Rework barrier and event code (#761)

* Rework barrier and event code * Switch to inline asm
2023-05-31 13:36:51 -07:00
parent 7519ecb476
commit 5a38ff192b
3 changed files with 5 additions and 6 deletions
@@ -16,12 +16,11 @@
 #define NCCL_SPINS_BEFORE_CHECK_ABORT 1000000

 #define barrier_by_group() do { \
-  const int w = threadIdx.x/WARP_SIZE; \
-  const int wid = threadIdx.x%WARP_SIZE; \
-  __threadfence(); \
  if (nthreads == NCCL_MAX_NTHREADS) { \
-    __syncthreads(); \
+    __asm__ __volatile__("s_waitcnt vmcnt(0) lgkmcnt(0)\ns_barrier\ns_waitcnt lgkmcnt(0)"); \
  } else { \
+    const int w = threadIdx.x/WARP_SIZE; \
+    const int wid = threadIdx.x%WARP_SIZE; \
    if (wid == 0) { \
      barrier_next[w] += nthreads/WARP_SIZE; \
      atomicAdd((unsigned long long *)barriers, 1); \