From 820002fa6d3cc0d4314e6e61f756744a3ee9faa3 Mon Sep 17 00:00:00 2001 From: hsharif3 <hsharif3@illinois.edu> Date: Mon, 15 Mar 2021 06:43:04 +0000 Subject: [PATCH] Update Main README.md --- README.md | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 4280373aa5..536d398233 100644 --- a/README.md +++ b/README.md @@ -51,14 +51,15 @@ Supported/tested GPU architectures for Tensor Backend: HPVM has not been tested but might work on other CPUs supported by LLVM Backend, and GPUs supported by OpenCL such as Intel, AMD, etc. -**NOTE: Approximations are tuned for Jetson TX2 and same speedups may not exist for other architectures ** +**NOTE**: Approximations are tuned for Jetson TX2 and same speedups may not exist for other architectures ## Getting source code and building HPVM Checkout HPVM: ```shell -git clone --recursive https://gitlab.engr.illinois.edu/llvm/hpvm-release.git/ -cd hpvm-release/hpvm +git clone --recursive https://gitlab.engr.illinois.edu/llvm/hpvm.git +git checkout approx_hpvm_reorg_keras +cd hpvm/hpvm ``` HPVM needs to be able to find CUDA. @@ -79,6 +80,12 @@ HPVM installer script can be used to download, configure and build HPVM along wi ```shell bash install.sh ``` +Post Installation Build the HPVM Compilation Tool `approxhpvm.py` using: + +``` +make approxhpvm.py +``` + Specifically, the HPVM installer downloads LLVM, and Clang, copies HPVM source into llvm/tools and builds the entire tree. It also builds a modified LLVM C-Backend, based on the one maintained by [Julia Computing](https://github.com/JuliaComputing/llvm-cbe), as a part of HPVM and is currently used to generate OpenCL kernels for GPUs. -- GitLab