[HARDWARE][POWER] Enable SHM communicator support for PowerPC (#43754)

Signed-off-by: Rukhaiya <rukhaiya@c643n08aix1-lp1.pok.stglabs.ibm.com>
Signed-off-by: Rukhaiya <bibirukhaiya123@gmail.com>
Co-authored-by: Rukhaiya <rukhaiya@c643n08aix1-lp1.pok.stglabs.ibm.com>
Co-authored-by: Akash kaothalkar <61960177+Akashcodes732@users.noreply.github.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
Rukhaiya2004
2026-06-02 18:06:32 +08:00
committed by GitHub
co-authored by Rukhaiya Akash kaothalkar Li, Jiang <jiang1.li@intel.com>
parent f8e9c56d15
commit 689b0eeb9e
6 changed files with 125 additions and 10 deletions
+10 -8
View File
@@ -5,7 +5,7 @@
#include <sys/stat.h>
#include <unistd.h>
#ifdef __aarch64__
#if defined(__aarch64__) || defined(__powerpc64__)
#include <atomic>
#endif
@@ -38,7 +38,7 @@ struct KernelVecType<c10::Half> {
};
struct ThreadSHMContext {
#ifdef __aarch64__
#if defined(__aarch64__) || defined(__powerpc64__)
// memory model is weaker on AArch64, so we use atomic variables for
// consumer (load-acquire) and producer (store-release) to make sure
// that a stamp cannot be ready before the corresponding data is ready.
@@ -75,7 +75,7 @@ struct ThreadSHMContext {
TORCH_CHECK(group_size <= MAX_SHM_RANK_NUM);
TORCH_CHECK((size_t)this % 64 == 0);
TORCH_CHECK((size_t)thread_shm_ptr % 64 == 0);
#ifdef __aarch64__
#if defined(__aarch64__) || defined(__powerpc64__)
_curr_thread_stamp[0].store(1, std::memory_order_relaxed);
_curr_thread_stamp[1].store(1, std::memory_order_relaxed);
_ready_thread_stamp[0].store(0, std::memory_order_relaxed);
@@ -124,7 +124,7 @@ struct ThreadSHMContext {
}
char get_curr_stamp(int idx) const {
#ifdef __aarch64__
#if defined(__aarch64__) || defined(__powerpc64__)
return _curr_thread_stamp[idx].load(std::memory_order_acquire);
#else
return _curr_thread_stamp[idx];
@@ -132,7 +132,7 @@ struct ThreadSHMContext {
}
char get_ready_stamp(int idx) const {
#ifdef __aarch64__
#if defined(__aarch64__) || defined(__powerpc64__)
return _ready_thread_stamp[idx].load(std::memory_order_acquire);
#else
return _ready_thread_stamp[idx];
@@ -140,7 +140,7 @@ struct ThreadSHMContext {
}
void next_stamp() {
#ifdef __aarch64__
#if defined(__aarch64__) || defined(__powerpc64__)
_curr_thread_stamp[local_stamp_buffer_idx].fetch_add(
1, std::memory_order_release);
#else
@@ -150,7 +150,7 @@ struct ThreadSHMContext {
}
void commit_ready_stamp() {
#ifdef __aarch64__
#if defined(__aarch64__) || defined(__powerpc64__)
_ready_thread_stamp[local_stamp_buffer_idx].store(
_curr_thread_stamp[local_stamp_buffer_idx].load(
std::memory_order_relaxed),
@@ -186,8 +186,10 @@ struct ThreadSHMContext {
break;
}
++_spinning_count;
#ifdef __aarch64__
#if defined(__aarch64__)
__asm__ __volatile__("yield");
#elif defined(__powerpc64__)
__asm__ __volatile__("or 1,1,1");
#else
_mm_pause();
#endif // __aarch64__