Saeed Maleki (saemal)
|
dced4c4c14
|
done with the design
|
2023-03-06 12:26:46 -08:00 |
|
Saeed Maleki (saemal)
|
b663469bcd
|
making a fifo for proxy threads
|
2023-03-06 10:58:12 -08:00 |
|
Saeed Maleki (saemal)
|
ae7407146b
|
removing unnecessary stat probe for cuda graph
|
2023-03-06 08:03:44 -08:00 |
|
Saeed Maleki
|
24614c9a7d
|
Merge pull request #4 from microsoft/chhwang/p2p-simple
Add connections and proxies
|
2023-03-06 03:05:36 -05:00 |
|
Saeed Maleki
|
0216ceb34e
|
added todos
|
2023-03-06 08:04:33 +00:00 |
|
Changho Hwang
|
5ac2ea6e9f
|
IB more fixes
|
2023-03-06 07:01:03 +00:00 |
|
Saeed Maleki
|
b296dca9f2
|
Merge pull request #5 from microsoft/saemal/dma-cleanup
Saemal/dma cleanup
|
2023-03-05 23:50:12 -05:00 |
|
Saeed Maleki
|
7e4bacf20c
|
works
|
2023-03-03 23:10:41 +00:00 |
|
Saeed Maleki (saemal)
|
3def04e72d
|
separating dma data/flag/sync logic
|
2023-03-03 15:05:54 -08:00 |
|
Changho Hwang
|
2c10142c89
|
IB fixes
|
2023-03-03 08:37:23 +00:00 |
|
Changho Hwang
|
9e5573f16b
|
Misc changes and comments
|
2023-03-03 08:32:47 +00:00 |
|
Changho Hwang
|
9674830db2
|
Change flags into uint64_t
|
2023-03-03 07:41:34 +00:00 |
|
Changho Hwang
|
e409247a21
|
Remove unneeded script
|
2023-03-03 07:34:00 +00:00 |
|
Changho Hwang
|
89b89fbae5
|
Erase duplicate TODO
|
2023-03-03 07:31:08 +00:00 |
|
Changho Hwang
|
a4df6e2d44
|
Merge branch 'main' into chhwang/p2p-simple
|
2023-03-01 05:37:46 +00:00 |
|
Saeed Maleki
|
ac1bf6dc52
|
cudagraph now works with p2p proxy
|
2023-02-28 23:25:51 +00:00 |
|
Changho Hwang
|
3d051a985f
|
Add p2p proxy: doesn't work with cuda graph yet
|
2023-02-28 18:58:03 +00:00 |
|
Changho Hwang
|
6bbee64482
|
Add cuda graph warmup
|
2023-02-28 14:19:11 +00:00 |
|
madanm
|
e67024a9d7
|
initial interface proposal for zero-copy push communication
|
2023-02-27 14:16:13 -08:00 |
|
Changho Hwang
|
a78b78aa43
|
Erase unnecessary memsets
|
2023-02-23 09:42:55 +00:00 |
|
Changho Hwang
|
29a430e7a8
|
NUMA binding
|
2023-02-23 08:18:12 +00:00 |
|
Saeed Maleki
|
1a528a3aa3
|
merged with main
|
2023-02-22 23:16:26 +00:00 |
|
Saeed Maleki
|
e1243191da
|
added cuda graphs few clean ups
|
2023-02-22 23:07:10 +00:00 |
|
Saeed Maleki
|
bca3362c12
|
a few clean ups
|
2023-02-22 22:43:18 +00:00 |
|
Changho Hwang
|
48b81edf6d
|
Move some files
|
2023-02-22 11:07:22 +00:00 |
|
Changho Hwang
|
89ca0451a8
|
Support incremental flag & add perf test
|
2023-02-22 10:55:35 +00:00 |
|
Changho Hwang
|
e1a7ea0f1a
|
One thread per connection (QP)
|
2023-02-22 10:18:54 +00:00 |
|
Changho Hwang
|
4cfb9b6727
|
GDRCopy support
|
2023-02-22 09:19:40 +00:00 |
|
Changho Hwang
|
7459a08699
|
Rename test code
|
2023-02-22 06:56:25 +00:00 |
|
Changho Hwang
|
368f8f4d24
|
Merge branch 'saemal/cleanup' into chhwang/p2p-simple
|
2023-02-22 06:54:51 +00:00 |
|
Changho Hwang
|
91e04a527b
|
Bidirectional connection
|
2023-02-22 06:06:14 +00:00 |
|
Saeed Maleki
|
ca89c17aaa
|
more clean up
|
2023-02-20 00:23:24 +00:00 |
|
Saeed Maleki
|
09d3e2f72c
|
comments for bootstrap test
|
2023-02-19 19:11:16 +00:00 |
|
Changho Hwang
|
33e20aceb9
|
IB all-to-all works
|
2023-02-17 11:39:16 +00:00 |
|
Saeed Maleki
|
537537563e
|
fixes connection refused
|
2023-02-17 01:51:02 +00:00 |
|
Saeed Maleki
|
4f3418aa77
|
more clean up
|
2023-02-16 07:13:04 +00:00 |
|
Saeed Maleki
|
71fbf283d7
|
works
|
2023-02-16 07:08:38 +00:00 |
|
v-xiaoxshi
|
654dd5f172
|
works
|
2023-02-16 07:07:13 +00:00 |
|
v-xiaoxshi
|
a364a39d17
|
compiles now
|
2023-02-16 05:25:17 +00:00 |
|
v-xiaoxshi
|
ad3be20b15
|
compiles now
|
2023-02-16 04:51:51 +00:00 |
|
v-xiaoxshi
|
81baa73822
|
more progress
|
2023-02-16 04:28:36 +00:00 |
|
v-xiaoxshi
|
1c156cf42f
|
not complete yet
|
2023-02-16 00:49:14 +00:00 |
|
Changho Hwang
|
8e57fd9896
|
p2p all-to-all works
|
2023-02-13 11:25:20 +00:00 |
|
Saeed Maleki
|
f7a137af61
|
Merge pull request #1 from microsoft/saemal/bootstrap
bootstrap is complete and works across nodes
|
2023-02-07 14:50:43 -08:00 |
|
Saeed Maleki
|
dfe1c4500a
|
test without mpi
|
2023-02-07 22:48:37 +00:00 |
|
Saeed Maleki
|
b9a253f82a
|
Revert "Add transport"
This reverts commit 692e9acd8f.
|
2023-02-07 22:28:14 +00:00 |
|
Changho Hwang
|
692e9acd8f
|
Add transport
|
2023-02-07 13:20:48 +00:00 |
|
Changho Hwang
|
8f7ebe99e3
|
Build into a shared library
|
2023-02-07 07:36:37 +00:00 |
|
lambda7xx
|
fe7d8097d6
|
cleaned up the mess
|
2023-02-07 04:42:58 +00:00 |
|
Saeed Maleki
|
38c3bf56eb
|
works without bcast
|
2023-02-06 23:04:03 +00:00 |
|