NCCL 2.4.6-1

Added detection of IBM/Power NVLink bridge device.
    Add NUMA support to PCI distance calculations.
    Added NCCL_IGNORE_CPU_AFFINITY env var.
    Fix memory leaks; GithubIssue#180
    Compiler warning fix; GithubIssue#178
    Replace non-standard variable length arrays. GithubIssue#171
    Fix Tree+Shared Memory crash. GithubPR#185
    Fix LL cleanup hang during long running DL jobs.
    Fix NCCL_RINGS environment variable handling.
    Added extra checks to catch repeat calls to ncclCommDestroy() GithubIssue#191
    Improve bootstrap socket connection reliability at scale.
    Fix hostname hashing issue. GithubIssue#187
    Code cleanup to rename all non device files from *.cu to *.cc

src/include/info.h

@@ -0,0 +1,45 @@
+/*************************************************************************
+ * Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
+ *
+ * See LICENSE.txt for license information
+ ************************************************************************/
+
+#ifndef NCCL_INFO_H_
+#define NCCL_INFO_H_
+
+#include "nccl.h"
+
+typedef enum {
+  ncclPatternRing,
+  ncclPatternRingTwice,
+  ncclPatternPipelineFrom,
+  ncclPatternPipelineTo,
+  ncclPatternTreeUp,
+  ncclPatternTreeDown,
+  ncclPatternTreeUpDown
+} ncclPattern_t;
+
+// Used to pass NCCL call information between functions
+struct ncclInfo {
+  ncclColl_t coll;
+  const char* opName;
+  // NCCL Coll Args
+  const void* sendbuff;
+  void* recvbuff;
+  size_t count;
+  ncclDataType_t datatype;
+  ncclRedOp_t op;
+  int root;
+  ncclComm_t comm;
+  cudaStream_t stream;
+  // Algorithm details
+  int chunkSteps;
+  int sliceSteps;
+  // Computed later
+  ncclPattern_t pattern;
+  size_t nBytes;
+  int nstepsPerLoop;
+  int nchunksPerLoop;
+};
+
+#endif