... and register them with CUDA runtime.
This is needed for commonly used cudaMemcpy*() APIs that use address of
host-side shadow to access their counterparts on device side.
Fixes PR26340
Differential Revision: http://reviews.llvm.org/D17779
llvm-svn: 262498
Summary:
Previously we compiled CUDA device code to PTX assembly and embedded
that asm as text in our host binary. Now we compile to PTX assembly and
then invoke ptxas to assemble the PTX into a cubin file. We gather the
ptx and cubin files for each of our --cuda-gpu-archs and combine them
using fatbinary, and then embed that into the host binary.
Adds two new command-line flags, -Xcuda_ptxas and -Xcuda_fatbinary,
which pass args down to the external tools.
Reviewers: tra, echristo
Subscribers: cfe-commits, jhen
Differential Revision: http://reviews.llvm.org/D16082
llvm-svn: 257809
Introduce an Address type to bundle a pointer value with an
alignment. Introduce APIs on CGBuilderTy to work with Address
values. Change core APIs on CGF/CGM to traffic in Address where
appropriate. Require alignments to be non-zero. Update a ton
of code to compute and propagate alignment information.
As part of this, I've promoted CGBuiltin's EmitPointerWithAlignment
helper function to CGF and made use of it in a number of places in
the expression emitter.
The end result is that we should now be significantly more correct
when performing operations on objects that are locally known to
be under-aligned. Since alignment is not reliably tracked in the
type system, there are inherent limits to this, but at least we
are no longer confused by standard operations like derived-to-base
conversions and array-to-pointer decay. I've also fixed a large
number of bugs where we were applying the complete-object alignment
to a pointer instead of the non-virtual alignment, although most of
these were hidden by the very conservative approach we took with
member alignment.
Also, because IRGen now reliably asserts on zero alignments, we
should no longer be subject to an absurd but frustrating recurring
bug where an incomplete type would report a zero alignment and then
we'd naively do a alignmentAtOffset on it and emit code using an
alignment equal to the largest power-of-two factor of the offset.
We should also now be emitting much more aggressive alignment
attributes in the presence of over-alignment. In particular,
field access now uses alignmentAtOffset instead of min.
Several times in this patch, I had to change the existing
code-generation pattern in order to more effectively use
the Address APIs. For the most part, this seems to be a strict
improvement, like doing pointer arithmetic with GEPs instead of
ptrtoint. That said, I've tried very hard to not change semantics,
but it is likely that I've failed in a few places, for which I
apologize.
ABIArgInfo now always carries the assumed alignment of indirect and
indirect byval arguments. In order to cut down on what was already
a dauntingly large patch, I changed the code to never set align
attributes in the IR on non-byval indirect arguments. That is,
we still generate code which assumes that indirect arguments have
the given alignment, but we don't express this information to the
backend except where it's semantically required (i.e. on byvals).
This is likely a minor regression for those targets that did provide
this information, but it'll be trivial to add it back in a later
patch.
I partially punted on applying this work to CGBuiltin. Please
do not add more uses of the CreateDefaultAligned{Load,Store}
APIs; they will be going away eventually.
llvm-svn: 246985
The patch is generated using this command:
$ tools/extra/clang-tidy/tool/run-clang-tidy.py -fix \
-checks=-*,llvm-namespace-comment -header-filter='llvm/.*|clang/.*' \
work/llvm/tools/clang
To reduce churn, not touching namespaces spanning less than 10 lines.
llvm-svn: 240270
- added -fcuda-include-gpubinary option to incorporate results of
device-side compilation into host-side one.
- generate code to register GPU binaries and associated kernels
with CUDA runtime and clean-up on exit.
- added test case for init/deinit code generation.
Differential Revision: http://reviews.llvm.org/D9507
llvm-svn: 236765
calls and declarations.
LLVM has a default CC determined by the target triple. This is
not always the actual default CC for the ABI we've been asked to
target, and so we sometimes find ourselves annotating all user
functions with an explicit calling convention. Since these
calling conventions usually agree for the simple set of argument
types passed to most runtime functions, using the LLVM-default CC
in principle has no effect. However, the LLVM optimizer goes
into histrionics if it sees this kind of formal CC mismatch,
since it has no concept of CC compatibility. Therefore, if this
module happens to define the "runtime" function, or got LTO'ed
with such a definition, we can miscompile; so it's quite
important to get this right.
Defining runtime functions locally is quite common in embedded
applications.
llvm-svn: 176286
uncovered.
This required manually correcting all of the incorrect main-module
headers I could find, and running the new llvm/utils/sort_includes.py
script over the files.
I also manually added quite a few missing headers that were uncovered by
shuffling the order or moving headers up to be main-module-headers.
llvm-svn: 169237
Artem Belevich