--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/src/impl/x86/sse3.c	Thu Apr 24 00:54:02 2025 -0400
@@ -0,0 +1,58 @@
+/**
+ * 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/sse3.h"
+
+#include <pmmintrin.h>
+
+/* SSE3 has a slightly more optimized load function */
+
+#define VEC_SSE2_DEFINE_OPERATIONS_SIGN(sign, bits, size) \
+	union v##sign##int##bits##x##size##_impl_data { \
+		v##sign##int##bits##x##size vec; \
+		__m128i sse; \
+	}; \
+	\
+	VEC_STATIC_ASSERT(VEC_ALIGNOF(__m128i) <= 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(__m128i) <= 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##_sse2_load(const vec_##sign##int##bits in[size]) \
+	{ \
+		union v##sign##int##bits##x##size##_impl_data vec; \
+		vec.sse = _mm_lddqu_si128((const __m128i *)in); \
+		return vec.vec; \
+	} \
+	\
+	const v##sign##int##bits##x##size##_impl v##sign##int##bits##x##size##_impl_sse3 = { \
+		.load = v##sign##int##bits##x##size##_sse2_load, \
+	};
+
+#define VEC_SSE2_DEFINE_OPERATIONS(bits, size) \
+	VEC_SSE2_DEFINE_OPERATIONS_SIGN(u, bits, size) \
+	VEC_SSE2_DEFINE_OPERATIONS_SIGN( , bits, size)
+
+VEC_SSE2_DEFINE_OPERATIONS(8, 16)
+VEC_SSE2_DEFINE_OPERATIONS(16, 8)
+VEC_SSE2_DEFINE_OPERATIONS(32, 4)
+VEC_SSE2_DEFINE_OPERATIONS(64, 2)