- 27f34a5 Fix -Wsign-compare warning by Richard O'Grady · 3 months ago main
- c9f9edf Fixes for Windows bazel build. by Richard O'Grady · 6 months ago
- 66a30b8 Add initial bazel build support for snappy. by Richard O'Grady · 6 months ago
- f725f67 Upgrade googletest to v1.13.0 release. by Richard O'Grady · 6 months ago
- 8325392 Disable Wimplicit-int-float-conversion warning in googletest by Richard O'Grady · 6 months ago
- 108139d Upgrade benchmark library to v1.7.1 release. by Richard O'Grady · 6 months ago
- 00aa9ac Disable -Wsign-compare warning. by Richard O'Grady · 6 months ago
- cfc573e Define missing SNAPPY_PREFETCH macros. by Richard O'Grady · 6 months ago
- 92f18e6 Add prefetch to zippy compress by Ilya Tokar · 6 months ago
- f603a02 Explicitly #include <utility> in snappy-internal.h by Snappy Team · 6 months ago
- 9c42b71 Optimize check for uncommon decompression for ARM, saving two instructions and three cycles. by Snappy Team · 6 months ago
- dc05e02 Tag open source release 1.1.10. by Victor Costan · 7 months ago 1.1.10
- 7b82423 The output buffer in DecompressBranchless is never read from and the source buffers are never written. This allows us to defer any writes to the output buffer for an arbitrary amount of time as long as the writes all occur in the proper order. When a MemCopy64 would have normally occurred we save away the source address and length. Once we reach the location of the next write to the output buffer first perform the deferred copy. This gives time for the source address calculation and length to finish before the deferred copy. by Snappy Team · 7 months ago
- 30326e5 Merge pull request #150 from davemgreen:betterunalignedloads by Victor Costan · 9 months ago
- 74960e8 Allow some buffer overwrite on literal emitting by Snappy Team · 9 months ago
- 37f375d Add prefetch to zippy decompess, by Ilya Tokar · 9 months ago
- 15e2a0e Add "cc" clobbers to inline asm that modifies flags. by Snappy Team · 9 months ago
- 8881ba1 Improve the speed of hashing in zippy compression. by Snappy Team · 9 months ago
- a2d219a Modify MemCopy64 to use AVX 32 byte copies instead of SSE2 16 byte copies on capable x86 platforms. This gives an average speedup of 6.87% on Milan and 1.90% on Skylake. by Snappy Team · 9 months ago
- 984b191 Fix the remaining occurrence of non-const `std::string::data()`. by Marcin Kowalczyk · 12 months ago
- 974fcc4 Fix compilation errors under C++11. by Matt Callanan · 12 months ago
- d644ca8 Fix warnings due to use of `__attribute__(always_inline)` without `inline`. by Marcin Kowalczyk · 12 months ago
- 9758c9d Add `snappy::CompressFromIOVec`. by Matt Callanan · 1 year ago
- af720f9 Merge pull request #148 from pitrou:ubsan-ptr-add-overflow by Victor Costan · 1 year, 2 months ago
- 44caf79 Move the comment about non-overlap requirement from the implementation to the by Marcin Kowalczyk · 1 year, 2 months ago
- d261d27 Optimize zippy MemCpy / MemMove during decompression by Snappy Team · 1 year, 2 months ago
- 6a2b78a Optimize Zippy compression for ARM by 5-10% by choosing csel instructions by Snappy Team · 1 year, 5 months ago
- 8dd58a5 Fix compilation for older GCC and Clang versions. by Snappy Team · 1 year, 7 months ago
- 6c6e890 Change LittleEndian loads/stores to use memcpy by David Green · 1 year, 9 months ago
- 8b07ff1 Update contributing guidelines. by Victor Costan · 1 year, 9 months ago
- 64df9f2 Fix UBSan error (ptr + offset overflow) by Antoine Pitrou · 1 year, 10 months ago
- 65dc7b3 Pass by reference the first argument of ExtractLowBytes by Snappy Team · 1 year, 11 months ago
- fe18b46 Switch CI to GitHub Actions. by Victor Costan · 2 years, 1 month ago
- a7ddc14 Merge pull request #140 from JunHe77:adv by Victor Costan · 2 years, 1 month ago
- aeb5de5 decompress: refine data depdency by Jun He · 2 years, 1 month ago
- 7062d7f Merge pull request #133 from JunHe77:simd by Victor Costan · 2 years, 1 month ago
- cbb83a1 Migrate feature detection macro checks from #ifdef to #if. by Victor Costan · 2 years, 2 months ago
- a8400f1 Add baseline CPU level to Travis CI. by Victor Costan · 2 years, 2 months ago
- b9c9a98 Merge pull request #135 from JunHe77:remove_extra by Victor Costan · 2 years, 2 months ago
- 5c87bc6 Merge pull request #136 from JunHe77:ext_arm by Victor Costan · 2 years, 2 months ago
- 734b32b Add config and header file for NEON support by Jun He · 2 years, 2 months ago
- ab9a572 Fix SSE3 and BMI2 compile error by Jun He · 2 years, 2 months ago
- d643b9a decompress: add hint to remove extra AND by Jun He · 2 years, 2 months ago
- f52721b decompression: optimize ExtractOffset for Arm by Jun He · 2 years, 2 months ago
- f2db8f7 Move the extract masks variable out in zippy. I see a consistent 1.5-2% improvement for ARM. Probably because ARM has more relaxed address computation than x86 https://www.godbolt.org/z/bfM1ezx41. I don't think this is a compiler bug or it can do something about it by Snappy Team · 2 years, 2 months ago
- c8f7641 Remove inline assembly as the bug in clang was fixed by Snappy Team · 2 years, 2 months ago
- 9cc3689 Optimize memset to pure SIMD because compilers generate consistently bad code. clang for ARM and gcc for x86 https://gcc.godbolt.org/z/oxeGG7aEx by Snappy Team · 2 years, 2 months ago
- b4888f7 Optimize tag extraction for ARM with conditional increment instruction generation (csinc). For codegen see https://gcc.godbolt.org/z/a8z9j95Pv by Snappy Team · 2 years, 3 months ago
- b3fb0b5 Enable vector byte shuffle optimizations on ARM NEON by atdt · 2 years, 3 months ago
- b638ebe Update Travis CI config. by Victor Costan · 2 years, 4 months ago
- d8f5dd8 Clarify, in a comment, that offset/256 fits in 3 bits. It has to in this context, because the other 5 bits in the byte are used for len-4 and the tag. by Snappy Team · 2 years, 4 months ago
- 2b63814 Tag open source release 1.1.9. by Victor Costan · 2 years, 5 months ago 1.1.9
- 9c1be17 'size' remains unused if none of ZLIB, LZO and LZ4 are available. by atdt · 2 years, 5 months ago
- 78650d1 Add project goals to CONTRIBUTING.md. by Chris Mumford · 2 years, 7 months ago
- 5e7c14b Add stubs for abseil flags. by Victor Costan · 2 years, 7 months ago
- 80a2a10 Remove unused run_microbenchmarks flag. by Victor Costan · 2 years, 7 months ago
- 453942b Add absl::GetFlag and absl::SetFlag to uses of flags. by Snappy Team · 2 years, 8 months ago
- ea368c2 Add AppVeyor status badge. by Victor Costan · 2 years, 10 months ago
- d1d1f48 Remove unused include in snappy_benchmark.cc. by Victor Costan · 2 years, 10 months ago
- 4ebd8b2 Split benchmarks and test tools into separate targets. by Victor Costan · 2 years, 10 months ago
- 0793e2a Merge pull request #117 from cmumford:disable-osx-fuzzer by Victor Costan · 2 years, 10 months ago
- ac55f84 Test stub improvements. by Victor Costan · 2 years, 10 months ago
- 6e9ae72 Disable fuzzing on OSX. by Chris Mumford · 2 years, 10 months ago
- 402d888 Fixup for adding the third_party/{benchmark, googletest} submodules. (#115) by Victor Costan · 2 years, 10 months ago
- 6badb0a Merge pull request #114 from cmumford:werror-only-clang by Victor Costan · 2 years, 10 months ago
- bc53daa Fixed endif clause. by Chris Mumford · 2 years, 10 months ago
- e9a6a08 Matching clang. by Chris Mumford · 2 years, 10 months ago
- 955a5dd Building with `-Werror` only with clang. by Chris Mumford · 2 years, 10 months ago
- 42d1dd7 Fix CHECK_EQ to call ok() instead of CheckSuccess(). by Chris Mumford · 2 years, 10 months ago
- eaaa0ed Fixup for adding the third_party/{benchmark, googletest} submodules. (#111) by Victor Costan · 2 years, 10 months ago
- e1e91ee Rework file:: stubs. by Victor Costan · 2 years, 10 months ago
- 6aa79cb Wrap snappy_unittest in an anonymous namespace and remove static from functions. by Victor Costan · 2 years, 10 months ago
- bae9f9b Fixup for adding the third_party/{benchmark, googletest} submodules. (#110) by Victor Costan · 2 years, 10 months ago
- 5f913be Fix unused local variable warnings. by Victor Costan · 2 years, 10 months ago
- 549685a Remove custom testing and benchmarking code. by Victor Costan · 2 years, 10 months ago
- 11f9a77 Add Travis-CI build status badge to README.md. by Chris Mumford · 2 years, 10 months ago
- 4954096 Update Travis CI config. by Victor Costan · 2 years, 10 months ago
- 8995ffa Replace #pragma nounroll with equivalent used elsewhere. by Victor Costan · 2 years, 10 months ago
- d1daa83 Remove inline qualifier from static variables. by Victor Costan · 2 years, 10 months ago
- 3b57165 1) Improve the lookup table data to require less instructions to extract the necessary data. We now store len - offset in a signed int16, this happens to remove masking offset in the calculations and the calculations that need to be done precisely give the flags that we need for testing correctness. by Snappy Team · 2 years, 10 months ago
- a9730ed Optimize zippy decompression by making IncrementalCopy faster. by Shahriar Rouf · 2 years, 10 months ago
- 56c2c24 Internal change by Snappy Team · 2 years, 10 months ago
- a94be58 Optimize zippy decompression by making IncrementalCopy faster. by Shahriar Rouf · 2 years, 10 months ago
- 01a566f Fix opensource version by Snappy Team · 2 years, 11 months ago
- 616b822 Add LZ4 as a benchmark option. Snappy is starting to look really good compared to LZ4. LZ4 is considered the fastest solution by many on internet. We now see that Snappy is actually becoming very competitive with compression a little faster and decompression slower but certainly not terribly slower. by Snappy Team · 2 years, 11 months ago
- e4a6e97 Extend validate benchmarks over all types and also add a medley for validation. by Snappy Team · 2 years, 11 months ago
- 719bed0 Bug fix. Error on 0 offset copies. by Snappy Team · 2 years, 11 months ago
- 289c8a3 Make zippy decompression branchless by Snappy Team · 2 years, 11 months ago
- 3bfa265 Revert zippy optimization that causes heap buffer overflows. by Snappy Team · 2 years, 11 months ago
- 4d2dc9d Optimize zippy unzipping by upto >10% by making IncrementalCopy faster. by Shahriar Rouf · 2 years, 11 months ago
- 11e5165 Add a benchmark that decreased the branch prediction memorization by increasing the amount of independent branches executed per benchmark iteration. by Snappy Team · 2 years, 11 months ago
- 6835abd Change hash function for Compress. by Luca Versari · 2 years, 11 months ago
- 368b01c Merge pull request #107 from jsteemann:bug-fix/fix-compile-warning by Victor Costan · 2 years, 11 months ago
- 1ce58af Fix the use of op + len when op is nullptr and len is non-zero. by Snappy Team · 2 years, 11 months ago
- 0b990db Run clang-format by Luca Versari · 2 years, 11 months ago
- cb2b3c7 fix compile warnings due to missing override specifiers by jsteemann · 3 years ago
- 7ffaf77 Replace ARCH_K8 with __x86_64__. by Chris Kennelly · 3 years ago
- 4dd277f Replace the division with a constant table in IncrementalCopy by Snappy Team · 3 years, 3 months ago
- f16eda3 Correct uninitialized variable. by Snappy Team · 3 years, 4 months ago
- 837f38b Revise stubs for ARCH_{K8,PPC,ARM}. by Victor Costan · 3 years, 5 months ago
