Skip to content

Fixes for TX1 64-bit OS + CUDA CMake Fix #1593

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
shehzan10 merged 4 commits into from
Sep 21, 2016
Merged

Fixes for TX1 64-bit OS + CUDA CMake Fix #1593

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
75d7133
Force update CUDA_LIBDEVICE_DIR when CUDA directories are updated
shehzan10 Sep 13, 2016
11b7bd3
BUGFIX: AARCH64 (TX1 64-bit OS) does not define __arm__ - Requires __…
shehzan10 Sep 15, 2016
333a31a
DOCS: Move INSTALL.md to install.md
shehzan10 Sep 15, 2016
00a8a03
DOCS: Remove unused packages from installation documentation
shehzan10 Sep 15, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 11 additions & 4 deletions docs/pages/INSTALL.md → docs/pages/install.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
ArrayFire binary installation instructions {#installing}
ArrayFire Binary Installation Instructions {#installing}
=====

Installing ArrayFire couldn't be easier. We ship installers for Windows,
Expand Down Expand Up @@ -67,7 +67,7 @@ Finally, verify that the path addition worked correctly. You can do this by:
First install the prerequisite packages:

# Prerequisite packages:
apt-get install libfreeimage-dev libatlas3gf-base libfftw3-dev libglew-dev libglewmx-dev libglfw3-dev cmake
apt-get install libglfw3-dev cmake

# Enable GPU support (OpenCL):
apt-get install ocl-icd-libopencl1
Expand All @@ -86,7 +86,7 @@ file, run the installer.
First install the prerequisite packages:

# Install prerequiste packages
yum install freeimage atlas fftw libGLEW libGLEWmx glfw cmake
yum install glfw cmake

On Centos and Redhat the `glfw` package is outdated and you will need to compile
it from source. Please
Expand All @@ -106,7 +106,7 @@ file, run the installer.
First install the prerequisite packages:

# Prerequisite packages:
sudo apt-get install libfreeimage-dev libatlas3gf-base libfftw3-dev cmake
sudo apt-get install cmake

Ubuntu 14.04 will not have the libglfw3-dev package in its repositories. You can either build the
library from source (following the
Expand All @@ -131,6 +131,13 @@ with any drivers required for your hardware.
# Enable GPU support (OpenCL):
apt-get install ocl-icd-libopencl1

### Special instructions for Tegra X1
**The ArrayFire binary installer for Terga X1 requires JetPack 2.3 or L4T 24.2
for Jetson TX1. This includes Ubuntu 16.04, CUDA 8.0 etc.**
If you are using ArrayFire on the Tegra X1 also install these packages:

sudo apt-get install libopenblas-dev liblapacke-dev

### Special instructions for Tegra K1
If you are using ArrayFire on the Tegra K1 also install these packages:

Expand Down
2 changes: 1 addition & 1 deletion src/backend/cuda/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ INCLUDE(CLKernelToH)
INCLUDE(FindNVVM)

OPTION(USE_LIBDEVICE "Use libdevice for CUDA JIT" ON)
SET(CUDA_LIBDEVICE_DIR "${CUDA_NVVM_HOME}/libdevice" CACHE PATH "Path where libdevice compute files are located")
SET(CUDA_LIBDEVICE_DIR "${CUDA_NVVM_HOME}/libdevice" CACHE PATH "Path where libdevice compute files are located" FORCE)

MARK_AS_ADVANCED(
CUDA_BUILD_CUBIN
Expand Down
2 changes: 1 addition & 1 deletion src/backend/cuda/platform.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,7 +242,7 @@ string getDriverVersion()
int x = nvDriverVersion(driverVersion, sizeof(driverVersion));
if (x != 1) {
// Windows, OSX, Tegra Need a new way to fetch driver
#if !defined(OS_WIN) && !defined(OS_MAC) && !defined(__arm__)
#if !defined(OS_WIN) && !defined(OS_MAC) && !defined(__arm__) && !defined(__aarch64__)
throw runtime_error("Invalid driver");
#endif
int driver = 0;
Expand Down