Summary:
This patch reworks the CMake handling for building plugins. All this
does is pull a lot of shared and common logic into a single helper
function.
This also simplifies the OMPT libraries from being built separately
instead of just added.
This patch implements `affinity` for AIX, which is quite different from
platforms such as Linux.
- Setting CPU affinity through masks and related functions are not
supported. System call `bindprocessor()` is used to bind a thread to one
CPU per call.
- There are no system routines to get the affinity info of a thread. The
implementation of `get_system_affinity()` for AIX gets the mask of all
available CPUs, to be used as the full mask only.
- Topology is not available from the file system. It is obtained through
system SRAD (Scheduler Resource Allocation Domain).
This patch has run through the libomp LIT tests successfully with
`affinity` enabled.
This PR refactors bounds offsetting by combining the two differing
implementations (one applying to initial derived type member map
implementation for descriptors and the other for regular arrays,
effectively allocatable array vs regular array in fortran) now that it's
a little simpler to do.
The PR also moves the utilization of createAlteredByCaptureMap into
genMapInfoOp, where it will be correctly applied to all MapInfoData,
appropriately offsetting and altering Pointer data set in the kernel
argument structure on the host. This primarily means bounds offsets will
now correctly apply to enter/exit/update map clauses as opposed to just
the Target directive that is currently the case. A few fortran runtime
tests have been added to verify this new behavior.
This PR depends on: https://github.com/llvm/llvm-project/pull/84328 and
is an extraction of the larger derived type member map PR stack (so a
requirement for it to land).
Commit a7d5f73a03c81cab8df64dbd099e8acb40f5dfe1 introduced an
error in a target_compile_definitions on the SystemZ, causing
the build to break. Fixed by adding the missing "PRIVATE".
Summary:
All of these CPU targets use the same underlying implementation. We
should consolidate them into a single target to make it easier to update
this to a static library based approach. I have decided to call this the
'host' target so it can be given a single name. We still only build
these if the system processor matches and we are on Linux.
This patch updates the construction of packet headers to replace the
usage of ACQUIRE/RELEASE with SCACQUIRE/SCRELEASE which is now
recommended.
The patch also ensures consistency across kernel dispatches.
This PR changes the build system to use use the sources for the module
`omp_lib` and the `omp_lib.h` include file from the `openmp` runtime
project and not from a separate copy of these files. This will greatly
reduce potential for inconsistencies when adding features to the OpenMP
runtime implementation.
When the OpenMP subproject is not configured, this PR also disables the
corresponding LIT tests with a "REQUIRES" directive at the beginning of
the OpenMP test files.
---------
Co-authored-by: Valentin Clement (バレンタイン クレメン) <clementval@gmail.com>
A kernel implicit parameter (dyn_ptr) was introduced some time back.
This patch increments the kernel args version for a compiler supporting
dyn_ptr. The version will be used by the runtime to determine whether
the implicit parameter is generated by the compiler. The versioning is
required to support use cases where code generated by an older compiler
is linked with a newer runtime.
If approved, this patch should be backported to release 18.
This reverts commit cd8843f87af2f04a85dda12b37738596cbf4cd5e.
Originally disabled to try to unstick the AMD build bot, didn't make a
difference after a week so it goes back in.
This patch enables the BodyCodeGen callback to still trigger for the
TargetData nested region during the device pass. There maybe Target code
nested within the TargetData region for which this is required.
Also add tests for the same.
This adds an API call ompx_dump_mapping_tables.
This allows users to debug the mapping tables and can be especially
useful for unified shared memory applications to check if the code
behaves in the way it should. The implementation reuses code already
present to dump mapping tables (in a debug setting).
---------
Co-authored-by: Joseph Huber <huberjn@outlook.com>
When running OpenMP offloading application with LIBOMPTARGET_INFO=-1,
the addresses of the Copying data from **device** to **host**, the
address are swap.
As an example, Currently the address would be
```
omptarget device 0 info: Mapping exists with HstPtrBegin=0x00007ffddaf0fb90, TgtPtrBegin=0x00007fb385404000, Size=8000, DynRefCount=0 (decremented, delayed deletion), HoldRefCount=0
omptarget device 0 info: Copying data from device to host, TgtPtr=0x00007ffddaf0fb90, HstPtr=0x00007fb385404000, Size=8000, Name=d
```
And it should be
```
omptarget device 0 info: Copying data from device to host, TgtPtr=0x00007fb385404000, HstPtr=0x00007ffddaf0fb90, Size=8000, Name=d
```
---------
Co-authored-by: fel-cab <fel-cab@github.com>
The plugin was not getting built as the build_generic_elf64 macro
assumes the LLVM triple processor name matches the CMake processor name,
which is unfortunately not the case for SystemZ.
Fix this by providing two separate arguments instead.
Actually building the plugin exposed a number of other issues causing
various test failures. Specifically, I've had to add the SystemZ target
to
- CompilerInvocation::ParseLangArgs
- linkDevice in ClangLinuxWrapper.cpp
- OMPContext::OMPContext (to set the device_kind_cpu trait)
- LIBOMPTARGET_ALL_TARGETS in libomptarget/CMakeLists.txt
- a check_plugin_target call in libomptarget/src/CMakeLists.txt
Finally, I've had to set a number of test cases to UNSUPPORTED on
s390x-ibm-linux-gnu; all these tests were already marked as UNSUPPORTED
for x86_64-pc-linux-gnu and aarch64-unknown-linux-gnu and are failing on
s390x for what seem to be the same reason.
In addition, this also requires support for BE ELF files in
plugins-nextgen: https://github.com/llvm/llvm-project/pull/85246
Code in plugins-nextgen reading ELF files is currently hard-coded to
assume a 64-bit little-endian ELF format. Unfortunately, this assumption
is even embedded in the interface between GlobalHandler and Utils/ELF
routines, which use ELF64LE types.
To fix this, I've refactored the interface to use generic types, in
particular by using (a unique_ptr to) ObjectFile instead of
ELF64LEObjectFile, and ELFSymbolRef instead of ELF64LE::Sym.
This allows properly templating over multiple ELF format variants inside
Utils/ELF; specifically, this patch adds support for 64-bit big-endian
ELF files in addition to 64-bit little-endian files.
Code in plugins-nextgen reading ELF files is currently hard-coded to
assume a 64-bit little-endian ELF format. Unfortunately, this assumption
is even embedded in the interface between GlobalHandler and Utils/ELF
routines, which use ELF64LE types.
To fix this, I've refactored the interface to use generic types, in
particular by using (a unique_ptr to) ObjectFile instead of
ELF64LEObjectFile, and ELFSymbolRef instead of ELF64LE::Sym.
This allows properly templating over multiple ELF format variants inside
Utils/ELF; specifically, this patch adds support for 64-bit big-endian
ELF files in addition to 64-bit little-endian files.
When OpenMP is compiled for WebAssembly (see #71297), it invokes a
microtask via a `switch` statement that dispatches to the `void *`
microtask pointer with spelled-out arguments (not varargs). As #83329
points out, however, this can result in a type mismatch when the
indirect call is executed by WebAssembly; WebAssembly expects the called
pointer to have the precise type of the call site. This change fixes the
issue by bringing back the approach in [D142593] of type-casting all the
`switch` arms to the precise type. This fixes#83329.
[D142593]: https://reviews.llvm.org/D142593
Various behavior around creating affinity masks and detecting uniform
topology depends on the topology being sorted.
resort topology after adding processor group layer to ensure that the
updated topology reflects the newly added processor group info.
Observed that the topology was not sorted correctly on high core count
AMD Epyc Genoa (2 sockets, 96 cores, 2 threads) using NUMA (NPS 2+).
Summary:
We are currently taking the lower 5 bites of the thread ID as the warp
ID. This doesn't work in non-1D grids and is also slower than just using
the dedicated hardware register.
MSVC does not define __BYTE_ORDER__ making the check for BigEndian
erroneously evaluate to true and breaking the struct definitions in MSVC
compiled builds correspondingly. The fix adds an additional check for
whether __BYTE_ORDER__ is defined by the compiler to fix these.
---------
Co-authored-by: Vadim Paretsky <b-vadipa@microsoft.com>
This PR adds OMP runtime support for more efficient partitioning of
certain types of collapsed loops that can be used by compilers that
support loop collapsing (i.e. MSVC) to achieve more optimal thread load
balancing.
In particular, this PR addresses double nested upper and lower isosceles
triangular loops of the following types
1. lower triangular 'less_than'
for (int i=0; i<N; i++)
for (int j=0; j<i; j++)
2. lower triangular 'less_than_equal'
for (int i=0; i<N; j++)
for (int j=0; j<=i; j++)
3. upper triangular
for (int i=0; i<N; i++)
for (int j=i; j<N; j++)
Includes tests for the three supported loop types.
---------
Co-authored-by: Vadim Paretsky <b-vadipa@microsoft.com>
As per the OpenMP standard, "If a variable appears in a link clause on a
declare target directive that does not have a device_type clause with
the nohost device-type-description then it is treated as if it had
appeared in a map clause with a map-type of tofrom" is an implicit
mapping rule. Before this change, such variables were mapped as to by
default.
After 3ecd38c8e, the Handler.getELFObjectFile routine is no
longer available. Call ELF64LEObjectFile::create directly,
which should always be suitable for CUDA images.
The plugin was not getting built as the build_generic_elf64 macro
assumes the LLVM triple processor name matches the CMake processor name,
which is unfortunately not the case for SystemZ.
Fix this by providing two separate arguments instead.
Actually building the plugin exposed a number of other issues causing
various test failures. Specifically, I've had to add the SystemZ target
to
- CompilerInvocation::ParseLangArgs
- linkDevice in ClangLinuxWrapper.cpp
- OMPContext::OMPContext (to set the device_kind_cpu trait)
- LIBOMPTARGET_ALL_TARGETS in libomptarget/CMakeLists.txt
- a check_plugin_target call in libomptarget/src/CMakeLists.txt
Finally, I've had to set a number of test cases to UNSUPPORTED on
s390x-ibm-linux-gnu; all these tests were already marked as UNSUPPORTED
for x86_64-pc-linux-gnu and aarch64-unknown-linux-gnu and are failing on
s390x for what seem to be the same reason.
In addition, this also requires support for BE ELF files in
plugins-nextgen: https://github.com/llvm/llvm-project/pull/83976
Code in plugins-nextgen reading ELF files is currently hard-coded to
assume a 64-bit little-endian ELF format. Unfortunately, this assumption
is even embedded in the interface between GlobalHandler and Utils/ELF
routines, which use ELF64LE types.
To fix this, I've refactored the interface to push all ELF specific
types into Utils/ELF. Specifically, this patch removes both the
getSymbol and getSymbolAddress routines and replaces them with a
single findSymbolInImage, which gets a StringRef identifying the
raw object file image as input, and returns a StringRef covering
the data addressed by the symbol (address and size) if found, or
std::nullopt otherwise.
This allows properly templating over multiple ELF format variants inside
Utils/ELF; specifically, this patch adds support for 64-bit big-endian
ELF files in addition to 64-bit little-endian files.
