Adding README's to HPVM directories

hpvm/README.md

+## HPVM Repository Structure
+
+The current directory consists of the following sub-directories and files:
+
+ - `benchmarks`  : This directory contains the benchmarks for the HPVM compiler infrastructure.
+ - `cmake`: Contains `cmake` related files which define additional variables needed to build `HPVM`.
+ - `docs`:  Contains the documentation for `HPVM` and its various sub-projects. We use `Sphinx` for generating the reference documentation. A deployed version of the documentation can be found at https://hpvm.readthedocs.io/en/latest/.
+ - `include`: This directory contains the C++ headers for the `HPVM`  compiler infrastructure.
+ - `lib`: This directory contains the C++ source files for the `HPVM` compiler infrastructure.
+ - `llvm_patches`: This directory contains the modified `LLVM` source files as well as a script to patch the corresponding source files in the `LLVM` source tree to enable building `HPVM`.
+ - `projects`: This directory contains the various sub-projects within `HPVM` which make use of the core `HPVM` infrastructure.
+ - `scripts`: Contains the script to build and install `HPVM` , and other utilities.
+ - `test`: Contains the automated `llvm-lit` tests for the various transformation passes in `HPVM`.
+ - `tools`: This directory contains the definition of various user-facing tools in `HPVM`.
+ - `env.yaml`: Defines the `Python` dependencies needed to support the `HPVM` Tensor Extensions.
+ - `install.sh`: Entry point script to build and install `HPVM`.
+ - `set_paths.sh`: Defines the various environment variables needed to build `HPVM` as well as it's sub-projects.
+ - `setup_environment.sh`: The script sets up the environment to use the `HPVM2FPGA` tool on Intel VLAB.

hpvm/include/README.md

+## HPVM Include
+
+This directory contains the C++ header files for the `HPVM`infrastruture. This are divided into the following categories:
+
+- `CoreHPVM`: Consists of the common Code Generation files used by the `HPVM` backend targets. Additionally, it defines various utilities which can be used within the specific target backend passes.
+- `IRCodeGen`: Defines the transformation passes which generate the `HPVM` IR and Dataflow graph representation from `LLVM` bitcode files written using `HPVM-C`.
+- `SupportHPVM`: Provides various utilities needed by the various `HPVM` transformation passes including a `DFG` Tree Traversal class.
+- `Transforms`: Defines the transformation passes which perform either DFG to DFG transformations, or transformations on `LLVM-IR`.

hpvm/lib/README.md

+## HPVM Lib
+
+This directory contains the C++ source files for the `HPVM`infrastruture. This are divided into the following categories:
+
+- `CoreHPVM`: Consists of the common Code Generation files used by the `HPVM` backend targets. Additionally, it defines various utilities which can be used within the specific target backend passes.
+- `IRCodeGen`: Defines the transformation passes which generate the `HPVM` IR and Dataflow graph representation from `LLVM` bitcode files written using `HPVM-C`.
+- `Targets`: Contains the instances of the specific backend targets `HPVM` compiles to.
+- `Transforms`: Defines the transformation passes which perform either DFG to DFG transformations, or transformations on `LLVM-IR`.

hpvm/projects/README.md

+## HPVM Projects
+
+This directory contains the subdirectories for `HPVM` sub-projects which are built on top the the `HPVM` compiler infrastructure. They consist of:
+
+- `hetero-c++`: A high level parallel dialect of C/C++ which describes hierarchical Task-level and Data-level parallelism. It compiles through `HPVM` to target `CPU`, `GPU` and the `FPGA`.
+- `hpvm-profiler`: Defines the python package for profiling `HPVM` approximation configurations for the `HPVM` Tensor Extensions.
+- `hpvm-rt`: Defines the `HPVM` runtime which manages the execution of `HPVM` programs on heterogeneous compute devices.
+- `keras`: Defines the `keras` frontend for `HPVM` Tensor Extensions which compiles neural network models through `HPVM`.
+- `llvm-ocl`: Tool to generate the `OpenCL` kernel file from `LLVM` bitcode. This is used by the `GPU` and `FPGA` benchmarks.
+- `torch2hpvm`: Defines the `onnx` frontend for `HPVM` Tensor Extensions which compiles `PyTorch` nearal network models through `HPVM`.