--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/src/impl/x86/avx512dq.c	Thu Apr 24 00:54:02 2025 -0400
@@ -0,0 +1,57 @@
+/**
+ * vec - a tiny SIMD vector library in C99
+ * 
+ * Copyright (c) 2024 Paper
+ * 
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ * 
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ * 
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+**/
+
+#include "vec/impl/x86/avx512dq.h"
+
+#include <immintrin.h>
+
+/* ------------------------------------------------------------------------ */
+
+#define VEC_AVX512DQ_DEFINE_OPERATIONS_SIGN(sign, bits, size) \
+	union v##sign##int##bits##x##size##_impl_data { \
+		v##sign##int##bits##x##size vec; \
+		__m512i avx512dq; \
+	}; \
+	\
+	VEC_STATIC_ASSERT(VEC_ALIGNOF(__m512i) <= VEC_ALIGNOF(v##sign##int##bits##x##size), "vec: v" #sign "int" #bits "x" #size " alignment needs to be expanded to fit intrinsic type size"); \
+	VEC_STATIC_ASSERT(sizeof(__m512i) <= sizeof(v##sign##int##bits##x##size), "vec: v" #sign "int" #bits "x" #size " needs to be expanded to fit intrinsic type size"); \
+	\
+	VEC_FUNC_IMPL v##sign##int##bits##x##size v##sign##int##bits##x##size##_avx512dq_mul(v##sign##int##bits##x##size vec1, v##sign##int##bits##x##size vec2) \
+	{ \
+		union v##sign##int##bits##x##size##_impl_data *vec1d = (union v##sign##int##bits##x##size##_impl_data *)&vec1; \
+		union v##sign##int##bits##x##size##_impl_data *vec2d = (union v##sign##int##bits##x##size##_impl_data *)&vec2; \
+	\
+		vec1d->avx512dq = _mm512_mullo_epi64(vec1d->avx512dq, vec2d->avx512dq); \
+		return vec1d->vec; \
+	} \
+	\
+	const v##sign##int##bits##x##size##_impl v##sign##int##bits##x##size##_impl_avx512dq = { \
+		.mul = v##sign##int##bits##x##size##_avx512dq_mul, \
+	};
+
+#define VEC_AVX512DQ_DEFINE_OPERATIONS(bits, size) \
+	VEC_AVX512DQ_DEFINE_OPERATIONS_SIGN(u, bits, size) \
+	VEC_AVX512DQ_DEFINE_OPERATIONS_SIGN( , bits, size)
+
+VEC_AVX512DQ_DEFINE_OPERATIONS(64, 8)