https://github.com/eulerkochy created
https://github.com/llvm/llvm-project/pull/156369
None
>From e3795502f1acf7ec5c3980ed9fdb502bbf9403ba Mon Sep 17 00:00:00 2001
From: Koustav Chowdhury <kc99....@gmail.com>
Date: Tue, 2 Sep 2025 01:11:34 +0530
Subject: [PATCH] feat: constexpr SSE multiplication intrinsics
---
clang/lib/Headers/avx2intrin.h | 5 ++---
clang/lib/Headers/avx512bwintrin.h | 4 ++--
clang/lib/Headers/avx512dqintrin.h | 8 ++++----
clang/lib/Headers/avx512fintrin.h | 15 ++++++---------
clang/lib/Headers/avx512vlbwintrin.h | 8 ++++----
clang/lib/Headers/avx512vldqintrin.h | 16 ++++++++--------
clang/lib/Headers/avx512vlintrin.h | 10 ++++------
clang/lib/Headers/smmintrin.h | 4 ++--
8 files changed, 32 insertions(+), 38 deletions(-)
diff --git a/clang/lib/Headers/avx2intrin.h b/clang/lib/Headers/avx2intrin.h
index 384faa35d246f..4d03103ac1e08 100644
--- a/clang/lib/Headers/avx2intrin.h
+++ b/clang/lib/Headers/avx2intrin.h
@@ -1766,9 +1766,8 @@ _mm256_mullo_epi16(__m256i __a, __m256i __b)
/// \param __b
/// A 256-bit vector of [8 x i32] containing one of the source operands.
/// \returns A 256-bit vector of [8 x i32] containing the products.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_mullo_epi32 (__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_mullo_epi32(__m256i __a, __m256i __b) {
return (__m256i)((__v8su)__a * (__v8su)__b);
}
diff --git a/clang/lib/Headers/avx512bwintrin.h
b/clang/lib/Headers/avx512bwintrin.h
index eabe215947761..8e9cc395abb2a 100644
--- a/clang/lib/Headers/avx512bwintrin.h
+++ b/clang/lib/Headers/avx512bwintrin.h
@@ -451,14 +451,14 @@ _mm512_mullo_epi16 (__m512i __A, __m512i __B) {
return (__m512i) ((__v32hu) __A * (__v32hu) __B);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_mullo_epi16(__m512i __W, __mmask32 __U, __m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_selectw_512((__mmask32)__U,
(__v32hi)_mm512_mullo_epi16(__A,
__B),
(__v32hi)__W);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_mullo_epi16(__mmask32 __U, __m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_selectw_512((__mmask32)__U,
(__v32hi)_mm512_mullo_epi16(__A,
__B),
diff --git a/clang/lib/Headers/avx512dqintrin.h
b/clang/lib/Headers/avx512dqintrin.h
index 87d16b474d466..b0fe903d82431 100644
--- a/clang/lib/Headers/avx512dqintrin.h
+++ b/clang/lib/Headers/avx512dqintrin.h
@@ -156,19 +156,19 @@ _store_mask8(__mmask8 *__A, __mmask8 __B) {
*(__mmask8 *)__A = __builtin_ia32_kmovb((__mmask8)__B);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mullo_epi64 (__m512i __A, __m512i __B) {
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mullo_epi64(__m512i __A, __m512i __B) {
return (__m512i) ((__v8du) __A * (__v8du) __B);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_mullo_epi64(__m512i __W, __mmask8 __U, __m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_selectq_512((__mmask8)__U,
(__v8di)_mm512_mullo_epi64(__A,
__B),
(__v8di)__W);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_mullo_epi64(__mmask8 __U, __m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_selectq_512((__mmask8)__U,
(__v8di)_mm512_mullo_epi64(__A,
__B),
diff --git a/clang/lib/Headers/avx512fintrin.h
b/clang/lib/Headers/avx512fintrin.h
index 0006e334022b6..1968b2b3d91d2 100644
--- a/clang/lib/Headers/avx512fintrin.h
+++ b/clang/lib/Headers/avx512fintrin.h
@@ -1450,23 +1450,20 @@ _mm512_maskz_mul_epu32(__mmask8 __M, __m512i __X,
__m512i __Y)
(__v8di)_mm512_setzero_si512 ());
}
-static __inline __m512i __DEFAULT_FN_ATTRS512
-_mm512_mullo_epi32 (__m512i __A, __m512i __B)
-{
+static __inline __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mullo_epi32(__m512i __A, __m512i __B) {
return (__m512i) ((__v16su) __A * (__v16su) __B);
}
-static __inline __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_mullo_epi32(__mmask16 __M, __m512i __A, __m512i __B)
-{
+static __inline __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_mullo_epi32(__mmask16 __M, __m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__M,
(__v16si)_mm512_mullo_epi32(__A,
__B),
(__v16si)_mm512_setzero_si512());
}
-static __inline __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_mullo_epi32(__m512i __W, __mmask16 __M, __m512i __A, __m512i __B)
-{
+static __inline __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_mullo_epi32(__m512i __W, __mmask16 __M, __m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__M,
(__v16si)_mm512_mullo_epi32(__A,
__B),
(__v16si)__W);
diff --git a/clang/lib/Headers/avx512vlbwintrin.h
b/clang/lib/Headers/avx512vlbwintrin.h
index ea6144008200a..888086dc214f1 100644
--- a/clang/lib/Headers/avx512vlbwintrin.h
+++ b/clang/lib/Headers/avx512vlbwintrin.h
@@ -426,28 +426,28 @@ _mm_maskz_sub_epi16(__mmask8 __U, __m128i __A, __m128i
__B) {
(__v8hi)_mm_setzero_si128());
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_mullo_epi16(__m256i __W, __mmask16 __U, __m256i __A, __m256i __B) {
return (__m256i)__builtin_ia32_selectw_256((__mmask16)__U,
(__v16hi)_mm256_mullo_epi16(__A,
__B),
(__v16hi)__W);
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_mullo_epi16(__mmask16 __U, __m256i __A, __m256i __B) {
return (__m256i)__builtin_ia32_selectw_256((__mmask16)__U,
(__v16hi)_mm256_mullo_epi16(__A,
__B),
(__v16hi)_mm256_setzero_si256());
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_mullo_epi16(__m128i __W, __mmask8 __U, __m128i __A, __m128i __B) {
return (__m128i)__builtin_ia32_selectw_128((__mmask8)__U,
(__v8hi)_mm_mullo_epi16(__A, __B),
(__v8hi)__W);
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_mullo_epi16(__mmask8 __U, __m128i __A, __m128i __B) {
return (__m128i)__builtin_ia32_selectw_128((__mmask8)__U,
(__v8hi)_mm_mullo_epi16(__A, __B),
diff --git a/clang/lib/Headers/avx512vldqintrin.h
b/clang/lib/Headers/avx512vldqintrin.h
index ceebd09e1d3af..e93eb10c31ce2 100644
--- a/clang/lib/Headers/avx512vldqintrin.h
+++ b/clang/lib/Headers/avx512vldqintrin.h
@@ -32,38 +32,38 @@
#define __DEFAULT_FN_ATTRS128_CONSTEXPR __DEFAULT_FN_ATTRS128
#endif
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_mullo_epi64 (__m256i __A, __m256i __B) {
+static __inline__ __m256i __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm256_mullo_epi64(__m256i __A, __m256i __B) {
return (__m256i) ((__v4du) __A * (__v4du) __B);
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm256_mask_mullo_epi64(__m256i __W, __mmask8 __U, __m256i __A, __m256i __B) {
return (__m256i)__builtin_ia32_selectq_256((__mmask8)__U,
(__v4di)_mm256_mullo_epi64(__A,
__B),
(__v4di)__W);
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm256_maskz_mullo_epi64(__mmask8 __U, __m256i __A, __m256i __B) {
return (__m256i)__builtin_ia32_selectq_256((__mmask8)__U,
(__v4di)_mm256_mullo_epi64(__A,
__B),
(__v4di)_mm256_setzero_si256());
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
-_mm_mullo_epi64 (__m128i __A, __m128i __B) {
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_mullo_epi64(__m128i __A, __m128i __B) {
return (__m128i) ((__v2du) __A * (__v2du) __B);
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_mullo_epi64(__m128i __W, __mmask8 __U, __m128i __A, __m128i __B) {
return (__m128i)__builtin_ia32_selectq_128((__mmask8)__U,
(__v2di)_mm_mullo_epi64(__A, __B),
(__v2di)__W);
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_mullo_epi64(__mmask8 __U, __m128i __A, __m128i __B) {
return (__m128i)__builtin_ia32_selectq_128((__mmask8)__U,
(__v2di)_mm_mullo_epi64(__A, __B),
diff --git a/clang/lib/Headers/avx512vlintrin.h
b/clang/lib/Headers/avx512vlintrin.h
index 6e16d2d4a0620..41f11757abbea 100644
--- a/clang/lib/Headers/avx512vlintrin.h
+++ b/clang/lib/Headers/avx512vlintrin.h
@@ -429,17 +429,15 @@ _mm_maskz_mul_epu32(__mmask8 __M, __m128i __X, __m128i
__Y)
(__v2di)_mm_setzero_si128());
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_maskz_mullo_epi32(__mmask8 __M, __m256i __A, __m256i __B)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm256_maskz_mullo_epi32(__mmask8 __M, __m256i __A, __m256i __B) {
return (__m256i)__builtin_ia32_selectd_256((__mmask8)__M,
(__v8si)_mm256_mullo_epi32(__A,
__B),
(__v8si)_mm256_setzero_si256());
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_mask_mullo_epi32(__m256i __W, __mmask8 __M, __m256i __A, __m256i __B)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm256_mask_mullo_epi32(__m256i __W, __mmask8 __M, __m256i __A, __m256i __B) {
return (__m256i)__builtin_ia32_selectd_256((__mmask8)__M,
(__v8si)_mm256_mullo_epi32(__A,
__B),
(__v8si)__W);
diff --git a/clang/lib/Headers/smmintrin.h b/clang/lib/Headers/smmintrin.h
index f68dd7ed2bcc9..e8f1f57c97c08 100644
--- a/clang/lib/Headers/smmintrin.h
+++ b/clang/lib/Headers/smmintrin.h
@@ -548,8 +548,8 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_blendv_epi8(__m128i __V1,
/// \param __V2
/// A 128-bit integer vector.
/// \returns A 128-bit integer vector containing the products of both operands.
-static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_mullo_epi32(__m128i __V1,
- __m128i __V2) {
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_mullo_epi32(__m128i __V1, __m128i __V2) {
return (__m128i)((__v4su)__V1 * (__v4su)__V2);
}
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
