| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
| |
Reviewer: tstellar
Differential Revision: https://reviews.llvm.org/D69966
|
|
|
|
|
|
|
|
| |
Run the file through target specific preprocessing stage.
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewer: Aaron Watry
llvm-svn: 347664
|
|
|
|
|
|
| |
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewer: Aaron Watry
llvm-svn: 347663
|
|
|
|
|
|
| |
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-By: Aaron Watry <awatry@gmail.com>
llvm-svn: 346085
|
|
|
|
|
|
|
|
| |
v2: Fix reference to Vega12/20 enabling commit
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewer: Aaron Watry
llvm-svn: 342341
|
|
|
|
|
|
| |
Sort amdgcn-- and amdgcn--amdhsa in a consistent way.
llvm-svn: 319017
|
|
|
|
|
|
| |
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 315018
|
|
|
|
|
|
| |
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Acked-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 314543
|
|
|
|
|
|
|
|
|
|
|
|
| |
Broken since r314111
V2: pointed out by Jan Vesely
- Use format() instead of % formating
Patch-by: Pavel Ondračka <pavel.ondracka@gmail.com>
Signed-off-by: Pavel Ondračka <pavel.ondracka@gmail.com>
Reviewed-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 314261
|
|
|
|
|
|
|
|
| |
Just add the SOURCE_X.Y list to the list of sources if X.Y is the current llvm version.
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <tstellar@redhat.com>
llvm-svn: 312837
|
|
|
|
|
|
|
|
|
|
| |
I can't reproduce the error that made me add this.
Reported-by: Kim Gräsman <kim.grasman@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Kim Gräsman <kim.grasman@gmail.com>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 310968
|
|
|
|
|
|
|
|
|
|
| |
mostly prints and exceptions.
Few behavioral changes are documented in the text
Generated Makefile is identical between python2 and python3
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 309820
|
|
|
|
| |
llvm-svn: 286634
|
|
|
|
| |
llvm-svn: 281793
|
|
|
|
| |
llvm-svn: 280121
|
|
|
|
|
|
| |
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 273044
|
|
|
|
|
|
|
|
| |
This is now handled by clang
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 273043
|
|
|
|
|
|
| |
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 273042
|
|
|
|
|
|
| |
Differential Revision: http://reviews.llvm.org/D18284
llvm-svn: 265713
|
|
|
|
|
|
|
|
|
|
|
| |
Most files remain in a common amdgpu directory.
Also switches barriers to to use convergent,
and use llvm.amdgcn.s.barrier.
This now requires 3.9/trunk to build amdgcn.
llvm-svn: 260777
|
|
|
|
|
|
|
|
| |
we require llvm 3.7
reviewer: tstellard
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 260304
|
|
|
|
|
|
|
|
|
| |
Also remove definitions if provided by clang (3.7+)
This halves the size of builtin.opt.{cedar,barts}.bc
reviewer: tstellard
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 260303
|
|
|
|
|
|
|
|
|
|
|
| |
Make cl_khr_fp64 define per-device.
This patch does not change the generated Makefile (for llvm 3.6, 3.7)
v2: Make the device defines per LLVM version, 'all' for all versions
reviewer: tstellard
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 260302
|
|
|
|
| |
llvm-svn: 255663
|
|
|
|
|
|
| |
Patch by: Vedran Mileti
llvm-svn: 255662
|
|
|
|
|
|
|
|
| |
v2: Also remove LLVM 3.6 traces from prepare-builtins.cpp
Patch by: EdB
llvm-svn: 244310
|
|
|
|
|
|
|
|
|
| |
It allows to keep temporary compatibilty with older version.
For exemple, this can be use when change are not to large.
Patch by: EdB
llvm-svn: 236113
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This makes it possible for runtime implementations to disable
subnormal handling at runtime.
When this flag is enabled, decisions about how to handle subnormals
in the library will be controlled by an external variable called
__CLC_SUBNORMAL_DISABLE.
Function implementations should use these new helpers for querying subnormal
support:
__clc_fp16_subnormals_supported();
__clc_fp32_subnormals_supported();
__clc_fp64_subnormals_supported();
In order for the library to link correctly with this feature,
users will be required to either:
1. Insert this variable into the module (if using the LLVM/Clang C++/C APIs).
2. Pass either subnormal_disable.bc or subnormal_use_default.bc to the
linker. These files are distributed with liblclc and installed to
$(installdir). e.g.:
llvm-link -o kernel-out.bc kernel.bc builtins-nosubnormal.bc subnormal_disable.bc
or
llvm-link -o kernel-out.bc kernel.bc builtins-nosubnormal.bc subnormal_use_default.bc
If you do not supply the --enable-runtime-subnormal then the library
behaves the same as it did before this commit.
In addition to these changes, the patch adds helper functions that
should be used when implementing library functions that need
special handling for denormals:
__clc_fp16_subnormals_supported();
__clc_fp32_subnormals_supported();
__clc_fp64_subnormals_supported();
llvm-svn: 235329
|
|
|
|
| |
llvm-svn: 225296
|
|
|
|
|
|
|
|
| |
Some functions are implemented using hand-written LLVM IR, and
LLVM assembly format is allowed to change between versions, so we
should require a specific version of LLVM.
llvm-svn: 225041
|
|
|
|
|
|
|
|
| |
v2: use space instead of '=' to make Mac happy
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Jeroen Ketema <j.ketema@imperial.ac.uk>
llvm-svn: 216922
|
|
|
|
| |
llvm-svn: 216126
|
|
|
|
|
|
|
|
| |
These do not import the code specific to nvidiacl
Patch by: Jeroen Ketema
llvm-svn: 201431
|
|
|
|
|
|
|
|
|
| |
This reverts commit r200413.
This was breaking the build on systems where the python 2.x executable
was called python.
llvm-svn: 201239
|
|
|
|
|
|
|
|
|
| |
This is necessary for building with Ninja because it does not allow
duplicate rule names.
Patch by: Dan Liew
llvm-svn: 200415
|
|
|
|
|
|
|
|
|
|
| |
We use ${DESTDIR} syntax now instead of $(DESTDIR) because that syntax
works both is the shell (at least it does for bash) and for make (at
least it does for GNU Make)
Patch By: Dan Liew
llvm-svn: 200414
|
|
|
|
|
|
| |
Patch by: Dan Liew
llvm-svn: 200413
|
|
|
|
|
| |
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 198168
|
|
|
|
|
| |
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 198167
|
|
|
|
| |
llvm-svn: 195023
|
|
|
|
|
|
|
|
|
|
|
|
| |
The C++ compiler used to build prepare-builtins
may differ from the llvm/clang for which we are
building libclc.
Use 'clang++' as the default compiler.
Patch by: Jeroen Ketema
llvm-svn: 193220
|
|
|
|
|
|
|
| |
This script generates implementations for the entire set of convert_*
functions,
llvm-svn: 192385
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
There are two implementations of nextafter():
1. Using clang's __builtin_nextafter. Clang replaces this builtin with
a call to nextafter which is part of libm. Therefore, this
implementation will only work for targets with an implementation of
libm (e.g. most CPU targets).
2. The other implementation is written in OpenCL C. This function is
known internally as __clc_nextafter and can be used by targets that
don't have access to libm.
llvm-svn: 192383
|
|
|
|
|
|
|
|
|
|
| |
libclc is ABI-agnostic, and $prefix/lib/pkgconfig causes issues
on multilib setups. Using $prefix/share/pkgconfig allows us to reuse
a single libclc build across all system ABIs.
Patch by: Michał Górny
llvm-svn: 190107
|
|
|
|
| |
llvm-svn: 188129
|
|
|
|
| |
llvm-svn: 184991
|
|
|
|
|
|
| |
Patch by: Niels Ole Salscheider
llvm-svn: 184990
|
|
|
|
|
|
|
|
|
|
|
|
| |
Targets can override generic implementations by adding a file called
OVERRIDES in $(TARGET_DIR)/lib and listing the generic implementations
that it wants to override. For example, to override get_group_id() and
get_global_size() you would add these lines to the OVERRIDES file:
workitem/get_group_id.cl
workitem/get_global_size.cl
llvm-svn: 184982
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- First introducing a versioning scheme
- Add --libexecdir, --includedir and --pkgconfigdir and prefill them as well as --prefix
- Build all targets by default
- Create clc.pc and install it in $pkgconfigdir
- Use clang++ instead of c++
- Rename builtins.bc to built_libs/$triple.bc and install them in $libexecdir
- Includes are installed recursively to $includedir
- Finally add $(DESTDIR) for 'make install'
Patch by: Johannes Obermayr
llvm-svn: 184981
|
|
|
|
|
|
|
| |
This includes a get_global_id() implementation and function stubs for
the other workitem and synchronization functions.
llvm-svn: 184975
|