### Run TornadoVM Examples and Benchmarks

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Commands to execute example applications and benchmarks.

```bash
$ tornado -m tornado.examples/uk.ac.manchester.tornado.examples.compute.MatrixMultiplication2D 1024
```

```bash
$ tornado -m tornado.benchmarks/uk.ac.manchester.tornado.benchmarks.BenchmarkRunner dft
```

--------------------------------

### Verify TornadoVM Installation

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Check available devices, run unit tests, or execute specific examples to confirm the installation.

```bash
# list the accelerator devices that are reachable from TornadoVM
tornado --devices

# run unit tests
tornado-test -V

## run specific examples (e.g., NBody)
tornado -m tornado.examples/uk.ac.manchester.tornado.examples.compute.NBody
```

--------------------------------

### Example Windows Path Directories

Source: https://tornadovm.readthedocs.io/en/latest/_sources/ide-integration.rst.txt

Example paths for CMake and the Python virtual environment on Windows.

```bash
C:\Program Files\Microsoft Visual Studio\2022\Community\Common7\IDE\CommonExtensions\Microsoft\CMake\CMake\bin\
```

```bash
<path-to-TornadoVM-directory>\.venv\Scripts
```

--------------------------------

### Install Documentation Dependencies

Source: https://tornadovm.readthedocs.io/en/latest/_sources/build-documentation.rst.txt

Install required Sphinx themes and extensions.

```bash
pip3 install sphinx_rtd_theme
pip3 install sphinxcontrib-jquery
```

--------------------------------

### Display TornadoVM Installer Help

Source: https://tornadovm.readthedocs.io/en/latest/installation.html

View available command-line options for the installer script.

```bash
$ ./bin/tornadovm-installer --help
  usage: tornadovm-installer [-h] [--jdk JDK] [--backend BACKEND] [--version] [--listJDKs] [--polyglot] [--mvn_single_threaded] [--auto-deps]

  TornadoVM Installer Tool. It will install all software dependencies except the GPU/FPGA drivers

  options:
    -h, --help            show this help message and exit
    --jdk JDK             Specify a JDK to install by its keyword (e.g., 'jdk21', 'graal-jdk-21'). Run with --listJDKs to view all available JDK keywords.
    --backend BACKEND     Select the backend to install: { opencl, ptx, spirv }
    --version             Print version
    --listJDKs            List supported JDKs
    --polyglot            Enable Truffle Interoperability with GraalVM
    --mvn_single_threaded
                          Run Maven in single-threaded mode
    --auto-deps           Automatic download and use any missing dependencies
```

--------------------------------

### Run TornadoVM Examples

Source: https://tornadovm.readthedocs.io/en/latest/installation.html

Command to run a specific TornadoVM example.

```bash
$ tornado -m tornado.examples/uk.ac.manchester.tornado.examples.compute.MatrixMultiplication2D 1024
```

--------------------------------

### Verify TornadoVM Installation

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Initialize the environment and list available devices to confirm successful installation.

```bash
source setvars.sh
tornado --devices
```

--------------------------------

### Install and Initialize Pre-commit Hooks

Source: https://tornadovm.readthedocs.io/en/latest/_sources/developer-guidelines.rst.txt

Install the pre-commit framework and initialize the hooks in the repository to automate style checks.

```bash
pip install pre-commit
pre-commit install
```

--------------------------------

### Display TornadoVM installer help

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Run this command to view available options and flags for the automated installation script.

```bash
$ ./bin/tornadovm-installer --help
  usage: tornadovm-installer [-h] [--jdk JDK] [--backend BACKEND] [--version] [--listJDKs] [--polyglot] [--mvn_single_threaded] [--auto-deps]

  TornadoVM Installer Tool. It will install all software dependencies except the GPU/FPGA drivers
```

--------------------------------

### Install Intel Compute Runtime Packages

Source: https://tornadovm.readthedocs.io/en/latest/installation.html

Command to install the downloaded .deb packages.

```bash
sudo dpkg -i *.deb
```

--------------------------------

### Install Sphinx

Source: https://tornadovm.readthedocs.io/en/latest/_sources/build-documentation.rst.txt

Install the Sphinx documentation generator using pip.

```bash
pip3 install -U sphinx
```

--------------------------------

### Install WSL

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Install the Windows Subsystem for Linux using PowerShell.

```bash
## By default, Windows 11 installs Ubuntu 24.04 LTS, as in Jan 2025
wsl --install
```

--------------------------------

### Install Intel Compute Runtime

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Download and install Intel OpenCL and Level Zero drivers for WSL.

```bash
mkdir -p ~/bin/neo
cd ~/bin/neo
wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.2.3/intel-igc-core-2_2.2.3+18220_amd64.deb
wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.2.3/intel-igc-opencl-2_2.2.3+18220_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.48.31907.7/intel-level-zero-gpu-dbgsym_1.6.31907.7_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/24.48.31907.7/intel-level-zero-gpu_1.6.31907.7_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.48.31907.7/intel-opencl-icd-dbgsym_24.48.31907.7_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/24.48.31907.7/intel-opencl-icd_24.48.31907.7_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.48.31907.7/libigdgmm12_22.5.4_amd64.deb
```

--------------------------------

### Run Matrix Multiplication Example

Source: https://tornadovm.readthedocs.io/en/latest/_sources/simple-start.rst.txt

Executes the MatrixMultiplication1D example on a specific device using the tornado command.

```bash
$ tornado --jvm="-Ds0.t0.device=1:1" -m tornado.examples/uk.ac.manchester.tornado.examples.compute.MatrixMultiplication1D
```

--------------------------------

### FPGA Configuration File Example

Source: https://tornadovm.readthedocs.io/en/latest/_sources/cloud.rst.txt

Example content for an AWS FPGA configuration file defining device paths, compiler flags, and S3 storage settings.

```ini
[device]
DEVICE_NAME = /home/centos/src/project_data/aws-fpga/Vitis/aws_platform/xilinx_aws-vu9p-f1_shell-v04261818_201920_3/xilinx_aws-vu9p-f1_shell-v04261818_201920_3.xpfm
[options]
COMPILER=v++
FLAGS = -O3 -j12 # Configure the compilation flags. You can also pass the HLS configuration file (e.g. --config conf.cfg).
DIRECTORY_BITSTREAM = fpga-source-comp/
# If the FPGA is in AWS EC2 F1 Instance
AWS_ENV = yes
[AWS S3 configuration]
AWS_S3_BUCKET = tornadovm-fpga-bucket
AWS_S3_DCP_KEY = outputfolder
AWS_S3_LOGS_KEY = logfolder
```

--------------------------------

### Execute Polyglot Examples

Source: https://tornadovm.readthedocs.io/en/latest/_sources/truffle-languages.rst.txt

Run the provided TornadoVM examples to demonstrate interoperability with Python, JavaScript, and Ruby.

```bash
$ tornado --debug -m tornado.examples/uk.ac.manchester.tornado.examples.polyglot.HelloPython
$ tornado --debug -m tornado.examples/uk.ac.manchester.tornado.examples.polyglot.HelloJS
$ tornado --debug -m tornado.examples/uk.ac.manchester.tornado.examples.polyglot.HelloRuby
```

--------------------------------

### Install TornadoVM

Source: https://tornadovm.readthedocs.io/en/latest/_sources/cloud.rst.txt

Clone the TornadoVM repository and run the installer as a CentOS user.

```bash
$ git clone https://github.com/beehive-lab/TornadoVM.git
$ cd TornadoVM
$ ./bin/tornadovm-installer
$ source setvars.env
```

--------------------------------

### Setup CUDA in WSL

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Update the WSL system and remove old CUDA keys before installing the CUDA SDK.

```bash
## Update the system
sudo apt-get update
sudo apt-get dist-upgrade
```

```bash
sudo apt-key del 7fa2af80
```

--------------------------------

### Example Device Discovery Output

Source: https://tornadovm.readthedocs.io/en/latest/_sources/simple-start.rst.txt

Sample output showing detected PTX and OpenCL devices with their respective configurations.

```bash
Number of Tornado drivers: 2
Total number of PTX devices  : 1
Tornado device=0:0
  PTX -- GeForce GTX 1650
    Global Memory Size: 3.8 GB
    Local Memory Size: 48.0 KB
    Workgroup Dimensions: 3
    Max WorkGroup Configuration: [1024, 1024, 64]
    Device OpenCL C version: N/A

Total number of OpenCL devices  : 4
Tornado device=1:0
  NVIDIA CUDA -- GeForce GTX 1650
    Global Memory Size: 3.8 GB
    Local Memory Size: 48.0 KB
    Workgroup Dimensions: 3
    Max WorkGroup Configuration: [1024, 1024, 64]
    Device OpenCL C version: OpenCL C 1.2

Tornado device=1:1
  Intel(R) OpenCL HD Graphics -- Intel(R) Gen9 HD Graphics NEO
    Global Memory Size: 24.8 GB
    Local Memory Size: 64.0 KB
    Workgroup Dimensions: 3
    Max WorkGroup Configuration: [256, 256, 256]
    Device OpenCL C version: OpenCL C 2.0

Tornado device=1:2
	  Intel(R) OpenCL -- Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz
		Global Memory Size: 31.0 GB
		Local Memory Size: 32.0 KB
		Workgroup Dimensions: 3
		Max WorkGroup Configuration: [8192, 8192, 8192]
		Device OpenCL C version: OpenCL C 1.2

Tornado device=1:3
	  AMD Accelerated Parallel Processing -- Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz
		Global Memory Size: 31.0 GB
		Local Memory Size: 32.0 KB
		Workgroup Dimensions: 3
		Max WorkGroup Configuration: [1024, 1024, 1024]
		Device OpenCL C version: OpenCL C 1.2
```

--------------------------------

### Install TornadoVM on Windows

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Use a virtual environment to manage dependencies and invoke the installer on Windows.

```bash
rem invoke the Microsoft Visual Studio Tool Terminal
.\bin\windowsMicrosoftStudioTools2022.cmd

rem create and activate a virtual environment

python -m venv .venv
.venv\Scripts\activate.bat

python bin\tornadovm-installer
```

--------------------------------

### Run Polyglot Example Scripts

Source: https://tornadovm.readthedocs.io/en/latest/_sources/truffle-languages.rst.txt

Execute provided polyglot examples using the test script or direct CLI commands.

```bash
$ ./scripts/polyglotTests.sh
```

```bash
$ tornado --printKernel --truffle python $TORNADOVM_HOME/examples/polyglotTruffle/mxmWithTornadoVM.py
```

```bash
$ tornado --printKernel --truffle js $TORNADOVM_HOME/examples/polyglotTruffle/mxmWithTornadoVM.js
```

```bash
$ tornado --printKernel --truffle ruby $TORNADOVM_HOME/examples/polyglotTruffle/mxmWithTornadoVM.rb
```

--------------------------------

### Run TornadoVM example with Intel Docker image

Source: https://tornadovm.readthedocs.io/en/latest/_sources/fpga-programming.rst.txt

Executes a DFTMT example using the TornadoVM Docker image with specific JVM device flags.

```bash
./run_intel_openjdk.sh tornado \
    --jvm="-Ds0.t0.device=1:0 "
    -m tornado.examples/uk.ac.manchester.tornado.examples.dynamic.DFTMT --params="1024 default 10"
```

--------------------------------

### Clone and Build TornadoVM

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Download the source code and run the installer.

```bash
cd ~/
git clone https://github.com/beehive-lab/TornadoVM.git tornado
cd tornado

./bin/tornadovm-installer
```

--------------------------------

### Build the SPIR-V Backend

Source: https://tornadovm.readthedocs.io/en/latest/_sources/spirv-backend.rst.txt

Use the TornadoVM installer to enable the SPIR-V backend during the build process.

```bash
$ cd <tornadovm-directory>
$ ./bin/tornadovm-installer
$ Select the backend(s) to install:
$   1. opencl
$   2. spirv
$   3. ptx
$ You can select more than one by typing the numbers separated by commas (e.g., 1, 2, 3).
$ Your selection: 2
$ . setvars.sh
```

--------------------------------

### Install macOS Dependencies

Source: https://tornadovm.readthedocs.io/en/latest/installation.html

Install required build tools via Homebrew.

```bash
brew install wget
brew install maven
```

--------------------------------

### Install Linux Dependencies

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Install required build tools on Red Hat or Ubuntu-based systems.

```bash
sudo dnf install gcc g++ git cmake python3
```

```bash
sudo apt-get install gcc g++ git cmake python3
```

--------------------------------

### Verify and Install Intel Drivers

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Verify checksums and install the downloaded Debian packages.

```bash
wget https://github.com/intel/compute-runtime/releases/download/24.48.31907.7/ww48.sum
sha256sum -c ww48.sum
```

```bash
sudo dpkg -i *.deb
```

--------------------------------

### Configure and run Intel FPGA emulator

Source: https://tornadovm.readthedocs.io/en/latest/_sources/fpga-programming.rst.txt

Sets the required environment variable to enable Intel FPGA emulation and executes the example.

```bash
$ export CL_CONTEXT_EMULATOR_DEVICE_INTELFPGA=1
```

```bash
env CL_CONTEXT_EMULATOR_DEVICE_INTELFPGA=1 tornado \
    --jvm="-Ds0.t0.device=0:1"
    -m tornado.examples/uk.ac.manchester.tornado.examples.dynamic.DFTMT \
    --params="1024 normal 10"
```

--------------------------------

### Compile TornadoVM

Source: https://tornadovm.readthedocs.io/en/latest/installation.html

Initializes the virtual environment and runs the installer to compile the project.

```batch
python -m venv .venv
.venv\Scripts\activate.bat
.\bin\windowsMicrosoftStudioTools2022.cmd
python bin\tornadovm-installer
setvars.cmd
```

--------------------------------

### Configure and Compile TornadoVM

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Initialize the environment and run the installer or recompile with specific backends.

```bash
python -m venv .venv
.venv\Scripts\activate.bat
.\bin\windowsMicrosoftStudioTools2022.cmd
python bin\tornadovm-installer
setvars.cmd
```

```bash
python -m venv .venv
.venv\Scripts\activate.bat
.\bin\windowsMicrosoftStudioTools2022.cmd
nmake /f Makefile.mak jdk21 BACKEND=opencl,ptx
setvars.cmd
```

--------------------------------

### Install Dependencies for RISC-V

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Install required system packages and create a symbolic link for the OpenCL library.

```bash
sudo apt-get install clinfo gcc g++
sudo ln -s libOpenCL.so.1 libOpenCL.so
```

--------------------------------

### Run Polyglot Language Examples

Source: https://tornadovm.readthedocs.io/en/latest/truffle-languages.html

Executes matrix multiplication examples for specific languages using the TornadoVM Truffle integration.

```bash
$ tornado --printKernel --truffle python $TORNADOVM_HOME/examples/polyglotTruffle/mxmWithTornadoVM.py
```

```bash
$ tornado --printKernel --truffle js $TORNADOVM_HOME/examples/polyglotTruffle/mxmWithTornadoVM.js
```

```bash
$ tornado --printKernel --truffle ruby $TORNADOVM_HOME/examples/polyglotTruffle/mxmWithTornadoVM.rb
```

--------------------------------

### Install TornadoVM on macOS

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Install dependencies and TornadoVM on Apple Silicon hardware.

```bash
brew install wget
brew install maven
```

```bash
git clone https://github.com/beehive-lab/TornadoVM.git
cd TornadoVM
bin/tornadovm-installer
Select the backend(s) to install:
  1. opencl
  2. spirv
  3. ptx
You can select more than one by typing the numbers separated by commas (e.g., 1, 2, 3).
Your selection: 1
source setvars.sh
```

```bash
# list the accelerator devices that are reachable from TornadoVM
tornado --devices

# run unit tests
tornado-test -V

## run specific examples (e.g., NBody)
tornado -m tornado.examples/uk.ac.manchester.tornado.examples.compute.NBody
```

```bash
source setvars.sh
make
```

--------------------------------

### Set Environment Variables

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Initialize environment variables after installation.

```bash
source setvars.sh
```

```bash
C:> setvars.cmd
```

--------------------------------

### Install SPIR-V Tools

Source: https://tornadovm.readthedocs.io/en/latest/_sources/spirv-backend.rst.txt

Install the spirv-tools package to enable binary disassembly on common Linux distributions.

```bash
## Fedora OS
sudo dnf install spirv-tools

## Ubuntu OS:
sudo apt-get install spirv-tools
```

--------------------------------

### Run TornadoVM example with Intel oneAPI emulator

Source: https://tornadovm.readthedocs.io/en/latest/_sources/fpga-programming.rst.txt

Executes the DFTMT example using the aocl-ioc64 emulator compiler provided by Intel oneAPI.

```bash
tornado \
    --jvm="-Ds0.t0.device=1:0 "
    -m tornado.examples/uk.ac.manchester.tornado.examples.dynamic.DFTMT --params="1024 default 10"
```

--------------------------------

### Install CUDA Toolkit on WSL

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Commands to download and install the NVIDIA CUDA toolkit for WSL environments.

```bash
wget https://developer.download.nvidia.com/compute/cuda/repos/wsl-ubuntu/x86_64/cuda-wsl-ubuntu.pin
sudo mv cuda-wsl-ubuntu.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/12.6.3/local_installers/cuda-repo-wsl-ubuntu-12-6-local_12.6.3-1_amd64.deb
sudo dpkg -i cuda-repo-wsl-ubuntu-12-6-local_12.6.3-1_amd64.deb
sudo cp /var/cuda-repo-wsl-ubuntu-12-6-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda-toolkit-12-6
```

--------------------------------

### Setup Python Environment for TornadoVM

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Create and activate a virtual environment for TornadoVM dependencies.

```bash
sudo apt install python3-venv
## Setup a new environment for Python modules
python3 -m venv ~/bin/venv
source ~/bin/venv/bin/activate
```

--------------------------------

### Execute Intel FPGA emulation with environment variable

Source: https://tornadovm.readthedocs.io/en/latest/fpga-programming.html

Run a TornadoVM example with the Intel emulation environment variable explicitly set.

```bash
env CL_CONTEXT_EMULATOR_DEVICE_INTELFPGA=1 tornado \
    --jvm="-Ds0.t0.device=0:1"
    -m tornado.examples/uk.ac.manchester.tornado.examples.dynamic.DFTMT \
    --params="1024 normal 10"
```

--------------------------------

### Recompile TornadoVM Backend

Source: https://tornadovm.readthedocs.io/en/latest/installation.html

Switch or update the backend configuration after initial installation.

```bash
source setvars.sh
make BACKEND=opencl
```

--------------------------------

### Execute Xilinx FPGA emulation

Source: https://tornadovm.readthedocs.io/en/latest/fpga-programming.html

Run a TornadoVM example on a Xilinx platform configured for emulation.

```bash
tornado \
    --jvm="-Ds0.t0.device=0:1"
    -m tornado.examples/uk.ac.manchester.tornado.examples.dynamic.DFTMT \
    --params="1024 normal 10"
```

--------------------------------

### Build and Verify TornadoVM on Linux

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Clone, install, and verify TornadoVM on Linux systems.

```bash
git clone https://github.com/beehive-lab/TornadoVM.git
cd TornadoVM
bin/tornadovm-installer
Select the backend(s) to install:
  1. opencl
  2. spirv
  3. ptx
You can select more than one by typing the numbers separated by commas (e.g., 1, 2, 3).
Your selection: 1, 2, 3
source setvars.sh
```

```bash
# list the accelerator devices that are reachable from TornadoVM
tornado --devices

# run unit tests
tornado-test -V

## run specific examples (e.g., NBody)
tornado -m tornado.examples/uk.ac.manchester.tornado.examples.compute.NBody
```

```bash
source setvars.sh
make BACKEND=opencl
```

--------------------------------

### Bytecode execution output

Source: https://tornadovm.readthedocs.io/en/latest/multi-device.html

Example output showing bytecode operations like ALLOC, TRANSFER, and LAUNCH across different devices.

```text
Interpreter instance running bytecodes for:   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 Running in thread:  pool-1-thread-1
bc:  ALLOC [I@2ffe106e on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0
bc:  ALLOC [I@705e1b5b on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0
bc:  ALLOC [F@63f945a3 on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0
bc:  TRANSFER_HOST_TO_DEVICE_ONCE  [Object Hash Code=0x2ffe106e] [I@2ffe106e on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0, offset=0 [event list=-1]
bc:  TRANSFER_HOST_TO_DEVICE_ONCE  [Object Hash Code=0x63f945a3] [F@63f945a3 on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0, offset=0 [event list=-1]
bc:  LAUNCH  task blur.red - compute on  [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070, size=0, offset=0 [event list=0]
bc:  ALLOC [I@738395e4 on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0
bc:  ALLOC [I@1d78beeb on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0
bc:  TRANSFER_HOST_TO_DEVICE_ONCE  [Object Hash Code=0x738395e4] [I@738395e4 on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0, offset=0 [event list=-1]
bc:  LAUNCH  task blur.blue - compute on  [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070, size=0, offset=0 [event list=2]
bc:  TRANSFER_DEVICE_TO_HOST_ALWAYS [0x705e1b5b] [I@705e1b5b on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0, offset=0 [event list=3]
bc:  TRANSFER_DEVICE_TO_HOST_ALWAYS [0x1d78beeb] [I@1d78beeb on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070 , size=0, offset=0 [event list=5]
bc:  DEALLOC [0x2ffe106e] [I@2ffe106e on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070
bc:  DEALLOC [0x705e1b5b] [I@705e1b5b on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070
bc:  DEALLOC [0x63f945a3] [F@63f945a3 on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070
bc:  DEALLOC [0x738395e4] [I@738395e4 on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070
bc:  DEALLOC [0x1d78beeb] [I@1d78beeb on   [NVIDIA CUDA] -- NVIDIA GeForce RTX 3070
bc:  BARRIER  event-list 17
bc:  END

Interpreter instance running bytecodes for:   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700 Running in thread:  pool-1-thread-2
bc:  ALLOC [I@41ac3343 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700 , size=0
bc:  ALLOC [I@16c36388 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700 , size=0
bc:  ALLOC [F@63f945a3 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700 , size=0
bc:  TRANSFER_HOST_TO_DEVICE_ONCE  [Object Hash Code=0x41ac3343] [I@41ac3343 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700 , size=0, offset=0 [event list=-1]
bc:  TRANSFER_HOST_TO_DEVICE_ONCE  [Object Hash Code=0x63f945a3] [F@63f945a3 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700 , size=0, offset=0 [event list=-1]
bc:  LAUNCH  task blur.green - compute on  [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700, size=0, offset=0 [event list=1]
bc:  TRANSFER_DEVICE_TO_HOST_ALWAYS [0x16c36388] [I@16c36388 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700 , size=0, offset=0 [event list=4]
bc:  DEALLOC [0x41ac3343] [I@41ac3343 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700
bc:  DEALLOC [0x16c36388] [I@16c36388 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700
bc:  DEALLOC [0x63f945a3] [F@63f945a3 on   [Intel(R) OpenCL] -- 13th Gen Intel(R) Core(TM) i7-13700
bc:  BARRIER  event-list 17
bc:  END
```

--------------------------------

### Execute BlurFilter on Multiple Devices

Source: https://tornadovm.readthedocs.io/en/latest/_sources/multi-device.rst.txt

Run the BlurFilter example by explicitly assigning specific tasks to different devices using JVM properties.

```bash
$ tornado --threadInfo  \
        --jvm=" -Dblur.red.device=0:0 -Dblur.green.device=0:1 -Dblur.blue.device=0:0" \
        -m  tornado.examples/uk.ac.manchester.tornado.examples.compute.BlurFilter
```

--------------------------------

### Extract and Display Features

Source: https://tornadovm.readthedocs.io/en/latest/_sources/profiler.rst.txt

Example command to run an NBody example with feature extraction enabled, followed by the resulting JSON output.

```bash
$ tornado --jvm="-Dtornado.feature.extraction=True" -m tornado.examples/uk.ac.manchester.tornado.examples.compute.NBody --params "1024 1"
```

```json
{
    "nBody": {
        "BACKEND" : "PTX",
        "DEVICE_ID": "0:2",
        "DEVICE": "GeForce GTX 1650",
        "Global Memory Loads":  "15",
        "Global Memory Stores":  "6",
        "Constant Memory Loads":  "0",
        "Constant Memory Stores":  "0",
        "Local Memory Loads":  "0",
        "Local Memory Stores":  "0",
        "Private Memory Loads":  "20",
        "Private Memory Stores":  "20",
        "Total Loops":  "2",
        "Parallel Loops":  "1",
        "If Statements":  "2",
        "Integer Comparison":  "2",
        "Float Comparison":  "0",
        "Switch Statements":  "0",
        "Switch Cases":  "0",
        "Vector Operations":  "0",
        "Integer & Float Operations":  "57",
        "Boolean Operations":  "9",
        "Cast Operations":  "2",
        "Float Math Functions":  "1",
        "Integer Math Functions":  "0"
    }
}
```

--------------------------------

### Verify OpenCL installation

Source: https://tornadovm.readthedocs.io/en/latest/_sources/fpga-programming.rst.txt

Use clinfo to check for available OpenCL platforms and devices.

```bash
$ clinfo
   Number of platforms                               1
   Platform Name                                   Intel(R) FPGA SDK for OpenCL(TM)
   Platform Vendor                                 Intel(R) Corporation
   Platform Version                                OpenCL 1.0 Intel(R) FPGA SDK for OpenCL(TM), Version 17.1
   Platform Profile                                EMBEDDED_PROFILE
   Platform Extensions                             cl_khr_byte_addressable_store cles_khr_int64 cl_intelfpga_live_object_tracking cl_intelfpga_compiler_mode cl_khr_icd cl_khr_3d_image_writes
   Platform Extensions function suffix             IntelFPGA

   Platform Name                                   Intel(R) FPGA SDK for OpenCL(TM)
   Number of devices                                 1
   Device Name                                     p385a_sch_ax115 : nalla_pcie (aclnalla_pcie0)
   Device Vendor                                   Nallatech ltd
   Device Vendor ID                                0x1172
   Device Version                                  OpenCL 1.0 Intel(R) FPGA SDK for OpenCL(TM), Version 17.1
   Driver Version                                  17.1
   Device OpenCL C Version                         OpenCL C 1.0
   Device Type                                     Accelerator
```

--------------------------------

### Run TornadoVM NVIDIA Experiment

Source: https://tornadovm.readthedocs.io/en/latest/docker.html

Example of cloning the repository and executing a matrix multiplication experiment using the provided runner script.

```bash
$ git clone https://github.com/beehive-lab/docker-tornado
$ cd docker-tornado

## Run Matrix Multiplication - provided in the docker-tornado repository
$ ./run_nvidia_openjdk.sh tornado -cp example/target/example-1.0-SNAPSHOT.jar example.MatrixMultiplication

Computing MxM of 2048x2048
    CPU Execution: 0.36 GFlops, Total time = 48254 ms
    GPU Execution: 277.09 GFlops, Total Time = 62 ms
    Speedup: 778x
```

--------------------------------

### Run Intel Matrix Multiplication Experiment

Source: https://tornadovm.readthedocs.io/en/latest/_sources/docker.rst.txt

Execute a matrix multiplication example on Intel hardware using the provided runner script.

```bash
$ git clone https://github.com/beehive-lab/docker-tornado
$ cd docker-tornado

## Run Matrix Multiplication - provided in the docker-tornado repository
$ ./run_intel_openjdk.sh tornado -cp example/target/example-1.0-SNAPSHOT.jar example.MatrixMultiplication --parms="256"
```

--------------------------------

### Build and Visualize Documentation

Source: https://tornadovm.readthedocs.io/en/latest/_sources/build-documentation.rst.txt

Execute the build process and open the generated HTML files in a browser.

```bash
make docs
## visualize the documentation (E.g., with Firefox)
firefox docs/build/html/index.html
```

--------------------------------

### Concurrent Execution Output

Source: https://tornadovm.readthedocs.io/en/latest/multi-device.html

Example output showing task information and device assignment when concurrent execution is enabled.

```text
    Task info: blur.red
    Backend           : OPENCL
    Device            : NVIDIA GeForce RTX 3070 CL_DEVICE_TYPE_GPU (available)
    Dims              : 2
    Global work offset: [0, 0]
    Global work size  : [4000, 6000]
    Local  work size  : [32, 30, 1]
    Number of workgroups  : [125, 200]

Task info: blur.green
    Backend           : OPENCL
    Device            : 13th Gen Intel(R) Core(TM) i7-13700 CL_DEVICE_TYPE_CPU (available)
    Dims              : 2
    Global work offset: [0, 0]
    Global work size  : [24, 1]
    Local  work size  : null
    Number of workgroups  : [0, 0]

Task info: blur.blue
    Backend           : OPENCL
    Device            : NVIDIA GeForce RTX 3070 CL_DEVICE_TYPE_GPU (available)
    Dims              : 2
    Global work offset: [0, 0]
    Global work size  : [4000, 6000]
    Local  work size  : [32, 30, 1]
    Number of workgroups  : [125, 200]
```

--------------------------------

### Run TornadoVM Intel Experiment

Source: https://tornadovm.readthedocs.io/en/latest/docker.html

Example of executing a matrix multiplication experiment on Intel hardware using the provided runner script.

```bash
$ git clone https://github.com/beehive-lab/docker-tornado
$ cd docker-tornado

## Run Matrix Multiplication - provided in the docker-tornado repository
$ ./run_intel_openjdk.sh tornado -cp example/target/example-1.0-SNAPSHOT.jar example.MatrixMultiplication --parms="256"

Computing MxM of 256x256
    CPU Execution: 1.53 GFlops, Total time = 22 ms
    GPU Execution: 8.39 GFlops, Total Time = 4 ms
    Speedup: 5x
```

--------------------------------

### Run the DFT benchmark

Source: https://tornadovm.readthedocs.io/en/latest/_sources/benchmarking.rst.txt

Example execution of the Discrete Fourier Transform benchmark showing typical JMH output format.

```bash
$ tornado -m tornado.benchmarks/uk.ac.manchester.tornado.benchmarks.dft.JMHDFT
# JMH version: 1.23
...
Benchmark          Mode  Cnt   Score   Error  Units
JMHDFT.dftJava     avgt    5  19.736 ± 1.589   s/op
JMHDFT.dftTornado  avgt    5   0.155 ± 0.008   s/op
```

--------------------------------

### View task execution info

Source: https://tornadovm.readthedocs.io/en/latest/multi-device.html

Expected output showing the device assignment and configuration for each task in the BlurFilter example.

```text
Task info: blur.red
    Backend           : OPENCL
    Device            : NVIDIA GeForce RTX 3070 CL_DEVICE_TYPE_GPU (available)
    Dims              : 2
    Global work offset: [0, 0]
    Global work size  : [4000, 6000]
    Local  work size  : [32, 30, 1]
    Number of workgroups  : [125, 200]

Task info: blur.blue
    Backend           : OPENCL
    Device            : NVIDIA GeForce RTX 3070 CL_DEVICE_TYPE_GPU (available)
    Dims              : 2
    Global work offset: [0, 0]
    Global work size  : [4000, 6000]
    Local  work size  : [32, 30, 1]
    Number of workgroups  : [125, 200]

Task info: blur.green
    Backend           : OPENCL
    Device            : 13th Gen Intel(R) Core(TM) i7-13700 CL_DEVICE_TYPE_CPU (available)
    Dims              : 2
    Global work offset: [0, 0]
    Global work size  : [24, 1]
    Local  work size  : null
    Number of workgroups  : [0, 0]
```

--------------------------------

### Run NVIDIA Matrix Multiplication Experiment

Source: https://tornadovm.readthedocs.io/en/latest/_sources/docker.rst.txt

Execute a matrix multiplication example using the provided runner script within the cloned repository.

```bash
$ git clone https://github.com/beehive-lab/docker-tornado
$ cd docker-tornado

## Run Matrix Multiplication - provided in the docker-tornado repository
$ ./run_nvidia_openjdk.sh tornado -cp example/target/example-1.0-SNAPSHOT.jar example.MatrixMultiplication
```

--------------------------------

### Execute Task on AWS F1 FPGA

Source: https://tornadovm.readthedocs.io/en/latest/_sources/cloud.rst.txt

Run a TornadoVM example using a custom configuration file and background the process to prevent connection timeout issues.

```bash
$ tornado --jvm "-Ds0.t0.device=0:0 -Dtornado.fpga.conf.file=/home/centos/TornadoVM/bin/sdk/etc/aws-fpga.conf -Xmx20g -Xms20g" --printKernel --threadInfo -m tornado.examples/uk.ac.manchester.tornado.examples.dynamic.DFTMT --params="256 default 1" >> output.log
$ Ctrl-Z (^Z)
$ bg
$ disown
```

--------------------------------

### Example TornadoVM Java Flags Output

Source: https://tornadovm.readthedocs.io/en/latest/_sources/ide-integration.rst.txt

Sample output of the Java flags required for configuring applications in IntelliJ.

```bash
<path-to-TornadoVM-directory>/etc/dependencies/TornadoVM-graal-jdk-21/graalvm-community-openjdk-21.0.1+12.1/bin/java
-server -XX:-UseCompressedOops -XX:+UnlockExperimentalVMOptions -XX:+EnableJVMCI -XX:-UseCompressedClassPointers --enable-preview -Djava.library.path=<path-to-TornadoVM-directory>/bin/sdk/lib  --module-path .:<path-to-TornadoVM-directory>/bin/sdk/share/java/tornado
-Dtornado.load.api.implementation=uk.ac.manchester.tornado.runtime.tasks.TornadoTaskGraph -Dtornado.load.runtime.implementation=uk.ac.manchester.tornado.runtime.TornadoCoreRuntime -Dtornado.load.tornado.implementation=uk.ac.manchester.tornado.runtime.common.Tornado
-Dtornado.load.annotation.implementation=uk.ac.manchester.tornado.annotation.ASMClassVisitor -Dtornado.load.annotation.parallel=uk.ac.manchester.tornado.api.annotations.Parallel  -XX:+UseParallelGC
@<path-to-TornadoVM-directory>/bin/sdk/etc/exportLists/common-exports
@<path-to-TornadoVM-directory>/bin/sdk/etc/exportLists/opencl-exports
@<path-to-TornadoVM-directory>/bin/sdk/etc/exportLists/spirv-exports
@<path-to-TornadoVM-directory>/bin/sdk/etc/exportLists/ptx-exports --add-modules ALL-SYSTEM,tornado.runtime,tornado.annotation,tornado.drivers.common,tornado.drivers.opencl,tornado.drivers.opencl,tornado.drivers.ptx
```

--------------------------------

### Verify NVIDIA driver installation

Source: https://tornadovm.readthedocs.io/en/latest/_sources/cuda-backend.rst.txt

Run nvidia-smi to check the status of the NVIDIA driver and GPU memory usage.

```bash
+-----------------------------------------------------------------------------+
 | NVIDIA-SMI 440.100      Driver Version: 440.100      CUDA Version: 10.2     |
 |-------------------------------+----------------------+----------------------|
 | GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
 | Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
 |===============================+======================+======================|
 |   0  GeForce GTX 1650    Off  | 00000000:01:00.0 Off |                  N/A |
 | N/A   51C    P8     1W /  N/A |     73MiB /  3914MiB |      0%      Default |
 +-------------------------------+----------------------+----------------------+

 +-----------------------------------------------------------------------------+
 | Processes:                                                       GPU Memory |
 |  GPU       PID   Type   Process name                             Usage      |
 |=============================================================================|
 |    0      1095      G   /usr/lib/xorg/Xorg                            36MiB |
 |    0      1707      G   /usr/lib/xorg/Xorg                            36MiB |
 +-----------------------------------------------------------------------------+
```

--------------------------------

### Initialize IntelliJ Project Files

Source: https://tornadovm.readthedocs.io/en/latest/_sources/ide-integration.rst.txt

Commands to build TornadoVM, set environment variables, and generate IntelliJ run configurations.

```bash
# Build TornadoVM first (with your desired backend)
$ make BACKEND=opencl   # or ptx, spirv, opencl,ptx, etc.

# Load the environment variables
$ source setvars.sh     # Linux/macOS
$ setvars.cmd           # Windows

# Generate IntelliJ project files
$ make intellijinit
```

--------------------------------

### Configure NVIDIA Execution Options

Source: https://tornadovm.readthedocs.io/en/latest/_sources/docker.rst.txt

Examples of passing flags to the runner script to inspect kernels, debug execution, or configure JVM memory settings.

```bash
# To see the generated OpenCL kernel
$ ./run_nvidia.sh tornado --printKernel example/MatrixMultiplication

# To check some runtime info about the kernel execution and device
$ ./run_nvidia.sh tornado --debug example/MatrixMultiplication

$ ./run_nvidia.sh tornado --jvm="-Xmx16g -Xms16g" example/MatrixMultiplication
```

--------------------------------

### Install OpenCL Development Package

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Install the ocl-icd-opencl-dev package required for Ubuntu 16.04 and newer.

```bash
$ apt-get install ocl-icd-opencl-dev
```

--------------------------------

### Enable Environment and Run Tests

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Activate the environment and execute the test suite.

```bash
source ~/bin/venv/bin/activate
source setvars.sh
```

```bash
make tests
```

--------------------------------

### Initialize TornadoVM for Root

Source: https://tornadovm.readthedocs.io/en/latest/cloud.html

Set up TornadoVM environment variables for the root user and verify device detection.

```bash
$ cd /home/centos/TornadoVM
$ source setvars.env

$ tornado --devices
```

--------------------------------

### Generate IntelliJ Project Files

Source: https://tornadovm.readthedocs.io/en/latest/ide-integration.html

Initializes the project by generating run configurations in the .build/ directory.

```bash
$ make intellijinit
```

--------------------------------

### Display TornadoVM Help

Source: https://tornadovm.readthedocs.io/en/latest/_sources/simple-start.rst.txt

View the command-line interface options and usage instructions.

```bash
$ tornado --help
usage: tornado [-h] [--version] [-version] [--debug] [--threadInfo] [--igv] [--igvLowTier] [--printKernel] [--printBytecodes] [--enableProfiler ENABLE_PROFILER] [--dumpProfiler DUMP_PROFILER] [--printJavaFlags] [--devices] [--ea]
             [--module-path MODULE_PATH] [--classpath CLASSPATH] [--jvm JVM_OPTIONS] [-m MODULE_APPLICATION] [-jar JAR_FILE] [--params APPLICATION_PARAMETERS]
             [application]

Tool for running TornadoVM Applications. This tool sets all Java options for enabling TornadoVM.

positional arguments:
  application

optional arguments:
  -h, --help            show this help message and exit
  --version             Print version of TornadoVM
  -version              Print JVM Version
  --debug               Enable debug mode
  --threadInfo          Print thread deploy information per task on the accelerator
  --igv                 Debug Compilation Graphs using Ideal Graph Visualizer (IGV)
  --igvLowTier          Debug Low Tier Compilation Graphs using Ideal Graph Visualizer (IGV)
  --printKernel, -pk    Print generated kernel (OpenCL, PTX or SPIR-V)
  --printBytecodes, -pc
                        Print the generated TornadoVM bytecodes
  --enableProfiler ENABLE_PROFILER
                        Enable the profiler {silent|console}
  --dumpProfiler DUMP_PROFILER  
                        Dump the profiler to a file
  --printJavaFlags      Print all the Java flags to enable the execution with TornadoVM
  --devices             Print information about the accelerators available
  --ea, -ea             Enable assertions
  --module-path MODULE_PATH
                        Module path option for the JVM
  --classpath CLASSPATH, -cp CLASSPATH, --cp CLASSPATH
                        Set class-path
  --jvm JVM_OPTIONS, -J JVM_OPTIONS
                        Pass Java options to the JVM. Use without spaces: e.g., --jvm="-Xms10g" or -J"-Xms10g"
  -m MODULE_APPLICATION
                        Application using Java modules
  -jar JAR_FILE         Main Java application in a JAR File
  --params APPLICATION_PARAMETERS
                      Command-line parameters for the host-application. Example: --params="param1 param2..."
```

--------------------------------

### Build GraalPy from Source

Source: https://tornadovm.readthedocs.io/en/latest/_sources/truffle-languages.rst.txt

Clone and build the GraalPy standalone distribution from source.

```bash
$ git clone https://github.com/oracle/graalpython.git && cd graalpython && git checkout graal-23.1.0
$ git clone https://github.com/graalvm/mx.git mx
$ export PATH=$PWD/mx:$PATH
$ mx fetch-jdk
$ export JAVA_HOME=~/.mx/jdks/labsjdk-ce-21.0.1-jvmci-23.1-b22
$ mx --dy /compiler python-gvm
```

--------------------------------

### Configure Maven on Windows

Source: https://tornadovm.readthedocs.io/en/latest/_sources/installation.rst.txt

Add the Maven bin directory to the system PATH.

```bash
rem Maven unpacked to %ProgramFiles%\apache-maven-3.9.1
set PATH=%ProgramFiles%\apache-maven-3.9.1\set;%PATH%
```

--------------------------------

### float get(int index)

Source: https://tornadovm.readthedocs.io/en/latest/_sources/programming.rst.txt

Returns the value at a specific index.

```APIDOC
## float get(int index)

### Description
Returns the value of a specific index.

### Parameters
- **index** (int) - The position to retrieve the value from.
```

--------------------------------

### Get value from FloatArray

Source: https://tornadovm.readthedocs.io/en/latest/_sources/programming.rst.txt

Retrieves the value at a specific index from a FloatArray.

```java
FloatArray floatArray = FloatArray.fromArray(new float[] {2.0f, 1.0f, 2.0f, 5.0f});
float floatValue = floatArray.get(3); // returns 5.0f
```

--------------------------------

### Initialize Windows Build Environment

Source: https://tornadovm.readthedocs.io/en/latest/_sources/ide-integration.rst.txt

Initialize the environment using the provided Windows batch script.

```bash
$ cd <path-to-TornadoVM-directory>
$ .\bin\windowsMicrosoftStudioTools2022.cmd
```

--------------------------------

### Set Environment Variables

Source: https://tornadovm.readthedocs.io/en/latest/installation.html

Initialize the TornadoVM SDK environment variables after installation.

```bash
$ source setvars.sh
```

```batch
C:> setvars.cmd
```

--------------------------------

### Configure Xilinx FPGA emulation

Source: https://tornadovm.readthedocs.io/en/latest/fpga-programming.html

Use the Makefile to configure Xilinx emulation parameters for specific platforms and device counts.

```bash
make xilinx_emulation FPGA_PLATFORM=xilinx_u50_gen3x16_xdma_201920_3 NUM_OF_FPGA_DEVICES=1
```

--------------------------------

### Verify CMake Installation

Source: https://tornadovm.readthedocs.io/en/latest/_sources/ide-integration.rst.txt

Check if the cmake command is available in the system PATH.

```bash
$ cmake --version
```

--------------------------------

### Get FloatArray size

Source: https://tornadovm.readthedocs.io/en/latest/_sources/programming.rst.txt

Returns the total number of elements in the FloatArray segment.

```java
FloatArray floatArray = new FloatArray(16);
int size = floatArray.getSize(); // returns 16
```

--------------------------------

### Build the CUDA Backend

Source: https://tornadovm.readthedocs.io/en/latest/_sources/cuda-backend.rst.txt

Set the JAVA_HOME environment variable and execute the make command to build the CUDA backend and SDK.

```bash
# JDK 21 is required
export JAVA_HOME=/path/to/jdk21

# Build the CUDA backend (tornado-drivers/cuda + cuda-jni) and the SDK
make BACKEND=cuda
```

--------------------------------

### Initialize Xilinx SDAccel environment

Source: https://tornadovm.readthedocs.io/en/latest/_sources/fpga-programming.rst.txt

Set the required environment variables for the Xilinx toolchain.

```bash
source /opt/Xilinx/SDx/2018.2/settings64.sh
```

--------------------------------

### Enter Root Shell

Source: https://tornadovm.readthedocs.io/en/latest/cloud.html

Switch to a bash shell with root privileges.

```bash
$ sudo -E /bin/bash
```