41554 blogs · [ { "id": "01a0871c-e979-72e1-ab1b-821580529390", "title": "Rust is perfectly imperfect", "url": "http://0x80.pl/notesen/2026-01-08-imperfect-rust.html", "published_at": "2026-01-08T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215813750e4", "title": "Change case of UTF-32-encoded strings", "url": "http://0x80.pl/notesen/2025-02-02-utf32-change-case.html", "published_at": "2025-02-02T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158175eb2c", "title": "LoongArch64 subjective higlights", "url": "http://0x80.pl/notesen/2025-01-21-loongarch64-highlights.html", "published_at": "2025-01-19T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215819bbdf3", "title": "SIMD binary heap operations", "url": "http://0x80.pl/notesen/2025-01-18-simd-heap.html", "published_at": "2025-01-18T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215826d4b8e", "title": "AVX512: printing u64 as binary", "url": "http://0x80.pl/notesen/2025-01-18-avx512-print-bin.html", "published_at": "2025-01-18T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215831ae25c", "title": "Drawing trees", "url": "http://0x80.pl/notesen/2025-01-12-drawing-trees.html", "published_at": "2025-01-12T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215832233f4", "title": "Building full-text search in Javascript", "url": "http://0x80.pl/notesen/2025-01-07-js-search.html", "published_at": "2025-01-07T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821584210504", "title": "SIMD parallel bits deposit/extract", "url": "http://0x80.pl/notesen/2025-01-05-simd-pdep-pext.html", "published_at": "2025-01-05T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215851734f8", "title": "Dividing unsigned 16-bit numbers", "url": "http://0x80.pl/notesen/2025-01-03-uint16-division.html", "published_at": "2025-01-03T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215854b11a7", "title": "Dividing unsigned 8-bit numbers", "url": "http://0x80.pl/notesen/2024-12-21-uint8-division.html", "published_at": "2024-12-21T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821586039cc2", "title": "Myriad sequences of RISC-V code", "url": "http://0x80.pl/notesen/2024-11-11-myriad-riscv-sequence.html", "published_at": "2024-11-11T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821586d8374e", "title": "RISC-V Vector Extension overview", "url": "http://0x80.pl/notesen/2024-11-09-riscv-vector-extension.html", "published_at": "2024-11-09T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821587b0f588", "title": "Simple suggestions using popcount", "url": "http://0x80.pl/notesen/2023-11-20-popcount-suggestions.html", "published_at": "2023-11-20T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821587f41b29", "title": "AVX-512 conflict detection without resolving conflicts", "url": "http://0x80.pl/notesen/2023-05-06-avx512-conflict-detection.html", "published_at": "2023-05-06T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821588a5fb7f", "title": "Modern perfect hashing for strings", "url": "http://0x80.pl/notesen/2023-04-30-lookup-in-strings.html", "published_at": "2023-04-30T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821589738685", "title": "SIMD-ized faster parse of IPv4 addresses", "url": "http://0x80.pl/notesen/2023-04-09-faster-parse-ipv4.html", "published_at": "2023-04-09T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215899c98f7", "title": "SWAR find any byte from set", "url": "http://0x80.pl/notesen/2023-03-06-swar-find-any.html", "published_at": "2023-03-06T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158a9748ce", "title": "AVX512: finding first byte in lanes", "url": "http://0x80.pl/notesen/2023-02-06-avx512-find-first-byte-in-lane.html", "published_at": "2023-02-06T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158af20ccf", "title": "Finding lowest common ancestor of two nodes", "url": "http://0x80.pl/notesen/2023-02-05-tree-lca.html", "published_at": "2023-02-05T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158af7c516", "title": "Faster fractional exponents", "url": "http://0x80.pl/notesen/2023-02-05-fraction-pow.html", "published_at": "2023-02-05T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158b499d70", "title": "Converting binary fraction to ratio", "url": "http://0x80.pl/notesen/2023-02-05-float-to-ratio.html", "published_at": "2023-02-05T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158bf47e50", "title": "AVX512: count trailing zeros", "url": "http://0x80.pl/notesen/2023-01-31-avx512-bsf.html", "published_at": "2023-01-31T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158c2919c6", "title": "AVX512: check if value belongs to a set", "url": "http://0x80.pl/notesen/2023-01-21-avx512-any-eq.html", "published_at": "2023-01-21T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158ca2f217", "title": "AVX512: generating constants", "url": "http://0x80.pl/notesen/2023-01-19-avx512-consts.html", "published_at": "2023-01-19T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158cfa69c9", "title": "AVX512: histogram of sixteen nibbles", "url": "http://0x80.pl/notesen/2023-01-06-avx512-popcount-4bit.html", "published_at": "2023-01-06T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158d3d4d43", "title": "Faster hack", "url": "http://0x80.pl/notesen/2022-01-31-faster-hack.html", "published_at": "2022-01-31T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158dbf187c", "title": "Fast parsing HTTP verbs", "url": "http://0x80.pl/notesen/2022-01-29-http-verb-parse.html", "published_at": "2022-01-29T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158e54e6e4", "title": "DDoS-ed by a service runs on AWS", "url": "http://0x80.pl/notesen/2022-01-29-ddos.html", "published_at": "2022-01-29T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158e9bbe2e", "title": "AVX512VBMI2 and packed varuint format", "url": "http://0x80.pl/notesen/2022-01-24-avx512vbmi2-varuint.html", "published_at": "2022-01-24T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158f64e025", "title": "Parsing hex numbers with validation", "url": "http://0x80.pl/notesen/2022-01-17-validating-hex-parse.html", "published_at": "2022-01-17T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82158f78465c", "title": "Bit test and reset vs compilers", "url": "http://0x80.pl/notesen/2021-12-22-test-and-clear-bit.html", "published_at": "2021-12-22T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821590611850", "title": "Conversion uint32 into decimal without division nor multiplication", "url": "http://0x80.pl/notesen/2021-11-23-uint-to-ascii.html", "published_at": "2021-11-23T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215914da9fd", "title": "How to check if any word is zero", "url": "http://0x80.pl/notesen/2021-03-11-any-word-is-zero.html", "published_at": "2021-03-11T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821592324911", "title": "Autovectorization status in MSVC in 2021", "url": "http://0x80.pl/notesen/2021-02-17-autovectorization-msvc.html", "published_at": "2021-02-17T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159266eff0", "title": "Counting byte in byte stream with AVX512BW instructions", "url": "http://0x80.pl/notesen/2021-02-14-avx512bw-count-bytes.html", "published_at": "2021-02-14T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821592bdcb59", "title": "How to detect if all bytes in SIMD register are the same?", "url": "http://0x80.pl/notesen/2021-02-02-all-bytes-in-reg-are-equal.html", "published_at": "2021-02-02T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215934f6099", "title": "Autovectorization status in GCC & Clang in 2021", "url": "http://0x80.pl/notesen/2021-01-18-autovectorization-gcc-clang.html", "published_at": "2021-01-18T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821594081c00", "title": "Use AVX512 to calculate binomial coefficient", "url": "http://0x80.pl/notesen/2020-03-21-avx512-binomial-coefficient.html", "published_at": "2020-03-21T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821594e8a056", "title": "Use AVX512 Galois field affine transformation for bit shuffling", "url": "http://0x80.pl/notesen/2020-01-19-avx512-galois-field-for-bit-shuffling.html", "published_at": "2020-01-19T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159507341f", "title": "AVX512 8-bit positional population count procedure", "url": "http://0x80.pl/notesen/2019-12-31-avx512-pospopcnt-8bit.html", "published_at": "2019-12-31T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215955dcf07", "title": "SIMDization of switch statements", "url": "http://0x80.pl/notesen/2019-02-03-simd-switch-implementation.html", "published_at": "2019-02-03T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821595f45ee6", "title": "Malloc internal memory fragmentation footprint", "url": "http://0x80.pl/notesen/2019-02-03-malloc-internal-memory-fragmentation.html", "published_at": "2019-02-03T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159655a81a", "title": "Auto-vectorization status in GCC, Clang, ICC and MSVC", "url": "http://0x80.pl/notesen/2019-02-02-autovectorization-gcc-clang.html", "published_at": "2019-02-02T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821596874ef3", "title": "SIMDized counting byte in byte stream", "url": "http://0x80.pl/notesen/2019-01-29-simd-count-byte.html", "published_at": "2019-01-29T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821596ee99d3", "title": "std::function and overloaded functions", "url": "http://0x80.pl/notesen/2019-01-23-std-function-problems.html", "published_at": "2019-01-23T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821597406049", "title": "pyahocorasick stabilisation story", "url": "http://0x80.pl/notesen/2019-01-08-pyahocorasick-debugging.html", "published_at": "2019-01-08T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159810b340", "title": "C++ --- how to read a file into a string", "url": "http://0x80.pl/notesen/2019-01-07-cpp-read-file.html", "published_at": "2019-01-07T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-821598dabcca", "title": "AVX512VBMI --- remove spaces from text", "url": "http://0x80.pl/notesen/2019-01-05-avx512vbmi-remove-spaces.html", "published_at": "2019-01-05T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215994387bb", "title": "Python --- file modification time perils", "url": "http://0x80.pl/notesen/2018-11-24-python-stat-float.html", "published_at": "2018-11-24T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215999618d1", "title": "SIMDized sum of all bytes in the array --- part 2: signed bytes", "url": "http://0x80.pl/notesen/2018-11-18-sse-sumbytes-part2.html", "published_at": "2018-11-18T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159a2d91d6", "title": "How many uops are there?", "url": "http://0x80.pl/notesen/2018-11-18-skylakex-uops.html", "published_at": "2018-11-18T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159b12d960", "title": "A short report from code::dive 2018", "url": "http://0x80.pl/notesen/2018-11-15-code-dive-2018.html", "published_at": "2018-11-18T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159b25f5d2", "title": "Speeding up multiple vector operations using SIMD", "url": "http://0x80.pl/notesen/2018-11-14-simd-multiple-vector-ops.html", "published_at": "2018-11-14T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159b84ddfd", "title": "SIMD --- why you shouldn't use static vector constants", "url": "http://0x80.pl/notesen/2018-10-28-cpp-static-vectors.html", "published_at": "2018-10-28T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159bcfab9f", "title": "SIMDized sum of all bytes in the array", "url": "http://0x80.pl/notesen/2018-10-24-sse-sumbytes.html", "published_at": "2018-10-24T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159c3aae3d", "title": "SIMDized check which bytes are in a set", "url": "http://0x80.pl/notesen/2018-10-18-simd-byte-lookup.html", "published_at": "2018-10-18T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159d19a036", "title": "Finding index of the minimum value using SIMD instructions", "url": "http://0x80.pl/notesen/2018-10-03-simd-index-of-min.html", "published_at": "2018-10-03T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159d19b2f6", "title": "AVX512 mask registers support in compilers", "url": "http://0x80.pl/notesen/2018-05-18-avx512-ktest-in-compilers.html", "published_at": "2018-05-18T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159d3e9bfb", "title": "AVX512 implementation of JPEG zigzag transformation", "url": "http://0x80.pl/notesen/2018-05-13-avx512-jpeg-zigzag-transform.html", "published_at": "2018-05-13T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159ddc0320", "title": "Be careful with directory_iterator", "url": "http://0x80.pl/notesen/2018-04-28-be-careful-with-dir-iterator.html", "published_at": "2018-04-28T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159e270866", "title": "Parsing series of integers with SIMD", "url": "http://0x80.pl/notesen/2018-04-19-simd-parsing-int-sequences.html", "published_at": "2018-04-19T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159ea863d1", "title": "Accidental recursion", "url": "http://0x80.pl/notesen/2018-04-14-accidental-recursion.html", "published_at": "2018-04-14T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-82159f9bce6b", "title": "Is sorted using SIMD instructions", "url": "http://0x80.pl/notesen/2018-04-11-simd-is-sorted.html", "published_at": "2018-04-11T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a0078aa3", "title": "When lock does not lock --- C++ story", "url": "http://0x80.pl/notesen/2018-03-26-when-lock-does-not-lock.html", "published_at": "2018-03-26T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a0d13156", "title": "An awful part of C++17", "url": "http://0x80.pl/notesen/2018-03-16-awful-part-of-cpp.html", "published_at": "2018-03-16T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a181250d", "title": "Intersection of ordered sets", "url": "http://0x80.pl/notesen/2018-03-14-set-intersection.html", "published_at": "2018-03-14T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a1dfc62f", "title": "SSE/AVX: absolute value of difference of unsigned integers", "url": "http://0x80.pl/notesen/2018-03-11-sse-abs-unsigned.html", "published_at": "2018-03-11T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a23539e4", "title": "Is power of two --- BMI1 version", "url": "http://0x80.pl/notesen/2018-03-11-is-power-of-two-bmi1.html", "published_at": "2018-03-11T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a30576e2", "title": "A short report from code::dive 2017", "url": "http://0x80.pl/notesen/2017-11-26-code-dive-2017.html", "published_at": "2017-11-26T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a340dff8", "title": "ARM Neon and Base64 encoding & decoding", "url": "http://0x80.pl/notesen/2017-01-07-base64-simd-neon.html", "published_at": "2017-01-07T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a3d1e5dc", "title": "AVX512 --- first bit set in a large array", "url": "http://0x80.pl/notesen/2016-12-22-avx512-sparse-bfs.html", "published_at": "2016-12-22T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a490ba75", "title": "SWAR check if all chars are digits", "url": "http://0x80.pl/notesen/2016-12-21-swar-digits-validate.html", "published_at": "2016-12-21T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a4fdf0fb", "title": "Population count using XOP instructions", "url": "http://0x80.pl/notesen/2016-12-16-xop-popcnt.html", "published_at": "2016-12-16T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a583792c", "title": "SIMD-friendly algorithms for substring searching", "url": "http://0x80.pl/notesen/2016-11-28-simd-strfind.html", "published_at": "2016-11-28T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a62d69af", "title": "What does AVX512 conflict detection do?", "url": "http://0x80.pl/notesen/2016-10-23-avx512-conflict-detection.html", "published_at": "2016-10-23T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a725b5e1", "title": "Detecting bit patterns with series of zeros followed by ones", "url": "http://0x80.pl/notesen/2016-10-16-detecting-bit-pattern.html", "published_at": "2016-10-16T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a7eb4f56", "title": "Byte-wise alignr in AVX512F", "url": "http://0x80.pl/notesen/2016-10-16-avx512-byte-alignr.html", "published_at": "2016-10-16T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a86befe3", "title": "GNU std::string::find is very slow", "url": "http://0x80.pl/notesen/2016-10-08-slow-std-string-find.html", "published_at": "2016-10-08T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a92da096", "title": "Sorting an AVX512 register", "url": "http://0x80.pl/notesen/2016-10-08-avx512-sort-register.html", "published_at": "2016-10-08T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215a993788b", "title": "AVX512F base64 coding and decoding", "url": "http://0x80.pl/notesen/2016-09-17-avx512-foundation-base64.html", "published_at": "2016-09-17T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215aa2d5c26", "title": "SIMD bit mask", "url": "http://0x80.pl/notesen/2016-09-14-simd-bit-mask.html", "published_at": "2016-09-14T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215aa5b16c9", "title": "Building a bitmask", "url": "http://0x80.pl/notesen/2016-09-14-building-bitmask.html", "published_at": "2016-09-14T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215aa642eca", "title": "Base64 encoding & decoding using AVX512BW instructions", "url": "http://0x80.pl/notesen/2016-04-03-avx512-base64.html", "published_at": "2016-04-03T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215aa89a4a0", "title": "Implementing byte-wise lookup table with PSHUFB", "url": "http://0x80.pl/notesen/2016-03-13-simd-lookup-pshufb.html", "published_at": "2016-03-13T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215ab7bb141", "title": "Base64 decoding with SIMD instructions", "url": "http://0x80.pl/notesen/2016-01-17-sse-base64-decoding.html", "published_at": "2016-01-17T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215ac4af332", "title": "Base64 encoding with SIMD instructions", "url": "http://0x80.pl/notesen/2016-01-12-sse-base64-encoding.html", "published_at": "2016-01-12T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215ad2921bb", "title": "Speeding up letter case conversion", "url": "http://0x80.pl/notesen/2016-01-06-swar-swap-case.html", "published_at": "2016-01-06T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215ad426908", "title": "Fast conversion of floating-point values to string", "url": "http://0x80.pl/notesen/2015-12-29-float-to-string.html", "published_at": "2015-12-29T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215ae2c4ff7", "title": "Base64 encoding --- implementation study", "url": "http://0x80.pl/notesen/2015-12-27-base64-encoding.html", "published_at": "2015-12-27T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215af033cab", "title": "Benefits from the obsession", "url": "http://0x80.pl/notesen/2015-12-13-obsession.html", "published_at": "2015-12-13T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215afb7e4c7", "title": "Implicit conversion --- the enemy", "url": "http://0x80.pl/notesen/2015-11-28-implicit-conversion.html", "published_at": "2015-11-28T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b0b78137", "title": "Another C++ nasty feature", "url": "http://0x80.pl/notesen/2015-11-22-another-cpp-nasty-feature.html", "published_at": "2015-11-22T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b12b22ac", "title": "Short report from code::dive 2015", "url": "http://0x80.pl/notesen/2015-11-15-code-dive.html", "published_at": "2015-11-15T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b1e948b8", "title": "Boolean function for the rescue", "url": "http://0x80.pl/notesen/2015-10-25-boolean-functions.html", "published_at": "2015-10-25T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b228c875", "title": "Tricky mistake", "url": "http://0x80.pl/notesen/2015-05-25-tricky-mistake.html", "published_at": "2015-05-25T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b2fdcf4c", "title": "Speeding up bit-parallel population count", "url": "http://0x80.pl/notesen/2015-04-13-faster-popcount-for-large-data.html", "published_at": "2015-04-13T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b317831c", "title": "SIMD-ized searching in unique constant dictionary", "url": "http://0x80.pl/notesen/2015-04-08-simd-search.html", "published_at": "2015-04-08T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b3fef651", "title": "SIMD: detecting a bit pattern", "url": "http://0x80.pl/notesen/2015-03-22-simd-pattern.html", "published_at": "2015-03-22T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b4c7e6a4", "title": "Compiler warnings are your future errors", "url": "http://0x80.pl/notesen/2015-03-22-compiler-warnings.html", "published_at": "2015-03-22T11:00:00+00:00" }, { "id": "01a0871c-e979-72e1-ab1b-8215b55763f9", "title": "AVX512: ternary functions evaluation", "url": "http://0x80.pl/notesen/2015-03-22-avx512-ternary-functions.html", "published_at": "2015-03-22T11:00:00+00:00" } ] posts Claim your blog

Back to 0x80.pl

Blog · corpus.blog/blogs/0x80.pl/posts

0x80.pl

0x80.pl

2026

Rust is perfectly imperfect original ↗

8 Jan 2026

2025

Change case of UTF-32-encoded strings original ↗

2 Feb 2025

LoongArch64 subjective higlights original ↗

19 Jan 2025

SIMD binary heap operations original ↗

18 Jan 2025

AVX512: printing u64 as binary original ↗

18 Jan 2025

Drawing trees original ↗

12 Jan 2025

Building full-text search in Javascript original ↗

7 Jan 2025

SIMD parallel bits deposit/extract original ↗

5 Jan 2025

Dividing unsigned 16-bit numbers original ↗

3 Jan 2025

2024

Dividing unsigned 8-bit numbers original ↗

21 Dec 2024

Myriad sequences of RISC-V code original ↗

11 Nov 2024

RISC-V Vector Extension overview original ↗

9 Nov 2024

2023

Simple suggestions using popcount original ↗

20 Nov 2023

AVX-512 conflict detection without resolving conflicts original ↗

6 May 2023

Modern perfect hashing for strings original ↗

30 Apr 2023

SIMD-ized faster parse of IPv4 addresses original ↗

9 Apr 2023

SWAR find any byte from set original ↗

6 Mar 2023

AVX512: finding first byte in lanes original ↗

6 Feb 2023

Finding lowest common ancestor of two nodes original ↗

5 Feb 2023

Faster fractional exponents original ↗

5 Feb 2023

Converting binary fraction to ratio original ↗

5 Feb 2023

AVX512: count trailing zeros original ↗

31 Jan 2023

AVX512: check if value belongs to a set original ↗

21 Jan 2023

AVX512: generating constants original ↗

19 Jan 2023

AVX512: histogram of sixteen nibbles original ↗

6 Jan 2023

2022

Faster hack original ↗

31 Jan 2022

Fast parsing HTTP verbs original ↗

29 Jan 2022

DDoS-ed by a service runs on AWS original ↗

29 Jan 2022

AVX512VBMI2 and packed varuint format original ↗

24 Jan 2022

Parsing hex numbers with validation original ↗

17 Jan 2022

2021

Bit test and reset vs compilers original ↗

22 Dec 2021

Conversion uint32 into decimal without division nor multiplication original ↗

23 Nov 2021

How to check if any word is zero original ↗

11 Mar 2021

Autovectorization status in MSVC in 2021 original ↗

17 Feb 2021

Counting byte in byte stream with AVX512BW instructions original ↗

14 Feb 2021

How to detect if all bytes in SIMD register are the same?original ↗

2 Feb 2021

Autovectorization status in GCC & Clang in 2021 original ↗

18 Jan 2021

2020

Use AVX512 to calculate binomial coefficient original ↗

21 Mar 2020

Use AVX512 Galois field affine transformation for bit shuffling original ↗

19 Jan 2020

2019

AVX512 8-bit positional population count procedure original ↗

31 Dec 2019

SIMDization of switch statements original ↗

3 Feb 2019

Malloc internal memory fragmentation footprint original ↗

3 Feb 2019

Auto-vectorization status in GCC, Clang, ICC and MSVC original ↗

2 Feb 2019

SIMDized counting byte in byte stream original ↗

29 Jan 2019

std::function and overloaded functions original ↗

23 Jan 2019

pyahocorasick stabilisation story original ↗

8 Jan 2019

C++ --- how to read a file into a string original ↗

7 Jan 2019

AVX512VBMI --- remove spaces from text original ↗

5 Jan 2019

2018

Python --- file modification time perils original ↗

24 Nov 2018

SIMDized sum of all bytes in the array --- part 2: signed bytes original ↗

18 Nov 2018

How many uops are there?original ↗

18 Nov 2018

A short report from code::dive 2018 original ↗

18 Nov 2018

Speeding up multiple vector operations using SIMD original ↗

14 Nov 2018

SIMD --- why you shouldn't use static vector constants original ↗

28 Oct 2018

SIMDized sum of all bytes in the array original ↗

24 Oct 2018

SIMDized check which bytes are in a set original ↗

18 Oct 2018

Finding index of the minimum value using SIMD instructions original ↗

3 Oct 2018

AVX512 mask registers support in compilers original ↗

18 May 2018

AVX512 implementation of JPEG zigzag transformation original ↗

13 May 2018

Be careful with directory_iterator original ↗

28 Apr 2018

Parsing series of integers with SIMD original ↗

19 Apr 2018

Accidental recursion original ↗

14 Apr 2018

Is sorted using SIMD instructions original ↗

11 Apr 2018

When lock does not lock --- C++ story original ↗

26 Mar 2018

An awful part of C++17 original ↗

16 Mar 2018

Intersection of ordered sets original ↗

14 Mar 2018

SSE/AVX: absolute value of difference of unsigned integers original ↗

11 Mar 2018

Is power of two --- BMI1 version original ↗

11 Mar 2018

2017

A short report from code::dive 2017 original ↗

26 Nov 2017

ARM Neon and Base64 encoding & decoding original ↗

7 Jan 2017

2016

AVX512 --- first bit set in a large array original ↗

22 Dec 2016

SWAR check if all chars are digits original ↗

21 Dec 2016

Population count using XOP instructions original ↗

16 Dec 2016

SIMD-friendly algorithms for substring searching original ↗

28 Nov 2016

What does AVX512 conflict detection do?original ↗

23 Oct 2016

Detecting bit patterns with series of zeros followed by ones original ↗

16 Oct 2016

Byte-wise alignr in AVX512F original ↗

16 Oct 2016

GNU std::string::find is very slow original ↗

8 Oct 2016

Sorting an AVX512 register original ↗

8 Oct 2016

AVX512F base64 coding and decoding original ↗

17 Sept 2016

SIMD bit mask original ↗

14 Sept 2016

Building a bitmask original ↗

14 Sept 2016

Base64 encoding & decoding using AVX512BW instructions original ↗

3 Apr 2016

Implementing byte-wise lookup table with PSHUFB original ↗

13 Mar 2016

Base64 decoding with SIMD instructions original ↗

17 Jan 2016

Base64 encoding with SIMD instructions original ↗

12 Jan 2016

Speeding up letter case conversion original ↗

6 Jan 2016

2015

Fast conversion of floating-point values to string original ↗

29 Dec 2015

Base64 encoding --- implementation study original ↗

27 Dec 2015

Benefits from the obsession original ↗

13 Dec 2015

Implicit conversion --- the enemy original ↗

28 Nov 2015

Another C++ nasty feature original ↗

22 Nov 2015

Short report from code::dive 2015 original ↗

15 Nov 2015

Boolean function for the rescue original ↗

25 Oct 2015

Tricky mistake original ↗

25 May 2015

Speeding up bit-parallel population count original ↗

13 Apr 2015

SIMD-ized searching in unique constant dictionary original ↗

8 Apr 2015

SIMD: detecting a bit pattern original ↗

22 Mar 2015

Compiler warnings are your future errors original ↗

22 Mar 2015

AVX512: ternary functions evaluation original ↗

22 Mar 2015