iziemba

Results 3 comments of iziemba

I ran the ANL-116 reproducer on Aurora and with an instrumented libfabric. I verified that the remote key MPICH is passing into libfabric RMA operations is not a key generated...

For user keys, I can update CXI provider to have check for RKEY size and ensure it is

>libfabric:103644:1742955972::cxi:ep_data:cxip_txc_can_emit_op():515 x4519c2s3b0n0: TXC (0x42aa0:1): TXC attr size saturated libfabric:103644:1742955972::cxi:ep_data:cxip_rma_emit_dma():359 x4519c2s3b0n0: TXC (0x42aa0:1): Failed to emit dma command: -11:Resource temporarily unavailable libfabric:103644:1742955972::cxi:ep_data:cxip_rma_common():663 x4519c2s3b0n0: TXC (0x42aa0:1): DMA RMA read failed: buf=0xff000003c25a9060 len=26880...