Typed MPI A Data Type Tool for MPI

1
Typed MPI - A Data Type Tool for MPI

• Nitin Bahadur
• and
• Florentina Irina Popovici bnitin, pif
  _at_cs.wisc.edu

Typed MPI
2
Why a Data Type Tool for MPI?

• No type message at receiver end
• User has to manually construct MPI data types
  corresponding to user defined data types

User code for constructing an MPI datatype for a
C struct
3
Objectives of our interface

• Automatic generation of MPI datatypes
• Type checking and error reporting to both sender
  and receiver
• Seamless integration within a C program
• Facility to send user-defined datatypes such as
  structures
• Facility to send multiple data in one send call
  (allowing arbitrary grouping of data to be sent)

4
Design Overview

• Code generated at compile time. It will perform
• signature generation
• data and signature packaging
• signature checking (receiver end)
• error reporting

Support for runtime
5
How does Typed MPI work ?

• Phase 1 preprocess the user files
• determine the types of the wrapper call
  parameters
• generate signature
• generate code for packaging data
• generate code for sending/receiving data
• generate code for error checking/reporting
• Phase 2 runtime
• Execute the program, make the actual MPI calls
  and do error checking and reporting

6
Type Checking

• Rules for type checking. Two types T1 and T2 are
  identical if
• T1 and T2 have the same primitive type (e.g.
  int, char )
• T1 and T2 are arrays and they have the same base
  type and the same size
• (int p5 and char q5 are different)
• T1 and T2 are structures and their members have
  the same type

• A Signature is
• generated for each variable to be sent/received
  based on its type
• sent by the sender along with the data
• compared at the receivers end with the expected
  signature (an error code will be returned to the
  sender )

Send / Receive Protocol
7
Signature
encompasses entire type of a variable
struct example1 int a float b5
START, VAR_START, STRUCT_START,
TYPE_INT, 1 , TYPE_ARRAY,
TYPE_FLOAT, 5, ST_UN_END, END
Signature

• depth first approach to signature construction
• type of a variable is broken down recursively to
  generate the signature

Recongnition of a complex C struct
VAR_START
STRUCT_START
struct eg1 int a struct eg2
int b float b5
STRUCT_START
TYPE_INT
TYPE_INT
TYPE_ARRAY
1
TYPE_FLOAT
1
5
8
Preprocessing steps
Preprocessor and generator
Compilation
/ Initial user code / .... MPI_Wrapper_Send
(dest, tag, comm, a, 1, b, 2) .... MPI_Wrapper_
Recv (src, tag, comm, status, a, 1, b, 2) ...
/ Modified user source code / .... MPI_Wrapper_
Send79205397130821 (dest, tag, comm, a, 1, b,
2) .... MPI_Wrapper_Recv79205397345131(src, tag,
comm, status, a, 1, b, 2) ...
Executable
/ generated file 1 / int MPI_Wrapper_Send7920539
7130821 (int, int, MPI_Comm, void , int, void
int) / signature and data packaging,
error reporting /
A new file is generated for every MPI_Wrapper
call and it contains code for that call
/ generated file 2 / int MPI_Wrapper_Recv792053
971345131 (int, int, MPI_Comm, MPI_Status , void
, int, void , int) / signature and data
packaging, error reporting /

Files resulting after preprocessing and source
code generation
9
Performance Evaluation
Type Checking overhead
Preprocessing overhead

• The graphs and figure show that our design is
  feasible for automatic type generation and type
  checking.
• The overhead of type checking gets overshadowed
  by data transmission time as data size increases.

10
Conclusions

• A simple interface for sending user defined
  datatypes and multiple data in one call
• Strict type checking and error reporting to both
  sender and receiver
• Low preprocessing time and runtime overhead
• Error reporting to sender can be disabled to (if
  required) to reduce number of data transfers

Future Work

• Extensions for Group Communication and Vector
  operations
• Handling of expressions in MPI_Wrapper calls
• Feasibility study for use of hashing functions
  to reduce size of signature