Sync up to NCCL 2.9.6 (#363)
* 2.9.6-1 Add support for CUDA graphs. Fuse BCM Gen4 switches to avoid suboptimal performance on some platforms. Issue #439. Fix bootstrap issue caused by connection reordering. Fix CPU locking block. Improve CollNet algorithm. Improve performance on DGX A100 for communicators with only one GPU per node. * Clique tuning upgrade (#352) (#19) * Enabling clique for any XGMI-connected topology, adding tuning * Updating CHANGELOG for clique tuning * Re-working clique barrier system to work on multi-process / multi-gpu Co-authored-by: Sylvain Jeaugey <sjeaugey@nvidia.com> Co-authored-by: gilbertlee-amd <44450918+gilbertlee-amd@users.noreply.github.com>
This commit is contained in:
@@ -40,7 +40,7 @@ namespace CorrectnessTests
|
||||
hipStream_t stream;
|
||||
HIPCHECK(hipStreamCreateWithFlags(&stream, hipStreamNonBlocking));
|
||||
struct ncclChannel* channel = comm->channels;
|
||||
uint64_t **p_dev_head = (uint64_t **)((uint8_t*)(channel->devPeers + channel->ring.next) + offsetof(struct ncclPeer, send.conn.head));
|
||||
uint64_t **p_dev_head = (uint64_t **)((uint8_t*)(channel->devPeers + channel->ring.next) + offsetof(struct ncclPeer, send[0].conn.head));
|
||||
uint64_t *real_head, *fake_head, *fake_h;
|
||||
|
||||
// get original head
|
||||
|
||||
@@ -41,7 +41,7 @@ namespace CorrectnessTests
|
||||
hipStream_t stream;
|
||||
HIPCHECK(hipStreamCreateWithFlags(&stream, hipStreamNonBlocking));
|
||||
struct ncclChannel* channel = comm->channels;
|
||||
uint64_t **p_dev_head = (uint64_t **)((uint8_t*)(channel->devPeers + channel->ring.next) + offsetof(struct ncclPeer, send.conn.head));
|
||||
uint64_t **p_dev_head = (uint64_t **)((uint8_t*)(channel->devPeers + channel->ring.next) + offsetof(struct ncclPeer, send[0].conn.head));
|
||||
uint64_t *real_head, *fake_head, *fake_h;
|
||||
|
||||
// get original head
|
||||
|
||||
Reference in New Issue
Block a user