Revert "[AG and RS channel tuning] Add thread work threshold to tuning models and precompute reg index in LL128 (#1641)"

This reverts commit 00c1eb098c.

src/include/device.h

@@ -95,7 +95,7 @@ static_assert(NCCL_LL_CLEAN_MASK % NCCL_STEPS == 0, "Invalid NCCL_LL_CLEAN_MASK
 #define NCCL_LL128_MAX_NTHREADS 256
 #define NCCL_LL128_ELEMS_PER_THREAD 28
 
-#define NCCL_LL128_SHMEM_ELEMS_PER_THREAD 16
+#define NCCL_LL128_SHMEM_ELEMS_PER_THREAD 4
 #define NCCL_LL128_SHMEM_SIZE (NCCL_LL128_SHMEM_ELEMS_PER_THREAD*NCCL_LL128_MAX_NTHREADS)
 
 #define NCCL_P2P_WRITE 0x01
@@ -698,7 +698,7 @@ inline int ncclDevFuncId(int coll, int devRedOp, int type, int algo, int proto)
 
     // RING / <all_protos> / <all_redops> / <all_types>
     if (coll == ncclFuncReduce) {
-      row += ((proto * ncclNumDevRedOps + devRedOp) * ncclNumTypes + type) - NCCL_NUM_FLOATS * proto;
+      row += ((proto * ncclNumDevRedOps + devRedOp) * ncclNumTypes + type) - NCCL_NUM_FLOATS * proto; 
       break;
     }
     row += NCCL_NUM_PROTOCOLS * (ncclNumDevRedOps * ncclNumTypes - NCCL_NUM_FLOATS);

src/include/rccl_common.h

@@ -33,11 +33,10 @@ typedef enum RcclTunableColls {
 } rcclTunableIndex_t;
 
 #define RCCL_LL_LIMITS_UNDEFINED 0
-#define RCCL_PROTOCOL_ENTRY_SIZE 4
+#define RCCL_PROTOCOL_ENTRY_SIZE 3
 #define RCCL_PROTOCOL_MIN_IDX 0
 #define RCCL_PROTOCOL_MAX_IDX 1
 #define RCCL_PROTOCOL_FACTOR_IDX 2
-#define RCCL_PROTOCOL_THREAD_THRESHOLD_IDX 3
 
 #ifdef RCCL_EXPOSE_STATIC
 #define RCCL_STATIC_EXPOSE_CHECK()
@@ -72,7 +71,8 @@ inline size_t rcclGetSizePerRank(ncclFunc_t const& func, size_t const& nBytes, i
   return (func == ncclFuncReduceScatter || func == ncclFuncAllGather) ? nBytes / nRanks : nBytes;
 }
 void rcclUpdateCollectiveProtocol(struct ncclComm* comm, size_t const& nBytes, struct ncclTaskColl* info);
-void rcclUpdateThreadThreshold(struct ncclComm* comm, size_t const& nBytes, struct ncclTaskColl* info, int& threadThreshold);
+
+
 ncclResult_t rcclGetAlgoInfo(struct ncclComm* comm, ncclFunc_t coll, uint64_t count, ncclDataType_t dataType,
                              int collNetSupport, int nvlsSupport, int numPipeOps,
                              int* algo, int* protocol, int* maxChannels);