In my current project I need a high performace xorcpy implemented in C. Here is my implementation to share and it is tested on my Xeon E5-2680 PC, it reaches almost 1.7GB\/s.<\/p>\n
#include <emmintrin.h>\n...\n__forceinline unsigned char* xorcpy(unsigned char* dst, const unsigned char* src, unsigned block_size)\n{\n \/\/ Do the bulk of the copy a __m128i at a time, for faster speed\n __m128i* mto = (__m128i*)dst;\n const __m128i* mfrom = (__m128i*)(src);\n for(int i=(block_size \/ sizeof(__m128i) - 1); i>=0; i--)\n {\n __m128i xmm1 = _mm_loadu_si128(mto);\n __m128i xmm2 = _mm_loadu_si128(mfrom);\n\n xmm1 = _mm_xor_si128(xmm1, xmm2); \/\/ XOR 16 bytes\n _mm_storeu_si128(mto, xmm1);\n ++mto;\n ++mfrom;\n }\n\n \/\/ The rest bytes we have to do a byte a time though\n unsigned char* cto = (unsigned char*) mto;\n const unsigned char* cfrom = (const unsigned char*)mfrom;\n for(int i=(block_size % sizeof(__m128i)) - 1; i>=0; i--)\n {\n *cto++ ^= (*cfrom++);\n }\n return dst;\n}\n<\/pre>\n","protected":false},"excerpt":{"rendered":"In my current project I need a high performace xorcpy implemented in C. Here is my implementation to share and it is tested on my Xeon E5-2680 PC, it reaches almost 1.7GB\/s. #include <emmintrin.h> … __forceinline unsigned char* xorcpy(unsigned char* dst, const unsigned char* src, unsigned block_size) { \/\/ Do the bulk of the copy … Continue reading “SIMD high performace xorcpy in C”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[12,2],"tags":[],"class_list":["post-558","post","type-post","status-publish","format-standard","hentry","category-cc","category-it"],"_links":{"self":[{"href":"https:\/\/nickdu.com\/index.php?rest_route=\/wp\/v2\/posts\/558","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nickdu.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nickdu.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nickdu.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/nickdu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=558"}],"version-history":[{"count":0,"href":"https:\/\/nickdu.com\/index.php?rest_route=\/wp\/v2\/posts\/558\/revisions"}],"wp:attachment":[{"href":"https:\/\/nickdu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=558"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nickdu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=558"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nickdu.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=558"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}