Revert "Intra-node shared memory (SHM) optimizations for CPU primitives (#458)" (#490)

This reverts commit 5994546.

Author: d4l3k

gloo/CMakeLists.txt

@@ -51,11 +51,6 @@ list(APPEND GLOO_HDRS
   "${CMAKE_CURRENT_SOURCE_DIR}/types.h"
   )
 
-if(NOT MSVC AND NOT CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm)")
-  list(APPEND GLOO_SRCS "${CMAKE_CURRENT_SOURCE_DIR}/allreduce_shm.cc")
-  list(APPEND GLOO_HDRS "${CMAKE_CURRENT_SOURCE_DIR}/allreduce_shm.h")
-endif()
-
 if(USE_CUDA)
   file(GLOB GLOO_CUDA_SRCS
     "${CMAKE_CURRENT_SOURCE_DIR}/cuda*.cc"

gloo/allreduce.cc

@@ -12,12 +12,8 @@
 #include <array>
 #include <cstring>
 
-#if !defined(_WIN32) && !defined(__aarch64__) && !defined(__arm__)
-#include "gloo/allreduce_shm.h"
-#endif
 #include "gloo/common/logging.h"
 #include "gloo/math.h"
-#include "gloo/transport/device.h"
 #include "gloo/types.h"
 
 namespace gloo {
@@ -135,27 +131,14 @@ void allreduce(const detail::AllreduceOptionsImpl& opts) {
     return;
   }
 
-  auto algorithm = opts.algorithm;
-
-#if !defined(_WIN32) && !defined(__aarch64__) && !defined(__arm__)
-  if (context->isIntraNode() && !context->getDevice()->hasGPUDirect()) {
-    algorithm = detail::AllreduceOptionsImpl::SHM;
-  }
-#endif
-
-  switch (algorithm) {
+  switch (opts.algorithm) {
     case detail::AllreduceOptionsImpl::UNSPECIFIED:
     case detail::AllreduceOptionsImpl::RING:
       ring(opts, reduceInputs, broadcastOutputs);
       break;
     case detail::AllreduceOptionsImpl::BCUBE:
       bcube(opts, reduceInputs, broadcastOutputs);
       break;
-#if !defined(_WIN32) && !defined(__aarch64__) && !defined(__arm__)
-    case detail::AllreduceOptionsImpl::SHM:
-      shm(opts);
-      break;
-#endif
     default:
       GLOO_ENFORCE(false, "Algorithm not handled.");
   }

gloo/allreduce.h

@@ -39,7 +39,6 @@ struct AllreduceOptionsImpl {
     UNSPECIFIED = 0,
     RING = 1,
     BCUBE = 2,
-    SHM = 3,
   };
 
   explicit AllreduceOptionsImpl(const std::shared_ptr<Context>& context)