Commit dfe8462f authored by Francois Tessier's avatar Francois Tessier

Minor fix in F90 code. Todo-list updated

parent d68c2b08
......@@ -8,21 +8,18 @@
- Change fprintf to the customized printMsg
- Change tp_network to tp_topology
- Remove the output file in Write/Read API as it's never used
- Write a getopt function to set the subfiling/output/tiers for the benchmarks
* Set aggregation/target tier in TAPIOCA
* File per I/O node on BG/Q == File per OST on Lustre (get the stripe count from tp_network.cpp)
- Ask Silvio for Vl3D for Cooley
- README and LICENCE
- Reuse aggregators? Does not work (wrong data read) with HACC-IO, SSF, SoA, while the AoS case works
- Foreach architecture (copy from Theta?) :
* Change the tiers of memory available: PFS, NLS (node-local storage), NVR, ...
* Function to determine the target storage used according to the output file (i.e. no need for the user to set memTarg)
* The memory abstraction should give the path of the on-node storage's mount point
- README and LICENCE
- Reuse aggregators? Does not work (wrong data read) with HACC-IO, SSF, SoA, while the AoS case works
\ No newline at end of file
* Change tp_network to tp_topology
......@@ -7,7 +7,7 @@ void tapioca_init_ ( int64_t *chunkCount, int *chunkSize, int64_t *chunkOffset,
int nChunks_ = *nChunks;
int64_t header_ = (int64_t)*header;
MPI_Comm comm_ = MPI_Comm_f2c ( *comm );
Tapioca_S::getInstance()->Init ( chunkCount, chunkSize, chunkOffset, nChunks_, header_, fileName, comm_ );
}
......
......@@ -3,7 +3,7 @@ PROGRAM main
use mpi
use iso_c_binding
integer ierr, i, myrank, mysize, filehandle, NBUFF, AGG_MEM, TARGET_MEM, TYPESIZE
integer ierr, i, myrank, mysize, filehandle, TYPESIZE
integer*8 BUFSIZE, TOTSIZE, SCANSIZE, HDR, FILESIZE
integer(kind=MPI_OFFSET_KIND) disp
integer status(MPI_STATUS_SIZE)
......@@ -17,10 +17,6 @@ PROGRAM main
TYPESIZE = 4
SCANSIZE = 0
HDR = 0
NBUFF = 2
! DDR=0, HBM=1, SSD=2, HDD=3, NVR=4
AGG_MEM = 0
TARGET_MEM = 3
call MPI_INIT(ierr)
call MPI_COMM_RANK(MPI_COMM_WORLD, myrank, ierr)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment