16 Commits (ec8719ccbfcd78c6b40b5f2b94f60769f3bd08aa)

Author	SHA1	Message	Date
Nathan Bossart	ec8719ccbf	Optimize hex_encode() and hex_decode() using SIMD. ... The hex_encode() and hex_decode() functions serve as the workhorses for hexadecimal data for bytea's text format conversion functions, and some workloads are sensitive to their performance. This commit adds new implementations that use routines from port/simd.h, which testing indicates are much faster for larger inputs. For small or invalid inputs, we fall back on the existing scalar versions. Since we are using port/simd.h, these optimizations apply to both x86-64 and AArch64. Author: Nathan Bossart <nathandbossart@gmail.com> Co-authored-by: Chiranmoy Bhattacharya <chiranmoy.bhattacharya@fujitsu.com> Co-authored-by: Susmitha Devanga <devanga.susmitha@fujitsu.com> Reviewed-by: John Naylor <johncnaylorls@gmail.com> Discussion: https://postgr.es/m/aLhVWTRy0QPbW2tl%40nathan	3 months ago
Nathan Bossart	f8f4afe751	Optimize vector8_has_le() on AArch64. ... Presently, the SIMD implementation of this function uses unsigned saturating subtraction to find bytes less than or equal to the given value, which is a workaround for the lack of unsigned comparison instructions on some architectures. However, Neon offers vminvq_u8(), which returns the minimum (unsigned) value in the vector. This commit adds a Neon-specific implementation that uses vminvq_u8() to optimize vector8_has_le() on AArch64. In passing, adjust the SSE2 implementation to use vector8_min() and vector8_eq() to find values less than or equal to the given value. This was the only use of vector8_ssub(), so it has been removed. Reviewed-by: John Naylor <johncnaylorls@gmail.com> Discussion: https://postgr.es/m/aNHDNDSHleq0ogC_%40nathan	3 months ago
Bruce Momjian	50e6eb731d	Update copyright for 2025 ... Backpatch-through: 13	12 months ago
John Naylor	de7c6fe834	Fix signedness error in 9f225e992 for gcc ... The first argument of vshrq_n_s8 needs to be a signed vector type, but it was passed unsigned. Clang is more lax with conversion, but gcc needs a cast. Fix by me, tested by Masahiko Sawada Per buildfarm members splitfin, batta, widowbird, snakefly, parula, massasauga Discussion: https://postgr.es/m/20240306074106.mg6w4koohdlworbs%40alap3.anarazel.de	2 years ago
John Naylor	9f225e992b	Introduce helper SIMD functions for small byte arrays ... vector8_min - helper for emulating ">=" semantics vector8_highbit_mask - used to turn the result of a vector comparison into a bitmask Masahiko Sawada Reviewed by Nathan Bossart, with additional adjustments by me Discussion: https://postgr.es/m/CAFBsxsHbBm_M22gLBO%2BAZT4mfMq3L_oX3wdKZxjeNnT7fHsYMQ%40mail.gmail.com	2 years ago
Bruce Momjian	29275b1d17	Update copyright for 2024 ... Reported-by: Michael Paquier Discussion: https://postgr.es/m/ZZKTDPxBBMt3C0J9@paquier.xyz Backpatch-through: 12	2 years ago
Michael Paquier	ef7002dbe0	Fix various typos in code and tests ... Most of these are recent, and the documentation portions are new as of v16 so there is no need for a backpatch. Author: Justin Pryzby Discussion: https://postgr.es/m/20230208155644.GM1653@telsasoft.com	3 years ago
Bruce Momjian	c8e1ba736b	Update copyright for 2023 ... Backpatch-through: 11	3 years ago
John Naylor	73b9d051c6	Fix sign-compare warnings arising from port/simd.h ... Noted while building an extension using -Wsign-compare. Per gripe from Pavel Stehule Discussion: https://www.postgresql.org/message-id/CAFj8pRAagKQHfw71aQbL8PbL0S_360M61V0_vPqJXbpUFvqnRA%40mail.gmail.com	3 years ago
John Naylor	865424627d	Further code review of port/simd.h ... Add missing declaration per existing style, and fix a couple typos. Nathan Bossart and Julien Rouhaud Discussion: https://www.postgresql.org/message-id/20220829171712.GA509233%40nathanxps13 Discussion: https://www.postgresql.org/message-id/20220830022636.qrcbcecmhztbxrwa%40jrouhaud	3 years ago
John Naylor	c6a43c25a8	Fix broken cast on MSVC ... Per buildfarm animal drongo, casting a vector type to the same type causes a compile error. We still need the cast on ARM64, so invent a wrapper function that does the casting only where necessary. Discussion: https://www.postgresql.org/message-id/CAFBsxsEouaTwbmpqV%2BEW2%3DwFbhw2vHRe26NQTRcd0%3DNaOFDy7A%40mail.gmail.com	3 years ago
John Naylor	82739d4a80	Use ARM Advanced SIMD (NEON) intrinsics where available ... NEON support is required on the Aarch64 architecture for standard implementations. Hardware designers for specialized markets can choose not to support it, but that's true of floating point as well, which we assume is supported. As with x86, some SIMD support is available on 32-bit platforms, but those are not interesting from a performance standpoint and would require an inconvenient runtime check. Nathan Bossart Reviewed by John Naylor, Andres Freund, Thomas Munro, and Tom Lane Discussion: https://www.postgresql.org/message-id/flat/CAFBsxsEyR9JkfbPcDXBRYEfdfC__OkwVGdwEAgY4Rv0cvw35EA%40mail.gmail.com#aba7a64b11503494ffd8dd27067626a9	3 years ago
John Naylor	f8f19f7086	Abstract some more architecture-specific details away from SIMD functionality ... Add a typedef to represent vectors containing four 32-bit integers, and add functions operating on them. Also separate out saturating subtraction into its own function. The motivation for this is to prepare for a future commit to add ARM NEON support. Nathan Bossart Reviewed by John Naylor and Tom Lane Discussion: https://www.postgresql.org/message-id/flat/CAFBsxsEyR9JkfbPcDXBRYEfdfC__OkwVGdwEAgY4Rv0cvw35EA%40mail.gmail.com#aba7a64b11503494ffd8dd27067626a9	3 years ago
John Naylor	121d2d3d70	Use SSE2 in is_valid_ascii() where available. ... Per flame graph from Jelte Fennema, COPY FROM ... USING BINARY shows input validation taking at least 5% of the profile, so it's worth trying to be more efficient here. With this change, validation of pure ASCII is nearly 40% faster on contemporary Intel hardware. To make this change legible and easier to adopt to additional architectures, use helper functions to abstract the platform details away. Reviewed by Nathan Bossart Discussion: https://www.postgresql.org/message-id/CAFBsxsG%3Dk8t%3DC457FXnoBXb%3D8iA4OaZkbFogFMachWif7mNnww%40mail.gmail.com	3 years ago
John Naylor	e813e0e168	Add optimized functions for linear search within byte arrays ... In similar vein to b6ef167564, add pg_lfind8() and pg_lfind8_le() to search for bytes equal or less-than-or-equal to a given byte, respectively. To abstract away platform details, add helper functions and typedefs to simd.h. John Naylor and Nathan Bossart, per suggestion from Andres Freund Discussion: https://www.postgresql.org/message-id/CAFBsxsGzaaGLF%3DNuq61iRXTyspbO9rOjhSqFN%3DV6ozzmta5mXg%40mail.gmail.com	3 years ago
John Naylor	56f2c7b58b	Support SSE2 intrinsics where available ... SSE2 vector instructions are part of the spec for the 64-bit x86 architecture. Until now we have relied on the compiler to autovectorize in some limited situations, but some useful coding idioms can only be expressed explicitly via compiler intrinsics. To this end, add a header that defines USE_SSE2 where available. While x86-only for now, we can add other architectures in the future. This will also be the intended place for helper functions that use vector operations. Reviewed by Nathan Bossart and Masahiko Sawada Discussion: https://www.postgresql.org/message-id/CAFBsxsE2G_H_5Wbw%2BNOPm70-BK4xxKf86-mRzY%3DL2sLoQqM%2B-Q%40mail.gmail.com	3 years ago