia32_vsqrtbf16256:
case X86::BI__builtin_ia32_vsqrtbf16:
case X86::BI__builtin_ia32_vsqrtbf16512:
case X86::BI__builtin_ia32_sqrtps512:
case X86::BI__builtin_ia32_sqrtpd512: {
if (Ops.size() == 2) {
Expand Down Expand Up @@ -16778,9 +16778,9 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
case X86::BI__builtin_ia32_fpclassps128_mask:
case X86::BI__builtin_ia32_fpclassps256_mask:
case X86::BI__builtin_ia32_fpclassps512_mask:
case X86::BI__builtin_ia32_vfpclasspbf16128_mask:
case X86::BI__builtin_ia32_vfpclasspbf16256_mask:
case X86::BI__builtin_ia32_vfpclasspbf16512_mask:
case X86::BI__builtin_ia32_vfpclassbf16128_mask:
case X86::BI__builtin_ia32_vfpclassbf16256_mask:
case X86::BI__builtin_ia32_vfpclassbf16512_mask:
case X86::BI__builtin_ia32_fpclassph128_mask:
case X86::BI__builtin_ia32_fpclassph256_mask:
case X86::BI__builtin_ia32_fpclassph512_mask:
Expand All @@ -16795,14 +16795,14 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
Intrinsic::ID ID;
switch (BuiltinID) {
default: llvm_unreachable("Unsupported intrinsic!");
case X86::BI__builtin_ia32_vfpclasspbf16128_mask:
ID = Intrinsic::x86_avx10_fpclass_nepbf16_128;
case X86::BI__builtin_ia32_vfpclassbf16128_mask:
ID = Intrinsic::x86_avx10_fpclass_bf16_128;
break;
case X86::BI__builtin_ia32_vfpclasspbf16256_mask:
ID = Intrinsic::x86_avx10_fpclass_nepbf16_256;
case X86::BI__builtin_ia32_vfpclassbf16256_mask:
ID = Intrinsic::x86_avx10_fpclass_bf16_256;
break;
case X86::BI__builtin_ia32_vfpclasspbf16512_mask:
ID = Intrinsic::x86_avx10_fpclass_nepbf16_512;
case X86::BI__builtin_ia32_vfpclassbf16512_mask:
ID = Intrinsic::x86_avx10_fpclass_bf16_512;
break;
case X86::BI__builtin_ia32_fpclassph128_mask:
ID = Intrinsic::x86_avx512fp16_fpclass_ph_128;
Expand Down Expand Up @@ -16962,9 +16962,9 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
case X86::BI__builtin_ia32_vcmppd256_round_mask:
case X86::BI__builtin_ia32_vcmpps256_round_mask:
case X86::BI__builtin_ia32_vcmpph256_round_mask:
case X86::BI__builtin_ia32_vcmppbf16512_mask:
case X86::BI__builtin_ia32_vcmppbf16256_mask:
case X86::BI__builtin_ia32_vcmppbf16128_mask:
case X86::BI__builtin_ia32_vcmpbf16512_mask:
case X86::BI__builtin_ia32_vcmpbf16256_mask:
case X86::BI__builtin_ia32_vcmpbf16128_mask:
IsMaskFCmp = true;
[[fallthrough]];
case X86::BI__builtin_ia32_cmpps:
Expand Down
Loading
Loading