From 3ba1d8179aed73f4cd50fd47c9da46cc2c4a4658 Mon Sep 17 00:00:00 2001
From: Paul McCarthy <pauldmccarthy@gmail.com>
Date: Mon, 12 Jul 2021 11:22:27 +0100
Subject: [PATCH] DOC: Update CUDA build overview
---
README.md | 15 +++------------
1 file changed, 3 insertions(+), 12 deletions(-)
diff --git a/README.md b/README.md
index 14b542f..d4825b1 100644
--- a/README.md
+++ b/README.md
@@ -22,20 +22,12 @@ in Python, and are executed with `pytest`.
Some FSL projects (e.g. [`fsl/eddy`(https://git.fmrib.ox.ac.uk/fsl/eddy) use
CUDA for GPU acceleration. In order to compile these projects, the `nvcc`
-compiler must be available on your `$PATH`, and you must provide the following
-variables:
-
- - `CUDA_VER`: CUDA version, in `major.minor` format, e.g. `10.2`. If not set,
- defaults to the version reported by `nvcc --version`.
- - `CUDA_HOME`: Path to the CUDA installation that the project should be
- compiled against. If not set, defaults to `/usr/local/cuda-X.Y`, where
- `X.Y` is the value of `CUDA_VER`.
-
+compiler must be available on your `$PATH`, or a variable called `$NVCC` must
+refer to the `nvcc` executable to use.
The following additional options may be used to control compilation of a CUDA
project:
- - `NVCC`: Path to a specific `nvcc` executable
- `CUDA_STATIC`: Statically link against the CUDA runtime and certain;
CUDA Toolkit libraris (default is to use dynamic linking).
- `GENCODEFLAGS`: `-gencode` options specifying the device architectures to
@@ -45,8 +37,7 @@ project:
For example, to compile a CUDA project with a specific CUDA installation, and
using static linking:
- export CUDA_HOME=/usr/local/cuda-10.1
- export PATH=$CUDA_HOME/bin:$PATH
+ export PATH=/usr/local/cuda-10.2/bin:$PATH
make CUDA_STATIC=1
The `Makefile` for each FSL CUDA project may provide additional options for
--
GitLab