-
Notifications
You must be signed in to change notification settings - Fork 14
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Initial FPGA Support #40
Conversation
queue = deque([old_edge_in_shape.src]) | ||
while len(queue) > 0: | ||
current_node = queue.popleft() | ||
|
||
edges = state.in_edges(current_node) | ||
state.remove_node(current_node) | ||
for e in edges: | ||
next_node = e.src | ||
if len(state.out_edges(next_node)) == 0: | ||
queue.append(next_node) | ||
|
||
# get the edges between the the access_node and the nsdfg_node | ||
old_edges = [ | ||
e for e in state.out_edges(access_node) if e.dst == nsdfg_node | ||
] | ||
|
||
for edge in old_edges: | ||
state.add_edge(old_edge_in.src, old_edge_in.src_conn, edge.dst, | ||
edge.dst_conn, old_edge_in.data) | ||
state.remove_edge(edge) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
looks a bit excessive here. There are only ever two edges and that's it.
@@ -0,0 +1,89 @@ | |||
""" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
what do you mean by the name "plot" in the filename
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
plot_
is the default prefix used by sphinx gallery. We can change it if we want, suggestions welcome.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ok, what do you think about demo_
?
@TizianoDeMatteis Seems like the main reason for the bad coverage is because reshape elimination is not tested |
This reverts commit 8acd5da.
This PR includes several ONNX Node expansions specifically tailored for FPGA, in particular IntelFPGA.