zlib-ng 2023-06-29 (cf89cf35)

Code extracted from:

    https://github.com/zlib-ng/zlib-ng.git

at commit cf89cf35037f152ce7adfeca864656de5d33ea1e (develop).

Author: kwrobot

CMakeLists.txt

@@ -1,18 +1,16 @@
+| CI | Stable | Develop |
+|:---|:-------|:--------|
+| GitHub Actions | [![Stable Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20CMake/badge.svg?branch=stable)](https://github.com/zlib-ng/zlib-ng/actions) <br> [![Stable Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20Configure/badge.svg?branch=stable)](https://github.com/zlib-ng/zlib-ng/actions) <br> [![Stable Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20NMake/badge.svg?branch=stable)](https://github.com/zlib-ng/zlib-ng/actions) | [![Develop Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20CMake/badge.svg?branch=develop)](https://github.com/zlib-ng/zlib-ng/actions) <br> [![Develop Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20Configure/badge.svg?branch=develop)](https://github.com/zlib-ng/zlib-ng/actions) <br> [![Develop Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20NMake/badge.svg?branch=develop)](https://github.com/zlib-ng/zlib-ng/actions) |
+| CodeFactor     | [![CodeFactor](https://www.codefactor.io/repository/github/zlib-ng/zlib-ng/badge/stable)](https://www.codefactor.io/repository/github/zlib-ng/zlib-ng/overview/stable) | [![CodeFactor](https://www.codefactor.io/repository/github/zlib-ng/zlib-ng/badge/develop)](https://www.codefactor.io/repository/github/zlib-ng/zlib-ng/overview/develop) |
+| OSS-Fuzz       | [![Fuzzing Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/zlib-ng.svg)](https://bugs.chromium.org/p/oss-fuzz/issues/list?sort=-opened&can=1&q=proj:zlib-ng) | [![Fuzzing Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/zlib-ng.svg)](https://bugs.chromium.org/p/oss-fuzz/issues/list?sort=-opened&can=1&q=proj:zlib-ng) |
+| Codecov        | [![codecov](https://codecov.io/github/zlib-ng/zlib-ng/branch/stable/graph/badge.svg?token=uKsgK9LIuC)](https://codecov.io/github/zlib-ng/zlib-ng/tree/stable) | [![codecov](https://codecov.io/github/zlib-ng/zlib-ng/branch/develop/graph/badge.svg?token=uKsgK9LIuC)](https://codecov.io/github/zlib-ng/zlib-ng/tree/develop) |
+
 ## zlib-ng
 *zlib data compression library for the next generation systems*
 
 Maintained by Hans Kristian Rosbach
           aka Dead2 (zlib-ng àt circlestorm dót org)
 
-|CI|Status|
-|:-|-|
-|GitHub Actions|[![Master Branch Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20CMake/badge.svg)](https://github.com/zlib-ng/zlib-ng/actions) [![Master Branch Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20Configure/badge.svg)](https://github.com/zlib-ng/zlib-ng/actions) [![Master Branch Status](https://github.com/zlib-ng/zlib-ng/workflows/CI%20NMake/badge.svg)](https://github.com/zlib-ng/zlib-ng/actions)|
-|Buildkite|[![Build status](https://badge.buildkite.com/7bb1ef84356d3baee26202706cc053ee1de871c0c712b65d26.svg?branch=develop)](https://buildkite.com/circlestorm-productions/zlib-ng)|
-|CodeFactor|[![CodeFactor](https://www.codefactor.io/repository/github/zlib-ng/zlib-ng/badge)](https://www.codefactor.io/repository/github/zlib-ng/zlib-ng)|
-|OSS-Fuzz|[![Fuzzing Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/zlib-ng.svg)](https://bugs.chromium.org/p/oss-fuzz/issues/list?sort=-opened&can=1&q=proj:zlib-ng)
-|Codecov|[![codecov.io](https://codecov.io/github/zlib-ng/zlib-ng/coverage.svg?branch=develop)](https://codecov.io/github/zlib-ng/zlib-ng/)|
-
-
 Features
 --------
 
@@ -25,60 +23,46 @@ Features
   * CRC32-B implementation using PCLMULQDQ, VPCLMULQDQ, ACLE, & IBM Z
   * Hash table implementation using CRC32-C intrinsics on x86 and ARM
   * Slide hash implementations using SSE2, AVX2, Neon, VMX & VSX
-  * Compare256 implementations using SSE2, AVX2, Neon, & POWER9
-  * Inflate chunk copying using SSE2, AVX, Neon & VSX
+  * Compare256 implementations using SSE2, AVX2, Neon, POWER9 & RVV
+  * Inflate chunk copying using SSE2, SSSE3, AVX, Neon & VSX
   * Support for hardware-accelerated deflate using IBM Z DFLTCC
 * Unaligned memory read/writes and large bit buffer improvements
 * Includes improvements from Cloudflare and Intel forks
 * Configure, CMake, and NMake build system support
 * Comprehensive set of CMake unit tests
 * Code sanitizers, fuzzing, and coverage
 * GitHub Actions continuous integration on Windows, macOS, and Linux
-  * Emulated CI for ARM, AARCH64, PPC, PPC64, SPARC64, S390x using qemu
+  * Emulated CI for ARM, AARCH64, PPC, PPC64, RISCV, SPARC64, S390x using qemu
 
 
 History
 -------
 
-The motivation for this fork came after seeing several 3rd party
-contributions containing new optimizations not getting implemented
-into the official zlib repository.
+The motivation for this fork was seeing several 3rd party contributions with new optimizations not getting
+implemented into the official zlib repository.
 
-Mark Adler has been maintaining zlib for a very long time, and he has
-done a great job and hopefully he will continue for a long time yet.
-The idea of zlib-ng is not to replace zlib, but to co-exist as a
-drop-in replacement with a lower threshold for code change.
+Mark Adler has been maintaining zlib for a very long time, and he has done a great job and hopefully he will continue
+for a long time yet. The idea of zlib-ng is not to replace zlib, but to co-exist as a drop-in replacement with a
+lower threshold for code change.
 
-zlib has a long history and is incredibly portable, even supporting
-lots of systems that predate the Internet. This is great, but it does
-complicate further development and maintainability.
-The zlib code has numerous workarounds for old compilers that do not
-understand ANSI-C or to accommodate systems with limitations such as
-operating in a 16-bit environment.
+zlib has a long history and is incredibly portable, even supporting many systems that predate the Internet.<br>
+That is great, but it can complicate further development and maintainability. The zlib code contains many workarounds
+for really old compilers or to accommodate systems with limitations such as operating in a 16-bit environment.
 
-Many of these workarounds are only maintenance burdens, some of them
-are pretty huge code-wise. For example, the [v]s[n]printf workaround
-code has a whopping 8 different implementations just to cater to
-various old compilers. With this many workarounds cluttered throughout
-the code, new programmers with an idea/interest for zlib will need
-to take some time to figure out why all of these seemingly strange
-things are used, and how to work within those confines.
+Many of these workarounds are only maintenance burdens, some of them are pretty huge code-wise. With many workarounds
+cluttered throughout the code, it makes it harder for new programmers with an idea/interest for zlib to contribute.
 
-So I decided to make a fork, merge all the Intel optimizations, merge
-the Cloudflare optimizations that did not conflict, plus a couple
-of other smaller patches. Then I started cleaning out workarounds,
-various dead code, all contrib and example code as there is little
-point in having those in this fork for various reasons.
+I decided to make a fork, merge all the Intel optimizations, some of the Cloudflare optimizations, plus a couple other
+smaller patches. Then started cleaning out workarounds, various dead code, all contrib and example code.<br>
+The result is a better performing and easier to maintain zlib-ng.
 
-A lot of improvements have gone into zlib-ng since its start, and
-numerous people and companies have contributed both small and big
-improvements, or valuable testing.
-
-Please read LICENSE.md, it is very simple and very liberal.
+A lot of improvements have gone into zlib-ng since its start, and numerous people and companies have contributed both
+small and big improvements, or valuable testing.
 
 
 Build
 -----
+<sup>Please read LICENSE.md, it is very simple and very liberal.</sup>
 
 There are two ways to build zlib-ng:
 
@@ -130,17 +114,14 @@ Build Options
 Install
 -------
 
-WARNING: We do not recommend manually installing unless you really
-know what you are doing, because this can potentially override the system
-default zlib library, and any incompatibility or wrong configuration of
-zlib-ng can make the whole system unusable, requiring recovery or reinstall.
+WARNING: We do not recommend manually installing unless you really know what you are doing, because this can
+potentially override the system default zlib library, and any incompatibility or wrong configuration of zlib-ng
+can make the whole system unusable, requiring recovery or reinstall.
 If you still want a manual install, we recommend using the /opt/ path prefix.
 
-For Linux distros, an alternative way to use zlib-ng (if compiled in
-zlib-compat mode) instead of zlib, is through the use of the
-_LD_PRELOAD_ environment variable. If the program is dynamically linked
-with zlib, then zlib-ng will temporarily be used instead by the program,
-without risking system-wide instability.
+For Linux distros, an alternative way to use zlib-ng (if compiled in zlib-compat mode) instead of zlib, is through
+the use of the _LD_PRELOAD_ environment variable. If the program is dynamically linked with zlib, then the program
+will temporarily attempt to use zlib-ng instead, without risking system-wide instability.
 
 ```
 LD_PRELOAD=/opt/zlib-ng/libz.so.1.2.13.zlib-ng /usr/bin/program
@@ -174,33 +155,27 @@ cd vcpkg
 ./vcpkg install zlib-ng
 ```
 
-The zlib-ng port in vcpkg is kept up to date by Microsoft team members and community contributors. If the version is out of date, please [create an issue or pull request](https://github.com/Microsoft/vcpkg) on the vcpkg repository.
+The zlib-ng port in vcpkg is kept up to date by Microsoft team members and community contributors.
+If the version is out of date, please [create an issue or pull request](https://github.com/Microsoft/vcpkg) on the vcpkg repository.
 
 Contributing
 ------------
 
-Zlib-ng is a aiming to be open to contributions, and we would be delighted to
-receive pull requests on github.
-Just remember that any code you submit must be your own and it must be zlib licensed.
-Help with testing and reviewing of pull requests etc is also very much appreciated.
-
-If you are interested in contributing, please consider joining our
-IRC channel #zlib-ng on the Freenode IRC network.
+Zlib-ng is aiming to be open to contributions, and we would be delighted to receive pull requests on github.
+Help with testing and reviewing pull requests etc is also very much appreciated.
 
+Please check the Wiki for more info: [Contributing](https://github.com/zlib-ng/zlib-ng/wiki/Contributing)
 
 Acknowledgments
 ----------------
 
-Thanks to Servebolt.com for sponsoring my maintainership of zlib-ng.
-
 Thanks go out to all the people and companies who have taken the time to contribute
 code reviews, testing and/or patches. Zlib-ng would not have been nearly as good without you.
 
-The deflate format used by zlib was defined by Phil Katz.
+The deflate format used by zlib was defined by Phil Katz.<br>
 The deflate and zlib specifications were written by L. Peter Deutsch.
 
-zlib was originally created by Jean-loup Gailly (compression)
-and Mark Adler (decompression).
+zlib was originally created by Jean-loup Gailly (compression) and Mark Adler (decompression).
 
 
 Advanced Build Options
@@ -213,14 +188,15 @@ Advanced Build Options
 | WITH_AVX512                     |                       | Build with AVX512 intrinsics                                        | ON                     |
 | WITH_AVX512VNNI                 |                       | Build with AVX512VNNI intrinsics                                    | ON                     |
 | WITH_SSE2                       |                       | Build with SSE2 intrinsics                                          | ON                     |
-| WITH_SSE41                      |                       | Build with SSE41 intrinsics                                         | ON                     |
+| WITH_SSSE3                      |                       | Build with SSSE3 intrinsics                                         | ON                     |
 | WITH_SSE42                      |                       | Build with SSE42 intrinsics                                         | ON                     |
 | WITH_PCLMULQDQ                  |                       | Build with PCLMULQDQ intrinsics                                     | ON                     |
 | WITH_VPCLMULQDQ                 | --without-vpclmulqdq  | Build with VPCLMULQDQ intrinsics                                    | ON                     |
 | WITH_ACLE                       | --without-acle        | Build with ACLE intrinsics                                          | ON                     |
 | WITH_NEON                       | --without-neon        | Build with NEON intrinsics                                          | ON                     |
 | WITH_ALTIVEC                    | --without-altivec     | Build with AltiVec (VMX) intrinsics                                 | ON                     |
 | WITH_POWER8                     | --without-power8      | Build with POWER8 optimisations                                     | ON                     |
+| WITH_RVV                        |                       | Build with RVV intrinsics                                           | ON                     |
 | WITH_CRC32_VX                   | --without-crc32-vx    | Build with vectorized CRC32 on IBM Z                                | ON                     |
 | WITH_DFLTCC_DEFLATE             | --with-dfltcc-deflate | Build with DFLTCC intrinsics for compression on IBM Z               | OFF                    |
 | WITH_DFLTCC_INFLATE             | --with-dfltcc-inflate | Build with DFLTCC intrinsics for decompression on IBM Z             | OFF                    |

README.md

@@ -73,5 +73,5 @@ clean:
 	rm -rf objs
 	rm -f *.gcda *.gcno *.gcov
 
-distclean:
+distclean: clean
 	rm -f Makefile

arch/arm/Makefile.in

@@ -5,7 +5,7 @@
  *   Adam Stylinski <kungfujesus06@gmail.com>
  * For conditions of distribution and use, see copyright notice in zlib.h
  */
-#ifdef ARM_NEON_ADLER32
+#ifdef ARM_NEON
 #include "neon_intrins.h"
 #include "../../zbuild.h"
 #include "../../adler32_p.h"
@@ -141,7 +141,7 @@ static void NEON_handle_tail(uint32_t *pair, const uint8_t *buf, size_t len) {
     }
 }
 
-uint32_t adler32_neon(uint32_t adler, const uint8_t *buf, size_t len) {
+Z_INTERNAL uint32_t adler32_neon(uint32_t adler, const uint8_t *buf, size_t len) {
     /* split Adler-32 into component sums */
     uint32_t sum2 = (adler >> 16) & 0xffff;
     adler &= 0xffff;

arch/arm/adler32_neon.c

@@ -1,4 +1,5 @@
 #include "../../zbuild.h"
+#include "arm_features.h"
 
 #if defined(__linux__) && defined(HAVE_SYS_AUXV_H)
 #  include <sys/auxv.h>
@@ -71,14 +72,11 @@ static inline int arm_has_neon() {
 }
 #endif
 
-Z_INTERNAL int arm_cpu_has_neon;
-Z_INTERNAL int arm_cpu_has_crc32;
-
-void Z_INTERNAL arm_check_features(void) {
+void Z_INTERNAL arm_check_features(struct arm_cpu_features *features) {
 #if defined(__aarch64__) || defined(_M_ARM64)
-    arm_cpu_has_neon = 1; /* always available */
+    features->has_neon = 1; /* always available */
 #else
-    arm_cpu_has_neon = arm_has_neon();
+    features->has_neon = arm_has_neon();
 #endif
-    arm_cpu_has_crc32 = arm_has_crc32();
+    features->has_crc32 = arm_has_crc32();
 }

arch/arm/arm_features.c

@@ -5,9 +5,11 @@
 #ifndef ARM_H_
 #define ARM_H_
 
-extern int arm_cpu_has_neon;
-extern int arm_cpu_has_crc32;
+struct arm_cpu_features {
+    int has_neon;
+    int has_crc32;
+};
 
-void Z_INTERNAL arm_check_features(void);
+void Z_INTERNAL arm_check_features(struct arm_cpu_features *features);
 
 #endif /* ARM_H_ */

arch/arm/arm_features.h

@@ -2,7 +2,7 @@
  * For conditions of distribution and use, see copyright notice in zlib.h
  */
 
-#ifdef ARM_NEON_CHUNKSET
+#ifdef ARM_NEON
 #include "neon_intrins.h"
 #include "../../zbuild.h"
 #include "../generic/chunk_permute_table.h"
@@ -69,7 +69,7 @@ static inline chunk_t GET_CHUNK_MAG(uint8_t *buf, uint32_t *chunk_rem, uint32_t
     *chunk_rem = lut_rem.remval;
 
 #ifdef Z_MEMORY_SANITIZER
-    /* See note in chunkset_sse41.c for why this is ok */
+    /* See note in chunkset_ssse3.c for why this is ok */
     __msan_unpoison(buf + dist, 16 - dist);
 #endif
 

arch/arm/chunkset_neon.c

@@ -5,15 +5,15 @@
  *
 */
 
-#ifdef ARM_ACLE_CRC_HASH
+#ifdef ARM_ACLE
 #ifdef _MSC_VER
 #  include <intrin.h>
 #else
 #  include <arm_acle.h>
 #endif
 #include "../../zbuild.h"
 
-uint32_t crc32_acle(uint32_t crc, const uint8_t *buf, size_t len) {
+Z_INTERNAL uint32_t crc32_acle(uint32_t crc, const uint8_t *buf, size_t len) {
     Z_REGISTER uint32_t c;
     Z_REGISTER const uint16_t *buf2;
     Z_REGISTER const uint32_t *buf4;

arch/arm/crc32_acle.c

@@ -5,7 +5,7 @@
  *
  */
 
-#ifdef ARM_ACLE_CRC_HASH
+#ifdef ARM_ACLE
 #ifndef _MSC_VER
 #  include <arm_acle.h>
 #endif

arch/arm/insert_string_acle.c

@@ -7,15 +7,15 @@
 #  include <arm_neon.h>
 #endif
 
-#if defined(ARM_NEON_ADLER32) && !defined(__aarch64__) && !defined(_M_ARM64)
+#if defined(ARM_NEON) && !defined(__aarch64__) && !defined(_M_ARM64)
 /* Compatibility shim for the _high family of functions */
 #define vmull_high_u8(a, b) vmull_u8(vget_high_u8(a), vget_high_u8(b))
 #define vmlal_high_u8(a, b, c) vmlal_u8(a, vget_high_u8(b), vget_high_u8(c))
 #define vmlal_high_u16(a, b, c) vmlal_u16(a, vget_high_u16(b), vget_high_u16(c))
 #define vaddw_high_u8(a, b) vaddw_u8(a, vget_high_u8(b))
 #endif
 
-#ifdef ARM_NEON_SLIDEHASH
+#ifdef ARM_NEON
 
 #define vqsubq_u16_x4_x1(out, a, b) do { \
     out.val[0] = vqsubq_u16(a.val[0], b); \
@@ -24,9 +24,8 @@
     out.val[3] = vqsubq_u16(a.val[3], b); \
 } while (0)
 
-#endif
 
-#if !defined(ARM_NEON_HASLD4) && (defined(ARM_NEON_ADLER32) || defined(ARM_NEON_SLIDEHASH))
+#  ifndef ARM_NEON_HASLD4
 
 static inline uint16x8x4_t vld1q_u16_x4(uint16_t const *a) {
     uint16x8x4_t ret = (uint16x8x4_t) {{
@@ -52,6 +51,7 @@ static inline void vst1q_u16_x4(uint16_t *p, uint16x8x4_t a) {
     vst1q_u16(p + 16, a.val[2]);
     vst1q_u16(p + 24, a.val[3]);
 }
-#endif // HASLD4 check
+#  endif // HASLD4 check
+#endif
 
 #endif // include guard ARM_NEON_INTRINS_H