When pointers are passed within aggregates, we sometimes end up with IR that
loads them as integers and the converts them back to pointers. Typically it's
due to a memcpy or SROA. E.g. https://godbolt.org/z/xM3n5daaa
Normally we treat all pointers passed to a CUDA kernel as global pointers and
the same treatment should be applied to the pointers we load/store as integers.
Differential Revision: https://reviews.llvm.org/D142664
Fixes https://github.com/llvm/llvm-project/issues/46954
The assumption that generic pointers passed to a CUDA kernel is CUDA-specific
and should not be applied to non-CUDA compilations. Addrspacecasts to global AS
and back should never be applied to AS-specific pointers.
In order to make tests actually do the testing for non-CUDA compilation, we need
to get TargetMachine from the TargetPassConfig, instead of passing it explicitly
as a pass constructor argument.
Differential Revision: https://reviews.llvm.org/D142581
ptxas is a proprietary compiler from Nvidia that can compile PTX to
machine code (SASS). It has a lot of diagnostics to catch errors
in PTX, which can be used to verify PTX output from llc.
Set -DPXTAS_EXECUTABLE=/path/to/ptxas CMake option to enable it.
If this option is not set, then ptxas is substituted to true which
effectively disables all ptxas RUN lines.
LLVM_PTXAS_EXECUTABLE environment variable takes precedence over
the CMake option, and allows to override ptxas executable that is used for LIT
without complete re-configuration.
Differential Revision: https://reviews.llvm.org/D121727
Avoid making a temporary copy of byval argument if all accesses are loads and
therefore the pointer to the parameter can not escape.
This avoids excessive global memory accesses when each kernel makes its own
copy.
Differential revision: https://reviews.llvm.org/D98469
NVPTXLowerArgs works as follows.
* Create a regular alloca with alignment identical to arg.
* Copy arg from param space (and ASC'ing it from generic AS first) to
the alloca (it's still in generic AS).
* Replace loads of arg with loads of alloca.
The bug here is that we did not preserve the arg's alignment when
loading from the alloca.
The impact of this bug is that sometimes param loads would be lowered as
a series of u8 loads, because we're incorrectly assuming everything has
alignment 1.
Differential Revision: https://reviews.llvm.org/D89404
