A computer language based on Brainfuck.
- About
- Documentation
- Current Status
- How to build Brain
- How it has been built
- Technical Information
- Compiler Options
- Applications for real life
- Help the Project
- License
Brain wants to improve the performance of the Brainfuck programming language and extend it as well, as Brainfuck itself has a lack of flexibility and does not perform great control over complex computations. Brain is open to new model represetantion and allows programmers to extend its capability by attaching LLVM IR to its code.
One of the main ideas of Brain is saving some operations in machine language, creating an instruction optmizer due to the excess of instructions that Brainfuck would generate. Brain aims to implement it by using current technology (LLVM).
In spite of implementing new commands and features, Brain is completely compatible with Brainfuck (but the opposite is not true).
yaourt -S brain
docker pull luizperes/brain:1.0
docker run -it luizperes/brain:1.0
You can check this repository documentation on https://brain-labs.github.io/brain/docs/html/index.html
Brain is stable on its tag version 1.0
Obs.: To use Project Status (the "Kanban" below), please visit:https://github.com/luizperes/status-projects/blob/master/README.md and http://luizperes.github.io/status-projects/
| Project Name | Status | Technology | Priority | Deadline |
|---|---|---|---|---|
| Brain 1.0 | C/C++/LLVM | Low | ||
| Brain 1.1 | C/C++/LLVM | Low |
| To Do | In Progress | Done |
|---|---|---|
If you want to check the micro TODO list, please see this issue.
Brain runs on the top of LLVM, thus, you are required to install the lastest versions of LLVM. You can do that by following this http://llvm.org/releases/download.html
This project uses pre-commit to help us to check our commits in order to minimize bugs and other problems on the project, therefore is strongly recommended that you use it, if you are intending to contribute to the project. For that, you can install by:
if you have pip installed:
Mac
brew install pre-commit
Linux
sudo pip install pre-commit
After that, go to where Brain lives:
$ cd /path/to/brain
$ pre-commit install
More information about that here
To build it, after installing LLVM, execute:
$ cd /path/to/brain/src
$ make
$ make install
Brain will try to run on clang and clang++ automatically. However you can change your CC with the commands:
make build-3.8ormake build-3.9for LLVM 3.8 and 3.9make CC=clang++-3.7 LLVM_CONFIG=clang++-3.7for older versions (3.7 in this case)
And you can do the same for installing it and running tests:
make install C=clang-3.7make tests C=clang-3.7
After running make and make install on it, you can execute:./brain your_brain_file.b. Please check the current status of the project.
Brain is based on previous work https://github.com/luizperes/BrainfuckInterpreter and https://github.com/Lisapple/BF-Compiler-Tutorial-with-LLVM, now trying to make something more serious: Turing Complete, faster, more features/commands and different types.
Brain is now a Turing Complete language. You can now extend the tape size by using the flag --size=<tape size>.
Implemented
>increment the data pointer (to point to the next cell to the righ.<decrement the data pointer (to point to the next cell to the left).+increment (increase by one) the value at the data pointer.-decrement (decrease by one) the value at the data pointer..output the value at the data pointer.,accept one value of input, storing its value in the value at the data pointer.[if the value at the data pointer is zero, then instead of moving the instruction pointer forward to the next command, jump it forward to the command after the matching ] command.]jump to its correspondent [ .*multiply*ptrwith*(ptr-1). Store result in *ptr // format: 2 3 */divide*ptrwith*(ptr-1). Store the result in *ptr // format: 2 3 /%divide*ptrwith*(ptr-1). Store the remainder in *ptr // format: 2 3 %#prints out the current debug information.{(for loop) iterates'value-at-the-data-pointer' timesand needs to be closed with a matching } command. It does not decrease thevalueat the data pointer. It will only work for positive values.}jump to its correspondent { .!(break) jumps to the end of a loop ([ ] or { })?if the value at the data pointer iszero, jumps to the block with:or;and executes the commands one by one up to its correlative;, otherwise, it executes the code until it finds a:or;.:it works as anotherwise(orelse) for?.;ends a statement.$prints out the value at the data pointer divided by 100.^move the data pointer (jump) on the tape. Ex.: ++++++++++^ // the data pointer will jump to cell 10.&stores the value of*(ptr-1)in the*ptr-th cell // format: 10 500 & (stores 10 at cell number 500.)
Not Implemented
@calls a function according to the value at the data pointer.
Example of the instructions above:
- if-then:
? +++ ;// if (*ptr) { *ptr += 3; } - if-else:
? +++ : --- ;// if (*ptr) { *ptr += 3; } else { *ptr -= 3; } - for:
++++ { commands }// makes four iterations 4 through 0 (excluded) - float numbers:
++>+********$cell 0[2]cell 1[256]// '$' prints out 256 / 100 - break loop:
+[+++++!]// *ptr = 1; while(*ptr) { *ptr += 5; break; }
--code=<"inline code">Sets inline brain code--io=replSets the IO module to REPLs style--out=<filename>Sets the output filename--size=<number>Sets the number of cells used by the interpreter--size-cell=<number>Sets the cell width (8,16,32,64bits) of each cell--versionShows the current version of Brain-emit-llvmEmits LLVM IR code for the given input-emit-astEmits the AST for the given input-emit-codeEmits an optimized code for the given input-cGenerates object file-SGenerates assembly file-vUses verbose mode for the output-O0Generates output code with no optmizations-O1Optimizes Brain generated output code (Default)
- Artificial Intelligence/ Machine Learning
- Send commands to Arduino
- Easy support to primitive processors
Feel free to send your pull requests. :)
This project extends GNU GPL v. 3, so be aware of that, regarding copying, modifying and (re)destributing.