Summary:
Previous patches have made the `rpc.h` header independent of the `libc`
internals. This allows us to include it directly rather than providing
an indirect C API. This patch only does the work to move the header. A
future patch will pull out the `rpc_server` interface and simply replace
it with a single function that handles the opcodes.
Summary:
These functions were deprecated in ROCR 1.3 which was released quite
some time ago. The main functionality that was lost was modifying and
inspecting the code object indepedently of the executable, however we do
all of that custom through our ELF API. This should be within the
versions of other functions we use.
Summary:
Currently, the RPC interface uses a basic opcode to communicate with the
server. This currently is 16 bits. There's no reason for this to be 16
bits, because on the GPU a 32-bit write is the same as a 16-bit write
performance wise.
Additionally, I am now making all the `libc` based opcodes qualified
with the 'c' type, mimiciing how Linux handles `ioctls` all coming from
the same driver. This will make it easier to extend the interface when
it's exported directly.
- Implementation of `tan` for 16-bit floating point inputs scaled by pi.
i.e,. `tanpif16()`
- Implementation of Tanpi in MPFRWrapper for MPFR versions < 4.2
- Exhaustive tests for `tanpif16()`
We are finalizing the header inclusion policy, and for our public
headers in the `libc/include` folder, they must use relative path in
`"..."` when including each other.
This PR does the cleanup making sure that all the public header
inclusions in `libc/include` folder use relative paths.
---------
Co-authored-by: Nick Desaulniers <nickdesaulniers@users.noreply.github.com>
Implementation of `cos` for half precision floating point inputs scaled
by pi (i.e., `cospi`), correctly rounded for all rounding modes.
---------
Co-authored-by: OverMighty <its.overmighty@gmail.com>
Summary:
I'm going to attempt to move the `rpc.h` header to a separate folder
that we can install and include outside of `libc`. Before doing this I'm
going to try to trim up the file so there's not as many things I need to
copy to make it work. This dependency on `cpp::functional` is a low
hanging fruit. I only did it so that I could overload the argument of
the work function so that passing the id was optional in the lambda,
that's not a *huge* deal and it makes it more explicit I suppose.
Summary:
Make a separate thread to run the server when we launch. This is
required by CUDA, which you can force with `export
CUDA_LAUNCH_BLOCKING=1`. I figured I might as well be consistent and do
it for the AMD implementation as well even though I believe it's not
necessary.
Summary:
It's safer to use the maximum size, as this prevents the runtime from
oversubscribing with multiple producers. Additionally we should set the
barrier bit to ensure that the queue entries block if multiple are
submitted (Which shouldn't happen for this tool).
Summary:
This function can easily be implemented by forwarding it to the host
process. This shows up in a few places that we might want to test the
GPU so it should be provided. Also, I find the idea of the GPU
offloading work to the CPU via `system` very funny.
The RPC server directly includes the printf code, but doesn't support
errno, so the %m conversion needs to be disabled there as well. This
patch does that.
- added all variations of ffma and fdiv
- will add all new headers into yaml for next patch
- only fsub is left then all basic operations for float is complete
---------
Co-authored-by: OverMighty <its.overmighty@gmail.com>
Summary:
The loader is used as a test utility to run traditionally CPU based unit
tests on the GPU. This has issues when used with something like
`llvm-lit` because the GPU runtimes have a nasty habit of either running
out of resources or hanging when they are overloaded. To combat this, I
added this option to force each process to perform the GPU part
serially.
This is done right now with a simple file lock on the executing file. I
was originally thinking about using more complex IPC to allow N
processes to share execution, but that seemed overly complicated given
the incredibly large number of failure modes it introduces. File locks
are nice here because if the process crashes or is killed it will
release the lock automatically (at least on Linux). This is in contrast
to something like POSIX shared memory which will stick around until it's
unlinked, meaning that if someone did `sigkill` on the program it would
never get cleaned up and other threads might wait on a mutex that never
occurs.
Restricting this to one thread isn't overly ideal, given the fact that
the runtime can likely handle at least a *few* separate processes, but
this was easy and it works, so might as well start here. This will
hopefully unblock me on running `libcxx` tests, as those ran with so
much parallelism spurious failures were very common.
Summary:
This patch removes the ad-hoc parsing that I used previously and
replaces it with the LLVM CommnadLine interface. This doesn't change any
functionality, but makes it easier to maintain.
Summary:
We get the `strlen` to know how much memory to allocate here, but it
wasn't taking into account if the padding was larger than the string
itself. This patch sets it to an empty string so we always add the
minimum size. This implementation is slightly wasteful with memory, but
I am not concerned with a few extra bytes here and there for some memory
that gets immediately free'd.
Summary:
This patch implements the `printf` family of functions on the GPU using
the new variadic support. This patch adapts the old handling in the
`rpc_fprintf` placeholder, but adds an extra RPC call to get the size of
the buffer to copy. This prevents the GPU from needing to parse the
string. While it's theoretically possible for the pass to know the size
of the struct, it's prohibitively difficult to do while maintaining ABI
compatibility with NVIDIA's varargs.
Depends on https://github.com/llvm/llvm-project/pull/96015.
