Skip to content

[Clang][X86] Replace unnecessary vfmadd* builtins with element_wise_fma #152545

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 4 commits into from
Aug 8, 2025
Merged

[Clang][X86] Replace unnecessary vfmadd* builtins with element_wise_fma #152545

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f6ac261
[Clang][X86] Replace some `__builtin_ia32_vfmadd*` with `__builtin_el…
moorabbit Aug 7, 2025
b1f12e0
Clang format
moorabbit Aug 7, 2025
f14a124
phoebewang comment
moorabbit Aug 8, 2025
5e138bf
Merge branch 'main' into replace-ia32-vfma-intrinsics
RKSimon Aug 8, 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
27 changes: 2 additions & 25 deletions clang/include/clang/Basic/BuiltinsX86.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -878,11 +878,6 @@ let Features = "sha", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in
def sha256msg2 : X86Builtin<"_Vector<4, int>(_Vector<4, int>, _Vector<4, int>)">;
}

let Features = "fma|fma4", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vfmaddps : X86Builtin<"_Vector<4, float>(_Vector<4, float>, _Vector<4, float>, _Vector<4, float>)">;
def vfmaddpd : X86Builtin<"_Vector<2, double>(_Vector<2, double>, _Vector<2, double>, _Vector<2, double>)">;
}

let Features = "fma", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vfmaddss3 : X86Builtin<"_Vector<4, float>(_Vector<4, float>, _Vector<4, float>, _Vector<4, float>)">;
def vfmaddsd3 : X86Builtin<"_Vector<2, double>(_Vector<2, double>, _Vector<2, double>, _Vector<2, double>)">;
Expand All @@ -898,9 +893,8 @@ let Features = "fma|fma4", Attributes = [NoThrow, Const, RequiredVectorWidth<128
def vfmaddsubpd : X86Builtin<"_Vector<2, double>(_Vector<2, double>, _Vector<2, double>, _Vector<2, double>)">;
}

let Features = "fma|fma4", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vfmaddps256 : X86Builtin<"_Vector<8, float>(_Vector<8, float>, _Vector<8, float>, _Vector<8, float>)">;
def vfmaddpd256 : X86Builtin<"_Vector<4, double>(_Vector<4, double>, _Vector<4, double>, _Vector<4, double>)">;
let Features = "fma|fma4",
Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vfmaddsubps256 : X86Builtin<"_Vector<8, float>(_Vector<8, float>, _Vector<8, float>, _Vector<8, float>)">;
def vfmaddsubpd256 : X86Builtin<"_Vector<4, double>(_Vector<4, double>, _Vector<4, double>, _Vector<4, double>)">;
}
Expand Down Expand Up @@ -4140,14 +4134,6 @@ let Features = "avx512fp16,evex512", Attributes = [NoThrow, Const, RequiredVecto
def vcvtps2phx512_mask : X86Builtin<"_Vector<16, _Float16>(_Vector<16, float>, _Vector<16, _Float16>, unsigned short, _Constant int)">;
}

let Features = "avx512fp16,avx512vl", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vfmaddph : X86Builtin<"_Vector<8, _Float16>(_Vector<8, _Float16>, _Vector<8, _Float16>, _Vector<8, _Float16>)">;
}

let Features = "avx512fp16,avx512vl", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vfmaddph256 : X86Builtin<"_Vector<16, _Float16>(_Vector<16, _Float16>, _Vector<16, _Float16>, _Vector<16, _Float16>)">;
}

let Features = "avx512fp16,evex512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vfmaddph512_mask : X86Builtin<"_Vector<32, _Float16>(_Vector<32, _Float16>, _Vector<32, _Float16>, _Vector<32, _Float16>, unsigned int, _Constant int)">;
def vfmaddph512_mask3 : X86Builtin<"_Vector<32, _Float16>(_Vector<32, _Float16>, _Vector<32, _Float16>, _Vector<32, _Float16>, unsigned int, _Constant int)">;
Expand Down Expand Up @@ -5373,13 +5359,4 @@ let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<

let Features = "avx10.2-512", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
def vsqrtbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>)">;
def vfmaddbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, _Vector<32, __bf16>, _Vector<32, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
def vfmaddbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, _Vector<16, __bf16>, _Vector<16, __bf16>)">;
}

let Features = "avx10.2-256", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
def vfmaddbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, _Vector<8, __bf16>, _Vector<8, __bf16>)">;
}
9 changes: 0 additions & 9 deletions clang/lib/CodeGen/TargetBuiltins/X86.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1051,18 +1051,9 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
case X86::BI__builtin_ia32_vfmsubsd3_mask3:
return EmitScalarFMAExpr(*this, E, Ops, Ops[2], /*ZeroMask*/ false, 2,
/*NegAcc*/ true);
case X86::BI__builtin_ia32_vfmaddph:
case X86::BI__builtin_ia32_vfmaddps:
case X86::BI__builtin_ia32_vfmaddpd:
case X86::BI__builtin_ia32_vfmaddph256:
case X86::BI__builtin_ia32_vfmaddps256:
case X86::BI__builtin_ia32_vfmaddpd256:
case X86::BI__builtin_ia32_vfmaddph512_mask:
case X86::BI__builtin_ia32_vfmaddph512_maskz:
case X86::BI__builtin_ia32_vfmaddph512_mask3:
case X86::BI__builtin_ia32_vfmaddbf16128:
case X86::BI__builtin_ia32_vfmaddbf16256:
case X86::BI__builtin_ia32_vfmaddbf16512:
case X86::BI__builtin_ia32_vfmaddps512_mask:
case X86::BI__builtin_ia32_vfmaddps512_maskz:
case X86::BI__builtin_ia32_vfmaddps512_mask3:
Expand Down
16 changes: 8 additions & 8 deletions clang/lib/Headers/avx10_2_512bf16intrin.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -441,8 +441,8 @@ _mm512_maskz_sqrt_pbh(__mmask32 __U, __m512bh __A) {

static __inline__ __m512bh __DEFAULT_FN_ATTRS512
_mm512_fmadd_pbh(__m512bh __A, __m512bh __B, __m512bh __C) {
return (__m512bh)__builtin_ia32_vfmaddbf16512((__v32bf)__A, (__v32bf)__B,
(__v32bf)__C);
return (__m512bh)__builtin_elementwise_fma((__v32bf)__A, (__v32bf)__B,
(__v32bf)__C);
}

static __inline__ __m512bh __DEFAULT_FN_ATTRS512
Expand All @@ -469,8 +469,8 @@ static __inline__ __m512bh __DEFAULT_FN_ATTRS512 _mm512_maskz_fmadd_pbh(

static __inline__ __m512bh __DEFAULT_FN_ATTRS512
_mm512_fmsub_pbh(__m512bh __A, __m512bh __B, __m512bh __C) {
return (__m512bh)__builtin_ia32_vfmaddbf16512((__v32bf)__A, (__v32bf)__B,
-(__v32bf)__C);
return (__m512bh)__builtin_elementwise_fma((__v32bf)__A, (__v32bf)__B,
-(__v32bf)__C);
}

static __inline__ __m512bh __DEFAULT_FN_ATTRS512
Expand All @@ -497,8 +497,8 @@ static __inline__ __m512bh __DEFAULT_FN_ATTRS512 _mm512_maskz_fmsub_pbh(

static __inline__ __m512bh __DEFAULT_FN_ATTRS512
_mm512_fnmadd_pbh(__m512bh __A, __m512bh __B, __m512bh __C) {
return (__m512bh)__builtin_ia32_vfmaddbf16512((__v32bf)__A, -(__v32bf)__B,
(__v32bf)__C);
return (__m512bh)__builtin_elementwise_fma((__v32bf)__A, -(__v32bf)__B,
(__v32bf)__C);
}

static __inline__ __m512bh __DEFAULT_FN_ATTRS512 _mm512_mask_fnmadd_pbh(
Expand Down Expand Up @@ -527,8 +527,8 @@ static __inline__ __m512bh __DEFAULT_FN_ATTRS512 _mm512_maskz_fnmadd_pbh(

static __inline__ __m512bh __DEFAULT_FN_ATTRS512
_mm512_fnmsub_pbh(__m512bh __A, __m512bh __B, __m512bh __C) {
return (__m512bh)__builtin_ia32_vfmaddbf16512((__v32bf)__A, -(__v32bf)__B,
-(__v32bf)__C);
return (__m512bh)__builtin_elementwise_fma((__v32bf)__A, -(__v32bf)__B,
-(__v32bf)__C);
}

static __inline__ __m512bh __DEFAULT_FN_ATTRS512 _mm512_mask_fnmsub_pbh(
Expand Down
32 changes: 16 additions & 16 deletions clang/lib/Headers/avx10_2bf16intrin.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -852,8 +852,8 @@ _mm_maskz_sqrt_pbh(__mmask8 __U, __m128bh __A) {

static __inline__ __m256bh __DEFAULT_FN_ATTRS256
_mm256_fmadd_pbh(__m256bh __A, __m256bh __B, __m256bh __C) {
return (__m256bh)__builtin_ia32_vfmaddbf16256((__v16bf)__A, (__v16bf)__B,
(__v16bf)__C);
return (__m256bh)__builtin_elementwise_fma((__v16bf)__A, (__v16bf)__B,
(__v16bf)__C);
}

static __inline__ __m256bh __DEFAULT_FN_ATTRS256
Expand All @@ -880,8 +880,8 @@ static __inline__ __m256bh __DEFAULT_FN_ATTRS256 _mm256_maskz_fmadd_pbh(

static __inline__ __m256bh __DEFAULT_FN_ATTRS256
_mm256_fmsub_pbh(__m256bh __A, __m256bh __B, __m256bh __C) {
return (__m256bh)__builtin_ia32_vfmaddbf16256((__v16bf)__A, (__v16bf)__B,
-(__v16bf)__C);
return (__m256bh)__builtin_elementwise_fma((__v16bf)__A, (__v16bf)__B,
-(__v16bf)__C);
}

static __inline__ __m256bh __DEFAULT_FN_ATTRS256
Expand All @@ -908,8 +908,8 @@ static __inline__ __m256bh __DEFAULT_FN_ATTRS256 _mm256_maskz_fmsub_pbh(

static __inline__ __m256bh __DEFAULT_FN_ATTRS256
_mm256_fnmadd_pbh(__m256bh __A, __m256bh __B, __m256bh __C) {
return (__m256bh)__builtin_ia32_vfmaddbf16256((__v16bf)__A, -(__v16bf)__B,
(__v16bf)__C);
return (__m256bh)__builtin_elementwise_fma((__v16bf)__A, -(__v16bf)__B,
(__v16bf)__C);
}

static __inline__ __m256bh __DEFAULT_FN_ATTRS256 _mm256_mask_fnmadd_pbh(
Expand Down Expand Up @@ -938,8 +938,8 @@ static __inline__ __m256bh __DEFAULT_FN_ATTRS256 _mm256_maskz_fnmadd_pbh(

static __inline__ __m256bh __DEFAULT_FN_ATTRS256
_mm256_fnmsub_pbh(__m256bh __A, __m256bh __B, __m256bh __C) {
return (__m256bh)__builtin_ia32_vfmaddbf16256((__v16bf)__A, -(__v16bf)__B,
-(__v16bf)__C);
return (__m256bh)__builtin_elementwise_fma((__v16bf)__A, -(__v16bf)__B,
-(__v16bf)__C);
}

static __inline__ __m256bh __DEFAULT_FN_ATTRS256 _mm256_mask_fnmsub_pbh(
Expand Down Expand Up @@ -969,8 +969,8 @@ static __inline__ __m256bh __DEFAULT_FN_ATTRS256 _mm256_maskz_fnmsub_pbh(
static __inline__ __m128bh __DEFAULT_FN_ATTRS128 _mm_fmadd_pbh(__m128bh __A,
__m128bh __B,
__m128bh __C) {
return (__m128bh)__builtin_ia32_vfmaddbf16128((__v8bf)__A, (__v8bf)__B,
(__v8bf)__C);
return (__m128bh)__builtin_elementwise_fma((__v8bf)__A, (__v8bf)__B,
(__v8bf)__C);
}

static __inline__ __m128bh __DEFAULT_FN_ATTRS128
Expand All @@ -997,8 +997,8 @@ _mm_maskz_fmadd_pbh(__mmask8 __U, __m128bh __A, __m128bh __B, __m128bh __C) {
static __inline__ __m128bh __DEFAULT_FN_ATTRS128 _mm_fmsub_pbh(__m128bh __A,
__m128bh __B,
__m128bh __C) {
return (__m128bh)__builtin_ia32_vfmaddbf16128((__v8bf)__A, (__v8bf)__B,
-(__v8bf)__C);
return (__m128bh)__builtin_elementwise_fma((__v8bf)__A, (__v8bf)__B,
-(__v8bf)__C);
}

static __inline__ __m128bh __DEFAULT_FN_ATTRS128
Expand All @@ -1025,8 +1025,8 @@ _mm_maskz_fmsub_pbh(__mmask8 __U, __m128bh __A, __m128bh __B, __m128bh __C) {
static __inline__ __m128bh __DEFAULT_FN_ATTRS128 _mm_fnmadd_pbh(__m128bh __A,
__m128bh __B,
__m128bh __C) {
return (__m128bh)__builtin_ia32_vfmaddbf16128((__v8bf)__A, -(__v8bf)__B,
(__v8bf)__C);
return (__m128bh)__builtin_elementwise_fma((__v8bf)__A, -(__v8bf)__B,
(__v8bf)__C);
}

static __inline__ __m128bh __DEFAULT_FN_ATTRS128
Expand All @@ -1053,8 +1053,8 @@ _mm_maskz_fnmadd_pbh(__mmask8 __U, __m128bh __A, __m128bh __B, __m128bh __C) {
static __inline__ __m128bh __DEFAULT_FN_ATTRS128 _mm_fnmsub_pbh(__m128bh __A,
__m128bh __B,
__m128bh __C) {
return (__m128bh)__builtin_ia32_vfmaddbf16128((__v8bf)__A, -(__v8bf)__B,
-(__v8bf)__C);
return (__m128bh)__builtin_elementwise_fma((__v8bf)__A, -(__v8bf)__B,
-(__v8bf)__C);
}

static __inline__ __m128bh __DEFAULT_FN_ATTRS128
Expand Down
Loading