for it. Many of our benchmarks are microbenchmarks. We are effectively doing controlled scientific experiments for the purpose of understanding what affects our performance. So we simplify as much as possible. We try to avoid irrelevant factors such as page faults, interrupts, unnnecessary system calls. We recommend checking the performance as follows:
The last line becomes `./benchmark/Release/bench_parse_call.exe` under Windows. Under Windows, you can also build with the clang compiler by adding `-T ClangCL` to the call to `cmake ..`: `cmake .. - TClangCL`.
A key feature of simdjson is the ability to compile different processing kernels, optimized for specific instruction sets, and to select
the most appropriate kernel at runtime. This ensures that users get the very best performance while still enabling simdjson to run everywhere.
This technique is frequently called runtime dispatching. The simdjson achieves runtime dispatching entirely in C++: we do not assume
that the user is building the code using CMake, for example.
To make runtime dispatching work, it is critical that the code be compiled for the lowest supported processor. In particular, you should
not use flags such as -mavx2, /arch:AVX2 and so forth while compiling simdjson. When you do so, you allow the compiler to use advanced
instructions. In turn, these advanced instructions present in the code may cause a runtime failure if the runtime processor does not
support them. Even a simple loop, compiled with these flags, might generate binary code that only run on advanced processors.
So we compile simdjson for a generic processor. Our users should do the same if they want simdjson's runtime dispatch to work. It is important
to understand that if runtime dispatching does not work, then simdjson will cause crashes on older processors. Of course, if a user chooses
to compile their code for a specific instruction set (e.g., AVX2), they are responsible for the failures if they later run their code
on a processor that does not support AVX2. Yet, if we were to entice these users to do so, we would share the blame: thus we carefully instruct
users to compile their code in a generic way without doing anything to enable advanced instructions.
We only use runtime dispatching on x64 (AMD/Intel) platforms, at the moment. On ARM processors, we would need a standard way to query, at runtime,
the processor for its supported features. We do not know how to do so on ARM systems in general. Thankfully it is not yet a concern: 64-bit ARM
processors are fairly uniform as far as the instruction sets they support.
In all cases, simdjson uses advanced instructions by relying on "intrinsic functions": we do not write assembly code. The intrinsic functions
are special functions that the compiler might recognize and translate into fast code. To make runtime dispatching work, we rely on the fact that
the header providing these instructions
(intrin.h under Visual Studio, x86intrin.h elsewhere) defines all of the intrinsic functions, including those that are not supported
processor.
At this point, we are require to use one of two main strategies.
1. On POSIX systems, the main compilers (LLVM clang, GNU gcc) allow us to use any intrinsic function after including the header, but they fail to inline the resulting instruction if the target processor does not support them. Because we compile for a generic processor, we would not be able to use most intrinsic functions. Thankfully, more recent versions of these compilers allow us to flag a region of code with a specific target, so that we can compile only some of the code with support for advanced instructions. Thus in our C++, one might notice macros like `TARGET_HASWELL`. It is then our responsability, at runtime, to only run the regions of code (that we call kernels) matching the properties of the runtime processor. The benefit of this approach is that the compiler not only let us use intrinsic functions, but it can also optimize the rest of the code in the kernel with advanced instructions we enabled.
2. Under Visual Studio, the problem is somewhat simpler. Visual Studio will not only provide the intrinsic functions, but it will also allow us to use them. They will compile just fine. It is at runtime that they may cause a crash. So we do not need to mark regions of code for compilation toward advanced processors (e.g., with `TARGET_HASWELL` macros). The downside of the Visual Studio approach is that the compiler is not allowed to use advanced instructions others than those we specify. In principle, this means that Visual Studio has weaker optimization opportunities.
We also handle the special case where a user is compiling using LLVM clang under Windows, [using the Visual Studio toolchain](https://devblogs.microsoft.com/cppblog/clang-llvm-support-in-visual-studio/). If you compile with LLVM clang under Visual Studio, then the header files (intrin.h or x86intrin.h) no longer provides the intrinsic functions that are unsupported by the processor. This appears to be deliberate on the part of the LLVM engineers. With a few lines of code, we handle this scenario just like LLVM clang under a POSIX system, but forcing the inclusion of the specific headers, and rolling our own intrinsic function as needed.
In some cases, you may want to specify your compiler, especially if the default compiler on your system is too old. You need to tell cmake which compiler you wish to use by setting the CC and CXX variables. Under bash, you can do so with commands such as `export CC=gcc-7` and `export CXX=g++-7`. You can also do it as part of the `cmake` command: `cmake .. -DCMAKE_CXX_COMPILER=g++`. You may proceed as follows:
If your compiler does not default on C++11 support or better you may get failing tests. If so, you may be able to exclude the failing tests by replacing `ctest` with `ctest -E "^quickstart$"`.
Note that the name of directory (`build`) is arbitrary, you can name it as you want (e.g., `buildgcc`) and you can have as many different such directories as you would like (one per configuration).
### Usage (CMake on 64-bit Windows using Visual Studio)
We assume you have a common 64-bit Windows PC with at least Visual Studio 2017 and an x64 processor with AVX2 support (2013 Intel Haswell or later) or SSE 4.2 + CLMUL (2010 Westmere or later).
- Grab the simdjson code from GitHub, e.g., by cloning it using [GitHub Desktop](https://desktop.github.com/).
- Install [CMake](https://cmake.org/download/). When you install it, make sure to ask that `cmake` be made available from the command line. Please choose a recent version of cmake.
- Type `cmake -DCMAKE_GENERATOR_PLATFORM=x64 ..` in the shell while in the `build` repository. (Alternatively, if you want to build a DLL, you may use the command line `cmake -DCMAKE_GENERATOR_PLATFORM=x64 -DSIMDJSON_BUILD_STATIC=OFF ..`.)
- This last command (`cmake ...`) created a Visual Studio solution file in the newly created directory (e.g., `simdjson.sln`). Open this file in Visual Studio. You should now be able to build the project and run the tests. For example, in the `Solution Explorer` window (available from the `View` menu), right-click `ALL_BUILD` and select `Build`. To test the code, still in the `Solution Explorer` window, select `RUN_TESTS` and select `Build`.
Though having Visual Studio installed is necessary, one can build simdjson using only cmake commands:
-`mkdir build`
-`cd build`
-`cmake ..`
-`cmake --build . -config Release`
Furthermore, if you have installed LLVM clang on Windows, for example as a component of Visual Studio 2019, you can configure and build simdjson using LLVM clang on Windows using cmake:
### Usage (Using `vcpkg` on 64-bit Windows, Linux and macOS)
[vcpkg](https://github.com/Microsoft/vcpkg) users on Windows, Linux and macOS can download and install `simdjson` with one single command from their favorite shell.
On 64-bit Linux and macOS:
```
$ ./vcpkg install simdjson
```
will build and install `simdjson` as a static library.
On Windows (64-bit):
```
.\vcpkg.exe install simdjson:x64-windows
```
will build and install `simdjson` as a shared library.
- 64-bit platforms like Linux or macOS, as well as Windows through Visual Studio 2017 or later.
- Any 64-bit processor:
- AVX2 (i.e., Intel processors starting with the Haswell microarchitecture released 2013 and AMD
processors starting with the Zen microarchitecture released 2017),
- SSE 4.2 and CLMUL (i.e., Intel processors going back to Westmere released in 2010 or AMD
processors starting with the Jaguar used in the PS4 and XBox One),
- 64-bit ARM processor (ARMv8-A NEON): this covers a wide range of mobile processors, including
all Apple processors currently available for sale, going as far back as the iPhone 5s (2013).
- Any 64-bit processor (simdjson has a fallback generic 64-bit implementation that is still super
fast).
- A recent C++ compiler (e.g., GNU GCC or LLVM CLANG or Visual Studio 2017), we assume C++17. GNU
GCC 7 or better or LLVM's clang 6 or better.
- Some benchmark scripts assume bash and other common utilities, but they are optional.
### Scope
We provide a fast parser, that fully validates an input according to various specifications.
The parser builds a useful immutable (read-only) DOM (document-object model) which can be later accessed.
To simplify the engineering, we make some assumptions.
- We support UTF-8 (and thus ASCII), nothing else (no Latin, no UTF-16). We do not believe this is a
genuine limitation, because we do not think there is any serious application that needs to process
JSON data without an ASCII or UTF-8 encoding. If the UTF-8 contains a leading BOM, it should be
omitted: the user is responsible for detecting and skipping the BOM; UTF-8 BOMs are discouraged.
- All strings in the JSON document may have up to 4294967295 bytes in UTF-8 (4GB). To enforce this
constraint, we refuse to parse a document that contains more than 4294967295 bytes (4GB). This
should accommodate most JSON documents.
- As allowed by the specification, we allow repeated keys within an object (other parsers like
sajson do the same).
- [The simdjson library is fast for JSON documents spanning a few bytes up to many megabytes](https://github.com/lemire/simdjson/issues/312).
_We do not aim to provide a general-purpose JSON library._ A library like RapidJSON offers much more
than just parsing, it helps you generate JSON and offers various other convenient functions. We
merely parse the document. This may change in the future.
### Features
- The input string is unmodified. (Parsers like sajson and RapidJSON use the input string as a buffer.)
- We parse integers and floating-point numbers as separate types which allows us to support large signed 64-bit integers in [-9223372036854775808,9223372036854775808), like a Java `long` or a C/C++ `long long` and large unsigned integers up to the value 18446744073709551615. Among the parsers that differentiate between integers and floating-point numbers, not all support 64-bit integers. (For example, sajson rejects JSON files with integers larger than or equal to 2147483648. RapidJSON will parse a file containing an overly long integer like 18446744073709551616 as a floating-point number.) When we cannot represent exactly an integer as a signed or unsigned 64-bit value, we reject the JSON document.
- We support the full range of 64-bit floating-point numbers (binary64). The values range from ` std::numeric_limits<double>::lowest()` to `std::numeric_limits<double>::max()`, so from -1.7976e308 all the way to 1.7975e308. Extreme values (less or equal to -1e308, greater or equal to 1e308) are rejected: we refuse to parse the input document.
- We test for accurate float parsing with a perfect accuracy (ULP 0). Many parsers offer only approximate floating parsing. For example, RapidJSON also offers the option of accurate float parsing (`kParseFullPrecisionFlag`) but it comes at a significant performance penalty compared to the default settings. By default, RapidJSON tolerates an error of 3 ULP.
- We do full UTF-8 validation as part of the parsing. (Parsers like fastjson, gason and dropbox json11 do not do UTF-8 validation. The sajson parser does incomplete UTF-8 validation, accepting code point
sequences like 0xb1 0x87.)
- We fully validate the numbers. (Parsers like gason and ultranjson will accept `[0e+]` as valid JSON.)
- We validate string content for unescaped characters. (Parsers like fastjson and ultrajson accept unescaped line breaks and tabs in strings.)
- We fully validate the white-space characters outside of the strings. Parsers like RapidJSON will accept JSON documents with null characters outside of strings.
### Architecture
The parser works in two stages:
- Stage 1. (Find marks) Identifies quickly structure elements, strings, and so forth. We validate UTF-8 encoding at that stage.
- Stage 2. (Structure building) Involves constructing a "tree" of sort (materialized as a tape) to navigate through the data. Strings and numbers are parsed at this stage.
### Remarks on JSON parsing
- The JSON spec defines what a JSON parser is:
> A JSON parser transforms a JSON text into another representation. A JSON parser MUST accept all texts that conform to the JSON grammar. A JSON parser MAY accept non-JSON forms or extensions. An implementation may set limits on the size of texts that it accepts. An implementation may set limits on the maximum depth of nesting. An implementation may set limits on the range and precision of numbers. An implementation may set limits on the length and character contents of strings.
* JSON is not JavaScript:
> All JSON is Javascript but NOT all Javascript is JSON. So {property:1} is invalid because property does not have double quotes around it. {'property':1} is also invalid, because it's single quoted while the only thing that can placate the JSON specification is double quoting. JSON is even fussy enough that {"property":.1} is invalid too, because you should have of course written {"property":0.1}. Also, don't even think about having comments or semicolons, you guessed it: they're invalid. (credit:https://github.com/elzr/vim-json)
* The structural characters are:
begin-array = [ left square bracket
begin-object = { left curly bracket
end-array = ] right square bracket
end-object = } right curly bracket
name-separator = : colon
value-separator = , comma
### Pseudo-structural elements
A character is pseudo-structural if and only if:
1. Not enclosed in quotes, AND
2. Is a non-whitespace character, AND
3. Its preceding character is either:
(a) a structural character, OR
(b) whitespace.
This helps as we redefine some new characters as pseudo-structural such as the characters 1, G, n in the following:
> { "foo" : 1.5, "bar" : 1.5 GEOFF_IS_A_DUMMY bla bla , "baz", null }
The simdjson library relies on the lookup2 algorithm for UTF-8 validation on x64 platforms.
This algorithm validate the length of multibyte characters (that each multibyte character has the right number of continuation characters, and that all continuation characters are part of a multibyte character).
#### Algorithm
This algorithm compares *expected* continuation characters with *actual* continuation bytes, and emits an error anytime there is a mismatch.
For example, in the string "𝄞₿֏ab", which has a 4-, 3-, 2- and 1-byte
- [SimdJsonSharp](https://github.com/EgorBo/SimdJsonSharp): C# version for .NET Core (bindings and full port).
- [simdjson_nodejs](https://github.com/luizperes/simdjson_nodejs): Node.js bindings for the simdjson project.
- [simdjson_php](https://github.com/crazyxman/simdjson_php): PHP bindings for the simdjson project.
- [simdjson_ruby](https://github.com/saka1/simdjson_ruby): Ruby bindings for the simdjson project.
- [simdjson-go](https://github.com/minio/simdjson-go): Go port using Golang assembly.
- [rcppsimdjson](https://github.com/eddelbuettel/rcppsimdjson): R bindings.
### Tools
-`json2json mydoc.json` parses the document, constructs a model and then dumps back the result to standard output.
-`json2json -d mydoc.json` parses the document, constructs a model and then dumps model (as a tape) to standard output. The tape format is described in the accompanying file `tape.md`.
-`minify mydoc.json` minifies the JSON document, outputting the result to standard output. Minifying means to remove the unneeded white space characters.
-`jsonpointer mydoc.json <jsonpath> <jsonpath> ... <jsonpath>` parses the document, constructs a model and then processes a series of [JSON Pointer paths](https://tools.ietf.org/html/rfc6901). The result is itself a JSON document.
- Lu, Yifan, et al. "Tree structured data processing on GPUs." Cloud Computing, Data Science & Engineering-Confluence, 2017 7th International Conference on. IEEE, 2017.
- Sidhu, Reetinder. "High throughput, tree automata based XML processing using FPGAs." Field-Programmable Technology (FPT), 2013 International Conference on. IEEE, 2013.
- Dai, Zefu, Nick Ni, and Jianwen Zhu. "A 1 cycle-per-byte XML parsing accelerator." Proceedings of the 18th annual ACM/SIGDA international symposium on Field programmable gate arrays. ACM, 2010.
- Lin, Dan, et al. "Parabix: Boosting the efficiency of text processing on commodity processors." High Performance Computer Architecture (HPCA), 2012 IEEE 18th International Symposium on. IEEE, 2012. http://parabix.costar.sfu.ca/export/1783/docs/HPCA2012/final_ieee/final.pdf
- Deshmukh, V. M., and G. R. Bamnote. "An empirical evaluation of optimization parameters in XML parsing for performance enhancement." Computer, Communication and Control (IC4), 2015 International Conference on. IEEE, 2015.
- Moussalli, Roger, et al. "Efficient XML Path Filtering Using GPUs." ADMS@ VLDB. 2011.
- Jianliang, Ma, et al. "Parallel speculative dom-based XML parser." High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), 2012 IEEE 14th International Conference on. IEEE, 2012.
- Li, Y., Katsipoulakis, N.R., Chandramouli, B., Goldstein, J. and Kossmann, D., 2017. Mison: a fast JSON parser for data analytics. Proceedings of the VLDB Endowment, 10(10), pp.1118-1129. http://www.vldb.org/pvldb/vol10/p1118-li.pdf
- Cameron, Robert D., et al. "Parallel scanning with bitstream addition: An xml case study." European Conference on Parallel Processing. Springer, Berlin, Heidelberg, 2011.
- Cameron, Robert D., Kenneth S. Herdy, and Dan Lin. "High performance XML parsing using parallel bit stream technology." Proceedings of the 2008 conference of the center for advanced studies on collaborative research: meeting of minds. ACM, 2008.
- Shah, Bhavik, et al. "A data parallel algorithm for XML DOM parsing." International XML Database Symposium. Springer, Berlin, Heidelberg, 2009.
- Cameron, Robert D., and Dan Lin. "Architectural support for SWAR text processing with parallel bit streams: the inductive doubling principle." ACM Sigplan Notices. Vol. 44. No. 3. ACM, 2009.
- Amagasa, Toshiyuki, Mana Seino, and Hiroyuki Kitagawa. "Energy-Efficient XML Stream Processing through Element-Skipping Parsing." Database and Expert Systems Applications (DEXA), 2013 24th International Workshop on. IEEE, 2013.
- Medforth, Nigel Woodland. "icXML: Accelerating Xerces-C 3.1. 1 using the Parabix Framework." (2013).
- Zhang, Qiang Scott. Embedding Parallel Bit Stream Technology Into Expat. Diss. Simon Fraser University, 2010.
- Cameron, Robert D., et al. "Fast Regular Expression Matching with Bit-parallel Data Streams."
- Lin, Dan. Bits filter: a high-performance multiple string pattern matching algorithm for malware detection. Diss. School of Computing Science-Simon Fraser University, 2010.
- Yang, Shiyang. Validation of XML Document Based on Parallel Bit Stream Technology. Diss. Applied Sciences: School of Computing Science, 2013.
- N. Nakasato, "Implementation of a parallel tree method on a GPU", Journal of Computational Science, vol. 3, no. 3, pp. 132-141, 2012.
