The GPU plugins have a dependency on the device libraries. Sometimes we
cannot build the device libraries because the user does not have a valid
`clang` to use or it was explicitly disabled. Currently this leads to a
transitive failure because we cannot meet this dependency. This patch
simply removes that dependency.
Fixes https://github.com/llvm/llvm-project/issues/60457
Reviewed By: tianshilei1992
Differential Revision: https://reviews.llvm.org/D143196
Summary:
The previous patch also needed to apply this to the other AMDGPU plugin,
this will be removed soon but it should be correct while it's here at
least.
Summary:
We added a new agent information enum in a previous commit. This was not
added to the dynamic HSA implementation so it failed to compile without
a local HSA install to use.
Summary:
Recently AMD moved the "hsa.h" include to "hsa/hsa.h". This causes
several warning. This patch checks to see if we can include that one
instead. This should hopefully keep things backwards compatible while
silencing the warnings.
We already created a versioned `__tgt_kernel_arguments` struct but it
was only briefly used and its content was passed in isolation anyway.
This makes it hard to add more information in the future. With this
patch we fully embrace the struct as means to pass information from the
compiler to the plugin as part of a kernel launch.
The patch also extends and renames the struct, bumping the version
number to 2. Version 1 entries are auto-upgraded. This is in preparation
for "bare" kernel launches, per kernel dynamic shared memory, CUDA/HIP
lowering, etc.
The `__tgt_target_kernel_nowait` interface was deprecated as it was
unused. Once we actually implement support for something like that, we
can add an appropriate API.
Note: Only plugins with the `launch_kernel` interface are now supported.
That means that a new clang won't be able to use an old runtime.
An old clang can still use the new runtime since the libomptarget
interface did not change.
Differential Revision: https://reviews.llvm.org/D141232
The next gen plugin adds the def of `DEBUG_PREFIX` in CMake, causing
compiler warning that `DEBUG_PREFIX` is defined multiple times. This patch simply
guards the macro def.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D142064
Currently we build tests as long as the libraries are found on the
machine. This doesn't necessarily mean there is a GPU to use though.
This patch changes it to where we only will build the tests if we found
a compatible GPU via `nvptx-arch` or `amdgpu-arch`.
The only downside to this I could see if someone were to build LLVM on a
home node of a cluster and then wished to run the tests after switching
to a compute node. For this I think we should allow it to be overridden.
I think that's better than allowing us to run tests that will fail by
default.
Reviewed By: tianshilei1992
Differential Revision: https://reviews.llvm.org/D142018
This variable is used by the runtime. Before kernel launch we set it to
indicate several configuration options from the host. This patch renames
it to be more in-line with the rest of the named exported from the
runtime. This is better because this is the only symbol visible to the
host from the runtime, so it should have a reserved name.
Reviewed By: tianshilei1992
Differential Revision: https://reviews.llvm.org/D141960
The current only way to obtain pinned memory with libomptarget is to use a custom allocator llvm_omp_target_alloc_host.
This reflects well the CUDA implementation of libomptarget, but it does not correctly expose the AMDGPU runtime API,
where any system allocated page can be locked/unlocked through a call to hsa_amd_memory_lock/unlock.
This patch enables users to allocate memory through malloc (mmap, sbreak) and then pin the related memory pages
with a libomptarget special call. It is a base support in the amdgpu libomptarget plugin to enable users to prelock
their host memory pages so that the runtime doesn't need to lock them itself for asynchronous memory transfers.
Reviewed By: jdoerfert, ye-luo
Differential Revision: https://reviews.llvm.org/D139208
Summary:
We use the dynamic HSA file to forward declare needed definitions from
the HSA runtime if not present at build time. These definitions were not
included so using them caused problems on systems without it if used.
Just add them.
This commit adds the AMDGPU NextGen plugin inheriting from PluginInterface's classes.
It also implements the asynchronous behavior in the plugin operations: kernel launches
and memory transfers. To this end, it implements the concept of streams of asynchronous
operations. The streams are implemented using the HSA signals to define input and output
dependencies between asynchronous operations.
Missing features:
- Retrieve the maximum number of threads per group that a kernel can run. This requires
reading the image.
- Implement __tgt_rtl_sync_event, not used on the libomptarget side.
Differential Revision: https://reviews.llvm.org/D138389
This patch prepares the PluginInterface for the new AMDGPU NextGen plugin. The original and the
NextGen plugin will share some structures and functionalities. We use this header for defining
them and avoiding code duplication.
Differential Revision: https://reviews.llvm.org/D139792
The plugins all define the same interface symbols. This is generally not
a problem when calling the plugin directly from the dynamic library's
handle. However, when calling from within the plugin itself it is
possible for another plugin's symbols to preempt the symbols. This was
observed with the `__tgt_rtl_is_valid_binary` call in the
`__tgt_rtl_is_valid_binary_info` function being mapped to the x86_64
plugin.
This patch changes the default visibility to `protected` intead. This
visibility ensures that these symbols are all externally visible from
the plugin, but ensures their definitions are fixed within the shared
library. Having protected visiiblity makes such symbol preemption
impossible.
Reviewed By: tianshilei1992
Differential Revision: https://reviews.llvm.org/D136365
This reverts commit 096f93e73dc3f88636cdcb57515e3732385b452d.
Revert "[Libomptarget] Make the plugins ingore undefined exported symbols"
This reverts commit 3f62314c235bd2475c8e2b5b874b2932a444e823.
Revert "[LLD] Enable --no-undefined-version by default."
This reverts commit 7ec8b0d162e354c703f5390784287054601f9c69.
Three commits are reverted because of the current omp build fail
with GNU ld. See discussion here: https://reviews.llvm.org/rG096f93e73dc3
Summary:
Recent changes made the default behaviour to error when given an
undefined symbol in a version script. A previous patch fixed this for
`libomptarget` by removing the single undefined symbol. However, the
plguins are expected to only define a subset of the availible functions
so we shouldn't treat it as an error. This patch updates the build flags
to work appropriately.
Add OpenMP device runtime build support for the gfx1100, gfx1101,
gfx1102, and gfx1103 targets.
Differential Revision: https://reviews.llvm.org/D134465
These patches exposed a lot of problems in the AMD toolchain. Rather
than keep it broken we should revert it to its old semi-functional
state. This will prevent us from using device destructors but should
remove some new bugs. In the future this interface should be changed
once these problems are addressed more correctly.
This reverts commit ed0f21811544320f829124efbb6a38ee12eb9155.
This reverts commit 2b7203a35972e98b8521f92d2791043dc539ae88.
Fixes#57536
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D133997
Previous support for device memory allocators used a single free
routine and did not provide the original kind of the allocation. This is
problematic as some of these memory types required different handling.
Previously this was worked around using a map in runtime to record the
original kind of each pointer. Instead, this patch introduces new free
routines similar to the existing allocation routines. This allows us to
avoid a map traversal every time we free a device pointer.
The only interfaces defined by the standard are `omp_target_alloc` and
`omp_target_free`, these do not take a kind as `omp_alloc` does. The
standard dictates the following:
"The omp_target_alloc routine returns a device pointer that references
the device address of a storage location of size bytes. The storage
location is dynamically allocated in the device data environment of the
device specified by device_num."
Which suggests that these routines only allocate the default device
memory for the kind. So this has been changed to reflect this. This
change is somewhat breaking if users were using `omp_target_free` as
previously shown in the tests.
Reviewed By: JonChesterfield, tianshilei1992
Differential Revision: https://reviews.llvm.org/D133053
Summary:
The AMDGPU and CUDA plugins now relies on the Object and Support
libraries. This patch adds them explicitly rather than hoping that they
share the symbols loaded from the standard `libomptarget`.
This patch replaces the dependency on `libelf` with LLVM's ELF support.
With this patch the user no-longer needs to have `libelf` on their
system to build and configure OpenMP offloading. The replacement is
mostly mechanical, with the exception of the hash table support which
was added in D131309.
Depends on D131309
Reviewed By: JonChesterfield, saiislam
Differential Revision: https://reviews.llvm.org/D131401
The `SHT_HASH` sections in an ELF are used to look up a symbol in the
symbol table using a symbol's name. This is done by obtaining the
`SHT_HASH` section and using its `sh_link` attribute to access the
associated symbol table, from which we can access the string table
containing the associated name. We can then search for the symbol using
the hash of the name and the buckets and chains in the hash table
itself
This patch adds utility functions that allow us to look up a symbol in
an ELF file by name. It will first attempt to look through the hash
tables, and then search the section tables manually if failed. This
allows us to pull out constants necessary for setting up offloading
without first loading the object.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D131309
This patch adds support for the device memory type, this is currently equivalent
to the default type so it should be treated as the same.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D133128
The cuda plugin maps TARGET_ALLOC_HOST onto cuMemAllocHost
which is page locked host memory. Fine grain HSA memory is not
necessarily page locked but has the same read/write from host or
device semantics.
The cuda plugin does this per-gpu and this patch makes it accessible
from any gpu, but it can be locked down to match the cuda behaviour
if preferred.
Enabling tests requires an equivalent to
// RUN: %libomptarget-compile-run-and-check-nvptx64-nvidia-cuda
for amdgpu which doesn't seem to be in use yet.
Reviewed By: jhuber6
Differential Revision: https://reviews.llvm.org/D132660
if(TARGET amdgpu-arch) doesn't work when ENABLE_LLVM_PROJECTS=openmp because openmp subdirectory is processed before clang subdirectory. Adopt the same logic of enabling tests like the CUDA plugin.
Differential Revision: https://reviews.llvm.org/D132579
This patch replaces uses of `dlopen` and `dlsym` with LLVM's support
with `loadPermanentLibrary` and `getSymbolAddress`. This allows us to
remove the explicit dependency on the `dl` libraries in the CMake. This
removes another explicit dependency and solves an issue encountered
while building on Windows platforms. The one downside to this is that
the LLVM library does not currently support `dlclose` functionality, but
this could be added in the future.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D131507
A previous patch made the destruction of the HSA plugin more
deterministic. However, there were still other global values that are not
handled this way. When attempting to call a destructor kernel, the
device would have already been uninitialized and we could not find the
appropriate kernel to call. This is because they were stored in global
containers that had their destructors called already. Merges this global
state into the rest of the info state by putting those global values
inside of the global pointer already allocated and deallocated by the
constructor and destructor. This should allow the AMDGPU plugin to
correctly identify the destructors if we were to run them.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D131011
Moves DeviceInfo global to heap to accurately control lifetime.
Moves calls from libomptarget to deinit_plugin later, plugins need to stay
alive until very shortly before libomptarget is destructed.
Leaving the deinit_plugin calls where initially inserted hits use after
free from the dynamic_module.c offloading test (verified with valgrind
that the new location is sound with respect to this)
Reviewed By: tianshilei1992
Differential Revision: https://reviews.llvm.org/D130714
Will allow plugins to migrate away from using global variables to
manage lifetime, which will fix a segfault discovered in relation to D127432
Reviewed By: jhuber6
Differential Revision: https://reviews.llvm.org/D130712
This patch extends the is_valid_binary routine to also check if the
binary's target ID matches the one parsed from the system's runtime
environment.
This should allow us to only use the binary whose compute capability
matches, allowing us to support basic multi-architecture binaries for
AMDGPU.
It also handles compatibility testing of target IDs of the image and
the enviornment.
Depends on D127432
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D127769
This patch extends the is_valid_binary routine to also check if the
binary's target ID matches the one parsed from the system's runtime
environment.
This should allow us to only use the binary whose compute capability
matches, allowing us to support basic multi-architecture binaries for
AMDGPU.
It also handles compatibility testing of target IDs of the image and
the enviornment.
Depends on D127432
Differential Revision: https://reviews.llvm.org/D127769
Previously we made `libomptarget` link as an LLVM library so we have
access to the LLVM core libraries. After the initial patch stuck we can
now apply the same changes to the plugins. This will allow us to use
LLVM in all of `libomptarget` when we have uses for them. In the future
this should allow us to remove the dependencies on `libelf`, `libffi`,
and `dl`.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D130262
