The calls to atmi_memcpy presently determine the direction of copy (host to
device or device to host) by storing pointers in a map during malloc and
looking up the pointers during memcpy. As each call site already knows the
direction, this stash+lookup can be eliminated.
This NFC will be followed by a functional one that deletes those map lookups.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D89776
Change-Id: I1d9089bc1e56b3a9a30e334735fa07dee1f84990
[libomptarget][amdgcn] Implement missing symbols in deviceRTL
Malloc, wtime are stubs. Malloc needs a hostrpc implementation which is
a work in progress, wtime needs some experimentation to find out the
multiplier to get a time in seconds as documentation is scarce.
Reviewed By: ronlieb
Differential Revision: https://reviews.llvm.org/D89725
This patch fixes a problem whereby the pointee object of a PTR_AND_OBJ entry with a `map(to)` motion clause can be overwritten on the device even if its reference counter is >=1.
Currently, we check the reference counter of the parent struct in order to determine whether the motion clause should be respected, but since the pointee object is not part of the struct, it's got its own reference counter which should be used to enqueue the copy or discard it.
The same behavior has already been implemented in targetDataEnd (omptarget.cpp:539-540), but we somehow missed doing the same in targetDataBegin.
Differential Revision: https://reviews.llvm.org/D89597
[openmp][libomptarget] Include header from LLVM source tree
The change is to the amdgpu plugin so is unlikely to break anything.
The point of contention is whether libomptarget can depend on LLVM.
A community discussion was cautiously not opposed yesterday.
This introduces a compile time dependency on the LLVM source tree, in this case
expressed as skipping the building of the plugin if LLVM_MAIN_INCLUDE_DIR is not
set. One the source files will #include llvm/Frontend/OpenMP/OMPGridValues.h,
instead of copy&pasting the numbers across.
For users that download the monorepo, the llvm tree is already on disk. This will
inconvenience users who download only the openmp source as a tar, as they would
now also have to download (at least a file or two) from the llvm source, if they want
to build the parts of the openmp project that (post this patch) depend on llvm.
There was interest expressed in going further - using llvm tools as part of
building libomp, or linking against llvm libraries. That seems less clear cut
an improvement and worthy of further discussion. This patch seeks only to change
policy to support openmp depending on the llvm source tree. Including in the
other direction, or using libraries / tools etc, are purposefully out of scope.
Reviewers are a best guess at interested parties, please feel free to add others
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D87841
[libomptarget][amdgcn] Implement partial barrier
named_sync is used to coordinate non-spmd kernels. This uses bar.sync on nvptx.
There is no corresponding ISA support on amdgcn, so this is implemented using
shared memory, one word initialized to zero.
Each wave increments the variable by one. Whichever wave is last is responsible
for resetting the variable to zero, at which point it and the others continue.
The race condition on a wave reaching the barrier before another wave has
noticed that it has been released is handled with a generation counter, packed
into the same word.
Uses a shared variable that is not needed on nvptx. Introduces a new hook,
kmpc_impl_target_init, to allow different targets to do extra initialization.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D88602
Summary:
This patch changes the CMake files for Clang and Libomptarget to query the
system for its supported CUDA architecture. This makes it much easier for the
user to build optimal code without needing to set the flags manually. This
relies on the now deprecated FindCUDA method in CMake, but full support for
architecture detection is only availible in CMake >3.18
Reviewers: jdoerfert ye-luo
Subscribers: cfe-commits guansong mgorny openmp-commits sstefan1 yaxunl
Tags: #clang #OpenMP
Differential Revision: https://reviews.llvm.org/D87946
The test disables suppression and therefore sometimes triggers a know false
positive in the openmp runtime. The test should only verify that the env
var is handles as expected.
The worker thread can start execution of the task before creation of the second task
Fixes the spurious failure reported in https://reviews.llvm.org/D61657
Currently, the parser used to tokenize the TSAN_OPTIONS in libomp uses
only spaces as separators, even though TSAN in compiler-rt supports
other separators like ':' or ','.
CTest uses ':' to separate sanitizer options by default.
The documentation for other sanitizers mentions ':' as separator,
but TSAN only lists spaces, which is probably where this mismatch originated.
Patch provided by upsj
Differential Revision: https://reviews.llvm.org/D87144
This patch updates the expected results for the GOMP interface patches: D87267, D87269, and D87271.
The taskwait-depend test is changed to really use taskwait-depend and copied to an task_if0-depend test.
To pass the tests, the handling of the return address was fixed.
Differential Revision: https://reviews.llvm.org/D87680
OpenMP 5.1 defines omp_get_initial_device to return the same value as omp_get_num_devices.
Since this change is also 5.0 compliant, no versioning is needed.
Differential Revision: https://reviews.llvm.org/D88149
[nfc][libomptarget] Drop parameter to named_sync
named_sync has one call site (in sync.cu) where it always passed L1_BARRIER.
Folding this into the call site and dropping the macro is a simplification.
amdgpu doesn't have ptx' bar.sync instruction. A correct implementation of
__kmpc_impl_named_sync in terms of shared memory is much easier if it can
assume that the barrier argument is this constant. Said implementation is left
for a second patch.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D88474
Summary:
Adding a missing directory needed for generating Sphinx documentation without
errors. Directory current contains a placeholder image just to populate the
directory.
It allows customizing MAX_SM for non-flagship GPU and reduces graphic memory usage.
In addition, so far the size is hard-coded up to __CUDA_ARCH__ 700 and is already a hassle for 800.
Introduce MAX_SM for 800 and protect future arch
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D88185
This change introduces the GOMP_taskwait_depend() function. It implements
the OpenMP 5.0 feature of #pragma omp taskwait with depend() clause by
wrapping around __kmpc_omp_wait_deps().
Differential Revision: https://reviews.llvm.org/D87269
Encapsulate GOMP task dependencies in separate class and introduce the
new mutexinoutset dependency type. This separate class allows
future GOMP task APIs easier access to the task dependency functionality
and better ability to propagate new dependency types to all existing GOMP
task APIs which use task dependencies.
Differential Revision: https://reviews.llvm.org/D87267
Implement GOMP_teams_reg() function which enables GOMP support of the
standalone teams construct. The GOMP_parallel* functions were modified
to call __kmp_fork_call() unconditionally so that the teams-specific
code could be reused within __kmp_fork_call() instead of reproduced
inside the GOMP_* functions.
Differential Revision: https://reviews.llvm.org/D87167
If an error code can not be recognized by cuGetErrorString, errStr remains null and causes crashing at DP() printing.
Protect this case.
Reviewed By: jhuber6, tianshilei1992
Differential Revision: https://reviews.llvm.org/D87980
Summary:
Adding support for generated html documentation for OpenMP. Changing
Cmake files to build the documentation and adding the base templates for
future documentation to be added.
Reviewers: jdoerfert
Subscribers: aaron.ballman arphaman guansong mgorny openmp-commits sstefan1 yaxunl
Tags: #OpenMP
Differential Revision: https://reviews.llvm.org/D87797
Summary:
This patch adds additonal support for priting infromation from Libomptarget for
already existing maps and printing the final data mapped on the device at
device destruction.
Reviewers: jdoerfort gkistanova
Subscribers: guansong openmp-commits sstefan1 yaxunl
Tags: #OpenMP
Differential Revision: https://reviews.llvm.org/D87722
Summary:
This patch starts adding support for adding information dumps to libomptarget
and rtl plugins. The information printing is controlled by the
LIBOMPTARGET_INFO environment variable introduced in D86483. The goal of this
patch is to provide the user with additional information about the device
during kernel execution and providing the user with information dumps in the
case of failure. This patch added the ability to dump the pointer mapping table
as well as printing the number of blocks and threads in the cuda RTL.
Reviewers: jdoerfort gkistanova ye-luo
Subscribers: guansong openmp-commits sstefan1 yaxunl ye-luo
Tags: #OpenMP
Differential Revision: https://reviews.llvm.org/D87165
The size of worker_rootS should have been DS_Max_Warp_Number.
This reduces memory usage by deviceRTL on AMDGPU from around 2.3GB
to around 770MB.
Reviewed By: JonChesterfield, jdoerfert
Differential Revision: https://reviews.llvm.org/D87084
Summary:
This patch consolidates the error handling and messaging routines to a single
file omptargetmessage. The goal is to simplify the error handling interface
prior to adding more error handling support
Reviewers: jdoerfert grokos ABataev AndreyChurbanov ronlieb JonChesterfield ye-luo tianshilei1992
Subscribers: danielkiss guansong jvesely kerbowa nhaehnle openmp-commits sstefan1 yaxunl
PrivateArgumentManager shall immediately allocate firstprivates if they
are bases for the next parameters and the next paramaters rely on the
fact that the base musst be allocated already.
Differential Revision: https://reviews.llvm.org/D86781
The test command in `private_mapping.c` was set to expect failure by mistake. It is fixed in this patch.
Reviewed By: ABataev
Differential Revision: https://reviews.llvm.org/D86758
Summary:
This patch changes the libomptarget runtime to always emit debug messages that
occur before offloading failure. The goal is to provide users with information
about why their application failed in the target region rather than a single
failure message. This is only done in regions that precede offloading failure
so this should not impact runtime performance. if the debug environment
variable is set then the message is forwarded to the debug output as usual.
A new environment variable was added for future use but does nothing in this
current patch. LIBOMPTARGET_INFO will be used to report runtime information to
the user if requrested, such as grid size, SPMD usage, or data mapping. It will
take an integer indicating the level of information verbosity and a value of 0
will disable it.
Reviewers: jdoerfort
Subscribers: guansong sstefan1 yaxunl ye-luo
Tags: #OpenMP
Differential Revision: https://reviews.llvm.org/D86483
In this patch, we pack all small first-private arguments, allocate and transfer them all at once to reduce the number of data transfer which is very expensive.
Let's take the test case as example.
```
int main() {
int data1[3] = {1}, data2[3] = {2}, data3[3] = {3};
int sum[16] = {0};
#pragma omp target teams distribute parallel for map(tofrom: sum) firstprivate(data1, data2, data3)
for (int i = 0; i < 16; ++i) {
for (int j = 0; j < 3; ++j) {
sum[i] += data1[j];
sum[i] += data2[j];
sum[i] += data3[j];
}
}
}
```
Here `data1`, `data2`, and `data3` are three first-private arguments of the target region. In the previous `libomptarget`, it called data allocation and data transfer three times, each of which allocated and transferred 12 bytes. With this patch, it only calls allocation and transfer once. The size is `(12+4)*3=48` where 12 is the size of each array and 4 is the padding to keep the address aligned with 8. It is implemented in this way:
1. First collect all information for those *first*-private arguments. _private_ arguments are not the case because private arguments don't need to be mapped to target device. It just needs a data allocation. With the patch for memory manager, the data allocation could be very cheap, especially for the small size. For each qualified argument, push a place holder pointer `nullptr` to the `vector` for kernel arguments, and we will update them later.
2. After we have all information, create a buffer that can accommodate all arguments plus their paddings. Copy the arguments to the buffer at the right place, i.e. aligned address.
3. Allocate a target memory with the same size as the host buffer, transfer the host buffer to target device, and finally update all place holder pointers in the arguments `vector`.
The reason we only consider small arguments is, the data transfer is asynchronous. Therefore, for the large argument, we could continue to do things on the host side meanwhile, hopefully, the data is also being transferred. The "small" is defined by that the argument size is less than a predefined value. Currently it is 1024. I'm not sure whether it is a good one, and that is an open question. Another question is, do we need to make it configurable via an environment variable?
Reviewed By: ye-luo
Differential Revision: https://reviews.llvm.org/D86307
Instead of copying and pasting the same `#ifdef` expressions in multiple
places, define a type and a pair of macros in `kmp_os.h`, to handle
whether `va_list` is pointer-like or not:
* `kmp_va_list` is the type to use for `__kmp_fork_call()`
* `kmp_va_deref()` dereferences a `va_list`, if necessary
* `kmp_va_addr_of()` takes the address of a `va_list`, if necessary
Also add FreeBSD to the list of OSes that has a non pointer-like
va_list. This can now be easily extended to other OSes too.
Reviewed By: AndreyChurbanov
Differential Revision: https://reviews.llvm.org/D86397
Target memory manager is introduced in this patch which aims to manage target
memory such that they will not be freed immediately when they are not used
because the overhead of memory allocation and free is very large. For CUDA
device, cuMemFree even blocks the context switch on device which affects
concurrent kernel execution.
The memory manager can be taken as a memory pool. It divides the pool into
multiple buckets according to the size such that memory allocation/free
distributed to different buckets will not affect each other.
In this version, we use the exact-equality policy to find a free buffer. This
is an open question: will best-fit work better here? IMO, best-fit is not good
for target memory management because computation on GPU usually requires GBs of
data. Best-fit might lead to a serious waste. For example, there is a free
buffer of size 1960MB, and now we need a buffer of size 1200MB. If best-fit,
the free buffer will be returned, leading to a 760MB waste.
The allocation will happen when there is no free memory left, and the memory
free on device will take place in the following two cases:
1. The program ends. Obviously. However, there is a little problem that plugin
library is destroyed before the memory manager is destroyed, leading to a fact
that the call to target plugin will not succeed.
2. Device is out of memory when we request a new memory. The manager will walk
through all free buffers from the bucket with largest base size, pick up one
buffer, free it, and try to allocate immediately. If it succeeds, it will
return right away rather than freeing all buffers in free list.
Update:
A threshold (8KB by default) is set such that users could control what size of memory
will be managed by the manager. It can also be configured by an environment variable
`LIBOMPTARGET_MEMORY_MANAGER_THRESHOLD`.
Reviewed By: jdoerfert, ye-luo, JonChesterfield
Differential Revision: https://reviews.llvm.org/D81054
This patch contains the following changes:
1. Renamed the function `DeviceTy::data_exchange` to `DeviceTy::dataExchange`;
2. Changed the second argument `DeviceTy DstDev` to `DeviceTy &DstDev`;
3. Renamed the last argument.
Reviewed By: ye-luo
Differential Revision: https://reviews.llvm.org/D86238
Instead of calling `cuFuncGetAttribute` with
`CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK` for every kernel invocation,
we can do it for the first one and cache the result as part of the
`KernelInfo` struct. The only functional change is that we now expect
`cuFuncGetAttribute` to succeed and otherwise propagate the error.
Ignoring any error seems like a slippery slope...
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D86038
[libomptarget] Implement host plugin for amdgpu
Replacement for D71384. Primary difference is inlining the dependency on atmi
followed by extensive simplification and bugfixes. This is the latest version
from https://github.com/ROCm-Developer-Tools/amd-llvm-project/tree/aomp12 with
minor patches and a rename from hsa to amdgpu, on the basis that this can't be
used by other implementations of hsa without additional work.
This will not build unless the ROCM_DIR variable is passed so won't break other
builds. That variable is used to locate two amdgpu specific libraries that ship
as part of rocm:
libhsakmt at https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface
libhsa-runtime64 at https://github.com/RadeonOpenCompute/ROCR-Runtime
These libraries build from source. The build scripts in those repos are for
shared libraries, but can be adapted to statically link both into this plugin.
There are caveats.
- This works well enough to run various tests and benchmarks, and will be used
to support the current clang bring up
- It is adequately thread safe for the above but there will be races remaining
- It is not stylistically correct for llvm, though has had clang-format run
- It has suboptimal memory management and locking strategies
- The debug printing / error handling is inconsistent
I would like to contribute this pretty much as-is and then improve it in-tree.
This would be advantagous because the aomp12 branch that was in use for fixing
this codebase has just been joined with the amd internal rocm dev process.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D85742
Starting with 787eb0c637 I got spurious segmentation faults for some testcases. I could nail it down to `brel` trying to release the "memory" of the node allocated on the stack of __kmpc_omp_wait_deps. With this patch, you will see the assertion triggering for some of the tests in the test suite.
My proposed solution for the issue is to just patch __kmpc_omp_wait_deps:
```
__kmp_init_node(&node);
- node.dn.on_stack = 1;
+ // the stack owns the node
+ __kmp_node_ref(&node);
```
What do you think?
Reviewed By: AndreyChurbanov
Differential Revision: https://reviews.llvm.org/D84472
Pushpinder Singh