Distributed-Model.md

@@ -29,13 +29,14 @@ Data transfer is done all at once through one single blocking MPI instruction.
 Dt = 1.0 s
 
 ![all-at-once-5](uploads/afd3253f7a71005bf376d39c6e3d68c6/all-at-once-5.png)
-![base-5.code_legend](uploads/56f3e0f7bc8eb219a295bd16106f9008/base-5.code_legend.png)
 
 - Broadcast takes about 95 ms
 - Reduce takes about 380 ms
 - - Forward + backward pass takes about 143 ms
 - Time per iteration is 650 ms
 
+![base-5.code_legend](uploads/56f3e0f7bc8eb219a295bd16106f9008/base-5.code_legend.png)
+
 ## Using 8 workers and 1 server
 
 **One worker is computing half a token sequence (32 tokens / worker)**
@@ -53,8 +54,10 @@ Data transfer is done all at once through one single blocking MPI instruction.
 Dt = 2.5 s
 
 ![all-nine](uploads/2d471a1e2cf8dc0bf30f957a4554d9e5/all-nine.png)
-![base-9-priority.code_legend](uploads/fd7dfb7130bb685aa20d6636fe20d339/base-9-priority.code_legend.png)
-- Broadcast takes about 500 ms
-- Reduce takes about 115 ms
+
+- Reduce takes about 500 ms
+- Broadcast takes about 115 ms
 - Forward + backward pass takes about 100 ms
 - Time per iteration is about 720 ms
+
+![base-9-priority.code_legend](uploads/fd7dfb7130bb685aa20d6636fe20d339/base-9-priority.code_legend.png)
\ No newline at end of file