RMA Test Cases

LocalConcurrency test cases

Combines different operations with different RMA sync modes to cover all possible conflict/sync variants for local concurrency problems / local buffer races.

Operations / Calls covered:

• Buffer accesses: buffer read, buffer write
• Local buffer write: MPI_Get, MPI_Rget
• Local buffer read: MPI_Put, MPI_Rput, MPI_Accumulate, MPI_Raccumulate, MPI_Get_accumulate, MPI_Rget_accumulate, MPI_Fetch_and_op, MPI_Compare_and_swap (Note: MPI_Get_accumulate and others may also write results in another local buffer, but we only consider the reading accesses here.)

Synchronization modes covered:

• Fences: MPI_Win_fence
• Lockall + Flush_all + Unlock_all
• Lockall + Flush_local_all + Unlock_all
• Lock + Flush + Unlock: MPI_Win_(lock|flush|unlock)
• Lock + Unlock
• Requests: MPI_R(put|get|accumulate|get_accumulate) + MPI_Wait
• PSCW
• Currently missing: Lock_all + Unlock_all

Currently missing compared to MBI (for LocalConcurrency):

• Conflict between MPI RMA operation and (non-)blocking P2P, e.g. MPI_Get + MPI_Isend/Send on the same buffer
• The conflicting access could be on a separate buffer or on the window itself (i.e., the window memory itself could be target of a local buffer access).

GlobalConcurrency test cases

Operations / Calls covered:

• Buffer accesses: buffer read, buffer write
• Local buffer read/write: MPI_Put / MPI_Get (we do not consider all other possibilities of local buffer accesses to avoid a test case explosion)
• Remote read: MPI_Get, MPI_Put
• Remote write: MPI_Put, MPI_Rput, MPI_Accumulate, MPI_Raccumulate, MPI_Get_accumulate, MPI_Rget_accumulate, MPI_Fetch_and_op, MPI_Compare_and_swap

Synchronization modes covered:

• Fences: MPI_Win_fence
• Lockall + Flush_all + Barrier + Unlock_all
• Lock + Unlock: Exclusive vs. Shared
• Requests: MPI_R(put|get|accumulate|get_accumulate) + MPI_Wait
• PSCW
• Optional (currently missing): Lock + Unlock, Lock_all + Unlock_all

Invalid Argument test cases

• Invalid target rank (-1, >= nranks, ...)
• Invalid buffer (NULL)
• Invalid Datatype (MPI_DATATYPE_NULL, freed data type)
• Invalid window (no window initialized, window freed to early)

Epoch Lifecycle

• RMA access before epoch is opened
• RMA access without closing epoch
• Double open of access epoch (double lock, non-collective fence)
• Mixing RMA access modes (fence + lock)

scripts/Infrastructure/CorrectParameter.py

 #! /usr/bin/python3
 from scripts.Infrastructure import MPICall
 from scripts.Infrastructure.Instruction import Instruction
-from scripts.Infrastructure.MPICallFactory import MPICallFactory
+# from scripts.Infrastructure.MPICallFactory import MPICallFactory
 from scripts.Infrastructure.AllocCall import AllocCall, get_free
 
-
 class CorrectParameterFactory:
     # default params
     buf_size = "10"
@@ -13,15 +12,26 @@ class CorrectParameterFactory:
     tag = 0
     buf_var_name = "buf"
     winbuf_var_name = "winbuf"
+    request_counter = 0
+    _instance = None
 
     def __init__(self):
         pass
 
+    @classmethod
+    def instance(cls):
+        if cls._instance is None:
+            cls._instance = cls.__new__(cls)
+        return cls._instance
+
     def get_buffer_alloc(self) -> AllocCall:
         return AllocCall(self.dtype[0], self.buf_size, self.buf_var_name, use_malloc=False)
 
     def get_buffer_free(self) -> Instruction:
         return get_free(AllocCall(self.dtype[0], self.buf_size, self.buf_var_name, use_malloc=False))
+    
+    def consume_request(self):
+        self.request_counter += 1
 
     def get(self, param: str) -> str:
         if param in ["BUFFER", "buf", "buffer", "sendbuf", "recvbuf", "origin_addr"]:
@@ -56,7 +66,7 @@ class CorrectParameterFactory:
         if param in ["PARTITION", "partition"]:
             return "0"
         if param in ["REQUEST", "request"]:
-            return "&mpi_request_0"
+            return "&mpi_request_" + str(self.request_counter)
         if param in ["GROUP", "group"]:
             return "&mpi_group_0"
         if param in ["color"]:
@@ -114,17 +124,17 @@ class CorrectParameterFactory:
         assert False, "Param not known"
 
 
-# todo also for send and non default args
-def get_matching_recv(call: MPICall) -> MPICall:
-    correct_params = CorrectParameterFactory()
-    recv = MPICallFactory().mpi_recv(
-        correct_params.get("BUFFER"),
-        correct_params.get("COUNT"),
-        correct_params.get("DATATYPE"),
-        correct_params.get("SRC"),
-        correct_params.get("TAG"),
-        correct_params.get("COMM"),
-        correct_params.get("STATUS", "MPI_Recv"),
-    )
+# # todo also for send and non default args
+# def get_matching_recv(call: MPICall) -> MPICall:
+#     correct_params = CorrectParameterFactory()
+#     recv = MPICallFactory().mpi_recv(
+#         correct_params.get("BUFFER"),
+#         correct_params.get("COUNT"),
+#         correct_params.get("DATATYPE"),
+#         correct_params.get("SRC"),
+#         correct_params.get("TAG"),
+#         correct_params.get("COMM"),
+#         correct_params.get("STATUS", "MPI_Recv"),
+#     )
 
-    return recv
+#     return recv