50445dff43
This patch adds extra intrinsics for the GPU. Some of these are unused for now but will be used later. We use these currently to update the `RPC` handling. Currently, every thread can update the RPC client, which isn't correct. This patch adds code neccesary to allow a single thread to perfrom the write while the others wait. Feedback is welcome for the naming of these functions. I'm copying the OpenMP nomenclature where we call an AMD `wavefront` or NVIDIA `warp` a `lane`. Reviewed By: tra Differential Revision: https://reviews.llvm.org/D148810
44 lines
1.4 KiB
C++
44 lines
1.4 KiB
C++
//===-- Implementation of crt for nvptx -----------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "src/__support/GPU/utils.h"
|
|
#include "src/__support/RPC/rpc_client.h"
|
|
|
|
extern "C" int main(int argc, char **argv, char **envp);
|
|
|
|
namespace __llvm_libc {
|
|
|
|
static cpp::Atomic<uint32_t> lock = 0;
|
|
|
|
static cpp::Atomic<uint32_t> init = 0;
|
|
|
|
void init_rpc(void *in, void *out, void *buffer) {
|
|
// Only a single thread should update the RPC data.
|
|
if (gpu::get_thread_id() == 0 && gpu::get_block_id() == 0) {
|
|
rpc::client.reset(&lock, in, out, buffer);
|
|
init.store(1, cpp::MemoryOrder::RELAXED);
|
|
}
|
|
|
|
// Wait until the previous thread signals that the data has been written.
|
|
while (!init.load(cpp::MemoryOrder::RELAXED))
|
|
rpc::sleep_briefly();
|
|
|
|
// Wait for the threads in the block to converge and fence the write.
|
|
gpu::sync_threads();
|
|
}
|
|
|
|
} // namespace __llvm_libc
|
|
|
|
extern "C" [[gnu::visibility("protected"), clang::nvptx_kernel]] void
|
|
_start(int argc, char **argv, char **envp, int *ret, void *in, void *out,
|
|
void *buffer) {
|
|
__llvm_libc::init_rpc(in, out, buffer);
|
|
|
|
__atomic_fetch_or(ret, main(argc, argv, envp), __ATOMIC_RELAXED);
|
|
}
|