Unify environment variable management (#235)

* Add environment variable configuration infrastructure
  - Namespace rocshmem::envvar
  - Track all config env vars in per-category lists
  - Remove duplicates from list of allowed env var types
  - Reject negative inputs for unsigned integer types
  - Accept empty strings for std::string
  - Print error source location using C++20 std::source_location
  - Unit tests
* Port environment variables
  - ROCSHMEM_UNIQUEID_WITH_MPI
  - ROCSHMEM_RO_DISABLE_IPC
  - ROCSHMEM_BOOTSTRAP_TIMEOUT
  - ROCSHMEM_BOOTSTRAP_HOSTID
  - ROCSHMEM_BOOTSTRAP_SOCKET_IFNAME
  - ROCSHMEM_RO_PROGRESS_DELAY
  - ROCSHMEM_BOOTSTRAP_SOCKET_FAMILY
  - ROCSHMEM_MAX_NUM_CONTEXTS
    + Merge the independent per-backend copies into a single variable
      that is used by all three backends (IPC, RO, GDA).
    + Set default to 32 (for GDA); prior default for IPC and RO was 1024.
  - ROCSHMEM_MAX_NUM_HOST_CONTEXTS
  - ROCSHMEM_MAX_WF_BUFFERS
  - ROCSHMEM_SQ_SIZE
  - ROCSHMEM_RO_NET_CPU_QUEUE
    + Renamed from RO_NET_CPU_QUEUE
    + Change env var input type to bool, default to false
    + Invert code logic: setting RO_NET_CPU_QUEUE to anything
      would /disable/ a variable gpu_queue, which defaulted to true.
      Variable is now named config::ro::net_cpu_queue,
      with all prior checks for gpu_queue inverted.
  - ROCSHMEM_USE_IB_HCA
  - ROCSHMEM_HEAP_SIZE
    + Defaults to 1L << 30 i.e. 1 GiB,
      from default heap size in memory/heap_memory.hpp.
  - ROCSHMEM_MAX_NUM_TEAMS
    + Unlike other env vars, this can be referenced from devices.
    + Function currently narrows from size_t to int: uses need to be audited
      for safety and correctness in using size_t directly.
  - ROCSHMEM_GDA_ALTERNATE_QP_PORTS
* New env var ROCSHMEM_DEBUG
  - Debug levels:
    + NONE
    + VERSION
    + WARN
    + INFO
    + TRACE
  - Currently unused - will be added later
  - Mirrors RCCL debug control
* Remove rocshmem::rocshmem_env_config
* Change interface for GetClosestNicToGpu
  to accept const char** instead of char**:
  the pointed-to string does not need to be modified
  - Files were not audited for inclusion of util.hpp only for env vars
---------
Signed-off-by: Omri Mor <Omri.Mor@amd.com>

src/reverse_offload/queue.cpp

@@ -23,30 +23,18 @@
  *****************************************************************************/
 
 #include "queue.hpp"
+#include "envvar.hpp"
 #include "mpi_transport.hpp"
 
 namespace rocshmem {
 
-Queue::Queue() {
-  gpu_queue = true;
-  char *value{nullptr};
-  if ((value = getenv("RO_NET_CPU_QUEUE")) != nullptr) {
-    gpu_queue = false;
-  }
-}
+Queue::Queue() { }
 
 Queue::Queue(size_t max_queues, size_t queue_size)
     : max_queues_{max_queues},
       queue_size_{queue_size},
       queue_proxy_{max_queues, queue_size},
-      queue_desc_proxy_{max_queues} {
-
-  gpu_queue = true;
-  char *value{nullptr};
-  if ((value = getenv("RO_NET_CPU_QUEUE")) != nullptr) {
-    gpu_queue = false;
-  }
-}
+      queue_desc_proxy_{max_queues} { }
 
 uint64_t Queue::get_read_index(uint64_t queue_index) {
   return descriptor(queue_index)->read_index % queue_size_;
@@ -70,7 +58,7 @@ bool Queue::process(uint64_t queue_index, MPITransport* transport) {
 
 queue_element* Queue::next_element(uint64_t queue_index) {
   queue_element *next_elem{nullptr};
-  if (gpu_queue) {
+  if (!envvar::ro::net_cpu_queue) {
     hdp_proxy_.get()->hdp_flush();
     copy_element_to_cache(queue_index);
     next_elem = queue_element_cache_proxy_.get();
@@ -90,13 +78,13 @@ void Queue::copy_element_to_cache(uint64_t queue_index) {
 }
 
 void Queue::flush_hdp() {
-  if (!gpu_queue) {
+  if (envvar::ro::net_cpu_queue) {
     hdp_proxy_.get()->hdp_flush();
   }
 }
 
 void Queue::sfence_flush_hdp() {
-  if (!gpu_queue) {
+  if (envvar::ro::net_cpu_queue) {
     asm volatile("sfence" ::: "memory");
     hdp_proxy_.get()->hdp_flush();
   }